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
1640fa2
·
verified ·
1 Parent(s): 53d22c6

Training in progress, step 2100, 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 sha256:47fcfe1e9428b2f487ecdeddc474d5670e8087aa3d56aac36ba7cbe654cd0577
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88baf6e130dd025d7367cb6b2041757d6dc5dfe0d5a0cfc07c9f0512ceb465ae
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc4cb9cfa32d84f90ece33f7d034f5a4f420542b342a5f9ea402c4c14a5e3560
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398b68cb0514ab9cd4b8a6c865ebd1420b3064a4513ce0a5c01b5651f4a71b8b
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05c06483dd0fd68d6bd892985563eff71b9211f41fce9cb5acdf70c25fd21786
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4749d1b30a709b110e23e61415e2016f4ebf4ae472d68dd081fec452584be44
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5f4b5e1b8893855703c0f2c56c490e82239b9024b3a7a1c2b67bb19d4da7f98
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621e2d22465ecb33c8f957578230e4a8d20454e49cf74c74c56a5af8e4cf8969
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": 0.4458666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2090,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2108,6 +2108,16 @@
2108
  "mean_token_accuracy": 0.7585179045796394,
2109
  "num_tokens": 9670927.0,
2110
  "step": 2090
 
 
 
 
 
 
 
 
 
 
2111
  }
2112
  ],
2113
  "logging_steps": 10,
@@ -2127,7 +2137,7 @@
2127
  "attributes": {}
2128
  }
2129
  },
2130
- "total_flos": 4.589733900407194e+16,
2131
  "train_batch_size": 4,
2132
  "trial_name": null,
2133
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.448,
6
  "eval_steps": 500,
7
+ "global_step": 2100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2108
  "mean_token_accuracy": 0.7585179045796394,
2109
  "num_tokens": 9670927.0,
2110
  "step": 2090
2111
+ },
2112
+ {
2113
+ "entropy": 0.8527260765433311,
2114
+ "epoch": 0.448,
2115
+ "grad_norm": 0.22426480054855347,
2116
+ "learning_rate": 9.061501359834108e-05,
2117
+ "loss": 0.9534576416015625,
2118
+ "mean_token_accuracy": 0.7796914517879486,
2119
+ "num_tokens": 9717399.0,
2120
+ "step": 2100
2121
  }
2122
  ],
2123
  "logging_steps": 10,
 
2137
  "attributes": {}
2138
  }
2139
  },
2140
+ "total_flos": 4.609600564894618e+16,
2141
  "train_batch_size": 4,
2142
  "trial_name": null,
2143
  "trial_params": null