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
4d40e75
·
verified ·
1 Parent(s): 0322058

Training in progress, step 1590, 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:d9c53dabb900e99eee33ca2ac454c719769eaae531f660633c607673c6e5874f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15a606af16096574d55da5bfa0c97bd61ac1873e1a2c616ae0869bbee98ef94
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:223770d028053d083440568d90fd1d8306d2c971605f3166a12232a66d03aced
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5fff7f0ebe315f406de49ed6476679f89574d84ece5cd848bbcbf5b1865f732
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b6b0847db423591a8a030203311fa002c257cf22cf07191ac8843953d031319
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb3fa2d957c53aaffc3cde109a07f2f86fccb5f9a7691be7af2f77587f268701
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b07e64ecba4365ba1d0832e39d1b8d05e53c9486b9362ec65534b976064356aa
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:032046bbcdfa1f36d1626b0ebf00f2c99f764144f3ab3f5ab38455677cb9010b
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": 0.3370666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1580,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1598,6 +1598,16 @@
1598
  "mean_token_accuracy": 0.7790701374411583,
1599
  "num_tokens": 7352371.0,
1600
  "step": 1580
 
 
 
 
 
 
 
 
 
 
1601
  }
1602
  ],
1603
  "logging_steps": 10,
@@ -1617,7 +1627,7 @@
1617
  "attributes": {}
1618
  }
1619
  },
1620
- "total_flos": 3.484521030033715e+16,
1621
  "train_batch_size": 4,
1622
  "trial_name": null,
1623
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.3392,
6
  "eval_steps": 500,
7
+ "global_step": 1590,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1598
  "mean_token_accuracy": 0.7790701374411583,
1599
  "num_tokens": 7352371.0,
1600
  "step": 1580
1601
+ },
1602
+ {
1603
+ "entropy": 0.8671779796481133,
1604
+ "epoch": 0.3392,
1605
+ "grad_norm": 0.32672831416130066,
1606
+ "learning_rate": 9.510514465900653e-05,
1607
+ "loss": 0.9251022338867188,
1608
+ "mean_token_accuracy": 0.7759940758347511,
1609
+ "num_tokens": 7393383.0,
1610
+ "step": 1590
1611
  }
1612
  ],
1613
  "logging_steps": 10,
 
1627
  "attributes": {}
1628
  }
1629
  },
1630
+ "total_flos": 3.503919077350195e+16,
1631
  "train_batch_size": 4,
1632
  "trial_name": null,
1633
  "trial_params": null