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
e3388ba
·
verified ·
1 Parent(s): 98b3311

Training in progress, step 4700, 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:d9891707facbf59cb701e4e90396bb1b791554a7e357f79370284f032e8b2514
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2a68f7d9e0a543fe75b7163a399cf5b0bf1a0ef1750338f105db7351e36270
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d27201866dc283b390acb05f52c519567dd9a07cf765880dcaf0b0d9c6fbe32a
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f81b6d162fd96f7d11cb719f3fcf99dac6824efbac7feecd4fd27c5e87e2265
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:effd1a63ea106f1c978690dd1bfdc7e9c430740a23dccf7aad02d01b79cb685a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c61da9b117d62f98bb1ace4af08410b60db8fefb001196c18c05e0b9940a8f
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be13bfa65e548520ace5cebaf073676c6f5dc87bc0a9c77183829a44f1ae3b98
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da625ffd446e8c6673e23bcb9af0578aec3b58f68e107c37a452176de1fa5e45
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": 1.0004266666666666,
6
  "eval_steps": 500,
7
- "global_step": 4690,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4708,6 +4708,16 @@
4708
  "mean_token_accuracy": 0.7673146160025346,
4709
  "num_tokens": 21789348.0,
4710
  "step": 4690
 
 
 
 
 
 
 
 
 
 
4711
  }
4712
  ],
4713
  "logging_steps": 10,
@@ -4727,7 +4737,7 @@
4727
  "attributes": {}
4728
  }
4729
  },
4730
- "total_flos": 1.0316783650958131e+17,
4731
  "train_batch_size": 4,
4732
  "trial_name": null,
4733
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.00256,
6
  "eval_steps": 500,
7
+ "global_step": 4700,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4708
  "mean_token_accuracy": 0.7673146160025346,
4709
  "num_tokens": 21789348.0,
4710
  "step": 4690
4711
+ },
4712
+ {
4713
+ "entropy": 0.9121152207255363,
4714
+ "epoch": 1.00256,
4715
+ "grad_norm": 0.2546738386154175,
4716
+ "learning_rate": 5.240476485367317e-05,
4717
+ "loss": 0.9231260299682618,
4718
+ "mean_token_accuracy": 0.7732596561312676,
4719
+ "num_tokens": 21834781.0,
4720
+ "step": 4700
4721
  }
4722
  ],
4723
  "logging_steps": 10,
 
4737
  "attributes": {}
4738
  }
4739
  },
4740
+ "total_flos": 1.0338854618522726e+17,
4741
  "train_batch_size": 4,
4742
  "trial_name": null,
4743
  "trial_params": null