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
d3b1b4f
·
verified ·
1 Parent(s): be08837

Training in progress, step 480, 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 sha256:377450f9d5e72c2a3ac138957ba72da38269ec4e8ace8a689cfafdbdc8e9de67
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e990e391071b8d4048879093997e7db3afcbc95b090b3ec0b577babea240dc91
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2380a7f0a5febe1dc2cd09aa1d226529df0e940571ad9cb0358a30c713970ff
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80cc3e9e43a4c7dfa5ba3c75954929e098eeb95cc02bf2905e26e045b2518ef9
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d4966ec76bc7bc8bb4cdbc928ada4e289b036911fee3cd860685c86f7168807
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e7eaafece8194551464fd0b14320e4e95d30bf2e6e881011be23a5ea286d88
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d98f0d9d23105e8e46650fe3f487dd24428a36e6adf2ab34bc7f6b949f3ec6f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd32ac6c89402773b495c5d8d6f7091f0b550ddd70bc7009ff38b47681cf6cda
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": 0.10026666666666667,
6
  "eval_steps": 500,
7
- "global_step": 470,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -488,6 +488,16 @@
488
  "mean_token_accuracy": 0.7427436165511608,
489
  "num_tokens": 2171365.0,
490
  "step": 470
 
 
 
 
 
 
 
 
 
 
491
  }
492
  ],
493
  "logging_steps": 10,
@@ -507,7 +517,7 @@
507
  "attributes": {}
508
  }
509
  },
510
- "total_flos": 1.0306892223903744e+16,
511
  "train_batch_size": 4,
512
  "trial_name": null,
513
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1024,
6
  "eval_steps": 500,
7
+ "global_step": 480,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
488
  "mean_token_accuracy": 0.7427436165511608,
489
  "num_tokens": 2171365.0,
490
  "step": 470
491
+ },
492
+ {
493
+ "entropy": 0.8950243927538395,
494
+ "epoch": 0.1024,
495
+ "grad_norm": 0.27864041924476624,
496
+ "learning_rate": 9.990405598258212e-05,
497
+ "loss": 0.965212631225586,
498
+ "mean_token_accuracy": 0.773382380604744,
499
+ "num_tokens": 2216186.0,
500
+ "step": 480
501
  }
502
  ],
503
  "logging_steps": 10,
 
517
  "attributes": {}
518
  }
519
  },
520
+ "total_flos": 1.0529665617475584e+16,
521
  "train_batch_size": 4,
522
  "trial_name": null,
523
  "trial_params": null