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
a8c9e65
·
verified ·
1 Parent(s): 1d36a3c

Training in progress, step 1080, 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:aaee39d3429fd04041eb97153c8ed2416c794f3ca1cd3b719028844572f773ae
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b677436dd94556d37c63fc5af8bf2e83e88c02585e0795eede5b7d18ece090e3
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc505ffa7602ca9c31cb380c978f30c74e6f330c07bf9c826a553e4d5d75731f
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b41fff34c9c4db8f2dae4bdb454365cb800e8b15e086e0c63e975c901857327
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:f6ead786d67611b1bc6ea0b189c9fe6c35148f3fbf50d8caf39ac88f12063c33
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139de0f138ce017808ee13c821f8b51685debdb88ec246d824204e8ee58e9121
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efd0335654ff33fc2ef31d0d1183d257249034b8a39cd5e36172e39810b6cddd
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca0f477eea906279e8db214340d995b3591b113025e493facb925355442eaa0
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": 0.22826666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1070,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1088,6 +1088,16 @@
1088
  "mean_token_accuracy": 0.7766690820455551,
1089
  "num_tokens": 4974286.0,
1090
  "step": 1070
 
 
 
 
 
 
 
 
 
 
1091
  }
1092
  ],
1093
  "logging_steps": 10,
@@ -1107,7 +1117,7 @@
1107
  "attributes": {}
1108
  }
1109
  },
1110
- "total_flos": 2.3502881401626624e+16,
1111
  "train_batch_size": 4,
1112
  "trial_name": null,
1113
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2304,
6
  "eval_steps": 500,
7
+ "global_step": 1080,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1088
  "mean_token_accuracy": 0.7766690820455551,
1089
  "num_tokens": 4974286.0,
1090
  "step": 1070
1091
+ },
1092
+ {
1093
+ "entropy": 0.9813514620065689,
1094
+ "epoch": 0.2304,
1095
+ "grad_norm": 0.23850619792938232,
1096
+ "learning_rate": 9.819327236522411e-05,
1097
+ "loss": 1.0773870468139648,
1098
+ "mean_token_accuracy": 0.7523389101028443,
1099
+ "num_tokens": 5029521.0,
1100
+ "step": 1080
1101
  }
1102
  ],
1103
  "logging_steps": 10,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.377317437870592e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null