minpeter commited on
Commit
bb3724b
·
verified ·
1 Parent(s): ab3c0be

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 31989,
8
+ "eos_token_id": 31989,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.036084391824351615,
13
+ "intermediate_size": 1920,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 27,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 31989,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 1000000.0,
25
+ "tie_word_embeddings": true,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.54.1",
28
+ "use_cache": false,
29
+ "vocab_size": 32000
30
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 31989,
4
+ "eos_token_id": 31989,
5
+ "pad_token_id": 31989,
6
+ "transformers_version": "4.54.1",
7
+ "use_cache": false
8
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd4d7deb85b2a3543b5afa31bbc84f94cbb8c34a94e35e2215c354aebb0376d
3
+ size 373077376
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f6b0ee44f3b73f289f7863976838a4d4935e338ff11708d6a81805fb7aaa52
3
+ size 373225035
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a794a6cb9cd4bbd0c53d08db0e20a5536c789bba6f22113385c1c408d58908bd
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fabf68d4ba15fc505c3ddaa1aef5ae6a1cb7856a1ce87040e1d0d9375e28c9bf
3
+ size 1401
last-checkpoint/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": 0.2079002079002079,
6
+ "eval_steps": 100,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002079002079002079,
14
+ "grad_norm": 1.4921875,
15
+ "learning_rate": 0.0,
16
+ "loss": 10.8788,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.004158004158004158,
21
+ "grad_norm": 4.5,
22
+ "learning_rate": 4.149377593360996e-06,
23
+ "loss": 10.8665,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.006237006237006237,
28
+ "grad_norm": 1.40625,
29
+ "learning_rate": 8.298755186721992e-06,
30
+ "loss": 10.8779,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.008316008316008316,
35
+ "grad_norm": 1.375,
36
+ "learning_rate": 1.2448132780082987e-05,
37
+ "loss": 10.8758,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.010395010395010396,
42
+ "grad_norm": 1.6328125,
43
+ "learning_rate": 1.6597510373443984e-05,
44
+ "loss": 10.8705,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.012474012474012475,
49
+ "grad_norm": 1.3984375,
50
+ "learning_rate": 2.074688796680498e-05,
51
+ "loss": 10.8667,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.014553014553014554,
56
+ "grad_norm": 1.4296875,
57
+ "learning_rate": 2.4896265560165973e-05,
58
+ "loss": 10.8705,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.016632016632016633,
63
+ "grad_norm": 1.3515625,
64
+ "learning_rate": 2.904564315352697e-05,
65
+ "loss": 10.875,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.018711018711018712,
70
+ "grad_norm": 1.609375,
71
+ "learning_rate": 3.319502074688797e-05,
72
+ "loss": 10.8695,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.02079002079002079,
77
+ "grad_norm": 1.3125,
78
+ "learning_rate": 3.734439834024896e-05,
79
+ "loss": 10.8753,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.02286902286902287,
84
+ "grad_norm": 1.40625,
85
+ "learning_rate": 4.149377593360996e-05,
86
+ "loss": 10.8749,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.02494802494802495,
91
+ "grad_norm": 1.375,
92
+ "learning_rate": 4.564315352697095e-05,
93
+ "loss": 10.8792,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.02702702702702703,
98
+ "grad_norm": 1.328125,
99
+ "learning_rate": 4.9792531120331946e-05,
100
+ "loss": 10.869,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.029106029106029108,
105
+ "grad_norm": 1.3984375,
106
+ "learning_rate": 5.394190871369295e-05,
107
+ "loss": 10.8685,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.031185031185031187,
112
+ "grad_norm": 1.46875,
113
+ "learning_rate": 5.809128630705394e-05,
114
+ "loss": 10.8719,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.033264033264033266,
119
+ "grad_norm": 1.3828125,
120
+ "learning_rate": 6.224066390041494e-05,
121
+ "loss": 10.8719,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.035343035343035345,
126
+ "grad_norm": 1.3828125,
127
+ "learning_rate": 6.639004149377594e-05,
128
+ "loss": 10.8723,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.037422037422037424,
133
+ "grad_norm": 1.390625,
134
+ "learning_rate": 7.053941908713692e-05,
135
+ "loss": 10.8653,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.0395010395010395,
140
+ "grad_norm": 1.3671875,
141
+ "learning_rate": 7.468879668049793e-05,
142
+ "loss": 10.863,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.04158004158004158,
147
+ "grad_norm": 1.53125,
148
+ "learning_rate": 7.883817427385891e-05,
149
+ "loss": 10.8578,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.04365904365904366,
154
+ "grad_norm": 1.40625,
155
+ "learning_rate": 8.298755186721991e-05,
156
+ "loss": 10.8624,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.04573804573804574,
161
+ "grad_norm": 1.3515625,
162
+ "learning_rate": 8.713692946058092e-05,
163
+ "loss": 10.8686,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.04781704781704782,
168
+ "grad_norm": 1.53125,
169
+ "learning_rate": 9.12863070539419e-05,
170
+ "loss": 10.8658,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.0498960498960499,
175
+ "grad_norm": 4.40625,
176
+ "learning_rate": 9.54356846473029e-05,
177
+ "loss": 10.8098,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.05197505197505198,
182
+ "grad_norm": 1.46875,
183
+ "learning_rate": 9.958506224066389e-05,
184
+ "loss": 10.8677,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.05405405405405406,
189
+ "grad_norm": 1.4765625,
190
+ "learning_rate": 0.00010373443983402491,
191
+ "loss": 10.8655,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.056133056133056136,
196
+ "grad_norm": 4.375,
197
+ "learning_rate": 0.0001078838174273859,
198
+ "loss": 10.8047,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.058212058212058215,
203
+ "grad_norm": 1.4609375,
204
+ "learning_rate": 0.0001120331950207469,
205
+ "loss": 10.8632,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.060291060291060294,
210
+ "grad_norm": 1.5,
211
+ "learning_rate": 0.00011618257261410788,
212
+ "loss": 10.8634,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.062370062370062374,
217
+ "grad_norm": 1.4296875,
218
+ "learning_rate": 0.00012033195020746888,
219
+ "loss": 10.8661,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.06444906444906445,
224
+ "grad_norm": 1.296875,
225
+ "learning_rate": 0.00012448132780082987,
226
+ "loss": 10.864,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.06652806652806653,
231
+ "grad_norm": 1.453125,
232
+ "learning_rate": 0.00012863070539419086,
233
+ "loss": 10.8622,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.06860706860706861,
238
+ "grad_norm": 1.34375,
239
+ "learning_rate": 0.00013278008298755187,
240
+ "loss": 10.8646,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.07068607068607069,
245
+ "grad_norm": 1.4921875,
246
+ "learning_rate": 0.0001369294605809129,
247
+ "loss": 10.8593,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.07276507276507277,
252
+ "grad_norm": 1.4296875,
253
+ "learning_rate": 0.00014107883817427385,
254
+ "loss": 10.8608,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.07484407484407485,
259
+ "grad_norm": 1.2109375,
260
+ "learning_rate": 0.00014522821576763486,
261
+ "loss": 10.8601,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.07692307692307693,
266
+ "grad_norm": 1.3046875,
267
+ "learning_rate": 0.00014937759336099585,
268
+ "loss": 10.8584,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.079002079002079,
273
+ "grad_norm": 1.4609375,
274
+ "learning_rate": 0.00015352697095435687,
275
+ "loss": 10.8649,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.08108108108108109,
280
+ "grad_norm": 1.3671875,
281
+ "learning_rate": 0.00015767634854771783,
282
+ "loss": 10.8509,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.08316008316008316,
287
+ "grad_norm": 1.53125,
288
+ "learning_rate": 0.00016182572614107884,
289
+ "loss": 10.8655,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.08523908523908524,
294
+ "grad_norm": 1.359375,
295
+ "learning_rate": 0.00016597510373443983,
296
+ "loss": 10.8572,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.08731808731808732,
301
+ "grad_norm": 1.421875,
302
+ "learning_rate": 0.00017012448132780084,
303
+ "loss": 10.8498,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.0893970893970894,
308
+ "grad_norm": 3.78125,
309
+ "learning_rate": 0.00017427385892116183,
310
+ "loss": 10.7,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.09147609147609148,
315
+ "grad_norm": 1.3125,
316
+ "learning_rate": 0.00017842323651452282,
317
+ "loss": 10.8577,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.09355509355509356,
322
+ "grad_norm": 1.390625,
323
+ "learning_rate": 0.0001825726141078838,
324
+ "loss": 10.8574,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.09563409563409564,
329
+ "grad_norm": 1.46875,
330
+ "learning_rate": 0.00018672199170124482,
331
+ "loss": 10.8341,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.09771309771309772,
336
+ "grad_norm": 1.390625,
337
+ "learning_rate": 0.0001908713692946058,
338
+ "loss": 10.8505,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.0997920997920998,
343
+ "grad_norm": 1.3671875,
344
+ "learning_rate": 0.0001950207468879668,
345
+ "loss": 10.8296,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.10187110187110188,
350
+ "grad_norm": 1.3984375,
351
+ "learning_rate": 0.00019917012448132778,
352
+ "loss": 10.8462,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.10395010395010396,
357
+ "grad_norm": 1.375,
358
+ "learning_rate": 0.0002033195020746888,
359
+ "loss": 10.8442,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.10602910602910603,
364
+ "grad_norm": 1.3203125,
365
+ "learning_rate": 0.00020746887966804981,
366
+ "loss": 10.8353,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.10810810810810811,
371
+ "grad_norm": 1.4609375,
372
+ "learning_rate": 0.0002116182572614108,
373
+ "loss": 10.8277,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.1101871101871102,
378
+ "grad_norm": 1.3125,
379
+ "learning_rate": 0.0002157676348547718,
380
+ "loss": 10.8403,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.11226611226611227,
385
+ "grad_norm": 1.3359375,
386
+ "learning_rate": 0.00021991701244813278,
387
+ "loss": 10.829,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.11434511434511435,
392
+ "grad_norm": 1.421875,
393
+ "learning_rate": 0.0002240663900414938,
394
+ "loss": 10.8103,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.11642411642411643,
399
+ "grad_norm": 1.3359375,
400
+ "learning_rate": 0.00022821576763485478,
401
+ "loss": 10.8384,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.11850311850311851,
406
+ "grad_norm": 1.3671875,
407
+ "learning_rate": 0.00023236514522821577,
408
+ "loss": 10.8279,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.12058212058212059,
413
+ "grad_norm": 1.625,
414
+ "learning_rate": 0.00023651452282157675,
415
+ "loss": 10.8164,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.12266112266112267,
420
+ "grad_norm": 1.3671875,
421
+ "learning_rate": 0.00024066390041493777,
422
+ "loss": 10.8323,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.12474012474012475,
427
+ "grad_norm": 4.21875,
428
+ "learning_rate": 0.00024481327800829876,
429
+ "loss": 10.6432,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.12681912681912683,
434
+ "grad_norm": 1.4375,
435
+ "learning_rate": 0.00024896265560165974,
436
+ "loss": 10.8131,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.1288981288981289,
441
+ "grad_norm": 1.4453125,
442
+ "learning_rate": 0.00025311203319502073,
443
+ "loss": 10.8202,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.13097713097713098,
448
+ "grad_norm": 2.53125,
449
+ "learning_rate": 0.0002572614107883817,
450
+ "loss": 10.5981,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.13305613305613306,
455
+ "grad_norm": 1.3359375,
456
+ "learning_rate": 0.00026141078838174276,
457
+ "loss": 10.8243,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.13513513513513514,
462
+ "grad_norm": 1.3125,
463
+ "learning_rate": 0.00026556016597510375,
464
+ "loss": 10.8219,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.13721413721413722,
469
+ "grad_norm": 1.4140625,
470
+ "learning_rate": 0.00026970954356846474,
471
+ "loss": 10.7936,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.1392931392931393,
476
+ "grad_norm": 1.3203125,
477
+ "learning_rate": 0.0002738589211618258,
478
+ "loss": 10.8229,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.14137214137214138,
483
+ "grad_norm": 1.46875,
484
+ "learning_rate": 0.0002780082987551867,
485
+ "loss": 10.7755,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.14345114345114346,
490
+ "grad_norm": 1.390625,
491
+ "learning_rate": 0.0002821576763485477,
492
+ "loss": 10.8028,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.14553014553014554,
497
+ "grad_norm": 1.5078125,
498
+ "learning_rate": 0.0002863070539419087,
499
+ "loss": 10.7772,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.14760914760914762,
504
+ "grad_norm": 1.3984375,
505
+ "learning_rate": 0.00029045643153526973,
506
+ "loss": 10.7781,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.1496881496881497,
511
+ "grad_norm": 1.5234375,
512
+ "learning_rate": 0.0002946058091286307,
513
+ "loss": 10.7663,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.15176715176715178,
518
+ "grad_norm": 1.328125,
519
+ "learning_rate": 0.0002987551867219917,
520
+ "loss": 10.7976,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.15384615384615385,
525
+ "grad_norm": 4.15625,
526
+ "learning_rate": 0.0003029045643153527,
527
+ "loss": 10.5842,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.15592515592515593,
532
+ "grad_norm": 1.375,
533
+ "learning_rate": 0.00030705394190871373,
534
+ "loss": 10.795,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.158004158004158,
539
+ "grad_norm": 1.375,
540
+ "learning_rate": 0.0003112033195020747,
541
+ "loss": 10.791,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.1600831600831601,
546
+ "grad_norm": 1.484375,
547
+ "learning_rate": 0.00031535269709543565,
548
+ "loss": 10.7756,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.16216216216216217,
553
+ "grad_norm": 1.421875,
554
+ "learning_rate": 0.00031950207468879664,
555
+ "loss": 10.7924,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.16424116424116425,
560
+ "grad_norm": 1.4375,
561
+ "learning_rate": 0.0003236514522821577,
562
+ "loss": 10.7854,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.16632016632016633,
567
+ "grad_norm": 1.4296875,
568
+ "learning_rate": 0.00032780082987551867,
569
+ "loss": 10.7742,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.1683991683991684,
574
+ "grad_norm": 1.359375,
575
+ "learning_rate": 0.00033195020746887966,
576
+ "loss": 10.7746,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.1704781704781705,
581
+ "grad_norm": 1.453125,
582
+ "learning_rate": 0.0003360995850622407,
583
+ "loss": 10.755,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.17255717255717257,
588
+ "grad_norm": 1.390625,
589
+ "learning_rate": 0.0003402489626556017,
590
+ "loss": 10.7675,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.17463617463617465,
595
+ "grad_norm": 1.6484375,
596
+ "learning_rate": 0.0003443983402489627,
597
+ "loss": 10.7589,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.17671517671517672,
602
+ "grad_norm": 1.40625,
603
+ "learning_rate": 0.00034854771784232366,
604
+ "loss": 10.7611,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.1787941787941788,
609
+ "grad_norm": 1.8203125,
610
+ "learning_rate": 0.00035269709543568465,
611
+ "loss": 10.775,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.18087318087318088,
616
+ "grad_norm": 1.3984375,
617
+ "learning_rate": 0.00035684647302904564,
618
+ "loss": 10.7117,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.18295218295218296,
623
+ "grad_norm": 1.34375,
624
+ "learning_rate": 0.00036099585062240663,
625
+ "loss": 10.7534,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.18503118503118504,
630
+ "grad_norm": 3.75,
631
+ "learning_rate": 0.0003651452282157676,
632
+ "loss": 10.7575,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.18711018711018712,
637
+ "grad_norm": 1.4765625,
638
+ "learning_rate": 0.00036929460580912866,
639
+ "loss": 10.7342,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.1891891891891892,
644
+ "grad_norm": 1.3671875,
645
+ "learning_rate": 0.00037344398340248964,
646
+ "loss": 10.7605,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.19126819126819128,
651
+ "grad_norm": 1.40625,
652
+ "learning_rate": 0.00037759336099585063,
653
+ "loss": 10.7133,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.19334719334719336,
658
+ "grad_norm": 1.40625,
659
+ "learning_rate": 0.0003817427385892116,
660
+ "loss": 10.7354,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.19542619542619544,
665
+ "grad_norm": 1.3671875,
666
+ "learning_rate": 0.00038589211618257266,
667
+ "loss": 10.7689,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.19750519750519752,
672
+ "grad_norm": 1.34375,
673
+ "learning_rate": 0.0003900414937759336,
674
+ "loss": 10.7537,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.1995841995841996,
679
+ "grad_norm": 1.515625,
680
+ "learning_rate": 0.0003941908713692946,
681
+ "loss": 10.7218,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.20166320166320167,
686
+ "grad_norm": 1.390625,
687
+ "learning_rate": 0.00039834024896265557,
688
+ "loss": 10.7424,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.20374220374220375,
693
+ "grad_norm": 1.4765625,
694
+ "learning_rate": 0.0004024896265560166,
695
+ "loss": 10.7158,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.20582120582120583,
700
+ "grad_norm": 1.484375,
701
+ "learning_rate": 0.0004066390041493776,
702
+ "loss": 10.7036,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.2079002079002079,
707
+ "grad_norm": 1.4609375,
708
+ "learning_rate": 0.0004107883817427386,
709
+ "loss": 10.6947,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.2079002079002079,
714
+ "eval_loss": 10.23933219909668,
715
+ "eval_runtime": 0.6087,
716
+ "eval_samples_per_second": 26.284,
717
+ "eval_steps_per_second": 3.286,
718
+ "step": 100
719
+ }
720
+ ],
721
+ "logging_steps": 1,
722
+ "max_steps": 4810,
723
+ "num_input_tokens_seen": 0,
724
+ "num_train_epochs": 10,
725
+ "save_steps": 100,
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": 2.54723638689792e+16,
739
+ "train_batch_size": 32,
740
+ "trial_name": null,
741
+ "trial_params": null
742
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2176662ce199a6498d6a867ed32a93ee009dc49982d0046d74255209c006f204
3
+ size 5777