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
b94fd80
·
verified ·
1 Parent(s): 700ccd5

Training in progress, step 2820, 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 sha256:34322ebac780430a2d0f180530bb946169ada1e82457837e6ce8d367b0e6a5d6
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b79ddd928ce2ca00d5f0105035d5f190bc06cbcb082adfff6b129ee4104d4b1
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b050f0f67ea3b048da51fe12d4be43883a0c4a32aa27ad9a4bd2a9973b682c86
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5321fe757bbe6fe43781b82066d52c8cb724ab840d19405f505f289a5cc3b8d
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:d20a8d2718d6d7598cc26964f5cca4073cecbc57d6bcaef8758ee5cf2e3bd4ab
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2262eae713a8f93be84b5a396f7e1bf83e6e68900870de1744420262b11a8b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cd6e15982ff81496b6f33aa5453d99d96b19411f1c911bb21595815ecca8608
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c045759635f0f21e0ddf565a723e81205082188f9c8117a5fd90a3d45310160
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": 0.5994666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2810,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2828,6 +2828,16 @@
2828
  "mean_token_accuracy": 0.7469129160046577,
2829
  "num_tokens": 13064583.0,
2830
  "step": 2810
 
 
 
 
 
 
 
 
 
 
2831
  }
2832
  ],
2833
  "logging_steps": 10,
@@ -2847,7 +2857,7 @@
2847
  "attributes": {}
2848
  }
2849
  },
2850
- "total_flos": 6.191695390971187e+16,
2851
  "train_batch_size": 4,
2852
  "trial_name": null,
2853
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.6016,
6
  "eval_steps": 500,
7
+ "global_step": 2820,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2828
  "mean_token_accuracy": 0.7469129160046577,
2829
  "num_tokens": 13064583.0,
2830
  "step": 2810
2831
+ },
2832
+ {
2833
+ "entropy": 1.0561771862208844,
2834
+ "epoch": 0.6016,
2835
+ "grad_norm": 0.2526226043701172,
2836
+ "learning_rate": 8.216736109836534e-05,
2837
+ "loss": 1.1680998802185059,
2838
+ "mean_token_accuracy": 0.7392091482877732,
2839
+ "num_tokens": 13115184.0,
2840
+ "step": 2820
2841
  }
2842
  ],
2843
  "logging_steps": 10,
 
2857
  "attributes": {}
2858
  }
2859
  },
2860
+ "total_flos": 6.216075199289549e+16,
2861
  "train_batch_size": 4,
2862
  "trial_name": null,
2863
  "trial_params": null