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
bcdfe02
·
verified ·
1 Parent(s): 7b6bff0

Training in progress, step 3590, 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:caa9b7c0a190c86f2695462813e725ed6169d7c326e76dbf137bd88402ae8cbe
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f24cac5e831ed8e001438af1b550ef4d490c5ca40c2109fbb0baa8b034ea0c
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cb9e092b3f120ee3aa810a1773d3cd2154dc52ef0aa15c04fa4f15a5e5e5099
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0322edbb159fe7e634196474c2aa629c346313cccce165c4ca1eaf947c915756
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:e75f99ba7404a13d285204d93a3e3637658ba102c01a0944ff1a22abbf3246be
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bffc29469a12bb508beb45d01233b39925a4be0672172c7531ac8100b8b95e2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d6b09727e622e66e0924ba95376900463ef4050999980640d19d577396a0b5a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c054f30f0fd08a2666abbe4a3c60f5f0356120818c2a21d22b3f600f03165cb
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": 0.7637333333333334,
6
  "eval_steps": 500,
7
- "global_step": 3580,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3598,6 +3598,16 @@
3598
  "mean_token_accuracy": 0.7789977833628654,
3599
  "num_tokens": 16666011.0,
3600
  "step": 3580
 
 
 
 
 
 
 
 
 
 
3601
  }
3602
  ],
3603
  "logging_steps": 10,
@@ -3617,7 +3627,7 @@
3617
  "attributes": {}
3618
  }
3619
  },
3620
- "total_flos": 7.898810969947546e+16,
3621
  "train_batch_size": 4,
3622
  "trial_name": null,
3623
  "trial_params": null
 
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,
 
3598
  "mean_token_accuracy": 0.7789977833628654,
3599
  "num_tokens": 16666011.0,
3600
  "step": 3580
3601
+ },
3602
+ {
3603
+ "entropy": 0.8767322935163975,
3604
+ "epoch": 0.7658666666666667,
3605
+ "grad_norm": 0.30208712816238403,
3606
+ "learning_rate": 7.094948872618507e-05,
3607
+ "loss": 1.0047502517700195,
3608
+ "mean_token_accuracy": 0.7747991606593132,
3609
+ "num_tokens": 16709398.0,
3610
+ "step": 3590
3611
  }
3612
  ],
3613
  "logging_steps": 10,
 
3627
  "attributes": {}
3628
  }
3629
  },
3630
+ "total_flos": 7.918068432112742e+16,
3631
  "train_batch_size": 4,
3632
  "trial_name": null,
3633
  "trial_params": null