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
21af9e7
·
verified ·
1 Parent(s): ab0fa01

Training in progress, step 4310, 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 sha256:591057de2045f91c06d92bacd46c8c670bbcdeb3679439cc3171c6fa6b1d2b5e
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379e7c09a8435312320fd3f42c51aca14c3b3d141aadd1d5a47d4944761ef87b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c10e7a8390d425d69b7e7129c842d44526d3329311272fade0d43d672c13788
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81a6534b019eb61967026cceff175089e80c2ea88d8406d0280932b54ff4c7a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1192914ebd2625f2ef9c95d07fc13f494650b554ecb7448bc203744491dcd281
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9151967e720f9a7fd521ecc1d8e8412b603cb89d8c94615ec38445c729eac23
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac321c0e85ad319b7f8df05655fea5c1a7e38017586ce3b92ba36567667240e9
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef72916f4b6a0705455ef61f800ba9d14316c2b5453a4c0c19e5f0c81adfba6
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": 0.9173333333333333,
6
  "eval_steps": 500,
7
- "global_step": 4300,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4318,6 +4318,16 @@
4318
  "mean_token_accuracy": 0.7699793577194214,
4319
  "num_tokens": 20021630.0,
4320
  "step": 4300
 
 
 
 
 
 
 
 
 
 
4321
  }
4322
  ],
4323
  "logging_steps": 10,
@@ -4337,7 +4347,7 @@
4337
  "attributes": {}
4338
  }
4339
  },
4340
- "total_flos": 9.476189885148058e+16,
4341
  "train_batch_size": 4,
4342
  "trial_name": null,
4343
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.9194666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 4310,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4318
  "mean_token_accuracy": 0.7699793577194214,
4319
  "num_tokens": 20021630.0,
4320
  "step": 4300
4321
+ },
4322
+ {
4323
+ "entropy": 0.930675259232521,
4324
+ "epoch": 0.9194666666666667,
4325
+ "grad_norm": 0.23214256763458252,
4326
+ "learning_rate": 5.9104401994242786e-05,
4327
+ "loss": 1.0291691780090333,
4328
+ "mean_token_accuracy": 0.7654816180467605,
4329
+ "num_tokens": 20070846.0,
4330
+ "step": 4310
4331
  }
4332
  ],
4333
  "logging_steps": 10,
 
4347
  "attributes": {}
4348
  }
4349
  },
4350
+ "total_flos": 9.49961984250839e+16,
4351
  "train_batch_size": 4,
4352
  "trial_name": null,
4353
  "trial_params": null