Hugging Face's logo

anhdai312
/
math6

Transformers
Safetensors
Generated from Trainer
unsloth
trl
sft
Model card Files
xet
 Community
anhdai312 commited on
Commit
f5f53b8
·
verified ·
1 Parent(s): 3c824b2

Training in progress, step 60, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +85 -7
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f05f2e30c71514edaef4052a0f97817810d3934c16b60b0484221a4bb357b5
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36a81b0f1c28f8e8d50574b5ee09f780004a9dcb49906974969a5f6187b268d
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc9d2830cd1feda2dba6daa23dd6681e2db56238df036ba92dad6534ce474360
3
  size 18813829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a34ab3c490958eb351eb1b914cb18839cd94f34d71fbd9a78b3737396019056
3
  size 18813829
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d6d8fafcd1ee268414be5acf0366296af5b03d60871978712eac1979cb42d65
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89645f9f6a2a8823b334e0748e4f5ea683a27b3d02632f0a241397db55d82fad
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cd0e9d505fbc3f97feb166d29026132bdf14eb3e5c7ff77beebc303ee666f96
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c146ae1cf47c9929c1f0cc98e903ce1070f0c3ea64421f26971b053d42844b7
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73237befb0f6c84dda182d7ec74c57320cd4d602fd2de223cb47f56d5c9e8c5e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd468a12037943abc731ea6bb19f58d78121bbf9a8793bca485cff41de78943
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 50,
3
- "best_metric": 2.1459906101226807,
4
- "best_model_checkpoint": "/tmp/checkpoints_/job_2d7db242-d10c-4b68-8580-8faf9983d2ac/checkpoint-50",
5
- "epoch": 2.5,
6
  "eval_steps": 50,
7
- "global_step": 50,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -366,6 +366,84 @@
366
  "eval_samples_per_second": 24.835,
367
  "eval_steps_per_second": 7.451,
368
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
369
  }
370
  ],
371
  "logging_steps": 1,
@@ -380,12 +458,12 @@
380
  "should_evaluate": false,
381
  "should_log": false,
382
  "should_save": true,
383
- "should_training_stop": false
384
  },
385
  "attributes": {}
386
  }
387
  },
388
- "total_flos": 121762246448640.0,
389
  "train_batch_size": 1,
390
  "trial_name": null,
391
  "trial_params": null
 
1
  {
2
+ "best_global_step": 60,
3
+ "best_metric": 2.1111679077148438,
4
+ "best_model_checkpoint": "/tmp/checkpoints_/job_2d7db242-d10c-4b68-8580-8faf9983d2ac/checkpoint-60",
5
+ "epoch": 3.0,
6
  "eval_steps": 50,
7
+ "global_step": 60,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
366
  "eval_samples_per_second": 24.835,
367
  "eval_steps_per_second": 7.451,
368
  "step": 50
369
+ },
370
+ {
371
+ "epoch": 2.55,
372
+ "grad_norm": 3.0704660415649414,
373
+ "learning_rate": 3.6363636363636366e-06,
374
+ "loss": 2.046316146850586,
375
+ "step": 51
376
+ },
377
+ {
378
+ "epoch": 2.6,
379
+ "grad_norm": 3.510226249694824,
380
+ "learning_rate": 3.272727272727273e-06,
381
+ "loss": 2.2383902072906494,
382
+ "step": 52
383
+ },
384
+ {
385
+ "epoch": 2.65,
386
+ "grad_norm": 2.91780686378479,
387
+ "learning_rate": 2.9090909090909093e-06,
388
+ "loss": 2.0489413738250732,
389
+ "step": 53
390
+ },
391
+ {
392
+ "epoch": 2.7,
393
+ "grad_norm": 2.8892462253570557,
394
+ "learning_rate": 2.5454545454545456e-06,
395
+ "loss": 2.042137384414673,
396
+ "step": 54
397
+ },
398
+ {
399
+ "epoch": 2.75,
400
+ "grad_norm": 2.9248545169830322,
401
+ "learning_rate": 2.181818181818182e-06,
402
+ "loss": 2.2285079956054688,
403
+ "step": 55
404
+ },
405
+ {
406
+ "epoch": 2.8,
407
+ "grad_norm": 3.120967149734497,
408
+ "learning_rate": 1.8181818181818183e-06,
409
+ "loss": 2.1922335624694824,
410
+ "step": 56
411
+ },
412
+ {
413
+ "epoch": 2.85,
414
+ "grad_norm": 2.938640594482422,
415
+ "learning_rate": 1.4545454545454546e-06,
416
+ "loss": 2.115161895751953,
417
+ "step": 57
418
+ },
419
+ {
420
+ "epoch": 2.9,
421
+ "grad_norm": 3.638606309890747,
422
+ "learning_rate": 1.090909090909091e-06,
423
+ "loss": 2.0304441452026367,
424
+ "step": 58
425
+ },
426
+ {
427
+ "epoch": 2.95,
428
+ "grad_norm": 3.6058709621429443,
429
+ "learning_rate": 7.272727272727273e-07,
430
+ "loss": 2.1807315349578857,
431
+ "step": 59
432
+ },
433
+ {
434
+ "epoch": 3.0,
435
+ "grad_norm": 3.680497407913208,
436
+ "learning_rate": 3.6363636363636366e-07,
437
+ "loss": 2.085890769958496,
438
+ "step": 60
439
+ },
440
+ {
441
+ "epoch": 3.0,
442
+ "eval_loss": 2.1111679077148438,
443
+ "eval_runtime": 0.3942,
444
+ "eval_samples_per_second": 25.367,
445
+ "eval_steps_per_second": 7.61,
446
+ "step": 60
447
  }
448
  ],
449
  "logging_steps": 1,
 
458
  "should_evaluate": false,
459
  "should_log": false,
460
  "should_save": true,
461
+ "should_training_stop": true
462
  },
463
  "attributes": {}
464
  }
465
  },
466
+ "total_flos": 146320632391680.0,
467
  "train_batch_size": 1,
468
  "trial_name": null,
469
  "trial_params": null