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
ffe4abf
·
verified ·
1 Parent(s): 1e56252

Training in progress, step 1710, 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 sha256:2ec49c3967dff2fa5b4a6a722b16997f9c1a5259c9837d392661c7e6f4ab9850
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014c0d12f1a956d8a9aee31eee688ca0b8eb039a7a58a63a9fb1a11bed6cea9a
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4310f9048a90692626545079c9084f0bf6e554f96e223294a7f562ca79488880
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f9d0676755dc016ab10cf2537f9d10f21f94c67a0e4f0e699830ef2f7db45f
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:501286c6ba5d51ed8db1a9581b908f10e3b219be550991bef23ea25332a068e3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67740b58de2d398f118cf26025c0b2dd055c24fbf6c9d71776ef18279c5cac42
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d72a5a59fd1cab254c751670f6dddd1229c370946cade7a7966f22da4d7a37b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:755cc8d3ef932fccb0a2acd2756939cec461b9e4d5b6b2409e7355cc6da2226e
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": 0.3626666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1700,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1718,6 +1718,16 @@
1718
  "mean_token_accuracy": 0.7566492781043053,
1719
  "num_tokens": 7890665.0,
1720
  "step": 1700
 
 
 
 
 
 
 
 
 
 
1721
  }
1722
  ],
1723
  "logging_steps": 10,
@@ -1737,7 +1747,7 @@
1737
  "attributes": {}
1738
  }
1739
  },
1740
- "total_flos": 3.74272548647639e+16,
1741
  "train_batch_size": 4,
1742
  "trial_name": null,
1743
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.3648,
6
  "eval_steps": 500,
7
+ "global_step": 1710,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1718
  "mean_token_accuracy": 0.7566492781043053,
1719
  "num_tokens": 7890665.0,
1720
  "step": 1700
1721
+ },
1722
+ {
1723
+ "entropy": 0.8920052781701088,
1724
+ "epoch": 0.3648,
1725
+ "grad_norm": 0.22740185260772705,
1726
+ "learning_rate": 9.417028972676359e-05,
1727
+ "loss": 1.005050277709961,
1728
+ "mean_token_accuracy": 0.7736168324947357,
1729
+ "num_tokens": 7933849.0,
1730
+ "step": 1710
1731
  }
1732
  ],
1733
  "logging_steps": 10,
 
1747
  "attributes": {}
1748
  }
1749
  },
1750
+ "total_flos": 3.762971550634906e+16,
1751
  "train_batch_size": 4,
1752
  "trial_name": null,
1753
  "trial_params": null