Hugging Face's logo

xshubhamx
/
bart-large

Text Classification
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xshubhamx commited on
Commit
d21f2af
•
1 Parent(s): 4bf4202

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. training_checkpoints/checkpoint-41104/config.json +99 -0
  2. training_checkpoints/checkpoint-41104/merges.txt +0 -0
  3. training_checkpoints/checkpoint-41104/model.safetensors +3 -0
  4. training_checkpoints/checkpoint-41104/optimizer.pt +3 -0
  5. training_checkpoints/checkpoint-41104/rng_state.pth +3 -0
  6. training_checkpoints/checkpoint-41104/scheduler.pt +3 -0
  7. training_checkpoints/checkpoint-41104/special_tokens_map.json +15 -0
  8. training_checkpoints/checkpoint-41104/tokenizer.json +0 -0
  9. training_checkpoints/checkpoint-41104/tokenizer_config.json +57 -0
  10. training_checkpoints/checkpoint-41104/trainer_state.json +863 -0
  11. training_checkpoints/checkpoint-41104/training_args.bin +3 -0
  12. training_checkpoints/checkpoint-41104/vocab.json +0 -0
training_checkpoints/checkpoint-41104/config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForSequenceClassification"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "Issue",
32
+ "1": "Court Discourse",
33
+ "2": "Conclusion",
34
+ "3": "Precedent Analysis",
35
+ "4": "Section Analysis",
36
+ "5": "Argument by Petitioner",
37
+ "6": "Fact",
38
+ "7": "Argument by Respondent",
39
+ "8": "Ratio",
40
+ "9": "Appellant",
41
+ "10": "Respondent",
42
+ "11": "Argument by Appellant",
43
+ "12": "Petitioner",
44
+ "13": "Judge",
45
+ "14": "Argument by Defendant"
46
+ },
47
+ "init_std": 0.02,
48
+ "is_encoder_decoder": true,
49
+ "label2id": {
50
+ "Appellant": 9,
51
+ "Argument by Appellant": 11,
52
+ "Argument by Defendant": 14,
53
+ "Argument by Petitioner": 5,
54
+ "Argument by Respondent": 7,
55
+ "Conclusion": 2,
56
+ "Court Discourse": 1,
57
+ "Fact": 6,
58
+ "Issue": 0,
59
+ "Judge": 13,
60
+ "Petitioner": 12,
61
+ "Precedent Analysis": 3,
62
+ "Ratio": 8,
63
+ "Respondent": 10,
64
+ "Section Analysis": 4
65
+ },
66
+ "max_position_embeddings": 1024,
67
+ "model_type": "bart",
68
+ "no_repeat_ngram_size": 3,
69
+ "normalize_before": false,
70
+ "num_beams": 4,
71
+ "num_hidden_layers": 12,
72
+ "pad_token_id": 1,
73
+ "problem_type": "single_label_classification",
74
+ "scale_embedding": false,
75
+ "task_specific_params": {
76
+ "summarization": {
77
+ "length_penalty": 1.0,
78
+ "max_length": 128,
79
+ "min_length": 12,
80
+ "num_beams": 4
81
+ },
82
+ "summarization_cnn": {
83
+ "length_penalty": 2.0,
84
+ "max_length": 142,
85
+ "min_length": 56,
86
+ "num_beams": 4
87
+ },
88
+ "summarization_xsum": {
89
+ "length_penalty": 1.0,
90
+ "max_length": 62,
91
+ "min_length": 11,
92
+ "num_beams": 6
93
+ }
94
+ },
95
+ "torch_dtype": "float32",
96
+ "transformers_version": "4.35.2",
97
+ "use_cache": true,
98
+ "vocab_size": 50265
99
+ }
training_checkpoints/checkpoint-41104/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_checkpoints/checkpoint-41104/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7357504f0a71da87a36c85c294470d7cdfa7eb7a10c5407b0305f5e05182f018
3
+ size 1629486164
training_checkpoints/checkpoint-41104/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc11abf1e3694e80ca9e84e9354e345c32716f29a7c52fda38cd88ece062d2db
3
+ size 3259283099
training_checkpoints/checkpoint-41104/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7931aca3d2ceb56ddb0b99ab039075ab89be75afaae45289cfd240677db8e53f
3
+ size 14244
training_checkpoints/checkpoint-41104/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2954745f55a9bbb4654f35c0364574a57fd6ebd0d2e7b165172b563765f4a76
3
+ size 1064
training_checkpoints/checkpoint-41104/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
training_checkpoints/checkpoint-41104/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training_checkpoints/checkpoint-41104/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_checkpoints/checkpoint-41104/trainer_state.json ADDED
@@ -0,0 +1,863 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7295133712588342,
3
+ "best_model_checkpoint": "bart-large/checkpoint-41104",
4
+ "epoch": 16.0,
5
+ "eval_steps": 500,
6
+ "global_step": 41104,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.19,
13
+ "learning_rate": 4.967886337096146e-05,
14
+ "loss": 2.0273,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.39,
19
+ "learning_rate": 4.9354482937589206e-05,
20
+ "loss": 1.4983,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.58,
25
+ "learning_rate": 4.903140002595043e-05,
26
+ "loss": 1.4727,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.78,
31
+ "learning_rate": 4.870701959257818e-05,
32
+ "loss": 1.3945,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.97,
37
+ "learning_rate": 4.8383287920072665e-05,
38
+ "loss": 1.1685,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.0,
43
+ "eval_accuracy": 0.6847405112316034,
44
+ "eval_f1_macro": 0.4296023125768376,
45
+ "eval_f1_micro": 0.6847405112316034,
46
+ "eval_f1_weighted": 0.6471198955620663,
47
+ "eval_loss": 1.258675456047058,
48
+ "eval_macro_fpr": 0.03310536835500512,
49
+ "eval_macro_sensitivity": 0.47197476920519743,
50
+ "eval_macro_specificity": 0.9759825618150952,
51
+ "eval_precision": 0.6359796796355663,
52
+ "eval_precision_macro": 0.4175869918662546,
53
+ "eval_recall": 0.6847405112316034,
54
+ "eval_recall_macro": 0.47197476920519743,
55
+ "eval_runtime": 166.2079,
56
+ "eval_samples_per_second": 7.767,
57
+ "eval_steps_per_second": 3.887,
58
+ "eval_weighted_fpr": 0.03183916138621607,
59
+ "eval_weighted_sensitivity": 0.6847405112316034,
60
+ "eval_weighted_specificity": 0.9549979159948256,
61
+ "step": 2569
62
+ },
63
+ {
64
+ "epoch": 1.17,
65
+ "learning_rate": 4.80589074867004e-05,
66
+ "loss": 1.2814,
67
+ "step": 3000
68
+ },
69
+ {
70
+ "epoch": 1.36,
71
+ "learning_rate": 4.7734527053328146e-05,
72
+ "loss": 1.2579,
73
+ "step": 3500
74
+ },
75
+ {
76
+ "epoch": 1.56,
77
+ "learning_rate": 4.741079538082263e-05,
78
+ "loss": 1.246,
79
+ "step": 4000
80
+ },
81
+ {
82
+ "epoch": 1.75,
83
+ "learning_rate": 4.708641494745037e-05,
84
+ "loss": 1.0685,
85
+ "step": 4500
86
+ },
87
+ {
88
+ "epoch": 1.95,
89
+ "learning_rate": 4.676203451407811e-05,
90
+ "loss": 1.1965,
91
+ "step": 5000
92
+ },
93
+ {
94
+ "epoch": 2.0,
95
+ "eval_accuracy": 0.6638264910921766,
96
+ "eval_f1_macro": 0.3954707529203812,
97
+ "eval_f1_micro": 0.6638264910921766,
98
+ "eval_f1_weighted": 0.6467821848395333,
99
+ "eval_loss": 1.1623183488845825,
100
+ "eval_macro_fpr": 0.03422706134984445,
101
+ "eval_macro_sensitivity": 0.4261017849773373,
102
+ "eval_macro_specificity": 0.9752839802406176,
103
+ "eval_precision": 0.6943370263824146,
104
+ "eval_precision_macro": 0.45636498568634104,
105
+ "eval_recall": 0.6638264910921766,
106
+ "eval_recall_macro": 0.4261017849773373,
107
+ "eval_runtime": 320.2013,
108
+ "eval_samples_per_second": 4.032,
109
+ "eval_steps_per_second": 2.017,
110
+ "eval_weighted_fpr": 0.03490990990990991,
111
+ "eval_weighted_sensitivity": 0.6638264910921766,
112
+ "eval_weighted_specificity": 0.9654332125170877,
113
+ "step": 5138
114
+ },
115
+ {
116
+ "epoch": 2.14,
117
+ "learning_rate": 4.643765408070585e-05,
118
+ "loss": 1.0697,
119
+ "step": 5500
120
+ },
121
+ {
122
+ "epoch": 2.34,
123
+ "learning_rate": 4.611327364733359e-05,
124
+ "loss": 1.1042,
125
+ "step": 6000
126
+ },
127
+ {
128
+ "epoch": 2.53,
129
+ "learning_rate": 4.578954197482808e-05,
130
+ "loss": 1.124,
131
+ "step": 6500
132
+ },
133
+ {
134
+ "epoch": 2.72,
135
+ "learning_rate": 4.546516154145582e-05,
136
+ "loss": 1.1449,
137
+ "step": 7000
138
+ },
139
+ {
140
+ "epoch": 2.92,
141
+ "learning_rate": 4.514078110808356e-05,
142
+ "loss": 1.189,
143
+ "step": 7500
144
+ },
145
+ {
146
+ "epoch": 3.0,
147
+ "eval_accuracy": 0.7234701781564679,
148
+ "eval_f1_macro": 0.5196282925085354,
149
+ "eval_f1_micro": 0.7234701781564679,
150
+ "eval_f1_weighted": 0.7031290239201134,
151
+ "eval_loss": 1.357356309890747,
152
+ "eval_macro_fpr": 0.027073020005110214,
153
+ "eval_macro_sensitivity": 0.5527845991176076,
154
+ "eval_macro_specificity": 0.9790845865453512,
155
+ "eval_precision": 0.7219921821470505,
156
+ "eval_precision_macro": 0.5413306235947684,
157
+ "eval_recall": 0.7234701781564679,
158
+ "eval_recall_macro": 0.5527845991176076,
159
+ "eval_runtime": 290.3268,
160
+ "eval_samples_per_second": 4.447,
161
+ "eval_steps_per_second": 2.225,
162
+ "eval_weighted_fpr": 0.026576341844710787,
163
+ "eval_weighted_sensitivity": 0.7234701781564679,
164
+ "eval_weighted_specificity": 0.9627986200238022,
165
+ "step": 7707
166
+ },
167
+ {
168
+ "epoch": 3.11,
169
+ "learning_rate": 4.481704943557805e-05,
170
+ "loss": 0.9829,
171
+ "step": 8000
172
+ },
173
+ {
174
+ "epoch": 3.31,
175
+ "learning_rate": 4.4492669002205786e-05,
176
+ "loss": 0.9172,
177
+ "step": 8500
178
+ },
179
+ {
180
+ "epoch": 3.5,
181
+ "learning_rate": 4.416828856883353e-05,
182
+ "loss": 0.9911,
183
+ "step": 9000
184
+ },
185
+ {
186
+ "epoch": 3.7,
187
+ "learning_rate": 4.384390813546127e-05,
188
+ "loss": 0.9934,
189
+ "step": 9500
190
+ },
191
+ {
192
+ "epoch": 3.89,
193
+ "learning_rate": 4.351952770208901e-05,
194
+ "loss": 1.0127,
195
+ "step": 10000
196
+ },
197
+ {
198
+ "epoch": 4.0,
199
+ "eval_accuracy": 0.7668474051123161,
200
+ "eval_f1_macro": 0.6233324855492023,
201
+ "eval_f1_micro": 0.7668474051123161,
202
+ "eval_f1_weighted": 0.7569127961671379,
203
+ "eval_loss": 1.4684507846832275,
204
+ "eval_macro_fpr": 0.022371017412255348,
205
+ "eval_macro_sensitivity": 0.6201844239757082,
206
+ "eval_macro_specificity": 0.9821444214871504,
207
+ "eval_precision": 0.7584494799967734,
208
+ "eval_precision_macro": 0.6670503035550461,
209
+ "eval_recall": 0.7668474051123161,
210
+ "eval_recall_macro": 0.6201844239757082,
211
+ "eval_runtime": 296.0277,
212
+ "eval_samples_per_second": 4.361,
213
+ "eval_steps_per_second": 2.182,
214
+ "eval_weighted_fpr": 0.021255561047948592,
215
+ "eval_weighted_sensitivity": 0.7668474051123161,
216
+ "eval_weighted_specificity": 0.9653189171949409,
217
+ "step": 10276
218
+ },
219
+ {
220
+ "epoch": 4.09,
221
+ "learning_rate": 4.3196444790450244e-05,
222
+ "loss": 0.9926,
223
+ "step": 10500
224
+ },
225
+ {
226
+ "epoch": 4.28,
227
+ "learning_rate": 4.287206435707798e-05,
228
+ "loss": 1.1046,
229
+ "step": 11000
230
+ },
231
+ {
232
+ "epoch": 4.48,
233
+ "learning_rate": 4.2547683923705725e-05,
234
+ "loss": 0.8572,
235
+ "step": 11500
236
+ },
237
+ {
238
+ "epoch": 4.67,
239
+ "learning_rate": 4.222330349033346e-05,
240
+ "loss": 0.8623,
241
+ "step": 12000
242
+ },
243
+ {
244
+ "epoch": 4.87,
245
+ "learning_rate": 4.1898923056961206e-05,
246
+ "loss": 1.0205,
247
+ "step": 12500
248
+ },
249
+ {
250
+ "epoch": 5.0,
251
+ "eval_accuracy": 0.7668474051123161,
252
+ "eval_f1_macro": 0.6732447131282889,
253
+ "eval_f1_micro": 0.7668474051123161,
254
+ "eval_f1_weighted": 0.7643097206437405,
255
+ "eval_loss": 1.4232454299926758,
256
+ "eval_macro_fpr": 0.021536303183803004,
257
+ "eval_macro_sensitivity": 0.6871530786461169,
258
+ "eval_macro_specificity": 0.9827017397959152,
259
+ "eval_precision": 0.7710604143740172,
260
+ "eval_precision_macro": 0.6764905863857386,
261
+ "eval_recall": 0.7668474051123161,
262
+ "eval_recall_macro": 0.6871530786461169,
263
+ "eval_runtime": 288.8657,
264
+ "eval_samples_per_second": 4.469,
265
+ "eval_steps_per_second": 2.236,
266
+ "eval_weighted_fpr": 0.021255561047948592,
267
+ "eval_weighted_sensitivity": 0.7668474051123161,
268
+ "eval_weighted_specificity": 0.9736786918264111,
269
+ "step": 12845
270
+ },
271
+ {
272
+ "epoch": 5.06,
273
+ "learning_rate": 4.1574542623588944e-05,
274
+ "loss": 0.888,
275
+ "step": 13000
276
+ },
277
+ {
278
+ "epoch": 5.25,
279
+ "learning_rate": 4.125016219021669e-05,
280
+ "loss": 0.7739,
281
+ "step": 13500
282
+ },
283
+ {
284
+ "epoch": 5.45,
285
+ "learning_rate": 4.0925781756844425e-05,
286
+ "loss": 0.9572,
287
+ "step": 14000
288
+ },
289
+ {
290
+ "epoch": 5.64,
291
+ "learning_rate": 4.060140132347217e-05,
292
+ "loss": 0.8296,
293
+ "step": 14500
294
+ },
295
+ {
296
+ "epoch": 5.84,
297
+ "learning_rate": 4.0277020890099906e-05,
298
+ "loss": 0.7927,
299
+ "step": 15000
300
+ },
301
+ {
302
+ "epoch": 6.0,
303
+ "eval_accuracy": 0.7428350116189001,
304
+ "eval_f1_macro": 0.6107557579512543,
305
+ "eval_f1_micro": 0.7428350116189001,
306
+ "eval_f1_weighted": 0.729163687728552,
307
+ "eval_loss": 1.5677722692489624,
308
+ "eval_macro_fpr": 0.024790721920250693,
309
+ "eval_macro_sensitivity": 0.6332883060366477,
310
+ "eval_macro_specificity": 0.9807865890062467,
311
+ "eval_precision": 0.7451349692354797,
312
+ "eval_precision_macro": 0.6488747447950202,
313
+ "eval_recall": 0.7428350116189001,
314
+ "eval_recall_macro": 0.6332883060366477,
315
+ "eval_runtime": 291.455,
316
+ "eval_samples_per_second": 4.429,
317
+ "eval_steps_per_second": 2.216,
318
+ "eval_weighted_fpr": 0.024131414449774676,
319
+ "eval_weighted_sensitivity": 0.7428350116189001,
320
+ "eval_weighted_specificity": 0.9689638234747989,
321
+ "step": 15414
322
+ },
323
+ {
324
+ "epoch": 6.03,
325
+ "learning_rate": 3.995264045672765e-05,
326
+ "loss": 0.8196,
327
+ "step": 15500
328
+ },
329
+ {
330
+ "epoch": 6.23,
331
+ "learning_rate": 3.9628260023355394e-05,
332
+ "loss": 0.6989,
333
+ "step": 16000
334
+ },
335
+ {
336
+ "epoch": 6.42,
337
+ "learning_rate": 3.930387958998313e-05,
338
+ "loss": 0.7149,
339
+ "step": 16500
340
+ },
341
+ {
342
+ "epoch": 6.62,
343
+ "learning_rate": 3.8979499156610875e-05,
344
+ "loss": 0.7459,
345
+ "step": 17000
346
+ },
347
+ {
348
+ "epoch": 6.81,
349
+ "learning_rate": 3.865511872323861e-05,
350
+ "loss": 0.7701,
351
+ "step": 17500
352
+ },
353
+ {
354
+ "epoch": 7.0,
355
+ "eval_accuracy": 0.7467079783113865,
356
+ "eval_f1_macro": 0.6583574261846535,
357
+ "eval_f1_micro": 0.7467079783113864,
358
+ "eval_f1_weighted": 0.7399270546375634,
359
+ "eval_loss": 1.7336597442626953,
360
+ "eval_macro_fpr": 0.023989153033760927,
361
+ "eval_macro_sensitivity": 0.6536163621805403,
362
+ "eval_macro_specificity": 0.9809809544706846,
363
+ "eval_precision": 0.759972067375925,
364
+ "eval_precision_macro": 0.6862877418910309,
365
+ "eval_recall": 0.7467079783113865,
366
+ "eval_recall_macro": 0.6536163621805403,
367
+ "eval_runtime": 289.659,
368
+ "eval_samples_per_second": 4.457,
369
+ "eval_steps_per_second": 2.23,
370
+ "eval_weighted_fpr": 0.023656225132026334,
371
+ "eval_weighted_sensitivity": 0.7467079783113865,
372
+ "eval_weighted_specificity": 0.9680063387488825,
373
+ "step": 17983
374
+ },
375
+ {
376
+ "epoch": 7.01,
377
+ "learning_rate": 3.83313870507331e-05,
378
+ "loss": 0.826,
379
+ "step": 18000
380
+ },
381
+ {
382
+ "epoch": 7.2,
383
+ "learning_rate": 3.800765537822758e-05,
384
+ "loss": 0.6803,
385
+ "step": 18500
386
+ },
387
+ {
388
+ "epoch": 7.4,
389
+ "learning_rate": 3.7683274944855327e-05,
390
+ "loss": 0.6779,
391
+ "step": 19000
392
+ },
393
+ {
394
+ "epoch": 7.59,
395
+ "learning_rate": 3.7358894511483064e-05,
396
+ "loss": 0.616,
397
+ "step": 19500
398
+ },
399
+ {
400
+ "epoch": 7.79,
401
+ "learning_rate": 3.703451407811081e-05,
402
+ "loss": 0.608,
403
+ "step": 20000
404
+ },
405
+ {
406
+ "epoch": 7.98,
407
+ "learning_rate": 3.671013364473855e-05,
408
+ "loss": 0.584,
409
+ "step": 20500
410
+ },
411
+ {
412
+ "epoch": 8.0,
413
+ "eval_accuracy": 0.7691711851278079,
414
+ "eval_f1_macro": 0.6979809418287721,
415
+ "eval_f1_micro": 0.7691711851278079,
416
+ "eval_f1_weighted": 0.7682883483181749,
417
+ "eval_loss": 1.6188185214996338,
418
+ "eval_macro_fpr": 0.021432185448306138,
419
+ "eval_macro_sensitivity": 0.7065204224528159,
420
+ "eval_macro_specificity": 0.9826542042505794,
421
+ "eval_precision": 0.7766202006674988,
422
+ "eval_precision_macro": 0.6979437669181305,
423
+ "eval_recall": 0.7691711851278079,
424
+ "eval_recall_macro": 0.7065204224528159,
425
+ "eval_runtime": 303.6709,
426
+ "eval_samples_per_second": 4.251,
427
+ "eval_steps_per_second": 2.127,
428
+ "eval_weighted_fpr": 0.020985915492957745,
429
+ "eval_weighted_sensitivity": 0.7691711851278079,
430
+ "eval_weighted_specificity": 0.9706418786308822,
431
+ "step": 20552
432
+ },
433
+ {
434
+ "epoch": 8.17,
435
+ "learning_rate": 3.638575321136629e-05,
436
+ "loss": 0.5266,
437
+ "step": 21000
438
+ },
439
+ {
440
+ "epoch": 8.37,
441
+ "learning_rate": 3.606137277799403e-05,
442
+ "loss": 0.6717,
443
+ "step": 21500
444
+ },
445
+ {
446
+ "epoch": 8.56,
447
+ "learning_rate": 3.573699234462177e-05,
448
+ "loss": 0.5474,
449
+ "step": 22000
450
+ },
451
+ {
452
+ "epoch": 8.76,
453
+ "learning_rate": 3.5412611911249514e-05,
454
+ "loss": 0.638,
455
+ "step": 22500
456
+ },
457
+ {
458
+ "epoch": 8.95,
459
+ "learning_rate": 3.5088880238743996e-05,
460
+ "loss": 0.5659,
461
+ "step": 23000
462
+ },
463
+ {
464
+ "epoch": 9.0,
465
+ "eval_accuracy": 0.7598760650658405,
466
+ "eval_f1_macro": 0.6728187845754294,
467
+ "eval_f1_micro": 0.7598760650658405,
468
+ "eval_f1_weighted": 0.7542471407266271,
469
+ "eval_loss": 1.6982707977294922,
470
+ "eval_macro_fpr": 0.02271263520390573,
471
+ "eval_macro_sensitivity": 0.680403785625184,
472
+ "eval_macro_specificity": 0.9819588600237938,
473
+ "eval_precision": 0.766529422163196,
474
+ "eval_precision_macro": 0.7000337979719602,
475
+ "eval_recall": 0.7598760650658405,
476
+ "eval_recall_macro": 0.680403785625184,
477
+ "eval_runtime": 286.113,
478
+ "eval_samples_per_second": 4.512,
479
+ "eval_steps_per_second": 2.258,
480
+ "eval_weighted_fpr": 0.02207348333808032,
481
+ "eval_weighted_sensitivity": 0.7598760650658405,
482
+ "eval_weighted_specificity": 0.9695068352910698,
483
+ "step": 23121
484
+ },
485
+ {
486
+ "epoch": 9.15,
487
+ "learning_rate": 3.476449980537174e-05,
488
+ "loss": 0.5062,
489
+ "step": 23500
490
+ },
491
+ {
492
+ "epoch": 9.34,
493
+ "learning_rate": 3.4440119371999484e-05,
494
+ "loss": 0.4485,
495
+ "step": 24000
496
+ },
497
+ {
498
+ "epoch": 9.54,
499
+ "learning_rate": 3.411573893862722e-05,
500
+ "loss": 0.6239,
501
+ "step": 24500
502
+ },
503
+ {
504
+ "epoch": 9.73,
505
+ "learning_rate": 3.379200726612171e-05,
506
+ "loss": 0.6764,
507
+ "step": 25000
508
+ },
509
+ {
510
+ "epoch": 9.93,
511
+ "learning_rate": 3.3467626832749447e-05,
512
+ "loss": 0.7021,
513
+ "step": 25500
514
+ },
515
+ {
516
+ "epoch": 10.0,
517
+ "eval_accuracy": 0.7699457784663052,
518
+ "eval_f1_macro": 0.6953722525071192,
519
+ "eval_f1_micro": 0.7699457784663051,
520
+ "eval_f1_weighted": 0.7634449085212252,
521
+ "eval_loss": 1.6445409059524536,
522
+ "eval_macro_fpr": 0.022344139928734137,
523
+ "eval_macro_sensitivity": 0.6856644071349105,
524
+ "eval_macro_specificity": 0.9820521636968861,
525
+ "eval_precision": 0.7656296240571903,
526
+ "eval_precision_macro": 0.7143810783711486,
527
+ "eval_recall": 0.7699457784663052,
528
+ "eval_recall_macro": 0.6856644071349105,
529
+ "eval_runtime": 288.6164,
530
+ "eval_samples_per_second": 4.473,
531
+ "eval_steps_per_second": 2.238,
532
+ "eval_weighted_fpr": 0.0208963624850489,
533
+ "eval_weighted_sensitivity": 0.7699457784663052,
534
+ "eval_weighted_specificity": 0.9608366769869864,
535
+ "step": 25690
536
+ },
537
+ {
538
+ "epoch": 10.12,
539
+ "learning_rate": 3.314324639937719e-05,
540
+ "loss": 0.6243,
541
+ "step": 26000
542
+ },
543
+ {
544
+ "epoch": 10.32,
545
+ "learning_rate": 3.281886596600493e-05,
546
+ "loss": 0.6952,
547
+ "step": 26500
548
+ },
549
+ {
550
+ "epoch": 10.51,
551
+ "learning_rate": 3.249448553263267e-05,
552
+ "loss": 0.7705,
553
+ "step": 27000
554
+ },
555
+ {
556
+ "epoch": 10.7,
557
+ "learning_rate": 3.217010509926041e-05,
558
+ "loss": 0.6582,
559
+ "step": 27500
560
+ },
561
+ {
562
+ "epoch": 10.9,
563
+ "learning_rate": 3.184572466588815e-05,
564
+ "loss": 0.6216,
565
+ "step": 28000
566
+ },
567
+ {
568
+ "epoch": 11.0,
569
+ "eval_accuracy": 0.7676219984508134,
570
+ "eval_f1_macro": 0.6786279912338002,
571
+ "eval_f1_micro": 0.7676219984508135,
572
+ "eval_f1_weighted": 0.7623696014823479,
573
+ "eval_loss": 1.656176209449768,
574
+ "eval_macro_fpr": 0.022330481497328643,
575
+ "eval_macro_sensitivity": 0.6775994679116955,
576
+ "eval_macro_specificity": 0.9821081561015023,
577
+ "eval_precision": 0.7633744243747118,
578
+ "eval_precision_macro": 0.6856198086678005,
579
+ "eval_recall": 0.7676219984508134,
580
+ "eval_recall_macro": 0.6775994679116955,
581
+ "eval_runtime": 286.2474,
582
+ "eval_samples_per_second": 4.51,
583
+ "eval_steps_per_second": 2.257,
584
+ "eval_weighted_fpr": 0.021165514321998025,
585
+ "eval_weighted_sensitivity": 0.7676219984508134,
586
+ "eval_weighted_specificity": 0.9640003430717192,
587
+ "step": 28259
588
+ },
589
+ {
590
+ "epoch": 11.09,
591
+ "learning_rate": 3.15213442325159e-05,
592
+ "loss": 0.716,
593
+ "step": 28500
594
+ },
595
+ {
596
+ "epoch": 11.29,
597
+ "learning_rate": 3.119826132087712e-05,
598
+ "loss": 0.5161,
599
+ "step": 29000
600
+ },
601
+ {
602
+ "epoch": 11.48,
603
+ "learning_rate": 3.087388088750487e-05,
604
+ "loss": 0.5121,
605
+ "step": 29500
606
+ },
607
+ {
608
+ "epoch": 11.68,
609
+ "learning_rate": 3.0549500454132604e-05,
610
+ "loss": 0.4694,
611
+ "step": 30000
612
+ },
613
+ {
614
+ "epoch": 11.87,
615
+ "learning_rate": 3.0225120020760352e-05,
616
+ "loss": 0.6408,
617
+ "step": 30500
618
+ },
619
+ {
620
+ "epoch": 12.0,
621
+ "eval_accuracy": 0.7668474051123161,
622
+ "eval_f1_macro": 0.6665576721498584,
623
+ "eval_f1_micro": 0.7668474051123161,
624
+ "eval_f1_weighted": 0.760771317042359,
625
+ "eval_loss": 1.6681983470916748,
626
+ "eval_macro_fpr": 0.022265012904393446,
627
+ "eval_macro_sensitivity": 0.6719396221017415,
628
+ "eval_macro_specificity": 0.9822275271243499,
629
+ "eval_precision": 0.7628875217070834,
630
+ "eval_precision_macro": 0.6705561723407458,
631
+ "eval_recall": 0.7668474051123161,
632
+ "eval_recall_macro": 0.6719396221017415,
633
+ "eval_runtime": 285.4858,
634
+ "eval_samples_per_second": 4.522,
635
+ "eval_steps_per_second": 2.263,
636
+ "eval_weighted_fpr": 0.021255561047948592,
637
+ "eval_weighted_sensitivity": 0.7668474051123161,
638
+ "eval_weighted_specificity": 0.9665655017529341,
639
+ "step": 30828
640
+ },
641
+ {
642
+ "epoch": 12.07,
643
+ "learning_rate": 2.990073958738809e-05,
644
+ "loss": 0.518,
645
+ "step": 31000
646
+ },
647
+ {
648
+ "epoch": 12.26,
649
+ "learning_rate": 2.9577007914882577e-05,
650
+ "loss": 0.3736,
651
+ "step": 31500
652
+ },
653
+ {
654
+ "epoch": 12.46,
655
+ "learning_rate": 2.9252627481510315e-05,
656
+ "loss": 0.4537,
657
+ "step": 32000
658
+ },
659
+ {
660
+ "epoch": 12.65,
661
+ "learning_rate": 2.892824704813806e-05,
662
+ "loss": 0.5017,
663
+ "step": 32500
664
+ },
665
+ {
666
+ "epoch": 12.85,
667
+ "learning_rate": 2.86038666147658e-05,
668
+ "loss": 0.523,
669
+ "step": 33000
670
+ },
671
+ {
672
+ "epoch": 13.0,
673
+ "eval_accuracy": 0.7652982184353214,
674
+ "eval_f1_macro": 0.7065905031891068,
675
+ "eval_f1_micro": 0.7652982184353214,
676
+ "eval_f1_weighted": 0.7533906957445078,
677
+ "eval_loss": 1.7727322578430176,
678
+ "eval_macro_fpr": 0.02260077041026825,
679
+ "eval_macro_sensitivity": 0.6934075054851363,
680
+ "eval_macro_specificity": 0.9820770689956008,
681
+ "eval_precision": 0.7674159154971928,
682
+ "eval_precision_macro": 0.8238391848974315,
683
+ "eval_recall": 0.7652982184353214,
684
+ "eval_recall_macro": 0.6934075054851363,
685
+ "eval_runtime": 282.4043,
686
+ "eval_samples_per_second": 4.571,
687
+ "eval_steps_per_second": 2.288,
688
+ "eval_weighted_fpr": 0.02143615139724089,
689
+ "eval_weighted_sensitivity": 0.7652982184353214,
690
+ "eval_weighted_specificity": 0.9658578164986904,
691
+ "step": 33397
692
+ },
693
+ {
694
+ "epoch": 13.04,
695
+ "learning_rate": 2.8280134942260284e-05,
696
+ "loss": 0.4438,
697
+ "step": 33500
698
+ },
699
+ {
700
+ "epoch": 13.23,
701
+ "learning_rate": 2.7955754508888028e-05,
702
+ "loss": 0.3444,
703
+ "step": 34000
704
+ },
705
+ {
706
+ "epoch": 13.43,
707
+ "learning_rate": 2.7631374075515765e-05,
708
+ "loss": 0.3751,
709
+ "step": 34500
710
+ },
711
+ {
712
+ "epoch": 13.62,
713
+ "learning_rate": 2.730699364214351e-05,
714
+ "loss": 0.3835,
715
+ "step": 35000
716
+ },
717
+ {
718
+ "epoch": 13.82,
719
+ "learning_rate": 2.6982613208771247e-05,
720
+ "loss": 0.3688,
721
+ "step": 35500
722
+ },
723
+ {
724
+ "epoch": 14.0,
725
+ "eval_accuracy": 0.7792408985282726,
726
+ "eval_f1_macro": 0.6960443476037717,
727
+ "eval_f1_micro": 0.7792408985282726,
728
+ "eval_f1_weighted": 0.7731313238375468,
729
+ "eval_loss": 1.840445876121521,
730
+ "eval_macro_fpr": 0.020905039822376084,
731
+ "eval_macro_sensitivity": 0.6920728491541597,
732
+ "eval_macro_specificity": 0.9831130726980227,
733
+ "eval_precision": 0.7787988846597094,
734
+ "eval_precision_macro": 0.7228983794850382,
735
+ "eval_recall": 0.7792408985282726,
736
+ "eval_recall_macro": 0.6920728491541597,
737
+ "eval_runtime": 289.1315,
738
+ "eval_samples_per_second": 4.465,
739
+ "eval_steps_per_second": 2.234,
740
+ "eval_weighted_fpr": 0.019834365648270583,
741
+ "eval_weighted_sensitivity": 0.7792408985282726,
742
+ "eval_weighted_specificity": 0.9674551919420677,
743
+ "step": 35966
744
+ },
745
+ {
746
+ "epoch": 14.01,
747
+ "learning_rate": 2.665823277539899e-05,
748
+ "loss": 0.3816,
749
+ "step": 36000
750
+ },
751
+ {
752
+ "epoch": 14.21,
753
+ "learning_rate": 2.633385234202673e-05,
754
+ "loss": 0.3767,
755
+ "step": 36500
756
+ },
757
+ {
758
+ "epoch": 14.4,
759
+ "learning_rate": 2.6009471908654472e-05,
760
+ "loss": 0.3859,
761
+ "step": 37000
762
+ },
763
+ {
764
+ "epoch": 14.6,
765
+ "learning_rate": 2.5685091475282212e-05,
766
+ "loss": 0.3066,
767
+ "step": 37500
768
+ },
769
+ {
770
+ "epoch": 14.79,
771
+ "learning_rate": 2.5360711041909953e-05,
772
+ "loss": 0.402,
773
+ "step": 38000
774
+ },
775
+ {
776
+ "epoch": 14.99,
777
+ "learning_rate": 2.5036330608537694e-05,
778
+ "loss": 0.2394,
779
+ "step": 38500
780
+ },
781
+ {
782
+ "epoch": 15.0,
783
+ "eval_accuracy": 0.7815646785437645,
784
+ "eval_f1_macro": 0.7230355619154473,
785
+ "eval_f1_micro": 0.7815646785437644,
786
+ "eval_f1_weighted": 0.7765270107358122,
787
+ "eval_loss": 1.7884501218795776,
788
+ "eval_macro_fpr": 0.020978052492475165,
789
+ "eval_macro_sensitivity": 0.711481022624799,
790
+ "eval_macro_specificity": 0.9829555212885144,
791
+ "eval_precision": 0.7809140931231899,
792
+ "eval_precision_macro": 0.7440727141565046,
793
+ "eval_recall": 0.7815646785437645,
794
+ "eval_recall_macro": 0.711481022624799,
795
+ "eval_runtime": 286.1698,
796
+ "eval_samples_per_second": 4.511,
797
+ "eval_steps_per_second": 2.257,
798
+ "eval_weighted_fpr": 0.01957245974458634,
799
+ "eval_weighted_sensitivity": 0.7815646785437645,
800
+ "eval_weighted_specificity": 0.9627681407839513,
801
+ "step": 38535
802
+ },
803
+ {
804
+ "epoch": 15.18,
805
+ "learning_rate": 2.4711950175165434e-05,
806
+ "loss": 0.4596,
807
+ "step": 39000
808
+ },
809
+ {
810
+ "epoch": 15.38,
811
+ "learning_rate": 2.4387569741793175e-05,
812
+ "loss": 0.5262,
813
+ "step": 39500
814
+ },
815
+ {
816
+ "epoch": 15.57,
817
+ "learning_rate": 2.4063189308420915e-05,
818
+ "loss": 0.4665,
819
+ "step": 40000
820
+ },
821
+ {
822
+ "epoch": 15.76,
823
+ "learning_rate": 2.3738808875048656e-05,
824
+ "loss": 0.3048,
825
+ "step": 40500
826
+ },
827
+ {
828
+ "epoch": 15.96,
829
+ "learning_rate": 2.341572596340989e-05,
830
+ "loss": 0.2734,
831
+ "step": 41000
832
+ },
833
+ {
834
+ "epoch": 16.0,
835
+ "eval_accuracy": 0.7776917118512781,
836
+ "eval_f1_macro": 0.7295133712588342,
837
+ "eval_f1_micro": 0.7776917118512781,
838
+ "eval_f1_weighted": 0.7776503309668394,
839
+ "eval_loss": 1.8943842649459839,
840
+ "eval_macro_fpr": 0.0202894340480138,
841
+ "eval_macro_sensitivity": 0.7265129858866516,
842
+ "eval_macro_specificity": 0.9833416395469147,
843
+ "eval_precision": 0.787044263189245,
844
+ "eval_precision_macro": 0.7538684462791384,
845
+ "eval_recall": 0.7776917118512781,
846
+ "eval_recall_macro": 0.7265129858866516,
847
+ "eval_runtime": 289.6948,
848
+ "eval_samples_per_second": 4.456,
849
+ "eval_steps_per_second": 2.23,
850
+ "eval_weighted_fpr": 0.02000976085895559,
851
+ "eval_weighted_sensitivity": 0.7776917118512781,
852
+ "eval_weighted_specificity": 0.9724328813524437,
853
+ "step": 41104
854
+ }
855
+ ],
856
+ "logging_steps": 500,
857
+ "max_steps": 77070,
858
+ "num_train_epochs": 30,
859
+ "save_steps": 500,
860
+ "total_flos": 8.934561952107725e+16,
861
+ "trial_name": null,
862
+ "trial_params": null
863
+ }
training_checkpoints/checkpoint-41104/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e37f60a60daa651d8e7f2ff3947107bcf8c19f622a0416af7b872e6562bd538
3
+ size 4600
training_checkpoints/checkpoint-41104/vocab.json ADDED
The diff for this file is too large to render. See raw diff