Hugging Face's logo

cite-text-analysis
/
case-analysis-InLegalBERT

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
cite-text-analysis commited on
Commit
376ce70
·
verified ·
1 Parent(s): aad910d

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. training_checkpoints/checkpoint-2688/added_tokens.json +3 -0
  2. training_checkpoints/checkpoint-2688/config.json +41 -0
  3. training_checkpoints/checkpoint-2688/model.safetensors +3 -0
  4. training_checkpoints/checkpoint-2688/optimizer.pt +3 -0
  5. training_checkpoints/checkpoint-2688/rng_state.pth +3 -0
  6. training_checkpoints/checkpoint-2688/scheduler.pt +3 -0
  7. training_checkpoints/checkpoint-2688/special_tokens_map.json +13 -0
  8. training_checkpoints/checkpoint-2688/tokenizer.json +0 -0
  9. training_checkpoints/checkpoint-2688/tokenizer_config.json +65 -0
  10. training_checkpoints/checkpoint-2688/trainer_state.json +320 -0
  11. training_checkpoints/checkpoint-2688/training_args.bin +3 -0
  12. training_checkpoints/checkpoint-2688/vocab.txt +0 -0
training_checkpoints/checkpoint-2688/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 30522
3
+ }
training_checkpoints/checkpoint-2688/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "law-ai/InLegalBERT",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_ids": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "positive",
15
+ "1": "negative",
16
+ "2": "neutral",
17
+ "3": "rel_by_party"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 1,
23
+ "neutral": 2,
24
+ "positive": 0,
25
+ "rel_by_party": 3
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "output_past": true,
33
+ "pad_token_id": 30522,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "single_label_classification",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.39.3",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 30523
41
+ }
training_checkpoints/checkpoint-2688/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51317e09d06ff6ad36d1a7dac4d266cac2a962fc0ca51c4052e65cc53e906036
3
+ size 437967872
training_checkpoints/checkpoint-2688/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4896f4129b031e0c2d7e508d1368ad47f50887ad0058df5f8d642cf46a927ff
3
+ size 876056826
training_checkpoints/checkpoint-2688/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07c0d3d75ccd510156a69fc00a18c8ee500b5647683f3286579c8c609f9abb12
3
+ size 14244
training_checkpoints/checkpoint-2688/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a055c75a246816aaee23e7539ad6ecbe03e82f0c7309cae5651a435fc6fb62
3
+ size 1064
training_checkpoints/checkpoint-2688/special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "sep_token": "[SEP]",
12
+ "unk_token": "[UNK]"
13
+ }
training_checkpoints/checkpoint-2688/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training_checkpoints/checkpoint-2688/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30522": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "clean_up_tokenization_spaces": true,
53
+ "cls_token": "[CLS]",
54
+ "do_basic_tokenize": true,
55
+ "do_lower_case": true,
56
+ "mask_token": "[MASK]",
57
+ "model_max_length": 512,
58
+ "never_split": null,
59
+ "pad_token": "<pad>",
60
+ "sep_token": "[SEP]",
61
+ "strip_accents": null,
62
+ "tokenize_chinese_chars": true,
63
+ "tokenizer_class": "BertTokenizer",
64
+ "unk_token": "[UNK]"
65
+ }
training_checkpoints/checkpoint-2688/trainer_state.json ADDED
@@ -0,0 +1,320 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6690246389304302,
3
+ "best_model_checkpoint": "case-analysis-InLegalBERT/checkpoint-1344",
4
+ "epoch": 12.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2688,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.8017817371937639,
14
+ "eval_f1_macro": 0.5936102522033613,
15
+ "eval_f1_micro": 0.8017817371937639,
16
+ "eval_f1_weighted": 0.7819923339877444,
17
+ "eval_loss": 0.6545999050140381,
18
+ "eval_macro_fpr": 0.09781883735656886,
19
+ "eval_macro_sensitivity": 0.6106003826592061,
20
+ "eval_macro_specificity": 0.9112420642353884,
21
+ "eval_precision": 0.763240968439436,
22
+ "eval_precision_macro": 0.5776616905319997,
23
+ "eval_recall": 0.8017817371937639,
24
+ "eval_recall_macro": 0.6106003826592061,
25
+ "eval_runtime": 9.2925,
26
+ "eval_samples_per_second": 48.318,
27
+ "eval_steps_per_second": 6.134,
28
+ "eval_weighted_fpr": 0.07613344739093242,
29
+ "eval_weighted_sensitivity": 0.8017817371937639,
30
+ "eval_weighted_specificity": 0.84318651974779,
31
+ "step": 224
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.8129175946547884,
36
+ "eval_f1_macro": 0.5995597405020452,
37
+ "eval_f1_micro": 0.8129175946547884,
38
+ "eval_f1_weighted": 0.7925821933419933,
39
+ "eval_loss": 0.6830806732177734,
40
+ "eval_macro_fpr": 0.0922965769071398,
41
+ "eval_macro_sensitivity": 0.615426637485461,
42
+ "eval_macro_specificity": 0.9170902440637451,
43
+ "eval_precision": 0.7732439444566204,
44
+ "eval_precision_macro": 0.5844969763606377,
45
+ "eval_recall": 0.8129175946547884,
46
+ "eval_recall_macro": 0.615426637485461,
47
+ "eval_runtime": 36.5377,
48
+ "eval_samples_per_second": 12.289,
49
+ "eval_steps_per_second": 1.56,
50
+ "eval_weighted_fpr": 0.07124681933842239,
51
+ "eval_weighted_sensitivity": 0.8129175946547884,
52
+ "eval_weighted_specificity": 0.8554433816001921,
53
+ "step": 448
54
+ },
55
+ {
56
+ "epoch": 2.23,
57
+ "grad_norm": 6.910687446594238,
58
+ "learning_rate": 4.6302083333333335e-05,
59
+ "loss": 0.607,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.8262806236080178,
65
+ "eval_f1_macro": 0.6362135046138226,
66
+ "eval_f1_micro": 0.8262806236080178,
67
+ "eval_f1_weighted": 0.8105096248986687,
68
+ "eval_loss": 0.7626442909240723,
69
+ "eval_macro_fpr": 0.0885057964533289,
70
+ "eval_macro_sensitivity": 0.6341414944356121,
71
+ "eval_macro_specificity": 0.9181782637863818,
72
+ "eval_precision": 0.8060163824047696,
73
+ "eval_precision_macro": 0.6772816989326722,
74
+ "eval_recall": 0.8262806236080178,
75
+ "eval_recall_macro": 0.6341414944356121,
76
+ "eval_runtime": 35.6726,
77
+ "eval_samples_per_second": 12.587,
78
+ "eval_steps_per_second": 1.598,
79
+ "eval_weighted_fpr": 0.0654911838790932,
80
+ "eval_weighted_sensitivity": 0.8262806236080178,
81
+ "eval_weighted_specificity": 0.8464324315375095,
82
+ "step": 672
83
+ },
84
+ {
85
+ "epoch": 4.0,
86
+ "eval_accuracy": 0.8084632516703786,
87
+ "eval_f1_macro": 0.6313839669673806,
88
+ "eval_f1_micro": 0.8084632516703786,
89
+ "eval_f1_weighted": 0.8017481865377005,
90
+ "eval_loss": 0.7839008569717407,
91
+ "eval_macro_fpr": 0.08961602877899306,
92
+ "eval_macro_sensitivity": 0.630579873226932,
93
+ "eval_macro_specificity": 0.9209618973154744,
94
+ "eval_precision": 0.7990879202460494,
95
+ "eval_precision_macro": 0.6390850934968582,
96
+ "eval_recall": 0.8084632516703786,
97
+ "eval_recall_macro": 0.630579873226932,
98
+ "eval_runtime": 33.6763,
99
+ "eval_samples_per_second": 13.333,
100
+ "eval_steps_per_second": 1.693,
101
+ "eval_weighted_fpr": 0.07319148936170213,
102
+ "eval_weighted_sensitivity": 0.8084632516703786,
103
+ "eval_weighted_specificity": 0.8753843375915193,
104
+ "step": 896
105
+ },
106
+ {
107
+ "epoch": 4.46,
108
+ "grad_norm": 0.3201627731323242,
109
+ "learning_rate": 4.258184523809524e-05,
110
+ "loss": 0.316,
111
+ "step": 1000
112
+ },
113
+ {
114
+ "epoch": 5.0,
115
+ "eval_accuracy": 0.8262806236080178,
116
+ "eval_f1_macro": 0.6513945578231293,
117
+ "eval_f1_micro": 0.8262806236080178,
118
+ "eval_f1_weighted": 0.8161065406117904,
119
+ "eval_loss": 0.9380576610565186,
120
+ "eval_macro_fpr": 0.08224137352531583,
121
+ "eval_macro_sensitivity": 0.6573161205514146,
122
+ "eval_macro_specificity": 0.9260657452373569,
123
+ "eval_precision": 0.8127349298285333,
124
+ "eval_precision_macro": 0.668810150869688,
125
+ "eval_recall": 0.8262806236080178,
126
+ "eval_recall_macro": 0.6573161205514146,
127
+ "eval_runtime": 34.3275,
128
+ "eval_samples_per_second": 13.08,
129
+ "eval_steps_per_second": 1.66,
130
+ "eval_weighted_fpr": 0.0654911838790932,
131
+ "eval_weighted_sensitivity": 0.8262806236080178,
132
+ "eval_weighted_specificity": 0.8779823573414097,
133
+ "step": 1120
134
+ },
135
+ {
136
+ "epoch": 6.0,
137
+ "eval_accuracy": 0.821826280623608,
138
+ "eval_f1_macro": 0.6690246389304302,
139
+ "eval_f1_micro": 0.821826280623608,
140
+ "eval_f1_weighted": 0.8159237291984361,
141
+ "eval_loss": 1.0433590412139893,
142
+ "eval_macro_fpr": 0.08967976675610558,
143
+ "eval_macro_sensitivity": 0.6533037047742931,
144
+ "eval_macro_specificity": 0.9186687903009794,
145
+ "eval_precision": 0.8145202780918083,
146
+ "eval_precision_macro": 0.6906556062141168,
147
+ "eval_recall": 0.821826280623608,
148
+ "eval_recall_macro": 0.6533037047742931,
149
+ "eval_runtime": 43.316,
150
+ "eval_samples_per_second": 10.366,
151
+ "eval_steps_per_second": 1.316,
152
+ "eval_weighted_fpr": 0.06739679865206402,
153
+ "eval_weighted_sensitivity": 0.821826280623608,
154
+ "eval_weighted_specificity": 0.8528488805803094,
155
+ "step": 1344
156
+ },
157
+ {
158
+ "epoch": 6.7,
159
+ "grad_norm": 0.028867056593298912,
160
+ "learning_rate": 3.8869047619047625e-05,
161
+ "loss": 0.1513,
162
+ "step": 1500
163
+ },
164
+ {
165
+ "epoch": 7.0,
166
+ "eval_accuracy": 0.8017817371937639,
167
+ "eval_f1_macro": 0.6374820990180032,
168
+ "eval_f1_micro": 0.8017817371937639,
169
+ "eval_f1_weighted": 0.8030061499337195,
170
+ "eval_loss": 1.2181551456451416,
171
+ "eval_macro_fpr": 0.09161393040768498,
172
+ "eval_macro_sensitivity": 0.6398633163339046,
173
+ "eval_macro_specificity": 0.9204902964282863,
174
+ "eval_precision": 0.8065681635796801,
175
+ "eval_precision_macro": 0.6382217224720973,
176
+ "eval_recall": 0.8017817371937639,
177
+ "eval_recall_macro": 0.6398633163339046,
178
+ "eval_runtime": 38.5257,
179
+ "eval_samples_per_second": 11.655,
180
+ "eval_steps_per_second": 1.48,
181
+ "eval_weighted_fpr": 0.07613344739093242,
182
+ "eval_weighted_sensitivity": 0.8017817371937639,
183
+ "eval_weighted_specificity": 0.8801794485193812,
184
+ "step": 1568
185
+ },
186
+ {
187
+ "epoch": 8.0,
188
+ "eval_accuracy": 0.8285077951002228,
189
+ "eval_f1_macro": 0.6375618771468077,
190
+ "eval_f1_micro": 0.8285077951002228,
191
+ "eval_f1_weighted": 0.8152450374079808,
192
+ "eval_loss": 1.3192639350891113,
193
+ "eval_macro_fpr": 0.08815434538353528,
194
+ "eval_macro_sensitivity": 0.6279757603287015,
195
+ "eval_macro_specificity": 0.9201548104191046,
196
+ "eval_precision": 0.8069973553326301,
197
+ "eval_precision_macro": 0.6565998635009741,
198
+ "eval_recall": 0.8285077951002228,
199
+ "eval_recall_macro": 0.6279757603287015,
200
+ "eval_runtime": 33.4932,
201
+ "eval_samples_per_second": 13.406,
202
+ "eval_steps_per_second": 1.702,
203
+ "eval_weighted_fpr": 0.06454316848281642,
204
+ "eval_weighted_sensitivity": 0.8285077951002228,
205
+ "eval_weighted_specificity": 0.8521114465761961,
206
+ "step": 1792
207
+ },
208
+ {
209
+ "epoch": 8.93,
210
+ "grad_norm": 0.008128850720822811,
211
+ "learning_rate": 3.514880952380952e-05,
212
+ "loss": 0.0491,
213
+ "step": 2000
214
+ },
215
+ {
216
+ "epoch": 9.0,
217
+ "eval_accuracy": 0.8329621380846325,
218
+ "eval_f1_macro": 0.6687059701183248,
219
+ "eval_f1_micro": 0.8329621380846325,
220
+ "eval_f1_weighted": 0.8234691462881575,
221
+ "eval_loss": 1.3168540000915527,
222
+ "eval_macro_fpr": 0.08276943574584078,
223
+ "eval_macro_sensitivity": 0.6554578833990599,
224
+ "eval_macro_specificity": 0.9245723745022232,
225
+ "eval_precision": 0.8179557632761028,
226
+ "eval_precision_macro": 0.6949834258114409,
227
+ "eval_recall": 0.8329621380846325,
228
+ "eval_recall_macro": 0.6554578833990599,
229
+ "eval_runtime": 36.7708,
230
+ "eval_samples_per_second": 12.211,
231
+ "eval_steps_per_second": 1.55,
232
+ "eval_weighted_fpr": 0.06265664160401002,
233
+ "eval_weighted_sensitivity": 0.8329621380846325,
234
+ "eval_weighted_specificity": 0.86532735992426,
235
+ "step": 2016
236
+ },
237
+ {
238
+ "epoch": 10.0,
239
+ "eval_accuracy": 0.8307349665924276,
240
+ "eval_f1_macro": 0.6397801007606054,
241
+ "eval_f1_micro": 0.8307349665924276,
242
+ "eval_f1_weighted": 0.8183915457597033,
243
+ "eval_loss": 1.4459574222564697,
244
+ "eval_macro_fpr": 0.08684003094467867,
245
+ "eval_macro_sensitivity": 0.6290898423251364,
246
+ "eval_macro_specificity": 0.9210102525156295,
247
+ "eval_precision": 0.8108965608714154,
248
+ "eval_precision_macro": 0.6584470636889992,
249
+ "eval_recall": 0.8307349665924276,
250
+ "eval_recall_macro": 0.6290898423251364,
251
+ "eval_runtime": 36.4367,
252
+ "eval_samples_per_second": 12.323,
253
+ "eval_steps_per_second": 1.564,
254
+ "eval_weighted_fpr": 0.06359832635983263,
255
+ "eval_weighted_sensitivity": 0.8307349665924276,
256
+ "eval_weighted_specificity": 0.8533060434700906,
257
+ "step": 2240
258
+ },
259
+ {
260
+ "epoch": 11.0,
261
+ "eval_accuracy": 0.8418708240534521,
262
+ "eval_f1_macro": 0.6463830564509832,
263
+ "eval_f1_micro": 0.8418708240534521,
264
+ "eval_f1_weighted": 0.8263008274936262,
265
+ "eval_loss": 1.4100018739700317,
266
+ "eval_macro_fpr": 0.08061341387649999,
267
+ "eval_macro_sensitivity": 0.6398590148590149,
268
+ "eval_macro_specificity": 0.9265216670805116,
269
+ "eval_precision": 0.8165947524130448,
270
+ "eval_precision_macro": 0.6717971143983426,
271
+ "eval_recall": 0.8418708240534521,
272
+ "eval_recall_macro": 0.6398590148590149,
273
+ "eval_runtime": 33.4877,
274
+ "eval_samples_per_second": 13.408,
275
+ "eval_steps_per_second": 1.702,
276
+ "eval_weighted_fpr": 0.05892116182572614,
277
+ "eval_weighted_sensitivity": 0.8418708240534521,
278
+ "eval_weighted_specificity": 0.8642158442685944,
279
+ "step": 2464
280
+ },
281
+ {
282
+ "epoch": 11.16,
283
+ "grad_norm": 0.002102190162986517,
284
+ "learning_rate": 3.143601190476191e-05,
285
+ "loss": 0.0148,
286
+ "step": 2500
287
+ },
288
+ {
289
+ "epoch": 12.0,
290
+ "eval_accuracy": 0.821826280623608,
291
+ "eval_f1_macro": 0.6469130501099637,
292
+ "eval_f1_micro": 0.821826280623608,
293
+ "eval_f1_weighted": 0.8136991543918022,
294
+ "eval_loss": 1.5364338159561157,
295
+ "eval_macro_fpr": 0.09029608603507376,
296
+ "eval_macro_sensitivity": 0.6339926634044281,
297
+ "eval_macro_specificity": 0.918073461922396,
298
+ "eval_precision": 0.810454717235043,
299
+ "eval_precision_macro": 0.6661052171615551,
300
+ "eval_recall": 0.821826280623608,
301
+ "eval_recall_macro": 0.6339926634044281,
302
+ "eval_runtime": 39.7939,
303
+ "eval_samples_per_second": 11.283,
304
+ "eval_steps_per_second": 1.432,
305
+ "eval_weighted_fpr": 0.06739679865206402,
306
+ "eval_weighted_sensitivity": 0.821826280623608,
307
+ "eval_weighted_specificity": 0.8504675670659761,
308
+ "step": 2688
309
+ }
310
+ ],
311
+ "logging_steps": 500,
312
+ "max_steps": 6720,
313
+ "num_input_tokens_seen": 0,
314
+ "num_train_epochs": 30,
315
+ "save_steps": 500,
316
+ "total_flos": 5658041735184384.0,
317
+ "train_batch_size": 8,
318
+ "trial_name": null,
319
+ "trial_params": null
320
+ }
training_checkpoints/checkpoint-2688/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4168c8c84941deb81d05fe2d714c7e20c482e1e8b4900f8d6b307d6f8c3828dd
3
+ size 4984
training_checkpoints/checkpoint-2688/vocab.txt ADDED
The diff for this file is too large to render. See raw diff