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
c4ac913
·
verified ·
1 Parent(s): c7036dc

Training in progress, step 4380, 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 sha256:82cc149ef7aa5726e7680b3c537e9c5ddebf7f591c22e428594ef0bb469c98b9
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b57499e7743293e3d63393286b1030b9ad58b617e9da83647241dbe9048e37
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4158e85ad7e01ede6b2d761975c00d09e04dabef6a8426f783291f78cc837cdd
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50adcb58c766a6af5fb5ae4d9231da8e4fd3cd711d2b78b237b1a5325c87cec7
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4898aa41ae9c0dc6a440b0ece13b774d0a448d5a4cb6548c8575099a0c42bb3a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c08d4497334c96aec714474814fbf07fd5c4b74414f334d4bf742d8252f204f
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55917511ddd5e3426aba1af2b9b91eeaf3e4cd8f87821c15e034a4afc0acb105
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40e6a84f7bdae3c64a3e94c5cdd0573fe920cb78e23fc2b376054692b452f4c
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": 0.9322666666666667,
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,
@@ -4388,6 +4388,16 @@
4388
  "mean_token_accuracy": 0.7632610902190209,
4389
  "num_tokens": 20335084.0,
4390
  "step": 4370
 
 
 
 
 
 
 
 
 
 
4391
  }
4392
  ],
4393
  "logging_steps": 10,
@@ -4407,7 +4417,7 @@
4407
  "attributes": {}
4408
  }
4409
  },
4410
- "total_flos": 9.628967193557606e+16,
4411
  "train_batch_size": 4,
4412
  "trial_name": null,
4413
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.9344,
6
  "eval_steps": 500,
7
+ "global_step": 4380,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4388
  "mean_token_accuracy": 0.7632610902190209,
4389
  "num_tokens": 20335084.0,
4390
  "step": 4370
4391
+ },
4392
+ {
4393
+ "entropy": 0.9218877613544464,
4394
+ "epoch": 0.9344,
4395
+ "grad_norm": 0.23900526762008667,
4396
+ "learning_rate": 5.791059966464164e-05,
4397
+ "loss": 0.9873531341552735,
4398
+ "mean_token_accuracy": 0.7675649732351303,
4399
+ "num_tokens": 20384687.0,
4400
+ "step": 4380
4401
  }
4402
  ],
4403
  "logging_steps": 10,
 
4417
  "attributes": {}
4418
  }
4419
  },
4420
+ "total_flos": 9.65205920584274e+16,
4421
  "train_batch_size": 4,
4422
  "trial_name": null,
4423
  "trial_params": null