bimabk commited on
Commit
4259f52
·
verified ·
1 Parent(s): 79f3e71

Upload task output 1

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_remove_final_layer_norm": false,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "OPTForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 2,
10
+ "do_layer_norm_before": true,
11
+ "dropout": 0.1,
12
+ "enable_bias": true,
13
+ "eos_token_id": 2,
14
+ "ffn_dim": 3072,
15
+ "hidden_size": 768,
16
+ "init_std": 0.02,
17
+ "layer_norm_elementwise_affine": true,
18
+ "layerdrop": 0.0,
19
+ "max_position_embeddings": 2048,
20
+ "model_type": "opt",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 1,
24
+ "prefix": "</s>",
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": false,
28
+ "vocab_size": 50272,
29
+ "word_embed_proj_dim": 768
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.51.3"
7
+ }
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 500,0.7584288716316223
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8334417a9a80d381401ecb53eff142b1288cc860dc4f3e4f3519d7c8c37adf3f
3
+ size 250501160
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": false,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "extra_special_tokens": {},
27
+ "model_max_length": 1000000000000000019884624838656,
28
+ "pad_token": "<pad>",
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "</s>"
31
+ }
trainer_state.json ADDED
@@ -0,0 +1,742 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.1203659123736158,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.001203659123736158,
14
+ "grad_norm": 4.625,
15
+ "learning_rate": 2.065577232275662e-05,
16
+ "loss": 1.9427,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.002407318247472316,
21
+ "grad_norm": 3.90625,
22
+ "learning_rate": 4.647548772620239e-05,
23
+ "loss": 1.8343,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.0036109773712084737,
28
+ "grad_norm": 3.09375,
29
+ "learning_rate": 7.229520312964818e-05,
30
+ "loss": 1.7165,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.004814636494944632,
35
+ "grad_norm": 3.09375,
36
+ "learning_rate": 9.811491853309394e-05,
37
+ "loss": 1.5909,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.00601829561868079,
42
+ "grad_norm": 3.6875,
43
+ "learning_rate": 0.00012393463393653973,
44
+ "loss": 1.5327,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.007221954742416947,
49
+ "grad_norm": 3.0625,
50
+ "learning_rate": 0.0001497543493399855,
51
+ "loss": 1.4456,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.008425613866153106,
56
+ "grad_norm": 2.65625,
57
+ "learning_rate": 0.00017557406474343128,
58
+ "loss": 1.3967,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.009629272989889264,
63
+ "grad_norm": 2.90625,
64
+ "learning_rate": 0.0001807379731713583,
65
+ "loss": 1.3353,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.010832932113625422,
70
+ "grad_norm": 3.421875,
71
+ "learning_rate": 0.00018073783239457288,
72
+ "loss": 1.3252,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.01203659123736158,
77
+ "grad_norm": 2.875,
78
+ "learning_rate": 0.00018073758332819127,
79
+ "loss": 1.2706,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.013240250361097737,
84
+ "grad_norm": 3.015625,
85
+ "learning_rate": 0.00018073722597261146,
86
+ "loss": 1.2637,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.014443909484833895,
91
+ "grad_norm": 2.71875,
92
+ "learning_rate": 0.00018073676032840438,
93
+ "loss": 1.218,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.015647568608570053,
98
+ "grad_norm": 2.734375,
99
+ "learning_rate": 0.00018073618639631402,
100
+ "loss": 1.2207,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.016851227732306212,
105
+ "grad_norm": 2.765625,
106
+ "learning_rate": 0.00018073550417725735,
107
+ "loss": 1.1901,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.018054886856042368,
112
+ "grad_norm": 2.4375,
113
+ "learning_rate": 0.0001807347136723244,
114
+ "loss": 1.1795,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.019258545979778528,
119
+ "grad_norm": 2.65625,
120
+ "learning_rate": 0.00018073381488277823,
121
+ "loss": 1.1604,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.020462205103514684,
126
+ "grad_norm": 2.4375,
127
+ "learning_rate": 0.00018073280781005481,
128
+ "loss": 1.1633,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.021665864227250843,
133
+ "grad_norm": 2.671875,
134
+ "learning_rate": 0.00018073169245576325,
135
+ "loss": 1.1536,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.022869523350987,
140
+ "grad_norm": 2.4375,
141
+ "learning_rate": 0.00018073046882168553,
142
+ "loss": 1.1296,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.02407318247472316,
147
+ "grad_norm": 2.515625,
148
+ "learning_rate": 0.00018072913690977675,
149
+ "loss": 1.1209,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.025276841598459315,
154
+ "grad_norm": 2.515625,
155
+ "learning_rate": 0.00018072769672216498,
156
+ "loss": 1.0913,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.026480500722195474,
161
+ "grad_norm": 2.484375,
162
+ "learning_rate": 0.0001807261482611512,
163
+ "loss": 1.1271,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.027684159845931634,
168
+ "grad_norm": 2.71875,
169
+ "learning_rate": 0.00018072449152920953,
170
+ "loss": 1.1263,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.02888781896966779,
175
+ "grad_norm": 2.75,
176
+ "learning_rate": 0.00018072272652898695,
177
+ "loss": 1.0988,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.03009147809340395,
182
+ "grad_norm": 2.296875,
183
+ "learning_rate": 0.0001807208532633035,
184
+ "loss": 1.0511,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.031295137217140105,
189
+ "grad_norm": 2.890625,
190
+ "learning_rate": 0.0001807188717351522,
191
+ "loss": 1.1231,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.03249879634087626,
196
+ "grad_norm": 2.546875,
197
+ "learning_rate": 0.00018071678194769898,
198
+ "loss": 1.054,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.033702455464612424,
203
+ "grad_norm": 2.515625,
204
+ "learning_rate": 0.0001807145839042828,
205
+ "loss": 1.0571,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.03490611458834858,
210
+ "grad_norm": 2.703125,
211
+ "learning_rate": 0.0001807122776084156,
212
+ "loss": 1.0463,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.036109773712084736,
217
+ "grad_norm": 2.296875,
218
+ "learning_rate": 0.00018070986306378223,
219
+ "loss": 1.0482,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.03731343283582089,
224
+ "grad_norm": 2.375,
225
+ "learning_rate": 0.00018070734027424048,
226
+ "loss": 1.0518,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.038517091959557055,
231
+ "grad_norm": 2.25,
232
+ "learning_rate": 0.00018070470924382115,
233
+ "loss": 1.0772,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.03972075108329321,
238
+ "grad_norm": 2.140625,
239
+ "learning_rate": 0.00018070196997672797,
240
+ "loss": 1.0396,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.04092441020702937,
245
+ "grad_norm": 2.484375,
246
+ "learning_rate": 0.00018069912247733758,
247
+ "loss": 1.0425,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.04212806933076553,
252
+ "grad_norm": 2.0625,
253
+ "learning_rate": 0.00018069616675019952,
254
+ "loss": 1.034,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.043331728454501686,
259
+ "grad_norm": 2.265625,
260
+ "learning_rate": 0.00018069310280003633,
261
+ "loss": 1.0382,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.04453538757823784,
266
+ "grad_norm": 1.984375,
267
+ "learning_rate": 0.00018068993063174337,
268
+ "loss": 0.982,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.045739046701974,
273
+ "grad_norm": 2.515625,
274
+ "learning_rate": 0.00018068665025038899,
275
+ "loss": 1.0471,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.04694270582571016,
280
+ "grad_norm": 2.421875,
281
+ "learning_rate": 0.00018068326166121437,
282
+ "loss": 1.002,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.04814636494944632,
287
+ "grad_norm": 2.390625,
288
+ "learning_rate": 0.00018067976486963364,
289
+ "loss": 0.9909,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.04935002407318247,
294
+ "grad_norm": 1.921875,
295
+ "learning_rate": 0.00018067615988123374,
296
+ "loss": 0.9895,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.05055368319691863,
301
+ "grad_norm": 1.921875,
302
+ "learning_rate": 0.00018067244670177452,
303
+ "loss": 0.9895,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.05175734232065479,
308
+ "grad_norm": 2.4375,
309
+ "learning_rate": 0.00018066862533718873,
310
+ "loss": 0.9932,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.05296100144439095,
315
+ "grad_norm": 2.0625,
316
+ "learning_rate": 0.0001806646957935819,
317
+ "loss": 0.9931,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.054164660568127104,
322
+ "grad_norm": 2.28125,
323
+ "learning_rate": 0.00018066065807723243,
324
+ "loss": 0.9888,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.05536831969186327,
329
+ "grad_norm": 2.21875,
330
+ "learning_rate": 0.00018065651219459158,
331
+ "loss": 0.9817,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.05657197881559942,
336
+ "grad_norm": 2.234375,
337
+ "learning_rate": 0.00018065225815228335,
338
+ "loss": 0.9572,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.05777563793933558,
343
+ "grad_norm": 2.09375,
344
+ "learning_rate": 0.00018064789595710468,
345
+ "loss": 0.9525,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.058979297063071735,
350
+ "grad_norm": 2.09375,
351
+ "learning_rate": 0.00018064342561602522,
352
+ "loss": 0.9726,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.0601829561868079,
357
+ "grad_norm": 2.21875,
358
+ "learning_rate": 0.00018063884713618737,
359
+ "loss": 0.9637,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.061386615310544054,
364
+ "grad_norm": 2.203125,
365
+ "learning_rate": 0.00018063416052490648,
366
+ "loss": 0.9902,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.06259027443428021,
371
+ "grad_norm": 2.1875,
372
+ "learning_rate": 0.00018062936578967044,
373
+ "loss": 0.9271,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.06379393355801637,
378
+ "grad_norm": 2.375,
379
+ "learning_rate": 0.00018062446293814008,
380
+ "loss": 0.9563,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.06499759268175252,
385
+ "grad_norm": 2.171875,
386
+ "learning_rate": 0.0001806194519781489,
387
+ "loss": 0.9442,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.06620125180548869,
392
+ "grad_norm": 2.078125,
393
+ "learning_rate": 0.00018061433291770306,
394
+ "loss": 0.945,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.06740491092922485,
399
+ "grad_norm": 2.328125,
400
+ "learning_rate": 0.00018060910576498158,
401
+ "loss": 0.9385,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.068608570052961,
406
+ "grad_norm": 2.296875,
407
+ "learning_rate": 0.0001806037705283361,
408
+ "loss": 0.9244,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.06981222917669716,
413
+ "grad_norm": 2.234375,
414
+ "learning_rate": 0.0001805983272162909,
415
+ "loss": 0.926,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.07101588830043332,
420
+ "grad_norm": 2.40625,
421
+ "learning_rate": 0.00018059277583754304,
422
+ "loss": 0.9232,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.07221954742416947,
427
+ "grad_norm": 2.09375,
428
+ "learning_rate": 0.00018058711640096223,
429
+ "loss": 0.8977,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.07342320654790563,
434
+ "grad_norm": 2.125,
435
+ "learning_rate": 0.00018058134891559078,
436
+ "loss": 0.9126,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.07462686567164178,
441
+ "grad_norm": 2.125,
442
+ "learning_rate": 0.00018057547339064362,
443
+ "loss": 0.9649,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.07583052479537795,
448
+ "grad_norm": 2.265625,
449
+ "learning_rate": 0.00018056948983550834,
450
+ "loss": 0.8945,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.07703418391911411,
455
+ "grad_norm": 2.203125,
456
+ "learning_rate": 0.00018056339825974518,
457
+ "loss": 0.9023,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.07823784304285027,
462
+ "grad_norm": 1.9375,
463
+ "learning_rate": 0.00018055719867308685,
464
+ "loss": 0.907,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.07944150216658642,
469
+ "grad_norm": 2.046875,
470
+ "learning_rate": 0.00018055089108543872,
471
+ "loss": 0.9306,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 0.08064516129032258,
476
+ "grad_norm": 2.359375,
477
+ "learning_rate": 0.00018054447550687873,
478
+ "loss": 0.9115,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 0.08184882041405873,
483
+ "grad_norm": 2.03125,
484
+ "learning_rate": 0.00018053795194765732,
485
+ "loss": 0.909,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 0.08305247953779489,
490
+ "grad_norm": 2.171875,
491
+ "learning_rate": 0.00018053132041819745,
492
+ "loss": 0.8878,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 0.08425613866153106,
497
+ "grad_norm": 1.90625,
498
+ "learning_rate": 0.00018052458092909456,
499
+ "loss": 0.9281,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 0.08545979778526722,
504
+ "grad_norm": 2.15625,
505
+ "learning_rate": 0.00018051773349111671,
506
+ "loss": 0.9012,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 0.08666345690900337,
511
+ "grad_norm": 1.7890625,
512
+ "learning_rate": 0.00018051077811520431,
513
+ "loss": 0.9071,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 0.08786711603273953,
518
+ "grad_norm": 2.0625,
519
+ "learning_rate": 0.00018050371481247027,
520
+ "loss": 0.9063,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 0.08907077515647568,
525
+ "grad_norm": 1.859375,
526
+ "learning_rate": 0.00018049654359419994,
527
+ "loss": 0.903,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 0.09027443428021184,
532
+ "grad_norm": 2.09375,
533
+ "learning_rate": 0.00018048926447185106,
534
+ "loss": 0.9166,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 0.091478093403948,
539
+ "grad_norm": 1.8359375,
540
+ "learning_rate": 0.00018048187745705387,
541
+ "loss": 0.8833,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 0.09268175252768417,
546
+ "grad_norm": 2.125,
547
+ "learning_rate": 0.00018047438256161086,
548
+ "loss": 0.8981,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 0.09388541165142032,
553
+ "grad_norm": 2.03125,
554
+ "learning_rate": 0.00018046677979749698,
555
+ "loss": 0.8898,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 0.09508907077515648,
560
+ "grad_norm": 1.9609375,
561
+ "learning_rate": 0.00018045906917685947,
562
+ "loss": 0.8837,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 0.09629272989889263,
567
+ "grad_norm": 2.015625,
568
+ "learning_rate": 0.000180451250712018,
569
+ "loss": 0.8803,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 0.09749638902262879,
574
+ "grad_norm": 1.8984375,
575
+ "learning_rate": 0.00018044332441546437,
576
+ "loss": 0.8851,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 0.09870004814636495,
581
+ "grad_norm": 1.9453125,
582
+ "learning_rate": 0.00018043529029986285,
583
+ "loss": 0.8997,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 0.0999037072701011,
588
+ "grad_norm": 1.9140625,
589
+ "learning_rate": 0.00018042714837804985,
590
+ "loss": 0.8991,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 0.10110736639383726,
595
+ "grad_norm": 2.03125,
596
+ "learning_rate": 0.0001804188986630341,
597
+ "loss": 0.8939,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 0.10231102551757343,
602
+ "grad_norm": 2.203125,
603
+ "learning_rate": 0.00018041054116799653,
604
+ "loss": 0.8914,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 0.10351468464130958,
609
+ "grad_norm": 2.1875,
610
+ "learning_rate": 0.00018040207590629026,
611
+ "loss": 0.8398,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 0.10471834376504574,
616
+ "grad_norm": 1.8203125,
617
+ "learning_rate": 0.0001803935028914406,
618
+ "loss": 0.8818,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 0.1059220028887819,
623
+ "grad_norm": 1.953125,
624
+ "learning_rate": 0.00018038482213714508,
625
+ "loss": 0.8518,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 0.10712566201251805,
630
+ "grad_norm": 2.09375,
631
+ "learning_rate": 0.00018037603365727323,
632
+ "loss": 0.8874,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 0.10832932113625421,
637
+ "grad_norm": 1.921875,
638
+ "learning_rate": 0.00018036713746586689,
639
+ "loss": 0.8923,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 0.10953298025999036,
644
+ "grad_norm": 1.7109375,
645
+ "learning_rate": 0.00018035813357713984,
646
+ "loss": 0.8945,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 0.11073663938372653,
651
+ "grad_norm": 1.71875,
652
+ "learning_rate": 0.00018034902200547796,
653
+ "loss": 0.857,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 0.11194029850746269,
658
+ "grad_norm": 2.015625,
659
+ "learning_rate": 0.00018033980276543928,
660
+ "loss": 0.8514,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 0.11314395763119885,
665
+ "grad_norm": 1.703125,
666
+ "learning_rate": 0.0001803304758717537,
667
+ "loss": 0.8674,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 0.114347616754935,
672
+ "grad_norm": 1.96875,
673
+ "learning_rate": 0.00018032104133932326,
674
+ "loss": 0.9035,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 0.11555127587867116,
679
+ "grad_norm": 1.7734375,
680
+ "learning_rate": 0.00018031149918322191,
681
+ "loss": 0.8484,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 0.11675493500240731,
686
+ "grad_norm": 1.9140625,
687
+ "learning_rate": 0.0001803018494186956,
688
+ "loss": 0.8609,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 0.11795859412614347,
693
+ "grad_norm": 1.875,
694
+ "learning_rate": 0.0001802920920611621,
695
+ "loss": 0.8008,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 0.11916225324987964,
700
+ "grad_norm": 1.7890625,
701
+ "learning_rate": 0.00018028222712621126,
702
+ "loss": 0.8406,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 0.1203659123736158,
707
+ "grad_norm": 2.03125,
708
+ "learning_rate": 0.00018027225462960463,
709
+ "loss": 0.8552,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 0.1203659123736158,
714
+ "eval_loss": 0.7584288716316223,
715
+ "eval_runtime": 2.397,
716
+ "eval_samples_per_second": 83.437,
717
+ "eval_steps_per_second": 83.437,
718
+ "step": 500
719
+ }
720
+ ],
721
+ "logging_steps": 5,
722
+ "max_steps": 12462,
723
+ "num_input_tokens_seen": 0,
724
+ "num_train_epochs": 3,
725
+ "save_steps": 500,
726
+ "stateful_callbacks": {
727
+ "TrainerControl": {
728
+ "args": {
729
+ "should_epoch_stop": false,
730
+ "should_evaluate": false,
731
+ "should_log": false,
732
+ "should_save": true,
733
+ "should_training_stop": false
734
+ },
735
+ "attributes": {}
736
+ }
737
+ },
738
+ "total_flos": 1.2542017536e+16,
739
+ "train_batch_size": 48,
740
+ "trial_name": null,
741
+ "trial_params": null
742
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4cd2ce39993917afa2c76516ae1cbbbde8c0400a83c73de09a91220e95a7ba3
3
+ size 5560
vocab.json ADDED
The diff for this file is too large to render. See raw diff