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
9ccff03
·
verified ·
1 Parent(s): 27c775e

Training in progress, step 290, 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:dc63e0424688f9c0485d1d5a9148a8665ee34253db47b99964b80ae7869ed9ec
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6051fbbefff19e058364693c7ab443c185cb140da23bed10cc980597d446db8d
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82f76c33b5ad53221da9a09bdd90e703653f5706e71a24f6125f7fdf277d9683
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c70e864ccca55cdc6e89d131d41bc36e39777d56461c3020d8d1de8c60c650
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2417fa1b3b71e6d37a773fb88599c00bdf826ce5c9286e6153ace88e25deb0ef
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41d3ffbfb03b10da9b4626cd8b9b00bab51013a29a4465045e6f297d3e3e90f3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dede46dc4302b123da5b2207ee9f17dd9c7c07b09680b189dc51e5c256034772
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c8620862e4ed90337eb624028a2be8520e6bf7e74fa5fb67b36338e9e11ff3a
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": 0.05973333333333333,
6
  "eval_steps": 500,
7
- "global_step": 280,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -298,6 +298,16 @@
298
  "mean_token_accuracy": 0.7694767877459526,
299
  "num_tokens": 1286049.0,
300
  "step": 280
 
 
 
 
 
 
 
 
 
 
301
  }
302
  ],
303
  "logging_steps": 10,
@@ -317,7 +327,7 @@
317
  "attributes": {}
318
  }
319
  },
320
- "total_flos": 6124033379794944.0,
321
  "train_batch_size": 4,
322
  "trial_name": null,
323
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.06186666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 290,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
298
  "mean_token_accuracy": 0.7694767877459526,
299
  "num_tokens": 1286049.0,
300
  "step": 280
301
+ },
302
+ {
303
+ "entropy": 0.9980478152632714,
304
+ "epoch": 0.06186666666666667,
305
+ "grad_norm": 0.3078839182853699,
306
+ "learning_rate": 9.633333333333335e-05,
307
+ "loss": 1.1183401107788087,
308
+ "mean_token_accuracy": 0.7594211131334305,
309
+ "num_tokens": 1331161.0,
310
+ "step": 290
311
  }
312
  ],
313
  "logging_steps": 10,
 
327
  "attributes": {}
328
  }
329
  },
330
+ "total_flos": 6330603433494528.0,
331
  "train_batch_size": 4,
332
  "trial_name": null,
333
  "trial_params": null