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
a036e2f
·
verified ·
1 Parent(s): be4e042

Training in progress, step 710, 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 sha256:572394f94a94bd935b57ee0625ccc1a5fe3bda7aad1df0ff6599546d461f3900
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88e81d3f32ade194b58fb91379dff11bfd8e0f8fd0532bf90258df18eaf69e6
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ab61d8fdf2a3657ac71d2ade5eb62ff2b78d04e9b46f1b9e5168c5e9e047150
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05cafba8450ed17db6307e500537d4b840670d7e35ac7624ddb7e24624c9ead
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:ccd7a7a24476cb81cd83daa9c750585ba557219d9c597aeb4cb42b9a29821e85
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa752c8460d17d6915d88e6ab1ffc029d0cecbe38986f782a07070e0b27186e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eede5a83e89d96d694f8778553ecce393ab8b4ffab386dcf3ab06d145ebf21fb
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef5cf454641381822ccada9139aed26fd2ef08e6bf71fb1d478807e79577798
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": 0.14933333333333335,
6
  "eval_steps": 500,
7
- "global_step": 700,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -718,6 +718,16 @@
718
  "mean_token_accuracy": 0.759615159034729,
719
  "num_tokens": 3242439.0,
720
  "step": 700
 
 
 
 
 
 
 
 
 
 
721
  }
722
  ],
723
  "logging_steps": 10,
@@ -737,7 +747,7 @@
737
  "attributes": {}
738
  }
739
  },
740
- "total_flos": 1.535563844562432e+16,
741
  "train_batch_size": 4,
742
  "trial_name": null,
743
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.15146666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 710,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
718
  "mean_token_accuracy": 0.759615159034729,
719
  "num_tokens": 3242439.0,
720
  "step": 700
721
+ },
722
+ {
723
+ "entropy": 0.9880564108490943,
724
+ "epoch": 0.15146666666666667,
725
+ "grad_norm": 0.3781116306781769,
726
+ "learning_rate": 9.949976750151489e-05,
727
+ "loss": 1.100698184967041,
728
+ "mean_token_accuracy": 0.7498437210917472,
729
+ "num_tokens": 3287959.0,
730
+ "step": 710
731
  }
732
  ],
733
  "logging_steps": 10,
 
747
  "attributes": {}
748
  }
749
  },
750
+ "total_flos": 1.5570517442239488e+16,
751
  "train_batch_size": 4,
752
  "trial_name": null,
753
  "trial_params": null