Hugging Face's logo

diogopaes10
/
017-microsoft-MiniLM-finetuned-yahoo-800_200

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
diogopaes10 commited on
Commit
693d611
•
1 Parent(s): 86ff658

Training in progress, step 500

Browse files
Files changed (19) hide show
  1. checkpoint-500/config.json +50 -0
  2. checkpoint-500/optimizer.pt +3 -0
  3. checkpoint-500/pytorch_model.bin +3 -0
  4. checkpoint-500/rng_state.pth +3 -0
  5. checkpoint-500/scheduler.pt +3 -0
  6. checkpoint-500/special_tokens_map.json +7 -0
  7. checkpoint-500/tokenizer.json +0 -0
  8. checkpoint-500/tokenizer_config.json +15 -0
  9. checkpoint-500/trainer_state.json +412 -0
  10. checkpoint-500/training_args.bin +3 -0
  11. checkpoint-500/vocab.txt +0 -0
  12. config.json +50 -0
  13. pytorch_model.bin +3 -0
  14. runs/Jul23_00-34-55_2a6e7d97e315/events.out.tfevents.1690072504.2a6e7d97e315.7189.0 +3 -0
  15. special_tokens_map.json +7 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +15 -0
  18. training_args.bin +3 -0
  19. vocab.txt +0 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "Society & Culture",
13
+ "1": "Science & Mathematics",
14
+ "2": "Health",
15
+ "3": "Education & Reference",
16
+ "4": "Computers & Internet",
17
+ "5": "Sports",
18
+ "6": "Business & Finance",
19
+ "7": "Entertainment & Music",
20
+ "8": "Family & Relationships",
21
+ "9": "Politics & Government"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1536,
25
+ "label2id": {
26
+ "Business & Finance": 6,
27
+ "Computers & Internet": 4,
28
+ "Education & Reference": 3,
29
+ "Entertainment & Music": 7,
30
+ "Family & Relationships": 8,
31
+ "Health": 2,
32
+ "Politics & Government": 9,
33
+ "Science & Mathematics": 1,
34
+ "Society & Culture": 0,
35
+ "Sports": 5
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "single_label_classification",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.31.0",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30522
50
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca39e26a43f5acc33e4e87ad59d89d4955ddd2ea6ff7ffb935bbfb7e7754235
3
+ size 267028677
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e58ff51643acb2194499b1895dfacf8772e3baf0bb08e79e633a551fe601c3
3
+ size 133523761
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c71cf88a9d7472b779c96734d0b6f5c6c4d3edaaa3f54da9a9424173c7eddd
3
+ size 14575
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bedeefad39f70c49c93e419d1c8610c1f9a19e8bba96e2712d920ba0a33fd9
3
+ size 627
checkpoint-500/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
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,412 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 1.9968e-05,
13
+ "loss": 2.3062,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.28,
18
+ "learning_rate": 1.8976000000000003e-05,
19
+ "loss": 2.3021,
20
+ "step": 32
21
+ },
22
+ {
23
+ "epoch": 1.28,
24
+ "eval_accuracy": 0.12,
25
+ "eval_disk_space_total": 78.1898422241211,
26
+ "eval_disk_space_used": 24.56061553955078,
27
+ "eval_f1": 0.05185185185185186,
28
+ "eval_gpu_ram_allocated": 0.3903946876525879,
29
+ "eval_gpu_ram_cached": 12.833984375,
30
+ "eval_gpu_ram_total": 39.56402587890625,
31
+ "eval_gpu_utilization": 29,
32
+ "eval_loss": 2.2975096702575684,
33
+ "eval_precision": 0.11020408163265306,
34
+ "eval_recall": 0.12,
35
+ "eval_runtime": 0.2913,
36
+ "eval_samples_per_second": 686.621,
37
+ "eval_steps_per_second": 24.032,
38
+ "eval_system_ram_total": 83.48074722290039,
39
+ "eval_system_ram_used": 3.8423919677734375,
40
+ "step": 32
41
+ },
42
+ {
43
+ "epoch": 2.56,
44
+ "learning_rate": 1.7952e-05,
45
+ "loss": 2.2615,
46
+ "step": 64
47
+ },
48
+ {
49
+ "epoch": 2.56,
50
+ "eval_accuracy": 0.31,
51
+ "eval_disk_space_total": 78.1898422241211,
52
+ "eval_disk_space_used": 24.56061553955078,
53
+ "eval_f1": 0.2339181338497344,
54
+ "eval_gpu_ram_allocated": 0.39037179946899414,
55
+ "eval_gpu_ram_cached": 12.833984375,
56
+ "eval_gpu_ram_total": 39.56402587890625,
57
+ "eval_gpu_utilization": 30,
58
+ "eval_loss": 2.192563533782959,
59
+ "eval_precision": 0.4648550724637681,
60
+ "eval_recall": 0.31,
61
+ "eval_runtime": 0.2737,
62
+ "eval_samples_per_second": 730.737,
63
+ "eval_steps_per_second": 25.576,
64
+ "eval_system_ram_total": 83.48074722290039,
65
+ "eval_system_ram_used": 3.8513946533203125,
66
+ "step": 64
67
+ },
68
+ {
69
+ "epoch": 3.84,
70
+ "learning_rate": 1.6928e-05,
71
+ "loss": 2.0677,
72
+ "step": 96
73
+ },
74
+ {
75
+ "epoch": 3.84,
76
+ "eval_accuracy": 0.51,
77
+ "eval_disk_space_total": 78.1898422241211,
78
+ "eval_disk_space_used": 24.56061553955078,
79
+ "eval_f1": 0.4301287248566463,
80
+ "eval_gpu_ram_allocated": 0.39051055908203125,
81
+ "eval_gpu_ram_cached": 12.833984375,
82
+ "eval_gpu_ram_total": 39.56402587890625,
83
+ "eval_gpu_utilization": 22,
84
+ "eval_loss": 1.965756893157959,
85
+ "eval_precision": 0.3949837686822981,
86
+ "eval_recall": 0.51,
87
+ "eval_runtime": 0.3124,
88
+ "eval_samples_per_second": 640.226,
89
+ "eval_steps_per_second": 22.408,
90
+ "eval_system_ram_total": 83.48074722290039,
91
+ "eval_system_ram_used": 3.8537025451660156,
92
+ "step": 96
93
+ },
94
+ {
95
+ "epoch": 5.12,
96
+ "learning_rate": 1.5904000000000002e-05,
97
+ "loss": 1.8562,
98
+ "step": 128
99
+ },
100
+ {
101
+ "epoch": 5.12,
102
+ "eval_accuracy": 0.545,
103
+ "eval_disk_space_total": 78.1898422241211,
104
+ "eval_disk_space_used": 24.560619354248047,
105
+ "eval_f1": 0.46549419445976403,
106
+ "eval_gpu_ram_allocated": 0.39040040969848633,
107
+ "eval_gpu_ram_cached": 12.833984375,
108
+ "eval_gpu_ram_total": 39.56402587890625,
109
+ "eval_gpu_utilization": 41,
110
+ "eval_loss": 1.8382666110992432,
111
+ "eval_precision": 0.45874241633360424,
112
+ "eval_recall": 0.545,
113
+ "eval_runtime": 0.2734,
114
+ "eval_samples_per_second": 731.569,
115
+ "eval_steps_per_second": 25.605,
116
+ "eval_system_ram_total": 83.48074722290039,
117
+ "eval_system_ram_used": 3.857379913330078,
118
+ "step": 128
119
+ },
120
+ {
121
+ "epoch": 6.4,
122
+ "learning_rate": 1.4880000000000002e-05,
123
+ "loss": 1.6929,
124
+ "step": 160
125
+ },
126
+ {
127
+ "epoch": 6.4,
128
+ "eval_accuracy": 0.555,
129
+ "eval_disk_space_total": 78.1898422241211,
130
+ "eval_disk_space_used": 24.560688018798828,
131
+ "eval_f1": 0.4942300415011664,
132
+ "eval_gpu_ram_allocated": 0.39035606384277344,
133
+ "eval_gpu_ram_cached": 12.833984375,
134
+ "eval_gpu_ram_total": 39.56402587890625,
135
+ "eval_gpu_utilization": 29,
136
+ "eval_loss": 1.7403417825698853,
137
+ "eval_precision": 0.5261452781574115,
138
+ "eval_recall": 0.555,
139
+ "eval_runtime": 0.2751,
140
+ "eval_samples_per_second": 727.05,
141
+ "eval_steps_per_second": 25.447,
142
+ "eval_system_ram_total": 83.48074722290039,
143
+ "eval_system_ram_used": 3.854930877685547,
144
+ "step": 160
145
+ },
146
+ {
147
+ "epoch": 7.68,
148
+ "learning_rate": 1.3856e-05,
149
+ "loss": 1.5569,
150
+ "step": 192
151
+ },
152
+ {
153
+ "epoch": 7.68,
154
+ "eval_accuracy": 0.585,
155
+ "eval_disk_space_total": 78.1898422241211,
156
+ "eval_disk_space_used": 24.560688018798828,
157
+ "eval_f1": 0.5466732171455438,
158
+ "eval_gpu_ram_allocated": 0.39036035537719727,
159
+ "eval_gpu_ram_cached": 12.833984375,
160
+ "eval_gpu_ram_total": 39.56402587890625,
161
+ "eval_gpu_utilization": 37,
162
+ "eval_loss": 1.6662890911102295,
163
+ "eval_precision": 0.6495824550556009,
164
+ "eval_recall": 0.585,
165
+ "eval_runtime": 0.2754,
166
+ "eval_samples_per_second": 726.273,
167
+ "eval_steps_per_second": 25.42,
168
+ "eval_system_ram_total": 83.48074722290039,
169
+ "eval_system_ram_used": 3.8549232482910156,
170
+ "step": 192
171
+ },
172
+ {
173
+ "epoch": 8.96,
174
+ "learning_rate": 1.2832e-05,
175
+ "loss": 1.4636,
176
+ "step": 224
177
+ },
178
+ {
179
+ "epoch": 8.96,
180
+ "eval_accuracy": 0.58,
181
+ "eval_disk_space_total": 78.1898422241211,
182
+ "eval_disk_space_used": 24.560688018798828,
183
+ "eval_f1": 0.5475206766586077,
184
+ "eval_gpu_ram_allocated": 0.39038610458374023,
185
+ "eval_gpu_ram_cached": 12.833984375,
186
+ "eval_gpu_ram_total": 39.56402587890625,
187
+ "eval_gpu_utilization": 30,
188
+ "eval_loss": 1.612341284751892,
189
+ "eval_precision": 0.5538885280526147,
190
+ "eval_recall": 0.58,
191
+ "eval_runtime": 0.2831,
192
+ "eval_samples_per_second": 706.386,
193
+ "eval_steps_per_second": 24.724,
194
+ "eval_system_ram_total": 83.48074722290039,
195
+ "eval_system_ram_used": 3.8539352416992188,
196
+ "step": 224
197
+ },
198
+ {
199
+ "epoch": 10.24,
200
+ "learning_rate": 1.1808000000000001e-05,
201
+ "loss": 1.3683,
202
+ "step": 256
203
+ },
204
+ {
205
+ "epoch": 10.24,
206
+ "eval_accuracy": 0.595,
207
+ "eval_disk_space_total": 78.1898422241211,
208
+ "eval_disk_space_used": 24.56069564819336,
209
+ "eval_f1": 0.5828575381901582,
210
+ "eval_gpu_ram_allocated": 0.39037179946899414,
211
+ "eval_gpu_ram_cached": 12.833984375,
212
+ "eval_gpu_ram_total": 39.56402587890625,
213
+ "eval_gpu_utilization": 41,
214
+ "eval_loss": 1.5615015029907227,
215
+ "eval_precision": 0.6016443571048834,
216
+ "eval_recall": 0.595,
217
+ "eval_runtime": 0.2727,
218
+ "eval_samples_per_second": 733.478,
219
+ "eval_steps_per_second": 25.672,
220
+ "eval_system_ram_total": 83.48074722290039,
221
+ "eval_system_ram_used": 3.8527297973632812,
222
+ "step": 256
223
+ },
224
+ {
225
+ "epoch": 11.52,
226
+ "learning_rate": 1.0784e-05,
227
+ "loss": 1.2649,
228
+ "step": 288
229
+ },
230
+ {
231
+ "epoch": 11.52,
232
+ "eval_accuracy": 0.61,
233
+ "eval_disk_space_total": 78.1898422241211,
234
+ "eval_disk_space_used": 24.560710906982422,
235
+ "eval_f1": 0.590376982026963,
236
+ "eval_gpu_ram_allocated": 0.3903775215148926,
237
+ "eval_gpu_ram_cached": 12.833984375,
238
+ "eval_gpu_ram_total": 39.56402587890625,
239
+ "eval_gpu_utilization": 30,
240
+ "eval_loss": 1.526059627532959,
241
+ "eval_precision": 0.6242595289277212,
242
+ "eval_recall": 0.61,
243
+ "eval_runtime": 0.2757,
244
+ "eval_samples_per_second": 725.456,
245
+ "eval_steps_per_second": 25.391,
246
+ "eval_system_ram_total": 83.48074722290039,
247
+ "eval_system_ram_used": 3.864604949951172,
248
+ "step": 288
249
+ },
250
+ {
251
+ "epoch": 12.8,
252
+ "learning_rate": 9.760000000000001e-06,
253
+ "loss": 1.1968,
254
+ "step": 320
255
+ },
256
+ {
257
+ "epoch": 12.8,
258
+ "eval_accuracy": 0.615,
259
+ "eval_disk_space_total": 78.1898422241211,
260
+ "eval_disk_space_used": 24.560710906982422,
261
+ "eval_f1": 0.6011782661782662,
262
+ "eval_gpu_ram_allocated": 0.3903789520263672,
263
+ "eval_gpu_ram_cached": 12.833984375,
264
+ "eval_gpu_ram_total": 39.56402587890625,
265
+ "eval_gpu_utilization": 45,
266
+ "eval_loss": 1.4975976943969727,
267
+ "eval_precision": 0.6069767600820232,
268
+ "eval_recall": 0.615,
269
+ "eval_runtime": 0.2757,
270
+ "eval_samples_per_second": 725.338,
271
+ "eval_steps_per_second": 25.387,
272
+ "eval_system_ram_total": 83.48074722290039,
273
+ "eval_system_ram_used": 3.876636505126953,
274
+ "step": 320
275
+ },
276
+ {
277
+ "epoch": 14.08,
278
+ "learning_rate": 8.736e-06,
279
+ "loss": 1.1291,
280
+ "step": 352
281
+ },
282
+ {
283
+ "epoch": 14.08,
284
+ "eval_accuracy": 0.615,
285
+ "eval_disk_space_total": 78.1898422241211,
286
+ "eval_disk_space_used": 24.560710906982422,
287
+ "eval_f1": 0.598349347882615,
288
+ "eval_gpu_ram_allocated": 0.39051055908203125,
289
+ "eval_gpu_ram_cached": 12.833984375,
290
+ "eval_gpu_ram_total": 39.56402587890625,
291
+ "eval_gpu_utilization": 47,
292
+ "eval_loss": 1.4755542278289795,
293
+ "eval_precision": 0.6163792581687317,
294
+ "eval_recall": 0.615,
295
+ "eval_runtime": 0.2792,
296
+ "eval_samples_per_second": 716.432,
297
+ "eval_steps_per_second": 25.075,
298
+ "eval_system_ram_total": 83.48074722290039,
299
+ "eval_system_ram_used": 3.874866485595703,
300
+ "step": 352
301
+ },
302
+ {
303
+ "epoch": 15.36,
304
+ "learning_rate": 7.712e-06,
305
+ "loss": 1.0673,
306
+ "step": 384
307
+ },
308
+ {
309
+ "epoch": 15.36,
310
+ "eval_accuracy": 0.62,
311
+ "eval_disk_space_total": 78.1898422241211,
312
+ "eval_disk_space_used": 24.560714721679688,
313
+ "eval_f1": 0.6063605762373413,
314
+ "eval_gpu_ram_allocated": 0.39066219329833984,
315
+ "eval_gpu_ram_cached": 12.833984375,
316
+ "eval_gpu_ram_total": 39.56402587890625,
317
+ "eval_gpu_utilization": 35,
318
+ "eval_loss": 1.4659814834594727,
319
+ "eval_precision": 0.6257950937950938,
320
+ "eval_recall": 0.62,
321
+ "eval_runtime": 0.2762,
322
+ "eval_samples_per_second": 724.01,
323
+ "eval_steps_per_second": 25.34,
324
+ "eval_system_ram_total": 83.48074722290039,
325
+ "eval_system_ram_used": 3.875171661376953,
326
+ "step": 384
327
+ },
328
+ {
329
+ "epoch": 16.64,
330
+ "learning_rate": 6.688e-06,
331
+ "loss": 0.9884,
332
+ "step": 416
333
+ },
334
+ {
335
+ "epoch": 16.64,
336
+ "eval_accuracy": 0.625,
337
+ "eval_disk_space_total": 78.1898422241211,
338
+ "eval_disk_space_used": 24.560771942138672,
339
+ "eval_f1": 0.6134740161239549,
340
+ "eval_gpu_ram_allocated": 0.3903632164001465,
341
+ "eval_gpu_ram_cached": 12.833984375,
342
+ "eval_gpu_ram_total": 39.56402587890625,
343
+ "eval_gpu_utilization": 33,
344
+ "eval_loss": 1.4409570693969727,
345
+ "eval_precision": 0.6203985870473285,
346
+ "eval_recall": 0.625,
347
+ "eval_runtime": 0.2727,
348
+ "eval_samples_per_second": 733.533,
349
+ "eval_steps_per_second": 25.674,
350
+ "eval_system_ram_total": 83.48074722290039,
351
+ "eval_system_ram_used": 3.8757286071777344,
352
+ "step": 416
353
+ },
354
+ {
355
+ "epoch": 17.92,
356
+ "learning_rate": 5.664e-06,
357
+ "loss": 0.9743,
358
+ "step": 448
359
+ },
360
+ {
361
+ "epoch": 17.92,
362
+ "eval_accuracy": 0.635,
363
+ "eval_disk_space_total": 78.1898422241211,
364
+ "eval_disk_space_used": 24.560775756835938,
365
+ "eval_f1": 0.6233316744944652,
366
+ "eval_gpu_ram_allocated": 0.3904705047607422,
367
+ "eval_gpu_ram_cached": 12.833984375,
368
+ "eval_gpu_ram_total": 39.56402587890625,
369
+ "eval_gpu_utilization": 44,
370
+ "eval_loss": 1.4327807426452637,
371
+ "eval_precision": 0.6343307918132929,
372
+ "eval_recall": 0.635,
373
+ "eval_runtime": 0.2727,
374
+ "eval_samples_per_second": 733.287,
375
+ "eval_steps_per_second": 25.665,
376
+ "eval_system_ram_total": 83.48074722290039,
377
+ "eval_system_ram_used": 3.874713897705078,
378
+ "step": 448
379
+ },
380
+ {
381
+ "epoch": 19.2,
382
+ "learning_rate": 4.6400000000000005e-06,
383
+ "loss": 0.926,
384
+ "step": 480
385
+ },
386
+ {
387
+ "epoch": 19.2,
388
+ "eval_accuracy": 0.615,
389
+ "eval_disk_space_total": 78.1898422241211,
390
+ "eval_disk_space_used": 24.560775756835938,
391
+ "eval_f1": 0.6088320577269858,
392
+ "eval_gpu_ram_allocated": 0.39035749435424805,
393
+ "eval_gpu_ram_cached": 12.833984375,
394
+ "eval_gpu_ram_total": 39.56402587890625,
395
+ "eval_gpu_utilization": 31,
396
+ "eval_loss": 1.4344311952590942,
397
+ "eval_precision": 0.6237836346659876,
398
+ "eval_recall": 0.615,
399
+ "eval_runtime": 0.2758,
400
+ "eval_samples_per_second": 725.226,
401
+ "eval_steps_per_second": 25.383,
402
+ "eval_system_ram_total": 83.48074722290039,
403
+ "eval_system_ram_used": 3.8742332458496094,
404
+ "step": 480
405
+ }
406
+ ],
407
+ "max_steps": 625,
408
+ "num_train_epochs": 25,
409
+ "total_flos": 287732237726976.0,
410
+ "trial_name": null,
411
+ "trial_params": null
412
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95dfde0fcae054bf86282ae2c6a8dc5ce2a68b6cb126e32d4bdd6e21e27bf0b0
3
+ size 4091
checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "Society & Culture",
13
+ "1": "Science & Mathematics",
14
+ "2": "Health",
15
+ "3": "Education & Reference",
16
+ "4": "Computers & Internet",
17
+ "5": "Sports",
18
+ "6": "Business & Finance",
19
+ "7": "Entertainment & Music",
20
+ "8": "Family & Relationships",
21
+ "9": "Politics & Government"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1536,
25
+ "label2id": {
26
+ "Business & Finance": 6,
27
+ "Computers & Internet": 4,
28
+ "Education & Reference": 3,
29
+ "Entertainment & Music": 7,
30
+ "Family & Relationships": 8,
31
+ "Health": 2,
32
+ "Politics & Government": 9,
33
+ "Science & Mathematics": 1,
34
+ "Society & Culture": 0,
35
+ "Sports": 5
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "single_label_classification",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.31.0",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30522
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e58ff51643acb2194499b1895dfacf8772e3baf0bb08e79e633a551fe601c3
3
+ size 133523761
runs/Jul23_00-34-55_2a6e7d97e315/events.out.tfevents.1690072504.2a6e7d97e315.7189.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6c1cf87b67f5527548ec1cf492b0498941392a1bb263214332c80e42a00d0c
3
+ size 21339
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95dfde0fcae054bf86282ae2c6a8dc5ce2a68b6cb126e32d4bdd6e21e27bf0b0
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff