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
b82c54c
·
verified ·
1 Parent(s): b10b509

Training in progress, step 2790, 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 sha256:446933e758674bdbeab8254eda223f066b9052a14ea7eab235c0581a4dd1a724
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37258b88d4b55629e16ef77e90055c21b06213ac84193378923069465a658e4b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1693d202a270b5264eabf82b65cfd8ab43c97dbd641cadb285d6d279606ca776
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539c9c6d7f6e7b3199c866be2fc7c4562101d864f1ddf7944172916393ed8b04
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18d915098765590b6ff28cf2ed5c38caee02cbbcd9e668d39f3795cc44640341
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9c46983932da8321f2c5dbb8ea5410da30af4d346db8e0b2930998d2eccad2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7dde02378f849a5f969ad88bdffeead677640fc459b4249505e9f49c2e07b50
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8630299177872f010910d690bb332dab07e8ed803dcb5975749e6ae723c534c9
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": 0.5930666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2780,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2798,6 +2798,16 @@
2798
  "mean_token_accuracy": 0.7723072916269302,
2799
  "num_tokens": 12921599.0,
2800
  "step": 2780
 
 
 
 
 
 
 
 
 
 
2801
  }
2802
  ],
2803
  "logging_steps": 10,
@@ -2817,7 +2827,7 @@
2817
  "attributes": {}
2818
  }
2819
  },
2820
- "total_flos": 6.123599007724954e+16,
2821
  "train_batch_size": 4,
2822
  "trial_name": null,
2823
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5952,
6
  "eval_steps": 500,
7
+ "global_step": 2790,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2798
  "mean_token_accuracy": 0.7723072916269302,
2799
  "num_tokens": 12921599.0,
2800
  "step": 2780
2801
+ },
2802
+ {
2803
+ "entropy": 0.9700805857777596,
2804
+ "epoch": 0.5952,
2805
+ "grad_norm": 0.27477312088012695,
2806
+ "learning_rate": 8.256311685229085e-05,
2807
+ "loss": 1.1071263313293458,
2808
+ "mean_token_accuracy": 0.7538750320672989,
2809
+ "num_tokens": 12969810.0,
2810
+ "step": 2790
2811
  }
2812
  ],
2813
  "logging_steps": 10,
 
2827
  "attributes": {}
2828
  }
2829
  },
2830
+ "total_flos": 6.147365107786752e+16,
2831
  "train_batch_size": 4,
2832
  "trial_name": null,
2833
  "trial_params": null