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
df76808
·
verified ·
1 Parent(s): 8730a3f

Training in progress, step 1800, 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:db850b67ea7c6e8dfc6fff996630ebca0373e266bdf9a7563852a21a31a27519
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83783d606cd824f2f6041919fa0d046573a81fa8c2147a263d33471b60bdf4f3
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce55cb1e263ea2d5fd546cea9912f84fea357b030bd8375beb2b59d7b235a405
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c77f8336c1ed8c1c2baa9a0a421b359896bd3ce32961171b7eeb8fc3c09e37
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20abbe0709a08bb0d55ec9e4263a0c87b8cafe4e40118d178fa4cabe0e57626f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a9978791bbf62f5f5d42f8b5d355d0fd47d1899bdded4ed3bea740f2601d46
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46fd591e592870127c67addd89407fd20b2f87ea858f9f3f9640f6e32d088608
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:180a1823af3df2638ec65911fe40ac441d8f1f67d7dbb8494c98c5503d586af5
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": 0.3818666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1790,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1808,6 +1808,16 @@
1808
  "mean_token_accuracy": 0.746114706993103,
1809
  "num_tokens": 8300355.0,
1810
  "step": 1790
 
 
 
 
 
 
 
 
 
 
1811
  }
1812
  ],
1813
  "logging_steps": 10,
@@ -1827,7 +1837,7 @@
1827
  "attributes": {}
1828
  }
1829
  },
1830
- "total_flos": 3.94250599831849e+16,
1831
  "train_batch_size": 4,
1832
  "trial_name": null,
1833
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.384,
6
  "eval_steps": 500,
7
+ "global_step": 1800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1808
  "mean_token_accuracy": 0.746114706993103,
1809
  "num_tokens": 8300355.0,
1810
  "step": 1790
1811
+ },
1812
+ {
1813
+ "entropy": 0.943967767059803,
1814
+ "epoch": 0.384,
1815
+ "grad_norm": 0.2434380203485489,
1816
+ "learning_rate": 9.34190507139859e-05,
1817
+ "loss": 0.9968074798583985,
1818
+ "mean_token_accuracy": 0.7640544638037682,
1819
+ "num_tokens": 8346150.0,
1820
+ "step": 1800
1821
  }
1822
  ],
1823
  "logging_steps": 10,
 
1837
  "attributes": {}
1838
  }
1839
  },
1840
+ "total_flos": 3.965886390401126e+16,
1841
  "train_batch_size": 4,
1842
  "trial_name": null,
1843
  "trial_params": null