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
fa80b17
·
verified ·
1 Parent(s): e657389

Training in progress, step 2090, 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 sha256:757ffee9f035309f3e94d8424db99c14c9982a0e399cd49f9d7e57587c6ef344
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fcfe1e9428b2f487ecdeddc474d5670e8087aa3d56aac36ba7cbe654cd0577
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c44d01af45036adc5956b69e7802d64494e76fde68065df05f22cd16030d787
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4cb9cfa32d84f90ece33f7d034f5a4f420542b342a5f9ea402c4c14a5e3560
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d30953a6c4219b232dc932b47c5da22b3be2325bb0f179a417955c84590a05a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c06483dd0fd68d6bd892985563eff71b9211f41fce9cb5acdf70c25fd21786
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d57873271a065bcbd42a222528b35e0e783b73a43db85ec19de91f186457823
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f4b5e1b8893855703c0f2c56c490e82239b9024b3a7a1c2b67bb19d4da7f98
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": 0.4437333333333333,
6
  "eval_steps": 500,
7
- "global_step": 2080,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2098,6 +2098,16 @@
2098
  "mean_token_accuracy": 0.7857892021536828,
2099
  "num_tokens": 9624465.0,
2100
  "step": 2080
 
 
 
 
 
 
 
 
 
 
2101
  }
2102
  ],
2103
  "logging_steps": 10,
@@ -2117,7 +2127,7 @@
2117
  "attributes": {}
2118
  }
2119
  },
2120
- "total_flos": 4.568532578169446e+16,
2121
  "train_batch_size": 4,
2122
  "trial_name": null,
2123
  "trial_params": null
 
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,
 
2098
  "mean_token_accuracy": 0.7857892021536828,
2099
  "num_tokens": 9624465.0,
2100
  "step": 2080
2101
+ },
2102
+ {
2103
+ "entropy": 0.9573663167655468,
2104
+ "epoch": 0.4458666666666667,
2105
+ "grad_norm": 0.2500694692134857,
2106
+ "learning_rate": 9.071571217210443e-05,
2107
+ "loss": 1.042325496673584,
2108
+ "mean_token_accuracy": 0.7585179045796394,
2109
+ "num_tokens": 9670927.0,
2110
+ "step": 2090
2111
  }
2112
  ],
2113
  "logging_steps": 10,
 
2127
  "attributes": {}
2128
  }
2129
  },
2130
+ "total_flos": 4.589733900407194e+16,
2131
  "train_batch_size": 4,
2132
  "trial_name": null,
2133
  "trial_params": null