gsmyrnis commited on
Commit
558a58e
·
verified ·
1 Parent(s): c7b79b6

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: llama3-1_8b_oh_v3.1_wo_collective_cognition
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # llama3-1_8b_oh_v3.1_wo_collective_cognition
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.6409
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: llama3-1_8b_oh_v3.1_wo_collective_cognition
 
16
 
17
  # llama3-1_8b_oh_v3.1_wo_collective_cognition
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh_v3.1_wo_collective_cognition dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6409
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.6408979892730713,
4
+ "eval_runtime": 40.4908,
5
+ "eval_samples_per_second": 281.273,
6
+ "eval_steps_per_second": 1.111,
7
+ "total_flos": 2125622264463360.0,
8
+ "train_loss": 0.6192652515955475,
9
+ "train_runtime": 7838.8261,
10
+ "train_samples_per_second": 82.815,
11
+ "train_steps_per_second": 0.162
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.6408979892730713,
4
+ "eval_runtime": 40.4908,
5
+ "eval_samples_per_second": 281.273,
6
+ "eval_steps_per_second": 1.111
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 2125622264463360.0,
4
+ "train_loss": 0.6192652515955475,
5
+ "train_runtime": 7838.8261,
6
+ "train_samples_per_second": 82.815,
7
+ "train_steps_per_second": 0.162
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,948 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1269,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02364066193853428,
13
+ "grad_norm": 2.72535029902805,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.8948,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04728132387706856,
20
+ "grad_norm": 1.349869757361133,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7791,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.07092198581560284,
27
+ "grad_norm": 1.1982665750771995,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.7498,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.09456264775413711,
34
+ "grad_norm": 1.3901014180682558,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.7383,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.1182033096926714,
41
+ "grad_norm": 1.6352055235262863,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.7156,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.14184397163120568,
48
+ "grad_norm": 0.9228519705928501,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7113,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.16548463356973994,
55
+ "grad_norm": 0.6109421695741598,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7015,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.18912529550827423,
62
+ "grad_norm": 1.1570191508750998,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6928,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.2127659574468085,
69
+ "grad_norm": 0.5479664575799189,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6881,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2364066193853428,
76
+ "grad_norm": 0.6511091776660864,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6791,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.26004728132387706,
83
+ "grad_norm": 0.48965953407572976,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6875,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.28368794326241137,
90
+ "grad_norm": 0.5366385574454531,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6943,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.3073286052009456,
97
+ "grad_norm": 0.5940009124876445,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6732,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3309692671394799,
104
+ "grad_norm": 0.5363561097267587,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6705,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3546099290780142,
111
+ "grad_norm": 0.47312672873118417,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6736,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.37825059101654845,
118
+ "grad_norm": 0.5936177797142055,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6714,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.40189125295508277,
125
+ "grad_norm": 0.559796603492257,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.677,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.425531914893617,
132
+ "grad_norm": 0.6712065525809435,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6739,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4491725768321513,
139
+ "grad_norm": 0.6276897126428631,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6712,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4728132387706856,
146
+ "grad_norm": 0.5058454380091781,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6704,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.49645390070921985,
153
+ "grad_norm": 0.4856083261066063,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6734,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5200945626477541,
160
+ "grad_norm": 0.47853309599062016,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6679,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5437352245862884,
167
+ "grad_norm": 0.5028725498074064,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6603,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5673758865248227,
174
+ "grad_norm": 0.573425790046604,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6666,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5910165484633569,
181
+ "grad_norm": 0.5450174649743487,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.663,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.6146572104018913,
188
+ "grad_norm": 0.6439202377303648,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.6619,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6382978723404256,
195
+ "grad_norm": 0.6134638277704878,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6537,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6619385342789598,
202
+ "grad_norm": 0.5994186482549169,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6618,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6855791962174941,
209
+ "grad_norm": 0.5012460436454785,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6608,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.7092198581560284,
216
+ "grad_norm": 0.5441826630708447,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.66,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.7328605200945626,
223
+ "grad_norm": 0.522329425801996,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6568,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7565011820330969,
230
+ "grad_norm": 0.4758083660420685,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.6554,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7801418439716312,
237
+ "grad_norm": 0.49940764507627,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.6566,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.8037825059101655,
244
+ "grad_norm": 0.6679446252287796,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.6604,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.8274231678486997,
251
+ "grad_norm": 0.4668378880080796,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.6542,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.851063829787234,
258
+ "grad_norm": 0.6341578495542675,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.6517,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8747044917257684,
265
+ "grad_norm": 0.4656594360564299,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.6535,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8983451536643026,
272
+ "grad_norm": 0.44357749005248587,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.6606,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.9219858156028369,
279
+ "grad_norm": 0.4530641632992077,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.6507,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9456264775413712,
286
+ "grad_norm": 0.5037838223896282,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.6555,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9692671394799054,
293
+ "grad_norm": 0.6623305884354875,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.6534,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9929078014184397,
300
+ "grad_norm": 0.43978357483041475,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.6503,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 1.0,
307
+ "eval_loss": 0.6491107940673828,
308
+ "eval_runtime": 40.7764,
309
+ "eval_samples_per_second": 279.304,
310
+ "eval_steps_per_second": 1.104,
311
+ "step": 423
312
+ },
313
+ {
314
+ "epoch": 1.016548463356974,
315
+ "grad_norm": 0.6718862738139351,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.626,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.0401891252955082,
322
+ "grad_norm": 0.5240286124375526,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6033,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.0638297872340425,
329
+ "grad_norm": 0.5544933380864768,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6171,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.0874704491725768,
336
+ "grad_norm": 0.5500112360385622,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6138,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.1111111111111112,
343
+ "grad_norm": 0.6555691233512699,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6114,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.1347517730496455,
350
+ "grad_norm": 0.460930139599731,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6141,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.1583924349881798,
357
+ "grad_norm": 0.5188774400467296,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6158,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1820330969267139,
364
+ "grad_norm": 0.4640360714483605,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6154,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.2056737588652482,
371
+ "grad_norm": 0.6093764843000187,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6093,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.2293144208037825,
378
+ "grad_norm": 0.6555953339288757,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6096,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.2529550827423168,
385
+ "grad_norm": 0.5237254449671765,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6133,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2765957446808511,
392
+ "grad_norm": 0.6077697942607891,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6087,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.3002364066193852,
399
+ "grad_norm": 0.4959290366758788,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.603,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.3238770685579198,
406
+ "grad_norm": 0.5120427167213613,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.6104,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.3475177304964538,
413
+ "grad_norm": 0.467013186042987,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.6095,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.3711583924349882,
420
+ "grad_norm": 0.49118088063072135,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.6166,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3947990543735225,
427
+ "grad_norm": 0.48826248333502054,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.6055,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.4184397163120568,
434
+ "grad_norm": 0.5012542755180496,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.6091,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.442080378250591,
441
+ "grad_norm": 0.41199293127019976,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6111,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.4657210401891252,
448
+ "grad_norm": 0.5227856582567488,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.6094,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.4893617021276595,
455
+ "grad_norm": 0.4396680922197246,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.6053,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.5130023640661938,
462
+ "grad_norm": 0.4667905586119019,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.6083,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.5366430260047281,
469
+ "grad_norm": 0.4909469537010317,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.6047,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.5602836879432624,
476
+ "grad_norm": 0.44596683795863395,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.612,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.5839243498817965,
483
+ "grad_norm": 0.5717586109502525,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.6095,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.607565011820331,
490
+ "grad_norm": 0.4490571190501361,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.6085,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.6312056737588652,
497
+ "grad_norm": 0.5286431637266866,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.6074,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.6548463356973995,
504
+ "grad_norm": 0.5173624908943171,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.6038,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.6784869976359338,
511
+ "grad_norm": 0.43453587339422367,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.6128,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.702127659574468,
518
+ "grad_norm": 0.4902717681255394,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.6036,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.7257683215130024,
525
+ "grad_norm": 0.4350343628276203,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.605,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.7494089834515365,
532
+ "grad_norm": 0.528540441581878,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.6095,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.773049645390071,
539
+ "grad_norm": 0.600684912479072,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.6106,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.7966903073286051,
546
+ "grad_norm": 0.5051323358574029,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.6091,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.8203309692671394,
553
+ "grad_norm": 0.47055245921215216,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.6052,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.8439716312056738,
560
+ "grad_norm": 0.40634667845025374,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.6077,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.867612293144208,
567
+ "grad_norm": 0.42084763446520207,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.6101,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.8912529550827424,
574
+ "grad_norm": 0.4874640354448252,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.6064,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.9148936170212765,
581
+ "grad_norm": 0.4503284940019477,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.6057,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.938534278959811,
588
+ "grad_norm": 0.5426691149205667,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.6066,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.962174940898345,
595
+ "grad_norm": 0.44537977097090253,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.6082,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.9858156028368794,
602
+ "grad_norm": 0.47774839135537583,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.602,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 2.0,
609
+ "eval_loss": 0.6393836736679077,
610
+ "eval_runtime": 41.0339,
611
+ "eval_samples_per_second": 277.551,
612
+ "eval_steps_per_second": 1.097,
613
+ "step": 846
614
+ },
615
+ {
616
+ "epoch": 2.0094562647754137,
617
+ "grad_norm": 0.6118720101139726,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.5868,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.033096926713948,
624
+ "grad_norm": 0.5572904299838869,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5582,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.0567375886524824,
631
+ "grad_norm": 0.5303184511401988,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5637,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.0803782505910164,
638
+ "grad_norm": 0.46454295303538246,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.5592,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.104018912529551,
645
+ "grad_norm": 0.6361956702505728,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.562,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.127659574468085,
652
+ "grad_norm": 0.7820428278668116,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5611,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.1513002364066196,
659
+ "grad_norm": 0.45298061775995824,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.562,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.1749408983451537,
666
+ "grad_norm": 0.5810391810087593,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.566,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.198581560283688,
673
+ "grad_norm": 0.4908474714534316,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.5634,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.2222222222222223,
680
+ "grad_norm": 0.46389513213427735,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.5634,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.2458628841607564,
687
+ "grad_norm": 0.6367614359838906,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.566,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.269503546099291,
694
+ "grad_norm": 0.6141281239807579,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.5674,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.293144208037825,
701
+ "grad_norm": 0.542025677626535,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.5651,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.3167848699763596,
708
+ "grad_norm": 0.551857948487274,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.5661,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.3404255319148937,
715
+ "grad_norm": 0.5734053167546258,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.5656,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.3640661938534278,
722
+ "grad_norm": 0.5234453524143412,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.5741,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.3877068557919623,
729
+ "grad_norm": 0.45374696937088277,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.5671,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.4113475177304964,
736
+ "grad_norm": 0.4880786886377219,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.5721,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.434988179669031,
743
+ "grad_norm": 0.5028949189688434,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.5667,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.458628841607565,
750
+ "grad_norm": 0.49048839220420004,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.5643,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.482269503546099,
757
+ "grad_norm": 0.5197651600869932,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.5692,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.5059101654846336,
764
+ "grad_norm": 0.4874044145512749,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.5667,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.5295508274231677,
771
+ "grad_norm": 0.4664634995358468,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.5671,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.5531914893617023,
778
+ "grad_norm": 0.48656363327654745,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.574,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.5768321513002364,
785
+ "grad_norm": 0.5305320232208198,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.572,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.6004728132387704,
792
+ "grad_norm": 0.4910484019313719,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.5732,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.624113475177305,
799
+ "grad_norm": 0.5239661409291978,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.571,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.6477541371158395,
806
+ "grad_norm": 0.46223769122758984,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.5734,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.6713947990543736,
813
+ "grad_norm": 0.5142173641545875,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.5694,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.6950354609929077,
820
+ "grad_norm": 0.5294027287882332,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.5646,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.7186761229314422,
827
+ "grad_norm": 0.5331405829578174,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.5723,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.7423167848699763,
834
+ "grad_norm": 0.44857073429789307,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.5683,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.7659574468085104,
841
+ "grad_norm": 0.474611592323436,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.5786,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.789598108747045,
848
+ "grad_norm": 0.4950458376766123,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.5741,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.813238770685579,
855
+ "grad_norm": 0.5359701758991028,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.5728,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.8368794326241136,
862
+ "grad_norm": 0.43477013271067744,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.569,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.8605200945626477,
869
+ "grad_norm": 0.46358204115129703,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.5694,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.884160756501182,
876
+ "grad_norm": 0.4374097557825778,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.5689,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.9078014184397163,
883
+ "grad_norm": 0.5145958315798522,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.5738,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.9314420803782504,
890
+ "grad_norm": 0.5316891926922875,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.5748,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.955082742316785,
897
+ "grad_norm": 0.4296286799595667,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.5663,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.978723404255319,
904
+ "grad_norm": 0.5500793615243753,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.5681,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 3.0,
911
+ "eval_loss": 0.6408979892730713,
912
+ "eval_runtime": 40.071,
913
+ "eval_samples_per_second": 284.22,
914
+ "eval_steps_per_second": 1.123,
915
+ "step": 1269
916
+ },
917
+ {
918
+ "epoch": 3.0,
919
+ "step": 1269,
920
+ "total_flos": 2125622264463360.0,
921
+ "train_loss": 0.6192652515955475,
922
+ "train_runtime": 7838.8261,
923
+ "train_samples_per_second": 82.815,
924
+ "train_steps_per_second": 0.162
925
+ }
926
+ ],
927
+ "logging_steps": 10,
928
+ "max_steps": 1269,
929
+ "num_input_tokens_seen": 0,
930
+ "num_train_epochs": 3,
931
+ "save_steps": 500,
932
+ "stateful_callbacks": {
933
+ "TrainerControl": {
934
+ "args": {
935
+ "should_epoch_stop": false,
936
+ "should_evaluate": false,
937
+ "should_log": false,
938
+ "should_save": true,
939
+ "should_training_stop": true
940
+ },
941
+ "attributes": {}
942
+ }
943
+ },
944
+ "total_flos": 2125622264463360.0,
945
+ "train_batch_size": 16,
946
+ "trial_name": null,
947
+ "trial_params": null
948
+ }
training_eval_loss.png ADDED
training_loss.png ADDED