Hugging Face's logo

bradmin
/
reward-gpt

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
gpt_neox
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
bradmin commited on
Commit
15616f9
·
1 Parent(s): 3ca426c

Training in progress, step 500, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-500/config.json +14 -15
  2. checkpoint-500/optimizer.pt +2 -2
  3. checkpoint-500/pytorch_model.bin +2 -2
  4. checkpoint-500/rng_state.pth +1 -1
  5. checkpoint-500/scheduler.pt +1 -1
  6. checkpoint-500/special_tokens_map.json +7 -9
  7. checkpoint-500/tokenizer.json +0 -0
  8. checkpoint-500/tokenizer_config.json +20 -33
  9. checkpoint-500/trainer_state.json +175 -175
  10. checkpoint-500/training_args.bin +1 -1
  11. checkpoint-500/vocab.txt +0 -0
checkpoint-500/config.json CHANGED
@@ -1,36 +1,35 @@
1
  {
2
- "_name_or_path": "EleutherAI/polyglot-ko-1.3b",
3
  "architectures": [
4
- "GPTNeoXForSequenceClassification"
5
  ],
6
- "attention_dropout": 0.0,
7
  "bos_token_id": 0,
8
- "classifier_dropout": 0.1,
9
  "eos_token_id": 2,
 
10
  "hidden_act": "gelu",
11
- "hidden_dropout": 0.0,
12
- "hidden_size": 2048,
13
  "id2label": {
14
  "0": "LABEL_0"
15
  },
16
  "initializer_range": 0.02,
17
- "intermediate_size": 8192,
18
  "label2id": {
19
  "LABEL_0": 0
20
  },
21
  "layer_norm_eps": 1e-05,
22
- "max_position_embeddings": 2048,
23
- "model_type": "gpt_neox",
24
  "num_attention_heads": 16,
25
  "num_hidden_layers": 24,
26
  "pad_token_id": 2,
27
- "rope_scaling": null,
28
- "rotary_emb_base": 10000,
29
- "rotary_pct": 0.5,
30
- "tie_word_embeddings": false,
31
  "torch_dtype": "float32",
32
  "transformers_version": "4.34.1",
 
33
  "use_cache": true,
34
- "use_parallel_residual": true,
35
- "vocab_size": 30080
36
  }
 
1
  {
2
+ "_name_or_path": "klue/roberta-large",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
  "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
  "id2label": {
15
  "0": "LABEL_0"
16
  },
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
  "label2id": {
20
  "LABEL_0": 0
21
  },
22
  "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "roberta",
25
  "num_attention_heads": 16,
26
  "num_hidden_layers": 24,
27
  "pad_token_id": 2,
28
+ "position_embedding_type": "absolute",
29
+ "tokenizer_class": "BertTokenizer",
 
 
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.34.1",
32
+ "type_vocab_size": 1,
33
  "use_cache": true,
34
+ "vocab_size": 32000
 
35
  }
checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cb45ec156c143e45d0ef8bd0f74e32e249196d711c3b7e36bfa5949b1b7bbbe
3
- size 10161845830
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba251489adc241ca5b80fc76223ef4d3da0cb383b4ce2e38e1b6df12e553a82f
3
+ size 2693490618
checkpoint-500/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:854106c6a2953f168cd714931746fb06fbd548fe5b69803f26f7e17200475f41
3
- size 5080945162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d2f74d9bcc8ca2b625c57615e15de06cb5c20bfd7bda4045de13a365ab13ff7
3
+ size 1346765678
checkpoint-500/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1e8951467f672e599a0e398344ed3975b70688312b5cb70540069055b72cdd8
3
  size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ebeff58a949a84383d357f1360894c8fa9939d4e472a24cc74450ae4313a4bb
3
  size 14308
checkpoint-500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32dae175c043887d5db523143708418db76c276616cbe819e634ecc6b7d59f4a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc61220c925006e8916e7b98f3b9bf9ef82f46341cb3d17973ccd33d25c46fd
3
  size 1064
checkpoint-500/special_tokens_map.json CHANGED
@@ -1,11 +1,9 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|endoftext|>",
4
- "<|sep|>",
5
- "<|acc|>",
6
- "<|tel|>",
7
- "<|rrn|>"
8
- ],
9
- "eos_token": "<|endoftext|>",
10
- "pad_token": "<|endoftext|>"
11
  }
 
1
  {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
 
 
9
  }
checkpoint-500/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<|unused0|>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "<|unused1|>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "<|endoftext|>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,31 +25,15 @@
25
  "special": true
26
  },
27
  "3": {
28
- "content": "<|sep|>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "30000": {
36
- "content": "<|acc|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "30001": {
44
- "content": "<|tel|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "30002": {
52
- "content": "<|rrn|>",
53
  "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
@@ -57,16 +41,19 @@
57
  "special": true
58
  }
59
  },
60
- "additional_special_tokens": [
61
- "<|endoftext|>",
62
- "<|sep|>",
63
- "<|acc|>",
64
- "<|tel|>",
65
- "<|rrn|>"
66
- ],
67
  "clean_up_tokenization_spaces": true,
68
- "eos_token": "<|endoftext|>",
69
- "model_max_length": 1000000000000000019884624838656,
70
- "pad_token": "<|endoftext|>",
71
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
 
 
 
 
72
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[CLS]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "[PAD]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[SEP]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "[UNK]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
+ "content": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "[CLS]",
 
 
 
 
 
 
45
  "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
  }
checkpoint-500/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.812842918106076,
5
  "eval_steps": 100,
6
  "global_step": 500,
7
  "is_hyper_param_search": false,
@@ -10,352 +10,352 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.02,
13
- "learning_rate": 8.994130006901536e-06,
14
- "loss": 0.3053,
15
  "step": 10
16
  },
17
  {
18
  "epoch": 0.03,
19
- "learning_rate": 8.976535341747906e-06,
20
- "loss": 0.1363,
21
  "step": 20
22
  },
23
  {
24
  "epoch": 0.05,
25
- "learning_rate": 8.947261907011569e-06,
26
- "loss": 0.1087,
27
  "step": 30
28
  },
29
  {
30
- "epoch": 0.07,
31
- "learning_rate": 8.906386073741352e-06,
32
- "loss": 0.106,
33
  "step": 40
34
  },
35
  {
36
  "epoch": 0.08,
37
- "learning_rate": 8.85401448231912e-06,
38
- "loss": 0.0791,
39
  "step": 50
40
  },
41
  {
42
- "epoch": 0.1,
43
- "learning_rate": 8.790283764247187e-06,
44
- "loss": 0.0702,
45
  "step": 60
46
  },
47
  {
48
  "epoch": 0.11,
49
- "learning_rate": 8.715360185692326e-06,
50
- "loss": 0.0773,
51
  "step": 70
52
  },
53
  {
54
- "epoch": 0.13,
55
- "learning_rate": 8.629439213716327e-06,
56
- "loss": 0.0583,
57
  "step": 80
58
  },
59
  {
60
- "epoch": 0.15,
61
- "learning_rate": 8.532745006324751e-06,
62
- "loss": 0.0637,
63
  "step": 90
64
  },
65
  {
66
- "epoch": 0.16,
67
- "learning_rate": 8.425529827664287e-06,
68
- "loss": 0.0554,
69
  "step": 100
70
  },
71
  {
72
- "epoch": 0.16,
73
- "eval_accuracy": 0.5,
74
- "eval_loss": 7.870811641330633e-11,
75
- "eval_runtime": 51.3409,
76
- "eval_samples_per_second": 85.195,
77
- "eval_steps_per_second": 10.654,
78
  "step": 100
79
  },
80
  {
81
- "epoch": 0.18,
82
- "learning_rate": 8.308073389894399e-06,
83
- "loss": 0.0666,
84
  "step": 110
85
  },
86
  {
87
- "epoch": 0.2,
88
- "learning_rate": 8.18068212345023e-06,
89
- "loss": 0.0598,
90
  "step": 120
91
  },
92
  {
93
- "epoch": 0.21,
94
- "learning_rate": 8.043688377600596e-06,
95
- "loss": 0.0423,
96
  "step": 130
97
  },
98
  {
99
- "epoch": 0.23,
100
- "learning_rate": 7.897449553386683e-06,
101
- "loss": 0.0311,
102
  "step": 140
103
  },
104
  {
105
- "epoch": 0.24,
106
- "learning_rate": 7.742347171203542e-06,
107
- "loss": 0.0527,
108
  "step": 150
109
  },
110
  {
111
- "epoch": 0.26,
112
- "learning_rate": 7.578785875456937e-06,
113
- "loss": 0.0847,
114
  "step": 160
115
  },
116
  {
117
- "epoch": 0.28,
118
- "learning_rate": 7.407192378892295e-06,
119
- "loss": 0.0595,
120
  "step": 170
121
  },
122
  {
123
- "epoch": 0.29,
124
- "learning_rate": 7.2280143493498716e-06,
125
- "loss": 0.0327,
126
  "step": 180
127
  },
128
  {
129
- "epoch": 0.31,
130
- "learning_rate": 7.041719241850471e-06,
131
- "loss": 0.0877,
132
  "step": 190
133
  },
134
  {
135
- "epoch": 0.33,
136
- "learning_rate": 6.848793079058672e-06,
137
- "loss": 0.0356,
138
  "step": 200
139
  },
140
  {
141
- "epoch": 0.33,
142
- "eval_accuracy": 0.5,
143
- "eval_loss": 9.303278147854144e-08,
144
- "eval_runtime": 53.2016,
145
- "eval_samples_per_second": 82.216,
146
- "eval_steps_per_second": 10.282,
147
  "step": 200
148
  },
149
  {
150
- "epoch": 0.34,
151
- "learning_rate": 6.649739183305183e-06,
152
- "loss": 0.0332,
153
  "step": 210
154
  },
155
  {
156
- "epoch": 0.36,
157
- "learning_rate": 6.445076863476361e-06,
158
- "loss": 0.0537,
159
  "step": 220
160
  },
161
  {
162
- "epoch": 0.37,
163
- "learning_rate": 6.235340060196612e-06,
164
- "loss": 0.0548,
165
  "step": 230
166
  },
167
  {
168
- "epoch": 0.39,
169
- "learning_rate": 6.021075952838263e-06,
170
- "loss": 0.0485,
171
  "step": 240
172
  },
173
  {
174
- "epoch": 0.41,
175
- "learning_rate": 5.802843531993069e-06,
176
- "loss": 0.041,
177
  "step": 250
178
  },
179
  {
180
- "epoch": 0.42,
181
- "learning_rate": 5.581212141129573e-06,
182
- "loss": 0.0266,
183
  "step": 260
184
  },
185
  {
186
- "epoch": 0.44,
187
- "learning_rate": 5.3567599912410075e-06,
188
- "loss": 0.0421,
189
  "step": 270
190
  },
191
  {
192
- "epoch": 0.46,
193
- "learning_rate": 5.130072652358832e-06,
194
- "loss": 0.0522,
195
  "step": 280
196
  },
197
  {
198
- "epoch": 0.47,
199
- "learning_rate": 4.901741525867374e-06,
200
- "loss": 0.0302,
201
  "step": 290
202
  },
203
  {
204
- "epoch": 0.49,
205
- "learning_rate": 4.67236230160516e-06,
206
- "loss": 0.0741,
207
  "step": 300
208
  },
209
  {
210
- "epoch": 0.49,
211
  "eval_accuracy": 0.0,
212
- "eval_loss": 2.2148276457301108e-07,
213
- "eval_runtime": 51.7845,
214
- "eval_samples_per_second": 84.465,
215
- "eval_steps_per_second": 10.563,
216
  "step": 300
217
  },
218
  {
219
- "epoch": 0.5,
220
- "learning_rate": 4.44253340377812e-06,
221
- "loss": 0.0388,
222
  "step": 310
223
  },
224
  {
225
- "epoch": 0.52,
226
- "learning_rate": 4.212854429739172e-06,
227
- "loss": 0.0309,
228
  "step": 320
229
  },
230
  {
231
- "epoch": 0.54,
232
- "learning_rate": 3.983924585707199e-06,
233
- "loss": 0.0288,
234
  "step": 330
235
  },
236
  {
237
- "epoch": 0.55,
238
- "learning_rate": 3.7563411235064183e-06,
239
- "loss": 0.053,
240
  "step": 340
241
  },
242
  {
243
- "epoch": 0.57,
244
- "learning_rate": 3.530697782404584e-06,
245
- "loss": 0.0557,
246
  "step": 350
247
  },
248
  {
249
- "epoch": 0.59,
250
- "learning_rate": 3.3075832401150233e-06,
251
- "loss": 0.0571,
252
  "step": 360
253
  },
254
  {
255
- "epoch": 0.6,
256
- "learning_rate": 3.0875795770036908e-06,
257
- "loss": 0.0436,
258
  "step": 370
259
  },
260
  {
261
- "epoch": 0.62,
262
- "learning_rate": 2.871260757507969e-06,
263
- "loss": 0.0535,
264
  "step": 380
265
  },
266
  {
267
- "epoch": 0.63,
268
- "learning_rate": 2.6591911327289704e-06,
269
- "loss": 0.0265,
270
  "step": 390
271
  },
272
  {
273
- "epoch": 0.65,
274
- "learning_rate": 2.4519239681039617e-06,
275
- "loss": 0.0399,
276
  "step": 400
277
  },
278
  {
279
- "epoch": 0.65,
280
  "eval_accuracy": 0.0,
281
- "eval_loss": 5.652063350680692e-07,
282
- "eval_runtime": 52.7896,
283
- "eval_samples_per_second": 82.857,
284
- "eval_steps_per_second": 10.362,
285
  "step": 400
286
  },
287
  {
288
- "epoch": 0.67,
289
- "learning_rate": 2.250000000000001e-06,
290
- "loss": 0.0365,
291
  "step": 410
292
  },
293
  {
294
- "epoch": 0.68,
295
- "learning_rate": 2.0539460249945052e-06,
296
- "loss": 0.0524,
297
  "step": 420
298
  },
299
  {
300
- "epoch": 0.7,
301
- "learning_rate": 1.8642735255231234e-06,
302
- "loss": 0.033,
303
  "step": 430
304
  },
305
  {
306
- "epoch": 0.72,
307
- "learning_rate": 1.681477335480462e-06,
308
- "loss": 0.03,
309
  "step": 440
310
  },
311
  {
312
- "epoch": 0.73,
313
- "learning_rate": 1.5060343492549563e-06,
314
- "loss": 0.0431,
315
  "step": 450
316
  },
317
  {
318
- "epoch": 0.75,
319
- "learning_rate": 1.3384022775658566e-06,
320
- "loss": 0.0487,
321
  "step": 460
322
  },
323
  {
324
- "epoch": 0.76,
325
- "learning_rate": 1.1790184533482286e-06,
326
- "loss": 0.0261,
327
  "step": 470
328
  },
329
  {
330
- "epoch": 0.78,
331
- "learning_rate": 1.0282986908012566e-06,
332
- "loss": 0.0287,
333
  "step": 480
334
  },
335
  {
336
- "epoch": 0.8,
337
- "learning_rate": 8.866362005764765e-07,
338
- "loss": 0.0259,
339
  "step": 490
340
  },
341
  {
342
- "epoch": 0.81,
343
- "learning_rate": 7.544005639360776e-07,
344
- "loss": 0.0307,
345
  "step": 500
346
  },
347
  {
348
- "epoch": 0.81,
349
- "eval_accuracy": 0.5,
350
- "eval_loss": 1.5770057260056092e-08,
351
- "eval_runtime": 51.4653,
352
- "eval_samples_per_second": 84.989,
353
- "eval_steps_per_second": 10.629,
354
  "step": 500
355
  }
356
  ],
357
  "logging_steps": 10,
358
- "max_steps": 615,
359
  "num_train_epochs": 1,
360
  "save_steps": 100,
361
  "total_flos": 0.0,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7620789513793629,
5
  "eval_steps": 100,
6
  "global_step": 500,
7
  "is_hyper_param_search": false,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.02,
13
+ "learning_rate": 8.99484069051768e-06,
14
+ "loss": 0.672,
15
  "step": 10
16
  },
17
  {
18
  "epoch": 0.03,
19
+ "learning_rate": 8.979374592503753e-06,
20
+ "loss": 0.393,
21
  "step": 20
22
  },
23
  {
24
  "epoch": 0.05,
25
+ "learning_rate": 8.953637170129838e-06,
26
+ "loss": 0.1594,
27
  "step": 30
28
  },
29
  {
30
+ "epoch": 0.06,
31
+ "learning_rate": 8.917687439985847e-06,
32
+ "loss": 0.122,
33
  "step": 40
34
  },
35
  {
36
  "epoch": 0.08,
37
+ "learning_rate": 8.87160783575339e-06,
38
+ "loss": 0.0956,
39
  "step": 50
40
  },
41
  {
42
+ "epoch": 0.09,
43
+ "learning_rate": 8.815504019183158e-06,
44
+ "loss": 0.102,
45
  "step": 60
46
  },
47
  {
48
  "epoch": 0.11,
49
+ "learning_rate": 8.749504637809742e-06,
50
+ "loss": 0.0888,
51
  "step": 70
52
  },
53
  {
54
+ "epoch": 0.12,
55
+ "learning_rate": 8.673761029959426e-06,
56
+ "loss": 0.097,
57
  "step": 80
58
  },
59
  {
60
+ "epoch": 0.14,
61
+ "learning_rate": 8.588446877727417e-06,
62
+ "loss": 0.0968,
63
  "step": 90
64
  },
65
  {
66
+ "epoch": 0.15,
67
+ "learning_rate": 8.493757808720196e-06,
68
+ "loss": 0.0808,
69
  "step": 100
70
  },
71
  {
72
+ "epoch": 0.15,
73
+ "eval_accuracy": 0.0,
74
+ "eval_loss": 3.0685205274494365e-05,
75
+ "eval_runtime": 30.877,
76
+ "eval_samples_per_second": 141.659,
77
+ "eval_steps_per_second": 23.61,
78
  "step": 100
79
  },
80
  {
81
+ "epoch": 0.17,
82
+ "learning_rate": 8.389910947476252e-06,
83
+ "loss": 0.0797,
84
  "step": 110
85
  },
86
  {
87
+ "epoch": 0.18,
88
+ "learning_rate": 8.277144417593776e-06,
89
+ "loss": 0.0933,
90
  "step": 120
91
  },
92
  {
93
+ "epoch": 0.2,
94
+ "learning_rate": 8.155716795706948e-06,
95
+ "loss": 0.084,
96
  "step": 130
97
  },
98
  {
99
+ "epoch": 0.21,
100
+ "learning_rate": 8.02590651856289e-06,
101
+ "loss": 0.0605,
102
  "step": 140
103
  },
104
  {
105
+ "epoch": 0.23,
106
+ "learning_rate": 7.88801124455883e-06,
107
+ "loss": 0.0746,
108
  "step": 150
109
  },
110
  {
111
+ "epoch": 0.24,
112
+ "learning_rate": 7.742347171203542e-06,
113
+ "loss": 0.1016,
114
  "step": 160
115
  },
116
  {
117
+ "epoch": 0.26,
118
+ "learning_rate": 7.589248310068091e-06,
119
+ "loss": 0.0919,
120
  "step": 170
121
  },
122
  {
123
+ "epoch": 0.27,
124
+ "learning_rate": 7.429065720888471e-06,
125
+ "loss": 0.1076,
126
  "step": 180
127
  },
128
  {
129
+ "epoch": 0.29,
130
+ "learning_rate": 7.262166706576352e-06,
131
+ "loss": 0.0586,
132
  "step": 190
133
  },
134
  {
135
+ "epoch": 0.3,
136
+ "learning_rate": 7.088933970983793e-06,
137
+ "loss": 0.0682,
138
  "step": 200
139
  },
140
  {
141
+ "epoch": 0.3,
142
+ "eval_accuracy": 0.0,
143
+ "eval_loss": 9.85040060186293e-06,
144
+ "eval_runtime": 31.5055,
145
+ "eval_samples_per_second": 138.833,
146
+ "eval_steps_per_second": 23.139,
147
  "step": 200
148
  },
149
  {
150
+ "epoch": 0.32,
151
+ "learning_rate": 6.909764741353188e-06,
152
+ "loss": 0.069,
153
  "step": 210
154
  },
155
  {
156
+ "epoch": 0.34,
157
+ "learning_rate": 6.7250698574647064e-06,
158
+ "loss": 0.0483,
159
  "step": 220
160
  },
161
  {
162
+ "epoch": 0.35,
163
+ "learning_rate": 6.5352728295698045e-06,
164
+ "loss": 0.0639,
165
  "step": 230
166
  },
167
  {
168
+ "epoch": 0.37,
169
+ "learning_rate": 6.340808867271031e-06,
170
+ "loss": 0.0865,
171
  "step": 240
172
  },
173
  {
174
+ "epoch": 0.38,
175
+ "learning_rate": 6.142123881574899e-06,
176
+ "loss": 0.0861,
177
  "step": 250
178
  },
179
  {
180
+ "epoch": 0.4,
181
+ "learning_rate": 5.939673462406165e-06,
182
+ "loss": 0.0805,
183
  "step": 260
184
  },
185
  {
186
+ "epoch": 0.41,
187
+ "learning_rate": 5.7339218339280815e-06,
188
+ "loss": 0.0751,
189
  "step": 270
190
  },
191
  {
192
+ "epoch": 0.43,
193
+ "learning_rate": 5.52534079006412e-06,
194
+ "loss": 0.0687,
195
  "step": 280
196
  },
197
  {
198
+ "epoch": 0.44,
199
+ "learning_rate": 5.314408612662028e-06,
200
+ "loss": 0.092,
201
  "step": 290
202
  },
203
  {
204
+ "epoch": 0.46,
205
+ "learning_rate": 5.101608974780918e-06,
206
+ "loss": 0.0718,
207
  "step": 300
208
  },
209
  {
210
+ "epoch": 0.46,
211
  "eval_accuracy": 0.0,
212
+ "eval_loss": 7.04687363395351e-06,
213
+ "eval_runtime": 30.7873,
214
+ "eval_samples_per_second": 142.071,
215
+ "eval_steps_per_second": 23.679,
216
  "step": 300
217
  },
218
  {
219
+ "epoch": 0.47,
220
+ "learning_rate": 4.887429831616148e-06,
221
+ "loss": 0.0556,
222
  "step": 310
223
  },
224
  {
225
+ "epoch": 0.49,
226
+ "learning_rate": 4.67236230160516e-06,
227
+ "loss": 0.0825,
228
  "step": 320
229
  },
230
  {
231
+ "epoch": 0.5,
232
+ "learning_rate": 4.456899540279919e-06,
233
+ "loss": 0.0355,
234
  "step": 330
235
  },
236
  {
237
+ "epoch": 0.52,
238
+ "learning_rate": 4.2415356094482455e-06,
239
+ "loss": 0.0572,
240
  "step": 340
241
  },
242
  {
243
+ "epoch": 0.53,
244
+ "learning_rate": 4.026764344297024e-06,
245
+ "loss": 0.0735,
246
  "step": 350
247
  },
248
  {
249
+ "epoch": 0.55,
250
+ "learning_rate": 3.8130782210150645e-06,
251
+ "loss": 0.0851,
252
  "step": 360
253
  },
254
  {
255
+ "epoch": 0.56,
256
+ "learning_rate": 3.600967227532187e-06,
257
+ "loss": 0.0703,
258
  "step": 370
259
  },
260
  {
261
+ "epoch": 0.58,
262
+ "learning_rate": 3.3909177399639346e-06,
263
+ "loss": 0.0651,
264
  "step": 380
265
  },
266
  {
267
+ "epoch": 0.59,
268
+ "learning_rate": 3.1834114073382947e-06,
269
+ "loss": 0.0596,
270
  "step": 390
271
  },
272
  {
273
+ "epoch": 0.61,
274
+ "learning_rate": 2.9789240471617385e-06,
275
+ "loss": 0.0579,
276
  "step": 400
277
  },
278
  {
279
+ "epoch": 0.61,
280
  "eval_accuracy": 0.0,
281
+ "eval_loss": 3.991552148363553e-06,
282
+ "eval_runtime": 31.7373,
283
+ "eval_samples_per_second": 137.819,
284
+ "eval_steps_per_second": 22.97,
285
  "step": 400
286
  },
287
  {
288
+ "epoch": 0.62,
289
+ "learning_rate": 2.7779245543570964e-06,
290
+ "loss": 0.0457,
291
  "step": 410
292
  },
293
  {
294
+ "epoch": 0.64,
295
+ "learning_rate": 2.580873826075111e-06,
296
+ "loss": 0.0642,
297
  "step": 420
298
  },
299
  {
300
+ "epoch": 0.66,
301
+ "learning_rate": 2.388223704845083e-06,
302
+ "loss": 0.0613,
303
  "step": 430
304
  },
305
  {
306
+ "epoch": 0.67,
307
+ "learning_rate": 2.2004159424880025e-06,
308
+ "loss": 0.0533,
309
  "step": 440
310
  },
311
  {
312
+ "epoch": 0.69,
313
+ "learning_rate": 2.0178811871679537e-06,
314
+ "loss": 0.0533,
315
  "step": 450
316
  },
317
  {
318
+ "epoch": 0.7,
319
+ "learning_rate": 1.8410379959044793e-06,
320
+ "loss": 0.0607,
321
  "step": 460
322
  },
323
  {
324
+ "epoch": 0.72,
325
+ "learning_rate": 1.6702918748102748e-06,
326
+ "loss": 0.0469,
327
  "step": 470
328
  },
329
  {
330
+ "epoch": 0.73,
331
+ "learning_rate": 1.5060343492549563e-06,
332
+ "loss": 0.0754,
333
  "step": 480
334
  },
335
  {
336
+ "epoch": 0.75,
337
+ "learning_rate": 1.3486420660870307e-06,
338
+ "loss": 0.065,
339
  "step": 490
340
  },
341
  {
342
+ "epoch": 0.76,
343
+ "learning_rate": 1.1984759299727166e-06,
344
+ "loss": 0.0557,
345
  "step": 500
346
  },
347
  {
348
+ "epoch": 0.76,
349
+ "eval_accuracy": 0.0,
350
+ "eval_loss": 4.362014351499965e-06,
351
+ "eval_runtime": 30.9641,
352
+ "eval_samples_per_second": 141.26,
353
+ "eval_steps_per_second": 23.543,
354
  "step": 500
355
  }
356
  ],
357
  "logging_steps": 10,
358
+ "max_steps": 656,
359
  "num_train_epochs": 1,
360
  "save_steps": 100,
361
  "total_flos": 0.0,
checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f83b04586007121ba3ee6bfcd4a06860c6098884f4f89ada67554e532440c28
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b0be5f447301b577e44061c504ec9398fb05913a538169784e7cfc7134c7d3
3
  size 4600
checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff