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
8cc5c77
·
verified ·
1 Parent(s): aef7bd8

Training in progress, step 3450, 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 sha256:51352825e456fc9189b1e5dfddfa4babad7f75511c8ec489e78ff1a3de338f87
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07b78eeecb81ff2ff3db73ffd3bd439147272dbc61cf6254569bd9159395ba8
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e06d3cd2fb04d72abcc0008b4d588c8e8083784298237cd20852cdb95e3f0523
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73e452e1ac35f87aeeb399a8625ee3f27dd7ebd2bd25f53d0ed99c0597496da
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:ddc21210cdbfad33c045629b1dcb92169570a41a295e1a328d0d865b35ea1cb5
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6191bf4b81ba084172fa2bdfcbf72f3b9527022fdd20bd4494e733bafb423a9
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99e58e88c4c4cadecd08c67b9da11d26c1eec21844733026b7df7963f70c4527
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1eb5a2d64117b6f060427c98f9e7c895a461779409d0a875ab55445d57100aa
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": 0.7338666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3440,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3458,6 +3458,16 @@
3458
  "mean_token_accuracy": 0.7715103484690189,
3459
  "num_tokens": 16029965.0,
3460
  "step": 3440
 
 
 
 
 
 
 
 
 
 
3461
  }
3462
  ],
3463
  "logging_steps": 10,
@@ -3477,7 +3487,7 @@
3477
  "attributes": {}
3478
  }
3479
  },
3480
- "total_flos": 7.592043355605197e+16,
3481
  "train_batch_size": 4,
3482
  "trial_name": null,
3483
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.736,
6
  "eval_steps": 500,
7
+ "global_step": 3450,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3458
  "mean_token_accuracy": 0.7715103484690189,
3459
  "num_tokens": 16029965.0,
3460
  "step": 3440
3461
+ },
3462
+ {
3463
+ "entropy": 0.9526532724499702,
3464
+ "epoch": 0.736,
3465
+ "grad_norm": 0.24097904562950134,
3466
+ "learning_rate": 7.312409608752208e-05,
3467
+ "loss": 1.0411754608154298,
3468
+ "mean_token_accuracy": 0.7602859303355217,
3469
+ "num_tokens": 16078997.0,
3470
+ "step": 3450
3471
  }
3472
  ],
3473
  "logging_steps": 10,
 
3487
  "attributes": {}
3488
  }
3489
  },
3490
+ "total_flos": 7.615748174960026e+16,
3491
  "train_batch_size": 4,
3492
  "trial_name": null,
3493
  "trial_params": null