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
9a3a1ed
·
verified ·
1 Parent(s): e00ff2f

Training in progress, step 370, 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:a0d6e359e539a5f26d8a51261ed9f7de39807813a7f8e4bc873d15659124250d
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5304af3f27d3534d351511fca5e6a6863ebbafe222d93778ef73271a7fae5f2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d14e24ec9ba2864a3c2318d823a53a2af60c551c01c6e252aab5be07988b290
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69ffd45f83268adebe065f312dfd395bd1507435cef0e4e4d1146fd0b39e3c2f
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:cfcf6304d5286485f87450adfab2d89055f68f2f0d8ff1e2ba88b89fcd503781
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9221be7cf0b53d9897129a89b43f1ca268fdebcfb1504935f4e54c55403b602
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8bb10ddf1edbaebdbec7cc943f8256421c02f5142b106181e6965df5901035a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b36df719885e8c29c64e277b702d22ef4d9ad1644bbb4180ff17df8ae4af2cc
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": 0.0768,
6
  "eval_steps": 500,
7
- "global_step": 360,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -378,6 +378,16 @@
378
  "mean_token_accuracy": 0.7367698416113854,
379
  "num_tokens": 1661987.0,
380
  "step": 360
 
 
 
 
 
 
 
 
 
 
381
  }
382
  ],
383
  "logging_steps": 10,
@@ -397,7 +407,7 @@
397
  "attributes": {}
398
  }
399
  },
400
- "total_flos": 7900209611965440.0,
401
  "train_batch_size": 4,
402
  "trial_name": null,
403
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.07893333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 370,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
378
  "mean_token_accuracy": 0.7367698416113854,
379
  "num_tokens": 1661987.0,
380
  "step": 360
381
+ },
382
+ {
383
+ "entropy": 1.0857299536466598,
384
+ "epoch": 0.07893333333333333,
385
+ "grad_norm": 0.31553569436073303,
386
+ "learning_rate": 9.99857397113579e-05,
387
+ "loss": 1.1405964851379395,
388
+ "mean_token_accuracy": 0.7424520552158356,
389
+ "num_tokens": 1712075.0,
390
+ "step": 370
391
  }
392
  ],
393
  "logging_steps": 10,
 
407
  "attributes": {}
408
  }
409
  },
410
+ "total_flos": 8147477264587776.0,
411
  "train_batch_size": 4,
412
  "trial_name": null,
413
  "trial_params": null