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
9fa7e19
·
verified ·
1 Parent(s): 1edb2dc

Training in progress, step 500, 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 sha256:99b20e3dc241ba7e61559848a4782261510aeb595780c8b6ba37d2e8cd071e73
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222f354ce672e26e119a4df981d0a477189667641a94131f5247803c806632e2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d11fc1e3f068586a108c35f0e84046ed075886913c14e8aab2062ed522abebb
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c957d847f6a5729353e8d7d7eb25041514559e2b32562cb3d0b9ad19f3ecfc9d
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22618160cbfa09502376be3800a7692462b312dee3f727003804d83614555a3d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d57511ac1749e127e707489114310b0a5924c2367e986c010bc6535bb404725
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:791bd3b5bf2fe8605f5fb8b3e81e0b70c8390e444ae91052abb3ee7a092dd572
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ee2fe33536c5ce94544af34c4eb4758956d214568dce7ea91d805d4d22272e
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": 0.10453333333333334,
6
  "eval_steps": 500,
7
- "global_step": 490,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -508,6 +508,16 @@
508
  "mean_token_accuracy": 0.7602177545428276,
509
  "num_tokens": 2263172.0,
510
  "step": 490
 
 
 
 
 
 
 
 
 
 
511
  }
512
  ],
513
  "logging_steps": 10,
@@ -527,7 +537,7 @@
527
  "attributes": {}
528
  }
529
  },
530
- "total_flos": 1.0758801390329856e+16,
531
  "train_batch_size": 4,
532
  "trial_name": null,
533
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.10666666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
508
  "mean_token_accuracy": 0.7602177545428276,
509
  "num_tokens": 2263172.0,
510
  "step": 490
511
+ },
512
+ {
513
+ "entropy": 1.1295288607478142,
514
+ "epoch": 0.10666666666666667,
515
+ "grad_norm": 0.2654035985469818,
516
+ "learning_rate": 9.988142716436546e-05,
517
+ "loss": 1.2499847412109375,
518
+ "mean_token_accuracy": 0.7319100961089134,
519
+ "num_tokens": 2309133.0,
520
+ "step": 500
521
  }
522
  ],
523
  "logging_steps": 10,
 
537
  "attributes": {}
538
  }
539
  },
540
+ "total_flos": 1.0975518808154112e+16,
541
  "train_batch_size": 4,
542
  "trial_name": null,
543
  "trial_params": null