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
53064cd
·
verified ·
1 Parent(s): f0bf50d

Training in progress, step 1090, 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:b677436dd94556d37c63fc5af8bf2e83e88c02585e0795eede5b7d18ece090e3
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2266909bcfd2e827eb1644c50ad60182408a20dd4791721e05a2d2424f52d733
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b41fff34c9c4db8f2dae4bdb454365cb800e8b15e086e0c63e975c901857327
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12332144975affdb003534d9320ced91261c5d06175622b0482d316f5fd5c1db
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:139de0f138ce017808ee13c821f8b51685debdb88ec246d824204e8ee58e9121
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0fc4fcfe56c602e1eb84d078940fc4e452ff2da4b06a81af7010bdbb7280548
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ca0f477eea906279e8db214340d995b3591b113025e493facb925355442eaa0
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b02d89b912cb5bc35901cdc6c613c57df00b6380625e03f944bf88eb1c6053
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": 0.2304,
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,
@@ -1098,6 +1098,16 @@
1098
  "mean_token_accuracy": 0.7523389101028443,
1099
  "num_tokens": 5029521.0,
1100
  "step": 1080
 
 
 
 
 
 
 
 
 
 
1101
  }
1102
  ],
1103
  "logging_steps": 10,
@@ -1117,7 +1127,7 @@
1117
  "attributes": {}
1118
  }
1119
  },
1120
- "total_flos": 2.377317437870592e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.23253333333333334,
6
  "eval_steps": 500,
7
+ "global_step": 1090,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1098
  "mean_token_accuracy": 0.7523389101028443,
1099
  "num_tokens": 5029521.0,
1100
  "step": 1080
1101
+ },
1102
+ {
1103
+ "entropy": 0.9586616240441799,
1104
+ "epoch": 0.23253333333333334,
1105
+ "grad_norm": 0.32606637477874756,
1106
+ "learning_rate": 9.814687932051123e-05,
1107
+ "loss": 1.0027738571166993,
1108
+ "mean_token_accuracy": 0.7671207025647163,
1109
+ "num_tokens": 5074269.0,
1110
+ "step": 1090
1111
  }
1112
  ],
1113
  "logging_steps": 10,
 
1127
  "attributes": {}
1128
  }
1129
  },
1130
+ "total_flos": 2.398053747684864e+16,
1131
  "train_batch_size": 4,
1132
  "trial_name": null,
1133
  "trial_params": null