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
8f2467c
·
verified ·
1 Parent(s): bd65934

Training in progress, step 3690, 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:c110a31da32ffd213cc59e0053a9afa56351942d16adcf5eaddb709a747bdb50
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c728235a28f70c1e97df57a473dff643f9db1346153db530108166d8f0b08a
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58e5e0230eff9b5e794d7b8d1cd83bcbb85fa38445afd970234bb68dcef10fb4
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ce75a80fb9febdc2dacea305435c24147b95ed49ba4d4e6e1ae09377d07ebe
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31e58fd132b14730d384ea8fd82ae553fa932d349d08d387f8d2630fd9bd431c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b0ee53aaa7b15f40d5acaacd65cf41914be86f5b912a706a0603a303c017969
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47c397115142eeea4d4000613982af98eada11892d251ef48622f892e5a6db62
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088a934885c759df7b726589fa840469c0e1efb1e62073d69611f3615ec20d9a
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": 0.7850666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3680,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3698,6 +3698,16 @@
3698
  "mean_token_accuracy": 0.7587296038866043,
3699
  "num_tokens": 17144177.0,
3700
  "step": 3680
 
 
 
 
 
 
 
 
 
 
3701
  }
3702
  ],
3703
  "logging_steps": 10,
@@ -3717,7 +3727,7 @@
3717
  "attributes": {}
3718
  }
3719
  },
3720
- "total_flos": 8.119511633724826e+16,
3721
  "train_batch_size": 4,
3722
  "trial_name": null,
3723
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7872,
6
  "eval_steps": 500,
7
+ "global_step": 3690,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3698
  "mean_token_accuracy": 0.7587296038866043,
3699
  "num_tokens": 17144177.0,
3700
  "step": 3680
3701
+ },
3702
+ {
3703
+ "entropy": 0.9973213374614716,
3704
+ "epoch": 0.7872,
3705
+ "grad_norm": 0.2418157011270523,
3706
+ "learning_rate": 6.936578051443219e-05,
3707
+ "loss": 1.1423637390136718,
3708
+ "mean_token_accuracy": 0.7530387908220291,
3709
+ "num_tokens": 17191263.0,
3710
+ "step": 3690
3711
  }
3712
  ],
3713
  "logging_steps": 10,
 
3727
  "attributes": {}
3728
  }
3729
  },
3730
+ "total_flos": 8.140795865154355e+16,
3731
  "train_batch_size": 4,
3732
  "trial_name": null,
3733
  "trial_params": null