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
8cdc7ec
·
verified ·
1 Parent(s): e3a3977

Training in progress, step 3420, 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 sha256:7521f37bee0ee52e735bad9c72319f217d014fb444f098ce64f95ebb37c3fdaa
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e89e44b91aac5e4c697aefb456d3794cb4ceae9fb23cf3242a021b509de54f5
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af07ffe897abfd723adcd9431b56fcace89cfee5544c962c16f32d2914255771
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c4981f3300789db77485698a69af8e4eb0941a43231fed7da399b23f1cd439
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71a98c890f0dde5e487a2c8dd6730156298c761e78de84e99519359ad62979ef
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3a66281a4dfc5e1bf8c05491b91a0cf9bc09fa84735dc6f0c51bf11a0943ce
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01ebfa5ecb9b488cde9cea210c2835fe825c038d4fa1cf731b310ebe9642e0e7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9d0be4797a7ac97fc7aedc2d5f3f558ebb5d97823a9cdbee6b416e4e71ccca
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": 0.7274666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3410,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3428,6 +3428,16 @@
3428
  "mean_token_accuracy": 0.7566501721739769,
3429
  "num_tokens": 15885904.0,
3430
  "step": 3410
 
 
 
 
 
 
 
 
 
 
3431
  }
3432
  ],
3433
  "logging_steps": 10,
@@ -3447,7 +3457,7 @@
3447
  "attributes": {}
3448
  }
3449
  },
3450
- "total_flos": 7.52470126576681e+16,
3451
  "train_batch_size": 4,
3452
  "trial_name": null,
3453
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7296,
6
  "eval_steps": 500,
7
+ "global_step": 3420,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3428
  "mean_token_accuracy": 0.7566501721739769,
3429
  "num_tokens": 15885904.0,
3430
  "step": 3410
3431
+ },
3432
+ {
3433
+ "entropy": 1.0563621714711189,
3434
+ "epoch": 0.7296,
3435
+ "grad_norm": 0.3054843246936798,
3436
+ "learning_rate": 7.358319135552285e-05,
3437
+ "loss": 1.189220142364502,
3438
+ "mean_token_accuracy": 0.738009649515152,
3439
+ "num_tokens": 15937698.0,
3440
+ "step": 3420
3441
  }
3442
  ],
3443
  "logging_steps": 10,
 
3457
  "attributes": {}
3458
  }
3459
  },
3460
+ "total_flos": 7.550473407794995e+16,
3461
  "train_batch_size": 4,
3462
  "trial_name": null,
3463
  "trial_params": null