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
000219e
·
verified ·
1 Parent(s): 4a1ef87

Training in progress, step 590, 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 sha256:0550856e8c5ffe718f27b6251a10c2d584a524baf4c8152e1cd219f9169c37fc
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0f84716d8cec074c95ed582a055c8f5d1f4b62732a4f4e906884dcdb5431b2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:474f7b4c43d108b4cd1d5366b625488d3654336c80ef295c20e8a3dbce1d4e8d
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6b300e3ddf2612f0daf77e949a79296b8f6ea3973b76e83e594caad6a75fbb
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:a3140e01ac85c810d8fd77bf3a10cbe89cc874aefee356886db6544c7b6037ce
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e49732998a38b5707be22380a3b06b74ebddbc0c68379725cade23e827ead71
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:282809178dae42b67982ea6894af4966949a61b782fee74d2b37ea8b3b19f28d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e95c424288941f4f7d49c6fe841c41c1221a9e81e78aa0725573f3872f3f9d
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": 0.12373333333333333,
6
  "eval_steps": 500,
7
- "global_step": 580,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -598,6 +598,16 @@
598
  "mean_token_accuracy": 0.735442753136158,
599
  "num_tokens": 2686009.0,
600
  "step": 580
 
 
 
 
 
 
 
 
 
 
601
  }
602
  ],
603
  "logging_steps": 10,
@@ -617,7 +627,7 @@
617
  "attributes": {}
618
  }
619
  },
620
- "total_flos": 1.2798133199591424e+16,
621
  "train_batch_size": 4,
622
  "trial_name": null,
623
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.12586666666666665,
6
  "eval_steps": 500,
7
+ "global_step": 590,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
598
  "mean_token_accuracy": 0.735442753136158,
599
  "num_tokens": 2686009.0,
600
  "step": 580
601
+ },
602
+ {
603
+ "entropy": 0.8992204323410988,
604
+ "epoch": 0.12586666666666665,
605
+ "grad_norm": 0.2524716556072235,
606
+ "learning_rate": 9.975003208519522e-05,
607
+ "loss": 0.9971331596374512,
608
+ "mean_token_accuracy": 0.7749405071139336,
609
+ "num_tokens": 2731814.0,
610
+ "step": 590
611
  }
612
  ],
613
  "logging_steps": 10,
 
627
  "attributes": {}
628
  }
629
  },
630
+ "total_flos": 1.2998476052038656e+16,
631
  "train_batch_size": 4,
632
  "trial_name": null,
633
  "trial_params": null