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
903772e
·
verified ·
1 Parent(s): 16725bb

Training in progress, step 1680, 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:d18f4bede538fb77c43a62bdca00e26aa30dcf195248f62a3598659814ec19c0
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41476e49b090903ec985ce734655edd92f1742c464f2a2c494b77fc726f1c220
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1165ab4e11ab7bcec1ea7321355d19fb814e136f6352a5dd5dcdf9d80ed349ae
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f45db4ca2a1a4d813085422fdad697d17d8d7ce0f96083c89fb10ded3912625
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:a8a2f69f3f90165766f90290a98ab2f3907ab00e4e729f214bf01d66571e9a07
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9667fe4badec69ee64f16d4a5626beca97a4c63dbd9a9a037e189c56397ceb
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91584877eaa067f530efefaa9e443f0d57fc27ba3f3efdab77901f5c93132e56
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0973aeb522de3163eb423dd4b562f39092155a20798f19e2b87aaa557aa2eae4
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": 0.3562666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1670,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1688,6 +1688,16 @@
1688
  "mean_token_accuracy": 0.7885566264390945,
1689
  "num_tokens": 7760984.0,
1690
  "step": 1670
 
 
 
 
 
 
 
 
 
 
1691
  }
1692
  ],
1693
  "logging_steps": 10,
@@ -1707,7 +1717,7 @@
1707
  "attributes": {}
1708
  }
1709
  },
1710
- "total_flos": 3.681182534128435e+16,
1711
  "train_batch_size": 4,
1712
  "trial_name": null,
1713
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.3584,
6
  "eval_steps": 500,
7
+ "global_step": 1680,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1688
  "mean_token_accuracy": 0.7885566264390945,
1689
  "num_tokens": 7760984.0,
1690
  "step": 1670
1691
+ },
1692
+ {
1693
+ "entropy": 0.9119837798178196,
1694
+ "epoch": 0.3584,
1695
+ "grad_norm": 0.2830665111541748,
1696
+ "learning_rate": 9.441121224605629e-05,
1697
+ "loss": 0.9864655494689941,
1698
+ "mean_token_accuracy": 0.7652302265167237,
1699
+ "num_tokens": 7806335.0,
1700
+ "step": 1680
1701
  }
1702
  ],
1703
  "logging_steps": 10,
 
1717
  "attributes": {}
1718
  }
1719
  },
1720
+ "total_flos": 3.701439412529357e+16,
1721
  "train_batch_size": 4,
1722
  "trial_name": null,
1723
  "trial_params": null