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
bf37eab
·
verified ·
1 Parent(s): fac33fd

Training in progress, step 4370, 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 sha256:5dd22ad50eca0c97d3087dee9f828155637132c8493f95e5b45a650228e8fe4f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82cc149ef7aa5726e7680b3c537e9c5ddebf7f591c22e428594ef0bb469c98b9
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92c434b9032fd844ba9bea78485389833c3d56d0ecd7af4353bec3e35e2ec2ff
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4158e85ad7e01ede6b2d761975c00d09e04dabef6a8426f783291f78cc837cdd
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:bceae117c299b3530d1c8082e7de8ba11c4a7a3879e946f34d1babb497a05267
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4898aa41ae9c0dc6a440b0ece13b774d0a448d5a4cb6548c8575099a0c42bb3a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0065d77907671e06967cc54d2afe420aaa55e85dbdfc2f6b3450358ac68ce592
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55917511ddd5e3426aba1af2b9b91eeaf3e4cd8f87821c15e034a4afc0acb105
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": 0.9301333333333334,
6
  "eval_steps": 500,
7
- "global_step": 4360,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4378,6 +4378,16 @@
4378
  "mean_token_accuracy": 0.7782815754413605,
4379
  "num_tokens": 20288504.0,
4380
  "step": 4360
 
 
 
 
 
 
 
 
 
 
4381
  }
4382
  ],
4383
  "logging_steps": 10,
@@ -4397,7 +4407,7 @@
4397
  "attributes": {}
4398
  }
4399
  },
4400
- "total_flos": 9.6052452516523e+16,
4401
  "train_batch_size": 4,
4402
  "trial_name": null,
4403
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.9322666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 4370,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4378
  "mean_token_accuracy": 0.7782815754413605,
4379
  "num_tokens": 20288504.0,
4380
  "step": 4360
4381
+ },
4382
+ {
4383
+ "entropy": 0.9351005107164383,
4384
+ "epoch": 0.9322666666666667,
4385
+ "grad_norm": 0.2535351812839508,
4386
+ "learning_rate": 5.808144356047414e-05,
4387
+ "loss": 1.0453302383422851,
4388
+ "mean_token_accuracy": 0.7632610902190209,
4389
+ "num_tokens": 20335084.0,
4390
+ "step": 4370
4391
  }
4392
  ],
4393
  "logging_steps": 10,
 
4407
  "attributes": {}
4408
  }
4409
  },
4410
+ "total_flos": 9.628967193557606e+16,
4411
  "train_batch_size": 4,
4412
  "trial_name": null,
4413
  "trial_params": null