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
fd09479
·
verified ·
1 Parent(s): 1a6f261

Training in progress, step 280, 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:a83e334499e13010cbbf5cecb0bb22142b1face7b601f1296f3bc5ff257e68d7
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc63e0424688f9c0485d1d5a9148a8665ee34253db47b99964b80ae7869ed9ec
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:029229960761235bb4caff3db2819104d0b659f6e15151da4eb01d39467ff942
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f76c33b5ad53221da9a09bdd90e703653f5706e71a24f6125f7fdf277d9683
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0154f3c4d93ae23ed70888eed113babeac6a19733650f59df1defa4fafdf197c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2417fa1b3b71e6d37a773fb88599c00bdf826ce5c9286e6153ace88e25deb0ef
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6142b90a0b9151f21aa0bf0aec5bd23876596c79fceb1461e144f427fbe24d9b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dede46dc4302b123da5b2207ee9f17dd9c7c07b09680b189dc51e5c256034772
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": 0.0576,
6
  "eval_steps": 500,
7
- "global_step": 270,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -288,6 +288,16 @@
288
  "mean_token_accuracy": 0.7550511255860328,
289
  "num_tokens": 1246554.0,
290
  "step": 270
 
 
 
 
 
 
 
 
 
 
291
  }
292
  ],
293
  "logging_steps": 10,
@@ -307,7 +317,7 @@
307
  "attributes": {}
308
  }
309
  },
310
- "total_flos": 5944904466201600.0,
311
  "train_batch_size": 4,
312
  "trial_name": null,
313
  "trial_params": null
 
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,
 
288
  "mean_token_accuracy": 0.7550511255860328,
289
  "num_tokens": 1246554.0,
290
  "step": 270
291
+ },
292
+ {
293
+ "entropy": 0.9443735256791115,
294
+ "epoch": 0.05973333333333333,
295
+ "grad_norm": 0.29017189145088196,
296
+ "learning_rate": 9.300000000000001e-05,
297
+ "loss": 1.0578758239746093,
298
+ "mean_token_accuracy": 0.7694767877459526,
299
+ "num_tokens": 1286049.0,
300
+ "step": 280
301
  }
302
  ],
303
  "logging_steps": 10,
 
317
  "attributes": {}
318
  }
319
  },
320
+ "total_flos": 6124033379794944.0,
321
  "train_batch_size": 4,
322
  "trial_name": null,
323
  "trial_params": null