duplicated block id: 1
size: 78 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (111:197)
 - src/autotrain/trainers/image_regression/__main__.py (97:183)

duplicated block id: 2
size: 68 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (359:427)
 - src/autotrain/commands.py (435:504)

duplicated block id: 3
size: 66 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (139:212)
 - src/autotrain/trainers/text_classification/__main__.py (134:207)

duplicated block id: 4
size: 53 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (126:184)
 - src/autotrain/trainers/token_classification/__main__.py (132:190)

duplicated block id: 5
size: 53 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (139:197)
 - src/autotrain/trainers/token_classification/__main__.py (132:190)

duplicated block id: 6
size: 53 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (125:183)
 - src/autotrain/trainers/text_regression/__main__.py (126:184)

duplicated block id: 7
size: 53 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (134:192)
 - src/autotrain/trainers/token_classification/__main__.py (132:190)

duplicated block id: 8
size: 53 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (125:183)
 - src/autotrain/trainers/text_classification/__main__.py (134:192)

duplicated block id: 9
size: 53 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (125:183)
 - src/autotrain/trainers/token_classification/__main__.py (132:190)

duplicated block id: 10
size: 53 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (134:192)
 - src/autotrain/trainers/text_regression/__main__.py (126:184)

duplicated block id: 11
size: 53 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (139:197)
 - src/autotrain/trainers/text_regression/__main__.py (126:184)

duplicated block id: 12
size: 52 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (654:760)
 - src/autotrain/trainers/vlm/utils.py (127:183)

duplicated block id: 13
size: 49 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (10:122)
 - src/autotrain/trainers/text_classification/utils.py (8:115)

duplicated block id: 14
size: 48 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:200)
 - src/autotrain/trainers/image_regression/__main__.py (125:177)

duplicated block id: 15
size: 48 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:200)
 - src/autotrain/trainers/text_regression/__main__.py (126:178)

duplicated block id: 16
size: 48 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:200)
 - src/autotrain/trainers/image_classification/__main__.py (139:191)

duplicated block id: 17
size: 48 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:200)
 - src/autotrain/trainers/text_classification/__main__.py (134:186)

duplicated block id: 18
size: 48 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:200)
 - src/autotrain/trainers/token_classification/__main__.py (132:184)

duplicated block id: 19
size: 45 cleaned lines of code
in 2 files:
 - notebooks/text_classification.ipynb (74:118)
 - notebooks/text_regression.ipynb (74:118)

duplicated block id: 20
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (45:90)
 - src/autotrain/trainers/token_classification/__main__.py (46:91)

duplicated block id: 21
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (50:95)
 - src/autotrain/trainers/text_regression/__main__.py (45:90)

duplicated block id: 22
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (42:87)
 - src/autotrain/trainers/text_classification/__main__.py (45:90)

duplicated block id: 23
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (47:92)
 - src/autotrain/trainers/text_regression/__main__.py (45:90)

duplicated block id: 24
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (47:92)
 - src/autotrain/trainers/sent_transformers/__main__.py (42:87)

duplicated block id: 25
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (45:90)
 - src/autotrain/trainers/text_regression/__main__.py (45:90)

duplicated block id: 26
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (50:95)
 - src/autotrain/trainers/text_classification/__main__.py (45:90)

duplicated block id: 27
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (45:90)
 - src/autotrain/trainers/token_classification/__main__.py (46:91)

duplicated block id: 28
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (50:95)
 - src/autotrain/trainers/token_classification/__main__.py (46:91)

duplicated block id: 29
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (47:92)
 - src/autotrain/trainers/text_classification/__main__.py (45:90)

duplicated block id: 30
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (42:87)
 - src/autotrain/trainers/text_regression/__main__.py (45:90)

duplicated block id: 31
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (42:87)
 - src/autotrain/trainers/seq2seq/__main__.py (50:95)

duplicated block id: 32
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (47:92)
 - src/autotrain/trainers/token_classification/__main__.py (46:91)

duplicated block id: 33
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (47:92)
 - src/autotrain/trainers/seq2seq/__main__.py (50:95)

duplicated block id: 34
size: 44 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (42:87)
 - src/autotrain/trainers/token_classification/__main__.py (46:91)

duplicated block id: 35
size: 43 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (121:168)
 - src/autotrain/trainers/object_detection/__main__.py (124:171)

duplicated block id: 36
size: 43 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (135:182)
 - src/autotrain/trainers/object_detection/__main__.py (124:171)

duplicated block id: 37
size: 42 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (44:87)
 - src/autotrain/trainers/object_detection/__main__.py (45:88)

duplicated block id: 38
size: 42 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (44:87)
 - src/autotrain/trainers/object_detection/__main__.py (45:88)

duplicated block id: 39
size: 42 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (44:87)
 - src/autotrain/trainers/image_regression/__main__.py (44:87)

duplicated block id: 40
size: 41 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (110:155)
 - src/autotrain/dataset.py (420:465)

duplicated block id: 41
size: 41 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (80:120)
 - notebooks/text_classification.ipynb (78:118)

duplicated block id: 42
size: 41 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (320:365)
 - src/autotrain/dataset.py (420:465)

duplicated block id: 43
size: 41 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (209:254)
 - src/autotrain/dataset.py (420:465)

duplicated block id: 44
size: 41 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (209:254)
 - src/autotrain/dataset.py (320:365)

duplicated block id: 45
size: 41 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (110:155)
 - src/autotrain/dataset.py (320:365)

duplicated block id: 46
size: 41 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (110:155)
 - src/autotrain/dataset.py (209:254)

duplicated block id: 47
size: 41 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (80:120)
 - notebooks/text_regression.ipynb (78:118)

duplicated block id: 48
size: 41 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (438:495)
 - src/autotrain/preprocessor/vlm.py (71:128)

duplicated block id: 49
size: 40 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (128:171)
 - src/autotrain/trainers/text_classification/__main__.py (134:177)

duplicated block id: 50
size: 40 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (128:171)
 - src/autotrain/trainers/token_classification/__main__.py (132:175)

duplicated block id: 51
size: 40 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:191)
 - src/autotrain/trainers/object_detection/__main__.py (128:171)

duplicated block id: 52
size: 40 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (128:171)
 - src/autotrain/trainers/text_regression/__main__.py (126:169)

duplicated block id: 53
size: 35 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (140:177)
 - src/autotrain/trainers/sent_transformers/__main__.py (123:160)

duplicated block id: 54
size: 35 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (123:160)
 - src/autotrain/trainers/text_classification/__main__.py (149:186)

duplicated block id: 55
size: 35 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (123:160)
 - src/autotrain/trainers/text_regression/__main__.py (141:178)

duplicated block id: 56
size: 35 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (163:200)
 - src/autotrain/trainers/sent_transformers/__main__.py (123:160)

duplicated block id: 57
size: 35 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (123:160)
 - src/autotrain/trainers/token_classification/__main__.py (147:184)

duplicated block id: 58
size: 35 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (154:191)
 - src/autotrain/trainers/sent_transformers/__main__.py (123:160)

duplicated block id: 59
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (72:109)
 - src/autotrain/cli/run_vlm.py (70:107)

duplicated block id: 60
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (128:163)
 - src/autotrain/trainers/seq2seq/__main__.py (103:138)

duplicated block id: 61
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (125:160)
 - src/autotrain/trainers/seq2seq/__main__.py (103:138)

duplicated block id: 62
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (139:174)
 - src/autotrain/trainers/seq2seq/__main__.py (103:138)

duplicated block id: 63
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:183)
 - src/autotrain/trainers/seq2seq/__main__.py (103:138)

duplicated block id: 64
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (175:209)
 - src/autotrain/commands.py (295:329)

duplicated block id: 65
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (103:138)
 - src/autotrain/trainers/text_classification/__main__.py (134:169)

duplicated block id: 66
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (262:309)
 - src/autotrain/preprocessor/vlm.py (73:120)

duplicated block id: 67
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (103:138)
 - src/autotrain/trainers/text_regression/__main__.py (126:161)

duplicated block id: 68
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (103:138)
 - src/autotrain/trainers/token_classification/__main__.py (132:167)

duplicated block id: 69
size: 34 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (262:309)
 - src/autotrain/preprocessor/vision.py (440:487)

duplicated block id: 70
size: 33 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (248:281)
 - src/autotrain/commands.py (296:329)

duplicated block id: 71
size: 33 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (311:348)
 - src/autotrain/preprocessor/vision.py (374:411)

duplicated block id: 72
size: 33 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (220:261)
 - src/autotrain/trainers/text_regression/__main__.py (186:227)

duplicated block id: 73
size: 33 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (176:209)
 - src/autotrain/commands.py (248:281)

duplicated block id: 74
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:107)
 - src/autotrain/cli/run_object_detection.py (72:107)

duplicated block id: 75
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (94:126)
 - src/autotrain/preprocessor/tabular.py (237:269)

duplicated block id: 76
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (94:126)
 - src/autotrain/preprocessor/text.py (411:443)

duplicated block id: 77
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (72:107)
 - src/autotrain/cli/run_sent_tranformers.py (72:107)

duplicated block id: 78
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (72:107)
 - src/autotrain/cli/run_sent_tranformers.py (72:107)

duplicated block id: 79
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (72:107)
 - src/autotrain/cli/run_vlm.py (70:105)

duplicated block id: 80
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (72:107)
 - src/autotrain/cli/run_vlm.py (70:105)

duplicated block id: 81
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:107)
 - src/autotrain/cli/run_sent_tranformers.py (72:107)

duplicated block id: 82
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (72:107)
 - src/autotrain/cli/run_object_detection.py (72:107)

duplicated block id: 83
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (237:269)
 - src/autotrain/preprocessor/text.py (411:443)

duplicated block id: 84
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:107)
 - src/autotrain/cli/run_image_regression.py (72:107)

duplicated block id: 85
size: 32 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:107)
 - src/autotrain/cli/run_vlm.py (70:105)

duplicated block id: 86
size: 31 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (505:544)
 - src/autotrain/preprocessor/vlm.py (151:190)

duplicated block id: 87
size: 31 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (413:446)
 - src/autotrain/preprocessor/text.py (524:559)

duplicated block id: 88
size: 31 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vlm.py (122:158)
 - src/autotrain/preprocessor/vlm.py (184:220)

duplicated block id: 89
size: 31 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (185:224)
 - src/autotrain/trainers/object_detection/__main__.py (195:234)

duplicated block id: 90
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (96:126)
 - src/autotrain/preprocessor/text.py (796:828)

duplicated block id: 91
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (96:126)
 - src/autotrain/preprocessor/text.py (524:556)

duplicated block id: 92
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (191:224)
 - src/autotrain/preprocessor/text.py (524:556)

duplicated block id: 93
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (96:126)
 - src/autotrain/preprocessor/text.py (191:224)

duplicated block id: 94
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (191:224)
 - src/autotrain/preprocessor/text.py (796:828)

duplicated block id: 95
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (413:443)
 - src/autotrain/preprocessor/text.py (796:828)

duplicated block id: 96
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (191:224)
 - src/autotrain/preprocessor/text.py (413:443)

duplicated block id: 97
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (524:556)
 - src/autotrain/preprocessor/text.py (796:828)

duplicated block id: 98
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (239:269)
 - src/autotrain/preprocessor/text.py (524:556)

duplicated block id: 99
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (239:269)
 - src/autotrain/preprocessor/text.py (191:224)

duplicated block id: 100
size: 30 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (239:269)
 - src/autotrain/preprocessor/text.py (796:828)

duplicated block id: 101
size: 28 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (31:60)
 - src/autotrain/trainers/clm/utils.py (921:950)

duplicated block id: 102
size: 28 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (19:46)
 - src/autotrain/cli/run_token_classification.py (19:46)

duplicated block id: 103
size: 28 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (19:46)
 - src/autotrain/cli/run_text_regression.py (19:46)

duplicated block id: 104
size: 28 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (19:46)
 - src/autotrain/cli/run_token_classification.py (19:46)

duplicated block id: 105
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_llm.py (19:45)

duplicated block id: 106
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (19:45)
 - src/autotrain/cli/run_text_regression.py (19:45)

duplicated block id: 107
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_object_detection.py (19:45)

duplicated block id: 108
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (19:45)
 - src/autotrain/cli/run_seq2seq.py (19:45)

duplicated block id: 109
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (19:45)
 - src/autotrain/cli/run_token_classification.py (19:45)

duplicated block id: 110
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (19:45)
 - src/autotrain/cli/run_text_regression.py (19:45)

duplicated block id: 111
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_text_classification.py (19:45)

duplicated block id: 112
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (19:45)
 - src/autotrain/cli/run_tabular.py (19:45)

duplicated block id: 113
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (338:372)
 - src/autotrain/preprocessor/vision.py (502:536)

duplicated block id: 114
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (19:45)
 - src/autotrain/cli/run_object_detection.py (19:45)

duplicated block id: 115
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_seq2seq.py (19:45)

duplicated block id: 116
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (19:45)
 - src/autotrain/cli/run_seq2seq.py (19:45)

duplicated block id: 117
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (19:45)
 - src/autotrain/cli/run_tabular.py (19:45)

duplicated block id: 118
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 119
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (19:45)
 - src/autotrain/cli/run_text_classification.py (19:45)

duplicated block id: 120
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 121
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (19:45)
 - src/autotrain/cli/run_token_classification.py (19:45)

duplicated block id: 122
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_token_classification.py (19:45)

duplicated block id: 123
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (19:45)
 - src/autotrain/cli/run_text_regression.py (19:45)

duplicated block id: 124
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (19:45)
 - src/autotrain/cli/run_text_classification.py (19:45)

duplicated block id: 125
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_tabular.py (19:45)

duplicated block id: 126
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_token_classification.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 127
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 128
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_text_regression.py (19:45)

duplicated block id: 129
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_llm.py (19:45)

duplicated block id: 130
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (19:45)
 - src/autotrain/cli/run_text_regression.py (19:45)

duplicated block id: 131
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (432:462)
 - src/autotrain/trainers/vlm/utils.py (299:329)

duplicated block id: 132
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 133
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_tabular.py (19:45)

duplicated block id: 134
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (19:45)
 - src/autotrain/cli/run_sent_tranformers.py (19:45)

duplicated block id: 135
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 136
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (19:45)
 - src/autotrain/cli/run_sent_tranformers.py (19:45)

duplicated block id: 137
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_token_classification.py (19:45)

duplicated block id: 138
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 139
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (19:45)
 - src/autotrain/cli/run_text_regression.py (19:45)

duplicated block id: 140
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_sent_tranformers.py (19:45)

duplicated block id: 141
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (143:171)
 - src/autotrain/trainers/sent_transformers/__main__.py (123:151)

duplicated block id: 142
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_text_regression.py (19:45)

duplicated block id: 143
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_seq2seq.py (19:45)

duplicated block id: 144
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (19:45)
 - src/autotrain/cli/run_text_classification.py (19:45)

duplicated block id: 145
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_sent_tranformers.py (19:45)

duplicated block id: 146
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 147
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (19:45)
 - src/autotrain/cli/run_text_classification.py (19:45)

duplicated block id: 148
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 149
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (19:45)
 - src/autotrain/cli/run_text_classification.py (19:45)

duplicated block id: 150
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (19:45)
 - src/autotrain/cli/run_text_classification.py (19:45)

duplicated block id: 151
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (19:45)
 - src/autotrain/cli/run_vlm.py (19:45)

duplicated block id: 152
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (19:45)
 - src/autotrain/cli/run_token_classification.py (19:45)

duplicated block id: 153
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (19:45)
 - src/autotrain/cli/run_seq2seq.py (19:45)

duplicated block id: 154
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (19:45)
 - src/autotrain/cli/run_token_classification.py (19:45)

duplicated block id: 155
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (19:45)
 - src/autotrain/cli/run_tabular.py (19:45)

duplicated block id: 156
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_object_detection.py (19:45)

duplicated block id: 157
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (19:45)
 - src/autotrain/cli/run_image_regression.py (19:45)

duplicated block id: 158
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (19:45)
 - src/autotrain/cli/run_token_classification.py (19:45)

duplicated block id: 159
size: 27 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (19:45)
 - src/autotrain/cli/run_tabular.py (19:45)

duplicated block id: 160
size: 26 cleaned lines of code
in 2 files:
 - notebooks/text_classification.ipynb (47:72)
 - notebooks/text_regression.ipynb (47:72)

duplicated block id: 161
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (56:86)
 - src/autotrain/preprocessor/text.py (479:509)

duplicated block id: 162
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:99)
 - src/autotrain/cli/run_text_regression.py (73:100)

duplicated block id: 163
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (966:991)
 - src/autotrain/trainers/vlm/utils.py (231:256)

duplicated block id: 164
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (533:559)
 - src/autotrain/preprocessor/text.py (658:684)

duplicated block id: 165
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (73:100)
 - src/autotrain/cli/run_token_classification.py (73:100)

duplicated block id: 166
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (73:100)
 - src/autotrain/cli/run_token_classification.py (73:100)

duplicated block id: 167
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (341:372)
 - src/autotrain/preprocessor/vlm.py (151:182)

duplicated block id: 168
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:99)
 - src/autotrain/cli/run_text_classification.py (73:100)

duplicated block id: 169
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (73:100)
 - src/autotrain/cli/run_text_regression.py (73:100)

duplicated block id: 170
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (420:446)
 - src/autotrain/preprocessor/text.py (658:684)

duplicated block id: 171
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (283:310)
 - src/autotrain/preprocessor/text.py (420:446)

duplicated block id: 172
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (283:310)
 - src/autotrain/preprocessor/text.py (658:684)

duplicated block id: 173
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:99)
 - src/autotrain/cli/run_token_classification.py (73:100)

duplicated block id: 174
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (283:310)
 - src/autotrain/preprocessor/text.py (533:559)

duplicated block id: 175
size: 25 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (125:163)
 - src/autotrain/trainers/image_regression/utils.py (91:129)

duplicated block id: 176
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (72:97)
 - src/autotrain/cli/run_text_classification.py (73:98)

duplicated block id: 177
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (72:97)
 - src/autotrain/cli/run_text_classification.py (73:98)

duplicated block id: 178
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (72:97)
 - src/autotrain/cli/run_text_classification.py (73:98)

duplicated block id: 179
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:97)
 - src/autotrain/cli/run_image_regression.py (72:97)

duplicated block id: 180
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (72:97)
 - src/autotrain/cli/run_token_classification.py (73:98)

duplicated block id: 181
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (72:97)
 - src/autotrain/cli/run_text_regression.py (73:98)

duplicated block id: 182
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (246:269)
 - src/autotrain/preprocessor/text.py (283:307)

duplicated block id: 183
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (103:126)
 - src/autotrain/preprocessor/text.py (283:307)

duplicated block id: 184
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (200:224)
 - src/autotrain/preprocessor/text.py (658:681)

duplicated block id: 185
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (200:224)
 - src/autotrain/preprocessor/text.py (283:307)

duplicated block id: 186
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (103:126)
 - src/autotrain/preprocessor/text.py (658:681)

duplicated block id: 187
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:97)
 - src/autotrain/cli/run_token_classification.py (73:98)

duplicated block id: 188
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:97)
 - src/autotrain/cli/run_object_detection.py (72:97)

duplicated block id: 189
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (103:126)
 - src/autotrain/preprocessor/text.py (120:144)

duplicated block id: 190
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (73:98)
 - src/autotrain/cli/run_vlm.py (70:95)

duplicated block id: 191
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:97)
 - src/autotrain/cli/run_image_classification.py (72:97)

duplicated block id: 192
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (72:97)
 - src/autotrain/cli/run_token_classification.py (73:98)

duplicated block id: 193
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (72:97)
 - src/autotrain/cli/run_token_classification.py (73:98)

duplicated block id: 194
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (246:269)
 - src/autotrain/preprocessor/text.py (658:681)

duplicated block id: 195
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (72:97)
 - src/autotrain/cli/run_text_regression.py (73:98)

duplicated block id: 196
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:97)
 - src/autotrain/cli/run_text_regression.py (73:98)

duplicated block id: 197
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (73:98)
 - src/autotrain/cli/run_vlm.py (70:95)

duplicated block id: 198
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:97)
 - src/autotrain/cli/run_vlm.py (70:95)

duplicated block id: 199
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (246:269)
 - src/autotrain/preprocessor/text.py (120:144)

duplicated block id: 200
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (120:144)
 - src/autotrain/preprocessor/text.py (533:556)

duplicated block id: 201
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (120:144)
 - src/autotrain/preprocessor/text.py (420:443)

duplicated block id: 202
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (120:144)
 - src/autotrain/preprocessor/text.py (658:681)

duplicated block id: 203
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (658:681)
 - src/autotrain/preprocessor/text.py (805:828)

duplicated block id: 204
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (120:144)
 - src/autotrain/preprocessor/text.py (200:224)

duplicated block id: 205
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:97)
 - src/autotrain/cli/run_text_classification.py (73:98)

duplicated block id: 206
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (120:144)
 - src/autotrain/preprocessor/text.py (283:307)

duplicated block id: 207
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (283:307)
 - src/autotrain/preprocessor/text.py (805:828)

duplicated block id: 208
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (72:97)
 - src/autotrain/cli/run_text_regression.py (73:98)

duplicated block id: 209
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (43:66)
 - src/autotrain/trainers/object_detection/params.py (44:67)

duplicated block id: 210
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (120:144)
 - src/autotrain/preprocessor/text.py (805:828)

duplicated block id: 211
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (171:218)
 - src/autotrain/trainers/text_classification/utils.py (118:156)

duplicated block id: 212
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:97)
 - src/autotrain/cli/run_sent_tranformers.py (72:97)

duplicated block id: 213
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_token_classification.py (73:98)
 - src/autotrain/cli/run_vlm.py (70:95)

duplicated block id: 214
size: 24 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (48:73)
 - src/autotrain/app/models.py (212:237)

duplicated block id: 215
size: 23 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (8:41)
 - src/autotrain/trainers/image_regression/__main__.py (8:41)

duplicated block id: 216
size: 23 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (8:42)
 - src/autotrain/trainers/text_regression/__main__.py (8:42)

duplicated block id: 217
size: 22 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (61:86)
 - src/autotrain/preprocessor/text.py (68:93)

duplicated block id: 218
size: 22 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (321:348)
 - src/autotrain/trainers/seq2seq/utils.py (57:98)

duplicated block id: 219
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (12:44)
 - src/autotrain/trainers/token_classification/__main__.py (11:43)

duplicated block id: 220
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_text_regression.py (19:39)

duplicated block id: 221
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (123:143)
 - src/autotrain/trainers/seq2seq/__main__.py (118:138)

duplicated block id: 222
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_image_classification.py (19:39)

duplicated block id: 223
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (12:44)
 - src/autotrain/trainers/text_classification/__main__.py (10:42)

duplicated block id: 224
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/utils.py (137:174)
 - src/autotrain/trainers/object_detection/utils.py (232:270)

duplicated block id: 225
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_tabular.py (19:39)

duplicated block id: 226
size: 21 cleaned lines of code
in 2 files:
 - notebooks/text_classification.ipynb (21:41)
 - notebooks/text_regression.ipynb (21:41)

duplicated block id: 227
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (213:237)
 - src/autotrain/trainers/text_regression/__main__.py (203:227)

duplicated block id: 228
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (10:42)
 - src/autotrain/trainers/token_classification/__main__.py (11:43)

duplicated block id: 229
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (207:227)
 - src/autotrain/trainers/text_regression/__main__.py (70:90)

duplicated block id: 230
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_image_regression.py (19:39)

duplicated block id: 231
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (75:95)
 - src/autotrain/trainers/tabular/__main__.py (207:227)

duplicated block id: 232
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (12:44)
 - src/autotrain/trainers/text_regression/__main__.py (10:42)

duplicated block id: 233
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_object_detection.py (19:39)

duplicated block id: 234
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (67:87)
 - src/autotrain/trainers/tabular/__main__.py (207:227)

duplicated block id: 235
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (49:69)
 - src/autotrain/cli/run_vlm.py (47:67)

duplicated block id: 236
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_sent_tranformers.py (19:39)

duplicated block id: 237
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_llm.py (19:39)

duplicated block id: 238
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_token_classification.py (19:39)

duplicated block id: 239
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (10:42)
 - src/autotrain/trainers/token_classification/__main__.py (11:43)

duplicated block id: 240
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (207:227)
 - src/autotrain/trainers/text_classification/__main__.py (70:90)

duplicated block id: 241
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (72:92)
 - src/autotrain/trainers/tabular/__main__.py (207:227)

duplicated block id: 242
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_seq2seq.py (19:39)

duplicated block id: 243
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_text_classification.py (19:39)

duplicated block id: 244
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (489:512)
 - src/autotrain/preprocessor/vision.py (538:561)

duplicated block id: 245
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (237:261)
 - src/autotrain/trainers/text_classification/__main__.py (213:237)

duplicated block id: 246
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (65:87)
 - src/autotrain/preprocessor/tabular.py (203:225)

duplicated block id: 247
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (19:39)
 - src/autotrain/cli/run_vlm.py (19:39)

duplicated block id: 248
size: 21 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (207:227)
 - src/autotrain/trainers/token_classification/__main__.py (71:91)

duplicated block id: 249
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (226:249)
 - src/autotrain/trainers/seq2seq/__main__.py (254:277)

duplicated block id: 250
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (11:41)
 - src/autotrain/trainers/object_detection/__main__.py (12:42)

duplicated block id: 251
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (46:66)
 - src/autotrain/trainers/token_classification/__main__.py (52:72)

duplicated block id: 252
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (46:66)
 - src/autotrain/trainers/sent_transformers/__main__.py (48:68)

duplicated block id: 253
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (31:51)
 - src/autotrain/trainers/vlm/utils.py (192:212)

duplicated block id: 254
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (486:505)
 - src/autotrain/trainers/tabular/__main__.py (185:204)

duplicated block id: 255
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (516:535)
 - src/autotrain/trainers/object_detection/__main__.py (66:85)

duplicated block id: 256
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (486:505)
 - src/autotrain/trainers/token_classification/__main__.py (50:69)

duplicated block id: 257
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (11:41)
 - src/autotrain/trainers/token_classification/__main__.py (12:43)

duplicated block id: 258
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (238:261)
 - src/autotrain/trainers/token_classification/__main__.py (210:233)

duplicated block id: 259
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (486:505)
 - src/autotrain/trainers/text_classification/__main__.py (49:68)

duplicated block id: 260
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (46:66)
 - src/autotrain/trainers/sent_transformers/__main__.py (48:68)

duplicated block id: 261
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (47:67)
 - src/autotrain/trainers/seq2seq/__main__.py (56:76)

duplicated block id: 262
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (46:66)
 - src/autotrain/trainers/text_regression/__main__.py (51:71)

duplicated block id: 263
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (486:505)
 - src/autotrain/trainers/sent_transformers/__main__.py (46:65)

duplicated block id: 264
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (214:237)
 - src/autotrain/trainers/token_classification/__main__.py (210:233)

duplicated block id: 265
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (11:41)
 - src/autotrain/trainers/token_classification/__main__.py (12:43)

duplicated block id: 266
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (222:247)
 - src/autotrain/trainers/text_regression/__main__.py (200:225)

duplicated block id: 267
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (53:73)
 - src/autotrain/trainers/image_regression/__main__.py (46:66)

duplicated block id: 268
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (486:505)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (51:70)

duplicated block id: 269
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (46:66)
 - src/autotrain/trainers/seq2seq/__main__.py (56:76)

duplicated block id: 270
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (11:41)
 - src/autotrain/trainers/text_regression/__main__.py (11:42)

duplicated block id: 271
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (486:505)
 - src/autotrain/trainers/seq2seq/__main__.py (54:73)

duplicated block id: 272
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (11:41)
 - src/autotrain/trainers/text_regression/__main__.py (11:42)

duplicated block id: 273
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (11:41)
 - src/autotrain/trainers/object_detection/__main__.py (12:42)

duplicated block id: 274
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (203:224)
 - src/autotrain/preprocessor/text.py (72:93)

duplicated block id: 275
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (108:129)
 - src/autotrain/trainers/text_regression/__main__.py (100:121)

duplicated block id: 276
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (51:70)
 - src/autotrain/trainers/tabular/__main__.py (185:204)

duplicated block id: 277
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (486:505)
 - src/autotrain/trainers/text_regression/__main__.py (49:68)

duplicated block id: 278
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (47:67)
 - src/autotrain/trainers/token_classification/__main__.py (52:72)

duplicated block id: 279
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (185:204)
 - src/autotrain/trainers/text_regression/__main__.py (49:68)

duplicated block id: 280
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (46:65)
 - src/autotrain/trainers/tabular/__main__.py (185:204)

duplicated block id: 281
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (47:67)
 - src/autotrain/trainers/text_regression/__main__.py (51:71)

duplicated block id: 282
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (250:275)
 - src/autotrain/trainers/token_classification/__main__.py (206:231)

duplicated block id: 283
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (516:535)
 - src/autotrain/trainers/image_classification/__main__.py (65:84)

duplicated block id: 284
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (185:204)
 - src/autotrain/trainers/token_classification/__main__.py (50:69)

duplicated block id: 285
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (12:42)
 - src/autotrain/trainers/token_classification/__main__.py (12:43)

duplicated block id: 286
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (234:259)
 - src/autotrain/trainers/sent_transformers/__main__.py (222:247)

duplicated block id: 287
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (47:67)
 - src/autotrain/trainers/text_classification/__main__.py (51:71)

duplicated block id: 288
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (46:66)
 - src/autotrain/trainers/seq2seq/__main__.py (56:76)

duplicated block id: 289
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (11:41)
 - src/autotrain/trainers/text_classification/__main__.py (11:42)

duplicated block id: 290
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (46:66)
 - src/autotrain/trainers/text_classification/__main__.py (51:71)

duplicated block id: 291
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (12:42)
 - src/autotrain/trainers/text_classification/__main__.py (11:42)

duplicated block id: 292
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (54:73)
 - src/autotrain/trainers/tabular/__main__.py (185:204)

duplicated block id: 293
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (13:44)
 - src/autotrain/trainers/object_detection/__main__.py (12:42)

duplicated block id: 294
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (204:227)
 - src/autotrain/trainers/token_classification/__main__.py (210:233)

duplicated block id: 295
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (11:41)
 - src/autotrain/trainers/text_classification/__main__.py (11:42)

duplicated block id: 296
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (13:44)
 - src/autotrain/trainers/image_classification/__main__.py (11:41)

duplicated block id: 297
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (185:204)
 - src/autotrain/trainers/text_classification/__main__.py (49:68)

duplicated block id: 298
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (53:73)
 - src/autotrain/trainers/object_detection/__main__.py (47:67)

duplicated block id: 299
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (46:66)
 - src/autotrain/trainers/token_classification/__main__.py (52:72)

duplicated block id: 300
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (921:941)
 - src/autotrain/trainers/vlm/utils.py (192:212)

duplicated block id: 301
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (12:42)
 - src/autotrain/trainers/text_regression/__main__.py (11:42)

duplicated block id: 302
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (516:535)
 - src/autotrain/trainers/image_regression/__main__.py (65:84)

duplicated block id: 303
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (46:66)
 - src/autotrain/trainers/text_regression/__main__.py (51:71)

duplicated block id: 304
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (46:66)
 - src/autotrain/trainers/text_classification/__main__.py (51:71)

duplicated block id: 305
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (47:67)
 - src/autotrain/trainers/sent_transformers/__main__.py (48:68)

duplicated block id: 306
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (13:44)
 - src/autotrain/trainers/image_regression/__main__.py (11:41)

duplicated block id: 307
size: 20 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (53:73)
 - src/autotrain/trainers/image_classification/__main__.py (46:66)

duplicated block id: 308
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (218:240)
 - src/autotrain/trainers/object_detection/__main__.py (212:234)

duplicated block id: 309
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 310
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 311
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 312
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 313
size: 19 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (26:44)
 - notebooks/text_regression.ipynb (94:112)

duplicated block id: 314
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 315
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (225:247)
 - src/autotrain/trainers/text_classification/__main__.py (213:235)

duplicated block id: 316
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 317
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (218:240)
 - src/autotrain/trainers/image_regression/__main__.py (202:224)

duplicated block id: 318
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_vlm.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 319
size: 19 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (26:44)
 - notebooks/text_classification.ipynb (94:112)

duplicated block id: 320
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_token_classification.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 321
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (257:291)
 - src/autotrain/trainers/vlm/utils.py (93:114)

duplicated block id: 322
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 323
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 324
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 325
size: 19 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (26:44)
 - notebooks/llm_finetuning.ipynb (96:114)

duplicated block id: 326
size: 19 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (20:38)
 - src/autotrain/cli/utils.py (8:26)

duplicated block id: 327
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/utils.py (139:159)
 - src/autotrain/trainers/seq2seq/utils.py (77:98)

duplicated block id: 328
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (75:92)
 - src/autotrain/trainers/image_classification/__main__.py (67:84)

duplicated block id: 329
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (48:65)
 - src/autotrain/trainers/sent_transformers/params.py (52:69)

duplicated block id: 330
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (254:275)
 - src/autotrain/trainers/text_classification/__main__.py (214:235)

duplicated block id: 331
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (67:84)
 - src/autotrain/trainers/token_classification/__main__.py (74:91)

duplicated block id: 332
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/params.py (49:66)
 - src/autotrain/trainers/sent_transformers/params.py (52:69)

duplicated block id: 333
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (327:348)
 - src/autotrain/trainers/sent_transformers/utils.py (139:159)

duplicated block id: 334
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (488:505)
 - src/autotrain/trainers/object_detection/__main__.py (47:64)

duplicated block id: 335
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (67:84)
 - src/autotrain/trainers/sent_transformers/__main__.py (70:87)

duplicated block id: 336
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (518:535)
 - src/autotrain/trainers/seq2seq/__main__.py (78:95)

duplicated block id: 337
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (68:85)
 - src/autotrain/trainers/seq2seq/__main__.py (78:95)

duplicated block id: 338
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (67:84)
 - src/autotrain/trainers/sent_transformers/__main__.py (70:87)

duplicated block id: 339
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (68:85)
 - src/autotrain/trainers/tabular/__main__.py (210:227)

duplicated block id: 340
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (67:84)
 - src/autotrain/trainers/tabular/__main__.py (210:227)

duplicated block id: 341
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (75:92)
 - src/autotrain/trainers/image_regression/__main__.py (67:84)

duplicated block id: 342
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (518:535)
 - src/autotrain/trainers/token_classification/__main__.py (74:91)

duplicated block id: 343
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (254:275)
 - src/autotrain/trainers/text_regression/__main__.py (204:225)

duplicated block id: 344
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (518:535)
 - src/autotrain/trainers/tabular/__main__.py (210:227)

duplicated block id: 345
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (518:535)
 - src/autotrain/trainers/text_regression/__main__.py (73:90)

duplicated block id: 346
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (67:84)
 - src/autotrain/trainers/text_classification/__main__.py (73:90)

duplicated block id: 347
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (197:218)
 - src/autotrain/trainers/token_classification/utils.py (78:98)

duplicated block id: 348
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (68:85)
 - src/autotrain/trainers/token_classification/__main__.py (74:91)

duplicated block id: 349
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (67:84)
 - src/autotrain/trainers/text_classification/__main__.py (73:90)

duplicated block id: 350
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (488:505)
 - src/autotrain/trainers/image_classification/__main__.py (46:63)

duplicated block id: 351
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (226:247)
 - src/autotrain/trainers/token_classification/__main__.py (210:231)

duplicated block id: 352
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (67:84)
 - src/autotrain/trainers/seq2seq/__main__.py (78:95)

duplicated block id: 353
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (68:85)
 - src/autotrain/trainers/sent_transformers/__main__.py (70:87)

duplicated block id: 354
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (68:85)
 - src/autotrain/trainers/text_regression/__main__.py (73:90)

duplicated block id: 355
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (68:85)
 - src/autotrain/trainers/text_classification/__main__.py (73:90)

duplicated block id: 356
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (67:84)
 - src/autotrain/trainers/text_regression/__main__.py (73:90)

duplicated block id: 357
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (518:535)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (75:92)

duplicated block id: 358
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (518:535)
 - src/autotrain/trainers/text_classification/__main__.py (73:90)

duplicated block id: 359
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (46:63)
 - src/autotrain/trainers/tabular/__main__.py (187:204)

duplicated block id: 360
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (488:505)
 - src/autotrain/trainers/image_regression/__main__.py (46:63)

duplicated block id: 361
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (238:259)
 - src/autotrain/trainers/seq2seq/__main__.py (254:275)

duplicated block id: 362
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (75:92)
 - src/autotrain/trainers/object_detection/__main__.py (68:85)

duplicated block id: 363
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (46:63)
 - src/autotrain/trainers/tabular/__main__.py (187:204)

duplicated block id: 364
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (67:84)
 - src/autotrain/trainers/text_regression/__main__.py (73:90)

duplicated block id: 365
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (67:84)
 - src/autotrain/trainers/tabular/__main__.py (210:227)

duplicated block id: 366
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (518:535)
 - src/autotrain/trainers/sent_transformers/__main__.py (70:87)

duplicated block id: 367
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (67:84)
 - src/autotrain/trainers/token_classification/__main__.py (74:91)

duplicated block id: 368
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (496:515)
 - src/autotrain/preprocessor/text.py (603:622)

duplicated block id: 369
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (67:84)
 - src/autotrain/trainers/seq2seq/__main__.py (78:95)

duplicated block id: 370
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (47:64)
 - src/autotrain/trainers/tabular/__main__.py (187:204)

duplicated block id: 371
size: 18 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/utils.py (135:156)
 - src/autotrain/trainers/token_classification/utils.py (78:98)

duplicated block id: 372
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/utils.py (140:159)
 - src/autotrain/trainers/text_classification/utils.py (136:156)

duplicated block id: 373
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (198:218)
 - src/autotrain/trainers/seq2seq/utils.py (78:98)

duplicated block id: 374
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/object_detection/__main__.py (147:163)

duplicated block id: 375
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/utils.py (154:174)
 - src/autotrain/trainers/text_classification/utils.py (136:156)

duplicated block id: 376
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (79:96)
 - src/autotrain/cli/run_vlm.py (78:95)

duplicated block id: 377
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (158:174)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 378
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (144:160)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 379
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/utils.py (98:118)
 - src/autotrain/trainers/token_classification/utils.py (79:98)

duplicated block id: 380
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (153:169)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 381
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (79:96)
 - src/autotrain/cli/run_token_classification.py (81:98)

duplicated block id: 382
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/utils.py (78:98)
 - src/autotrain/trainers/text_regression/utils.py (98:118)

duplicated block id: 383
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/text_classification/__main__.py (153:169)

duplicated block id: 384
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (328:348)
 - src/autotrain/trainers/token_classification/utils.py (79:98)

duplicated block id: 385
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/utils.py (154:174)
 - src/autotrain/trainers/sent_transformers/utils.py (140:159)

duplicated block id: 386
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (79:96)
 - src/autotrain/cli/run_text_regression.py (81:98)

duplicated block id: 387
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/text_regression/__main__.py (145:161)

duplicated block id: 388
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (198:218)
 - src/autotrain/trainers/image_regression/utils.py (154:174)

duplicated block id: 389
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (328:348)
 - src/autotrain/trainers/image_classification/utils.py (198:218)

duplicated block id: 390
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (80:97)
 - src/autotrain/cli/run_tabular.py (79:96)

duplicated block id: 391
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (122:138)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 392
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/sent_transformers/__main__.py (127:143)

duplicated block id: 393
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/image_regression/__main__.py (144:160)

duplicated block id: 394
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (328:348)
 - src/autotrain/trainers/object_detection/utils.py (250:270)

duplicated block id: 395
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (151:167)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 396
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (19:47)
 - src/autotrain/trainers/text_regression/__main__.py (14:42)

duplicated block id: 397
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/seq2seq/__main__.py (122:138)

duplicated block id: 398
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (19:47)
 - src/autotrain/trainers/text_classification/__main__.py (14:42)

duplicated block id: 399
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/utils.py (78:98)
 - src/autotrain/trainers/token_classification/utils.py (79:98)

duplicated block id: 400
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (147:163)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 401
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/utils.py (140:159)
 - src/autotrain/trainers/text_regression/utils.py (98:118)

duplicated block id: 402
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/token_classification/__main__.py (151:167)

duplicated block id: 403
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (198:218)
 - src/autotrain/trainers/text_regression/utils.py (98:118)

duplicated block id: 404
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (198:218)
 - src/autotrain/trainers/object_detection/utils.py (250:270)

duplicated block id: 405
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (167:183)

duplicated block id: 406
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (80:97)
 - src/autotrain/cli/run_tabular.py (79:96)

duplicated block id: 407
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/utils.py (250:270)
 - src/autotrain/trainers/text_regression/utils.py (98:118)

duplicated block id: 408
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (80:97)
 - src/autotrain/cli/run_tabular.py (79:96)

duplicated block id: 409
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (14:41)
 - src/autotrain/trainers/seq2seq/__main__.py (19:47)

duplicated block id: 410
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/utils.py (250:270)
 - src/autotrain/trainers/token_classification/utils.py (79:98)

duplicated block id: 411
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (127:143)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 412
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (79:96)
 - src/autotrain/cli/run_text_classification.py (81:98)

duplicated block id: 413
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/utils.py (250:270)
 - src/autotrain/trainers/seq2seq/utils.py (78:98)

duplicated block id: 414
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/utils.py (154:174)
 - src/autotrain/trainers/seq2seq/utils.py (78:98)

duplicated block id: 415
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (328:348)
 - src/autotrain/trainers/text_classification/utils.py (136:156)

duplicated block id: 416
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_orpo.py (27:45)
 - src/autotrain/trainers/clm/train_clm_sft.py (27:45)

duplicated block id: 417
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (80:97)
 - src/autotrain/cli/run_tabular.py (79:96)

duplicated block id: 418
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/utils.py (250:270)
 - src/autotrain/trainers/text_classification/utils.py (136:156)

duplicated block id: 419
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/utils.py (136:156)
 - src/autotrain/trainers/text_regression/utils.py (98:118)

duplicated block id: 420
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (145:161)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 421
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/utils.py (140:159)
 - src/autotrain/trainers/token_classification/utils.py (79:98)

duplicated block id: 422
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (728:744)
 - src/autotrain/trainers/image_classification/__main__.py (158:174)

duplicated block id: 423
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (16:44)
 - src/autotrain/trainers/seq2seq/__main__.py (19:47)

duplicated block id: 424
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/utils.py (250:270)
 - src/autotrain/trainers/sent_transformers/utils.py (140:159)

duplicated block id: 425
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (80:97)
 - src/autotrain/cli/run_tabular.py (79:96)

duplicated block id: 426
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/utils.py (154:174)
 - src/autotrain/trainers/token_classification/utils.py (79:98)

duplicated block id: 427
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (167:183)
 - src/autotrain/trainers/vlm/utils.py (151:167)

duplicated block id: 428
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (198:218)
 - src/autotrain/trainers/sent_transformers/utils.py (140:159)

duplicated block id: 429
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (19:47)
 - src/autotrain/trainers/token_classification/__main__.py (15:43)

duplicated block id: 430
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/utils.py (154:174)
 - src/autotrain/trainers/text_regression/utils.py (98:118)

duplicated block id: 431
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (328:348)
 - src/autotrain/trainers/text_regression/utils.py (98:118)

duplicated block id: 432
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/utils.py (78:98)
 - src/autotrain/trainers/text_classification/utils.py (136:156)

duplicated block id: 433
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (328:348)
 - src/autotrain/trainers/image_regression/utils.py (154:174)

duplicated block id: 434
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (14:41)
 - src/autotrain/trainers/seq2seq/__main__.py (19:47)

duplicated block id: 435
size: 17 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (15:42)
 - src/autotrain/trainers/seq2seq/__main__.py (19:47)

duplicated block id: 436
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (21:44)
 - src/autotrain/trainers/sent_transformers/__main__.py (17:39)

duplicated block id: 437
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (17:39)
 - src/autotrain/trainers/text_regression/__main__.py (19:42)

duplicated block id: 438
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (164:180)
 - src/autotrain/project.py (404:420)

duplicated block id: 439
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (164:180)
 - src/autotrain/project.py (313:329)

duplicated block id: 440
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (89:105)
 - src/autotrain/trainers/clm/train_clm_sft.py (29:45)

duplicated block id: 441
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (164:180)
 - src/autotrain/project.py (199:215)

duplicated block id: 442
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (164:180)
 - src/autotrain/project.py (234:250)

duplicated block id: 443
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (61:79)
 - src/autotrain/preprocessor/text.py (491:509)

duplicated block id: 444
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (199:215)
 - src/autotrain/project.py (404:420)

duplicated block id: 445
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (199:215)
 - src/autotrain/project.py (313:329)

duplicated block id: 446
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (20:42)
 - src/autotrain/trainers/sent_transformers/__main__.py (17:39)

duplicated block id: 447
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (199:215)
 - src/autotrain/project.py (234:250)

duplicated block id: 448
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (76:91)
 - src/autotrain/commands.py (398:413)

duplicated block id: 449
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (76:91)
 - src/autotrain/commands.py (474:489)

duplicated block id: 450
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (74:91)
 - src/autotrain/cli/run_token_classification.py (83:100)

duplicated block id: 451
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (234:250)
 - src/autotrain/project.py (313:329)

duplicated block id: 452
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (19:41)
 - src/autotrain/trainers/sent_transformers/__main__.py (17:39)

duplicated block id: 453
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (234:250)
 - src/autotrain/project.py (404:420)

duplicated block id: 454
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (17:39)
 - src/autotrain/trainers/text_classification/__main__.py (19:42)

duplicated block id: 455
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (19:41)
 - src/autotrain/trainers/sent_transformers/__main__.py (17:39)

duplicated block id: 456
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (74:91)
 - src/autotrain/cli/run_text_classification.py (83:100)

duplicated block id: 457
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (82:99)
 - src/autotrain/cli/run_seq2seq.py (74:91)

duplicated block id: 458
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (89:105)
 - src/autotrain/trainers/clm/train_clm_orpo.py (29:45)

duplicated block id: 459
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (17:39)
 - src/autotrain/trainers/token_classification/__main__.py (20:43)

duplicated block id: 460
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/params.py (44:59)
 - src/autotrain/trainers/text_regression/params.py (44:59)

duplicated block id: 461
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (17:39)
 - src/autotrain/trainers/seq2seq/__main__.py (24:47)

duplicated block id: 462
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (74:91)
 - src/autotrain/cli/run_text_regression.py (83:100)

duplicated block id: 463
size: 16 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (313:329)
 - src/autotrain/project.py (404:420)

duplicated block id: 464
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (74:89)
 - src/autotrain/cli/run_vlm.py (80:95)

duplicated block id: 465
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (53:68)
 - src/autotrain/project.py (404:419)

duplicated block id: 466
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (180:195)
 - src/autotrain/preprocessor/text.py (243:258)

duplicated block id: 467
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (53:68)
 - src/autotrain/project.py (130:145)

duplicated block id: 468
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/params.py (44:58)
 - src/autotrain/trainers/token_classification/params.py (44:58)

duplicated block id: 469
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/params.py (44:58)
 - src/autotrain/trainers/token_classification/params.py (44:58)

duplicated block id: 470
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (74:89)
 - src/autotrain/cli/run_tabular.py (81:96)

duplicated block id: 471
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (82:97)
 - src/autotrain/cli/run_seq2seq.py (74:89)

duplicated block id: 472
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (130:145)
 - src/autotrain/project.py (404:419)

duplicated block id: 473
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (130:145)
 - src/autotrain/project.py (234:249)

duplicated block id: 474
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (130:145)
 - src/autotrain/project.py (199:214)

duplicated block id: 475
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (130:145)
 - src/autotrain/project.py (164:179)

duplicated block id: 476
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (82:97)
 - src/autotrain/cli/run_seq2seq.py (74:89)

duplicated block id: 477
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (130:145)
 - src/autotrain/project.py (313:328)

duplicated block id: 478
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (53:68)
 - src/autotrain/project.py (313:328)

duplicated block id: 479
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (82:97)
 - src/autotrain/cli/run_seq2seq.py (74:89)

duplicated block id: 480
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (53:68)
 - src/autotrain/project.py (234:249)

duplicated block id: 481
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (53:68)
 - src/autotrain/project.py (164:179)

duplicated block id: 482
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (88:106)
 - src/autotrain/preprocessor/text.py (510:528)

duplicated block id: 483
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (53:68)
 - src/autotrain/project.py (199:214)

duplicated block id: 484
size: 15 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (82:97)
 - src/autotrain/cli/run_seq2seq.py (74:89)

duplicated block id: 485
size: 14 cleaned lines of code
in 2 files:
 - colabs/AutoTrain_LLM.ipynb (129:142)
 - colabs/AutoTrain_ngrok.ipynb (33:46)

duplicated block id: 486
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (177:190)
 - src/autotrain/commands.py (361:374)

duplicated block id: 487
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (177:190)
 - src/autotrain/commands.py (437:450)

duplicated block id: 488
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (184:200)
 - src/autotrain/trainers/seq2seq/__main__.py (141:157)

duplicated block id: 489
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (297:310)
 - src/autotrain/commands.py (361:374)

duplicated block id: 490
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (161:177)
 - src/autotrain/trainers/seq2seq/__main__.py (141:157)

duplicated block id: 491
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (297:310)
 - src/autotrain/commands.py (437:450)

duplicated block id: 492
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/backends/base.py (22:35)
 - src/autotrain/client.py (13:26)

duplicated block id: 493
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (141:157)
 - src/autotrain/trainers/text_regression/__main__.py (162:178)

duplicated block id: 494
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (175:191)
 - src/autotrain/trainers/seq2seq/__main__.py (141:157)

duplicated block id: 495
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (249:262)
 - src/autotrain/commands.py (437:450)

duplicated block id: 496
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (249:262)
 - src/autotrain/commands.py (361:374)

duplicated block id: 497
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (502:516)
 - src/autotrain/preprocessor/text.py (764:778)

duplicated block id: 498
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/app/templates/duplicate.html (1:18)
 - src/autotrain/app/templates/error.html (1:18)

duplicated block id: 499
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (203:217)
 - src/autotrain/preprocessor/text.py (495:509)

duplicated block id: 500
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (141:157)
 - src/autotrain/trainers/token_classification/__main__.py (168:184)

duplicated block id: 501
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (144:160)
 - src/autotrain/trainers/seq2seq/__main__.py (141:157)

duplicated block id: 502
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/dataset.py (42:58)
 - src/autotrain/trainers/text_regression/dataset.py (43:59)

duplicated block id: 503
size: 14 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (141:157)
 - src/autotrain/trainers/text_classification/__main__.py (170:186)

duplicated block id: 504
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (41:53)
 - src/autotrain/trainers/vlm/utils.py (200:212)

duplicated block id: 505
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (204:217)
 - src/autotrain/preprocessor/text.py (603:616)

duplicated block id: 506
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (94:108)
 - src/autotrain/dataset.py (404:418)

duplicated block id: 507
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (125:138)
 - src/autotrain/trainers/vlm/utils.py (129:141)

duplicated block id: 508
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (193:207)
 - src/autotrain/dataset.py (404:418)

duplicated block id: 509
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (139:152)
 - src/autotrain/trainers/vlm/utils.py (129:141)

duplicated block id: 510
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (604:616)
 - src/autotrain/app/params.py (725:737)

duplicated block id: 511
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (604:616)
 - src/autotrain/app/params.py (618:630)

duplicated block id: 512
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (604:616)
 - src/autotrain/app/params.py (664:676)

duplicated block id: 513
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (604:616)
 - src/autotrain/app/params.py (650:662)

duplicated block id: 514
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (604:616)
 - src/autotrain/app/params.py (678:690)

duplicated block id: 515
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (604:616)
 - src/autotrain/app/params.py (692:704)

duplicated block id: 516
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (53:66)
 - src/autotrain/project.py (90:103)

duplicated block id: 517
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/templates/error.html (1:14)
 - src/autotrain/app/templates/login.html (1:14)

duplicated block id: 518
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (90:103)
 - src/autotrain/project.py (404:417)

duplicated block id: 519
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (672:684)
 - src/autotrain/trainers/text_regression/__main__.py (126:139)

duplicated block id: 520
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (199:214)
 - src/autotrain/trainers/sent_transformers/__main__.py (222:237)

duplicated block id: 521
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (357:369)
 - src/autotrain/app/params.py (390:402)

duplicated block id: 522
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (90:103)
 - src/autotrain/project.py (164:177)

duplicated block id: 523
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (73:86)
 - src/autotrain/preprocessor/text.py (603:616)

duplicated block id: 524
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (90:103)
 - src/autotrain/project.py (234:247)

duplicated block id: 525
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (90:103)
 - src/autotrain/project.py (199:212)

duplicated block id: 526
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (90:103)
 - src/autotrain/project.py (313:326)

duplicated block id: 527
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/static/scripts/listeners.js (135:150)
 - src/autotrain/app/static/scripts/listeners.js (152:167)

duplicated block id: 528
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (672:684)
 - src/autotrain/trainers/token_classification/__main__.py (132:145)

duplicated block id: 529
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:161)
 - src/autotrain/trainers/vlm/utils.py (129:141)

duplicated block id: 530
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (664:676)
 - src/autotrain/app/params.py (725:737)

duplicated block id: 531
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (209:224)
 - src/autotrain/trainers/text_regression/__main__.py (200:215)

duplicated block id: 532
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (121:135)
 - src/autotrain/preprocessor/vlm.py (106:120)

duplicated block id: 533
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (664:676)
 - src/autotrain/app/params.py (678:690)

duplicated block id: 534
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (664:676)
 - src/autotrain/app/params.py (692:704)

duplicated block id: 535
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (121:135)
 - src/autotrain/preprocessor/vision.py (473:487)

duplicated block id: 536
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (134:147)
 - src/autotrain/trainers/vlm/utils.py (129:141)

duplicated block id: 537
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (121:135)
 - src/autotrain/preprocessor/vision.py (295:309)

duplicated block id: 538
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (321:333)
 - src/autotrain/app/params.py (357:369)

duplicated block id: 539
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/utils.py (287:299)
 - src/autotrain/trainers/tabular/utils.py (307:319)

duplicated block id: 540
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (321:333)
 - src/autotrain/app/params.py (390:402)

duplicated block id: 541
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (678:690)
 - src/autotrain/app/params.py (725:737)

duplicated block id: 542
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (90:103)
 - src/autotrain/project.py (130:143)

duplicated block id: 543
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (678:690)
 - src/autotrain/app/params.py (692:704)

duplicated block id: 544
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (672:684)
 - src/autotrain/trainers/image_classification/__main__.py (139:152)

duplicated block id: 545
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (128:141)
 - src/autotrain/trainers/vlm/utils.py (129:141)

duplicated block id: 546
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/templates/duplicate.html (1:14)
 - src/autotrain/app/templates/login.html (1:14)

duplicated block id: 547
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (672:684)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (148:161)

duplicated block id: 548
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (672:684)
 - src/autotrain/trainers/text_classification/__main__.py (134:147)

duplicated block id: 549
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (692:704)
 - src/autotrain/app/params.py (725:737)

duplicated block id: 550
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (126:139)
 - src/autotrain/trainers/vlm/utils.py (129:141)

duplicated block id: 551
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (39:51)
 - src/autotrain/trainers/clm/train_clm_reward.py (41:53)

duplicated block id: 552
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (234:249)
 - src/autotrain/trainers/image_regression/__main__.py (199:214)

duplicated block id: 553
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (103:116)
 - src/autotrain/trainers/vlm/utils.py (129:141)

duplicated block id: 554
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (132:145)
 - src/autotrain/trainers/vlm/utils.py (129:141)

duplicated block id: 555
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (609:622)
 - src/autotrain/preprocessor/text.py (764:777)

duplicated block id: 556
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (672:684)
 - src/autotrain/trainers/image_regression/__main__.py (125:138)

duplicated block id: 557
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (234:249)
 - src/autotrain/trainers/object_detection/__main__.py (209:224)

duplicated block id: 558
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (199:214)
 - src/autotrain/trainers/text_regression/__main__.py (200:215)

duplicated block id: 559
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (401:415)
 - src/autotrain/preprocessor/vision.py (551:565)

duplicated block id: 560
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (650:662)
 - src/autotrain/app/params.py (725:737)

duplicated block id: 561
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (576:588)
 - src/autotrain/dataset.py (594:606)

duplicated block id: 562
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (650:662)
 - src/autotrain/app/params.py (678:690)

duplicated block id: 563
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (650:662)
 - src/autotrain/app/params.py (664:676)

duplicated block id: 564
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (650:662)
 - src/autotrain/app/params.py (692:704)

duplicated block id: 565
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (618:630)
 - src/autotrain/app/params.py (725:737)

duplicated block id: 566
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (215:230)
 - src/autotrain/trainers/text_classification/__main__.py (210:225)

duplicated block id: 567
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (66:79)
 - src/autotrain/preprocessor/text.py (603:616)

duplicated block id: 568
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (672:684)
 - src/autotrain/trainers/object_detection/__main__.py (128:141)

duplicated block id: 569
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:602)
 - src/autotrain/app/params.py (604:616)

duplicated block id: 570
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (209:224)
 - src/autotrain/trainers/sent_transformers/__main__.py (222:237)

duplicated block id: 571
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:602)
 - src/autotrain/app/params.py (678:690)

duplicated block id: 572
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:602)
 - src/autotrain/app/params.py (650:662)

duplicated block id: 573
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:602)
 - src/autotrain/app/params.py (664:676)

duplicated block id: 574
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:602)
 - src/autotrain/app/params.py (618:630)

duplicated block id: 575
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:602)
 - src/autotrain/app/params.py (692:704)

duplicated block id: 576
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (94:108)
 - src/autotrain/dataset.py (193:207)

duplicated block id: 577
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (618:630)
 - src/autotrain/app/params.py (650:662)

duplicated block id: 578
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (618:630)
 - src/autotrain/app/params.py (664:676)

duplicated block id: 579
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (41:53)
 - src/autotrain/trainers/clm/utils.py (929:941)

duplicated block id: 580
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (618:630)
 - src/autotrain/app/params.py (692:704)

duplicated block id: 581
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (672:684)
 - src/autotrain/trainers/seq2seq/__main__.py (103:116)

duplicated block id: 582
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:602)
 - src/autotrain/app/params.py (725:737)

duplicated block id: 583
size: 13 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (618:630)
 - src/autotrain/app/params.py (678:690)

duplicated block id: 584
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (243:254)
 - src/autotrain/preprocessor/text.py (502:513)

duplicated block id: 585
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/params.py (62:73)
 - src/autotrain/trainers/text_classification/params.py (61:72)

duplicated block id: 586
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (179:193)
 - src/autotrain/preprocessor/vision.py (404:418)

duplicated block id: 587
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (243:254)
 - src/autotrain/preprocessor/text.py (609:620)

duplicated block id: 588
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (727:738)
 - src/autotrain/dataset.py (799:810)

duplicated block id: 589
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (727:738)
 - src/autotrain/dataset.py (781:792)

duplicated block id: 590
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/params.py (61:72)
 - src/autotrain/trainers/token_classification/params.py (61:72)

duplicated block id: 591
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (727:738)
 - src/autotrain/dataset.py (763:774)

duplicated block id: 592
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (727:738)
 - src/autotrain/dataset.py (745:756)

duplicated block id: 593
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (218:230)
 - src/autotrain/trainers/sent_transformers/__main__.py (225:237)

duplicated block id: 594
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/params.py (50:61)
 - src/autotrain/trainers/text_classification/params.py (47:58)

duplicated block id: 595
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (180:191)
 - src/autotrain/preprocessor/text.py (609:620)

duplicated block id: 596
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (61:73)
 - src/autotrain/app/models.py (184:195)

duplicated block id: 597
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (180:191)
 - src/autotrain/preprocessor/text.py (764:775)

duplicated block id: 598
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/params.py (61:72)
 - src/autotrain/trainers/token_classification/params.py (61:72)

duplicated block id: 599
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/params.py (50:61)
 - src/autotrain/trainers/text_regression/params.py (47:58)

duplicated block id: 600
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (763:774)
 - src/autotrain/dataset.py (799:810)

duplicated block id: 601
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (121:133)
 - src/autotrain/app/models.py (184:195)

duplicated block id: 602
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (121:133)
 - src/autotrain/app/models.py (225:237)

duplicated block id: 603
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (763:774)
 - src/autotrain/dataset.py (781:792)

duplicated block id: 604
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (63:75)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (45:57)

duplicated block id: 605
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (180:191)
 - src/autotrain/preprocessor/text.py (502:513)

duplicated block id: 606
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/params.py (50:61)
 - src/autotrain/trainers/token_classification/params.py (47:58)

duplicated block id: 607
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (220:234)
 - src/autotrain/trainers/token_classification/__main__.py (192:206)

duplicated block id: 608
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (745:756)
 - src/autotrain/dataset.py (763:774)

duplicated block id: 609
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (745:756)
 - src/autotrain/dataset.py (799:810)

duplicated block id: 610
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (745:756)
 - src/autotrain/dataset.py (781:792)

duplicated block id: 611
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (272:285)
 - src/autotrain/commands.py (491:504)

duplicated block id: 612
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (243:254)
 - src/autotrain/preprocessor/text.py (764:775)

duplicated block id: 613
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (272:285)
 - src/autotrain/commands.py (415:427)

duplicated block id: 614
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (218:230)
 - src/autotrain/trainers/text_regression/__main__.py (203:215)

duplicated block id: 615
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (134:145)
 - src/autotrain/preprocessor/text.py (502:513)

duplicated block id: 616
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (134:145)
 - src/autotrain/preprocessor/text.py (243:254)

duplicated block id: 617
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (134:145)
 - src/autotrain/preprocessor/text.py (764:775)

duplicated block id: 618
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/params.py (62:73)
 - src/autotrain/trainers/text_regression/params.py (61:72)

duplicated block id: 619
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (134:145)
 - src/autotrain/preprocessor/text.py (609:620)

duplicated block id: 620
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (64:76)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (45:57)

duplicated block id: 621
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (212:224)
 - src/autotrain/trainers/text_classification/__main__.py (213:225)

duplicated block id: 622
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (276:287)
 - src/autotrain/project.py (362:373)

duplicated block id: 623
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (202:214)
 - src/autotrain/trainers/text_classification/__main__.py (213:225)

duplicated block id: 624
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (91:102)
 - src/autotrain/app/models.py (121:133)

duplicated block id: 625
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (630:641)
 - src/autotrain/dataset.py (647:658)

duplicated block id: 626
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (63:75)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (45:57)

duplicated block id: 627
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (35:46)
 - src/autotrain/app/models.py (199:210)

duplicated block id: 628
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (184:195)
 - src/autotrain/app/models.py (225:237)

duplicated block id: 629
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (781:792)
 - src/autotrain/dataset.py (799:810)

duplicated block id: 630
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/params.py (62:73)
 - src/autotrain/trainers/token_classification/params.py (61:72)

duplicated block id: 631
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (61:73)
 - src/autotrain/app/models.py (91:102)

duplicated block id: 632
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/params.py (61:72)
 - src/autotrain/trainers/text_regression/params.py (61:72)

duplicated block id: 633
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (61:73)
 - src/autotrain/app/models.py (121:133)

duplicated block id: 634
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (91:102)
 - src/autotrain/app/models.py (184:195)

duplicated block id: 635
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (91:102)
 - src/autotrain/app/models.py (225:237)

duplicated block id: 636
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (134:145)
 - src/autotrain/preprocessor/text.py (180:191)

duplicated block id: 637
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (186:200)
 - src/autotrain/trainers/token_classification/__main__.py (192:206)

duplicated block id: 638
size: 12 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (237:249)
 - src/autotrain/trainers/image_classification/__main__.py (218:230)

duplicated block id: 639
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (89:100)
 - src/autotrain/trainers/text_regression/__main__.py (92:103)

duplicated block id: 640
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (136:147)
 - src/autotrain/commands.py (274:285)

duplicated block id: 641
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (217:228)
 - src/autotrain/trainers/vlm/utils.py (318:329)

duplicated block id: 642
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (226:237)
 - src/autotrain/app/models.py (269:279)

duplicated block id: 643
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (179:190)
 - src/autotrain/preprocessor/vision.py (554:565)

duplicated block id: 644
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (451:462)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (245:256)

duplicated block id: 645
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (451:462)
 - src/autotrain/trainers/text_classification/__main__.py (221:232)

duplicated block id: 646
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (92:102)
 - src/autotrain/app/models.py (269:279)

duplicated block id: 647
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (554:565)
 - src/autotrain/preprocessor/vlm.py (213:224)

duplicated block id: 648
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (604:614)
 - src/autotrain/app/params.py (632:642)

duplicated block id: 649
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (122:133)
 - src/autotrain/app/models.py (269:279)

duplicated block id: 650
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (62:73)
 - src/autotrain/app/models.py (269:279)

duplicated block id: 651
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (45:55)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (28:38)

duplicated block id: 652
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (404:415)
 - src/autotrain/preprocessor/vlm.py (213:224)

duplicated block id: 653
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (451:462)
 - src/autotrain/trainers/text_regression/__main__.py (211:222)

duplicated block id: 654
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (221:232)
 - src/autotrain/trainers/vlm/utils.py (318:329)

duplicated block id: 655
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (196:208)
 - src/autotrain/trainers/token_classification/__main__.py (192:204)

duplicated block id: 656
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (44:54)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (28:38)

duplicated block id: 657
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (245:256)
 - src/autotrain/trainers/vlm/utils.py (318:329)

duplicated block id: 658
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (632:642)
 - src/autotrain/app/params.py (678:688)

duplicated block id: 659
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (632:642)
 - src/autotrain/app/params.py (650:660)

duplicated block id: 660
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (220:232)
 - src/autotrain/trainers/text_classification/__main__.py (196:208)

duplicated block id: 661
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (632:642)
 - src/autotrain/app/params.py (664:674)

duplicated block id: 662
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (632:642)
 - src/autotrain/app/params.py (692:702)

duplicated block id: 663
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (196:208)
 - src/autotrain/trainers/text_regression/__main__.py (186:198)

duplicated block id: 664
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/dataset.py (11:24)
 - src/autotrain/trainers/extractive_question_answering/utils.py (361:374)

duplicated block id: 665
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (213:224)
 - src/autotrain/trainers/seq2seq/__main__.py (254:265)

duplicated block id: 666
size: 11 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (27:37)
 - notebooks/text_regression.ipynb (27:37)

duplicated block id: 667
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (233:244)
 - src/autotrain/trainers/vlm/utils.py (318:329)

duplicated block id: 668
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (451:462)
 - src/autotrain/trainers/seq2seq/__main__.py (261:272)

duplicated block id: 669
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (203:214)
 - src/autotrain/trainers/token_classification/__main__.py (210:221)

duplicated block id: 670
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (632:642)
 - src/autotrain/app/params.py (725:735)

duplicated block id: 671
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (201:213)
 - src/autotrain/trainers/object_detection/__main__.py (195:207)

duplicated block id: 672
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (516:526)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (47:57)

duplicated block id: 673
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (44:54)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (28:38)

duplicated block id: 674
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (229:240)
 - src/autotrain/preprocessor/vision.py (420:431)

duplicated block id: 675
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (179:190)
 - src/autotrain/preprocessor/vlm.py (213:224)

duplicated block id: 676
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (451:462)
 - src/autotrain/trainers/sent_transformers/__main__.py (233:244)

duplicated block id: 677
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (213:224)
 - src/autotrain/trainers/token_classification/__main__.py (210:221)

duplicated block id: 678
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (261:272)
 - src/autotrain/trainers/vlm/utils.py (318:329)

duplicated block id: 679
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (203:214)
 - src/autotrain/trainers/seq2seq/__main__.py (254:265)

duplicated block id: 680
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (211:222)
 - src/autotrain/trainers/vlm/utils.py (318:329)

duplicated block id: 681
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (185:195)
 - src/autotrain/app/models.py (269:279)

duplicated block id: 682
size: 11 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (27:37)
 - notebooks/text_classification.ipynb (27:37)

duplicated block id: 683
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (219:230)
 - src/autotrain/trainers/seq2seq/__main__.py (254:265)

duplicated block id: 684
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (136:147)
 - src/autotrain/commands.py (493:504)

duplicated block id: 685
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (219:230)
 - src/autotrain/trainers/token_classification/__main__.py (210:221)

duplicated block id: 686
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (451:462)
 - src/autotrain/trainers/token_classification/__main__.py (217:228)

duplicated block id: 687
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:600)
 - src/autotrain/app/params.py (632:642)

duplicated block id: 688
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (136:147)
 - src/autotrain/commands.py (416:427)

duplicated block id: 689
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (618:628)
 - src/autotrain/app/params.py (632:642)

duplicated block id: 690
size: 11 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (201:213)
 - src/autotrain/trainers/image_regression/__main__.py (185:197)

duplicated block id: 691
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (338:348)
 - src/autotrain/preprocessor/vision.py (551:561)

duplicated block id: 692
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (220:231)
 - src/autotrain/trainers/image_classification/__main__.py (201:212)

duplicated block id: 693
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/extractive_question_answering/utils.py (333:344)

duplicated block id: 694
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (473:484)
 - src/autotrain/preprocessor/text.py (713:724)

duplicated block id: 695
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/utils.py (203:214)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 696
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (48:57)
 - src/autotrain/trainers/text_classification/params.py (49:58)

duplicated block id: 697
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (137:146)
 - src/autotrain/preprocessor/vision.py (177:186)

duplicated block id: 698
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (220:231)
 - src/autotrain/trainers/image_regression/__main__.py (185:196)

duplicated block id: 699
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (195:206)
 - src/autotrain/trainers/text_classification/__main__.py (196:207)

duplicated block id: 700
size: 10 cleaned lines of code
in 2 files:
 - notebooks/text_classification.ipynb (10:19)
 - notebooks/text_regression.ipynb (10:19)

duplicated block id: 701
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (185:196)
 - src/autotrain/trainers/text_regression/__main__.py (186:197)

duplicated block id: 702
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (195:206)
 - src/autotrain/trainers/token_classification/__main__.py (192:203)

duplicated block id: 703
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (80:89)
 - src/autotrain/app/models.py (109:119)

duplicated block id: 704
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/utils.py (255:266)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 705
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/utils.py (159:170)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 706
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/utils.py (83:94)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 707
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/text_classification/utils.py (141:152)

duplicated block id: 708
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (80:89)
 - src/autotrain/app/models.py (173:182)

duplicated block id: 709
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (48:57)
 - src/autotrain/trainers/token_classification/params.py (49:58)

duplicated block id: 710
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (109:119)
 - src/autotrain/app/models.py (173:182)

duplicated block id: 711
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/object_detection/utils.py (255:266)

duplicated block id: 712
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/seq2seq/utils.py (83:94)

duplicated block id: 713
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/utils.py (103:114)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 714
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (201:212)
 - src/autotrain/trainers/text_regression/__main__.py (186:197)

duplicated block id: 715
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (612:621)
 - src/autotrain/dataset.py (647:656)

duplicated block id: 716
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (612:621)
 - src/autotrain/dataset.py (630:639)

duplicated block id: 717
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/params.py (49:58)
 - src/autotrain/trainers/text_regression/params.py (49:58)

duplicated block id: 718
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (298:307)
 - src/autotrain/project.py (362:371)

duplicated block id: 719
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/utils.py (141:152)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 720
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/utils.py (333:344)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 721
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/params.py (49:58)
 - src/autotrain/trainers/token_classification/params.py (49:58)

duplicated block id: 722
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (15:26)
 - src/autotrain/trainers/clm/train_clm_orpo.py (12:23)

duplicated block id: 723
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/utils.py (144:155)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 724
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/token_classification/utils.py (83:94)

duplicated block id: 725
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/utils.py (83:94)
 - src/autotrain/trainers/vlm/utils.py (99:110)

duplicated block id: 726
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (276:285)
 - src/autotrain/project.py (298:307)

duplicated block id: 727
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (407:416)
 - src/autotrain/app/params.py (424:433)

duplicated block id: 728
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/image_regression/utils.py (159:170)

duplicated block id: 729
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (201:212)
 - src/autotrain/trainers/token_classification/__main__.py (192:203)

duplicated block id: 730
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (632:641)
 - src/autotrain/dataset.py (747:756)

duplicated block id: 731
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (632:641)
 - src/autotrain/dataset.py (765:774)

duplicated block id: 732
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (632:641)
 - src/autotrain/dataset.py (783:792)

duplicated block id: 733
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (632:641)
 - src/autotrain/dataset.py (801:810)

duplicated block id: 734
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (185:196)
 - src/autotrain/trainers/text_classification/__main__.py (196:207)

duplicated block id: 735
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (632:641)
 - src/autotrain/dataset.py (729:738)

duplicated block id: 736
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (185:196)
 - src/autotrain/trainers/token_classification/__main__.py (192:203)

duplicated block id: 737
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (48:57)
 - src/autotrain/trainers/text_regression/params.py (49:58)

duplicated block id: 738
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (220:231)
 - src/autotrain/trainers/object_detection/__main__.py (195:206)

duplicated block id: 739
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/text_regression/utils.py (103:114)

duplicated block id: 740
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (401:411)
 - src/autotrain/preprocessor/vision.py (502:512)

duplicated block id: 741
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (195:206)
 - src/autotrain/trainers/text_regression/__main__.py (186:197)

duplicated block id: 742
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/image_classification/utils.py (203:214)

duplicated block id: 743
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (91:102)
 - src/autotrain/trainers/text_classification/__main__.py (93:104)

duplicated block id: 744
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (276:287)
 - src/autotrain/trainers/sent_transformers/utils.py (144:155)

duplicated block id: 745
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/params.py (49:58)
 - src/autotrain/trainers/text_classification/params.py (49:58)

duplicated block id: 746
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (649:658)
 - src/autotrain/dataset.py (801:810)

duplicated block id: 747
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (649:658)
 - src/autotrain/dataset.py (783:792)

duplicated block id: 748
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (649:658)
 - src/autotrain/dataset.py (765:774)

duplicated block id: 749
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (649:658)
 - src/autotrain/dataset.py (747:756)

duplicated block id: 750
size: 10 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (649:658)
 - src/autotrain/dataset.py (729:738)

duplicated block id: 751
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (139:148)
 - src/autotrain/preprocessor/vision.py (505:513)

duplicated block id: 752
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (139:148)
 - src/autotrain/preprocessor/vision.py (341:349)

duplicated block id: 753
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (650:658)
 - src/autotrain/dataset.py (669:677)

duplicated block id: 754
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (650:658)
 - src/autotrain/dataset.py (711:719)

duplicated block id: 755
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (187:195)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (30:38)

duplicated block id: 756
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (108:117)
 - src/autotrain/cli/run_sent_tranformers.py (86:94)

duplicated block id: 757
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (86:94)
 - src/autotrain/cli/run_llm.py (108:117)

duplicated block id: 758
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)
 - src/autotrain/trainers/text_classification/__main__.py (138:147)

duplicated block id: 759
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (669:677)
 - src/autotrain/dataset.py (711:719)

duplicated block id: 760
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (604:612)
 - src/autotrain/app/params.py (706:714)

duplicated block id: 761
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (375:384)
 - src/autotrain/preprocessor/text.py (602:611)

duplicated block id: 762
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (18:31)
 - src/autotrain/trainers/text_classification/__main__.py (23:37)

duplicated block id: 763
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (264:272)
 - src/autotrain/commands.py (463:471)

duplicated block id: 764
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (86:94)
 - src/autotrain/cli/run_llm.py (108:117)

duplicated block id: 765
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (264:272)
 - src/autotrain/commands.py (387:395)

duplicated block id: 766
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (312:320)
 - src/autotrain/commands.py (387:395)

duplicated block id: 767
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (312:320)
 - src/autotrain/commands.py (463:471)

duplicated block id: 768
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (108:117)
 - src/autotrain/cli/run_tabular.py (85:93)

duplicated block id: 769
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (18:31)
 - src/autotrain/trainers/token_classification/__main__.py (24:38)

duplicated block id: 770
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (633:641)
 - src/autotrain/dataset.py (669:677)

duplicated block id: 771
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (633:641)
 - src/autotrain/dataset.py (711:719)

duplicated block id: 772
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (18:31)
 - src/autotrain/trainers/text_regression/__main__.py (23:37)

duplicated block id: 773
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (51:59)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (30:38)

duplicated block id: 774
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (52:60)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (30:38)

duplicated block id: 775
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (115:124)
 - src/autotrain/trainers/clm/train_clm_sft.py (47:56)

duplicated block id: 776
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (53:61)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (30:38)

duplicated block id: 777
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (24:37)
 - src/autotrain/trainers/tabular/__main__.py (18:31)

duplicated block id: 778
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (308:318)
 - src/autotrain/dataset.py (408:418)

duplicated block id: 779
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (669:677)
 - src/autotrain/dataset.py (802:810)

duplicated block id: 780
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (669:677)
 - src/autotrain/dataset.py (748:756)

duplicated block id: 781
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (669:677)
 - src/autotrain/dataset.py (730:738)

duplicated block id: 782
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (669:677)
 - src/autotrain/dataset.py (784:792)

duplicated block id: 783
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (669:677)
 - src/autotrain/dataset.py (766:774)

duplicated block id: 784
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (664:672)
 - src/autotrain/app/params.py (706:714)

duplicated block id: 785
size: 9 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (67:75)
 - notebooks/text_regression.ipynb (64:72)

duplicated block id: 786
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (632:640)
 - src/autotrain/app/params.py (706:714)

duplicated block id: 787
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (143:152)
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)

duplicated block id: 788
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (70:81)
 - src/autotrain/preprocessor/vision.py (101:113)

duplicated block id: 789
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (74:82)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (49:57)

duplicated block id: 790
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (23:36)
 - src/autotrain/trainers/tabular/__main__.py (18:31)

duplicated block id: 791
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (594:602)
 - src/autotrain/dataset.py (612:620)

duplicated block id: 792
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (23:36)
 - src/autotrain/trainers/tabular/__main__.py (18:31)

duplicated block id: 793
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (93:103)
 - src/autotrain/trainers/text_classification/__main__.py (94:104)

duplicated block id: 794
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (98:108)
 - src/autotrain/dataset.py (308:318)

duplicated block id: 795
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (706:714)
 - src/autotrain/app/params.py (725:733)

duplicated block id: 796
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (158:168)
 - src/autotrain/dataset.py (468:478)

duplicated block id: 797
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (594:602)
 - src/autotrain/dataset.py (630:638)

duplicated block id: 798
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (711:719)
 - src/autotrain/dataset.py (784:792)

duplicated block id: 799
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (711:719)
 - src/autotrain/dataset.py (802:810)

duplicated block id: 800
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (73:81)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (49:57)

duplicated block id: 801
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (678:686)
 - src/autotrain/app/params.py (706:714)

duplicated block id: 802
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (48:56)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (30:38)

duplicated block id: 803
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_orpo.py (12:22)
 - src/autotrain/trainers/clm/train_clm_reward.py (17:26)

duplicated block id: 804
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (200:209)
 - src/autotrain/commands.py (491:500)

duplicated block id: 805
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (692:700)
 - src/autotrain/app/params.py (706:714)

duplicated block id: 806
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (711:719)
 - src/autotrain/dataset.py (730:738)

duplicated block id: 807
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (711:719)
 - src/autotrain/dataset.py (748:756)

duplicated block id: 808
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (711:719)
 - src/autotrain/dataset.py (766:774)

duplicated block id: 809
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (594:602)
 - src/autotrain/dataset.py (647:655)

duplicated block id: 810
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (200:209)
 - src/autotrain/commands.py (415:423)

duplicated block id: 811
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (46:54)
 - src/autotrain/preprocessor/text.py (470:478)

duplicated block id: 812
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (78:86)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (49:57)

duplicated block id: 813
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (129:138)
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)

duplicated block id: 814
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (51:59)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (30:38)

duplicated block id: 815
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (86:94)
 - src/autotrain/cli/run_llm.py (108:117)

duplicated block id: 816
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)
 - src/autotrain/trainers/text_regression/__main__.py (130:139)

duplicated block id: 817
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (139:148)
 - src/autotrain/preprocessor/vlm.py (151:159)

duplicated block id: 818
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)
 - src/autotrain/trainers/seq2seq/__main__.py (107:116)

duplicated block id: 819
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (73:81)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (49:57)

duplicated block id: 820
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (75:83)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (49:57)

duplicated block id: 821
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)
 - src/autotrain/trainers/token_classification/__main__.py (136:145)

duplicated block id: 822
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (152:161)
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)

duplicated block id: 823
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (158:168)
 - src/autotrain/dataset.py (257:267)

duplicated block id: 824
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (488:496)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (30:38)

duplicated block id: 825
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (56:64)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (30:38)

duplicated block id: 826
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (25:39)
 - src/autotrain/trainers/tabular/__main__.py (18:31)

duplicated block id: 827
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (108:117)
 - src/autotrain/cli/run_vlm.py (84:92)

duplicated block id: 828
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (132:141)
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)

duplicated block id: 829
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (108:117)
 - src/autotrain/cli/run_token_classification.py (87:95)

duplicated block id: 830
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (92:102)
 - src/autotrain/trainers/sent_transformers/__main__.py (93:103)

duplicated block id: 831
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (320:329)
 - src/autotrain/commands.py (491:500)

duplicated block id: 832
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (192:200)
 - src/autotrain/commands.py (387:395)

duplicated block id: 833
size: 9 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (67:75)
 - notebooks/text_classification.ipynb (64:72)

duplicated block id: 834
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (197:207)
 - src/autotrain/dataset.py (308:318)

duplicated block id: 835
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (192:200)
 - src/autotrain/commands.py (463:471)

duplicated block id: 836
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (21:34)
 - src/autotrain/trainers/tabular/__main__.py (18:31)

duplicated block id: 837
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (70:78)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (49:57)

duplicated block id: 838
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)
 - src/autotrain/trainers/vlm/utils.py (133:141)

duplicated block id: 839
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (28:42)
 - src/autotrain/trainers/tabular/__main__.py (18:31)

duplicated block id: 840
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (576:584)
 - src/autotrain/dataset.py (612:620)

duplicated block id: 841
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (257:267)
 - src/autotrain/dataset.py (468:478)

duplicated block id: 842
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (108:117)
 - src/autotrain/cli/run_text_regression.py (87:95)

duplicated block id: 843
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (15:25)
 - src/autotrain/trainers/clm/train_clm_reward.py (17:26)

duplicated block id: 844
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (650:658)
 - src/autotrain/app/params.py (706:714)

duplicated block id: 845
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (576:584)
 - src/autotrain/dataset.py (647:655)

duplicated block id: 846
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (576:584)
 - src/autotrain/dataset.py (630:638)

duplicated block id: 847
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (210:218)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (49:57)

duplicated block id: 848
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (676:684)
 - src/autotrain/trainers/sent_transformers/__main__.py (106:115)

duplicated block id: 849
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (108:117)
 - src/autotrain/cli/run_text_classification.py (87:95)

duplicated block id: 850
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (108:117)
 - src/autotrain/cli/run_object_detection.py (86:94)

duplicated block id: 851
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (320:329)
 - src/autotrain/commands.py (415:423)

duplicated block id: 852
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (590:598)
 - src/autotrain/app/params.py (706:714)

duplicated block id: 853
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (108:117)
 - src/autotrain/cli/run_seq2seq.py (78:86)

duplicated block id: 854
size: 9 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (618:626)
 - src/autotrain/app/params.py (706:714)

duplicated block id: 855
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 856
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (72:79)
 - src/autotrain/preprocessor/tabular.py (134:141)

duplicated block id: 857
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:60)
 - src/autotrain/cli/run_object_detection.py (53:60)

duplicated block id: 858
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 859
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (179:186)
 - src/autotrain/preprocessor/vision.py (341:348)

duplicated block id: 860
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_token_classification.py (54:61)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 861
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/params.py (59:66)
 - src/autotrain/trainers/text_regression/params.py (61:68)

duplicated block id: 862
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (34:41)
 - notebooks/text_classification.ipynb (83:90)

duplicated block id: 863
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (139:146)
 - src/autotrain/preprocessor/vision.py (554:561)

duplicated block id: 864
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:60)
 - src/autotrain/cli/run_text_classification.py (54:61)

duplicated block id: 865
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_image_classification.py (62:69)

duplicated block id: 866
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (136:143)
 - src/autotrain/commands.py (202:209)

duplicated block id: 867
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (53:60)
 - src/autotrain/cli/run_text_classification.py (54:61)

duplicated block id: 868
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (12:19)
 - notebooks/text_regression.ipynb (22:29)

duplicated block id: 869
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_spacerunner.py (83:90)

duplicated block id: 870
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:69)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 871
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (60:67)
 - src/autotrain/cli/run_spacerunner.py (83:90)

duplicated block id: 872
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (34:41)
 - notebooks/text_regression.ipynb (83:90)

duplicated block id: 873
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (179:186)
 - src/autotrain/preprocessor/vision.py (505:512)

duplicated block id: 874
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_orpo.py (12:20)
 - src/autotrain/trainers/clm/train_clm_sft.py (12:20)

duplicated block id: 875
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (210:217)
 - src/autotrain/preprocessor/text.py (180:187)

duplicated block id: 876
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (79:86)
 - src/autotrain/preprocessor/text.py (764:771)

duplicated block id: 877
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (51:58)
 - src/autotrain/cli/run_tabular.py (53:60)

duplicated block id: 878
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (139:146)
 - src/autotrain/preprocessor/vision.py (404:411)

duplicated block id: 879
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (62:69)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 880
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (60:67)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 881
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (54:61)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 882
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_spacerunner.py (83:90)

duplicated block id: 883
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (62:69)
 - src/autotrain/cli/run_spacerunner.py (83:90)

duplicated block id: 884
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (53:60)
 - src/autotrain/cli/run_text_classification.py (54:61)

duplicated block id: 885
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_default.py (85:93)
 - src/autotrain/trainers/clm/train_clm_dpo.py (97:105)

duplicated block id: 886
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (62:69)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 887
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_image_regression.py (53:60)

duplicated block id: 888
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (63:70)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 889
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (150:171)
 - src/autotrain/trainers/vlm/utils.py (83:90)

duplicated block id: 890
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (169:177)
 - src/autotrain/trainers/object_detection/__main__.py (173:181)

duplicated block id: 891
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (53:60)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 892
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (62:69)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 893
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_llm.py (62:69)

duplicated block id: 894
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:60)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 895
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 896
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_spacerunner.py (83:90)

duplicated block id: 897
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (65:73)
 - src/autotrain/trainers/clm/utils.py (953:961)

duplicated block id: 898
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (173:181)
 - src/autotrain/trainers/text_regression/__main__.py (170:178)

duplicated block id: 899
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (79:86)
 - src/autotrain/preprocessor/text.py (243:250)

duplicated block id: 900
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_object_detection.py (53:60)

duplicated block id: 901
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:69)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 902
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:69)
 - src/autotrain/cli/run_object_detection.py (53:60)

duplicated block id: 903
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (51:58)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 904
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (72:79)
 - src/autotrain/preprocessor/text.py (764:771)

duplicated block id: 905
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_orpo.py (37:45)
 - src/autotrain/trainers/clm/train_clm_reward.py (105:113)

duplicated block id: 906
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:69)
 - src/autotrain/cli/run_sent_tranformers.py (53:60)

duplicated block id: 907
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (60:67)
 - src/autotrain/cli/run_tabular.py (62:69)

duplicated block id: 908
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_object_detection.py (53:60)

duplicated block id: 909
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (15:23)
 - src/autotrain/trainers/clm/train_clm_sft.py (12:20)

duplicated block id: 910
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_sent_tranformers.py (53:60)

duplicated block id: 911
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_image_regression.py (53:60)

duplicated block id: 912
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_image_classification.py (53:60)

duplicated block id: 913
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 914
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (62:69)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 915
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (54:61)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 916
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 917
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (54:61)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 918
size: 8 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (37:44)
 - notebooks/text_regression.ipynb (83:90)

duplicated block id: 919
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:60)
 - src/autotrain/cli/run_llm.py (62:69)

duplicated block id: 920
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (554:561)
 - src/autotrain/preprocessor/vlm.py (151:158)

duplicated block id: 921
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 922
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (204:212)
 - src/autotrain/preprocessor/text.py (376:384)

duplicated block id: 923
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (51:58)
 - src/autotrain/cli/run_text_classification.py (54:61)

duplicated block id: 924
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (34:41)
 - notebooks/llm_finetuning.ipynb (85:92)

duplicated block id: 925
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (53:60)
 - src/autotrain/cli/run_tabular.py (53:60)

duplicated block id: 926
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 927
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 928
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (53:60)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 929
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_sent_tranformers.py (62:69)

duplicated block id: 930
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (62:69)
 - src/autotrain/cli/run_sent_tranformers.py (62:69)

duplicated block id: 931
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (192:200)
 - src/autotrain/trainers/object_detection/__main__.py (173:181)

duplicated block id: 932
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 933
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (173:181)
 - src/autotrain/trainers/seq2seq/__main__.py (149:157)

duplicated block id: 934
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (73:81)
 - src/autotrain/preprocessor/text.py (376:384)

duplicated block id: 935
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 936
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 937
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (12:19)
 - notebooks/text_classification.ipynb (22:29)

duplicated block id: 938
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (62:69)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 939
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 940
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (62:69)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 941
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (60:67)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 942
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (58:65)
 - src/autotrain/trainers/text_classification/params.py (61:68)

duplicated block id: 943
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_sent_tranformers.py (53:60)

duplicated block id: 944
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_text_classification.py (54:61)

duplicated block id: 945
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (210:217)
 - src/autotrain/preprocessor/text.py (764:771)

duplicated block id: 946
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (392:426)
 - src/autotrain/trainers/vlm/utils.py (283:294)

duplicated block id: 947
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (210:217)
 - src/autotrain/preprocessor/text.py (243:250)

duplicated block id: 948
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_spacerunner.py (83:90)

duplicated block id: 949
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/params.py (54:61)
 - src/autotrain/trainers/image_classification/params.py (50:57)

duplicated block id: 950
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/app/ui_routes.py (593:600)
 - src/autotrain/app/ui_routes.py (603:610)

duplicated block id: 951
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (62:69)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 952
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (62:69)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 953
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (56:63)
 - src/autotrain/trainers/clm/utils.py (944:951)

duplicated block id: 954
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (53:60)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 955
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (173:181)
 - src/autotrain/trainers/text_classification/__main__.py (178:186)

duplicated block id: 956
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (179:186)
 - src/autotrain/preprocessor/vlm.py (151:158)

duplicated block id: 957
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_llm.py (71:78)

duplicated block id: 958
size: 8 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (37:44)
 - notebooks/llm_finetuning.ipynb (34:41)

duplicated block id: 959
size: 8 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (37:44)
 - notebooks/llm_finetuning.ipynb (22:29)

duplicated block id: 960
size: 8 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (37:44)
 - notebooks/llm_finetuning.ipynb (85:92)

duplicated block id: 961
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (63:70)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 962
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (63:70)
 - src/autotrain/trainers/clm/utils.py (951:958)

duplicated block id: 963
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (58:65)
 - src/autotrain/trainers/text_regression/params.py (61:68)

duplicated block id: 964
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_seq2seq.py (51:58)

duplicated block id: 965
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_sent_tranformers.py (62:69)

duplicated block id: 966
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/params.py (59:66)
 - src/autotrain/trainers/token_classification/params.py (61:68)

duplicated block id: 967
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_tabular.py (53:60)

duplicated block id: 968
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_object_detection.py (62:69)

duplicated block id: 969
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (22:29)
 - notebooks/text_regression.ipynb (83:90)

duplicated block id: 970
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_image_regression.py (62:69)

duplicated block id: 971
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (49:56)
 - src/autotrain/preprocessor/vision.py (229:236)

duplicated block id: 972
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (53:60)
 - src/autotrain/cli/run_tabular.py (53:60)

duplicated block id: 973
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:69)
 - src/autotrain/cli/run_tabular.py (53:60)

duplicated block id: 974
size: 8 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (13:20)
 - notebooks/text_classification.ipynb (83:90)

duplicated block id: 975
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (183:191)
 - src/autotrain/trainers/object_detection/__main__.py (173:181)

duplicated block id: 976
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:69)
 - src/autotrain/cli/run_seq2seq.py (51:58)

duplicated block id: 977
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:60)
 - src/autotrain/cli/run_tabular.py (53:60)

duplicated block id: 978
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (60:67)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 979
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (110:118)
 - src/autotrain/trainers/text_regression/__main__.py (113:121)

duplicated block id: 980
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (49:56)
 - src/autotrain/preprocessor/vision.py (420:427)

duplicated block id: 981
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (173:181)
 - src/autotrain/trainers/token_classification/__main__.py (176:184)

duplicated block id: 982
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/app/ui_routes.py (583:590)
 - src/autotrain/app/ui_routes.py (603:610)

duplicated block id: 983
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/app/ui_routes.py (583:590)
 - src/autotrain/app/ui_routes.py (593:600)

duplicated block id: 984
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (63:70)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 985
size: 8 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (37:44)
 - notebooks/text_classification.ipynb (83:90)

duplicated block id: 986
size: 8 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (13:20)
 - notebooks/text_regression.ipynb (83:90)

duplicated block id: 987
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:60)
 - src/autotrain/cli/run_seq2seq.py (51:58)

duplicated block id: 988
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_text_classification.py (54:61)

duplicated block id: 989
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (53:60)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 990
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (83:90)
 - src/autotrain/cli/run_tabular.py (62:69)

duplicated block id: 991
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (51:58)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 992
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_object_detection.py (62:69)

duplicated block id: 993
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_image_regression.py (62:69)

duplicated block id: 994
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 995
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:69)
 - src/autotrain/cli/run_text_classification.py (54:61)

duplicated block id: 996
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_seq2seq.py (60:67)

duplicated block id: 997
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (105:113)
 - src/autotrain/trainers/clm/train_clm_sft.py (37:45)

duplicated block id: 998
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_tabular.py (62:69)

duplicated block id: 999
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_llm.py (62:69)

duplicated block id: 1000
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (72:79)
 - src/autotrain/preprocessor/text.py (180:187)

duplicated block id: 1001
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (53:60)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 1002
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (62:69)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 1003
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (51:58)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 1004
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 1005
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (62:69)
 - src/autotrain/cli/run_seq2seq.py (60:67)

duplicated block id: 1006
size: 8 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (13:20)
 - colabs/image_classification.ipynb (37:44)

duplicated block id: 1007
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_llm.py (71:78)

duplicated block id: 1008
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_object_detection.py (62:69)

duplicated block id: 1009
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (83:90)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 1010
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (53:60)
 - src/autotrain/cli/run_text_classification.py (54:61)

duplicated block id: 1011
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (139:146)
 - src/autotrain/preprocessor/vlm.py (213:220)

duplicated block id: 1012
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_seq2seq.py (60:67)

duplicated block id: 1013
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_default.py (85:93)
 - src/autotrain/trainers/clm/train_clm_reward.py (105:113)

duplicated block id: 1014
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (62:69)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 1015
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_default.py (85:93)
 - src/autotrain/trainers/clm/train_clm_sft.py (37:45)

duplicated block id: 1016
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (63:70)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 1017
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_object_detection.py (62:69)

duplicated block id: 1018
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (53:60)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 1019
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (62:69)
 - src/autotrain/cli/run_seq2seq.py (60:67)

duplicated block id: 1020
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (404:411)
 - src/autotrain/preprocessor/vlm.py (151:158)

duplicated block id: 1021
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (62:69)
 - src/autotrain/cli/run_spacerunner.py (83:90)

duplicated block id: 1022
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (134:141)
 - src/autotrain/preprocessor/tabular.py (210:217)

duplicated block id: 1023
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (62:69)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 1024
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (22:29)
 - notebooks/llm_finetuning.ipynb (34:41)

duplicated block id: 1025
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (53:60)
 - src/autotrain/cli/run_seq2seq.py (51:58)

duplicated block id: 1026
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_tabular.py (62:69)

duplicated block id: 1027
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (83:90)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 1028
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (22:29)
 - notebooks/llm_finetuning.ipynb (85:92)

duplicated block id: 1029
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_sent_tranformers.py (62:69)

duplicated block id: 1030
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_token_classification.py (63:70)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 1031
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (83:90)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 1032
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (186:193)
 - src/autotrain/project.py (430:437)

duplicated block id: 1033
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (341:348)
 - src/autotrain/preprocessor/vlm.py (213:220)

duplicated block id: 1034
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (66:73)
 - src/autotrain/commands.py (388:395)

duplicated block id: 1035
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/params.py (59:66)
 - src/autotrain/trainers/text_classification/params.py (61:68)

duplicated block id: 1036
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (72:79)
 - src/autotrain/preprocessor/text.py (243:250)

duplicated block id: 1037
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (62:69)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 1038
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 1039
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (66:73)
 - src/autotrain/commands.py (464:471)

duplicated block id: 1040
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (54:61)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 1041
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_classification.py (54:61)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 1042
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 1043
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (53:60)
 - src/autotrain/cli/run_sent_tranformers.py (53:60)

duplicated block id: 1044
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (66:73)
 - src/autotrain/commands.py (313:320)

duplicated block id: 1045
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 1046
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (79:86)
 - src/autotrain/preprocessor/text.py (180:187)

duplicated block id: 1047
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_seq2seq.py (51:58)

duplicated block id: 1048
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (62:69)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 1049
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (173:181)
 - src/autotrain/trainers/sent_transformers/__main__.py (152:160)

duplicated block id: 1050
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (53:60)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 1051
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (18:25)
 - src/autotrain/trainers/vlm/utils.py (11:18)

duplicated block id: 1052
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_llm.py (71:78)

duplicated block id: 1053
size: 8 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (13:20)
 - notebooks/llm_finetuning.ipynb (34:41)

duplicated block id: 1054
size: 8 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (13:20)
 - notebooks/llm_finetuning.ipynb (22:29)

duplicated block id: 1055
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (234:241)
 - src/autotrain/commands.py (345:352)

duplicated block id: 1056
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (614:621)
 - src/autotrain/dataset.py (765:772)

duplicated block id: 1057
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_default.py (85:93)
 - src/autotrain/trainers/clm/train_clm_orpo.py (37:45)

duplicated block id: 1058
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (83:90)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 1059
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (614:621)
 - src/autotrain/dataset.py (783:790)

duplicated block id: 1060
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (53:60)
 - src/autotrain/cli/run_seq2seq.py (51:58)

duplicated block id: 1061
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_sent_tranformers.py (62:69)

duplicated block id: 1062
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (614:621)
 - src/autotrain/dataset.py (729:736)

duplicated block id: 1063
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (614:621)
 - src/autotrain/dataset.py (747:754)

duplicated block id: 1064
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_seq2seq.py (60:67)

duplicated block id: 1065
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (110:118)
 - src/autotrain/trainers/clm/train_clm_orpo.py (49:57)

duplicated block id: 1066
size: 8 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (13:20)
 - notebooks/llm_finetuning.ipynb (85:92)

duplicated block id: 1067
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (614:621)
 - src/autotrain/dataset.py (801:808)

duplicated block id: 1068
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:60)
 - src/autotrain/cli/run_tabular.py (53:60)

duplicated block id: 1069
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (62:69)
 - src/autotrain/cli/run_tabular.py (62:69)

duplicated block id: 1070
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (110:118)
 - src/autotrain/trainers/text_classification/__main__.py (121:129)

duplicated block id: 1071
size: 8 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (22:29)
 - notebooks/text_classification.ipynb (83:90)

duplicated block id: 1072
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:60)
 - src/autotrain/cli/run_text_regression.py (54:61)

duplicated block id: 1073
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_tabular.py (62:69)

duplicated block id: 1074
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (62:69)
 - src/autotrain/cli/run_tabular.py (62:69)

duplicated block id: 1075
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (53:60)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 1076
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:60)
 - src/autotrain/cli/run_token_classification.py (54:61)

duplicated block id: 1077
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (97:105)
 - src/autotrain/trainers/clm/train_clm_reward.py (105:113)

duplicated block id: 1078
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/app/ui_routes.py (725:732)
 - src/autotrain/commands.py (126:133)

duplicated block id: 1079
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (60:67)
 - src/autotrain/cli/run_text_regression.py (63:70)

duplicated block id: 1080
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (376:384)
 - src/autotrain/preprocessor/text.py (496:504)

duplicated block id: 1081
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (134:141)
 - src/autotrain/preprocessor/text.py (79:86)

duplicated block id: 1082
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (71:78)
 - src/autotrain/cli/run_vlm.py (60:67)

duplicated block id: 1083
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (66:74)
 - src/autotrain/preprocessor/text.py (376:384)

duplicated block id: 1084
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:69)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 1085
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (58:65)
 - src/autotrain/trainers/token_classification/params.py (61:68)

duplicated block id: 1086
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (53:60)
 - src/autotrain/cli/run_vlm.py (51:58)

duplicated block id: 1087
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (505:512)
 - src/autotrain/preprocessor/vlm.py (213:220)

duplicated block id: 1088
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/dataset.py (28:37)
 - src/autotrain/trainers/image_regression/dataset.py (24:33)

duplicated block id: 1089
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_text_classification.py (63:70)

duplicated block id: 1090
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (66:73)
 - src/autotrain/commands.py (265:272)

duplicated block id: 1091
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (66:73)
 - src/autotrain/commands.py (193:200)

duplicated block id: 1092
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (17:25)
 - src/autotrain/trainers/clm/train_clm_sft.py (12:20)

duplicated block id: 1093
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_text_regression.py (63:70)
 - src/autotrain/cli/run_token_classification.py (63:70)

duplicated block id: 1094
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:60)
 - src/autotrain/cli/run_sent_tranformers.py (53:60)

duplicated block id: 1095
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (62:69)
 - src/autotrain/cli/run_seq2seq.py (60:67)

duplicated block id: 1096
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (136:143)
 - src/autotrain/commands.py (322:329)

duplicated block id: 1097
size: 8 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (62:69)
 - src/autotrain/cli/run_tabular.py (62:69)

duplicated block id: 1098
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1099
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1100
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (52:58)
 - src/autotrain/trainers/object_detection/__main__.py (73:79)

duplicated block id: 1101
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)

duplicated block id: 1102
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (72:78)
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)

duplicated block id: 1103
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/image_classification/__main__.py (72:78)

duplicated block id: 1104
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (110:116)
 - src/autotrain/trainers/image_regression/__main__.py (110:116)

duplicated block id: 1105
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/token_classification/__main__.py (34:43)

duplicated block id: 1106
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (687:693)
 - src/autotrain/dataset.py (730:736)

duplicated block id: 1107
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/text_classification/__main__.py (33:42)

duplicated block id: 1108
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (687:693)
 - src/autotrain/dataset.py (748:754)

duplicated block id: 1109
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (687:693)
 - src/autotrain/dataset.py (766:772)

duplicated block id: 1110
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (650:656)
 - src/autotrain/dataset.py (687:693)

duplicated block id: 1111
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (51:57)
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)

duplicated block id: 1112
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (72:78)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1113
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/image_classification/__main__.py (51:57)

duplicated block id: 1114
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)

duplicated block id: 1115
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (52:58)
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)

duplicated block id: 1116
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (256:262)
 - src/autotrain/project.py (430:436)

duplicated block id: 1117
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (72:78)
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)

duplicated block id: 1118
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (124:130)
 - src/autotrain/trainers/text_regression/__main__.py (113:119)

duplicated block id: 1119
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (687:693)
 - src/autotrain/dataset.py (784:790)

duplicated block id: 1120
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (387:393)
 - src/autotrain/commands.py (452:458)

duplicated block id: 1121
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (51:57)
 - src/autotrain/trainers/tabular/__main__.py (215:221)

duplicated block id: 1122
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (687:693)
 - src/autotrain/dataset.py (802:808)

duplicated block id: 1123
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (473:479)
 - src/autotrain/preprocessor/text.py (587:593)

duplicated block id: 1124
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (116:122)
 - src/autotrain/trainers/text_regression/__main__.py (105:111)

duplicated block id: 1125
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/object_detection/__main__.py (73:79)

duplicated block id: 1126
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (116:122)
 - src/autotrain/trainers/token_classification/__main__.py (103:109)

duplicated block id: 1127
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1128
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (215:221)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1129
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (102:108)
 - src/autotrain/trainers/text_regression/__main__.py (105:111)

duplicated block id: 1130
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)

duplicated block id: 1131
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (72:78)
 - src/autotrain/trainers/text_classification/__main__.py (56:62)

duplicated block id: 1132
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (122:128)
 - src/autotrain/cli/run_vlm.py (97:103)

duplicated block id: 1133
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1134
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (102:108)
 - src/autotrain/trainers/text_regression/__main__.py (105:111)

duplicated block id: 1135
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (35:44)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1136
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (72:78)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1137
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (78:84)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1138
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (192:198)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1139
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (52:58)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1140
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (669:675)
 - src/autotrain/dataset.py (687:693)

duplicated block id: 1141
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1142
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)
 - src/autotrain/trainers/tabular/__main__.py (192:198)

duplicated block id: 1143
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (72:78)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1144
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (301:310)
 - src/autotrain/preprocessor/vision.py (184:193)

duplicated block id: 1145
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1146
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (192:198)
 - src/autotrain/trainers/tabular/__main__.py (215:221)

duplicated block id: 1147
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (29:35)
 - src/autotrain/trainers/vlm/utils.py (192:198)

duplicated block id: 1148
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (264:270)
 - src/autotrain/commands.py (376:382)

duplicated block id: 1149
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (186:193)
 - src/autotrain/preprocessor/vlm.py (104:111)

duplicated block id: 1150
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (56:62)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1151
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (312:318)
 - src/autotrain/commands.py (376:382)

duplicated block id: 1152
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (32:41)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1153
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (301:310)
 - src/autotrain/preprocessor/vision.py (409:418)

duplicated block id: 1154
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (73:79)
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)

duplicated block id: 1155
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (264:270)
 - src/autotrain/commands.py (452:458)

duplicated block id: 1156
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (33:42)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1157
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (57:63)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1158
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (52:58)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1159
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (687:693)
 - src/autotrain/dataset.py (711:717)

duplicated block id: 1160
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)

duplicated block id: 1161
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (312:318)
 - src/autotrain/commands.py (452:458)

duplicated block id: 1162
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (113:119)
 - src/autotrain/trainers/token_classification/__main__.py (103:109)

duplicated block id: 1163
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1164
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/image_regression/__main__.py (51:57)

duplicated block id: 1165
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (102:108)
 - src/autotrain/trainers/token_classification/__main__.py (103:109)

duplicated block id: 1166
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1167
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (51:57)
 - src/autotrain/trainers/object_detection/__main__.py (73:79)

duplicated block id: 1168
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1169
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/image_classification/__main__.py (72:78)

duplicated block id: 1170
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (73:79)
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)

duplicated block id: 1171
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)
 - src/autotrain/trainers/tabular/__main__.py (215:221)

duplicated block id: 1172
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1173
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_default.py (87:93)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (80:86)

duplicated block id: 1174
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)

duplicated block id: 1175
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1176
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (110:116)
 - src/autotrain/trainers/image_classification/__main__.py (124:130)

duplicated block id: 1177
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (633:639)
 - src/autotrain/dataset.py (687:693)

duplicated block id: 1178
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)

duplicated block id: 1179
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (587:593)
 - src/autotrain/preprocessor/text.py (713:719)

duplicated block id: 1180
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (113:119)
 - src/autotrain/trainers/token_classification/__main__.py (111:117)

duplicated block id: 1181
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (186:193)
 - src/autotrain/preprocessor/vision.py (293:300)

duplicated block id: 1182
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (159:166)
 - src/autotrain/app/models.py (230:237)

duplicated block id: 1183
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (159:166)
 - src/autotrain/app/models.py (189:195)

duplicated block id: 1184
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (99:105)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (80:86)

duplicated block id: 1185
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (185:191)
 - src/autotrain/trainers/vlm/utils.py (215:221)

duplicated block id: 1186
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (35:44)

duplicated block id: 1187
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (33:42)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1188
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (202:208)
 - src/autotrain/app/models.py (212:218)

duplicated block id: 1189
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (578:584)
 - src/autotrain/dataset.py (765:771)

duplicated block id: 1190
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_orpo.py (39:45)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (80:86)

duplicated block id: 1191
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1192
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (159:166)
 - src/autotrain/app/models.py (273:279)

duplicated block id: 1193
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (578:584)
 - src/autotrain/dataset.py (747:753)

duplicated block id: 1194
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (578:584)
 - src/autotrain/dataset.py (801:807)

duplicated block id: 1195
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (578:584)
 - src/autotrain/dataset.py (783:789)

duplicated block id: 1196
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1197
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (72:78)
 - src/autotrain/trainers/tabular/__main__.py (192:198)

duplicated block id: 1198
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (578:584)
 - src/autotrain/dataset.py (729:735)

duplicated block id: 1199
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (30:39)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1200
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (32:41)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1201
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/image_regression/__main__.py (72:78)

duplicated block id: 1202
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/tabular/__main__.py (192:198)

duplicated block id: 1203
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/tabular/__main__.py (215:221)

duplicated block id: 1204
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/image_classification/__main__.py (51:57)

duplicated block id: 1205
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (215:221)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1206
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (122:128)
 - src/autotrain/cli/run_sent_tranformers.py (99:105)

duplicated block id: 1207
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (124:130)
 - src/autotrain/trainers/text_classification/__main__.py (121:127)

duplicated block id: 1208
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (52:58)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1209
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (72:78)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1210
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (249:256)
 - src/autotrain/preprocessor/vision.py (293:300)

duplicated block id: 1211
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (34:43)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1212
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/image_classification/__main__.py (32:41)

duplicated block id: 1213
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/object_detection/__main__.py (52:58)

duplicated block id: 1214
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (38:44)
 - src/autotrain/app/models.py (173:179)

duplicated block id: 1215
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (38:44)
 - src/autotrain/app/models.py (212:218)

duplicated block id: 1216
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (551:559)
 - src/autotrain/preprocessor/vision.py (409:418)

duplicated block id: 1217
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)

duplicated block id: 1218
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)
 - src/autotrain/trainers/text_classification/__main__.py (56:62)

duplicated block id: 1219
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/object_detection/__main__.py (73:79)

duplicated block id: 1220
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (80:86)
 - src/autotrain/app/models.py (212:218)

duplicated block id: 1221
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (80:86)
 - src/autotrain/app/models.py (202:208)

duplicated block id: 1222
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (438:446)
 - src/autotrain/preprocessor/vision.py (184:193)

duplicated block id: 1223
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (116:122)
 - src/autotrain/trainers/text_classification/__main__.py (113:119)

duplicated block id: 1224
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (215:221)
 - src/autotrain/trainers/text_classification/__main__.py (56:62)

duplicated block id: 1225
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (56:62)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1226
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (551:559)
 - src/autotrain/preprocessor/vision.py (184:193)

duplicated block id: 1227
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/image_regression/__main__.py (32:41)

duplicated block id: 1228
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (249:256)
 - src/autotrain/preprocessor/vision.py (471:478)

duplicated block id: 1229
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (107:113)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (80:86)

duplicated block id: 1230
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1231
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (99:105)
 - src/autotrain/cli/run_llm.py (122:128)

duplicated block id: 1232
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (192:198)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1233
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (110:116)
 - src/autotrain/trainers/token_classification/__main__.py (111:117)

duplicated block id: 1234
size: 7 cleaned lines of code
in 2 files:
 - colabs/AutoTrain_LLM.ipynb (1:7)
 - colabs/AutoTrain_ngrok.ipynb (1:7)

duplicated block id: 1235
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (376:382)
 - src/autotrain/commands.py (387:393)

duplicated block id: 1236
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1237
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (78:84)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1238
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (376:382)
 - src/autotrain/commands.py (463:469)

duplicated block id: 1239
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (109:115)
 - src/autotrain/app/models.py (202:208)

duplicated block id: 1240
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1241
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (109:115)
 - src/autotrain/app/models.py (212:218)

duplicated block id: 1242
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (102:108)
 - src/autotrain/trainers/text_classification/__main__.py (113:119)

duplicated block id: 1243
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1244
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (29:35)
 - src/autotrain/commands.py (184:190)

duplicated block id: 1245
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (110:116)
 - src/autotrain/trainers/text_classification/__main__.py (121:127)

duplicated block id: 1246
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1247
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (29:35)
 - src/autotrain/commands.py (256:262)

duplicated block id: 1248
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)
 - src/autotrain/trainers/text_classification/__main__.py (56:62)

duplicated block id: 1249
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/tabular/__main__.py (215:221)

duplicated block id: 1250
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1251
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (73:79)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1252
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (73:79)
 - src/autotrain/trainers/tabular/__main__.py (192:198)

duplicated block id: 1253
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (438:446)
 - src/autotrain/preprocessor/vision.py (409:418)

duplicated block id: 1254
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (33:42)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1255
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (31:37)
 - src/autotrain/trainers/clm/train_clm_reward.py (29:35)

duplicated block id: 1256
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)

duplicated block id: 1257
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (29:35)
 - src/autotrain/commands.py (444:450)

duplicated block id: 1258
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (102:108)
 - src/autotrain/trainers/image_regression/__main__.py (102:108)

duplicated block id: 1259
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/image_regression/__main__.py (72:78)

duplicated block id: 1260
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (615:621)
 - src/autotrain/dataset.py (711:717)

duplicated block id: 1261
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (615:621)
 - src/autotrain/dataset.py (669:675)

duplicated block id: 1262
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (615:621)
 - src/autotrain/dataset.py (687:693)

duplicated block id: 1263
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1264
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (29:35)
 - src/autotrain/commands.py (304:310)

duplicated block id: 1265
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (29:35)
 - src/autotrain/commands.py (368:374)

duplicated block id: 1266
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (29:35)
 - src/autotrain/trainers/clm/utils.py (921:927)

duplicated block id: 1267
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/tabular/__main__.py (215:221)

duplicated block id: 1268
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (73:79)
 - src/autotrain/trainers/token_classification/__main__.py (57:63)

duplicated block id: 1269
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (56:62)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1270
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/text_classification/__main__.py (56:62)

duplicated block id: 1271
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/object_detection/__main__.py (52:58)

duplicated block id: 1272
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (51:57)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1273
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/text_regression/__main__.py (33:42)

duplicated block id: 1274
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (51:57)
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)

duplicated block id: 1275
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/tabular/__main__.py (192:198)

duplicated block id: 1276
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (173:179)
 - src/autotrain/app/models.py (212:218)

duplicated block id: 1277
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/api_routes.py (51:57)
 - src/autotrain/app/params.py (531:537)

duplicated block id: 1278
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1279
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (173:179)
 - src/autotrain/app/models.py (202:208)

duplicated block id: 1280
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (216:223)
 - src/autotrain/app/models.py (258:266)

duplicated block id: 1281
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (596:602)
 - src/autotrain/dataset.py (801:807)

duplicated block id: 1282
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (596:602)
 - src/autotrain/dataset.py (783:789)

duplicated block id: 1283
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (66:73)
 - src/autotrain/app/models.py (159:166)

duplicated block id: 1284
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (596:602)
 - src/autotrain/dataset.py (765:771)

duplicated block id: 1285
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (596:602)
 - src/autotrain/dataset.py (747:753)

duplicated block id: 1286
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (72:78)
 - src/autotrain/trainers/image_regression/__main__.py (51:57)

duplicated block id: 1287
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (56:62)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1288
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (72:78)
 - src/autotrain/trainers/tabular/__main__.py (192:198)

duplicated block id: 1289
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/text_classification/__main__.py (56:62)

duplicated block id: 1290
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (452:458)
 - src/autotrain/commands.py (463:469)

duplicated block id: 1291
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (596:602)
 - src/autotrain/dataset.py (729:735)

duplicated block id: 1292
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (189:195)
 - src/autotrain/project.py (224:230)

duplicated block id: 1293
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)

duplicated block id: 1294
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (102:108)
 - src/autotrain/trainers/image_classification/__main__.py (116:122)

duplicated block id: 1295
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (352:358)
 - src/autotrain/preprocessor/text.py (586:592)

duplicated block id: 1296
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (186:193)
 - src/autotrain/preprocessor/vision.py (471:478)

duplicated block id: 1297
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (110:116)
 - src/autotrain/trainers/text_regression/__main__.py (113:119)

duplicated block id: 1298
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)

duplicated block id: 1299
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1300
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (58:64)
 - src/autotrain/trainers/object_detection/__main__.py (73:79)

duplicated block id: 1301
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (56:62)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1302
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (51:57)
 - src/autotrain/trainers/text_classification/__main__.py (78:84)

duplicated block id: 1303
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (54:60)
 - src/autotrain/trainers/clm/train_clm_reward.py (56:62)

duplicated block id: 1304
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)

duplicated block id: 1305
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (110:116)
 - src/autotrain/trainers/token_classification/__main__.py (111:117)

duplicated block id: 1306
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/sent_transformers/__main__.py (30:39)

duplicated block id: 1307
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (38:47)
 - src/autotrain/trainers/vlm/__main__.py (9:18)

duplicated block id: 1308
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (126:133)
 - src/autotrain/app/models.py (159:166)

duplicated block id: 1309
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)
 - src/autotrain/trainers/tabular/__main__.py (192:198)

duplicated block id: 1310
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (192:198)
 - src/autotrain/commands.py (376:382)

duplicated block id: 1311
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (192:198)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1312
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1313
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (72:78)
 - src/autotrain/trainers/text_classification/__main__.py (56:62)

duplicated block id: 1314
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (78:84)
 - src/autotrain/trainers/text_regression/__main__.py (56:62)

duplicated block id: 1315
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (74:80)
 - src/autotrain/project.py (151:157)

duplicated block id: 1316
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/params.py (53:59)
 - src/autotrain/trainers/tabular/params.py (36:42)

duplicated block id: 1317
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (192:198)
 - src/autotrain/commands.py (452:458)

duplicated block id: 1318
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_sft.py (39:45)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (80:86)

duplicated block id: 1319
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (96:102)
 - src/autotrain/app/models.py (159:166)

duplicated block id: 1320
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (48:54)
 - src/autotrain/app/models.py (173:179)

duplicated block id: 1321
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (72:78)
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)

duplicated block id: 1322
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/image_regression/__main__.py (51:57)

duplicated block id: 1323
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (48:54)
 - src/autotrain/app/models.py (202:208)

duplicated block id: 1324
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (676:684)
 - src/autotrain/preprocessor/vision.py (184:193)

duplicated block id: 1325
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)
 - src/autotrain/trainers/sent_transformers/__main__.py (75:81)

duplicated block id: 1326
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)

duplicated block id: 1327
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (38:44)
 - src/autotrain/app/models.py (80:86)

duplicated block id: 1328
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/extractive_question_answering/__main__.py (80:86)

duplicated block id: 1329
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (38:44)
 - src/autotrain/app/models.py (109:115)

duplicated block id: 1330
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (38:44)
 - src/autotrain/app/models.py (48:54)

duplicated block id: 1331
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (51:57)
 - src/autotrain/trainers/token_classification/__main__.py (79:85)

duplicated block id: 1332
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (51:57)
 - src/autotrain/trainers/image_regression/__main__.py (72:78)

duplicated block id: 1333
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (52:58)
 - src/autotrain/trainers/tabular/__main__.py (215:221)

duplicated block id: 1334
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (676:684)
 - src/autotrain/preprocessor/vision.py (409:418)

duplicated block id: 1335
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/clm/utils.py (523:529)

duplicated block id: 1336
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (121:127)
 - src/autotrain/trainers/token_classification/__main__.py (111:117)

duplicated block id: 1337
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)

duplicated block id: 1338
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)
 - src/autotrain/trainers/tabular/__main__.py (215:221)

duplicated block id: 1339
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (523:529)
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)

duplicated block id: 1340
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)
 - src/autotrain/trainers/text_regression/__main__.py (78:84)

duplicated block id: 1341
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (48:54)
 - src/autotrain/app/models.py (109:115)

duplicated block id: 1342
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (48:54)
 - src/autotrain/app/models.py (80:86)

duplicated block id: 1343
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (61:67)
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)

duplicated block id: 1344
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (99:105)
 - src/autotrain/cli/run_llm.py (122:128)

duplicated block id: 1345
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/seq2seq/__main__.py (38:47)

duplicated block id: 1346
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (102:108)
 - src/autotrain/trainers/text_classification/__main__.py (113:119)

duplicated block id: 1347
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (493:499)
 - src/autotrain/trainers/image_classification/__main__.py (72:78)

duplicated block id: 1348
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (249:256)
 - src/autotrain/preprocessor/vlm.py (104:111)

duplicated block id: 1349
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (51:57)
 - src/autotrain/trainers/image_regression/__main__.py (72:78)

duplicated block id: 1350
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (52:59)
 - src/autotrain/app/models.py (258:266)

duplicated block id: 1351
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (73:79)
 - src/autotrain/trainers/text_classification/__main__.py (56:62)

duplicated block id: 1352
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (124:130)
 - src/autotrain/trainers/token_classification/__main__.py (111:117)

duplicated block id: 1353
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (102:108)
 - src/autotrain/trainers/token_classification/__main__.py (103:109)

duplicated block id: 1354
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (72:78)
 - src/autotrain/trainers/object_detection/__main__.py (52:58)

duplicated block id: 1355
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (154:160)
 - src/autotrain/project.py (224:230)

duplicated block id: 1356
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (72:78)
 - src/autotrain/trainers/sent_transformers/__main__.py (53:59)

duplicated block id: 1357
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (122:128)
 - src/autotrain/cli/run_object_detection.py (99:105)

duplicated block id: 1358
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (72:78)
 - src/autotrain/trainers/object_detection/__main__.py (52:58)

duplicated block id: 1359
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (186:192)
 - src/autotrain/project.py (256:262)

duplicated block id: 1360
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/__main__.py (8:17)
 - src/autotrain/trainers/object_detection/__main__.py (33:42)

duplicated block id: 1361
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (154:160)
 - src/autotrain/project.py (189:195)

duplicated block id: 1362
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (52:58)
 - src/autotrain/trainers/seq2seq/__main__.py (83:89)

duplicated block id: 1363
size: 7 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (105:111)
 - src/autotrain/trainers/token_classification/__main__.py (103:109)

duplicated block id: 1364
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (110:115)
 - src/autotrain/dataset.py (526:531)

duplicated block id: 1365
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (56:61)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1366
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (140:145)
 - src/autotrain/preprocessor/vision.py (471:476)

duplicated block id: 1367
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (81:87)
 - src/autotrain/cli/run_vlm.py (70:76)

duplicated block id: 1368
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (770:775)
 - src/autotrain/preprocessor/vision.py (471:476)

duplicated block id: 1369
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (81:87)
 - src/autotrain/cli/run_object_detection.py (72:78)

duplicated block id: 1370
size: 6 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (3:8)
 - notebooks/text_regression.ipynb (85:90)

duplicated block id: 1371
size: 6 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (1:6)
 - notebooks/llm_finetuning.ipynb (1:6)

duplicated block id: 1372
size: 6 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (1:6)
 - notebooks/text_regression.ipynb (1:6)

duplicated block id: 1373
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (78:83)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1374
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (140:145)
 - src/autotrain/preprocessor/vision.py (293:298)

duplicated block id: 1375
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (770:775)
 - src/autotrain/preprocessor/vision.py (293:298)

duplicated block id: 1376
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (73:78)
 - src/autotrain/cli/run_vlm.py (51:56)

duplicated block id: 1377
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (538:544)
 - src/autotrain/preprocessor/vlm.py (122:128)

duplicated block id: 1378
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (216:224)
 - src/autotrain/trainers/seq2seq/__main__.py (269:277)

duplicated block id: 1379
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (579:584)
 - src/autotrain/dataset.py (669:674)

duplicated block id: 1380
size: 6 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (3:8)
 - notebooks/llm_finetuning.ipynb (87:92)

duplicated block id: 1381
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (579:584)
 - src/autotrain/dataset.py (687:692)

duplicated block id: 1382
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (579:584)
 - src/autotrain/dataset.py (711:716)

duplicated block id: 1383
size: 6 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (3:8)
 - notebooks/llm_finetuning.ipynb (36:41)

duplicated block id: 1384
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (72:78)
 - src/autotrain/cli/run_llm.py (81:87)

duplicated block id: 1385
size: 6 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (3:8)
 - notebooks/llm_finetuning.ipynb (24:29)

duplicated block id: 1386
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (232:240)
 - src/autotrain/trainers/seq2seq/__main__.py (269:277)

duplicated block id: 1387
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (90:95)
 - src/autotrain/trainers/clm/utils.py (983:988)

duplicated block id: 1388
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (73:78)
 - src/autotrain/cli/run_text_classification.py (54:59)

duplicated block id: 1389
size: 6 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (10:15)
 - notebooks/text_regression.ipynb (10:15)

duplicated block id: 1390
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (80:85)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1391
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (73:78)
 - src/autotrain/cli/run_tabular.py (53:58)

duplicated block id: 1392
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (508:513)
 - src/autotrain/preprocessor/vision.py (293:298)

duplicated block id: 1393
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/generic/utils.py (181:199)
 - src/autotrain/trainers/text_classification/utils.py (159:177)

duplicated block id: 1394
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (353:358)
 - src/autotrain/preprocessor/text.py (473:478)

duplicated block id: 1395
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (269:274)
 - src/autotrain/project.py (355:360)

duplicated block id: 1396
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (62:67)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1397
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (220:225)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1398
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (508:513)
 - src/autotrain/preprocessor/vision.py (471:476)

duplicated block id: 1399
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (73:78)
 - src/autotrain/cli/run_token_classification.py (54:59)

duplicated block id: 1400
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (353:358)
 - src/autotrain/preprocessor/text.py (713:718)

duplicated block id: 1401
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (269:274)
 - src/autotrain/project.py (291:296)

duplicated block id: 1402
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (72:78)
 - src/autotrain/cli/run_token_classification.py (73:79)

duplicated block id: 1403
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (320:325)
 - src/autotrain/dataset.py (526:531)

duplicated block id: 1404
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (116:121)
 - src/autotrain/project.py (151:156)

duplicated block id: 1405
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (121:126)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1406
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (232:240)
 - src/autotrain/trainers/sent_transformers/__main__.py (241:249)

duplicated block id: 1407
size: 6 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (1:6)
 - notebooks/text_classification.ipynb (1:6)

duplicated block id: 1408
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/params.py (67:72)
 - src/autotrain/trainers/text_classification/params.py (50:55)

duplicated block id: 1409
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/token_classification/__main__.py (84:89)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1410
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (495:500)
 - src/autotrain/preprocessor/text.py (739:744)

duplicated block id: 1411
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (301:307)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1412
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (53:58)
 - src/autotrain/cli/run_spacerunner.py (73:78)

duplicated block id: 1413
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/__main__.py (58:63)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1414
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (528:533)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1415
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (81:87)
 - src/autotrain/cli/run_sent_tranformers.py (72:78)

duplicated block id: 1416
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (72:78)
 - src/autotrain/cli/run_tabular.py (72:78)

duplicated block id: 1417
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:78)
 - src/autotrain/cli/run_llm.py (81:87)

duplicated block id: 1418
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (226:234)
 - src/autotrain/trainers/sent_transformers/__main__.py (241:249)

duplicated block id: 1419
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/api_routes.py (69:74)
 - src/autotrain/app/params.py (555:560)

duplicated block id: 1420
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (424:429)
 - src/autotrain/app/params.py (441:446)

duplicated block id: 1421
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (209:214)
 - src/autotrain/dataset.py (526:531)

duplicated block id: 1422
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (368:373)
 - src/autotrain/dataset.py (468:473)

duplicated block id: 1423
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (88:93)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1424
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (74:79)
 - src/autotrain/project.py (116:121)

duplicated block id: 1425
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/static/scripts/utils.js (160:168)
 - src/autotrain/app/static/scripts/utils.js (171:179)

duplicated block id: 1426
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/utils.py (11:16)
 - src/autotrain/trainers/text_regression/utils.py (8:13)

duplicated block id: 1427
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (264:269)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1428
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (89:94)
 - src/autotrain/trainers/clm/train_clm_reward.py (75:80)

duplicated block id: 1429
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (138:144)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1430
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (83:88)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1431
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (551:556)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1432
size: 6 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (1:6)
 - notebooks/text_classification.ipynb (1:6)

duplicated block id: 1433
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/params.py (67:72)
 - src/autotrain/trainers/text_regression/params.py (50:55)

duplicated block id: 1434
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/__main__.py (66:71)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1435
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (53:58)
 - src/autotrain/cli/run_spacerunner.py (73:78)

duplicated block id: 1436
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/templates/error.html (14:25)
 - src/autotrain/app/templates/login.html (22:32)

duplicated block id: 1437
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_sft.py (30:35)
 - src/autotrain/trainers/clm/utils.py (983:988)

duplicated block id: 1438
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (63:68)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1439
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (77:82)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1440
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_sent_tranformers.py (53:58)
 - src/autotrain/cli/run_spacerunner.py (73:78)

duplicated block id: 1441
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/callbacks.py (28:33)
 - src/autotrain/trainers/clm/callbacks.py (48:53)

duplicated block id: 1442
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (65:70)
 - src/autotrain/preprocessor/text.py (739:744)

duplicated block id: 1443
size: 6 cleaned lines of code
in 2 files:
 - colabs/AutoTrain.ipynb (15:20)
 - colabs/image_classification.ipynb (3:8)

duplicated block id: 1444
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/sent_transformers/params.py (53:58)
 - src/autotrain/trainers/seq2seq/params.py (67:72)

duplicated block id: 1445
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (301:307)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1446
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (498:503)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1447
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (438:443)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1448
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (245:250)
 - src/autotrain/app/models.py (255:260)

duplicated block id: 1449
size: 6 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (10:15)
 - notebooks/text_classification.ipynb (10:15)

duplicated block id: 1450
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_classification.py (72:78)
 - src/autotrain/cli/run_tabular.py (72:78)

duplicated block id: 1451
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (420:425)
 - src/autotrain/dataset.py (526:531)

duplicated block id: 1452
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (121:126)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1453
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (823:828)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1454
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (615:620)
 - src/autotrain/preprocessor/vlm.py (104:109)

duplicated block id: 1455
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/__main__.py (61:66)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1456
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (81:87)
 - src/autotrain/cli/run_text_regression.py (73:79)

duplicated block id: 1457
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (164:171)
 - src/autotrain/trainers/seq2seq/__main__.py (141:148)

duplicated block id: 1458
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_orpo.py (29:34)
 - src/autotrain/trainers/clm/train_clm_reward.py (75:80)

duplicated block id: 1459
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (438:443)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1460
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (321:326)
 - src/autotrain/app/params.py (337:342)

duplicated block id: 1461
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (158:163)
 - src/autotrain/dataset.py (368:373)

duplicated block id: 1462
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (264:269)
 - src/autotrain/preprocessor/vision.py (409:415)

duplicated block id: 1463
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/extractive_question_answering/__main__.py (85:90)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1464
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (72:78)
 - src/autotrain/cli/run_tabular.py (72:78)

duplicated block id: 1465
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (264:269)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1466
size: 6 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (3:8)
 - notebooks/text_classification.ipynb (85:90)

duplicated block id: 1467
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (72:77)
 - src/autotrain/preprocessor/text.py (739:744)

duplicated block id: 1468
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:78)
 - src/autotrain/cli/run_tabular.py (72:78)

duplicated block id: 1469
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (72:78)
 - src/autotrain/cli/run_vlm.py (70:76)

duplicated block id: 1470
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_object_detection.py (72:78)
 - src/autotrain/cli/run_tabular.py (72:78)

duplicated block id: 1471
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (264:269)
 - src/autotrain/preprocessor/vision.py (184:190)

duplicated block id: 1472
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (57:62)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1473
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/seq2seq/params.py (67:72)
 - src/autotrain/trainers/token_classification/params.py (50:55)

duplicated block id: 1474
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (81:87)
 - src/autotrain/cli/run_text_classification.py (73:79)

duplicated block id: 1475
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/ui_routes.py (21:26)
 - src/autotrain/project.py (16:21)

duplicated block id: 1476
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/api_routes.py (51:56)
 - src/autotrain/app/params.py (539:544)

duplicated block id: 1477
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (81:87)
 - src/autotrain/cli/run_tabular.py (72:78)

duplicated block id: 1478
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (337:342)
 - src/autotrain/app/params.py (357:362)

duplicated block id: 1479
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/vlm/train_vlm_generic.py (35:40)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (54:59)

duplicated block id: 1480
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (140:145)
 - src/autotrain/preprocessor/vlm.py (104:109)

duplicated block id: 1481
size: 6 cleaned lines of code
in 2 files:
 - colabs/AutoTrain_LLM.ipynb (30:35)
 - colabs/AutoTrain_LLM.ipynb (117:122)

duplicated block id: 1482
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (138:144)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1483
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (407:412)
 - src/autotrain/app/params.py (441:446)

duplicated block id: 1484
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (337:342)
 - src/autotrain/app/params.py (390:395)

duplicated block id: 1485
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/utils.py (295:300)
 - src/autotrain/trainers/tabular/utils.py (331:336)

duplicated block id: 1486
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_orpo.py (30:35)
 - src/autotrain/trainers/clm/utils.py (983:988)

duplicated block id: 1487
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/models.py (356:361)
 - src/autotrain/app/models.py (368:373)

duplicated block id: 1488
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (49:54)
 - src/autotrain/preprocessor/text.py (713:718)

duplicated block id: 1489
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (615:620)
 - src/autotrain/preprocessor/vision.py (293:298)

duplicated block id: 1490
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_sft.py (30:35)
 - src/autotrain/trainers/vlm/utils.py (248:253)

duplicated block id: 1491
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (53:58)
 - src/autotrain/cli/run_spacerunner.py (73:78)

duplicated block id: 1492
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (49:54)
 - src/autotrain/preprocessor/text.py (587:592)

duplicated block id: 1493
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (676:681)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1494
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (72:78)
 - src/autotrain/cli/run_text_regression.py (73:79)

duplicated block id: 1495
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/params.py (50:55)
 - src/autotrain/trainers/seq2seq/params.py (67:72)

duplicated block id: 1496
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (615:620)
 - src/autotrain/preprocessor/vision.py (471:476)

duplicated block id: 1497
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_extractive_qa.py (72:78)
 - src/autotrain/cli/run_llm.py (81:87)

duplicated block id: 1498
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_image_regression.py (53:58)
 - src/autotrain/cli/run_spacerunner.py (73:78)

duplicated block id: 1499
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/tabular/__main__.py (197:202)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1500
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (49:54)
 - src/autotrain/preprocessor/text.py (353:358)

duplicated block id: 1501
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (676:681)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1502
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_seq2seq.py (51:56)
 - src/autotrain/cli/run_spacerunner.py (73:78)

duplicated block id: 1503
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (597:602)
 - src/autotrain/dataset.py (711:716)

duplicated block id: 1504
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (56:61)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1505
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (597:602)
 - src/autotrain/dataset.py (687:692)

duplicated block id: 1506
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (597:602)
 - src/autotrain/dataset.py (669:674)

duplicated block id: 1507
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (90:95)
 - src/autotrain/trainers/vlm/utils.py (248:253)

duplicated block id: 1508
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (66:71)
 - src/autotrain/commands.py (453:458)

duplicated block id: 1509
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/params.py (49:54)
 - src/autotrain/trainers/seq2seq/params.py (67:72)

duplicated block id: 1510
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (121:126)
 - src/autotrain/preprocessor/vision.py (409:415)

duplicated block id: 1511
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/commands.py (66:71)
 - src/autotrain/commands.py (377:382)

duplicated block id: 1512
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (203:208)
 - src/autotrain/preprocessor/text.py (739:744)

duplicated block id: 1513
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_regression/__main__.py (216:224)
 - src/autotrain/trainers/sent_transformers/__main__.py (241:249)

duplicated block id: 1514
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (138:144)
 - src/autotrain/preprocessor/vision.py (184:190)

duplicated block id: 1515
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_classification/dataset.py (25:30)
 - src/autotrain/trainers/text_regression/dataset.py (26:31)

duplicated block id: 1516
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_orpo.py (30:35)
 - src/autotrain/trainers/vlm/utils.py (248:253)

duplicated block id: 1517
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/app/params.py (531:536)
 - src/autotrain/app/params.py (539:544)

duplicated block id: 1518
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (218:224)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1519
size: 6 cleaned lines of code
in 2 files:
 - colabs/image_classification.ipynb (3:8)
 - colabs/image_classification.ipynb (39:44)

duplicated block id: 1520
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (138:144)
 - src/autotrain/preprocessor/vision.py (409:415)

duplicated block id: 1521
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (291:296)
 - src/autotrain/project.py (355:360)

duplicated block id: 1522
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/object_detection/__main__.py (226:234)
 - src/autotrain/trainers/seq2seq/__main__.py (269:277)

duplicated block id: 1523
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_spacerunner.py (73:78)
 - src/autotrain/cli/run_text_regression.py (54:59)

duplicated block id: 1524
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/dataset.py (257:262)
 - src/autotrain/dataset.py (368:373)

duplicated block id: 1525
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (62:67)
 - src/autotrain/cli/run_spacerunner.py (73:78)

duplicated block id: 1526
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/vision.py (489:495)
 - src/autotrain/preprocessor/vlm.py (184:190)

duplicated block id: 1527
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/tabular.py (121:126)
 - src/autotrain/preprocessor/vision.py (184:190)

duplicated block id: 1528
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (83:88)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1529
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (218:224)
 - src/autotrain/preprocessor/vision.py (409:415)

duplicated block id: 1530
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (551:556)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1531
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_dpo.py (65:70)
 - src/autotrain/trainers/clm/train_clm_reward.py (65:70)

duplicated block id: 1532
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (88:94)
 - src/autotrain/preprocessor/text.py (772:778)

duplicated block id: 1533
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/callbacks.py (11:16)
 - src/autotrain/trainers/clm/callbacks.py (28:33)

duplicated block id: 1534
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (637:642)
 - src/autotrain/trainers/clm/utils.py (645:650)

duplicated block id: 1535
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (823:828)
 - src/autotrain/preprocessor/vision.py (559:565)

duplicated block id: 1536
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/callbacks.py (11:16)
 - src/autotrain/trainers/clm/callbacks.py (48:53)

duplicated block id: 1537
size: 6 cleaned lines of code
in 2 files:
 - notebooks/text_classification.ipynb (1:6)
 - notebooks/text_regression.ipynb (1:6)

duplicated block id: 1538
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (218:224)
 - src/autotrain/preprocessor/vision.py (184:190)

duplicated block id: 1539
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/project.py (182:187)
 - src/autotrain/project.py (217:222)

duplicated block id: 1540
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_tabular.py (72:78)
 - src/autotrain/cli/run_text_classification.py (73:79)

duplicated block id: 1541
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (218:224)
 - src/autotrain/preprocessor/vlm.py (218:224)

duplicated block id: 1542
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (508:513)
 - src/autotrain/preprocessor/vlm.py (104:109)

duplicated block id: 1543
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/image_classification/__main__.py (77:82)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (58:63)

duplicated block id: 1544
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/cli/run_llm.py (81:87)
 - src/autotrain/cli/run_token_classification.py (73:79)

duplicated block id: 1545
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (823:828)
 - src/autotrain/preprocessor/vision.py (184:190)

duplicated block id: 1546
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/text_regression/__main__.py (61:66)
 - src/autotrain/trainers/vlm/train_vlm_generic.py (39:44)

duplicated block id: 1547
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/train_clm_reward.py (75:80)
 - src/autotrain/trainers/clm/train_clm_sft.py (29:34)

duplicated block id: 1548
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (294:313)
 - src/autotrain/trainers/text_classification/utils.py (159:177)

duplicated block id: 1549
size: 6 cleaned lines of code
in 2 files:
 - notebooks/llm_finetuning.ipynb (1:6)
 - notebooks/text_regression.ipynb (1:6)

duplicated block id: 1550
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/trainers/clm/utils.py (294:313)
 - src/autotrain/trainers/generic/utils.py (181:199)

duplicated block id: 1551
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (770:775)
 - src/autotrain/preprocessor/vlm.py (104:109)

duplicated block id: 1552
size: 6 cleaned lines of code
in 2 files:
 - src/autotrain/preprocessor/text.py (823:828)
 - src/autotrain/preprocessor/vision.py (409:415)