Hugging Face's logo

moos124
/
code-reasoning-0.5b

Transformers
Safetensors
Generated from Trainer
trl
hf_jobs
sft
Model card Files
xet
 Community
moos124 commited on
Commit
1ca4668
·
verified ·
1 Parent(s): 57c8731

Training in progress, step 3600, checkpoint

Browse files
Files changed (5) 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/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +13 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19f24cac5e831ed8e001438af1b550ef4d490c5ca40c2109fbb0baa8b034ea0c
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152e53012d9ed3cb9f5e37a874adf919e2b719bab34a3dd4e526125288289e39
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0322edbb159fe7e634196474c2aa629c346313cccce165c4ca1eaf947c915756
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd4cabb40c53905126ecaeaec0630954ad64f73a7c104726dd717828c5d2f4c
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bffc29469a12bb508beb45d01233b39925a4be0672172c7531ac8100b8b95e2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4af866f2b7f322f01e693aa3824250720cb08de1436cc21533c30d7d8e278d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c054f30f0fd08a2666abbe4a3c60f5f0356120818c2a21d22b3f600f03165cb
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27954431a2d12eaf65dd13bc9a9c77bee86311fa930834d281d825ef3480e985
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.7658666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3590,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3608,6 +3608,16 @@
3608
  "mean_token_accuracy": 0.7747991606593132,
3609
  "num_tokens": 16709398.0,
3610
  "step": 3590
 
 
 
 
 
 
 
 
 
 
3611
  }
3612
  ],
3613
  "logging_steps": 10,
@@ -3627,7 +3637,7 @@
3627
  "attributes": {}
3628
  }
3629
  },
3630
- "total_flos": 7.918068432112742e+16,
3631
  "train_batch_size": 4,
3632
  "trial_name": null,
3633
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.768,
6
  "eval_steps": 500,
7
+ "global_step": 3600,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3608
  "mean_token_accuracy": 0.7747991606593132,
3609
  "num_tokens": 16709398.0,
3610
  "step": 3590
3611
+ },
3612
+ {
3613
+ "entropy": 0.9047524333000183,
3614
+ "epoch": 0.768,
3615
+ "grad_norm": 0.23355495929718018,
3616
+ "learning_rate": 7.079221624179623e-05,
3617
+ "loss": 0.9877220153808594,
3618
+ "mean_token_accuracy": 0.7743734329938888,
3619
+ "num_tokens": 16759830.0,
3620
+ "step": 3600
3621
  }
3622
  ],
3623
  "logging_steps": 10,
 
3637
  "attributes": {}
3638
  }
3639
  },
3640
+ "total_flos": 7.941254167832064e+16,
3641
  "train_batch_size": 4,
3642
  "trial_name": null,
3643
  "trial_params": null