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
61ba01b
·
verified ·
1 Parent(s): b4c351c

Training in progress, step 2640, 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 sha256:5c9b8512aa1be3612a01e56e95534d2aafc3e03fe46fab0417ce5b86711a2568
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9a7265227379792bb8a91f7501942bcca1f4a8a718380547c29a2de423a705
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c842bf85026d7b26bcb687872072c5172dfe807bdec1a3e6f1dff3d7329272d
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:563caf471d67cfd6e9173dcbf1b31d0a08ae179af2e4f3b57def2b761fda91e6
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dc4ba2aa5c153f7d4ec40f47dab69d6b3b54f645f81bfc17911e09fab786004
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d6c3023a9852b60b657916fb6bffa08ee674ebece93486aaa244c25f713959
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eba85d8a959c650472bba485c18e1136a0db94e9ee761b395692036382b4b88
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c18dc318e6f3d40bcdb71a070581b494549a4e68afb73b54ebdd969f7f8d8964
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": 0.5610666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2630,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2648,6 +2648,16 @@
2648
  "mean_token_accuracy": 0.7620343893766404,
2649
  "num_tokens": 12223113.0,
2650
  "step": 2630
 
 
 
 
 
 
 
 
 
 
2651
  }
2652
  ],
2653
  "logging_steps": 10,
@@ -2667,7 +2677,7 @@
2667
  "attributes": {}
2668
  }
2669
  },
2670
- "total_flos": 5.791965845342822e+16,
2671
  "train_batch_size": 4,
2672
  "trial_name": null,
2673
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5632,
6
  "eval_steps": 500,
7
+ "global_step": 2640,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2648
  "mean_token_accuracy": 0.7620343893766404,
2649
  "num_tokens": 12223113.0,
2650
  "step": 2630
2651
+ },
2652
+ {
2653
+ "entropy": 0.9550898216664792,
2654
+ "epoch": 0.5632,
2655
+ "grad_norm": 0.25011542439460754,
2656
+ "learning_rate": 8.448838506515262e-05,
2657
+ "loss": 0.9950971603393555,
2658
+ "mean_token_accuracy": 0.7567313954234123,
2659
+ "num_tokens": 12274057.0,
2660
+ "step": 2640
2661
  }
2662
  ],
2663
  "logging_steps": 10,
 
2677
  "attributes": {}
2678
  }
2679
  },
2680
+ "total_flos": 5.816578159872922e+16,
2681
  "train_batch_size": 4,
2682
  "trial_name": null,
2683
  "trial_params": null