Hugging Face's logo

simon-clmtd
/
sdg-scibert-zo_up

Safetensors
bert
Model card Files
xet
Community
Simon Clematide commited on
Commit
6f8a996
·
1 Parent(s): 701eae6

Add more training files

Browse files
Files changed (9) hide show
  1. optimizer.pt +3 -0
  2. rng_state.pth +3 -0
  3. scheduler.pt +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. trainer_state.json +299 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af800954044ac77f67faa594ee6b44f94be08a4c0af0df89ac82f0047736334
3
+ size 879786763
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ddebc081cb89eddc65db71aedd21b0469c01e11fc02d785a620ee1898f9b361
3
+ size 14709
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca90010bac2bd78f3d9ffac3f4b5f9cf178a8f2a1b3358eacf6592b885071b8a
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7777777777777778,
3
+ "best_model_checkpoint": "/home/ubuntu/.cache/huggingface/checkpoints/final-nolowercase/allenai/scibert_scivocab_cased-zo_up/checkpoint-952",
4
+ "epoch": 14.0,
5
+ "eval_steps": 500,
6
+ "global_step": 952,
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
+ "grad_norm": 9.758819580078125,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 2.1465,
16
+ "step": 68
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6060606060606061,
21
+ "eval_f1": 0.5926804543443077,
22
+ "eval_loss": 1.737682580947876,
23
+ "eval_precision": 0.6542157960050116,
24
+ "eval_recall": 0.6060606060606061,
25
+ "eval_runtime": 5.5219,
26
+ "eval_samples_per_second": 35.858,
27
+ "eval_steps_per_second": 3.079,
28
+ "step": 68
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 5.286689758300781,
33
+ "learning_rate": 1.8e-05,
34
+ "loss": 1.3152,
35
+ "step": 136
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6919191919191919,
40
+ "eval_f1": 0.6839311008227865,
41
+ "eval_loss": 1.176934838294983,
42
+ "eval_precision": 0.6962589879256545,
43
+ "eval_recall": 0.6919191919191919,
44
+ "eval_runtime": 5.5816,
45
+ "eval_samples_per_second": 35.474,
46
+ "eval_steps_per_second": 3.046,
47
+ "step": 136
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 14.378315925598145,
52
+ "learning_rate": 1.7e-05,
53
+ "loss": 0.7672,
54
+ "step": 204
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7222222222222222,
59
+ "eval_f1": 0.7126444337555448,
60
+ "eval_loss": 0.9430862069129944,
61
+ "eval_precision": 0.7326162263662264,
62
+ "eval_recall": 0.7222222222222222,
63
+ "eval_runtime": 5.5762,
64
+ "eval_samples_per_second": 35.508,
65
+ "eval_steps_per_second": 3.049,
66
+ "step": 204
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 6.346803665161133,
71
+ "learning_rate": 1.6000000000000003e-05,
72
+ "loss": 0.428,
73
+ "step": 272
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.7424242424242424,
78
+ "eval_f1": 0.7374161797373577,
79
+ "eval_loss": 0.8948661684989929,
80
+ "eval_precision": 0.7697136967970301,
81
+ "eval_recall": 0.7424242424242424,
82
+ "eval_runtime": 5.5678,
83
+ "eval_samples_per_second": 35.561,
84
+ "eval_steps_per_second": 3.053,
85
+ "step": 272
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 2.8745429515838623,
90
+ "learning_rate": 1.5000000000000002e-05,
91
+ "loss": 0.2365,
92
+ "step": 340
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.7474747474747475,
97
+ "eval_f1": 0.7421610878166268,
98
+ "eval_loss": 0.9098976850509644,
99
+ "eval_precision": 0.7533454200120868,
100
+ "eval_recall": 0.7474747474747475,
101
+ "eval_runtime": 5.5605,
102
+ "eval_samples_per_second": 35.608,
103
+ "eval_steps_per_second": 3.057,
104
+ "step": 340
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 40.36902618408203,
109
+ "learning_rate": 1.4e-05,
110
+ "loss": 0.1471,
111
+ "step": 408
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.7575757575757576,
116
+ "eval_f1": 0.7509465650386367,
117
+ "eval_loss": 0.9332886338233948,
118
+ "eval_precision": 0.7571138737805404,
119
+ "eval_recall": 0.7575757575757576,
120
+ "eval_runtime": 5.5624,
121
+ "eval_samples_per_second": 35.596,
122
+ "eval_steps_per_second": 3.056,
123
+ "step": 408
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 0.5145724415779114,
128
+ "learning_rate": 1.3000000000000001e-05,
129
+ "loss": 0.0813,
130
+ "step": 476
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.7626262626262627,
135
+ "eval_f1": 0.7568973419007069,
136
+ "eval_loss": 1.031730055809021,
137
+ "eval_precision": 0.7752156022989356,
138
+ "eval_recall": 0.7626262626262627,
139
+ "eval_runtime": 5.5746,
140
+ "eval_samples_per_second": 35.518,
141
+ "eval_steps_per_second": 3.05,
142
+ "step": 476
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "grad_norm": 0.22983932495117188,
147
+ "learning_rate": 1.2e-05,
148
+ "loss": 0.0489,
149
+ "step": 544
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_accuracy": 0.7727272727272727,
154
+ "eval_f1": 0.7666605746845349,
155
+ "eval_loss": 1.0123027563095093,
156
+ "eval_precision": 0.7856826316385139,
157
+ "eval_recall": 0.7727272727272727,
158
+ "eval_runtime": 5.5743,
159
+ "eval_samples_per_second": 35.52,
160
+ "eval_steps_per_second": 3.05,
161
+ "step": 544
162
+ },
163
+ {
164
+ "epoch": 9.0,
165
+ "grad_norm": 0.1842876672744751,
166
+ "learning_rate": 1.1000000000000001e-05,
167
+ "loss": 0.032,
168
+ "step": 612
169
+ },
170
+ {
171
+ "epoch": 9.0,
172
+ "eval_accuracy": 0.7727272727272727,
173
+ "eval_f1": 0.7671998708627763,
174
+ "eval_loss": 1.100764513015747,
175
+ "eval_precision": 0.7916376062209396,
176
+ "eval_recall": 0.7727272727272727,
177
+ "eval_runtime": 5.5601,
178
+ "eval_samples_per_second": 35.611,
179
+ "eval_steps_per_second": 3.057,
180
+ "step": 612
181
+ },
182
+ {
183
+ "epoch": 10.0,
184
+ "grad_norm": 0.4087672233581543,
185
+ "learning_rate": 1e-05,
186
+ "loss": 0.0213,
187
+ "step": 680
188
+ },
189
+ {
190
+ "epoch": 10.0,
191
+ "eval_accuracy": 0.7727272727272727,
192
+ "eval_f1": 0.7671998708627763,
193
+ "eval_loss": 1.0900105237960815,
194
+ "eval_precision": 0.7916376062209396,
195
+ "eval_recall": 0.7727272727272727,
196
+ "eval_runtime": 5.5654,
197
+ "eval_samples_per_second": 35.577,
198
+ "eval_steps_per_second": 3.055,
199
+ "step": 680
200
+ },
201
+ {
202
+ "epoch": 11.0,
203
+ "grad_norm": 0.11046537756919861,
204
+ "learning_rate": 9e-06,
205
+ "loss": 0.0175,
206
+ "step": 748
207
+ },
208
+ {
209
+ "epoch": 11.0,
210
+ "eval_accuracy": 0.7676767676767676,
211
+ "eval_f1": 0.7623911252744204,
212
+ "eval_loss": 1.0985959768295288,
213
+ "eval_precision": 0.7916245791245792,
214
+ "eval_recall": 0.7676767676767676,
215
+ "eval_runtime": 5.5637,
216
+ "eval_samples_per_second": 35.588,
217
+ "eval_steps_per_second": 3.056,
218
+ "step": 748
219
+ },
220
+ {
221
+ "epoch": 12.0,
222
+ "grad_norm": 0.5795270204544067,
223
+ "learning_rate": 8.000000000000001e-06,
224
+ "loss": 0.0105,
225
+ "step": 816
226
+ },
227
+ {
228
+ "epoch": 12.0,
229
+ "eval_accuracy": 0.7575757575757576,
230
+ "eval_f1": 0.753315419105508,
231
+ "eval_loss": 1.2046688795089722,
232
+ "eval_precision": 0.7807447182447182,
233
+ "eval_recall": 0.7575757575757576,
234
+ "eval_runtime": 5.5698,
235
+ "eval_samples_per_second": 35.549,
236
+ "eval_steps_per_second": 3.052,
237
+ "step": 816
238
+ },
239
+ {
240
+ "epoch": 13.0,
241
+ "grad_norm": 0.07767060399055481,
242
+ "learning_rate": 7e-06,
243
+ "loss": 0.0099,
244
+ "step": 884
245
+ },
246
+ {
247
+ "epoch": 13.0,
248
+ "eval_accuracy": 0.7727272727272727,
249
+ "eval_f1": 0.7671686533256058,
250
+ "eval_loss": 1.1359951496124268,
251
+ "eval_precision": 0.7919163438900281,
252
+ "eval_recall": 0.7727272727272727,
253
+ "eval_runtime": 5.5591,
254
+ "eval_samples_per_second": 35.617,
255
+ "eval_steps_per_second": 3.058,
256
+ "step": 884
257
+ },
258
+ {
259
+ "epoch": 14.0,
260
+ "grad_norm": 0.0792476162314415,
261
+ "learning_rate": 6e-06,
262
+ "loss": 0.0072,
263
+ "step": 952
264
+ },
265
+ {
266
+ "epoch": 14.0,
267
+ "eval_accuracy": 0.7777777777777778,
268
+ "eval_f1": 0.7736904539650535,
269
+ "eval_loss": 1.1267083883285522,
270
+ "eval_precision": 0.797784549758234,
271
+ "eval_recall": 0.7777777777777778,
272
+ "eval_runtime": 5.5659,
273
+ "eval_samples_per_second": 35.574,
274
+ "eval_steps_per_second": 3.054,
275
+ "step": 952
276
+ }
277
+ ],
278
+ "logging_steps": 500,
279
+ "max_steps": 1360,
280
+ "num_input_tokens_seen": 0,
281
+ "num_train_epochs": 20,
282
+ "save_steps": 500,
283
+ "stateful_callbacks": {
284
+ "TrainerControl": {
285
+ "args": {
286
+ "should_epoch_stop": false,
287
+ "should_evaluate": false,
288
+ "should_log": false,
289
+ "should_save": true,
290
+ "should_training_stop": false
291
+ },
292
+ "attributes": {}
293
+ }
294
+ },
295
+ "total_flos": 2984107995832320.0,
296
+ "train_batch_size": 12,
297
+ "trial_name": null,
298
+ "trial_params": null
299
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6728d45aae9302ac2656ddf218d44224848150f29ea3fafc5535dde9cd98003
3
+ size 5713
vocab.txt ADDED
The diff for this file is too large to render. See raw diff