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
6049d2e
·
verified ·
1 Parent(s): 7689942

Training in progress, step 1740, 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 sha256:23a6ad4f9c2aedea7ef0ce1277e8ee175d0714e52ecce8c78d6ef1ee7a6d920d
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f4c98f6aabf49be4f26c5bcb1cf24907ecf0e87df4e6636ad3341d315bfeb6c
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed46718e9bc461b034c4ae6fc2f3b28ff26b6f03fec6979f1ea03d1a4dd46627
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10928bb50ddabe7412701f4397c876255be29494039fcf4ea3f9093e23997cf
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:a2f69827a8531f011e3a7ae14ebe8eaf52e6656f83a6d95d4946c4798f4e1c5a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deae801c158964c40f1573c507c036ee10487b29620e828b0bcf022410dd837b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f025b7a35a2fa800fe18e0083eb1b988995df608e432283222f76c9cbfde0b07
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cb4b5860837a63ee23b2a132dfbe0277b390aeac6122771e4989f0edff682dc
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": 0.36906666666666665,
6
  "eval_steps": 500,
7
- "global_step": 1730,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1748,6 +1748,16 @@
1748
  "mean_token_accuracy": 0.7606610782444477,
1749
  "num_tokens": 8028778.0,
1750
  "step": 1730
 
 
 
 
 
 
 
 
 
 
1751
  }
1752
  ],
1753
  "logging_steps": 10,
@@ -1767,7 +1777,7 @@
1767
  "attributes": {}
1768
  }
1769
  },
1770
- "total_flos": 3.810022516971418e+16,
1771
  "train_batch_size": 4,
1772
  "trial_name": null,
1773
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.3712,
6
  "eval_steps": 500,
7
+ "global_step": 1740,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1748
  "mean_token_accuracy": 0.7606610782444477,
1749
  "num_tokens": 8028778.0,
1750
  "step": 1730
1751
+ },
1752
+ {
1753
+ "entropy": 0.8785062082111835,
1754
+ "epoch": 0.3712,
1755
+ "grad_norm": 0.20483236014842987,
1756
+ "learning_rate": 9.392460421795328e-05,
1757
+ "loss": 0.9666107177734375,
1758
+ "mean_token_accuracy": 0.7833232149481774,
1759
+ "num_tokens": 8071410.0,
1760
+ "step": 1740
1761
  }
1762
  ],
1763
  "logging_steps": 10,
 
1777
  "attributes": {}
1778
  }
1779
  },
1780
+ "total_flos": 3.830219015852237e+16,
1781
  "train_batch_size": 4,
1782
  "trial_name": null,
1783
  "trial_params": null