Hugging Face's logo

YL95
/
copa_v_wright_CPT_mistral_file_folder_path_checkpoint

Transformers
Safetensors
English
text-generation-inference
unsloth
mistral
trl
Model card Files
xet
 Community
YL95 commited on
Commit
717ddcf
·
verified ·
1 Parent(s): acaa903

training state at step 25

Browse files
Files changed (1) hide show
  1. trainer_state.json +78 -3
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.27586206896551724,
5
  "eval_steps": 1,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -292,6 +292,81 @@
292
  "eval_samples_per_second": 1.132,
293
  "eval_steps_per_second": 0.566,
294
  "step": 19
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
295
  }
296
  ],
297
  "logging_steps": 1,
@@ -311,7 +386,7 @@
311
  "attributes": {}
312
  }
313
  },
314
- "total_flos": 2.4706263096016896e+16,
315
  "train_batch_size": 2,
316
  "trial_name": null,
317
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3448275862068966,
5
  "eval_steps": 1,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
292
  "eval_samples_per_second": 1.132,
293
  "eval_steps_per_second": 0.566,
294
  "step": 19
295
+ },
296
+ {
297
+ "epoch": 0.27586206896551724,
298
+ "grad_norm": 2.390448570251465,
299
+ "learning_rate": 4.545454545454546e-05,
300
+ "loss": 1.7181,
301
+ "step": 20
302
+ },
303
+ {
304
+ "epoch": 0.27586206896551724,
305
+ "eval_loss": 1.126497507095337,
306
+ "eval_runtime": 17.9736,
307
+ "eval_samples_per_second": 1.113,
308
+ "eval_steps_per_second": 0.556,
309
+ "step": 20
310
+ },
311
+ {
312
+ "epoch": 0.2896551724137931,
313
+ "grad_norm": 2.3728342056274414,
314
+ "learning_rate": 4.772727272727273e-05,
315
+ "loss": 1.4155,
316
+ "step": 21
317
+ },
318
+ {
319
+ "epoch": 0.2896551724137931,
320
+ "eval_loss": 1.09345281124115,
321
+ "eval_runtime": 17.8283,
322
+ "eval_samples_per_second": 1.122,
323
+ "eval_steps_per_second": 0.561,
324
+ "step": 21
325
+ },
326
+ {
327
+ "epoch": 0.30344827586206896,
328
+ "grad_norm": 2.4872097969055176,
329
+ "learning_rate": 5e-05,
330
+ "loss": 1.3752,
331
+ "step": 22
332
+ },
333
+ {
334
+ "epoch": 0.30344827586206896,
335
+ "eval_loss": 1.0705276727676392,
336
+ "eval_runtime": 17.6481,
337
+ "eval_samples_per_second": 1.133,
338
+ "eval_steps_per_second": 0.567,
339
+ "step": 22
340
+ },
341
+ {
342
+ "epoch": 0.31724137931034485,
343
+ "grad_norm": 2.953234910964966,
344
+ "learning_rate": 4.999672209164081e-05,
345
+ "loss": 1.4449,
346
+ "step": 23
347
+ },
348
+ {
349
+ "epoch": 0.31724137931034485,
350
+ "eval_loss": 1.0468412637710571,
351
+ "eval_runtime": 17.6053,
352
+ "eval_samples_per_second": 1.136,
353
+ "eval_steps_per_second": 0.568,
354
+ "step": 23
355
+ },
356
+ {
357
+ "epoch": 0.3310344827586207,
358
+ "grad_norm": 2.47603702545166,
359
+ "learning_rate": 4.998688922613788e-05,
360
+ "loss": 1.4286,
361
+ "step": 24
362
+ },
363
+ {
364
+ "epoch": 0.3310344827586207,
365
+ "eval_loss": 1.0292497873306274,
366
+ "eval_runtime": 17.5777,
367
+ "eval_samples_per_second": 1.138,
368
+ "eval_steps_per_second": 0.569,
369
+ "step": 24
370
  }
371
  ],
372
  "logging_steps": 1,
 
386
  "attributes": {}
387
  }
388
  },
389
+ "total_flos": 3.128103443541197e+16,
390
  "train_batch_size": 2,
391
  "trial_name": null,
392
  "trial_params": null