AlekseyKorshuk commited on
Commit
461ffb6
•
1 Parent(s): 940b328

huggingartists

Browse files
README.md CHANGED
@@ -14,7 +14,7 @@ widget:
14
  <div class="inline-flex flex-col" style="line-height: 1.5;">
15
  <div class="flex">
16
  <div
17
- style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/631b206379b60df5e1da90e84d35fdbe.1000x1000x1.png&#39;)">
18
  </div>
19
  </div>
20
  <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
@@ -45,15 +45,15 @@ from datasets import load_dataset
45
  dataset = load_dataset("huggingartists/drake")
46
  ```
47
 
48
- [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2e42ok17/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
 
50
  ## Training procedure
51
 
52
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Drake's lyrics.
53
 
54
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2xe72oq3) for full transparency and reproducibility.
55
 
56
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2xe72oq3/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
 
14
  <div class="inline-flex flex-col" style="line-height: 1.5;">
15
  <div class="flex">
16
  <div
17
+ style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/26104e61a238b70abfbad57be3de4359.1000x1000x1.jpg&#39;)">
18
  </div>
19
  </div>
20
  <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
 
45
  dataset = load_dataset("huggingartists/drake")
46
  ```
47
 
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/l3lz2q80/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
 
50
  ## Training procedure
51
 
52
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Drake's lyrics.
53
 
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/033yz8al) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/033yz8al/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
config.json CHANGED
@@ -37,7 +37,7 @@
37
  }
38
  },
39
  "torch_dtype": "float32",
40
- "transformers_version": "4.20.1",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
 
37
  }
38
  },
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.19.2",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
evaluation.txt CHANGED
@@ -1 +1 @@
1
- {"eval_loss": 2.6586830615997314, "eval_runtime": 12.618, "eval_samples_per_second": 43.906, "eval_steps_per_second": 5.548, "epoch": 6.0}
 
1
+ {"eval_loss": 2.7749314308166504, "eval_runtime": 12.0228, "eval_samples_per_second": 46.245, "eval_steps_per_second": 5.822, "epoch": 10.0}
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb6ff1968e33bafe123ccca386bcb5b25cdd34682f12236ab1c25d04630b79f6
3
  size 497764120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fef0a464f99ffa656aeba8703a8c9c59eb2598c171629983c040906e1c7766e
3
  size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de10120cd339dc8a2411ec8e4b7e1d4af7983ab863a59e4fb699101f393fde92
3
- size 995604017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19382944fed5bf94169b751f9f2c761e6a940ec4935733346ccf367d095b91b
3
+ size 995605189
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cce53ebbc5d19a5a3d4fe01b3d7363a3a0c4f9cb9bdafea201bad39efd63457
3
- size 510396521
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fb146089842dc107f59abde1a42cdaf31e4dfeccb19badbb328f55885d55b3
3
+ size 510398013
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:326cc7de00c3f20c4fcf0338fdce1a6ac81da32e3abb8094e79488b6be2ca9fb
3
- size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d12daffdff29f561a8ac5d4847e7c787fe37a041bca46606a130ed3e1f9c06
3
+ size 14639
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ae78cbe0368ef751528f9df25bdcc580eaf09b6340910f9e0e6aae733d99451
3
- size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d4c5d94f9a5a9ecc46479b626d88e73d0320a365a30f0a14c82026b0b9f86e
3
+ size 627
special_tokens_map.json CHANGED
@@ -1,5 +1 @@
1
- {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
5
- }
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
 
 
 
 
tokenizer_config.json CHANGED
@@ -1,10 +1 @@
1
- {
2
- "add_prefix_space": false,
3
- "bos_token": "<|endoftext|>",
4
- "eos_token": "<|endoftext|>",
5
- "model_max_length": 1024,
6
- "name_or_path": "huggingartists/drake",
7
- "special_tokens_map_file": null,
8
- "tokenizer_class": "GPT2Tokenizer",
9
- "unk_token": "<|endoftext|>"
10
- }
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "huggingartists/drake", "special_tokens_map_file": null, "tokenizer_class": "GPT2Tokenizer"}
 
 
 
 
 
 
 
 
 
trainer_state.json CHANGED
@@ -1,2162 +1,444 @@
1
  {
2
- "best_metric": 2.6586830615997314,
3
- "best_model_checkpoint": "output/drake/checkpoint-1755",
4
- "epoch": 5.0,
5
- "global_step": 1755,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 0.01,
12
- "learning_rate": 0.0001371432064088578,
13
- "loss": 4.0588,
14
  "step": 5
15
  },
16
  {
17
  "epoch": 0.03,
18
- "learning_rate": 0.00013697291967368176,
19
- "loss": 3.874,
20
  "step": 10
21
  },
22
  {
23
  "epoch": 0.04,
24
- "learning_rate": 0.000136689421753516,
25
- "loss": 3.7354,
26
  "step": 15
27
  },
28
  {
29
- "epoch": 0.05,
30
- "learning_rate": 0.0001362931820613334,
31
- "loss": 3.678,
32
  "step": 20
33
  },
34
  {
35
- "epoch": 0.06,
36
- "learning_rate": 0.00013578485668678617,
37
- "loss": 3.4762,
38
  "step": 25
39
  },
40
  {
41
- "epoch": 0.08,
42
- "learning_rate": 0.00013516528730985944,
43
- "loss": 3.9075,
44
  "step": 30
45
  },
46
  {
47
- "epoch": 0.09,
48
- "learning_rate": 0.000134435499807226,
49
- "loss": 3.8826,
50
  "step": 35
51
  },
52
  {
53
- "epoch": 0.1,
54
- "learning_rate": 0.00013359670255361022,
55
- "loss": 3.6832,
56
  "step": 40
57
  },
58
  {
59
- "epoch": 0.12,
60
- "learning_rate": 0.00013265028442097337,
61
- "loss": 3.5663,
62
  "step": 45
63
  },
64
  {
65
- "epoch": 0.13,
66
- "learning_rate": 0.00013159781247883373,
67
- "loss": 3.875,
68
  "step": 50
69
  },
70
  {
71
- "epoch": 0.14,
72
- "learning_rate": 0.00013044102939952857,
73
- "loss": 3.6027,
74
  "step": 55
75
  },
76
  {
77
- "epoch": 0.16,
78
- "learning_rate": 0.00012918185057271526,
79
- "loss": 3.7132,
80
  "step": 60
81
  },
82
  {
83
- "epoch": 0.17,
84
- "learning_rate": 0.0001278223609338884,
85
- "loss": 3.5338,
86
  "step": 65
87
  },
88
  {
89
- "epoch": 0.18,
90
- "learning_rate": 0.00012636481151216485,
91
- "loss": 3.8949,
92
  "step": 70
93
  },
94
  {
95
- "epoch": 0.19,
96
- "learning_rate": 0.0001248116157030527,
97
- "loss": 3.5964,
98
  "step": 75
99
  },
100
  {
101
- "epoch": 0.21,
102
- "learning_rate": 0.0001231653452723755,
103
- "loss": 3.7202,
104
  "step": 80
105
  },
106
  {
107
- "epoch": 0.22,
108
- "learning_rate": 0.00012142872609796847,
109
- "loss": 3.6172,
110
  "step": 85
111
  },
112
  {
113
- "epoch": 0.23,
114
- "learning_rate": 0.00011960463365619783,
115
- "loss": 3.4145,
116
  "step": 90
117
  },
118
  {
119
- "epoch": 0.25,
120
- "learning_rate": 0.00011769608826077622,
121
- "loss": 3.555,
122
  "step": 95
123
  },
124
  {
125
- "epoch": 0.26,
126
- "learning_rate": 0.000115706250061758,
127
- "loss": 3.4485,
128
  "step": 100
129
  },
130
  {
131
- "epoch": 0.27,
132
- "learning_rate": 0.00011363841381299484,
133
- "loss": 3.7157,
134
  "step": 105
135
  },
136
  {
137
- "epoch": 0.28,
138
- "learning_rate": 0.000111496003416716,
139
- "loss": 3.6139,
140
  "step": 110
141
  },
142
  {
143
- "epoch": 0.3,
144
- "learning_rate": 0.0001092825662542656,
145
- "loss": 3.6335,
146
  "step": 115
147
  },
148
  {
149
- "epoch": 0.31,
150
- "learning_rate": 0.00010700176731238488,
151
- "loss": 3.8618,
152
  "step": 120
153
  },
154
  {
155
- "epoch": 0.32,
156
- "learning_rate": 0.00010465738311476428,
157
- "loss": 3.5889,
158
  "step": 125
159
  },
160
  {
161
- "epoch": 0.34,
162
- "learning_rate": 0.00010225329546891398,
163
- "loss": 3.5039,
164
  "step": 130
165
  },
166
  {
167
- "epoch": 0.35,
168
- "learning_rate": 9.979348503870657e-05,
169
- "loss": 3.456,
170
  "step": 135
171
  },
172
  {
173
- "epoch": 0.36,
174
- "learning_rate": 9.728202475323418e-05,
175
- "loss": 3.5593,
176
  "step": 140
177
  },
178
  {
179
- "epoch": 0.38,
180
- "learning_rate": 9.472307306289397e-05,
181
- "loss": 3.6619,
182
  "step": 145
183
  },
184
  {
185
- "epoch": 0.39,
186
- "learning_rate": 9.21208670538683e-05,
187
- "loss": 3.2545,
188
  "step": 150
189
  },
190
  {
191
- "epoch": 0.4,
192
- "learning_rate": 8.94797154324004e-05,
193
- "loss": 3.5664,
194
  "step": 155
195
  },
196
  {
197
- "epoch": 0.41,
198
- "learning_rate": 8.680399139048255e-05,
199
- "loss": 3.6659,
200
  "step": 160
201
  },
202
  {
203
- "epoch": 0.43,
204
- "learning_rate": 8.409812536476914e-05,
205
- "loss": 3.4141,
206
  "step": 165
207
  },
208
  {
209
- "epoch": 0.44,
210
- "learning_rate": 8.136659770070481e-05,
211
- "loss": 3.3853,
212
  "step": 170
213
  },
214
  {
215
- "epoch": 0.45,
216
- "learning_rate": 7.86139312340139e-05,
217
- "loss": 3.5356,
218
  "step": 175
219
  },
220
  {
221
- "epoch": 0.47,
222
- "learning_rate": 7.584468380183525e-05,
223
- "loss": 3.6393,
224
  "step": 180
225
  },
226
  {
227
- "epoch": 0.48,
228
- "learning_rate": 7.306344069590158e-05,
229
- "loss": 3.7593,
230
  "step": 185
231
  },
232
  {
233
- "epoch": 0.49,
234
- "learning_rate": 7.027480707026031e-05,
235
- "loss": 3.6784,
236
  "step": 190
237
  },
238
  {
239
- "epoch": 0.51,
240
- "learning_rate": 6.748340031610621e-05,
241
- "loss": 3.4365,
242
  "step": 195
243
  },
244
  {
245
- "epoch": 0.52,
246
- "learning_rate": 6.469384241635202e-05,
247
- "loss": 3.4692,
248
  "step": 200
249
  },
250
  {
251
- "epoch": 0.53,
252
- "learning_rate": 6.191075229259615e-05,
253
- "loss": 3.5463,
254
  "step": 205
255
  },
256
  {
257
- "epoch": 0.54,
258
- "learning_rate": 5.9138738157159314e-05,
259
- "loss": 3.4183,
260
  "step": 210
261
  },
262
  {
263
- "epoch": 0.56,
264
- "learning_rate": 5.638238988285346e-05,
265
- "loss": 3.6126,
266
  "step": 215
267
  },
268
  {
269
- "epoch": 0.57,
270
- "learning_rate": 5.364627140311692e-05,
271
- "loss": 3.5828,
272
  "step": 220
273
  },
274
  {
275
- "epoch": 0.58,
276
- "learning_rate": 5.093491315510001e-05,
277
- "loss": 3.4454,
278
  "step": 225
279
  },
280
  {
281
- "epoch": 0.6,
282
- "learning_rate": 4.825280457821314e-05,
283
- "loss": 3.5058,
284
  "step": 230
285
  },
286
  {
287
- "epoch": 0.61,
288
- "learning_rate": 4.560438668055879e-05,
289
- "loss": 3.4436,
290
  "step": 235
291
  },
292
  {
293
- "epoch": 0.62,
294
- "learning_rate": 4.299404468555545e-05,
295
- "loss": 3.3312,
296
  "step": 240
297
  },
298
  {
299
- "epoch": 0.63,
300
- "learning_rate": 4.042610077092918e-05,
301
- "loss": 3.4519,
302
  "step": 245
303
  },
304
  {
305
- "epoch": 0.65,
306
- "learning_rate": 3.7904806912095865e-05,
307
- "loss": 3.2724,
308
  "step": 250
309
  },
310
  {
311
- "epoch": 0.66,
312
- "learning_rate": 3.543433784178337e-05,
313
- "loss": 3.708,
314
  "step": 255
315
  },
316
  {
317
- "epoch": 0.67,
318
- "learning_rate": 3.30187841375518e-05,
319
- "loss": 3.3732,
320
  "step": 260
321
  },
322
  {
323
- "epoch": 0.69,
324
- "learning_rate": 3.06621454486565e-05,
325
- "loss": 3.6682,
326
  "step": 265
327
  },
328
  {
329
- "epoch": 0.7,
330
- "learning_rate": 2.8368323873469696e-05,
331
- "loss": 3.3303,
332
  "step": 270
333
  },
334
  {
335
- "epoch": 0.71,
336
- "learning_rate": 2.614111749842566e-05,
337
- "loss": 3.4287,
338
  "step": 275
339
  },
340
  {
341
- "epoch": 0.73,
342
- "learning_rate": 2.39842141091877e-05,
343
- "loss": 3.4274,
344
  "step": 280
345
  },
346
  {
347
- "epoch": 0.74,
348
- "learning_rate": 2.1901185084450396e-05,
349
- "loss": 3.3246,
350
  "step": 285
351
  },
352
  {
353
- "epoch": 0.75,
354
- "learning_rate": 1.9895479482486794e-05,
355
- "loss": 3.4282,
356
  "step": 290
357
  },
358
  {
359
- "epoch": 0.76,
360
- "learning_rate": 1.7970418330233093e-05,
361
- "loss": 3.2375,
362
  "step": 295
363
  },
364
  {
365
- "epoch": 0.78,
366
- "learning_rate": 1.61291891243658e-05,
367
- "loss": 3.581,
368
  "step": 300
369
  },
370
  {
371
- "epoch": 0.79,
372
- "learning_rate": 1.4374840553477238e-05,
373
- "loss": 3.42,
374
  "step": 305
375
  },
376
  {
377
- "epoch": 0.8,
378
- "learning_rate": 1.2710277450088041e-05,
379
- "loss": 3.4236,
380
  "step": 310
381
  },
382
  {
383
- "epoch": 0.82,
384
- "learning_rate": 1.1138255980854819e-05,
385
- "loss": 3.3657,
386
  "step": 315
387
  },
388
  {
389
- "epoch": 0.83,
390
- "learning_rate": 9.661379082937688e-06,
391
- "loss": 3.1107,
392
  "step": 320
393
  },
394
  {
395
- "epoch": 0.84,
396
- "learning_rate": 8.282092154083231e-06,
397
- "loss": 3.3076,
398
  "step": 325
399
  },
400
  {
401
- "epoch": 0.85,
402
- "learning_rate": 7.002679003559785e-06,
403
- "loss": 3.3086,
404
  "step": 330
405
  },
406
  {
407
- "epoch": 0.87,
408
- "learning_rate": 5.825258070649407e-06,
409
- "loss": 3.3643,
410
  "step": 335
411
  },
412
  {
413
- "epoch": 0.88,
414
- "learning_rate": 4.7517789169574735e-06,
415
- "loss": 3.348,
416
  "step": 340
417
  },
418
  {
419
- "epoch": 0.89,
420
- "learning_rate": 3.7840189983485763e-06,
421
- "loss": 3.391,
422
  "step": 345
423
  },
424
  {
425
- "epoch": 0.91,
426
- "learning_rate": 2.9235807218530457e-06,
427
- "loss": 3.2735,
428
  "step": 350
429
  },
430
- {
431
- "epoch": 0.92,
432
- "learning_rate": 2.171888792417796e-06,
433
- "loss": 3.576,
434
- "step": 355
435
- },
436
- {
437
- "epoch": 0.93,
438
- "learning_rate": 1.5301878538942795e-06,
439
- "loss": 3.2583,
440
- "step": 360
441
- },
442
- {
443
- "epoch": 0.95,
444
- "learning_rate": 9.995404281699138e-07,
445
- "loss": 3.5956,
446
- "step": 365
447
- },
448
- {
449
- "epoch": 0.96,
450
- "learning_rate": 5.808251558551173e-07,
451
- "loss": 3.7098,
452
- "step": 370
453
- },
454
- {
455
- "epoch": 0.97,
456
- "learning_rate": 2.7473534143910847e-07,
457
- "loss": 3.3973,
458
- "step": 375
459
- },
460
- {
461
- "epoch": 0.98,
462
- "learning_rate": 8.177780532344056e-08,
463
- "loss": 3.3842,
464
- "step": 380
465
- },
466
  {
467
  "epoch": 1.0,
468
- "learning_rate": 2.2720446338799106e-09,
469
- "loss": 3.2786,
470
- "step": 385
471
- },
472
- {
473
- "epoch": 1.18,
474
- "learning_rate": 1.0890007647780969e-05,
475
- "loss": 3.2655,
476
- "step": 390
477
- },
478
- {
479
- "epoch": 1.2,
480
- "learning_rate": 1.2720089689346961e-05,
481
- "loss": 3.1689,
482
- "step": 395
483
- },
484
- {
485
- "epoch": 1.21,
486
- "learning_rate": 1.4676757700644785e-05,
487
- "loss": 3.15,
488
- "step": 400
489
- },
490
- {
491
- "epoch": 1.23,
492
- "learning_rate": 1.6755579199297876e-05,
493
- "loss": 3.3109,
494
- "step": 405
495
- },
496
- {
497
- "epoch": 1.24,
498
- "learning_rate": 1.8951844985992176e-05,
499
- "loss": 3.3557,
500
- "step": 410
501
- },
502
- {
503
- "epoch": 1.26,
504
- "learning_rate": 2.1260579812327114e-05,
505
- "loss": 3.2466,
506
- "step": 415
507
- },
508
- {
509
- "epoch": 1.27,
510
- "learning_rate": 2.3676553651353433e-05,
511
- "loss": 3.4927,
512
- "step": 420
513
- },
514
- {
515
- "epoch": 1.29,
516
- "learning_rate": 2.6194293545266464e-05,
517
- "loss": 3.5059,
518
- "step": 425
519
- },
520
- {
521
- "epoch": 1.3,
522
- "learning_rate": 2.8808096003415798e-05,
523
- "loss": 3.3394,
524
- "step": 430
525
- },
526
- {
527
- "epoch": 1.32,
528
- "learning_rate": 3.151203992254596e-05,
529
- "loss": 2.9776,
530
- "step": 435
531
- },
532
- {
533
- "epoch": 1.33,
534
- "learning_rate": 3.429999999999997e-05,
535
- "loss": 3.1045,
536
- "step": 440
537
- },
538
- {
539
- "epoch": 1.35,
540
- "learning_rate": 3.716566060949963e-05,
541
- "loss": 3.3412,
542
- "step": 445
543
- },
544
- {
545
- "epoch": 1.36,
546
- "learning_rate": 4.0102530108070535e-05,
547
- "loss": 3.3821,
548
- "step": 450
549
- },
550
- {
551
- "epoch": 1.38,
552
- "learning_rate": 4.3103955541701554e-05,
553
- "loss": 3.2771,
554
- "step": 455
555
- },
556
- {
557
- "epoch": 1.39,
558
- "learning_rate": 4.6163137716424864e-05,
559
- "loss": 3.2889,
560
- "step": 460
561
- },
562
- {
563
- "epoch": 1.41,
564
- "learning_rate": 4.927314660067792e-05,
565
- "loss": 3.1803,
566
- "step": 465
567
- },
568
- {
569
- "epoch": 1.42,
570
- "learning_rate": 5.242693702405331e-05,
571
- "loss": 3.3752,
572
- "step": 470
573
- },
574
- {
575
- "epoch": 1.44,
576
- "learning_rate": 5.561736463687583e-05,
577
- "loss": 3.4172,
578
- "step": 475
579
- },
580
- {
581
- "epoch": 1.45,
582
- "learning_rate": 5.883720209445263e-05,
583
- "loss": 3.1247,
584
- "step": 480
585
- },
586
- {
587
- "epoch": 1.47,
588
- "learning_rate": 6.207915542933309e-05,
589
- "loss": 3.1979,
590
- "step": 485
591
- },
592
- {
593
- "epoch": 1.48,
594
- "learning_rate": 6.533588057449125e-05,
595
- "loss": 3.2403,
596
- "step": 490
597
- },
598
- {
599
- "epoch": 1.5,
600
- "learning_rate": 6.859999999999999e-05,
601
- "loss": 3.3824,
602
- "step": 495
603
- },
604
- {
605
- "epoch": 1.52,
606
- "learning_rate": 7.186411942550872e-05,
607
- "loss": 3.2565,
608
- "step": 500
609
- },
610
- {
611
- "epoch": 1.53,
612
- "learning_rate": 7.512084457066689e-05,
613
- "loss": 3.1016,
614
- "step": 505
615
- },
616
- {
617
- "epoch": 1.55,
618
- "learning_rate": 7.836279790554734e-05,
619
- "loss": 3.4194,
620
- "step": 510
621
- },
622
- {
623
- "epoch": 1.56,
624
- "learning_rate": 8.158263536312414e-05,
625
- "loss": 3.1877,
626
- "step": 515
627
- },
628
- {
629
- "epoch": 1.58,
630
- "learning_rate": 8.477306297594667e-05,
631
- "loss": 3.4791,
632
- "step": 520
633
- },
634
- {
635
- "epoch": 1.59,
636
- "learning_rate": 8.792685339932205e-05,
637
- "loss": 3.2052,
638
- "step": 525
639
- },
640
- {
641
- "epoch": 1.61,
642
- "learning_rate": 9.103686228357512e-05,
643
- "loss": 3.4702,
644
- "step": 530
645
- },
646
- {
647
- "epoch": 1.62,
648
- "learning_rate": 9.409604445829843e-05,
649
- "loss": 3.152,
650
- "step": 535
651
- },
652
- {
653
- "epoch": 1.64,
654
- "learning_rate": 9.709746989192944e-05,
655
- "loss": 3.2925,
656
- "step": 540
657
- },
658
- {
659
- "epoch": 1.65,
660
- "learning_rate": 0.00010003433939050033,
661
- "loss": 3.2007,
662
- "step": 545
663
- },
664
- {
665
- "epoch": 1.67,
666
- "learning_rate": 0.00010290000000000001,
667
- "loss": 3.444,
668
- "step": 550
669
- },
670
- {
671
- "epoch": 1.68,
672
- "learning_rate": 0.00010568796007745401,
673
- "loss": 3.227,
674
- "step": 555
675
- },
676
- {
677
- "epoch": 1.7,
678
- "learning_rate": 0.00010839190399658417,
679
- "loss": 3.133,
680
- "step": 560
681
- },
682
- {
683
- "epoch": 1.71,
684
- "learning_rate": 0.00011100570645473351,
685
- "loss": 3.1161,
686
- "step": 565
687
- },
688
- {
689
- "epoch": 1.73,
690
- "learning_rate": 0.00011352344634864656,
691
- "loss": 3.2043,
692
- "step": 570
693
- },
694
- {
695
- "epoch": 1.74,
696
- "learning_rate": 0.00011593942018767285,
697
- "loss": 3.265,
698
- "step": 575
699
- },
700
- {
701
- "epoch": 1.76,
702
- "learning_rate": 0.00011824815501400781,
703
- "loss": 3.3016,
704
- "step": 580
705
- },
706
- {
707
- "epoch": 1.77,
708
- "learning_rate": 0.00012044442080070208,
709
- "loss": 3.3944,
710
- "step": 585
711
- },
712
- {
713
- "epoch": 1.79,
714
- "learning_rate": 0.0001225232422993552,
715
- "loss": 3.4325,
716
- "step": 590
717
- },
718
- {
719
- "epoch": 1.8,
720
- "learning_rate": 0.00012447991031065301,
721
- "loss": 3.3161,
722
- "step": 595
723
- },
724
- {
725
- "epoch": 1.82,
726
- "learning_rate": 0.000126309992352219,
727
- "loss": 3.2818,
728
- "step": 600
729
- },
730
- {
731
- "epoch": 1.83,
732
- "learning_rate": 0.00012800934269961248,
733
- "loss": 3.2362,
734
- "step": 605
735
- },
736
- {
737
- "epoch": 1.85,
738
- "learning_rate": 0.00012957411177772773,
739
- "loss": 3.1107,
740
- "step": 610
741
- },
742
- {
743
- "epoch": 1.86,
744
- "learning_rate": 0.00013100075488131993,
745
- "loss": 3.2821,
746
- "step": 615
747
- },
748
- {
749
- "epoch": 1.88,
750
- "learning_rate": 0.00013228604020490257,
751
- "loss": 3.3709,
752
- "step": 620
753
- },
754
- {
755
- "epoch": 1.89,
756
- "learning_rate": 0.00013342705616382626,
757
- "loss": 3.3293,
758
- "step": 625
759
- },
760
- {
761
- "epoch": 1.91,
762
- "learning_rate": 0.00013442121798995453,
763
- "loss": 3.5064,
764
- "step": 630
765
- },
766
- {
767
- "epoch": 1.92,
768
- "learning_rate": 0.00013526627358699495,
769
- "loss": 3.2024,
770
- "step": 635
771
- },
772
- {
773
- "epoch": 1.94,
774
- "learning_rate": 0.00013596030863222166,
775
- "loss": 3.378,
776
- "step": 640
777
- },
778
- {
779
- "epoch": 1.95,
780
- "learning_rate": 0.000136501750913032,
781
- "loss": 3.215,
782
- "step": 645
783
- },
784
- {
785
- "epoch": 1.97,
786
- "learning_rate": 0.0001368893738885136,
787
- "loss": 3.2645,
788
- "step": 650
789
- },
790
- {
791
- "epoch": 1.98,
792
- "learning_rate": 0.00013712229946795436,
793
- "loss": 3.2699,
794
- "step": 655
795
- },
796
- {
797
- "epoch": 2.0,
798
- "learning_rate": 0.0001372,
799
- "loss": 2.9558,
800
- "step": 660
801
- },
802
- {
803
- "epoch": 2.0,
804
- "eval_loss": 3.1339056491851807,
805
- "eval_runtime": 9.8661,
806
- "eval_samples_per_second": 45.611,
807
- "eval_steps_per_second": 5.777,
808
- "step": 660
809
- },
810
- {
811
- "epoch": 2.03,
812
- "learning_rate": 0.0001369452804670866,
813
- "loss": 2.8801,
814
- "step": 665
815
- },
816
- {
817
- "epoch": 2.04,
818
- "learning_rate": 0.00013658418337916058,
819
- "loss": 3.0411,
820
- "step": 670
821
- },
822
- {
823
- "epoch": 2.06,
824
- "learning_rate": 0.00013606719676147636,
825
- "loss": 3.1263,
826
- "step": 675
827
- },
828
- {
829
- "epoch": 2.07,
830
- "learning_rate": 0.00013539550607801564,
831
- "loss": 3.2868,
832
- "step": 680
833
- },
834
- {
835
- "epoch": 2.09,
836
- "learning_rate": 0.00013457065153327282,
837
- "loss": 3.0776,
838
- "step": 685
839
- },
840
- {
841
- "epoch": 2.1,
842
- "learning_rate": 0.00013359452454052534,
843
- "loss": 3.1467,
844
- "step": 690
845
- },
846
- {
847
- "epoch": 2.12,
848
- "learning_rate": 0.00013246936338477295,
849
- "loss": 2.9318,
850
- "step": 695
851
- },
852
- {
853
- "epoch": 2.13,
854
- "learning_rate": 0.00013119774809029134,
855
- "loss": 3.2317,
856
- "step": 700
857
- },
858
- {
859
- "epoch": 2.15,
860
- "learning_rate": 0.00012978259450456783,
861
- "loss": 2.9684,
862
- "step": 705
863
- },
864
- {
865
- "epoch": 2.16,
866
- "learning_rate": 0.0001282271476121864,
867
- "loss": 3.2684,
868
- "step": 710
869
- },
870
- {
871
- "epoch": 2.18,
872
- "learning_rate": 0.0001265349740939919,
873
- "loss": 3.1091,
874
- "step": 715
875
- },
876
- {
877
- "epoch": 2.2,
878
- "learning_rate": 0.00012470995414859683,
879
- "loss": 3.0846,
880
- "step": 720
881
- },
882
- {
883
- "epoch": 2.21,
884
- "learning_rate": 0.00012275627259498339,
885
- "loss": 3.2676,
886
- "step": 725
887
- },
888
- {
889
- "epoch": 2.23,
890
- "learning_rate": 0.00012067840927660262,
891
- "loss": 3.1157,
892
- "step": 730
893
- },
894
- {
895
- "epoch": 2.24,
896
- "learning_rate": 0.00011848112878897519,
897
- "loss": 3.2578,
898
- "step": 735
899
- },
900
- {
901
- "epoch": 2.26,
902
- "learning_rate": 0.00011616946955434783,
903
- "loss": 3.1545,
904
- "step": 740
905
- },
906
- {
907
- "epoch": 2.27,
908
- "learning_rate": 0.00011374873226845785,
909
- "loss": 3.0167,
910
- "step": 745
911
- },
912
- {
913
- "epoch": 2.29,
914
- "learning_rate": 0.00011122446774589795,
915
- "loss": 3.3236,
916
- "step": 750
917
- },
918
- {
919
- "epoch": 2.3,
920
- "learning_rate": 0.00010860246419195128,
921
- "loss": 3.0855,
922
- "step": 755
923
- },
924
- {
925
- "epoch": 2.32,
926
- "learning_rate": 0.00010588873393008382,
927
- "loss": 3.1622,
928
- "step": 760
929
- },
930
- {
931
- "epoch": 2.33,
932
- "learning_rate": 0.00010308949961552774,
933
- "loss": 3.1558,
934
- "step": 765
935
- },
936
- {
937
- "epoch": 2.35,
938
- "learning_rate": 0.0001002111799665686,
939
- "loss": 3.1256,
940
- "step": 770
941
- },
942
- {
943
- "epoch": 2.36,
944
- "learning_rate": 9.726037504625446e-05,
945
- "loss": 3.0624,
946
- "step": 775
947
- },
948
- {
949
- "epoch": 2.38,
950
- "learning_rate": 9.424385112827677e-05,
951
- "loss": 3.127,
952
- "step": 780
953
- },
954
- {
955
- "epoch": 2.39,
956
- "learning_rate": 9.1168525181726e-05,
957
- "loss": 3.2459,
958
- "step": 785
959
- },
960
- {
961
- "epoch": 2.41,
962
- "learning_rate": 8.80414490102987e-05,
963
- "loss": 3.2356,
964
- "step": 790
965
- },
966
- {
967
- "epoch": 2.42,
968
- "learning_rate": 8.486979308232529e-05,
969
- "loss": 3.1039,
970
- "step": 795
971
- },
972
- {
973
- "epoch": 2.44,
974
- "learning_rate": 8.16608300886963e-05,
975
- "loss": 3.1498,
976
- "step": 800
977
- },
978
- {
979
- "epoch": 2.45,
980
- "learning_rate": 7.842191826639015e-05,
981
- "loss": 3.2395,
982
- "step": 805
983
- },
984
- {
985
- "epoch": 2.47,
986
- "learning_rate": 7.516048452584106e-05,
987
- "loss": 3.0791,
988
- "step": 810
989
- },
990
- {
991
- "epoch": 2.48,
992
- "learning_rate": 7.18840074208375e-05,
993
- "loss": 2.9722,
994
- "step": 815
995
- },
996
- {
997
- "epoch": 2.5,
998
- "learning_rate": 6.860000000000001e-05,
999
- "loss": 3.0485,
1000
- "step": 820
1001
- },
1002
- {
1003
- "epoch": 2.52,
1004
- "learning_rate": 6.531599257916255e-05,
1005
- "loss": 3.26,
1006
- "step": 825
1007
- },
1008
- {
1009
- "epoch": 2.53,
1010
- "learning_rate": 6.203951547415898e-05,
1011
- "loss": 3.0569,
1012
- "step": 830
1013
- },
1014
- {
1015
- "epoch": 2.55,
1016
- "learning_rate": 5.877808173360989e-05,
1017
- "loss": 3.0239,
1018
- "step": 835
1019
- },
1020
- {
1021
- "epoch": 2.56,
1022
- "learning_rate": 5.553916991130374e-05,
1023
- "loss": 3.1443,
1024
- "step": 840
1025
- },
1026
- {
1027
- "epoch": 2.58,
1028
- "learning_rate": 5.2330206917674755e-05,
1029
- "loss": 3.1212,
1030
- "step": 845
1031
- },
1032
- {
1033
- "epoch": 2.59,
1034
- "learning_rate": 4.915855098970134e-05,
1035
- "loss": 2.8549,
1036
- "step": 850
1037
- },
1038
- {
1039
- "epoch": 2.61,
1040
- "learning_rate": 4.603147481827398e-05,
1041
- "loss": 2.9992,
1042
- "step": 855
1043
- },
1044
- {
1045
- "epoch": 2.62,
1046
- "learning_rate": 4.2956148871723224e-05,
1047
- "loss": 2.8552,
1048
- "step": 860
1049
- },
1050
- {
1051
- "epoch": 2.64,
1052
- "learning_rate": 3.9939624953745524e-05,
1053
- "loss": 3.0432,
1054
- "step": 865
1055
- },
1056
- {
1057
- "epoch": 2.65,
1058
- "learning_rate": 3.698882003343138e-05,
1059
- "loss": 3.028,
1060
- "step": 870
1061
- },
1062
- {
1063
- "epoch": 2.67,
1064
- "learning_rate": 3.411050038447229e-05,
1065
- "loss": 3.1615,
1066
- "step": 875
1067
- },
1068
- {
1069
- "epoch": 2.68,
1070
- "learning_rate": 3.131126606991618e-05,
1071
- "loss": 3.1442,
1072
- "step": 880
1073
- },
1074
- {
1075
- "epoch": 2.7,
1076
- "learning_rate": 2.8597535808048707e-05,
1077
- "loss": 3.0388,
1078
- "step": 885
1079
- },
1080
- {
1081
- "epoch": 2.71,
1082
- "learning_rate": 2.5975532254102027e-05,
1083
- "loss": 2.9324,
1084
- "step": 890
1085
- },
1086
- {
1087
- "epoch": 2.73,
1088
- "learning_rate": 2.3451267731542143e-05,
1089
- "loss": 2.9219,
1090
- "step": 895
1091
- },
1092
- {
1093
- "epoch": 2.74,
1094
- "learning_rate": 2.1030530445652233e-05,
1095
- "loss": 2.8783,
1096
- "step": 900
1097
- },
1098
- {
1099
- "epoch": 2.76,
1100
- "learning_rate": 1.871887121102488e-05,
1101
- "loss": 3.2507,
1102
- "step": 905
1103
- },
1104
- {
1105
- "epoch": 2.77,
1106
- "learning_rate": 1.6521590723397454e-05,
1107
- "loss": 2.969,
1108
- "step": 910
1109
- },
1110
- {
1111
- "epoch": 2.79,
1112
- "learning_rate": 1.4443727405016684e-05,
1113
- "loss": 2.9703,
1114
- "step": 915
1115
- },
1116
- {
1117
- "epoch": 2.8,
1118
- "learning_rate": 1.249004585140324e-05,
1119
- "loss": 3.105,
1120
- "step": 920
1121
- },
1122
- {
1123
- "epoch": 2.82,
1124
- "learning_rate": 1.0665025906008154e-05,
1125
- "loss": 3.1641,
1126
- "step": 925
1127
- },
1128
- {
1129
- "epoch": 2.84,
1130
- "learning_rate": 8.97285238781366e-06,
1131
- "loss": 2.9782,
1132
- "step": 930
1133
- },
1134
- {
1135
- "epoch": 2.85,
1136
- "learning_rate": 7.417405495432199e-06,
1137
- "loss": 3.0392,
1138
- "step": 935
1139
- },
1140
- {
1141
- "epoch": 2.87,
1142
- "learning_rate": 6.002251909708709e-06,
1143
- "loss": 2.962,
1144
- "step": 940
1145
- },
1146
- {
1147
- "epoch": 2.88,
1148
- "learning_rate": 4.730636615227076e-06,
1149
- "loss": 3.3658,
1150
- "step": 945
1151
- },
1152
- {
1153
- "epoch": 2.9,
1154
- "learning_rate": 3.605475459474696e-06,
1155
- "loss": 2.9995,
1156
- "step": 950
1157
- },
1158
- {
1159
- "epoch": 2.91,
1160
- "learning_rate": 2.6293484667271903e-06,
1161
- "loss": 3.1411,
1162
- "step": 955
1163
- },
1164
- {
1165
- "epoch": 2.93,
1166
- "learning_rate": 1.8044939219843706e-06,
1167
- "loss": 3.2262,
1168
- "step": 960
1169
- },
1170
- {
1171
- "epoch": 2.94,
1172
- "learning_rate": 1.132803238523659e-06,
1173
- "loss": 2.995,
1174
- "step": 965
1175
- },
1176
- {
1177
- "epoch": 2.96,
1178
- "learning_rate": 6.158166208394294e-07,
1179
- "loss": 3.1868,
1180
- "step": 970
1181
- },
1182
- {
1183
- "epoch": 2.97,
1184
- "learning_rate": 2.547195329134365e-07,
1185
- "loss": 3.0908,
1186
- "step": 975
1187
- },
1188
- {
1189
- "epoch": 2.99,
1190
- "learning_rate": 5.033997991443411e-08,
1191
- "loss": 3.0958,
1192
- "step": 980
1193
- },
1194
- {
1195
- "epoch": 3.0,
1196
- "eval_loss": 3.012192964553833,
1197
- "eval_runtime": 3.2423,
1198
- "eval_samples_per_second": 143.415,
1199
- "eval_steps_per_second": 18.197,
1200
- "step": 984
1201
- },
1202
- {
1203
- "epoch": 3.0,
1204
- "learning_rate": 3.1466095605587442e-09,
1205
- "loss": 3.2577,
1206
- "step": 985
1207
- },
1208
- {
1209
- "epoch": 3.02,
1210
- "learning_rate": 1.1324763749765112e-07,
1211
- "loss": 2.9737,
1212
- "step": 990
1213
- },
1214
- {
1215
- "epoch": 3.03,
1216
- "learning_rate": 3.803905991579816e-07,
1217
- "loss": 2.7524,
1218
- "step": 995
1219
- },
1220
- {
1221
- "epoch": 3.05,
1222
- "learning_rate": 8.03962928668091e-07,
1223
- "loss": 2.9894,
1224
- "step": 1000
1225
- },
1226
- {
1227
- "epoch": 3.06,
1228
- "learning_rate": 1.382993363478614e-06,
1229
- "loss": 2.8537,
1230
- "step": 1005
1231
- },
1232
- {
1233
- "epoch": 3.08,
1234
- "learning_rate": 2.116154171494932e-06,
1235
- "loss": 2.9448,
1236
- "step": 1010
1237
- },
1238
- {
1239
- "epoch": 3.09,
1240
- "learning_rate": 3.001764195602037e-06,
1241
- "loss": 2.8933,
1242
- "step": 1015
1243
- },
1244
- {
1245
- "epoch": 3.11,
1246
- "learning_rate": 4.037792708602087e-06,
1247
- "loss": 2.7567,
1248
- "step": 1020
1249
- },
1250
- {
1251
- "epoch": 3.12,
1252
- "learning_rate": 5.22186406972573e-06,
1253
- "loss": 2.8581,
1254
- "step": 1025
1255
- },
1256
- {
1257
- "epoch": 3.14,
1258
- "learning_rate": 6.55126317203911e-06,
1259
- "loss": 3.0563,
1260
- "step": 1030
1261
- },
1262
- {
1263
- "epoch": 3.16,
1264
- "learning_rate": 8.022941668255849e-06,
1265
- "loss": 3.1461,
1266
- "step": 1035
1267
- },
1268
- {
1269
- "epoch": 3.17,
1270
- "learning_rate": 9.633524960678029e-06,
1271
- "loss": 2.7869,
1272
- "step": 1040
1273
- },
1274
- {
1275
- "epoch": 3.19,
1276
- "learning_rate": 1.1379319939237678e-05,
1277
- "loss": 2.9909,
1278
- "step": 1045
1279
- },
1280
- {
1281
- "epoch": 3.2,
1282
- "learning_rate": 1.3256323449896148e-05,
1283
- "loss": 2.7969,
1284
- "step": 1050
1285
- },
1286
- {
1287
- "epoch": 3.22,
1288
- "learning_rate": 1.526023147398194e-05,
1289
- "loss": 3.0613,
1290
- "step": 1055
1291
- },
1292
- {
1293
- "epoch": 3.23,
1294
- "learning_rate": 1.7386448997419335e-05,
1295
- "loss": 2.9952,
1296
- "step": 1060
1297
- },
1298
- {
1299
- "epoch": 3.25,
1300
- "learning_rate": 1.9630100547217162e-05,
1301
- "loss": 2.8488,
1302
- "step": 1065
1303
- },
1304
- {
1305
- "epoch": 3.26,
1306
- "learning_rate": 2.198604137105723e-05,
1307
- "loss": 2.9286,
1308
- "step": 1070
1309
- },
1310
- {
1311
- "epoch": 3.28,
1312
- "learning_rate": 2.444886923434745e-05,
1313
- "loss": 2.9456,
1314
- "step": 1075
1315
- },
1316
- {
1317
- "epoch": 3.29,
1318
- "learning_rate": 2.7012936807688628e-05,
1319
- "loss": 2.9093,
1320
- "step": 1080
1321
- },
1322
- {
1323
- "epoch": 3.31,
1324
- "learning_rate": 2.9672364616349706e-05,
1325
- "loss": 2.6638,
1326
- "step": 1085
1327
- },
1328
- {
1329
- "epoch": 3.32,
1330
- "learning_rate": 3.242105452205932e-05,
1331
- "loss": 2.8781,
1332
- "step": 1090
1333
- },
1334
- {
1335
- "epoch": 3.34,
1336
- "learning_rate": 3.5252703706197704e-05,
1337
- "loss": 2.8149,
1338
- "step": 1095
1339
- },
1340
- {
1341
- "epoch": 3.35,
1342
- "learning_rate": 3.816081912232647e-05,
1343
- "loss": 2.9128,
1344
- "step": 1100
1345
- },
1346
- {
1347
- "epoch": 3.37,
1348
- "learning_rate": 4.113873238491593e-05,
1349
- "loss": 2.9003,
1350
- "step": 1105
1351
- },
1352
- {
1353
- "epoch": 3.38,
1354
- "learning_rate": 4.4179615060128864e-05,
1355
- "loss": 3.0516,
1356
- "step": 1110
1357
- },
1358
- {
1359
- "epoch": 3.4,
1360
- "learning_rate": 4.727649432360055e-05,
1361
- "loss": 2.9956,
1362
- "step": 1115
1363
- },
1364
- {
1365
- "epoch": 3.41,
1366
- "learning_rate": 5.042226894930894e-05,
1367
- "loss": 2.9518,
1368
- "step": 1120
1369
- },
1370
- {
1371
- "epoch": 3.43,
1372
- "learning_rate": 5.3609725592873736e-05,
1373
- "loss": 3.0925,
1374
- "step": 1125
1375
- },
1376
- {
1377
- "epoch": 3.45,
1378
- "learning_rate": 5.68315553319459e-05,
1379
- "loss": 2.9208,
1380
- "step": 1130
1381
- },
1382
- {
1383
- "epoch": 3.46,
1384
- "learning_rate": 6.00803704257593e-05,
1385
- "loss": 2.9595,
1386
- "step": 1135
1387
- },
1388
- {
1389
- "epoch": 3.48,
1390
- "learning_rate": 6.334872125541636e-05,
1391
- "loss": 2.7912,
1392
- "step": 1140
1393
- },
1394
- {
1395
- "epoch": 3.49,
1396
- "learning_rate": 6.662911340606064e-05,
1397
- "loss": 3.1123,
1398
- "step": 1145
1399
- },
1400
- {
1401
- "epoch": 3.51,
1402
- "learning_rate": 6.991402485176834e-05,
1403
- "loss": 3.0401,
1404
- "step": 1150
1405
- },
1406
- {
1407
- "epoch": 3.52,
1408
- "learning_rate": 7.319592320375272e-05,
1409
- "loss": 3.007,
1410
- "step": 1155
1411
- },
1412
- {
1413
- "epoch": 3.54,
1414
- "learning_rate": 7.646728298233026e-05,
1415
- "loss": 3.0709,
1416
- "step": 1160
1417
- },
1418
- {
1419
- "epoch": 3.55,
1420
- "learning_rate": 7.97206028730452e-05,
1421
- "loss": 2.8136,
1422
- "step": 1165
1423
- },
1424
- {
1425
- "epoch": 3.57,
1426
- "learning_rate": 8.294842292738145e-05,
1427
- "loss": 3.0615,
1428
- "step": 1170
1429
- },
1430
- {
1431
- "epoch": 3.58,
1432
- "learning_rate": 8.6143341668622e-05,
1433
- "loss": 2.8914,
1434
- "step": 1175
1435
- },
1436
- {
1437
- "epoch": 3.6,
1438
- "learning_rate": 8.92980330636302e-05,
1439
- "loss": 3.0546,
1440
- "step": 1180
1441
- },
1442
- {
1443
- "epoch": 3.61,
1444
- "learning_rate": 9.240526332163816e-05,
1445
- "loss": 2.7764,
1446
- "step": 1185
1447
- },
1448
- {
1449
- "epoch": 3.63,
1450
- "learning_rate": 9.545790748151966e-05,
1451
- "loss": 2.9967,
1452
- "step": 1190
1453
- },
1454
- {
1455
- "epoch": 3.64,
1456
- "learning_rate": 9.844896574951464e-05,
1457
- "loss": 2.8943,
1458
- "step": 1195
1459
- },
1460
- {
1461
- "epoch": 3.66,
1462
- "learning_rate": 0.00010137157954994128,
1463
- "loss": 2.7756,
1464
- "step": 1200
1465
- },
1466
- {
1467
- "epoch": 3.67,
1468
- "learning_rate": 0.00010421904725209109,
1469
- "loss": 2.6902,
1470
- "step": 1205
1471
- },
1472
- {
1473
- "epoch": 3.69,
1474
- "learning_rate": 0.0001069848395372458,
1475
- "loss": 3.0339,
1476
- "step": 1210
1477
- },
1478
- {
1479
- "epoch": 3.7,
1480
- "learning_rate": 0.00010966261437057745,
1481
- "loss": 2.9684,
1482
- "step": 1215
1483
- },
1484
- {
1485
- "epoch": 3.72,
1486
- "learning_rate": 0.00011224623154360197,
1487
- "loss": 2.993,
1488
- "step": 1220
1489
- },
1490
- {
1491
- "epoch": 3.73,
1492
- "learning_rate": 0.0001147297667538396,
1493
- "loss": 2.8925,
1494
- "step": 1225
1495
- },
1496
- {
1497
- "epoch": 3.75,
1498
- "learning_rate": 0.0001171075251893971,
1499
- "loss": 3.0326,
1500
- "step": 1230
1501
- },
1502
- {
1503
- "epoch": 3.77,
1504
- "learning_rate": 0.00011937405458732195,
1505
- "loss": 3.1186,
1506
- "step": 1235
1507
- },
1508
- {
1509
- "epoch": 3.78,
1510
- "learning_rate": 0.00012152415773578527,
1511
- "loss": 2.9294,
1512
- "step": 1240
1513
- },
1514
- {
1515
- "epoch": 3.8,
1516
- "learning_rate": 0.00012355290439142633,
1517
- "loss": 3.0367,
1518
- "step": 1245
1519
- },
1520
- {
1521
- "epoch": 3.81,
1522
- "learning_rate": 0.0001254556425845306,
1523
- "loss": 2.6842,
1524
- "step": 1250
1525
- },
1526
- {
1527
- "epoch": 3.83,
1528
- "learning_rate": 0.00012722800928611938,
1529
- "loss": 2.807,
1530
- "step": 1255
1531
- },
1532
- {
1533
- "epoch": 3.84,
1534
- "learning_rate": 0.0001288659404124906,
1535
- "loss": 2.874,
1536
- "step": 1260
1537
- },
1538
- {
1539
- "epoch": 3.86,
1540
- "learning_rate": 0.00013036568014427024,
1541
- "loss": 2.9999,
1542
- "step": 1265
1543
- },
1544
- {
1545
- "epoch": 3.87,
1546
- "learning_rate": 0.00013172378953860524,
1547
- "loss": 3.0116,
1548
- "step": 1270
1549
- },
1550
- {
1551
- "epoch": 3.89,
1552
- "learning_rate": 0.00013293715441475062,
1553
- "loss": 3.1574,
1554
- "step": 1275
1555
- },
1556
- {
1557
- "epoch": 3.9,
1558
- "learning_rate": 0.00013400299249496822,
1559
- "loss": 2.6983,
1560
- "step": 1280
1561
- },
1562
- {
1563
- "epoch": 3.92,
1564
- "learning_rate": 0.0001349188597843629,
1565
- "loss": 2.8115,
1566
- "step": 1285
1567
- },
1568
- {
1569
- "epoch": 3.93,
1570
- "learning_rate": 0.00013568265617502779,
1571
- "loss": 2.7446,
1572
- "step": 1290
1573
- },
1574
- {
1575
- "epoch": 3.95,
1576
- "learning_rate": 0.0001362926302616468,
1577
- "loss": 2.8728,
1578
- "step": 1295
1579
- },
1580
- {
1581
- "epoch": 3.96,
1582
- "learning_rate": 0.0001367473833575137,
1583
- "loss": 3.134,
1584
- "step": 1300
1585
- },
1586
- {
1587
- "epoch": 3.98,
1588
- "learning_rate": 0.0001370458727017576,
1589
- "loss": 2.8436,
1590
- "step": 1305
1591
- },
1592
- {
1593
- "epoch": 3.99,
1594
- "learning_rate": 0.0001371874138504211,
1595
- "loss": 2.901,
1596
- "step": 1310
1597
- },
1598
- {
1599
- "epoch": 4.0,
1600
- "eval_loss": 3.0180249214172363,
1601
- "eval_runtime": 3.2449,
1602
- "eval_samples_per_second": 143.301,
1603
- "eval_steps_per_second": 18.182,
1604
- "step": 1312
1605
- },
1606
- {
1607
- "epoch": 4.01,
1608
- "learning_rate": 0.0001371716822459084,
1609
- "loss": 2.7412,
1610
- "step": 1315
1611
- },
1612
- {
1613
- "epoch": 4.02,
1614
- "learning_rate": 0.00013699871396120457,
1615
- "loss": 2.5891,
1616
- "step": 1320
1617
- },
1618
- {
1619
- "epoch": 4.04,
1620
- "learning_rate": 0.00013666890561715917,
1621
- "loss": 3.1228,
1622
- "step": 1325
1623
- },
1624
- {
1625
- "epoch": 4.05,
1626
- "learning_rate": 0.00013618301347302405,
1627
- "loss": 2.9228,
1628
- "step": 1330
1629
- },
1630
- {
1631
- "epoch": 4.07,
1632
- "learning_rate": 0.000135542151692331,
1633
- "loss": 2.6346,
1634
- "step": 1335
1635
- },
1636
- {
1637
- "epoch": 4.09,
1638
- "learning_rate": 0.0001347477897880855,
1639
- "loss": 2.7065,
1640
- "step": 1340
1641
- },
1642
- {
1643
- "epoch": 4.1,
1644
- "learning_rate": 0.00013380174925313403,
1645
- "loss": 2.7945,
1646
- "step": 1345
1647
- },
1648
- {
1649
- "epoch": 4.12,
1650
- "learning_rate": 0.00013270619938343336,
1651
- "loss": 2.5638,
1652
- "step": 1350
1653
- },
1654
- {
1655
- "epoch": 4.13,
1656
- "learning_rate": 0.00013146365230379744,
1657
- "loss": 2.8108,
1658
- "step": 1355
1659
- },
1660
- {
1661
- "epoch": 4.15,
1662
- "learning_rate": 0.0001300769572075284,
1663
- "loss": 2.8114,
1664
- "step": 1360
1665
- },
1666
- {
1667
- "epoch": 4.16,
1668
- "learning_rate": 0.00012854929382314167,
1669
- "loss": 2.7208,
1670
- "step": 1365
1671
- },
1672
- {
1673
- "epoch": 4.18,
1674
- "learning_rate": 0.0001268841651231636,
1675
- "loss": 2.8124,
1676
- "step": 1370
1677
- },
1678
- {
1679
- "epoch": 4.19,
1680
- "learning_rate": 0.00012508538929172376,
1681
- "loss": 2.9135,
1682
- "step": 1375
1683
- },
1684
- {
1685
- "epoch": 4.21,
1686
- "learning_rate": 0.0001231570909693571,
1687
- "loss": 2.5881,
1688
- "step": 1380
1689
- },
1690
- {
1691
- "epoch": 4.22,
1692
- "learning_rate": 0.00012110369179509431,
1693
- "loss": 2.6689,
1694
- "step": 1385
1695
- },
1696
- {
1697
- "epoch": 4.24,
1698
- "learning_rate": 0.00011892990026752702,
1699
- "loss": 2.8313,
1700
- "step": 1390
1701
- },
1702
- {
1703
- "epoch": 4.25,
1704
- "learning_rate": 0.0001166407009480955,
1705
- "loss": 2.9475,
1706
- "step": 1395
1707
- },
1708
- {
1709
- "epoch": 4.27,
1710
- "learning_rate": 0.0001142413430313578,
1711
- "loss": 3.0502,
1712
- "step": 1400
1713
- },
1714
- {
1715
- "epoch": 4.28,
1716
- "learning_rate": 0.00011173732830844787,
1717
- "loss": 2.6531,
1718
- "step": 1405
1719
- },
1720
- {
1721
- "epoch": 4.3,
1722
- "learning_rate": 0.00010913439855132291,
1723
- "loss": 2.9528,
1724
- "step": 1410
1725
- },
1726
- {
1727
- "epoch": 4.31,
1728
- "learning_rate": 0.00010643852234672852,
1729
- "loss": 2.7701,
1730
- "step": 1415
1731
- },
1732
- {
1733
- "epoch": 4.33,
1734
- "learning_rate": 0.00010365588141007188,
1735
- "loss": 2.6251,
1736
- "step": 1420
1737
- },
1738
- {
1739
- "epoch": 4.34,
1740
- "learning_rate": 0.00010079285641058387,
1741
- "loss": 2.9979,
1742
- "step": 1425
1743
- },
1744
- {
1745
- "epoch": 4.36,
1746
- "learning_rate": 9.785601234027734e-05,
1747
- "loss": 2.807,
1748
- "step": 1430
1749
- },
1750
- {
1751
- "epoch": 4.38,
1752
- "learning_rate": 9.485208346024522e-05,
1753
- "loss": 2.8977,
1754
- "step": 1435
1755
- },
1756
- {
1757
- "epoch": 4.39,
1758
- "learning_rate": 9.178795785882326e-05,
1759
- "loss": 2.8219,
1760
- "step": 1440
1761
- },
1762
- {
1763
- "epoch": 4.41,
1764
- "learning_rate": 8.867066165702077e-05,
1765
- "loss": 2.6527,
1766
- "step": 1445
1767
- },
1768
- {
1769
- "epoch": 4.42,
1770
- "learning_rate": 8.550734289743871e-05,
1771
- "loss": 2.8599,
1772
- "step": 1450
1773
- },
1774
- {
1775
- "epoch": 4.44,
1776
- "learning_rate": 8.230525515362062e-05,
1777
- "loss": 2.9224,
1778
- "step": 1455
1779
- },
1780
- {
1781
- "epoch": 4.45,
1782
- "learning_rate": 7.907174089741485e-05,
1783
- "loss": 2.6402,
1784
- "step": 1460
1785
- },
1786
- {
1787
- "epoch": 4.47,
1788
- "learning_rate": 7.581421466249422e-05,
1789
- "loss": 2.658,
1790
- "step": 1465
1791
- },
1792
- {
1793
- "epoch": 4.48,
1794
- "learning_rate": 7.254014604263352e-05,
1795
- "loss": 2.6781,
1796
- "step": 1470
1797
- },
1798
- {
1799
- "epoch": 4.5,
1800
- "learning_rate": 6.92570425637328e-05,
1801
- "loss": 2.8161,
1802
- "step": 1475
1803
- },
1804
- {
1805
- "epoch": 4.51,
1806
- "learning_rate": 6.597243246886372e-05,
1807
- "loss": 2.7003,
1808
- "step": 1480
1809
- },
1810
- {
1811
- "epoch": 4.53,
1812
- "learning_rate": 6.269384745580722e-05,
1813
- "loss": 2.6335,
1814
- "step": 1485
1815
- },
1816
- {
1817
- "epoch": 4.54,
1818
- "learning_rate": 5.942880540667308e-05,
1819
- "loss": 2.9172,
1820
- "step": 1490
1821
- },
1822
- {
1823
- "epoch": 4.56,
1824
- "learning_rate": 5.618479314919675e-05,
1825
- "loss": 2.6901,
1826
- "step": 1495
1827
- },
1828
- {
1829
- "epoch": 4.57,
1830
- "learning_rate": 5.2969249289244765e-05,
1831
- "loss": 3.0955,
1832
- "step": 1500
1833
- },
1834
- {
1835
- "epoch": 4.59,
1836
- "learning_rate": 4.978954715389626e-05,
1837
- "loss": 2.8052,
1838
- "step": 1505
1839
- },
1840
- {
1841
- "epoch": 4.6,
1842
- "learning_rate": 4.6652977884208274e-05,
1843
- "loss": 2.5181,
1844
- "step": 1510
1845
- },
1846
- {
1847
- "epoch": 4.62,
1848
- "learning_rate": 4.356673371643594e-05,
1849
- "loss": 2.8346,
1850
- "step": 1515
1851
- },
1852
- {
1853
- "epoch": 4.63,
1854
- "learning_rate": 4.0537891490046174e-05,
1855
- "loss": 2.9267,
1856
- "step": 1520
1857
- },
1858
- {
1859
- "epoch": 4.65,
1860
- "learning_rate": 3.757339642033588e-05,
1861
- "loss": 2.6995,
1862
- "step": 1525
1863
- },
1864
- {
1865
- "epoch": 4.66,
1866
- "learning_rate": 3.468004617287139e-05,
1867
- "loss": 2.8038,
1868
- "step": 1530
1869
- },
1870
- {
1871
- "epoch": 4.68,
1872
- "learning_rate": 3.1864475276260315e-05,
1873
- "loss": 2.7572,
1874
- "step": 1535
1875
- },
1876
- {
1877
- "epoch": 4.7,
1878
- "learning_rate": 2.9133139909002586e-05,
1879
- "loss": 2.8888,
1880
- "step": 1540
1881
- },
1882
- {
1883
- "epoch": 4.71,
1884
- "learning_rate": 2.6492303095302796e-05,
1885
- "loss": 2.5902,
1886
- "step": 1545
1887
- },
1888
- {
1889
- "epoch": 4.73,
1890
- "learning_rate": 2.3948020343789084e-05,
1891
- "loss": 2.6841,
1892
- "step": 1550
1893
- },
1894
- {
1895
- "epoch": 4.74,
1896
- "learning_rate": 2.1506125762073123e-05,
1897
- "loss": 2.6346,
1898
- "step": 1555
1899
- },
1900
- {
1901
- "epoch": 4.76,
1902
- "learning_rate": 1.917221867898604e-05,
1903
- "loss": 2.574,
1904
- "step": 1560
1905
- },
1906
- {
1907
- "epoch": 4.77,
1908
- "learning_rate": 1.695165080516989e-05,
1909
- "loss": 2.742,
1910
- "step": 1565
1911
- },
1912
- {
1913
- "epoch": 4.79,
1914
- "learning_rate": 1.4849513961463578e-05,
1915
- "loss": 2.8388,
1916
- "step": 1570
1917
- },
1918
- {
1919
- "epoch": 4.8,
1920
- "learning_rate": 1.2870628403223036e-05,
1921
- "loss": 2.6697,
1922
- "step": 1575
1923
- },
1924
- {
1925
- "epoch": 4.82,
1926
- "learning_rate": 1.101953176734824e-05,
1927
- "loss": 2.7003,
1928
- "step": 1580
1929
- },
1930
- {
1931
- "epoch": 4.83,
1932
- "learning_rate": 9.30046866736211e-06,
1933
- "loss": 3.0252,
1934
- "step": 1585
1935
- },
1936
- {
1937
- "epoch": 4.85,
1938
- "learning_rate": 7.717380960398831e-06,
1939
- "loss": 2.8193,
1940
- "step": 1590
1941
- },
1942
- {
1943
- "epoch": 4.86,
1944
- "learning_rate": 6.273898708422032e-06,
1945
- "loss": 2.895,
1946
- "step": 1595
1947
- },
1948
- {
1949
- "epoch": 4.88,
1950
- "learning_rate": 4.9733318543963394e-06,
1951
- "loss": 2.7687,
1952
- "step": 1600
1953
- },
1954
- {
1955
- "epoch": 4.89,
1956
- "learning_rate": 3.818662632500395e-06,
1957
- "loss": 2.7358,
1958
- "step": 1605
1959
- },
1960
- {
1961
- "epoch": 4.91,
1962
- "learning_rate": 2.812538729785672e-06,
1963
- "loss": 2.7698,
1964
- "step": 1610
1965
- },
1966
- {
1967
- "epoch": 4.92,
1968
- "learning_rate": 1.9572672149594433e-06,
1969
- "loss": 2.7906,
1970
- "step": 1615
1971
- },
1972
- {
1973
- "epoch": 4.94,
1974
- "learning_rate": 1.2548092482157443e-06,
1975
- "loss": 2.6523,
1976
- "step": 1620
1977
- },
1978
- {
1979
- "epoch": 4.95,
1980
- "learning_rate": 7.067755842429393e-07,
1981
- "loss": 2.7697,
1982
- "step": 1625
1983
- },
1984
- {
1985
- "epoch": 4.97,
1986
- "learning_rate": 3.144228787205802e-07,
1987
- "loss": 2.7642,
1988
- "step": 1630
1989
- },
1990
- {
1991
- "epoch": 4.98,
1992
- "learning_rate": 7.865080677495002e-08,
1993
- "loss": 2.6786,
1994
- "step": 1635
1995
- },
1996
- {
1997
- "epoch": 5.0,
1998
- "learning_rate": 0.0,
1999
- "loss": 2.8629,
2000
- "step": 1640
2001
- },
2002
- {
2003
- "epoch": 5.0,
2004
- "eval_loss": 2.985200881958008,
2005
- "eval_runtime": 3.2565,
2006
- "eval_samples_per_second": 142.792,
2007
- "eval_steps_per_second": 18.118,
2008
- "step": 1640
2009
- },
2010
- {
2011
- "epoch": 4.69,
2012
- "learning_rate": 3.064756856761554e-05,
2013
- "loss": 2.7681,
2014
- "step": 1645
2015
- },
2016
- {
2017
- "epoch": 4.7,
2018
- "learning_rate": 2.8129056814413798e-05,
2019
- "loss": 2.7734,
2020
- "step": 1650
2021
- },
2022
- {
2023
- "epoch": 4.72,
2024
- "learning_rate": 2.5691584488661662e-05,
2025
- "loss": 2.8042,
2026
- "step": 1655
2027
- },
2028
- {
2029
- "epoch": 4.73,
2030
- "learning_rate": 2.3340032409686368e-05,
2031
- "loss": 2.8781,
2032
- "step": 1660
2033
- },
2034
- {
2035
- "epoch": 4.74,
2036
- "learning_rate": 2.1079109349241507e-05,
2037
- "loss": 2.8162,
2038
- "step": 1665
2039
- },
2040
- {
2041
- "epoch": 4.76,
2042
- "learning_rate": 1.891334260261341e-05,
2043
- "loss": 2.523,
2044
- "step": 1670
2045
- },
2046
- {
2047
- "epoch": 4.77,
2048
- "learning_rate": 1.6847068923119758e-05,
2049
- "loss": 2.8495,
2050
- "step": 1675
2051
- },
2052
- {
2053
- "epoch": 4.79,
2054
- "learning_rate": 1.4884425838151134e-05,
2055
- "loss": 2.791,
2056
- "step": 1680
2057
- },
2058
- {
2059
- "epoch": 4.8,
2060
- "learning_rate": 1.3029343364143164e-05,
2061
- "loss": 2.6161,
2062
- "step": 1685
2063
- },
2064
- {
2065
- "epoch": 4.81,
2066
- "learning_rate": 1.1285536137072603e-05,
2067
- "loss": 2.8099,
2068
- "step": 1690
2069
- },
2070
- {
2071
- "epoch": 4.83,
2072
- "learning_rate": 9.65649597423201e-06,
2073
- "loss": 2.9416,
2074
- "step": 1695
2075
- },
2076
- {
2077
- "epoch": 4.84,
2078
- "learning_rate": 8.145484882179486e-06,
2079
- "loss": 2.881,
2080
- "step": 1700
2081
- },
2082
- {
2083
- "epoch": 4.86,
2084
- "learning_rate": 6.755528524864052e-06,
2085
- "loss": 2.4485,
2086
- "step": 1705
2087
- },
2088
- {
2089
- "epoch": 4.87,
2090
- "learning_rate": 5.4894101650047195e-06,
2091
- "loss": 2.7043,
2092
- "step": 1710
2093
- },
2094
- {
2095
- "epoch": 4.89,
2096
- "learning_rate": 4.349665090857373e-06,
2097
- "loss": 2.9465,
2098
- "step": 1715
2099
- },
2100
- {
2101
- "epoch": 4.9,
2102
- "learning_rate": 3.3385755395280496e-06,
2103
- "loss": 2.8094,
2104
- "step": 1720
2105
- },
2106
- {
2107
- "epoch": 4.91,
2108
- "learning_rate": 2.4581661269975954e-06,
2109
- "loss": 2.8454,
2110
- "step": 1725
2111
- },
2112
- {
2113
- "epoch": 4.93,
2114
- "learning_rate": 1.7101997940107123e-06,
2115
- "loss": 2.717,
2116
- "step": 1730
2117
- },
2118
- {
2119
- "epoch": 4.94,
2120
- "learning_rate": 1.0961742759449984e-06,
2121
- "loss": 2.6812,
2122
- "step": 1735
2123
- },
2124
- {
2125
- "epoch": 4.96,
2126
- "learning_rate": 6.173191037306866e-07,
2127
- "loss": 2.7196,
2128
- "step": 1740
2129
- },
2130
- {
2131
- "epoch": 4.97,
2132
- "learning_rate": 2.7459314182545106e-07,
2133
- "loss": 2.8512,
2134
- "step": 1745
2135
- },
2136
- {
2137
- "epoch": 4.99,
2138
- "learning_rate": 6.868266817434572e-08,
2139
- "loss": 2.8381,
2140
- "step": 1750
2141
- },
2142
- {
2143
- "epoch": 5.0,
2144
- "learning_rate": 0.0,
2145
- "loss": 2.7245,
2146
- "step": 1755
2147
- },
2148
- {
2149
- "epoch": 5.0,
2150
- "eval_loss": 2.6586830615997314,
2151
- "eval_runtime": 12.7857,
2152
- "eval_samples_per_second": 43.33,
2153
- "eval_steps_per_second": 5.475,
2154
- "step": 1755
2155
  }
2156
  ],
2157
- "max_steps": 2106,
2158
- "num_train_epochs": 6,
2159
- "total_flos": 1831003914240000.0,
2160
  "trial_name": null,
2161
  "trial_params": null
2162
  }
 
1
  {
2
+ "best_metric": 2.7749314308166504,
3
+ "best_model_checkpoint": "output/drake/checkpoint-351",
4
+ "epoch": 1.0,
5
+ "global_step": 351,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 0.01,
12
+ "learning_rate": 0.00013713131733182566,
13
+ "loss": 2.8146,
14
  "step": 5
15
  },
16
  {
17
  "epoch": 0.03,
18
+ "learning_rate": 0.00013692540685817455,
19
+ "loss": 2.4938,
20
  "step": 10
21
  },
22
  {
23
  "epoch": 0.04,
24
+ "learning_rate": 0.00013658268089626935,
25
+ "loss": 2.6848,
26
  "step": 15
27
  },
28
  {
29
+ "epoch": 0.06,
30
+ "learning_rate": 0.000136103825724055,
31
+ "loss": 2.4887,
32
  "step": 20
33
  },
34
  {
35
+ "epoch": 0.07,
36
+ "learning_rate": 0.0001354898002059893,
37
+ "loss": 2.586,
38
  "step": 25
39
  },
40
  {
41
+ "epoch": 0.09,
42
+ "learning_rate": 0.00013474183387300238,
43
+ "loss": 2.4906,
44
  "step": 30
45
  },
46
  {
47
+ "epoch": 0.1,
48
+ "learning_rate": 0.00013386142446047196,
49
+ "loss": 2.4834,
50
  "step": 35
51
  },
52
  {
53
+ "epoch": 0.11,
54
+ "learning_rate": 0.00013285033490914263,
55
+ "loss": 2.6758,
56
  "step": 40
57
  },
58
  {
59
+ "epoch": 0.13,
60
+ "learning_rate": 0.00013171058983499532,
61
+ "loss": 2.4307,
62
  "step": 45
63
  },
64
  {
65
+ "epoch": 0.14,
66
+ "learning_rate": 0.00013044447147513605,
67
+ "loss": 2.8348,
68
  "step": 50
69
  },
70
  {
71
+ "epoch": 0.16,
72
+ "learning_rate": 0.00012905451511782055,
73
+ "loss": 2.7339,
74
  "step": 55
75
  },
76
  {
77
+ "epoch": 0.17,
78
+ "learning_rate": 0.0001275435040257681,
79
+ "loss": 2.4359,
80
  "step": 60
81
  },
82
  {
83
+ "epoch": 0.19,
84
+ "learning_rate": 0.00012591446386292745,
85
+ "loss": 2.7405,
86
  "step": 65
87
  },
88
  {
89
+ "epoch": 0.2,
90
+ "learning_rate": 0.00012417065663585696,
91
+ "loss": 2.5262,
92
  "step": 70
93
  },
94
  {
95
+ "epoch": 0.21,
96
+ "learning_rate": 0.00012231557416184885,
97
+ "loss": 2.5211,
98
  "step": 75
99
  },
100
  {
101
+ "epoch": 0.23,
102
+ "learning_rate": 0.0001203529310768803,
103
+ "loss": 2.4883,
104
  "step": 80
105
  },
106
  {
107
+ "epoch": 0.24,
108
+ "learning_rate": 0.00011828665739738674,
109
+ "loss": 2.6898,
110
  "step": 85
111
  },
112
  {
113
+ "epoch": 0.26,
114
+ "learning_rate": 0.00011612089065075855,
115
+ "loss": 2.5956,
116
  "step": 90
117
  },
118
  {
119
+ "epoch": 0.27,
120
+ "learning_rate": 0.0001138599675903136,
121
+ "loss": 2.4562,
122
  "step": 95
123
  },
124
  {
125
+ "epoch": 0.28,
126
+ "learning_rate": 0.00011150841551133841,
127
+ "loss": 2.457,
128
  "step": 100
129
  },
130
  {
131
+ "epoch": 0.3,
132
+ "learning_rate": 0.00010907094318558638,
133
+ "loss": 2.6934,
134
  "step": 105
135
  },
136
  {
137
+ "epoch": 0.31,
138
+ "learning_rate": 0.00010655243143238444,
139
+ "loss": 2.6493,
140
  "step": 110
141
  },
142
  {
143
+ "epoch": 0.33,
144
+ "learning_rate": 0.00010395792334523303,
145
+ "loss": 2.5976,
146
  "step": 115
147
  },
148
  {
149
+ "epoch": 0.34,
150
+ "learning_rate": 0.00010129261419346177,
151
+ "loss": 2.7521,
152
  "step": 120
153
  },
154
  {
155
+ "epoch": 0.36,
156
+ "learning_rate": 9.856184101917151e-05,
157
+ "loss": 2.5228,
158
  "step": 125
159
  },
160
  {
161
+ "epoch": 0.37,
162
+ "learning_rate": 9.577107195028614e-05,
163
+ "loss": 2.555,
164
  "step": 130
165
  },
166
  {
167
+ "epoch": 0.38,
168
+ "learning_rate": 9.292589525111789e-05,
169
+ "loss": 2.6695,
170
  "step": 135
171
  },
172
  {
173
+ "epoch": 0.4,
174
+ "learning_rate": 9.003200813237038e-05,
175
+ "loss": 2.5893,
176
  "step": 140
177
  },
178
  {
179
+ "epoch": 0.41,
180
+ "learning_rate": 8.709520534298517e-05,
181
+ "loss": 2.4968,
182
  "step": 145
183
  },
184
  {
185
+ "epoch": 0.43,
186
+ "learning_rate": 8.4121367566679e-05,
187
+ "loss": 2.6097,
188
  "step": 150
189
  },
190
  {
191
+ "epoch": 0.44,
192
+ "learning_rate": 8.111644964640216e-05,
193
+ "loss": 2.4365,
194
  "step": 155
195
  },
196
  {
197
+ "epoch": 0.46,
198
+ "learning_rate": 7.808646866030093e-05,
199
+ "loss": 2.6697,
200
  "step": 160
201
  },
202
  {
203
+ "epoch": 0.47,
204
+ "learning_rate": 7.503749187305804e-05,
205
+ "loss": 2.5317,
206
  "step": 165
207
  },
208
  {
209
+ "epoch": 0.48,
210
+ "learning_rate": 7.197562458674299e-05,
211
+ "loss": 2.6247,
212
  "step": 170
213
  },
214
  {
215
+ "epoch": 0.5,
216
+ "learning_rate": 6.890699791548972e-05,
217
+ "loss": 2.4144,
218
  "step": 175
219
  },
220
  {
221
+ "epoch": 0.51,
222
+ "learning_rate": 6.583775650849418e-05,
223
+ "loss": 2.6802,
224
  "step": 180
225
  },
226
  {
227
+ "epoch": 0.53,
228
+ "learning_rate": 6.277404624590518e-05,
229
+ "loss": 2.7703,
230
  "step": 185
231
  },
232
  {
233
+ "epoch": 0.54,
234
+ "learning_rate": 5.9722001932251785e-05,
235
+ "loss": 2.8038,
236
  "step": 190
237
  },
238
  {
239
+ "epoch": 0.56,
240
+ "learning_rate": 5.6687735012048764e-05,
241
+ "loss": 2.5009,
242
  "step": 195
243
  },
244
  {
245
+ "epoch": 0.57,
246
+ "learning_rate": 5.3677321332176824e-05,
247
+ "loss": 2.7397,
248
  "step": 200
249
  },
250
  {
251
+ "epoch": 0.58,
252
+ "learning_rate": 5.069678897554777e-05,
253
+ "loss": 2.2651,
254
  "step": 205
255
  },
256
  {
257
+ "epoch": 0.6,
258
+ "learning_rate": 4.775210619040673e-05,
259
+ "loss": 2.6494,
260
  "step": 210
261
  },
262
  {
263
+ "epoch": 0.61,
264
+ "learning_rate": 4.4849169439453994e-05,
265
+ "loss": 2.4319,
266
  "step": 215
267
  },
268
  {
269
+ "epoch": 0.63,
270
+ "learning_rate": 4.199379159270695e-05,
271
+ "loss": 2.5083,
272
  "step": 220
273
  },
274
  {
275
+ "epoch": 0.64,
276
+ "learning_rate": 3.919169028775044e-05,
277
+ "loss": 2.4238,
278
  "step": 225
279
  },
280
  {
281
+ "epoch": 0.66,
282
+ "learning_rate": 3.6448476480681456e-05,
283
+ "loss": 2.7361,
284
  "step": 230
285
  },
286
  {
287
+ "epoch": 0.67,
288
+ "learning_rate": 3.3769643210672815e-05,
289
+ "loss": 2.3582,
290
  "step": 235
291
  },
292
  {
293
+ "epoch": 0.68,
294
+ "learning_rate": 3.1160554600657045e-05,
295
+ "loss": 2.5586,
296
  "step": 240
297
  },
298
  {
299
+ "epoch": 0.7,
300
+ "learning_rate": 2.862643511615132e-05,
301
+ "loss": 2.6506,
302
  "step": 245
303
  },
304
  {
305
+ "epoch": 0.71,
306
+ "learning_rate": 2.6172359103734907e-05,
307
+ "loss": 2.4642,
308
  "step": 250
309
  },
310
  {
311
+ "epoch": 0.73,
312
+ "learning_rate": 2.3803240630126026e-05,
313
+ "loss": 2.4471,
314
  "step": 255
315
  },
316
  {
317
+ "epoch": 0.74,
318
+ "learning_rate": 2.152382364220499e-05,
319
+ "loss": 2.3953,
320
  "step": 260
321
  },
322
  {
323
+ "epoch": 0.75,
324
+ "learning_rate": 1.9338672467686093e-05,
325
+ "loss": 2.5485,
326
  "step": 265
327
  },
328
  {
329
+ "epoch": 0.77,
330
+ "learning_rate": 1.725216267546251e-05,
331
+ "loss": 2.483,
332
  "step": 270
333
  },
334
  {
335
+ "epoch": 0.78,
336
+ "learning_rate": 1.5268472313922077e-05,
337
+ "loss": 2.8104,
338
  "step": 275
339
  },
340
  {
341
+ "epoch": 0.8,
342
+ "learning_rate": 1.3391573544780878e-05,
343
+ "loss": 2.4582,
344
  "step": 280
345
  },
346
  {
347
+ "epoch": 0.81,
348
+ "learning_rate": 1.1625224689186508e-05,
349
+ "loss": 2.698,
350
  "step": 285
351
  },
352
  {
353
+ "epoch": 0.83,
354
+ "learning_rate": 9.97296270201696e-06,
355
+ "loss": 2.3153,
356
  "step": 290
357
  },
358
  {
359
+ "epoch": 0.84,
360
+ "learning_rate": 8.438096089447732e-06,
361
+ "loss": 2.4751,
362
  "step": 295
363
  },
364
  {
365
+ "epoch": 0.85,
366
+ "learning_rate": 7.023698283963675e-06,
367
+ "loss": 2.7106,
368
  "step": 300
369
  },
370
  {
371
+ "epoch": 0.87,
372
+ "learning_rate": 5.73260149008795e-06,
373
+ "loss": 2.6915,
374
  "step": 305
375
  },
376
  {
377
+ "epoch": 0.88,
378
+ "learning_rate": 4.567391013146352e-06,
379
+ "loss": 2.8011,
380
  "step": 310
381
  },
382
  {
383
+ "epoch": 0.9,
384
+ "learning_rate": 3.530400082425805e-06,
385
+ "loss": 2.65,
386
  "step": 315
387
  },
388
  {
389
+ "epoch": 0.91,
390
+ "learning_rate": 2.623705179092382e-06,
391
+ "loss": 2.4158,
392
  "step": 320
393
  },
394
  {
395
+ "epoch": 0.93,
396
+ "learning_rate": 1.8491218782241098e-06,
397
+ "loss": 2.3891,
398
  "step": 325
399
  },
400
  {
401
+ "epoch": 0.94,
402
+ "learning_rate": 1.2082012132854124e-06,
403
+ "loss": 2.5672,
404
  "step": 330
405
  },
406
  {
407
+ "epoch": 0.95,
408
+ "learning_rate": 7.022265703216476e-07,
409
+ "loss": 2.5956,
410
  "step": 335
411
  },
412
  {
413
+ "epoch": 0.97,
414
+ "learning_rate": 3.322111180939607e-07,
415
+ "loss": 2.4543,
416
  "step": 340
417
  },
418
  {
419
+ "epoch": 0.98,
420
+ "learning_rate": 9.889577929986752e-08,
421
+ "loss": 2.6378,
422
  "step": 345
423
  },
424
  {
425
+ "epoch": 1.0,
426
+ "learning_rate": 2.7477469421299584e-09,
427
+ "loss": 2.6626,
428
  "step": 350
429
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
430
  {
431
  "epoch": 1.0,
432
+ "eval_loss": 2.7749314308166504,
433
+ "eval_runtime": 12.2562,
434
+ "eval_samples_per_second": 45.365,
435
+ "eval_steps_per_second": 5.711,
436
+ "step": 351