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
9d1c75c
·
verified ·
1 Parent(s): d25bd26

Training in progress, step 360, 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:cf8ee527fa91aa5dbdcdb819ff11185ee6d1e902df96a1650bf4a6d2e009058c
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d6e359e539a5f26d8a51261ed9f7de39807813a7f8e4bc873d15659124250d
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c6e4c4ad130e31bde8c0eaab8e9d95a7fc24d96382dcef585a0fd79ce24228e
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d14e24ec9ba2864a3c2318d823a53a2af60c551c01c6e252aab5be07988b290
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:b7d2e204c8e6c7ce35f9439cf108ff7970920b5f63992b1b4c1109c1020960ac
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfcf6304d5286485f87450adfab2d89055f68f2f0d8ff1e2ba88b89fcd503781
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60cc17b17b71f67b56c6a43176ee4ccaf356beb51adcc6b22acb39d21228113a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8bb10ddf1edbaebdbec7cc943f8256421c02f5142b106181e6965df5901035a
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": 0.07466666666666667,
6
  "eval_steps": 500,
7
- "global_step": 350,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -368,6 +368,16 @@
368
  "mean_token_accuracy": 0.7645679444074631,
369
  "num_tokens": 1617068.0,
370
  "step": 350
 
 
 
 
 
 
 
 
 
 
371
  }
372
  ],
373
  "logging_steps": 10,
@@ -387,7 +397,7 @@
387
  "attributes": {}
388
  }
389
  },
390
- "total_flos": 7679995589096448.0,
391
  "train_batch_size": 4,
392
  "trial_name": null,
393
  "trial_params": null
 
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,
 
368
  "mean_token_accuracy": 0.7645679444074631,
369
  "num_tokens": 1617068.0,
370
  "step": 350
371
+ },
372
+ {
373
+ "entropy": 1.077889482676983,
374
+ "epoch": 0.0768,
375
+ "grad_norm": 0.24659322202205658,
376
+ "learning_rate": 9.998957347213085e-05,
377
+ "loss": 1.1968301773071288,
378
+ "mean_token_accuracy": 0.7367698416113854,
379
+ "num_tokens": 1661987.0,
380
+ "step": 360
381
  }
382
  ],
383
  "logging_steps": 10,
 
397
  "attributes": {}
398
  }
399
  },
400
+ "total_flos": 7900209611965440.0,
401
  "train_batch_size": 4,
402
  "trial_name": null,
403
  "trial_params": null