Bram Vanroy commited on
Commit
4ec14e7
1 Parent(s): 1a39287

model init

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pdelobelle/robbert-v2-dutch-base",
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": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.21.0.dev0",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 40000
39
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46bcf05bc1695e23df1ded5d9c92981bf3ac3c0841aea3a0bc2137f9dbb4b21
3
+ size 467129325
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": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "name_or_path": "pdelobelle/robbert-v2-dutch-base",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "./robbert-v2-dutch-base/special_tokens_map.json",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
trainer_state.json ADDED
@@ -0,0 +1,457 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.826051364529945,
3
+ "best_model_checkpoint": "/home/bram/shares/predict/trained/dutch/hebban-reviews/robbert-v2-dutch-base/checkpoint-2500",
4
+ "epoch": 3.9447731755424065,
5
+ "global_step": 12000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 4.7925000000000006e-05,
13
+ "loss": 0.7262,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "eval_accuracy": 0.7467948717948718,
19
+ "eval_f1": 0.7588505397999891,
20
+ "eval_loss": 0.6503846049308777,
21
+ "eval_precision": 0.7826608700318252,
22
+ "eval_recall": 0.7467948717948718,
23
+ "eval_runtime": 24.2662,
24
+ "eval_samples_per_second": 668.584,
25
+ "eval_steps_per_second": 27.858,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 0.33,
30
+ "learning_rate": 4.5841666666666665e-05,
31
+ "loss": 0.6388,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 0.33,
36
+ "eval_accuracy": 0.7707716962524654,
37
+ "eval_f1": 0.7828012503260621,
38
+ "eval_loss": 0.6046772599220276,
39
+ "eval_precision": 0.806817293633085,
40
+ "eval_recall": 0.7707716962524654,
41
+ "eval_runtime": 24.3206,
42
+ "eval_samples_per_second": 667.089,
43
+ "eval_steps_per_second": 27.795,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 0.49,
48
+ "learning_rate": 4.375833333333334e-05,
49
+ "loss": 0.6036,
50
+ "step": 1500
51
+ },
52
+ {
53
+ "epoch": 0.49,
54
+ "eval_accuracy": 0.7991247534516766,
55
+ "eval_f1": 0.8068009793163453,
56
+ "eval_loss": 0.5817954540252686,
57
+ "eval_precision": 0.8200694446499367,
58
+ "eval_recall": 0.7991247534516766,
59
+ "eval_runtime": 24.3415,
60
+ "eval_samples_per_second": 666.516,
61
+ "eval_steps_per_second": 27.771,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 0.66,
66
+ "learning_rate": 4.1675e-05,
67
+ "loss": 0.5894,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 0.66,
72
+ "eval_accuracy": 0.8214373767258383,
73
+ "eval_f1": 0.8223555383757819,
74
+ "eval_loss": 0.5838125944137573,
75
+ "eval_precision": 0.8240754296334577,
76
+ "eval_recall": 0.8214373767258383,
77
+ "eval_runtime": 24.3264,
78
+ "eval_samples_per_second": 666.929,
79
+ "eval_steps_per_second": 27.789,
80
+ "step": 2000
81
+ },
82
+ {
83
+ "epoch": 0.82,
84
+ "learning_rate": 3.960000000000001e-05,
85
+ "loss": 0.5678,
86
+ "step": 2500
87
+ },
88
+ {
89
+ "epoch": 0.82,
90
+ "eval_accuracy": 0.8257519723865878,
91
+ "eval_f1": 0.826051364529945,
92
+ "eval_loss": 0.565325915813446,
93
+ "eval_precision": 0.8264063729685338,
94
+ "eval_recall": 0.8257519723865878,
95
+ "eval_runtime": 24.3378,
96
+ "eval_samples_per_second": 666.617,
97
+ "eval_steps_per_second": 27.776,
98
+ "step": 2500
99
+ },
100
+ {
101
+ "epoch": 0.99,
102
+ "learning_rate": 3.7516666666666666e-05,
103
+ "loss": 0.5821,
104
+ "step": 3000
105
+ },
106
+ {
107
+ "epoch": 0.99,
108
+ "eval_accuracy": 0.8164447731755424,
109
+ "eval_f1": 0.8171577310703354,
110
+ "eval_loss": 0.5594866275787354,
111
+ "eval_precision": 0.8191229796098939,
112
+ "eval_recall": 0.8164447731755424,
113
+ "eval_runtime": 24.3358,
114
+ "eval_samples_per_second": 666.673,
115
+ "eval_steps_per_second": 27.778,
116
+ "step": 3000
117
+ },
118
+ {
119
+ "epoch": 1.15,
120
+ "learning_rate": 3.543333333333333e-05,
121
+ "loss": 0.4741,
122
+ "step": 3500
123
+ },
124
+ {
125
+ "epoch": 1.15,
126
+ "eval_accuracy": 0.7975838264299803,
127
+ "eval_f1": 0.8063837559416328,
128
+ "eval_loss": 0.5798861384391785,
129
+ "eval_precision": 0.8218943463788534,
130
+ "eval_recall": 0.7975838264299803,
131
+ "eval_runtime": 24.3305,
132
+ "eval_samples_per_second": 666.816,
133
+ "eval_steps_per_second": 27.784,
134
+ "step": 3500
135
+ },
136
+ {
137
+ "epoch": 1.31,
138
+ "learning_rate": 3.3350000000000004e-05,
139
+ "loss": 0.4763,
140
+ "step": 4000
141
+ },
142
+ {
143
+ "epoch": 1.31,
144
+ "eval_accuracy": 0.8000493096646942,
145
+ "eval_f1": 0.8080426775793622,
146
+ "eval_loss": 0.5934886336326599,
147
+ "eval_precision": 0.8221336258804294,
148
+ "eval_recall": 0.8000493096646942,
149
+ "eval_runtime": 24.3209,
150
+ "eval_samples_per_second": 667.08,
151
+ "eval_steps_per_second": 27.795,
152
+ "step": 4000
153
+ },
154
+ {
155
+ "epoch": 1.48,
156
+ "learning_rate": 3.126666666666666e-05,
157
+ "loss": 0.4719,
158
+ "step": 4500
159
+ },
160
+ {
161
+ "epoch": 1.48,
162
+ "eval_accuracy": 0.7595537475345168,
163
+ "eval_f1": 0.7769614913537937,
164
+ "eval_loss": 0.5927842855453491,
165
+ "eval_precision": 0.8215588992651691,
166
+ "eval_recall": 0.7595537475345168,
167
+ "eval_runtime": 24.3097,
168
+ "eval_samples_per_second": 667.388,
169
+ "eval_steps_per_second": 27.808,
170
+ "step": 4500
171
+ },
172
+ {
173
+ "epoch": 1.64,
174
+ "learning_rate": 2.91875e-05,
175
+ "loss": 0.477,
176
+ "step": 5000
177
+ },
178
+ {
179
+ "epoch": 1.64,
180
+ "eval_accuracy": 0.8143491124260355,
181
+ "eval_f1": 0.8178014358117583,
182
+ "eval_loss": 0.571167528629303,
183
+ "eval_precision": 0.8224283181214769,
184
+ "eval_recall": 0.8143491124260355,
185
+ "eval_runtime": 24.3019,
186
+ "eval_samples_per_second": 667.601,
187
+ "eval_steps_per_second": 27.817,
188
+ "step": 5000
189
+ },
190
+ {
191
+ "epoch": 1.81,
192
+ "learning_rate": 2.710416666666667e-05,
193
+ "loss": 0.4627,
194
+ "step": 5500
195
+ },
196
+ {
197
+ "epoch": 1.81,
198
+ "eval_accuracy": 0.8163831360946746,
199
+ "eval_f1": 0.8209409596272614,
200
+ "eval_loss": 0.5852541327476501,
201
+ "eval_precision": 0.8276030279019199,
202
+ "eval_recall": 0.8163831360946746,
203
+ "eval_runtime": 24.3288,
204
+ "eval_samples_per_second": 666.863,
205
+ "eval_steps_per_second": 27.786,
206
+ "step": 5500
207
+ },
208
+ {
209
+ "epoch": 1.97,
210
+ "learning_rate": 2.5020833333333333e-05,
211
+ "loss": 0.4669,
212
+ "step": 6000
213
+ },
214
+ {
215
+ "epoch": 1.97,
216
+ "eval_accuracy": 0.823594674556213,
217
+ "eval_f1": 0.8244437619387351,
218
+ "eval_loss": 0.5960806608200073,
219
+ "eval_precision": 0.8258010274342865,
220
+ "eval_recall": 0.823594674556213,
221
+ "eval_runtime": 24.228,
222
+ "eval_samples_per_second": 669.639,
223
+ "eval_steps_per_second": 27.902,
224
+ "step": 6000
225
+ },
226
+ {
227
+ "epoch": 2.14,
228
+ "learning_rate": 2.2937500000000002e-05,
229
+ "loss": 0.3604,
230
+ "step": 6500
231
+ },
232
+ {
233
+ "epoch": 2.14,
234
+ "eval_accuracy": 0.8014669625246549,
235
+ "eval_f1": 0.8102801213854947,
236
+ "eval_loss": 0.6862322092056274,
237
+ "eval_precision": 0.8275335401956307,
238
+ "eval_recall": 0.8014669625246549,
239
+ "eval_runtime": 24.2792,
240
+ "eval_samples_per_second": 668.227,
241
+ "eval_steps_per_second": 27.843,
242
+ "step": 6500
243
+ },
244
+ {
245
+ "epoch": 2.3,
246
+ "learning_rate": 2.0854166666666668e-05,
247
+ "loss": 0.3489,
248
+ "step": 7000
249
+ },
250
+ {
251
+ "epoch": 2.3,
252
+ "eval_accuracy": 0.7792776134122288,
253
+ "eval_f1": 0.7927818598604747,
254
+ "eval_loss": 0.6760165095329285,
255
+ "eval_precision": 0.822269294544987,
256
+ "eval_recall": 0.7792776134122288,
257
+ "eval_runtime": 24.2892,
258
+ "eval_samples_per_second": 667.95,
259
+ "eval_steps_per_second": 27.831,
260
+ "step": 7000
261
+ },
262
+ {
263
+ "epoch": 2.47,
264
+ "learning_rate": 1.8775000000000002e-05,
265
+ "loss": 0.3394,
266
+ "step": 7500
267
+ },
268
+ {
269
+ "epoch": 2.47,
270
+ "eval_accuracy": 0.8185404339250493,
271
+ "eval_f1": 0.8224920113739561,
272
+ "eval_loss": 0.6916875839233398,
273
+ "eval_precision": 0.8283683902286886,
274
+ "eval_recall": 0.8185404339250493,
275
+ "eval_runtime": 24.2568,
276
+ "eval_samples_per_second": 668.844,
277
+ "eval_steps_per_second": 27.868,
278
+ "step": 7500
279
+ },
280
+ {
281
+ "epoch": 2.63,
282
+ "learning_rate": 1.6695833333333334e-05,
283
+ "loss": 0.3462,
284
+ "step": 8000
285
+ },
286
+ {
287
+ "epoch": 2.63,
288
+ "eval_accuracy": 0.8147805719921104,
289
+ "eval_f1": 0.8200537266341018,
290
+ "eval_loss": 0.6634742617607117,
291
+ "eval_precision": 0.8279502059904518,
292
+ "eval_recall": 0.8147805719921104,
293
+ "eval_runtime": 24.237,
294
+ "eval_samples_per_second": 669.39,
295
+ "eval_steps_per_second": 27.891,
296
+ "step": 8000
297
+ },
298
+ {
299
+ "epoch": 2.79,
300
+ "learning_rate": 1.4612500000000001e-05,
301
+ "loss": 0.3498,
302
+ "step": 8500
303
+ },
304
+ {
305
+ "epoch": 2.79,
306
+ "eval_accuracy": 0.8173076923076923,
307
+ "eval_f1": 0.8219188790015944,
308
+ "eval_loss": 0.6741124987602234,
309
+ "eval_precision": 0.8291747460835226,
310
+ "eval_recall": 0.8173076923076923,
311
+ "eval_runtime": 24.3305,
312
+ "eval_samples_per_second": 666.817,
313
+ "eval_steps_per_second": 27.784,
314
+ "step": 8500
315
+ },
316
+ {
317
+ "epoch": 2.96,
318
+ "learning_rate": 1.2529166666666667e-05,
319
+ "loss": 0.335,
320
+ "step": 9000
321
+ },
322
+ {
323
+ "epoch": 2.96,
324
+ "eval_accuracy": 0.8091715976331361,
325
+ "eval_f1": 0.8160105785088146,
326
+ "eval_loss": 0.6432847380638123,
327
+ "eval_precision": 0.8271351948602929,
328
+ "eval_recall": 0.8091715976331361,
329
+ "eval_runtime": 24.2377,
330
+ "eval_samples_per_second": 669.372,
331
+ "eval_steps_per_second": 27.89,
332
+ "step": 9000
333
+ },
334
+ {
335
+ "epoch": 3.12,
336
+ "learning_rate": 1.0445833333333334e-05,
337
+ "loss": 0.2724,
338
+ "step": 9500
339
+ },
340
+ {
341
+ "epoch": 3.12,
342
+ "eval_accuracy": 0.8155818540433925,
343
+ "eval_f1": 0.8200452160739635,
344
+ "eval_loss": 0.778809666633606,
345
+ "eval_precision": 0.8263415739712193,
346
+ "eval_recall": 0.8155818540433925,
347
+ "eval_runtime": 24.3292,
348
+ "eval_samples_per_second": 666.853,
349
+ "eval_steps_per_second": 27.786,
350
+ "step": 9500
351
+ },
352
+ {
353
+ "epoch": 3.29,
354
+ "learning_rate": 8.362500000000002e-06,
355
+ "loss": 0.2404,
356
+ "step": 10000
357
+ },
358
+ {
359
+ "epoch": 3.29,
360
+ "eval_accuracy": 0.8102194280078896,
361
+ "eval_f1": 0.8165639264989629,
362
+ "eval_loss": 0.7925969958305359,
363
+ "eval_precision": 0.8272230495650681,
364
+ "eval_recall": 0.8102194280078896,
365
+ "eval_runtime": 24.3267,
366
+ "eval_samples_per_second": 666.921,
367
+ "eval_steps_per_second": 27.788,
368
+ "step": 10000
369
+ },
370
+ {
371
+ "epoch": 3.45,
372
+ "learning_rate": 6.2791666666666665e-06,
373
+ "loss": 0.2417,
374
+ "step": 10500
375
+ },
376
+ {
377
+ "epoch": 3.45,
378
+ "eval_accuracy": 0.811698717948718,
379
+ "eval_f1": 0.8176421251758528,
380
+ "eval_loss": 0.8324716687202454,
381
+ "eval_precision": 0.8284127391855651,
382
+ "eval_recall": 0.811698717948718,
383
+ "eval_runtime": 24.2309,
384
+ "eval_samples_per_second": 669.559,
385
+ "eval_steps_per_second": 27.898,
386
+ "step": 10500
387
+ },
388
+ {
389
+ "epoch": 3.62,
390
+ "learning_rate": 4.2000000000000004e-06,
391
+ "loss": 0.2426,
392
+ "step": 11000
393
+ },
394
+ {
395
+ "epoch": 3.62,
396
+ "eval_accuracy": 0.8218071992110454,
397
+ "eval_f1": 0.8237488575881482,
398
+ "eval_loss": 0.835399866104126,
399
+ "eval_precision": 0.8261715829036445,
400
+ "eval_recall": 0.8218071992110454,
401
+ "eval_runtime": 24.2418,
402
+ "eval_samples_per_second": 669.257,
403
+ "eval_steps_per_second": 27.886,
404
+ "step": 11000
405
+ },
406
+ {
407
+ "epoch": 3.78,
408
+ "learning_rate": 2.1166666666666666e-06,
409
+ "loss": 0.2399,
410
+ "step": 11500
411
+ },
412
+ {
413
+ "epoch": 3.78,
414
+ "eval_accuracy": 0.8130547337278107,
415
+ "eval_f1": 0.8181997138713092,
416
+ "eval_loss": 0.8061773777008057,
417
+ "eval_precision": 0.8260171371000359,
418
+ "eval_recall": 0.8130547337278107,
419
+ "eval_runtime": 24.2269,
420
+ "eval_samples_per_second": 669.67,
421
+ "eval_steps_per_second": 27.903,
422
+ "step": 11500
423
+ },
424
+ {
425
+ "epoch": 3.94,
426
+ "learning_rate": 3.3333333333333334e-08,
427
+ "loss": 0.2292,
428
+ "step": 12000
429
+ },
430
+ {
431
+ "epoch": 3.94,
432
+ "eval_accuracy": 0.8134245562130178,
433
+ "eval_f1": 0.8183934985407206,
434
+ "eval_loss": 0.8132809996604919,
435
+ "eval_precision": 0.8258917495347268,
436
+ "eval_recall": 0.8134245562130178,
437
+ "eval_runtime": 24.2378,
438
+ "eval_samples_per_second": 669.369,
439
+ "eval_steps_per_second": 27.89,
440
+ "step": 12000
441
+ },
442
+ {
443
+ "epoch": 3.94,
444
+ "step": 12000,
445
+ "total_flos": 1.481337892587438e+17,
446
+ "train_loss": 0.42010608355204265,
447
+ "train_runtime": 3460.7395,
448
+ "train_samples_per_second": 166.438,
449
+ "train_steps_per_second": 3.467
450
+ }
451
+ ],
452
+ "max_steps": 12000,
453
+ "num_train_epochs": 4,
454
+ "total_flos": 1.481337892587438e+17,
455
+ "trial_name": null,
456
+ "trial_params": null
457
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a595e075a32f1895e812ed866d982ad1bfebea5e607b63f47a60a916b06e1199
3
+ size 3375
vocab.json ADDED
The diff for this file is too large to render. See raw diff