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
f76e7a4
·
verified ·
1 Parent(s): 8360c96

Training in progress, step 2070, 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 sha256:91bb3770d253b1a24bad7741fddee6dc5b4f40846e40b7e40278ed99b37a8bfa
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16f87477d5a5cde07c69e4f9f1dfa4276d07cc9a9f4fa8a09b75cc8750caed2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fc32d45c2881816c9c3ac1b828ed2821c49751cd59e80405407443dbae93fa9
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438470c038a96895179b04e47f0ef0118bfaf68a81d1be3f0cc6dd998eca8b43
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92f264adc34fc7515262c2ee598436495113a5f616c855380ef9662306d6c453
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ae9143f68234646a5ea91bd7c90caa59715824b738df3bf8731063060a8bb4
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06e3174d1cda2eaa851aca799d52a3fb5daa9a31a0deff161ae38844159690f0
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6370af1e9b7ec7e2fd813075350b2a0057aff2620434789ee8072fb523650150
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": 0.43946666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2060,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2078,6 +2078,16 @@
2078
  "mean_token_accuracy": 0.7693670354783535,
2079
  "num_tokens": 9537791.0,
2080
  "step": 2060
 
 
 
 
 
 
 
 
 
 
2081
  }
2082
  ],
2083
  "logging_steps": 10,
@@ -2097,7 +2107,7 @@
2097
  "attributes": {}
2098
  }
2099
  },
2100
- "total_flos": 4.527589856418816e+16,
2101
  "train_batch_size": 4,
2102
  "trial_name": null,
2103
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4416,
6
  "eval_steps": 500,
7
+ "global_step": 2070,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2078
  "mean_token_accuracy": 0.7693670354783535,
2079
  "num_tokens": 9537791.0,
2080
  "step": 2060
2081
+ },
2082
+ {
2083
+ "entropy": 0.917995036393404,
2084
+ "epoch": 0.4416,
2085
+ "grad_norm": 0.22210952639579773,
2086
+ "learning_rate": 9.091564461592274e-05,
2087
+ "loss": 1.01414155960083,
2088
+ "mean_token_accuracy": 0.7708904504776001,
2089
+ "num_tokens": 9581893.0,
2090
+ "step": 2070
2091
  }
2092
  ],
2093
  "logging_steps": 10,
 
2107
  "attributes": {}
2108
  }
2109
  },
2110
+ "total_flos": 4.548506403606528e+16,
2111
  "train_batch_size": 4,
2112
  "trial_name": null,
2113
  "trial_params": null