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
a0053b3
·
verified ·
1 Parent(s): f4a3a98

Training in progress, step 750, 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 sha256:2160f352d544d8facab82fff4e8805f318003d22c994fa13eb044e196db534ce
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3cd0013d7c5b95e52aa4f3fa06aa106cb1539ff72f1b100bc97d7fec6704d14
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac1cdc83f65020769dfc55b378fd6129a44752bacfdc4e8cd1cae8f1388ecfef
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08973b94cb6a54b4ccecdf42ca1a81167afc7d30cfd0a0cd90bfcff6afcd6da
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43b48c8ab6e5b9f0eb0a5780add1130e164d4280670d666f1bfcd4b95bceea8b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f419413f7c052c03d917ef20ad1776825e90f8ccaba4e0ab51616fd4daa061
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf4a9609bbb6edc853eb0d8766257cb9e5f060e4e7eea7ee44216bbaadc8e458
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befca7a1c9442e933413cc49e7e1fbdeec25341984e36c362cfbe964523d027b
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": 0.15786666666666666,
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,
@@ -758,6 +758,16 @@
758
  "mean_token_accuracy": 0.7657118752598763,
759
  "num_tokens": 3430079.0,
760
  "step": 740
 
 
 
 
 
 
 
 
 
 
761
  }
762
  ],
763
  "logging_steps": 10,
@@ -777,7 +787,7 @@
777
  "attributes": {}
778
  }
779
  },
780
- "total_flos": 1.6239738809822208e+16,
781
  "train_batch_size": 4,
782
  "trial_name": null,
783
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.16,
6
  "eval_steps": 500,
7
+ "global_step": 750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
758
  "mean_token_accuracy": 0.7657118752598763,
759
  "num_tokens": 3430079.0,
760
  "step": 740
761
+ },
762
+ {
763
+ "entropy": 1.0482445612549782,
764
+ "epoch": 0.16,
765
+ "grad_norm": 0.2496950626373291,
766
+ "learning_rate": 9.939734454187365e-05,
767
+ "loss": 1.1575148582458497,
768
+ "mean_token_accuracy": 0.7434881895780563,
769
+ "num_tokens": 3482687.0,
770
+ "step": 750
771
  }
772
  ],
773
  "logging_steps": 10,
 
787
  "attributes": {}
788
  }
789
  },
790
+ "total_flos": 1.6475957911452672e+16,
791
  "train_batch_size": 4,
792
  "trial_name": null,
793
  "trial_params": null