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
85b99e1
·
verified ·
1 Parent(s): a2d376f

Training in progress, step 3360, 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:fcc4b212f4b34bd8874d899315d2e60dfbae0c591eb3bf238bbd9ca31178e566
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae0ae6e150b5a93ce8659f1539849528e8f9058b184f36e3d49d1c1f0ae3961
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2240733d1ab5ca97b0d453695d7dcd660453e692f542584436d5408629c5b1b8
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e6ae1cfb595c120f584cde7808f72de4ac234c6894f425fb61b66fa09b1f689
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:d115689a979af8bb48e773b327ba18020e29302259d5e780481635bcc3f51933
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a236f8b589de9ff5df9daacdf0d5b465eb4e27f9078a45c14457ba87ed8e12
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5b8dd5195df4b2c20795af97ed88166297ac00c9a7dd5cb232f96871ec6fbd6
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bd3f3ed2d8fce595cdd9922ae9854783d9dcf779632e047081b770aca96e1d
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": 0.7146666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3350,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3368,6 +3368,16 @@
3368
  "mean_token_accuracy": 0.7605102032423019,
3369
  "num_tokens": 15605470.0,
3370
  "step": 3350
 
 
 
 
 
 
 
 
 
 
3371
  }
3372
  ],
3373
  "logging_steps": 10,
@@ -3387,7 +3397,7 @@
3387
  "attributes": {}
3388
  }
3389
  },
3390
- "total_flos": 7.393354181059277e+16,
3391
  "train_batch_size": 4,
3392
  "trial_name": null,
3393
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7168,
6
  "eval_steps": 500,
7
+ "global_step": 3360,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3368
  "mean_token_accuracy": 0.7605102032423019,
3369
  "num_tokens": 15605470.0,
3370
  "step": 3350
3371
+ },
3372
+ {
3373
+ "entropy": 0.9598750308156013,
3374
+ "epoch": 0.7168,
3375
+ "grad_norm": 0.2748892903327942,
3376
+ "learning_rate": 7.449370356214814e-05,
3377
+ "loss": 1.0057992935180664,
3378
+ "mean_token_accuracy": 0.7655998513102531,
3379
+ "num_tokens": 15652544.0,
3380
+ "step": 3360
3381
  }
3382
  ],
3383
  "logging_steps": 10,
 
3397
  "attributes": {}
3398
  }
3399
  },
3400
+ "total_flos": 7.4148528949632e+16,
3401
  "train_batch_size": 4,
3402
  "trial_name": null,
3403
  "trial_params": null