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
3d2f690
·
verified ·
1 Parent(s): f1764e4

Training in progress, step 2720, 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 sha256:957d4df147552dccc03b5064da9940fbc96240e86d61616c67371be9873d17c2
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:506a613b0146512b986ba1981cdf2bbd94aeaffa8e987cd84342b92da5e79916
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06324cba1fcd52a3281fa6591c0e7d79c7acb68c99ee700e5d9f84ceecc36f9b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f1db54048384c15393cf611df07e5b8f554cf107ad4a691310de6e0b4a8216
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:047660a9cac5c5e004a2144f019fb08fcdcdbf76a9e4287f79b301d86876a187
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d207612e3cba97c108af817135a46e7bc9cc05ec08c71123cba020f8561bdba4
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08ad4f20a1fc4d01dd7776b063f1c7e8407abd02883f001aa8104a2ad0539776
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b2601e1c630be4d03abe53e6c9f6eeb50259e09077bbed2f0773274a364431
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": 0.5781333333333334,
6
  "eval_steps": 500,
7
- "global_step": 2710,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2728,6 +2728,16 @@
2728
  "mean_token_accuracy": 0.7509155049920082,
2729
  "num_tokens": 12586250.0,
2730
  "step": 2710
 
 
 
 
 
 
 
 
 
 
2731
  }
2732
  ],
2733
  "logging_steps": 10,
@@ -2747,7 +2757,7 @@
2747
  "attributes": {}
2748
  }
2749
  },
2750
- "total_flos": 5.966754642983731e+16,
2751
  "train_batch_size": 4,
2752
  "trial_name": null,
2753
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5802666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 2720,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2728
  "mean_token_accuracy": 0.7509155049920082,
2729
  "num_tokens": 12586250.0,
2730
  "step": 2710
2731
+ },
2732
+ {
2733
+ "entropy": 0.9664455614984035,
2734
+ "epoch": 0.5802666666666667,
2735
+ "grad_norm": 0.2820577323436737,
2736
+ "learning_rate": 8.347281860603375e-05,
2737
+ "loss": 1.0676399230957032,
2738
+ "mean_token_accuracy": 0.7622367069125175,
2739
+ "num_tokens": 12635296.0,
2740
+ "step": 2720
2741
  }
2742
  ],
2743
  "logging_steps": 10,
 
2757
  "attributes": {}
2758
  }
2759
  },
2760
+ "total_flos": 5.99009267928361e+16,
2761
  "train_batch_size": 4,
2762
  "trial_name": null,
2763
  "trial_params": null