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
b2e6c79
·
verified ·
1 Parent(s): ef5d129

Training in progress, step 740, 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 sha256:63fdcb9bc3e6d07fc2a7613712e20fdddfc0082758697cd04ad161f93a7750e5
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2160f352d544d8facab82fff4e8805f318003d22c994fa13eb044e196db534ce
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eab76774f7146f484fdbecd44e27d79d31bb82e48a6c0403aec0a8eae98e45bf
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1cdc83f65020769dfc55b378fd6129a44752bacfdc4e8cd1cae8f1388ecfef
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:b48869528bf508d3a1e510877ff0b496a88c9c68d27133d809e241e623afe2f0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b48c8ab6e5b9f0eb0a5780add1130e164d4280670d666f1bfcd4b95bceea8b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4dd1fe0881a329983c3df6ea0ded9f3b753faddab6eabf73568a4386b772df3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4a9609bbb6edc853eb0d8766257cb9e5f060e4e7eea7ee44216bbaadc8e458
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": 0.15573333333333333,
6
  "eval_steps": 500,
7
- "global_step": 730,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -748,6 +748,16 @@
748
  "mean_token_accuracy": 0.7387717284262181,
749
  "num_tokens": 3380879.0,
750
  "step": 730
 
 
 
 
 
 
 
 
 
 
751
  }
752
  ],
753
  "logging_steps": 10,
@@ -767,7 +777,7 @@
767
  "attributes": {}
768
  }
769
  },
770
- "total_flos": 1.6016559882160128e+16,
771
  "train_batch_size": 4,
772
  "trial_name": null,
773
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.15786666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 740,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
748
  "mean_token_accuracy": 0.7387717284262181,
749
  "num_tokens": 3380879.0,
750
  "step": 730
751
+ },
752
+ {
753
+ "entropy": 0.9154682122170925,
754
+ "epoch": 0.15786666666666666,
755
+ "grad_norm": 0.2581311762332916,
756
+ "learning_rate": 9.942383884619455e-05,
757
+ "loss": 1.0275691032409668,
758
+ "mean_token_accuracy": 0.7657118752598763,
759
+ "num_tokens": 3430079.0,
760
+ "step": 740
761
  }
762
  ],
763
  "logging_steps": 10,
 
777
  "attributes": {}
778
  }
779
  },
780
+ "total_flos": 1.6239738809822208e+16,
781
  "train_batch_size": 4,
782
  "trial_name": null,
783
  "trial_params": null