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
d3e65b3
·
verified ·
1 Parent(s): 179d080

Training in progress, step 1650, 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 sha256:2a789cc82fc55c5d1977b11b095e485df1d770d045fa5bcd10e1d6d6896cd202
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:684e1fddbfbfff93378789f73126d8e058dce6b0e8c4b258c584237c4d803a23
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e758a621f68658f478f9af1488bcbd512cb1884c61c4d03eec6469a82be5158
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163ef1e9a6f691fc31f4f8bf88590f5d0c498193b213adab9c17efcedb68e9a9
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c6a58b813668536860ea2f8905ed991304e0c6708601983c17a7d0c9ae1cfb2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f9164ece68d6d655afc29885c7f39b0f06a3a6409b46b08b0e4a936fc917e1
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec5b1ba2dd1208014572958a84bd2231054da43cd48315ebd0b09b5bb9db420c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a65a3644d5910687eecb81c370ab2316a583feb808ffc29e2384e0defe7fd6
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": 0.34986666666666666,
6
  "eval_steps": 500,
7
- "global_step": 1640,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1658,6 +1658,16 @@
1658
  "mean_token_accuracy": 0.769710011780262,
1659
  "num_tokens": 7619772.0,
1660
  "step": 1640
 
 
 
 
 
 
 
 
 
 
1661
  }
1662
  ],
1663
  "logging_steps": 10,
@@ -1677,7 +1687,7 @@
1677
  "attributes": {}
1678
  }
1679
  },
1680
- "total_flos": 3.614708287243162e+16,
1681
  "train_batch_size": 4,
1682
  "trial_name": null,
1683
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.352,
6
  "eval_steps": 500,
7
+ "global_step": 1650,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1658
  "mean_token_accuracy": 0.769710011780262,
1659
  "num_tokens": 7619772.0,
1660
  "step": 1640
1661
+ },
1662
+ {
1663
+ "entropy": 0.9953067198395729,
1664
+ "epoch": 0.352,
1665
+ "grad_norm": 0.2255147099494934,
1666
+ "learning_rate": 9.46473457965715e-05,
1667
+ "loss": 1.1140392303466797,
1668
+ "mean_token_accuracy": 0.7478319302201271,
1669
+ "num_tokens": 7666080.0,
1670
+ "step": 1650
1671
  }
1672
  ],
1673
  "logging_steps": 10,
 
1687
  "attributes": {}
1688
  }
1689
  },
1690
+ "total_flos": 3.63787239447767e+16,
1691
  "train_batch_size": 4,
1692
  "trial_name": null,
1693
  "trial_params": null