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
98da2c1
·
verified ·
1 Parent(s): 428fcf7

Training in progress, step 1580, 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:b8e6c870be5ceb8d82d0276ee27cb8d12f00d46d0db1c5f7fbed3b4273a62fbd
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c53dabb900e99eee33ca2ac454c719769eaae531f660633c607673c6e5874f
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8954329d1712a93afa49f43d0cc235897230fe1ab751f74db559f6d9500ae6dd
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223770d028053d083440568d90fd1d8306d2c971605f3166a12232a66d03aced
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:c607914c335452bf5c978af3416182d3900072495f5b292a3cf9fa6af1683ef4
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6b0847db423591a8a030203311fa002c257cf22cf07191ac8843953d031319
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0cfaa6e1371e6c425f66388060aaf89aa8e079158baefb2a1a9d5b7295faa4d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07e64ecba4365ba1d0832e39d1b8d05e53c9486b9362ec65534b976064356aa
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": 0.33493333333333336,
6
  "eval_steps": 500,
7
- "global_step": 1570,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1588,6 +1588,16 @@
1588
  "mean_token_accuracy": 0.7347081542015076,
1589
  "num_tokens": 7305883.0,
1590
  "step": 1570
 
 
 
 
 
 
 
 
 
 
1591
  }
1592
  ],
1593
  "logging_steps": 10,
@@ -1607,7 +1617,7 @@
1607
  "attributes": {}
1608
  }
1609
  },
1610
- "total_flos": 3.4627636754989056e+16,
1611
  "train_batch_size": 4,
1612
  "trial_name": null,
1613
  "trial_params": null
 
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,
 
1588
  "mean_token_accuracy": 0.7347081542015076,
1589
  "num_tokens": 7305883.0,
1590
  "step": 1570
1591
+ },
1592
+ {
1593
+ "entropy": 0.887219874560833,
1594
+ "epoch": 0.3370666666666667,
1595
+ "grad_norm": 0.2346959412097931,
1596
+ "learning_rate": 9.517955825397056e-05,
1597
+ "loss": 0.9671891212463379,
1598
+ "mean_token_accuracy": 0.7790701374411583,
1599
+ "num_tokens": 7352371.0,
1600
+ "step": 1580
1601
  }
1602
  ],
1603
  "logging_steps": 10,
 
1617
  "attributes": {}
1618
  }
1619
  },
1620
+ "total_flos": 3.484521030033715e+16,
1621
  "train_batch_size": 4,
1622
  "trial_name": null,
1623
  "trial_params": null