wu981526092 commited on
Commit
6ec131e
1 Parent(s): 9d96fe0

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.46.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.46.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:832b77495217d26f25a67e536176c37a259b8e5ae5563055d39cb1b2ba4e61e6
3
+ size 497774208
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc22c19db202173ce6e157a84e88c56de5aef2b1b8e61207355d1393474f4bb
3
+ size 995638202
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ffd2e67a5e106bcbed7941bfeb9076b68a447bab53d273e41d280ee2e05187
3
+ size 13990
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de45cda5065921ae804cbe613cae9b11f076f07429b3b6b95016130413aba591
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,720 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.214390277862549,
3
+ "best_model_checkpoint": "./gpt2_bias_model_mps/checkpoint-975",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 975,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010256410256410256,
13
+ "grad_norm": 15.915234565734863,
14
+ "learning_rate": 4.948717948717949e-05,
15
+ "loss": 4.1387,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.020512820512820513,
20
+ "grad_norm": 14.396087646484375,
21
+ "learning_rate": 4.8974358974358975e-05,
22
+ "loss": 4.0441,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.03076923076923077,
27
+ "grad_norm": 15.571473121643066,
28
+ "learning_rate": 4.846153846153846e-05,
29
+ "loss": 3.9314,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.041025641025641026,
34
+ "grad_norm": 14.709969520568848,
35
+ "learning_rate": 4.7948717948717955e-05,
36
+ "loss": 3.8778,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.05128205128205128,
41
+ "grad_norm": 13.663440704345703,
42
+ "learning_rate": 4.7435897435897435e-05,
43
+ "loss": 3.6624,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.06153846153846154,
48
+ "grad_norm": 13.031949996948242,
49
+ "learning_rate": 4.692307692307693e-05,
50
+ "loss": 3.7466,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.07179487179487179,
55
+ "grad_norm": 13.534045219421387,
56
+ "learning_rate": 4.6410256410256415e-05,
57
+ "loss": 3.886,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.08205128205128205,
62
+ "grad_norm": 13.990560531616211,
63
+ "learning_rate": 4.5897435897435895e-05,
64
+ "loss": 3.8182,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.09230769230769231,
69
+ "grad_norm": 14.367162704467773,
70
+ "learning_rate": 4.538461538461539e-05,
71
+ "loss": 3.6856,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.10256410256410256,
76
+ "grad_norm": 12.511638641357422,
77
+ "learning_rate": 4.4871794871794874e-05,
78
+ "loss": 3.7046,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.11282051282051282,
83
+ "grad_norm": 15.438050270080566,
84
+ "learning_rate": 4.435897435897436e-05,
85
+ "loss": 3.7047,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.12307692307692308,
90
+ "grad_norm": 12.294541358947754,
91
+ "learning_rate": 4.384615384615385e-05,
92
+ "loss": 3.787,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.13333333333333333,
97
+ "grad_norm": 14.492098808288574,
98
+ "learning_rate": 4.3333333333333334e-05,
99
+ "loss": 3.688,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.14358974358974358,
104
+ "grad_norm": 12.25203800201416,
105
+ "learning_rate": 4.282051282051282e-05,
106
+ "loss": 3.5417,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.15384615384615385,
111
+ "grad_norm": 13.325423240661621,
112
+ "learning_rate": 4.230769230769231e-05,
113
+ "loss": 3.5546,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.1641025641025641,
118
+ "grad_norm": 12.688371658325195,
119
+ "learning_rate": 4.17948717948718e-05,
120
+ "loss": 3.6785,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.17435897435897435,
125
+ "grad_norm": 13.553004264831543,
126
+ "learning_rate": 4.128205128205128e-05,
127
+ "loss": 3.575,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.18461538461538463,
132
+ "grad_norm": 12.279559135437012,
133
+ "learning_rate": 4.0769230769230773e-05,
134
+ "loss": 3.643,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.19487179487179487,
139
+ "grad_norm": 11.203484535217285,
140
+ "learning_rate": 4.025641025641026e-05,
141
+ "loss": 3.5966,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.20512820512820512,
146
+ "grad_norm": 11.550701141357422,
147
+ "learning_rate": 3.974358974358974e-05,
148
+ "loss": 3.6116,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.2153846153846154,
153
+ "grad_norm": 12.691393852233887,
154
+ "learning_rate": 3.923076923076923e-05,
155
+ "loss": 3.452,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.22564102564102564,
160
+ "grad_norm": 11.071481704711914,
161
+ "learning_rate": 3.871794871794872e-05,
162
+ "loss": 3.5236,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.2358974358974359,
167
+ "grad_norm": 12.220307350158691,
168
+ "learning_rate": 3.8205128205128206e-05,
169
+ "loss": 3.6149,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.24615384615384617,
174
+ "grad_norm": 12.471100807189941,
175
+ "learning_rate": 3.769230769230769e-05,
176
+ "loss": 3.6393,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.2564102564102564,
181
+ "grad_norm": 10.304001808166504,
182
+ "learning_rate": 3.717948717948718e-05,
183
+ "loss": 3.4771,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.26666666666666666,
188
+ "grad_norm": 10.889674186706543,
189
+ "learning_rate": 3.6666666666666666e-05,
190
+ "loss": 3.5182,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.27692307692307694,
195
+ "grad_norm": 10.550483703613281,
196
+ "learning_rate": 3.615384615384615e-05,
197
+ "loss": 3.3559,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.28717948717948716,
202
+ "grad_norm": 10.34374713897705,
203
+ "learning_rate": 3.5641025641025646e-05,
204
+ "loss": 3.4854,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.29743589743589743,
209
+ "grad_norm": 11.178277969360352,
210
+ "learning_rate": 3.5128205128205125e-05,
211
+ "loss": 3.5015,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.3076923076923077,
216
+ "grad_norm": 10.405166625976562,
217
+ "learning_rate": 3.461538461538462e-05,
218
+ "loss": 3.5436,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.31794871794871793,
223
+ "grad_norm": 10.547426223754883,
224
+ "learning_rate": 3.4102564102564105e-05,
225
+ "loss": 3.4588,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.3282051282051282,
230
+ "grad_norm": 11.255645751953125,
231
+ "learning_rate": 3.358974358974359e-05,
232
+ "loss": 3.4427,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.3384615384615385,
237
+ "grad_norm": 10.89976692199707,
238
+ "learning_rate": 3.307692307692308e-05,
239
+ "loss": 3.4668,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.3487179487179487,
244
+ "grad_norm": 10.082490921020508,
245
+ "learning_rate": 3.2564102564102565e-05,
246
+ "loss": 3.5122,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.358974358974359,
251
+ "grad_norm": 9.010897636413574,
252
+ "learning_rate": 3.205128205128206e-05,
253
+ "loss": 3.4547,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.36923076923076925,
258
+ "grad_norm": 10.768731117248535,
259
+ "learning_rate": 3.153846153846154e-05,
260
+ "loss": 3.4541,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.37948717948717947,
265
+ "grad_norm": 10.812358856201172,
266
+ "learning_rate": 3.102564102564103e-05,
267
+ "loss": 3.3868,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.38974358974358975,
272
+ "grad_norm": 10.063950538635254,
273
+ "learning_rate": 3.0512820512820518e-05,
274
+ "loss": 3.5424,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.4,
279
+ "grad_norm": 9.603002548217773,
280
+ "learning_rate": 3e-05,
281
+ "loss": 3.3761,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.41025641025641024,
286
+ "grad_norm": 9.461718559265137,
287
+ "learning_rate": 2.948717948717949e-05,
288
+ "loss": 3.423,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.4205128205128205,
293
+ "grad_norm": 9.013967514038086,
294
+ "learning_rate": 2.8974358974358977e-05,
295
+ "loss": 3.421,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.4307692307692308,
300
+ "grad_norm": 10.10628604888916,
301
+ "learning_rate": 2.846153846153846e-05,
302
+ "loss": 3.4225,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.441025641025641,
307
+ "grad_norm": 9.19229507446289,
308
+ "learning_rate": 2.794871794871795e-05,
309
+ "loss": 3.4973,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.4512820512820513,
314
+ "grad_norm": 9.309951782226562,
315
+ "learning_rate": 2.743589743589744e-05,
316
+ "loss": 3.4458,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.46153846153846156,
321
+ "grad_norm": 8.606375694274902,
322
+ "learning_rate": 2.6923076923076923e-05,
323
+ "loss": 3.4163,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.4717948717948718,
328
+ "grad_norm": 9.342279434204102,
329
+ "learning_rate": 2.6410256410256413e-05,
330
+ "loss": 3.4543,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.48205128205128206,
335
+ "grad_norm": 10.326979637145996,
336
+ "learning_rate": 2.58974358974359e-05,
337
+ "loss": 3.4219,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.49230769230769234,
342
+ "grad_norm": 9.113346099853516,
343
+ "learning_rate": 2.5384615384615383e-05,
344
+ "loss": 3.4182,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.5025641025641026,
349
+ "grad_norm": 9.695829391479492,
350
+ "learning_rate": 2.4871794871794873e-05,
351
+ "loss": 3.4622,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.5128205128205128,
356
+ "grad_norm": 10.052870750427246,
357
+ "learning_rate": 2.435897435897436e-05,
358
+ "loss": 3.392,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.5230769230769231,
363
+ "grad_norm": 7.836452960968018,
364
+ "learning_rate": 2.384615384615385e-05,
365
+ "loss": 3.4489,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.5333333333333333,
370
+ "grad_norm": 10.3803129196167,
371
+ "learning_rate": 2.3333333333333336e-05,
372
+ "loss": 3.4643,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.5435897435897435,
377
+ "grad_norm": 9.079364776611328,
378
+ "learning_rate": 2.2820512820512822e-05,
379
+ "loss": 3.4824,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.5538461538461539,
384
+ "grad_norm": 9.125578880310059,
385
+ "learning_rate": 2.230769230769231e-05,
386
+ "loss": 3.4399,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.5641025641025641,
391
+ "grad_norm": 8.740405082702637,
392
+ "learning_rate": 2.1794871794871795e-05,
393
+ "loss": 3.4194,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.5743589743589743,
398
+ "grad_norm": 8.519855499267578,
399
+ "learning_rate": 2.1282051282051282e-05,
400
+ "loss": 3.4603,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.5846153846153846,
405
+ "grad_norm": 8.29417610168457,
406
+ "learning_rate": 2.0769230769230772e-05,
407
+ "loss": 3.4312,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.5948717948717949,
412
+ "grad_norm": 8.083531379699707,
413
+ "learning_rate": 2.025641025641026e-05,
414
+ "loss": 3.3395,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.6051282051282051,
419
+ "grad_norm": 7.79611873626709,
420
+ "learning_rate": 1.9743589743589745e-05,
421
+ "loss": 3.319,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.6153846153846154,
426
+ "grad_norm": 9.557352066040039,
427
+ "learning_rate": 1.923076923076923e-05,
428
+ "loss": 3.5313,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.6256410256410256,
433
+ "grad_norm": 8.805798530578613,
434
+ "learning_rate": 1.8717948717948718e-05,
435
+ "loss": 3.4618,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.6358974358974359,
440
+ "grad_norm": 8.321375846862793,
441
+ "learning_rate": 1.8205128205128204e-05,
442
+ "loss": 3.4288,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.6461538461538462,
447
+ "grad_norm": 7.985848903656006,
448
+ "learning_rate": 1.7692307692307694e-05,
449
+ "loss": 3.4127,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.6564102564102564,
454
+ "grad_norm": 8.117752075195312,
455
+ "learning_rate": 1.717948717948718e-05,
456
+ "loss": 3.3404,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.6666666666666666,
461
+ "grad_norm": 9.96267318725586,
462
+ "learning_rate": 1.6666666666666667e-05,
463
+ "loss": 3.3629,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.676923076923077,
468
+ "grad_norm": 7.83555793762207,
469
+ "learning_rate": 1.6153846153846154e-05,
470
+ "loss": 3.4605,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.6871794871794872,
475
+ "grad_norm": 8.735118865966797,
476
+ "learning_rate": 1.564102564102564e-05,
477
+ "loss": 3.4665,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.6974358974358974,
482
+ "grad_norm": 8.65040397644043,
483
+ "learning_rate": 1.5128205128205129e-05,
484
+ "loss": 3.4698,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.7076923076923077,
489
+ "grad_norm": 6.974828243255615,
490
+ "learning_rate": 1.4615384615384617e-05,
491
+ "loss": 3.4783,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.717948717948718,
496
+ "grad_norm": 8.379024505615234,
497
+ "learning_rate": 1.4102564102564104e-05,
498
+ "loss": 3.3683,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.7282051282051282,
503
+ "grad_norm": 8.352046012878418,
504
+ "learning_rate": 1.358974358974359e-05,
505
+ "loss": 3.4313,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.7384615384615385,
510
+ "grad_norm": 7.566000461578369,
511
+ "learning_rate": 1.3076923076923078e-05,
512
+ "loss": 3.3775,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.7487179487179487,
517
+ "grad_norm": 7.003971099853516,
518
+ "learning_rate": 1.2564102564102565e-05,
519
+ "loss": 3.2418,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.7589743589743589,
524
+ "grad_norm": 7.048854351043701,
525
+ "learning_rate": 1.2051282051282051e-05,
526
+ "loss": 3.3531,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.7692307692307693,
531
+ "grad_norm": 7.653282642364502,
532
+ "learning_rate": 1.153846153846154e-05,
533
+ "loss": 3.4099,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.7794871794871795,
538
+ "grad_norm": 7.643819808959961,
539
+ "learning_rate": 1.1025641025641026e-05,
540
+ "loss": 3.3944,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.7897435897435897,
545
+ "grad_norm": 8.362899780273438,
546
+ "learning_rate": 1.0512820512820514e-05,
547
+ "loss": 3.411,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.8,
552
+ "grad_norm": 7.380786895751953,
553
+ "learning_rate": 1e-05,
554
+ "loss": 3.4135,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.8102564102564103,
559
+ "grad_norm": 8.83707332611084,
560
+ "learning_rate": 9.487179487179487e-06,
561
+ "loss": 3.2312,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.8205128205128205,
566
+ "grad_norm": 7.70910120010376,
567
+ "learning_rate": 8.974358974358976e-06,
568
+ "loss": 3.4221,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.8307692307692308,
573
+ "grad_norm": 7.079320430755615,
574
+ "learning_rate": 8.461538461538462e-06,
575
+ "loss": 3.338,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.841025641025641,
580
+ "grad_norm": 8.756903648376465,
581
+ "learning_rate": 7.948717948717949e-06,
582
+ "loss": 3.3683,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.8512820512820513,
587
+ "grad_norm": 8.349058151245117,
588
+ "learning_rate": 7.435897435897436e-06,
589
+ "loss": 3.4499,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.8615384615384616,
594
+ "grad_norm": 8.497963905334473,
595
+ "learning_rate": 6.923076923076923e-06,
596
+ "loss": 3.4448,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.8717948717948718,
601
+ "grad_norm": 8.383698463439941,
602
+ "learning_rate": 6.41025641025641e-06,
603
+ "loss": 3.2929,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.882051282051282,
608
+ "grad_norm": 8.016318321228027,
609
+ "learning_rate": 5.897435897435897e-06,
610
+ "loss": 3.4073,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.8923076923076924,
615
+ "grad_norm": 9.301827430725098,
616
+ "learning_rate": 5.3846153846153855e-06,
617
+ "loss": 3.4206,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.9025641025641026,
622
+ "grad_norm": 7.227042198181152,
623
+ "learning_rate": 4.871794871794872e-06,
624
+ "loss": 3.3388,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.9128205128205128,
629
+ "grad_norm": 6.956933975219727,
630
+ "learning_rate": 4.3589743589743586e-06,
631
+ "loss": 3.2773,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.9230769230769231,
636
+ "grad_norm": 8.344608306884766,
637
+ "learning_rate": 3.846153846153847e-06,
638
+ "loss": 3.2864,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.9333333333333333,
643
+ "grad_norm": 7.429567813873291,
644
+ "learning_rate": 3.3333333333333333e-06,
645
+ "loss": 3.3606,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.9435897435897436,
650
+ "grad_norm": 7.6066389083862305,
651
+ "learning_rate": 2.8205128205128207e-06,
652
+ "loss": 3.3459,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.9538461538461539,
657
+ "grad_norm": 7.413199424743652,
658
+ "learning_rate": 2.307692307692308e-06,
659
+ "loss": 3.3968,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.9641025641025641,
664
+ "grad_norm": 6.853078365325928,
665
+ "learning_rate": 1.7948717948717948e-06,
666
+ "loss": 3.3706,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.9743589743589743,
671
+ "grad_norm": 6.604455947875977,
672
+ "learning_rate": 1.282051282051282e-06,
673
+ "loss": 3.3048,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.9846153846153847,
678
+ "grad_norm": 8.022303581237793,
679
+ "learning_rate": 7.692307692307694e-07,
680
+ "loss": 3.3028,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.9948717948717949,
685
+ "grad_norm": 8.982901573181152,
686
+ "learning_rate": 2.564102564102564e-07,
687
+ "loss": 3.3398,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 1.0,
692
+ "eval_loss": 3.214390277862549,
693
+ "eval_runtime": 39.3331,
694
+ "eval_samples_per_second": 99.306,
695
+ "eval_steps_per_second": 6.229,
696
+ "step": 975
697
+ }
698
+ ],
699
+ "logging_steps": 10,
700
+ "max_steps": 975,
701
+ "num_input_tokens_seen": 0,
702
+ "num_train_epochs": 1,
703
+ "save_steps": 100,
704
+ "stateful_callbacks": {
705
+ "TrainerControl": {
706
+ "args": {
707
+ "should_epoch_stop": false,
708
+ "should_evaluate": false,
709
+ "should_log": false,
710
+ "should_save": true,
711
+ "should_training_stop": true
712
+ },
713
+ "attributes": {}
714
+ }
715
+ },
716
+ "total_flos": 1018842955776000.0,
717
+ "train_batch_size": 16,
718
+ "trial_name": null,
719
+ "trial_params": null
720
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cea7606350a4ea5cf17b1bae1ea34a044940cc6bb02e5dd4f33baa5a53da635
3
+ size 5240