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
4142db7
·
verified ·
1 Parent(s): 7abe81b

Training in progress, step 4320, 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 sha256:379e7c09a8435312320fd3f42c51aca14c3b3d141aadd1d5a47d4944761ef87b
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec65f8acf94fe10cc143c226ba5462b13e6dda24f25285d963bd6312f40fb1d8
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d81a6534b019eb61967026cceff175089e80c2ea88d8406d0280932b54ff4c7a
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997f3b3d9b6e131a2612a299ff700310c93f3b8745eb6eed2eca04a25d0efbde
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:c9151967e720f9a7fd521ecc1d8e8412b603cb89d8c94615ec38445c729eac23
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1d0bb8ad0c1af85064a3f208c9fa3130ac81991b66897c5b8fcd8f04de9369
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fef72916f4b6a0705455ef61f800ba9d14316c2b5453a4c0c19e5f0c81adfba6
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186864ceaa6f1eab7288a39c2c2b16a197e770dda4ea2f2efc87e138c7e21d5b
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": 0.9194666666666667,
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,
@@ -4328,6 +4328,16 @@
4328
  "mean_token_accuracy": 0.7654816180467605,
4329
  "num_tokens": 20070846.0,
4330
  "step": 4310
 
 
 
 
 
 
 
 
 
 
4331
  }
4332
  ],
4333
  "logging_steps": 10,
@@ -4347,7 +4357,7 @@
4347
  "attributes": {}
4348
  }
4349
  },
4350
- "total_flos": 9.49961984250839e+16,
4351
  "train_batch_size": 4,
4352
  "trial_name": null,
4353
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.9216,
6
  "eval_steps": 500,
7
+ "global_step": 4320,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4328
  "mean_token_accuracy": 0.7654816180467605,
4329
  "num_tokens": 20070846.0,
4330
  "step": 4310
4331
+ },
4332
+ {
4333
+ "entropy": 0.9637592114508152,
4334
+ "epoch": 0.9216,
4335
+ "grad_norm": 0.23460128903388977,
4336
+ "learning_rate": 5.893416972713217e-05,
4337
+ "loss": 1.0039209365844726,
4338
+ "mean_token_accuracy": 0.763984477519989,
4339
+ "num_tokens": 20116649.0,
4340
+ "step": 4320
4341
  }
4342
  ],
4343
  "logging_steps": 10,
 
4357
  "attributes": {}
4358
  }
4359
  },
4360
+ "total_flos": 9.523107475828224e+16,
4361
  "train_batch_size": 4,
4362
  "trial_name": null,
4363
  "trial_params": null