Hugging Face's logo

Dnsx077
/
fe55c49d-7ea6-45c5-91aa-2cc3bd1b9d82

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
Dnsx077 commited on
Commit
eabf523
·
verified ·
1 Parent(s): 60e3cbc

Training in progress, step 50, checkpoint

Browse files
Files changed (4) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/rng_state.pth +1 -1
  3. last-checkpoint/scheduler.pt +1 -1
  4. last-checkpoint/trainer_state.json +188 -5
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87423e0cf3b3cd963fe40fb99bfd4d3f9dc6247ff88ba91ab1cd48930b07d93e
3
  size 90365754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5faef0e34efad45fc7a93c3a540cf60e901d895d661c2e572b6e305d2de6e5a
3
  size 90365754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cab3b52bf979688e48d0ee4791f47293b7332f98d091655f1f6a221fdf1d58bd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dec293a7cb0ae2b3e9ebbc2b84631c43262dabb790f911c71cbfd22db5004ac
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.0008095592759301836,
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": 10.399,
199
  "eval_steps_per_second": 5.2,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -212,7 +395,7 @@
212
  "early_stopping_threshold": 0.0
213
  },
214
  "attributes": {
215
- "early_stopping_patience_counter": 0
216
  }
217
  },
218
  "TrainerControl": {
@@ -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": 4838612847820800.0,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.0016191185518603672,
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": 10.399,
199
  "eval_steps_per_second": 5.2,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.0008419416469673909,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 0.0001,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.0008743240180045982,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 9.345968707698569e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.0009067063890418057,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 8.694738077799488e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.000939088760079013,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 8.049096779838719e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.0009714711311162203,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 7.411809548974792e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.0010038535021534276,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 6.785605346968386e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.001036235873190635,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 6.173165676349103e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.0010686182442278423,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 5.577113097809989e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.0011010006152650496,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 5.000000000000002e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.0011333829863022572,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 4.444297669803981e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.0011657653573394645,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 3.9123857099127936e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.0011981477283766718,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 3.406541848999312e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.0012305300994138791,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 2.9289321881345254e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.0012629124704510864,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 2.4816019252102273e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.0012952948414882938,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 2.0664665970876496e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.001327677212525501,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 1.6853038769745467e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.0013600595835627084,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 1.339745962155613e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.0013924419545999157,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 1.0312725846731175e-05,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.001424824325637123,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 7.612046748871327e-06,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.0014572066966743306,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 5.306987050489442e-06,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.001489589067711538,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 3.40741737109318e-06,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.0015219714387487452,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 1.921471959676957e-06,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.0015543538097859526,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 8.555138626189618e-07,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.0015867361808231599,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 2.141076761396521e-07,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.0016191185518603672,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0016191185518603672,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 1250.3413,
381
+ "eval_samples_per_second": 10.4,
382
+ "eval_steps_per_second": 5.2,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
395
  "early_stopping_threshold": 0.0
396
  },
397
  "attributes": {
398
+ "early_stopping_patience_counter": 1
399
  }
400
  },
401
  "TrainerControl": {
 
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": 9677225695641600.0,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null