ljcamargo commited on
Commit
f9e66a5
·
verified ·
1 Parent(s): edfecf3

Training in progress, step 500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:713314fbb852d3681bdd457c456fa92a5a4b8f17efc7bc30d7fc0ec6809d1ff5
3
  size 3237829088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6737088db9e98673fb773f1a59f6d3462831ce3df34f251e3fa0a12870dd15
3
  size 3237829088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbccf36e4132dbd5bfad71a220b9bc80d7b97ebac7515e599e55da6e4237b7ec
3
- size 2061569879
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0fb8cc13677d7d807a121c2184df8b603bb0d1169d3cfd53c15fe292d8e835b
3
+ size 2061570519
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ddcedc173fc7bb8e4ee485559862a6e8da9544760dc1271958b7826bc1aa45c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b7bf30711c780cfc00bf1d7e9073a2f0212cb8ee4f14b6ced8cf97508142e3
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dde406fb39dc0bbced01120a84cbcd1c773bea6ac49dca8cecd1a0e473d9d2af
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff58b41c3672e659a0eb46d9ed11a0ca17415e7a2643a3ddfbaebb9f4e67f8f
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dcd7c5d64c278e09f29d8b235153f3bb9756409cbc039ad08add43eb299009c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262af81f2f23d66f087a6f7b0eea32e3dba253538f0517c5799e48488478b90c
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,48 +2,734 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.003826286588865506,
6
- "eval_steps": 10,
7
- "global_step": 10,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "epoch": 0.001913143294432753,
14
- "grad_norm": 427.26959228515625,
15
- "learning_rate": 1.9230769230769234e-06,
16
- "loss": 13.9595,
17
  "step": 5
18
  },
19
  {
20
- "epoch": 0.003826286588865506,
21
- "grad_norm": 119.46376037597656,
22
- "learning_rate": 1.153846153846154e-05,
23
- "loss": 10.2278,
24
  "step": 10
25
  },
26
  {
27
- "epoch": 0.003826286588865506,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "eval_avg_tokens": 300.0,
29
  "eval_code": 0.0,
30
  "eval_exact": 0.0,
31
  "eval_family": 0.0,
32
- "eval_loss": 7.974108695983887,
33
- "eval_runtime": 177.0011,
34
  "eval_samples": 300,
35
- "eval_samples_per_second": 1.695,
36
- "eval_steps_per_second": 1.695,
37
  "eval_super": 0.0,
38
  "eval_total_tokens": 90000,
39
- "step": 10
40
  }
41
  ],
42
  "logging_steps": 5,
43
- "max_steps": 2614,
44
  "num_input_tokens_seen": 0,
45
  "num_train_epochs": 1,
46
- "save_steps": 10,
47
  "stateful_callbacks": {
48
  "TrainerControl": {
49
  "args": {
@@ -56,8 +742,8 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 5.455843688448e+17,
60
- "train_batch_size": 8,
61
  "trial_name": null,
62
  "trial_params": null
63
  }
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.14349261013057826,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "epoch": 0.0014349261013057828,
14
+ "grad_norm": 391.24395751953125,
15
+ "learning_rate": 2.898550724637681e-06,
16
+ "loss": 13.9544,
17
  "step": 5
18
  },
19
  {
20
+ "epoch": 0.0028698522026115655,
21
+ "grad_norm": 169.8328399658203,
22
+ "learning_rate": 1.739130434782609e-05,
23
+ "loss": 10.071,
24
  "step": 10
25
  },
26
  {
27
+ "epoch": 0.004304778303917348,
28
+ "grad_norm": 252.62840270996094,
29
+ "learning_rate": 3.188405797101449e-05,
30
+ "loss": 8.0348,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.005739704405223131,
35
+ "grad_norm": 41.308902740478516,
36
+ "learning_rate": 4.63768115942029e-05,
37
+ "loss": 7.6824,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.007174630506528914,
42
+ "grad_norm": 20.71501922607422,
43
+ "learning_rate": 6.086956521739131e-05,
44
+ "loss": 6.5785,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.008609556607834697,
49
+ "grad_norm": 28.731815338134766,
50
+ "learning_rate": 7.536231884057971e-05,
51
+ "loss": 5.5247,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.01004448270914048,
56
+ "grad_norm": 13.58375358581543,
57
+ "learning_rate": 8.985507246376813e-05,
58
+ "loss": 4.0724,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.011479408810446262,
63
+ "grad_norm": 29.017719268798828,
64
+ "learning_rate": 0.00010434782608695653,
65
+ "loss": 3.0084,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.012914334911752045,
70
+ "grad_norm": 32.97686767578125,
71
+ "learning_rate": 0.00011884057971014493,
72
+ "loss": 3.2098,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.014349261013057828,
77
+ "grad_norm": 9.631165504455566,
78
+ "learning_rate": 0.00013333333333333334,
79
+ "loss": 2.8009,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.01578418711436361,
84
+ "grad_norm": 7.5439629554748535,
85
+ "learning_rate": 0.00014782608695652173,
86
+ "loss": 2.6667,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.017219113215669393,
91
+ "grad_norm": 30.146381378173828,
92
+ "learning_rate": 0.00016231884057971017,
93
+ "loss": 2.4567,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.018654039316975176,
98
+ "grad_norm": 9.834168434143066,
99
+ "learning_rate": 0.00017681159420289858,
100
+ "loss": 2.6511,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.02008896541828096,
105
+ "grad_norm": 8.466848373413086,
106
+ "learning_rate": 0.00019130434782608697,
107
+ "loss": 2.4647,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.02152389151958674,
112
+ "grad_norm": 15.979572296142578,
113
+ "learning_rate": 0.00019999983084147306,
114
+ "loss": 2.4322,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.022958817620892524,
119
+ "grad_norm": 8.879189491271973,
120
+ "learning_rate": 0.00019999792781461744,
121
+ "loss": 2.0723,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.024393743722198307,
126
+ "grad_norm": 7.873000144958496,
127
+ "learning_rate": 0.00019999391035312072,
128
+ "loss": 2.0487,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.02582866982350409,
133
+ "grad_norm": 7.232510089874268,
134
+ "learning_rate": 0.0001999877785419313,
135
+ "loss": 1.9332,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.027263595924809873,
140
+ "grad_norm": 7.322793483734131,
141
+ "learning_rate": 0.00019997953251070497,
142
+ "loss": 1.9108,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.028698522026115655,
147
+ "grad_norm": 8.617932319641113,
148
+ "learning_rate": 0.0001999691724338023,
149
+ "loss": 1.8038,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.030133448127421438,
154
+ "grad_norm": 7.669059753417969,
155
+ "learning_rate": 0.00019995669853028485,
156
+ "loss": 1.9083,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.03156837422872722,
161
+ "grad_norm": 10.190857887268066,
162
+ "learning_rate": 0.0001999421110639107,
163
+ "loss": 1.9832,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.033003300330033,
168
+ "grad_norm": 9.29393196105957,
169
+ "learning_rate": 0.0001999254103431286,
170
+ "loss": 1.8482,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.034438226431338786,
175
+ "grad_norm": 10.318120002746582,
176
+ "learning_rate": 0.00019990659672107177,
177
+ "loss": 1.8904,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.035873152532644566,
182
+ "grad_norm": 7.800939559936523,
183
+ "learning_rate": 0.00019988567059555013,
184
+ "loss": 1.756,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.03730807863395035,
189
+ "grad_norm": 6.906073093414307,
190
+ "learning_rate": 0.00019986263240904216,
191
+ "loss": 1.8059,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.03874300473525613,
196
+ "grad_norm": 9.81100845336914,
197
+ "learning_rate": 0.00019983748264868528,
198
+ "loss": 1.6887,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.04017793083656192,
203
+ "grad_norm": 11.59725570678711,
204
+ "learning_rate": 0.00019981022184626578,
205
+ "loss": 1.6778,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.0416128569378677,
210
+ "grad_norm": 7.840384006500244,
211
+ "learning_rate": 0.0001997808505782075,
212
+ "loss": 1.6421,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.04304778303917348,
217
+ "grad_norm": 10.421500205993652,
218
+ "learning_rate": 0.00019974936946555948,
219
+ "loss": 1.7217,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.04448270914047926,
224
+ "grad_norm": 8.085160255432129,
225
+ "learning_rate": 0.00019971577917398317,
226
+ "loss": 1.4836,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.04591763524178505,
231
+ "grad_norm": 7.500054836273193,
232
+ "learning_rate": 0.000199680080413738,
233
+ "loss": 1.6914,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.04735256134309083,
238
+ "grad_norm": 9.05443286895752,
239
+ "learning_rate": 0.00019964227393966656,
240
+ "loss": 1.6051,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.048787487444396614,
245
+ "grad_norm": 10.235902786254883,
246
+ "learning_rate": 0.0001996023605511786,
247
+ "loss": 1.5247,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.05022241354570239,
252
+ "grad_norm": 10.63776969909668,
253
+ "learning_rate": 0.00019956034109223415,
254
+ "loss": 1.412,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.05165733964700818,
259
+ "grad_norm": 6.892467498779297,
260
+ "learning_rate": 0.00019951621645132556,
261
+ "loss": 1.5032,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.05309226574831396,
266
+ "grad_norm": 9.97953987121582,
267
+ "learning_rate": 0.0001994699875614589,
268
+ "loss": 1.4722,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.054527191849619745,
273
+ "grad_norm": 8.126319885253906,
274
+ "learning_rate": 0.00019942165540013412,
275
+ "loss": 1.3494,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.055962117950925525,
280
+ "grad_norm": 10.368117332458496,
281
+ "learning_rate": 0.00019937122098932428,
282
+ "loss": 1.3037,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.05739704405223131,
287
+ "grad_norm": 11.593148231506348,
288
+ "learning_rate": 0.00019931868539545416,
289
+ "loss": 1.2657,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.05883197015353709,
294
+ "grad_norm": 11.356983184814453,
295
+ "learning_rate": 0.0001992640497293776,
296
+ "loss": 1.3293,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.060266896254842876,
301
+ "grad_norm": 11.849316596984863,
302
+ "learning_rate": 0.00019920731514635396,
303
+ "loss": 1.38,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.061701822356148656,
308
+ "grad_norm": 25.30244255065918,
309
+ "learning_rate": 0.0001991484828460238,
310
+ "loss": 1.3061,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.06313674845745444,
315
+ "grad_norm": 12.974631309509277,
316
+ "learning_rate": 0.00019908755407238343,
317
+ "loss": 1.2302,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.06457167455876023,
322
+ "grad_norm": 11.322882652282715,
323
+ "learning_rate": 0.00019902453011375865,
324
+ "loss": 1.364,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.066006600660066,
329
+ "grad_norm": 7.863698959350586,
330
+ "learning_rate": 0.00019895941230277744,
331
+ "loss": 1.3096,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.06744152676137179,
336
+ "grad_norm": 13.481120109558105,
337
+ "learning_rate": 0.00019889220201634193,
338
+ "loss": 1.2259,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.06887645286267757,
343
+ "grad_norm": 15.518793106079102,
344
+ "learning_rate": 0.00019882290067559915,
345
+ "loss": 1.2618,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.07031137896398336,
350
+ "grad_norm": 8.889978408813477,
351
+ "learning_rate": 0.000198751509745911,
352
+ "loss": 1.259,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.07174630506528913,
357
+ "grad_norm": 12.910364151000977,
358
+ "learning_rate": 0.0001986780307368233,
359
+ "loss": 1.1288,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.07318123116659492,
364
+ "grad_norm": 9.42977523803711,
365
+ "learning_rate": 0.0001986024652020339,
366
+ "loss": 1.1097,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.0746161572679007,
371
+ "grad_norm": 16.449186325073242,
372
+ "learning_rate": 0.00019852481473935974,
373
+ "loss": 1.0025,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.07605108336920649,
378
+ "grad_norm": 19.828948974609375,
379
+ "learning_rate": 0.0001984450809907031,
380
+ "loss": 1.0597,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.07748600947051226,
385
+ "grad_norm": 27.04888153076172,
386
+ "learning_rate": 0.000198363265642017,
387
+ "loss": 1.092,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.07892093557181805,
392
+ "grad_norm": 27.228042602539062,
393
+ "learning_rate": 0.00019827937042326928,
394
+ "loss": 1.1886,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.08035586167312384,
399
+ "grad_norm": 9.512433052062988,
400
+ "learning_rate": 0.00019819339710840626,
401
+ "loss": 1.127,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.08179078777442962,
406
+ "grad_norm": 26.35071563720703,
407
+ "learning_rate": 0.00019810534751531523,
408
+ "loss": 1.0337,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.0832257138757354,
413
+ "grad_norm": 9.270747184753418,
414
+ "learning_rate": 0.00019801522350578577,
415
+ "loss": 1.0625,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.08466063997704118,
420
+ "grad_norm": 13.372587203979492,
421
+ "learning_rate": 0.00019792302698547077,
422
+ "loss": 1.0753,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.08609556607834697,
427
+ "grad_norm": 27.558691024780273,
428
+ "learning_rate": 0.00019782875990384568,
429
+ "loss": 1.0572,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.08753049217965275,
434
+ "grad_norm": 6.429300785064697,
435
+ "learning_rate": 0.00019773242425416768,
436
+ "loss": 1.0431,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.08896541828095852,
441
+ "grad_norm": 13.104458808898926,
442
+ "learning_rate": 0.00019763402207343338,
443
+ "loss": 1.0644,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.09040034438226431,
448
+ "grad_norm": 11.63284969329834,
449
+ "learning_rate": 0.0001975335554423356,
450
+ "loss": 1.0902,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.0918352704835701,
455
+ "grad_norm": 12.347888946533203,
456
+ "learning_rate": 0.00019743102648521967,
457
+ "loss": 0.9932,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.09327019658487588,
462
+ "grad_norm": 16.778013229370117,
463
+ "learning_rate": 0.00019732643737003827,
464
+ "loss": 0.967,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.09470512268618166,
469
+ "grad_norm": 12.950679779052734,
470
+ "learning_rate": 0.00019721979030830572,
471
+ "loss": 0.9775,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 0.09614004878748744,
476
+ "grad_norm": 21.43748664855957,
477
+ "learning_rate": 0.00019711108755505116,
478
+ "loss": 0.931,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 0.09757497488879323,
483
+ "grad_norm": 9.503966331481934,
484
+ "learning_rate": 0.0001970003314087709,
485
+ "loss": 1.0295,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 0.09900990099009901,
490
+ "grad_norm": 13.628849983215332,
491
+ "learning_rate": 0.0001968875242113798,
492
+ "loss": 0.9998,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 0.10044482709140479,
497
+ "grad_norm": 7.438472747802734,
498
+ "learning_rate": 0.0001967726683481617,
499
+ "loss": 0.9935,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 0.10187975319271057,
504
+ "grad_norm": 7.533242702484131,
505
+ "learning_rate": 0.00019665576624771917,
506
+ "loss": 1.0334,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 0.10331467929401636,
511
+ "grad_norm": 8.190099716186523,
512
+ "learning_rate": 0.00019653682038192188,
513
+ "loss": 0.9273,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 0.10474960539532215,
518
+ "grad_norm": 12.107589721679688,
519
+ "learning_rate": 0.0001964158332658545,
520
+ "loss": 0.9917,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 0.10618453149662792,
525
+ "grad_norm": 8.531739234924316,
526
+ "learning_rate": 0.00019629280745776364,
527
+ "loss": 0.8793,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 0.1076194575979337,
532
+ "grad_norm": 8.719773292541504,
533
+ "learning_rate": 0.00019616774555900342,
534
+ "loss": 1.0215,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 0.10905438369923949,
539
+ "grad_norm": 8.249613761901855,
540
+ "learning_rate": 0.0001960406502139808,
541
+ "loss": 0.9413,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 0.11048930980054528,
546
+ "grad_norm": 12.444363594055176,
547
+ "learning_rate": 0.0001959115241100994,
548
+ "loss": 0.9262,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 0.11192423590185105,
553
+ "grad_norm": 17.167621612548828,
554
+ "learning_rate": 0.00019578036997770296,
555
+ "loss": 0.9388,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 0.11335916200315684,
560
+ "grad_norm": 9.513605117797852,
561
+ "learning_rate": 0.00019564719059001734,
562
+ "loss": 0.904,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 0.11479408810446262,
567
+ "grad_norm": 42.635414123535156,
568
+ "learning_rate": 0.0001955119887630919,
569
+ "loss": 0.9174,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 0.11622901420576841,
574
+ "grad_norm": 18.625703811645508,
575
+ "learning_rate": 0.0001953747673557403,
576
+ "loss": 0.9849,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 0.11766394030707418,
581
+ "grad_norm": 12.731193542480469,
582
+ "learning_rate": 0.0001952355292694795,
583
+ "loss": 0.9476,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 0.11909886640837997,
588
+ "grad_norm": 16.935991287231445,
589
+ "learning_rate": 0.0001950942774484689,
590
+ "loss": 0.9683,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 0.12053379250968575,
595
+ "grad_norm": 7.0110249519348145,
596
+ "learning_rate": 0.0001949510148794478,
597
+ "loss": 1.0143,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 0.12196871861099154,
602
+ "grad_norm": 13.457725524902344,
603
+ "learning_rate": 0.0001948057445916724,
604
+ "loss": 0.9607,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 0.12340364471229731,
609
+ "grad_norm": 9.616328239440918,
610
+ "learning_rate": 0.00019465846965685158,
611
+ "loss": 0.9426,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 0.1248385708136031,
616
+ "grad_norm": 10.017128944396973,
617
+ "learning_rate": 0.0001945091931890822,
618
+ "loss": 0.9967,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 0.12627349691490888,
623
+ "grad_norm": 10.576837539672852,
624
+ "learning_rate": 0.00019435791834478293,
625
+ "loss": 1.0039,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 0.12770842301621466,
630
+ "grad_norm": 19.164012908935547,
631
+ "learning_rate": 0.0001942046483226278,
632
+ "loss": 0.9536,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 0.12914334911752046,
637
+ "grad_norm": 9.686524391174316,
638
+ "learning_rate": 0.0001940493863634784,
639
+ "loss": 0.8871,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 0.13057827521882623,
644
+ "grad_norm": 11.136150360107422,
645
+ "learning_rate": 0.00019389213575031543,
646
+ "loss": 1.0405,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 0.132013201320132,
651
+ "grad_norm": 7.720663070678711,
652
+ "learning_rate": 0.00019373289980816917,
653
+ "loss": 0.8974,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 0.1334481274214378,
658
+ "grad_norm": 7.253653526306152,
659
+ "learning_rate": 0.00019357168190404936,
660
+ "loss": 0.9455,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 0.13488305352274357,
665
+ "grad_norm": 14.146231651306152,
666
+ "learning_rate": 0.00019340848544687386,
667
+ "loss": 0.916,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 0.13631797962404937,
672
+ "grad_norm": 10.805950164794922,
673
+ "learning_rate": 0.00019324331388739658,
674
+ "loss": 0.9894,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 0.13775290572535515,
679
+ "grad_norm": 11.11950397491455,
680
+ "learning_rate": 0.00019307617071813454,
681
+ "loss": 1.0485,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 0.13918783182666092,
686
+ "grad_norm": 6.732795715332031,
687
+ "learning_rate": 0.0001929070594732941,
688
+ "loss": 0.9406,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 0.14062275792796672,
693
+ "grad_norm": 8.768498420715332,
694
+ "learning_rate": 0.00019273598372869603,
695
+ "loss": 0.9745,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 0.1420576840292725,
700
+ "grad_norm": 10.62530517578125,
701
+ "learning_rate": 0.00019256294710170017,
702
+ "loss": 0.9702,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 0.14349261013057826,
707
+ "grad_norm": 8.457195281982422,
708
+ "learning_rate": 0.0001923879532511287,
709
+ "loss": 0.9026,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 0.14349261013057826,
714
  "eval_avg_tokens": 300.0,
715
  "eval_code": 0.0,
716
  "eval_exact": 0.0,
717
  "eval_family": 0.0,
718
+ "eval_loss": 0.9469140768051147,
719
+ "eval_runtime": 173.8266,
720
  "eval_samples": 300,
721
+ "eval_samples_per_second": 1.726,
722
+ "eval_steps_per_second": 1.726,
723
  "eval_super": 0.0,
724
  "eval_total_tokens": 90000,
725
+ "step": 500
726
  }
727
  ],
728
  "logging_steps": 5,
729
+ "max_steps": 3485,
730
  "num_input_tokens_seen": 0,
731
  "num_train_epochs": 1,
732
+ "save_steps": 500,
733
  "stateful_callbacks": {
734
  "TrainerControl": {
735
  "args": {
 
742
  "attributes": {}
743
  }
744
  },
745
+ "total_flos": 2.045941383168e+19,
746
+ "train_batch_size": 6,
747
  "trial_name": null,
748
  "trial_params": null
749
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57daf0b268e8db59107450b9b389ae9a34cdc454dce4f97c225a22e1e1824297
3
- size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335603833df1126fe248b6fbecf339f53f5e5ae272c26e1fa729e348528f8cfc
3
+ size 6033