gokulsrinivasagan commited on
Commit
8b5a953
1 Parent(s): 39168cf

End of training

Browse files
README.md CHANGED
@@ -3,9 +3,23 @@ license: mit
3
  base_model: gokulsrinivasagan/gpt_60
4
  tags:
5
  - generated_from_trainer
 
 
 
 
6
  model-index:
7
  - name: gpt_72
8
- results: []
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
14
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/gokulsrinivasagan/huggingface/runs/5vor9923)
15
  # gpt_72
16
 
17
- This model is a fine-tuned version of [gokulsrinivasagan/gpt_60](https://huggingface.co/gokulsrinivasagan/gpt_60) on an unknown dataset.
 
 
 
18
 
19
  ## Model description
20
 
 
3
  base_model: gokulsrinivasagan/gpt_60
4
  tags:
5
  - generated_from_trainer
6
+ datasets:
7
+ - gokuls/wiki_book_corpus_complete_raw_dataset
8
+ metrics:
9
+ - accuracy
10
  model-index:
11
  - name: gpt_72
12
+ results:
13
+ - task:
14
+ name: Causal Language Modeling
15
+ type: text-generation
16
+ dataset:
17
+ name: gokuls/wiki_book_corpus_complete_raw_dataset
18
+ type: gokuls/wiki_book_corpus_complete_raw_dataset
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.37394662149990554
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
28
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/gokulsrinivasagan/huggingface/runs/5vor9923)
29
  # gpt_72
30
 
31
+ This model is a fine-tuned version of [gokulsrinivasagan/gpt_60](https://huggingface.co/gokulsrinivasagan/gpt_60) on the gokuls/wiki_book_corpus_complete_raw_dataset dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 3.1768
34
+ - Accuracy: 0.3739
35
 
36
  ## Model description
37
 
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.39222519170640535,
3
+ "eval_accuracy": 0.37394662149990554,
4
+ "eval_loss": 3.1767821311950684,
5
+ "eval_perplexity": 23.969498618731922,
6
+ "eval_runtime": 674.7606,
7
+ "eval_samples": 55176,
8
+ "eval_samples_per_second": 81.771,
9
+ "eval_steps_per_second": 1.704,
10
+ "total_flos": 1.1264989248576553e+18,
11
+ "train_loss": 3.1353410507916006,
12
+ "train_runtime": 46794.5499,
13
+ "train_samples": 5495866,
14
+ "train_samples_per_second": 11744.671,
15
+ "train_steps_per_second": 244.682
16
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.39222519170640535,
3
+ "eval_accuracy": 0.37394662149990554,
4
+ "eval_loss": 3.1767821311950684,
5
+ "eval_perplexity": 23.969498618731922,
6
+ "eval_runtime": 674.7606,
7
+ "eval_samples": 55176,
8
+ "eval_samples_per_second": 81.771,
9
+ "eval_steps_per_second": 1.704
10
+ }
logs/events.out.tfevents.1720245182.ki-g0010 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1925d0b3b5dae6310cba79d292b951b4393ddd22ac783adbee4151229640f687
3
+ size 40
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.39222519170640535,
3
+ "total_flos": 1.1264989248576553e+18,
4
+ "train_loss": 3.1353410507916006,
5
+ "train_runtime": 46794.5499,
6
+ "train_samples": 5495866,
7
+ "train_samples_per_second": 11744.671,
8
+ "train_steps_per_second": 244.682
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,665 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.39222519170640535,
5
+ "eval_steps": 1000000,
6
+ "global_step": 44909,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0043668885046027,
13
+ "grad_norm": 1.5595725774765015,
14
+ "learning_rate": 9.99956331114954e-06,
15
+ "loss": 3.1525,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.0087337770092054,
20
+ "grad_norm": 1.5938678979873657,
21
+ "learning_rate": 9.99912662229908e-06,
22
+ "loss": 3.1559,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.013100665513808101,
27
+ "grad_norm": 1.6471061706542969,
28
+ "learning_rate": 9.99868993344862e-06,
29
+ "loss": 3.1529,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.0174675540184108,
34
+ "grad_norm": 1.5785421133041382,
35
+ "learning_rate": 9.99825324459816e-06,
36
+ "loss": 3.1604,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.021834442523013503,
41
+ "grad_norm": 1.598698377609253,
42
+ "learning_rate": 9.9978165557477e-06,
43
+ "loss": 3.1565,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.026201331027616202,
48
+ "grad_norm": 1.5545878410339355,
49
+ "learning_rate": 9.997379866897238e-06,
50
+ "loss": 3.1531,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.030568219532218905,
55
+ "grad_norm": 1.5569171905517578,
56
+ "learning_rate": 9.996943178046778e-06,
57
+ "loss": 3.1572,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.0349351080368216,
62
+ "grad_norm": 1.569543719291687,
63
+ "learning_rate": 9.996506489196318e-06,
64
+ "loss": 3.1594,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.03930199654142431,
69
+ "grad_norm": 1.6514673233032227,
70
+ "learning_rate": 9.996069800345858e-06,
71
+ "loss": 3.1553,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.043668885046027006,
76
+ "grad_norm": 1.604501485824585,
77
+ "learning_rate": 9.995633111495399e-06,
78
+ "loss": 3.1547,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.048035773550629705,
83
+ "grad_norm": 1.6219558715820312,
84
+ "learning_rate": 9.995196422644939e-06,
85
+ "loss": 3.1534,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.052402662055232405,
90
+ "grad_norm": 1.606451392173767,
91
+ "learning_rate": 9.994759733794479e-06,
92
+ "loss": 3.1522,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.056769550559835104,
97
+ "grad_norm": 1.6143338680267334,
98
+ "learning_rate": 9.994323044944017e-06,
99
+ "loss": 3.1445,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.06113643906443781,
104
+ "grad_norm": 1.6684553623199463,
105
+ "learning_rate": 9.993886356093557e-06,
106
+ "loss": 3.1551,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.06550332756904051,
111
+ "grad_norm": 1.6013703346252441,
112
+ "learning_rate": 9.993449667243097e-06,
113
+ "loss": 3.1498,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.0698702160736432,
118
+ "grad_norm": 1.626556396484375,
119
+ "learning_rate": 9.993012978392636e-06,
120
+ "loss": 3.1509,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.07423710457824591,
125
+ "grad_norm": 1.659162998199463,
126
+ "learning_rate": 9.992576289542176e-06,
127
+ "loss": 3.153,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.07860399308284861,
132
+ "grad_norm": 1.6168526411056519,
133
+ "learning_rate": 9.992139600691716e-06,
134
+ "loss": 3.1429,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.0829708815874513,
139
+ "grad_norm": 1.6810740232467651,
140
+ "learning_rate": 9.991702911841256e-06,
141
+ "loss": 3.1438,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.08733777009205401,
146
+ "grad_norm": 1.7077081203460693,
147
+ "learning_rate": 9.991266222990796e-06,
148
+ "loss": 3.1474,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.0917046585966567,
153
+ "grad_norm": 1.5795377492904663,
154
+ "learning_rate": 9.990829534140335e-06,
155
+ "loss": 3.1564,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.09607154710125941,
160
+ "grad_norm": 1.6760386228561401,
161
+ "learning_rate": 9.990392845289875e-06,
162
+ "loss": 3.1534,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.10043843560586212,
167
+ "grad_norm": 1.5983505249023438,
168
+ "learning_rate": 9.989956156439415e-06,
169
+ "loss": 3.1464,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.10480532411046481,
174
+ "grad_norm": 1.6111019849777222,
175
+ "learning_rate": 9.989519467588953e-06,
176
+ "loss": 3.1333,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.10917221261506752,
181
+ "grad_norm": 1.5885874032974243,
182
+ "learning_rate": 9.989082778738493e-06,
183
+ "loss": 3.1461,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.11353910111967021,
188
+ "grad_norm": 1.6448547840118408,
189
+ "learning_rate": 9.988646089888033e-06,
190
+ "loss": 3.1459,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.11790598962427291,
195
+ "grad_norm": 1.6023292541503906,
196
+ "learning_rate": 9.988209401037573e-06,
197
+ "loss": 3.1467,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 0.12227287812887562,
202
+ "grad_norm": 1.5931400060653687,
203
+ "learning_rate": 9.987772712187114e-06,
204
+ "loss": 3.1388,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 0.1266397666334783,
209
+ "grad_norm": 1.625355839729309,
210
+ "learning_rate": 9.987336023336654e-06,
211
+ "loss": 3.1473,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 0.13100665513808102,
216
+ "grad_norm": 1.6307705640792847,
217
+ "learning_rate": 9.986899334486194e-06,
218
+ "loss": 3.1424,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.13537354364268372,
223
+ "grad_norm": 1.6311821937561035,
224
+ "learning_rate": 9.986462645635732e-06,
225
+ "loss": 3.1477,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 0.1397404321472864,
230
+ "grad_norm": 1.6085231304168701,
231
+ "learning_rate": 9.986025956785272e-06,
232
+ "loss": 3.1358,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 0.1441073206518891,
237
+ "grad_norm": 1.6187548637390137,
238
+ "learning_rate": 9.985589267934812e-06,
239
+ "loss": 3.1459,
240
+ "step": 16500
241
+ },
242
+ {
243
+ "epoch": 0.14847420915649182,
244
+ "grad_norm": 1.5847587585449219,
245
+ "learning_rate": 9.985152579084352e-06,
246
+ "loss": 3.1359,
247
+ "step": 17000
248
+ },
249
+ {
250
+ "epoch": 0.15284109766109452,
251
+ "grad_norm": 1.6051414012908936,
252
+ "learning_rate": 9.984715890233891e-06,
253
+ "loss": 3.1368,
254
+ "step": 17500
255
+ },
256
+ {
257
+ "epoch": 0.15720798616569723,
258
+ "grad_norm": 1.6769737005233765,
259
+ "learning_rate": 9.984279201383431e-06,
260
+ "loss": 3.1366,
261
+ "step": 18000
262
+ },
263
+ {
264
+ "epoch": 0.1615748746702999,
265
+ "grad_norm": 1.586376428604126,
266
+ "learning_rate": 9.983842512532971e-06,
267
+ "loss": 3.1454,
268
+ "step": 18500
269
+ },
270
+ {
271
+ "epoch": 0.1659417631749026,
272
+ "grad_norm": 1.6034488677978516,
273
+ "learning_rate": 9.98340582368251e-06,
274
+ "loss": 3.1395,
275
+ "step": 19000
276
+ },
277
+ {
278
+ "epoch": 0.17030865167950532,
279
+ "grad_norm": 1.5914573669433594,
280
+ "learning_rate": 9.98296913483205e-06,
281
+ "loss": 3.1394,
282
+ "step": 19500
283
+ },
284
+ {
285
+ "epoch": 0.17467554018410802,
286
+ "grad_norm": 1.6094170808792114,
287
+ "learning_rate": 9.98253244598159e-06,
288
+ "loss": 3.1452,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 0.17904242868871073,
293
+ "grad_norm": 1.5861003398895264,
294
+ "learning_rate": 9.982095757131129e-06,
295
+ "loss": 3.1337,
296
+ "step": 20500
297
+ },
298
+ {
299
+ "epoch": 0.1834093171933134,
300
+ "grad_norm": 1.5987565517425537,
301
+ "learning_rate": 9.981659068280668e-06,
302
+ "loss": 3.1437,
303
+ "step": 21000
304
+ },
305
+ {
306
+ "epoch": 0.18777620569791612,
307
+ "grad_norm": 1.5903559923171997,
308
+ "learning_rate": 9.981222379430208e-06,
309
+ "loss": 3.1364,
310
+ "step": 21500
311
+ },
312
+ {
313
+ "epoch": 0.19214309420251882,
314
+ "grad_norm": 1.5559889078140259,
315
+ "learning_rate": 9.980785690579748e-06,
316
+ "loss": 3.1412,
317
+ "step": 22000
318
+ },
319
+ {
320
+ "epoch": 0.19650998270712153,
321
+ "grad_norm": 1.6113758087158203,
322
+ "learning_rate": 9.980349001729288e-06,
323
+ "loss": 3.1364,
324
+ "step": 22500
325
+ },
326
+ {
327
+ "epoch": 0.20087687121172423,
328
+ "grad_norm": 1.6110438108444214,
329
+ "learning_rate": 9.97991231287883e-06,
330
+ "loss": 3.1404,
331
+ "step": 23000
332
+ },
333
+ {
334
+ "epoch": 0.2052437597163269,
335
+ "grad_norm": 1.6391644477844238,
336
+ "learning_rate": 9.97947562402837e-06,
337
+ "loss": 3.1398,
338
+ "step": 23500
339
+ },
340
+ {
341
+ "epoch": 0.20961064822092962,
342
+ "grad_norm": 1.5945662260055542,
343
+ "learning_rate": 9.979038935177907e-06,
344
+ "loss": 3.1351,
345
+ "step": 24000
346
+ },
347
+ {
348
+ "epoch": 0.21397753672553232,
349
+ "grad_norm": 1.7338697910308838,
350
+ "learning_rate": 9.978602246327447e-06,
351
+ "loss": 3.1294,
352
+ "step": 24500
353
+ },
354
+ {
355
+ "epoch": 0.21834442523013503,
356
+ "grad_norm": 1.574798345565796,
357
+ "learning_rate": 9.978165557476987e-06,
358
+ "loss": 3.1328,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 0.22271131373473774,
363
+ "grad_norm": 1.5656156539916992,
364
+ "learning_rate": 9.977728868626527e-06,
365
+ "loss": 3.1307,
366
+ "step": 25500
367
+ },
368
+ {
369
+ "epoch": 0.22707820223934042,
370
+ "grad_norm": 1.6264046430587769,
371
+ "learning_rate": 9.977292179776067e-06,
372
+ "loss": 3.1382,
373
+ "step": 26000
374
+ },
375
+ {
376
+ "epoch": 0.23144509074394312,
377
+ "grad_norm": 1.591504454612732,
378
+ "learning_rate": 9.976855490925607e-06,
379
+ "loss": 3.1317,
380
+ "step": 26500
381
+ },
382
+ {
383
+ "epoch": 0.23581197924854583,
384
+ "grad_norm": 1.7037614583969116,
385
+ "learning_rate": 9.976418802075146e-06,
386
+ "loss": 3.1284,
387
+ "step": 27000
388
+ },
389
+ {
390
+ "epoch": 0.24017886775314853,
391
+ "grad_norm": 1.6053491830825806,
392
+ "learning_rate": 9.975982113224686e-06,
393
+ "loss": 3.1391,
394
+ "step": 27500
395
+ },
396
+ {
397
+ "epoch": 0.24454575625775124,
398
+ "grad_norm": 1.574787974357605,
399
+ "learning_rate": 9.975545424374226e-06,
400
+ "loss": 3.133,
401
+ "step": 28000
402
+ },
403
+ {
404
+ "epoch": 0.24891264476235392,
405
+ "grad_norm": 1.5841468572616577,
406
+ "learning_rate": 9.975108735523766e-06,
407
+ "loss": 3.1298,
408
+ "step": 28500
409
+ },
410
+ {
411
+ "epoch": 0.2532795332669566,
412
+ "grad_norm": 1.5428208112716675,
413
+ "learning_rate": 9.974672046673306e-06,
414
+ "loss": 3.1313,
415
+ "step": 29000
416
+ },
417
+ {
418
+ "epoch": 0.25764642177155933,
419
+ "grad_norm": 1.6238336563110352,
420
+ "learning_rate": 9.974235357822844e-06,
421
+ "loss": 3.1199,
422
+ "step": 29500
423
+ },
424
+ {
425
+ "epoch": 0.26201331027616204,
426
+ "grad_norm": 1.6074714660644531,
427
+ "learning_rate": 9.973798668972384e-06,
428
+ "loss": 3.1322,
429
+ "step": 30000
430
+ },
431
+ {
432
+ "epoch": 0.26638019878076474,
433
+ "grad_norm": 1.583072304725647,
434
+ "learning_rate": 9.973361980121923e-06,
435
+ "loss": 3.133,
436
+ "step": 30500
437
+ },
438
+ {
439
+ "epoch": 0.27074708728536745,
440
+ "grad_norm": 1.6968551874160767,
441
+ "learning_rate": 9.972925291271463e-06,
442
+ "loss": 3.1281,
443
+ "step": 31000
444
+ },
445
+ {
446
+ "epoch": 0.27511397578997016,
447
+ "grad_norm": 1.6063077449798584,
448
+ "learning_rate": 9.972488602421003e-06,
449
+ "loss": 3.1247,
450
+ "step": 31500
451
+ },
452
+ {
453
+ "epoch": 0.2794808642945728,
454
+ "grad_norm": 1.5899564027786255,
455
+ "learning_rate": 9.972051913570545e-06,
456
+ "loss": 3.1215,
457
+ "step": 32000
458
+ },
459
+ {
460
+ "epoch": 0.2838477527991755,
461
+ "grad_norm": 1.5838756561279297,
462
+ "learning_rate": 9.971615224720084e-06,
463
+ "loss": 3.1262,
464
+ "step": 32500
465
+ },
466
+ {
467
+ "epoch": 0.2882146413037782,
468
+ "grad_norm": 1.5518513917922974,
469
+ "learning_rate": 9.971178535869623e-06,
470
+ "loss": 3.1181,
471
+ "step": 33000
472
+ },
473
+ {
474
+ "epoch": 0.2925815298083809,
475
+ "grad_norm": 1.5394465923309326,
476
+ "learning_rate": 9.970741847019162e-06,
477
+ "loss": 3.1205,
478
+ "step": 33500
479
+ },
480
+ {
481
+ "epoch": 0.29694841831298363,
482
+ "grad_norm": 1.6238704919815063,
483
+ "learning_rate": 9.970305158168702e-06,
484
+ "loss": 3.1205,
485
+ "step": 34000
486
+ },
487
+ {
488
+ "epoch": 0.30131530681758634,
489
+ "grad_norm": 1.6042754650115967,
490
+ "learning_rate": 9.969868469318242e-06,
491
+ "loss": 3.1283,
492
+ "step": 34500
493
+ },
494
+ {
495
+ "epoch": 0.30568219532218904,
496
+ "grad_norm": 1.6376352310180664,
497
+ "learning_rate": 9.969431780467782e-06,
498
+ "loss": 3.1242,
499
+ "step": 35000
500
+ },
501
+ {
502
+ "epoch": 0.31004908382679175,
503
+ "grad_norm": 1.6078994274139404,
504
+ "learning_rate": 9.968995091617322e-06,
505
+ "loss": 3.1188,
506
+ "step": 35500
507
+ },
508
+ {
509
+ "epoch": 0.31441597233139446,
510
+ "grad_norm": 1.6135457754135132,
511
+ "learning_rate": 9.968558402766862e-06,
512
+ "loss": 3.1187,
513
+ "step": 36000
514
+ },
515
+ {
516
+ "epoch": 0.31878286083599716,
517
+ "grad_norm": 1.6336065530776978,
518
+ "learning_rate": 9.968121713916401e-06,
519
+ "loss": 3.1183,
520
+ "step": 36500
521
+ },
522
+ {
523
+ "epoch": 0.3231497493405998,
524
+ "grad_norm": 1.6096062660217285,
525
+ "learning_rate": 9.967685025065941e-06,
526
+ "loss": 3.1183,
527
+ "step": 37000
528
+ },
529
+ {
530
+ "epoch": 0.3275166378452025,
531
+ "grad_norm": 1.570556879043579,
532
+ "learning_rate": 9.967248336215481e-06,
533
+ "loss": 3.122,
534
+ "step": 37500
535
+ },
536
+ {
537
+ "epoch": 0.3318835263498052,
538
+ "grad_norm": 1.5272282361984253,
539
+ "learning_rate": 9.96681164736502e-06,
540
+ "loss": 3.1193,
541
+ "step": 38000
542
+ },
543
+ {
544
+ "epoch": 0.33625041485440793,
545
+ "grad_norm": 1.5485848188400269,
546
+ "learning_rate": 9.966374958514559e-06,
547
+ "loss": 3.1222,
548
+ "step": 38500
549
+ },
550
+ {
551
+ "epoch": 0.34061730335901064,
552
+ "grad_norm": 1.5924766063690186,
553
+ "learning_rate": 9.965938269664099e-06,
554
+ "loss": 3.1183,
555
+ "step": 39000
556
+ },
557
+ {
558
+ "epoch": 0.34498419186361334,
559
+ "grad_norm": 1.601727843284607,
560
+ "learning_rate": 9.965501580813639e-06,
561
+ "loss": 3.1194,
562
+ "step": 39500
563
+ },
564
+ {
565
+ "epoch": 0.34935108036821605,
566
+ "grad_norm": 1.6034713983535767,
567
+ "learning_rate": 9.965064891963178e-06,
568
+ "loss": 3.1146,
569
+ "step": 40000
570
+ },
571
+ {
572
+ "epoch": 0.35371796887281876,
573
+ "grad_norm": 1.6022893190383911,
574
+ "learning_rate": 9.964628203112718e-06,
575
+ "loss": 3.116,
576
+ "step": 40500
577
+ },
578
+ {
579
+ "epoch": 0.35808485737742146,
580
+ "grad_norm": 1.5923199653625488,
581
+ "learning_rate": 9.96419151426226e-06,
582
+ "loss": 3.1191,
583
+ "step": 41000
584
+ },
585
+ {
586
+ "epoch": 0.36245174588202417,
587
+ "grad_norm": 1.5369057655334473,
588
+ "learning_rate": 9.9637548254118e-06,
589
+ "loss": 3.1153,
590
+ "step": 41500
591
+ },
592
+ {
593
+ "epoch": 0.3668186343866268,
594
+ "grad_norm": 1.574439525604248,
595
+ "learning_rate": 9.963318136561338e-06,
596
+ "loss": 3.1164,
597
+ "step": 42000
598
+ },
599
+ {
600
+ "epoch": 0.3711855228912295,
601
+ "grad_norm": 1.5916707515716553,
602
+ "learning_rate": 9.962881447710878e-06,
603
+ "loss": 3.1115,
604
+ "step": 42500
605
+ },
606
+ {
607
+ "epoch": 0.37555241139583223,
608
+ "grad_norm": 1.551416277885437,
609
+ "learning_rate": 9.962444758860417e-06,
610
+ "loss": 3.1154,
611
+ "step": 43000
612
+ },
613
+ {
614
+ "epoch": 0.37991929990043494,
615
+ "grad_norm": 1.6488794088363647,
616
+ "learning_rate": 9.962008070009957e-06,
617
+ "loss": 3.1175,
618
+ "step": 43500
619
+ },
620
+ {
621
+ "epoch": 0.38428618840503764,
622
+ "grad_norm": 1.5746173858642578,
623
+ "learning_rate": 9.961571381159497e-06,
624
+ "loss": 3.1112,
625
+ "step": 44000
626
+ },
627
+ {
628
+ "epoch": 0.38865307690964035,
629
+ "grad_norm": 1.5648127794265747,
630
+ "learning_rate": 9.961134692309037e-06,
631
+ "loss": 3.1055,
632
+ "step": 44500
633
+ },
634
+ {
635
+ "epoch": 0.39222519170640535,
636
+ "step": 44909,
637
+ "total_flos": 1.1264989248576553e+18,
638
+ "train_loss": 3.1353410507916006,
639
+ "train_runtime": 46794.5499,
640
+ "train_samples_per_second": 11744.671,
641
+ "train_steps_per_second": 244.682
642
+ }
643
+ ],
644
+ "logging_steps": 500,
645
+ "max_steps": 11449800,
646
+ "num_input_tokens_seen": 0,
647
+ "num_train_epochs": 100,
648
+ "save_steps": 1000000,
649
+ "stateful_callbacks": {
650
+ "TrainerControl": {
651
+ "args": {
652
+ "should_epoch_stop": false,
653
+ "should_evaluate": false,
654
+ "should_log": false,
655
+ "should_save": false,
656
+ "should_training_stop": false
657
+ },
658
+ "attributes": {}
659
+ }
660
+ },
661
+ "total_flos": 1.1264989248576553e+18,
662
+ "train_batch_size": 48,
663
+ "trial_name": null,
664
+ "trial_params": null
665
+ }