sedrickkeh commited on
Commit
1bfae4b
1 Parent(s): 1ca0b86

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: OH_DCFT_V3_wo_cot_alpaca
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # OH_DCFT_V3_wo_cot_alpaca
17
 
18
- This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.6369
21
 
 
4
  base_model: meta-llama/Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: OH_DCFT_V3_wo_cot_alpaca
 
16
 
17
  # OH_DCFT_V3_wo_cot_alpaca
18
 
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the mlfoundations-dev/OH_DCFT_V3_wo_cot_alpaca dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6369
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9946268656716417,
3
+ "eval_loss": 0.636893630027771,
4
+ "eval_runtime": 142.6031,
5
+ "eval_samples_per_second": 79.129,
6
+ "eval_steps_per_second": 0.624,
7
+ "total_flos": 2100077946470400.0,
8
+ "train_loss": 0.6183488205479283,
9
+ "train_runtime": 21046.2129,
10
+ "train_samples_per_second": 30.56,
11
+ "train_steps_per_second": 0.06
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9946268656716417,
3
+ "eval_loss": 0.636893630027771,
4
+ "eval_runtime": 142.6031,
5
+ "eval_samples_per_second": 79.129,
6
+ "eval_steps_per_second": 0.624
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9946268656716417,
3
+ "total_flos": 2100077946470400.0,
4
+ "train_loss": 0.6183488205479283,
5
+ "train_runtime": 21046.2129,
6
+ "train_samples_per_second": 30.56,
7
+ "train_steps_per_second": 0.06
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9946268656716417,
5
+ "eval_steps": 500,
6
+ "global_step": 1254,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.023880597014925373,
13
+ "grad_norm": 10.273793568807084,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.8832,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04776119402985075,
20
+ "grad_norm": 17.413079986249713,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7826,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.07164179104477612,
27
+ "grad_norm": 1.7682355694433471,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.7785,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0955223880597015,
34
+ "grad_norm": 1.2119658541333866,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.7537,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11940298507462686,
41
+ "grad_norm": 0.8476848561416307,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.7389,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.14328358208955225,
48
+ "grad_norm": 0.7667403306996323,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7217,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.16716417910447762,
55
+ "grad_norm": 0.8702244781914732,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7085,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.191044776119403,
62
+ "grad_norm": 1.3853703465833076,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6971,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.21492537313432836,
69
+ "grad_norm": 1.2094222885220798,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6882,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.23880597014925373,
76
+ "grad_norm": 0.7689681572000278,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6849,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2626865671641791,
83
+ "grad_norm": 0.7780597190717987,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6818,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2865671641791045,
90
+ "grad_norm": 0.5000855152810337,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6816,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.31044776119402984,
97
+ "grad_norm": 0.7276396850932823,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6736,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.33432835820895523,
104
+ "grad_norm": 0.6186133127584187,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6818,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3582089552238806,
111
+ "grad_norm": 0.48005981720062146,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.673,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.382089552238806,
118
+ "grad_norm": 0.5023606142200144,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6773,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.4059701492537313,
125
+ "grad_norm": 0.5808170399886017,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.6677,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4298507462686567,
132
+ "grad_norm": 0.4379969982797677,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6685,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4537313432835821,
139
+ "grad_norm": 0.5347993662162854,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6752,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.47761194029850745,
146
+ "grad_norm": 0.5389725567643092,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6648,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.5014925373134328,
153
+ "grad_norm": 0.48052530490608086,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6641,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5253731343283582,
160
+ "grad_norm": 0.5805014519700745,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6591,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5492537313432836,
167
+ "grad_norm": 0.48958097076386,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6655,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.573134328358209,
174
+ "grad_norm": 0.49437501765783676,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6683,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5970149253731343,
181
+ "grad_norm": 0.45944903239035917,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.659,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.6208955223880597,
188
+ "grad_norm": 0.4748455280427033,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.6583,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6447761194029851,
195
+ "grad_norm": 0.507103510913949,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6583,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6686567164179105,
202
+ "grad_norm": 0.48478059033960125,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6587,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6925373134328359,
209
+ "grad_norm": 0.5180513023339883,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6557,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.7164179104477612,
216
+ "grad_norm": 0.6977133509211488,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.6596,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.7402985074626866,
223
+ "grad_norm": 0.6751977610973682,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6631,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.764179104477612,
230
+ "grad_norm": 0.5497977666993439,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.6538,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7880597014925373,
237
+ "grad_norm": 0.4930749400299794,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.6533,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.8119402985074626,
244
+ "grad_norm": 0.42531288506677356,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.654,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.835820895522388,
251
+ "grad_norm": 0.3981313944033897,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.6588,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8597014925373134,
258
+ "grad_norm": 0.5280916740215565,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.6467,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8835820895522388,
265
+ "grad_norm": 0.42664364036263097,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.6547,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.9074626865671642,
272
+ "grad_norm": 0.4407169068422887,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.6576,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.9313432835820895,
279
+ "grad_norm": 0.5863915466432706,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.6517,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9552238805970149,
286
+ "grad_norm": 0.591205757573771,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.6489,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9791044776119403,
293
+ "grad_norm": 0.4729812620066271,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.6443,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9982089552238806,
300
+ "eval_loss": 0.6459853649139404,
301
+ "eval_runtime": 145.5401,
302
+ "eval_samples_per_second": 77.532,
303
+ "eval_steps_per_second": 0.612,
304
+ "step": 418
305
+ },
306
+ {
307
+ "epoch": 1.0029850746268656,
308
+ "grad_norm": 0.7406302510482085,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6464,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.026865671641791,
315
+ "grad_norm": 0.5814842349080193,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6064,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.0507462686567164,
322
+ "grad_norm": 0.49550119932649633,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6082,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.0746268656716418,
329
+ "grad_norm": 0.5636659335114863,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6113,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.0985074626865672,
336
+ "grad_norm": 0.5990578133097235,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6025,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.1223880597014926,
343
+ "grad_norm": 0.5395914783918955,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6096,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.146268656716418,
350
+ "grad_norm": 0.5134850748551497,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6127,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.1701492537313434,
357
+ "grad_norm": 0.6291645545602457,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6016,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1940298507462686,
364
+ "grad_norm": 0.5896587056027497,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6078,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.217910447761194,
371
+ "grad_norm": 0.44004057090652665,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6028,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.2417910447761193,
378
+ "grad_norm": 0.6082489861086471,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6057,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.2656716417910447,
385
+ "grad_norm": 0.4757708288590624,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6128,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2895522388059701,
392
+ "grad_norm": 0.4866590721782206,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6133,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.3134328358208955,
399
+ "grad_norm": 0.4646472106430823,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6089,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.337313432835821,
406
+ "grad_norm": 0.44517915287397264,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.6079,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.3611940298507463,
413
+ "grad_norm": 0.6694478573734268,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.6069,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.3850746268656717,
420
+ "grad_norm": 0.5078303398930042,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.6069,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.408955223880597,
427
+ "grad_norm": 0.503001629794063,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.6111,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.4328358208955223,
434
+ "grad_norm": 0.5438514985018119,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.613,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.4567164179104477,
441
+ "grad_norm": 0.5056414273287846,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6031,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.480597014925373,
448
+ "grad_norm": 0.4588677461940861,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.6126,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.5044776119402985,
455
+ "grad_norm": 0.5151479126151606,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.608,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.528358208955224,
462
+ "grad_norm": 0.46401616793533473,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.6031,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.5522388059701493,
469
+ "grad_norm": 0.48451525361860803,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.605,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.5761194029850745,
476
+ "grad_norm": 0.47997260631095534,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.6109,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.6,
483
+ "grad_norm": 0.4897371630270623,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.6058,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.6238805970149253,
490
+ "grad_norm": 0.5654442922228684,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.6123,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.6477611940298509,
497
+ "grad_norm": 0.5784991723951006,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.5942,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.671641791044776,
504
+ "grad_norm": 0.4722303828551024,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.6106,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.6955223880597015,
511
+ "grad_norm": 0.4839424076756933,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.6091,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.7194029850746269,
518
+ "grad_norm": 0.47764784827023116,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.6123,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.7432835820895523,
525
+ "grad_norm": 0.6621875079490905,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.6019,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.7671641791044777,
532
+ "grad_norm": 0.41773352573318373,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.6012,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.7910447761194028,
539
+ "grad_norm": 0.5339311769344796,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.6088,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.8149253731343284,
546
+ "grad_norm": 0.41758051779371724,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.602,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.8388059701492536,
553
+ "grad_norm": 0.48493110488320246,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.609,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.8626865671641792,
560
+ "grad_norm": 0.503079485131092,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.6108,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.8865671641791044,
567
+ "grad_norm": 0.49999802261208487,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.6059,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.9104477611940298,
574
+ "grad_norm": 0.49289621093364544,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.6071,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.9343283582089552,
581
+ "grad_norm": 0.5213797280676552,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.6006,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.9582089552238806,
588
+ "grad_norm": 0.48494536428497287,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.606,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.982089552238806,
595
+ "grad_norm": 0.6304797916900879,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.6046,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.9988059701492538,
602
+ "eval_loss": 0.6354221701622009,
603
+ "eval_runtime": 145.6955,
604
+ "eval_samples_per_second": 77.449,
605
+ "eval_steps_per_second": 0.611,
606
+ "step": 837
607
+ },
608
+ {
609
+ "epoch": 2.005970149253731,
610
+ "grad_norm": 0.7544412739259527,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.6034,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.029850746268657,
617
+ "grad_norm": 0.6076312693154532,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.5647,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.053731343283582,
624
+ "grad_norm": 0.5264338967840297,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5566,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.0776119402985076,
631
+ "grad_norm": 0.5190037883143301,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5679,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.1014925373134328,
638
+ "grad_norm": 0.46674031058869914,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.5611,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.1253731343283584,
645
+ "grad_norm": 0.5072546488653424,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.565,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.1492537313432836,
652
+ "grad_norm": 0.6009874453432602,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5611,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.173134328358209,
659
+ "grad_norm": 0.46110082010928216,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.5618,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.1970149253731344,
666
+ "grad_norm": 0.5163994956633559,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.568,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.2208955223880595,
673
+ "grad_norm": 0.6176077747391998,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.5698,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.244776119402985,
680
+ "grad_norm": 0.46798047694883976,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.5607,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.2686567164179103,
687
+ "grad_norm": 0.5458770025747796,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.5657,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.292537313432836,
694
+ "grad_norm": 0.4522021510300349,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.5582,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.316417910447761,
701
+ "grad_norm": 0.4993495813706899,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.5673,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.3402985074626868,
708
+ "grad_norm": 0.5148727234502507,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.5627,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.364179104477612,
715
+ "grad_norm": 0.4746669105759272,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.5632,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.388059701492537,
722
+ "grad_norm": 0.49984909528425026,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.5683,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.4119402985074627,
729
+ "grad_norm": 0.44986277151799875,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.5616,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.435820895522388,
736
+ "grad_norm": 0.48588485615374555,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.5607,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.4597014925373135,
743
+ "grad_norm": 0.48231851620423527,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.564,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.4835820895522387,
750
+ "grad_norm": 0.5353905043801261,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.572,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.5074626865671643,
757
+ "grad_norm": 0.4911575383473398,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.561,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.5313432835820895,
764
+ "grad_norm": 0.5322320223748976,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.5702,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.5552238805970147,
771
+ "grad_norm": 0.47802103841875787,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.5648,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.5791044776119403,
778
+ "grad_norm": 0.5461878411480141,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.5699,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.602985074626866,
785
+ "grad_norm": 0.5723521540745492,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.5687,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.626865671641791,
792
+ "grad_norm": 0.43486752386685085,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.5647,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.6507462686567163,
799
+ "grad_norm": 0.4851163868024419,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.5628,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.674626865671642,
806
+ "grad_norm": 0.4819830185138904,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.5672,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.698507462686567,
813
+ "grad_norm": 0.4782708772767338,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.5715,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.7223880597014927,
820
+ "grad_norm": 0.4564853695633748,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.5664,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.746268656716418,
827
+ "grad_norm": 0.5672636342724084,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.5703,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.7701492537313435,
834
+ "grad_norm": 0.46200475373217254,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.568,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.7940298507462686,
841
+ "grad_norm": 0.439779919962293,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.5617,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.817910447761194,
848
+ "grad_norm": 0.48759282182632596,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.5632,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.8417910447761194,
855
+ "grad_norm": 0.5417263063839436,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.5659,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.8656716417910446,
862
+ "grad_norm": 0.4780631102145764,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.5677,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.8895522388059702,
869
+ "grad_norm": 0.500379213535652,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.5756,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.9134328358208954,
876
+ "grad_norm": 0.5402151963225374,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.5686,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.937313432835821,
883
+ "grad_norm": 0.4522864472397569,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.5734,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.961194029850746,
890
+ "grad_norm": 0.4647996850215528,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.5699,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.9850746268656714,
897
+ "grad_norm": 0.4918905334543915,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.5716,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.9946268656716417,
904
+ "eval_loss": 0.636893630027771,
905
+ "eval_runtime": 143.3398,
906
+ "eval_samples_per_second": 78.722,
907
+ "eval_steps_per_second": 0.621,
908
+ "step": 1254
909
+ },
910
+ {
911
+ "epoch": 2.9946268656716417,
912
+ "step": 1254,
913
+ "total_flos": 2100077946470400.0,
914
+ "train_loss": 0.6183488205479283,
915
+ "train_runtime": 21046.2129,
916
+ "train_samples_per_second": 30.56,
917
+ "train_steps_per_second": 0.06
918
+ }
919
+ ],
920
+ "logging_steps": 10,
921
+ "max_steps": 1254,
922
+ "num_input_tokens_seen": 0,
923
+ "num_train_epochs": 3,
924
+ "save_steps": 500,
925
+ "stateful_callbacks": {
926
+ "TrainerControl": {
927
+ "args": {
928
+ "should_epoch_stop": false,
929
+ "should_evaluate": false,
930
+ "should_log": false,
931
+ "should_save": true,
932
+ "should_training_stop": true
933
+ },
934
+ "attributes": {}
935
+ }
936
+ },
937
+ "total_flos": 2100077946470400.0,
938
+ "train_batch_size": 8,
939
+ "trial_name": null,
940
+ "trial_params": null
941
+ }
training_eval_loss.png ADDED
training_loss.png ADDED