shax commited on
Commit
018b51c
1 Parent(s): 0c2a9cf
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.784880518913269,
4
+ "eval_runtime": 4.5526,
5
+ "eval_samples": 800,
6
+ "eval_samples_per_second": 175.724,
7
+ "eval_steps_per_second": 21.965,
8
+ "perplexity": 5.958867933030973,
9
+ "train_loss": 1.8707820080738695,
10
+ "train_runtime": 8847.0854,
11
+ "train_samples": 15300,
12
+ "train_samples_per_second": 8.647,
13
+ "train_steps_per_second": 1.081
14
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.12.5",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.784880518913269,
4
+ "eval_runtime": 4.5526,
5
+ "eval_samples": 800,
6
+ "eval_samples_per_second": 175.724,
7
+ "eval_steps_per_second": 21.965,
8
+ "perplexity": 5.958867933030973
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f0b2bd31bd53c3e11cbe1a663831aa839a536ab4068b46b06c2971f0e6b06e
3
+ size 2240743698
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 1.8707820080738695,
4
+ "train_runtime": 8847.0854,
5
+ "train_samples": 15300,
6
+ "train_samples_per_second": 8.647,
7
+ "train_steps_per_second": 1.081
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,839 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 9565,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "eval_loss": 2.07426118850708,
13
+ "eval_runtime": 4.5218,
14
+ "eval_samples_per_second": 176.919,
15
+ "eval_steps_per_second": 22.115,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.1,
20
+ "eval_loss": 2.1192378997802734,
21
+ "eval_runtime": 4.5039,
22
+ "eval_samples_per_second": 177.622,
23
+ "eval_steps_per_second": 22.203,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.16,
28
+ "eval_loss": 2.0722081661224365,
29
+ "eval_runtime": 4.515,
30
+ "eval_samples_per_second": 177.189,
31
+ "eval_steps_per_second": 22.149,
32
+ "step": 300
33
+ },
34
+ {
35
+ "epoch": 0.21,
36
+ "eval_loss": 1.9933481216430664,
37
+ "eval_runtime": 4.523,
38
+ "eval_samples_per_second": 176.873,
39
+ "eval_steps_per_second": 22.109,
40
+ "step": 400
41
+ },
42
+ {
43
+ "epoch": 0.26,
44
+ "eval_loss": 1.922950029373169,
45
+ "eval_runtime": 4.5117,
46
+ "eval_samples_per_second": 177.317,
47
+ "eval_steps_per_second": 22.165,
48
+ "step": 500
49
+ },
50
+ {
51
+ "epoch": 0.31,
52
+ "eval_loss": 2.1238279342651367,
53
+ "eval_runtime": 4.5134,
54
+ "eval_samples_per_second": 177.248,
55
+ "eval_steps_per_second": 22.156,
56
+ "step": 600
57
+ },
58
+ {
59
+ "epoch": 0.37,
60
+ "eval_loss": 1.962709665298462,
61
+ "eval_runtime": 4.5323,
62
+ "eval_samples_per_second": 176.511,
63
+ "eval_steps_per_second": 22.064,
64
+ "step": 700
65
+ },
66
+ {
67
+ "epoch": 0.42,
68
+ "eval_loss": 1.95835542678833,
69
+ "eval_runtime": 4.5072,
70
+ "eval_samples_per_second": 177.495,
71
+ "eval_steps_per_second": 22.187,
72
+ "step": 800
73
+ },
74
+ {
75
+ "epoch": 0.47,
76
+ "eval_loss": 2.001847505569458,
77
+ "eval_runtime": 4.5141,
78
+ "eval_samples_per_second": 177.221,
79
+ "eval_steps_per_second": 22.153,
80
+ "step": 900
81
+ },
82
+ {
83
+ "epoch": 0.52,
84
+ "learning_rate": 8.954521693674857e-06,
85
+ "loss": 2.153,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 0.52,
90
+ "eval_loss": 2.0234880447387695,
91
+ "eval_runtime": 4.5971,
92
+ "eval_samples_per_second": 174.022,
93
+ "eval_steps_per_second": 21.753,
94
+ "step": 1000
95
+ },
96
+ {
97
+ "epoch": 0.58,
98
+ "eval_loss": 1.8845772743225098,
99
+ "eval_runtime": 4.5129,
100
+ "eval_samples_per_second": 177.269,
101
+ "eval_steps_per_second": 22.159,
102
+ "step": 1100
103
+ },
104
+ {
105
+ "epoch": 0.63,
106
+ "eval_loss": 1.9476629495620728,
107
+ "eval_runtime": 4.5112,
108
+ "eval_samples_per_second": 177.337,
109
+ "eval_steps_per_second": 22.167,
110
+ "step": 1200
111
+ },
112
+ {
113
+ "epoch": 0.68,
114
+ "eval_loss": 1.9745019674301147,
115
+ "eval_runtime": 4.5047,
116
+ "eval_samples_per_second": 177.592,
117
+ "eval_steps_per_second": 22.199,
118
+ "step": 1300
119
+ },
120
+ {
121
+ "epoch": 0.73,
122
+ "eval_loss": 1.9027578830718994,
123
+ "eval_runtime": 4.5114,
124
+ "eval_samples_per_second": 177.33,
125
+ "eval_steps_per_second": 22.166,
126
+ "step": 1400
127
+ },
128
+ {
129
+ "epoch": 0.78,
130
+ "eval_loss": 1.8273848295211792,
131
+ "eval_runtime": 4.5108,
132
+ "eval_samples_per_second": 177.35,
133
+ "eval_steps_per_second": 22.169,
134
+ "step": 1500
135
+ },
136
+ {
137
+ "epoch": 0.84,
138
+ "eval_loss": 1.8856213092803955,
139
+ "eval_runtime": 4.5175,
140
+ "eval_samples_per_second": 177.09,
141
+ "eval_steps_per_second": 22.136,
142
+ "step": 1600
143
+ },
144
+ {
145
+ "epoch": 0.89,
146
+ "eval_loss": 1.923270583152771,
147
+ "eval_runtime": 4.5201,
148
+ "eval_samples_per_second": 176.988,
149
+ "eval_steps_per_second": 22.123,
150
+ "step": 1700
151
+ },
152
+ {
153
+ "epoch": 0.94,
154
+ "eval_loss": 2.0153915882110596,
155
+ "eval_runtime": 4.5025,
156
+ "eval_samples_per_second": 177.679,
157
+ "eval_steps_per_second": 22.21,
158
+ "step": 1800
159
+ },
160
+ {
161
+ "epoch": 0.99,
162
+ "eval_loss": 1.9392834901809692,
163
+ "eval_runtime": 4.5093,
164
+ "eval_samples_per_second": 177.412,
165
+ "eval_steps_per_second": 22.177,
166
+ "step": 1900
167
+ },
168
+ {
169
+ "epoch": 1.05,
170
+ "learning_rate": 7.909043387349713e-06,
171
+ "loss": 2.0544,
172
+ "step": 2000
173
+ },
174
+ {
175
+ "epoch": 1.05,
176
+ "eval_loss": 1.8981847763061523,
177
+ "eval_runtime": 4.5359,
178
+ "eval_samples_per_second": 176.371,
179
+ "eval_steps_per_second": 22.046,
180
+ "step": 2000
181
+ },
182
+ {
183
+ "epoch": 1.1,
184
+ "eval_loss": 1.7835720777511597,
185
+ "eval_runtime": 4.507,
186
+ "eval_samples_per_second": 177.502,
187
+ "eval_steps_per_second": 22.188,
188
+ "step": 2100
189
+ },
190
+ {
191
+ "epoch": 1.15,
192
+ "eval_loss": 1.8530174493789673,
193
+ "eval_runtime": 4.5153,
194
+ "eval_samples_per_second": 177.176,
195
+ "eval_steps_per_second": 22.147,
196
+ "step": 2200
197
+ },
198
+ {
199
+ "epoch": 1.2,
200
+ "eval_loss": 1.923173189163208,
201
+ "eval_runtime": 4.499,
202
+ "eval_samples_per_second": 177.817,
203
+ "eval_steps_per_second": 22.227,
204
+ "step": 2300
205
+ },
206
+ {
207
+ "epoch": 1.25,
208
+ "eval_loss": 1.8458834886550903,
209
+ "eval_runtime": 4.4986,
210
+ "eval_samples_per_second": 177.834,
211
+ "eval_steps_per_second": 22.229,
212
+ "step": 2400
213
+ },
214
+ {
215
+ "epoch": 1.31,
216
+ "eval_loss": 1.9027942419052124,
217
+ "eval_runtime": 4.5007,
218
+ "eval_samples_per_second": 177.752,
219
+ "eval_steps_per_second": 22.219,
220
+ "step": 2500
221
+ },
222
+ {
223
+ "epoch": 1.36,
224
+ "eval_loss": 1.9002165794372559,
225
+ "eval_runtime": 4.5078,
226
+ "eval_samples_per_second": 177.472,
227
+ "eval_steps_per_second": 22.184,
228
+ "step": 2600
229
+ },
230
+ {
231
+ "epoch": 1.41,
232
+ "eval_loss": 1.8325750827789307,
233
+ "eval_runtime": 4.4946,
234
+ "eval_samples_per_second": 177.992,
235
+ "eval_steps_per_second": 22.249,
236
+ "step": 2700
237
+ },
238
+ {
239
+ "epoch": 1.46,
240
+ "eval_loss": 1.7771005630493164,
241
+ "eval_runtime": 4.5026,
242
+ "eval_samples_per_second": 177.675,
243
+ "eval_steps_per_second": 22.209,
244
+ "step": 2800
245
+ },
246
+ {
247
+ "epoch": 1.52,
248
+ "eval_loss": 1.8039147853851318,
249
+ "eval_runtime": 4.5124,
250
+ "eval_samples_per_second": 177.289,
251
+ "eval_steps_per_second": 22.161,
252
+ "step": 2900
253
+ },
254
+ {
255
+ "epoch": 1.57,
256
+ "learning_rate": 6.863565081024569e-06,
257
+ "loss": 1.9527,
258
+ "step": 3000
259
+ },
260
+ {
261
+ "epoch": 1.57,
262
+ "eval_loss": 1.7938885688781738,
263
+ "eval_runtime": 4.5501,
264
+ "eval_samples_per_second": 175.821,
265
+ "eval_steps_per_second": 21.978,
266
+ "step": 3000
267
+ },
268
+ {
269
+ "epoch": 1.62,
270
+ "eval_loss": 1.8785758018493652,
271
+ "eval_runtime": 4.5047,
272
+ "eval_samples_per_second": 177.594,
273
+ "eval_steps_per_second": 22.199,
274
+ "step": 3100
275
+ },
276
+ {
277
+ "epoch": 1.67,
278
+ "eval_loss": 1.9068948030471802,
279
+ "eval_runtime": 4.5135,
280
+ "eval_samples_per_second": 177.248,
281
+ "eval_steps_per_second": 22.156,
282
+ "step": 3200
283
+ },
284
+ {
285
+ "epoch": 1.73,
286
+ "eval_loss": 1.904042363166809,
287
+ "eval_runtime": 4.501,
288
+ "eval_samples_per_second": 177.74,
289
+ "eval_steps_per_second": 22.218,
290
+ "step": 3300
291
+ },
292
+ {
293
+ "epoch": 1.78,
294
+ "eval_loss": 1.7986688613891602,
295
+ "eval_runtime": 4.5011,
296
+ "eval_samples_per_second": 177.733,
297
+ "eval_steps_per_second": 22.217,
298
+ "step": 3400
299
+ },
300
+ {
301
+ "epoch": 1.83,
302
+ "eval_loss": 1.8004988431930542,
303
+ "eval_runtime": 4.5008,
304
+ "eval_samples_per_second": 177.745,
305
+ "eval_steps_per_second": 22.218,
306
+ "step": 3500
307
+ },
308
+ {
309
+ "epoch": 1.88,
310
+ "eval_loss": 1.7914013862609863,
311
+ "eval_runtime": 4.5051,
312
+ "eval_samples_per_second": 177.575,
313
+ "eval_steps_per_second": 22.197,
314
+ "step": 3600
315
+ },
316
+ {
317
+ "epoch": 1.93,
318
+ "eval_loss": 1.809700608253479,
319
+ "eval_runtime": 4.5139,
320
+ "eval_samples_per_second": 177.231,
321
+ "eval_steps_per_second": 22.154,
322
+ "step": 3700
323
+ },
324
+ {
325
+ "epoch": 1.99,
326
+ "eval_loss": 1.7780152559280396,
327
+ "eval_runtime": 4.5094,
328
+ "eval_samples_per_second": 177.406,
329
+ "eval_steps_per_second": 22.176,
330
+ "step": 3800
331
+ },
332
+ {
333
+ "epoch": 2.04,
334
+ "eval_loss": 1.8305178880691528,
335
+ "eval_runtime": 4.5176,
336
+ "eval_samples_per_second": 177.085,
337
+ "eval_steps_per_second": 22.136,
338
+ "step": 3900
339
+ },
340
+ {
341
+ "epoch": 2.09,
342
+ "learning_rate": 5.8180867746994255e-06,
343
+ "loss": 1.8792,
344
+ "step": 4000
345
+ },
346
+ {
347
+ "epoch": 2.09,
348
+ "eval_loss": 1.8090060949325562,
349
+ "eval_runtime": 4.5767,
350
+ "eval_samples_per_second": 174.798,
351
+ "eval_steps_per_second": 21.85,
352
+ "step": 4000
353
+ },
354
+ {
355
+ "epoch": 2.14,
356
+ "eval_loss": 1.8800756931304932,
357
+ "eval_runtime": 4.5273,
358
+ "eval_samples_per_second": 176.707,
359
+ "eval_steps_per_second": 22.088,
360
+ "step": 4100
361
+ },
362
+ {
363
+ "epoch": 2.2,
364
+ "eval_loss": 1.8428661823272705,
365
+ "eval_runtime": 4.5326,
366
+ "eval_samples_per_second": 176.498,
367
+ "eval_steps_per_second": 22.062,
368
+ "step": 4200
369
+ },
370
+ {
371
+ "epoch": 2.25,
372
+ "eval_loss": 1.6927213668823242,
373
+ "eval_runtime": 4.5371,
374
+ "eval_samples_per_second": 176.326,
375
+ "eval_steps_per_second": 22.041,
376
+ "step": 4300
377
+ },
378
+ {
379
+ "epoch": 2.3,
380
+ "eval_loss": 1.8311362266540527,
381
+ "eval_runtime": 4.5735,
382
+ "eval_samples_per_second": 174.921,
383
+ "eval_steps_per_second": 21.865,
384
+ "step": 4400
385
+ },
386
+ {
387
+ "epoch": 2.35,
388
+ "eval_loss": 1.7397173643112183,
389
+ "eval_runtime": 4.5487,
390
+ "eval_samples_per_second": 175.875,
391
+ "eval_steps_per_second": 21.984,
392
+ "step": 4500
393
+ },
394
+ {
395
+ "epoch": 2.4,
396
+ "eval_loss": 1.7626467943191528,
397
+ "eval_runtime": 4.524,
398
+ "eval_samples_per_second": 176.836,
399
+ "eval_steps_per_second": 22.105,
400
+ "step": 4600
401
+ },
402
+ {
403
+ "epoch": 2.46,
404
+ "eval_loss": 1.7439056634902954,
405
+ "eval_runtime": 4.5428,
406
+ "eval_samples_per_second": 176.104,
407
+ "eval_steps_per_second": 22.013,
408
+ "step": 4700
409
+ },
410
+ {
411
+ "epoch": 2.51,
412
+ "eval_loss": 1.8606833219528198,
413
+ "eval_runtime": 4.5132,
414
+ "eval_samples_per_second": 177.258,
415
+ "eval_steps_per_second": 22.157,
416
+ "step": 4800
417
+ },
418
+ {
419
+ "epoch": 2.56,
420
+ "eval_loss": 1.756654977798462,
421
+ "eval_runtime": 4.5487,
422
+ "eval_samples_per_second": 175.876,
423
+ "eval_steps_per_second": 21.984,
424
+ "step": 4900
425
+ },
426
+ {
427
+ "epoch": 2.61,
428
+ "learning_rate": 4.7726084683742815e-06,
429
+ "loss": 1.8665,
430
+ "step": 5000
431
+ },
432
+ {
433
+ "epoch": 2.61,
434
+ "eval_loss": 1.7967605590820312,
435
+ "eval_runtime": 4.5714,
436
+ "eval_samples_per_second": 175.001,
437
+ "eval_steps_per_second": 21.875,
438
+ "step": 5000
439
+ },
440
+ {
441
+ "epoch": 2.67,
442
+ "eval_loss": 1.6581268310546875,
443
+ "eval_runtime": 4.5516,
444
+ "eval_samples_per_second": 175.762,
445
+ "eval_steps_per_second": 21.97,
446
+ "step": 5100
447
+ },
448
+ {
449
+ "epoch": 2.72,
450
+ "eval_loss": 1.746982455253601,
451
+ "eval_runtime": 4.5429,
452
+ "eval_samples_per_second": 176.098,
453
+ "eval_steps_per_second": 22.012,
454
+ "step": 5200
455
+ },
456
+ {
457
+ "epoch": 2.77,
458
+ "eval_loss": 1.7988170385360718,
459
+ "eval_runtime": 4.5109,
460
+ "eval_samples_per_second": 177.348,
461
+ "eval_steps_per_second": 22.169,
462
+ "step": 5300
463
+ },
464
+ {
465
+ "epoch": 2.82,
466
+ "eval_loss": 1.7785247564315796,
467
+ "eval_runtime": 4.5225,
468
+ "eval_samples_per_second": 176.894,
469
+ "eval_steps_per_second": 22.112,
470
+ "step": 5400
471
+ },
472
+ {
473
+ "epoch": 2.88,
474
+ "eval_loss": 1.773697853088379,
475
+ "eval_runtime": 4.5413,
476
+ "eval_samples_per_second": 176.159,
477
+ "eval_steps_per_second": 22.02,
478
+ "step": 5500
479
+ },
480
+ {
481
+ "epoch": 2.93,
482
+ "eval_loss": 1.7781400680541992,
483
+ "eval_runtime": 4.5399,
484
+ "eval_samples_per_second": 176.215,
485
+ "eval_steps_per_second": 22.027,
486
+ "step": 5600
487
+ },
488
+ {
489
+ "epoch": 2.98,
490
+ "eval_loss": 1.7938991785049438,
491
+ "eval_runtime": 4.5409,
492
+ "eval_samples_per_second": 176.178,
493
+ "eval_steps_per_second": 22.022,
494
+ "step": 5700
495
+ },
496
+ {
497
+ "epoch": 3.03,
498
+ "eval_loss": 1.8099168539047241,
499
+ "eval_runtime": 4.531,
500
+ "eval_samples_per_second": 176.562,
501
+ "eval_steps_per_second": 22.07,
502
+ "step": 5800
503
+ },
504
+ {
505
+ "epoch": 3.08,
506
+ "eval_loss": 1.6920589208602905,
507
+ "eval_runtime": 4.5199,
508
+ "eval_samples_per_second": 176.996,
509
+ "eval_steps_per_second": 22.125,
510
+ "step": 5900
511
+ },
512
+ {
513
+ "epoch": 3.14,
514
+ "learning_rate": 3.727130162049138e-06,
515
+ "loss": 1.8279,
516
+ "step": 6000
517
+ },
518
+ {
519
+ "epoch": 3.14,
520
+ "eval_loss": 1.797145128250122,
521
+ "eval_runtime": 4.5816,
522
+ "eval_samples_per_second": 174.611,
523
+ "eval_steps_per_second": 21.826,
524
+ "step": 6000
525
+ },
526
+ {
527
+ "epoch": 3.19,
528
+ "eval_loss": 1.7772976160049438,
529
+ "eval_runtime": 4.5504,
530
+ "eval_samples_per_second": 175.809,
531
+ "eval_steps_per_second": 21.976,
532
+ "step": 6100
533
+ },
534
+ {
535
+ "epoch": 3.24,
536
+ "eval_loss": 1.7359503507614136,
537
+ "eval_runtime": 4.5413,
538
+ "eval_samples_per_second": 176.162,
539
+ "eval_steps_per_second": 22.02,
540
+ "step": 6200
541
+ },
542
+ {
543
+ "epoch": 3.29,
544
+ "eval_loss": 1.784250020980835,
545
+ "eval_runtime": 4.5269,
546
+ "eval_samples_per_second": 176.722,
547
+ "eval_steps_per_second": 22.09,
548
+ "step": 6300
549
+ },
550
+ {
551
+ "epoch": 3.35,
552
+ "eval_loss": 1.7917590141296387,
553
+ "eval_runtime": 4.539,
554
+ "eval_samples_per_second": 176.25,
555
+ "eval_steps_per_second": 22.031,
556
+ "step": 6400
557
+ },
558
+ {
559
+ "epoch": 3.4,
560
+ "eval_loss": 1.8440731763839722,
561
+ "eval_runtime": 4.5363,
562
+ "eval_samples_per_second": 176.356,
563
+ "eval_steps_per_second": 22.045,
564
+ "step": 6500
565
+ },
566
+ {
567
+ "epoch": 3.45,
568
+ "eval_loss": 1.7029565572738647,
569
+ "eval_runtime": 4.5307,
570
+ "eval_samples_per_second": 176.574,
571
+ "eval_steps_per_second": 22.072,
572
+ "step": 6600
573
+ },
574
+ {
575
+ "epoch": 3.5,
576
+ "eval_loss": 1.795900583267212,
577
+ "eval_runtime": 4.5612,
578
+ "eval_samples_per_second": 175.391,
579
+ "eval_steps_per_second": 21.924,
580
+ "step": 6700
581
+ },
582
+ {
583
+ "epoch": 3.55,
584
+ "eval_loss": 1.7106671333312988,
585
+ "eval_runtime": 4.5484,
586
+ "eval_samples_per_second": 175.888,
587
+ "eval_steps_per_second": 21.986,
588
+ "step": 6800
589
+ },
590
+ {
591
+ "epoch": 3.61,
592
+ "eval_loss": 1.7240768671035767,
593
+ "eval_runtime": 4.5058,
594
+ "eval_samples_per_second": 177.55,
595
+ "eval_steps_per_second": 22.194,
596
+ "step": 6900
597
+ },
598
+ {
599
+ "epoch": 3.66,
600
+ "learning_rate": 2.681651855723994e-06,
601
+ "loss": 1.7734,
602
+ "step": 7000
603
+ },
604
+ {
605
+ "epoch": 3.66,
606
+ "eval_loss": 1.690421462059021,
607
+ "eval_runtime": 4.5879,
608
+ "eval_samples_per_second": 174.371,
609
+ "eval_steps_per_second": 21.796,
610
+ "step": 7000
611
+ },
612
+ {
613
+ "epoch": 3.71,
614
+ "eval_loss": 1.7392058372497559,
615
+ "eval_runtime": 4.5577,
616
+ "eval_samples_per_second": 175.528,
617
+ "eval_steps_per_second": 21.941,
618
+ "step": 7100
619
+ },
620
+ {
621
+ "epoch": 3.76,
622
+ "eval_loss": 1.6490362882614136,
623
+ "eval_runtime": 4.5443,
624
+ "eval_samples_per_second": 176.043,
625
+ "eval_steps_per_second": 22.005,
626
+ "step": 7200
627
+ },
628
+ {
629
+ "epoch": 3.82,
630
+ "eval_loss": 1.7596625089645386,
631
+ "eval_runtime": 4.534,
632
+ "eval_samples_per_second": 176.445,
633
+ "eval_steps_per_second": 22.056,
634
+ "step": 7300
635
+ },
636
+ {
637
+ "epoch": 3.87,
638
+ "eval_loss": 1.7427598237991333,
639
+ "eval_runtime": 4.5411,
640
+ "eval_samples_per_second": 176.168,
641
+ "eval_steps_per_second": 22.021,
642
+ "step": 7400
643
+ },
644
+ {
645
+ "epoch": 3.92,
646
+ "eval_loss": 1.7453887462615967,
647
+ "eval_runtime": 4.5345,
648
+ "eval_samples_per_second": 176.424,
649
+ "eval_steps_per_second": 22.053,
650
+ "step": 7500
651
+ },
652
+ {
653
+ "epoch": 3.97,
654
+ "eval_loss": 1.6702288389205933,
655
+ "eval_runtime": 4.5374,
656
+ "eval_samples_per_second": 176.311,
657
+ "eval_steps_per_second": 22.039,
658
+ "step": 7600
659
+ },
660
+ {
661
+ "epoch": 4.03,
662
+ "eval_loss": 1.8289847373962402,
663
+ "eval_runtime": 5.0124,
664
+ "eval_samples_per_second": 159.603,
665
+ "eval_steps_per_second": 19.95,
666
+ "step": 7700
667
+ },
668
+ {
669
+ "epoch": 4.08,
670
+ "eval_loss": 1.8589656352996826,
671
+ "eval_runtime": 4.5769,
672
+ "eval_samples_per_second": 174.79,
673
+ "eval_steps_per_second": 21.849,
674
+ "step": 7800
675
+ },
676
+ {
677
+ "epoch": 4.13,
678
+ "eval_loss": 1.7294247150421143,
679
+ "eval_runtime": 4.5529,
680
+ "eval_samples_per_second": 175.711,
681
+ "eval_steps_per_second": 21.964,
682
+ "step": 7900
683
+ },
684
+ {
685
+ "epoch": 4.18,
686
+ "learning_rate": 1.63617354939885e-06,
687
+ "loss": 1.7346,
688
+ "step": 8000
689
+ },
690
+ {
691
+ "epoch": 4.18,
692
+ "eval_loss": 1.7356834411621094,
693
+ "eval_runtime": 4.5781,
694
+ "eval_samples_per_second": 174.745,
695
+ "eval_steps_per_second": 21.843,
696
+ "step": 8000
697
+ },
698
+ {
699
+ "epoch": 4.23,
700
+ "eval_loss": 1.8036160469055176,
701
+ "eval_runtime": 4.5507,
702
+ "eval_samples_per_second": 175.796,
703
+ "eval_steps_per_second": 21.974,
704
+ "step": 8100
705
+ },
706
+ {
707
+ "epoch": 4.29,
708
+ "eval_loss": 1.6360139846801758,
709
+ "eval_runtime": 4.5357,
710
+ "eval_samples_per_second": 176.379,
711
+ "eval_steps_per_second": 22.047,
712
+ "step": 8200
713
+ },
714
+ {
715
+ "epoch": 4.34,
716
+ "eval_loss": 1.710027813911438,
717
+ "eval_runtime": 4.5265,
718
+ "eval_samples_per_second": 176.736,
719
+ "eval_steps_per_second": 22.092,
720
+ "step": 8300
721
+ },
722
+ {
723
+ "epoch": 4.39,
724
+ "eval_loss": 1.7591100931167603,
725
+ "eval_runtime": 4.5309,
726
+ "eval_samples_per_second": 176.565,
727
+ "eval_steps_per_second": 22.071,
728
+ "step": 8400
729
+ },
730
+ {
731
+ "epoch": 4.44,
732
+ "eval_loss": 1.6441596746444702,
733
+ "eval_runtime": 4.5328,
734
+ "eval_samples_per_second": 176.493,
735
+ "eval_steps_per_second": 22.062,
736
+ "step": 8500
737
+ },
738
+ {
739
+ "epoch": 4.5,
740
+ "eval_loss": 1.6503033638000488,
741
+ "eval_runtime": 4.5354,
742
+ "eval_samples_per_second": 176.39,
743
+ "eval_steps_per_second": 22.049,
744
+ "step": 8600
745
+ },
746
+ {
747
+ "epoch": 4.55,
748
+ "eval_loss": 1.6993392705917358,
749
+ "eval_runtime": 4.5291,
750
+ "eval_samples_per_second": 176.634,
751
+ "eval_steps_per_second": 22.079,
752
+ "step": 8700
753
+ },
754
+ {
755
+ "epoch": 4.6,
756
+ "eval_loss": 1.741347312927246,
757
+ "eval_runtime": 4.5403,
758
+ "eval_samples_per_second": 176.201,
759
+ "eval_steps_per_second": 22.025,
760
+ "step": 8800
761
+ },
762
+ {
763
+ "epoch": 4.65,
764
+ "eval_loss": 1.7068595886230469,
765
+ "eval_runtime": 4.5165,
766
+ "eval_samples_per_second": 177.126,
767
+ "eval_steps_per_second": 22.141,
768
+ "step": 8900
769
+ },
770
+ {
771
+ "epoch": 4.7,
772
+ "learning_rate": 5.906952430737063e-07,
773
+ "loss": 1.7046,
774
+ "step": 9000
775
+ },
776
+ {
777
+ "epoch": 4.7,
778
+ "eval_loss": 1.741222858428955,
779
+ "eval_runtime": 4.5635,
780
+ "eval_samples_per_second": 175.305,
781
+ "eval_steps_per_second": 21.913,
782
+ "step": 9000
783
+ },
784
+ {
785
+ "epoch": 4.76,
786
+ "eval_loss": 1.695675015449524,
787
+ "eval_runtime": 4.542,
788
+ "eval_samples_per_second": 176.133,
789
+ "eval_steps_per_second": 22.017,
790
+ "step": 9100
791
+ },
792
+ {
793
+ "epoch": 4.81,
794
+ "eval_loss": 1.8147244453430176,
795
+ "eval_runtime": 4.5361,
796
+ "eval_samples_per_second": 176.364,
797
+ "eval_steps_per_second": 22.045,
798
+ "step": 9200
799
+ },
800
+ {
801
+ "epoch": 4.86,
802
+ "eval_loss": 1.6123968362808228,
803
+ "eval_runtime": 4.5504,
804
+ "eval_samples_per_second": 175.81,
805
+ "eval_steps_per_second": 21.976,
806
+ "step": 9300
807
+ },
808
+ {
809
+ "epoch": 4.91,
810
+ "eval_loss": 1.6993104219436646,
811
+ "eval_runtime": 4.5406,
812
+ "eval_samples_per_second": 176.188,
813
+ "eval_steps_per_second": 22.023,
814
+ "step": 9400
815
+ },
816
+ {
817
+ "epoch": 4.97,
818
+ "eval_loss": 1.6907097101211548,
819
+ "eval_runtime": 4.5386,
820
+ "eval_samples_per_second": 176.266,
821
+ "eval_steps_per_second": 22.033,
822
+ "step": 9500
823
+ },
824
+ {
825
+ "epoch": 5.0,
826
+ "step": 9565,
827
+ "total_flos": 6026840964129600.0,
828
+ "train_loss": 1.8707820080738695,
829
+ "train_runtime": 8847.0854,
830
+ "train_samples_per_second": 8.647,
831
+ "train_steps_per_second": 1.081
832
+ }
833
+ ],
834
+ "max_steps": 9565,
835
+ "num_train_epochs": 5,
836
+ "total_flos": 6026840964129600.0,
837
+ "trial_name": null,
838
+ "trial_params": null
839
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a960c6ba2650d2c11eb1a0d6ed12021cabd3897ae1e188891d48e4010352b37c
3
+ size 2927