aleegis09 commited on
Commit
feccfb3
·
verified ·
1 Parent(s): 1273a31

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:843121274a7c3b629c98b62c4fcf93672503e4afa2dd2ae2f50353ccdcee6a7d
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c2c0234d9c935b7b019be2c870ddb501bbc79df41215051d0fb277562ba8cb
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a8846062100bbe1013c3dc0e1e2fc05f2b25c7e35b84f3c0146a5c01842e5c7
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de21782f48c59df6f3dc9cd06c3bda640efae4bbe6da1bbe8c26c3a5e381e9b6
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4f6bef4ff30dd9c98931d912b97f5a04c264a19bc6d85352349670aeb5866ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58ea3121b5db61f9bf017e4c88e2feaffedec3b876fdaa4d53a11244caef90c9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.2046091556549072,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.09090909090909091,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -198,6 +198,189 @@
198
  "eval_samples_per_second": 27.874,
199
  "eval_steps_per_second": 3.492,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +404,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 1.7773608566784e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0614235401153564,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.18181818181818182,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 27.874,
199
  "eval_steps_per_second": 3.492,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.09454545454545454,
204
+ "grad_norm": 2.232198476791382,
205
+ "learning_rate": 5.522642316338268e-05,
206
+ "loss": 2.3027,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.09818181818181818,
211
+ "grad_norm": 2.7883410453796387,
212
+ "learning_rate": 5.174497483512506e-05,
213
+ "loss": 2.443,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.10181818181818182,
218
+ "grad_norm": 2.533133029937744,
219
+ "learning_rate": 4.825502516487497e-05,
220
+ "loss": 2.4495,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.10545454545454545,
225
+ "grad_norm": 2.0543668270111084,
226
+ "learning_rate": 4.477357683661734e-05,
227
+ "loss": 1.9154,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.10909090909090909,
232
+ "grad_norm": 2.120340585708618,
233
+ "learning_rate": 4.131759111665349e-05,
234
+ "loss": 1.9321,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.11272727272727273,
239
+ "grad_norm": 2.3573496341705322,
240
+ "learning_rate": 3.790390522001662e-05,
241
+ "loss": 2.2358,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.11636363636363636,
246
+ "grad_norm": 2.295992851257324,
247
+ "learning_rate": 3.4549150281252636e-05,
248
+ "loss": 2.1238,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.12,
253
+ "grad_norm": 2.4279768466949463,
254
+ "learning_rate": 3.12696703292044e-05,
255
+ "loss": 2.3682,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.12363636363636364,
260
+ "grad_norm": 2.529550313949585,
261
+ "learning_rate": 2.8081442660546125e-05,
262
+ "loss": 2.209,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.12727272727272726,
267
+ "grad_norm": 2.266796350479126,
268
+ "learning_rate": 2.500000000000001e-05,
269
+ "loss": 2.1055,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.13090909090909092,
274
+ "grad_norm": 2.4525721073150635,
275
+ "learning_rate": 2.2040354826462668e-05,
276
+ "loss": 2.1957,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.13454545454545455,
281
+ "grad_norm": 1.8528436422348022,
282
+ "learning_rate": 1.9216926233717085e-05,
283
+ "loss": 1.8631,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.13818181818181818,
288
+ "grad_norm": 1.8262501955032349,
289
+ "learning_rate": 1.6543469682057106e-05,
290
+ "loss": 2.0233,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.14181818181818182,
295
+ "grad_norm": 2.080160617828369,
296
+ "learning_rate": 1.4033009983067452e-05,
297
+ "loss": 1.884,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.14545454545454545,
302
+ "grad_norm": 2.064708709716797,
303
+ "learning_rate": 1.1697777844051105e-05,
304
+ "loss": 2.0776,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.14909090909090908,
309
+ "grad_norm": 2.0797815322875977,
310
+ "learning_rate": 9.549150281252633e-06,
311
+ "loss": 2.0999,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.15272727272727274,
316
+ "grad_norm": 2.636698007583618,
317
+ "learning_rate": 7.597595192178702e-06,
318
+ "loss": 2.0736,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.15636363636363637,
323
+ "grad_norm": 3.001413345336914,
324
+ "learning_rate": 5.852620357053651e-06,
325
+ "loss": 2.1067,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.16,
330
+ "grad_norm": 2.8234450817108154,
331
+ "learning_rate": 4.322727117869951e-06,
332
+ "loss": 2.7408,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.16363636363636364,
337
+ "grad_norm": 2.3741395473480225,
338
+ "learning_rate": 3.0153689607045845e-06,
339
+ "loss": 2.0327,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.16727272727272727,
344
+ "grad_norm": 2.951899290084839,
345
+ "learning_rate": 1.9369152030840556e-06,
346
+ "loss": 2.312,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.1709090909090909,
351
+ "grad_norm": 3.7195920944213867,
352
+ "learning_rate": 1.0926199633097157e-06,
353
+ "loss": 1.9652,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.17454545454545456,
358
+ "grad_norm": 3.5826423168182373,
359
+ "learning_rate": 4.865965629214819e-07,
360
+ "loss": 2.4803,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.1781818181818182,
365
+ "grad_norm": 3.770677328109741,
366
+ "learning_rate": 1.2179748700879012e-07,
367
+ "loss": 2.265,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.18181818181818182,
372
+ "grad_norm": 5.106058120727539,
373
+ "learning_rate": 0.0,
374
+ "loss": 2.3384,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.18181818181818182,
379
+ "eval_loss": 2.0614235401153564,
380
+ "eval_runtime": 16.6414,
381
+ "eval_samples_per_second": 27.822,
382
+ "eval_steps_per_second": 3.485,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
+ "should_training_stop": true
408
  },
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 3.5547217133568e+16,
413
  "train_batch_size": 8,
414
  "trial_name": null,
415
  "trial_params": null