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
58208d6
·
verified ·
1 Parent(s): 0f8a506

Training in progress, step 3870, 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 sha256:8fc51c516202e67d03f1363f44939bcb6ff07c405d032a382f751c1378380879
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5452a8566cef7a10a013cc2e23f291c6477209d9c969a489e18e07b72278dde2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9754fff118bc34519dc6cafdd2e2cd60ce83c9bbee2c9302f181c67bcd317333
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb8d6e54bade816d812f7537c3c90df49073a0c175f7641ec2bff919d3f7aef
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:c5b2891c671fc2302dca69e8ee5767c09e2e237951bcfbd09d793a7d6bd781b7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f0605ad09cba385522745b35ddc474bfc16c97ac22d6ac9e66b243c8f9dd99
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b28712991dc11956e5c2e4b4f10062177c8e32aae407836c6741d8f87ddbbc53
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25cef8ef2ad00fb79aa47d338148491c7979088bc8418196ec70b3e653ecab2b
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": 0.8234666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3860,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3878,6 +3878,16 @@
3878
  "mean_token_accuracy": 0.7554293870925903,
3879
  "num_tokens": 17990860.0,
3880
  "step": 3860
 
 
 
 
 
 
 
 
 
 
3881
  }
3882
  ],
3883
  "logging_steps": 10,
@@ -3897,7 +3907,7 @@
3897
  "attributes": {}
3898
  }
3899
  },
3900
- "total_flos": 8.518950095995085e+16,
3901
  "train_batch_size": 4,
3902
  "trial_name": null,
3903
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8256,
6
  "eval_steps": 500,
7
+ "global_step": 3870,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3878
  "mean_token_accuracy": 0.7554293870925903,
3879
  "num_tokens": 17990860.0,
3880
  "step": 3860
3881
+ },
3882
+ {
3883
+ "entropy": 0.9883775785565376,
3884
+ "epoch": 0.8256,
3885
+ "grad_norm": 0.273813396692276,
3886
+ "learning_rate": 6.645793259897288e-05,
3887
+ "loss": 1.1143600463867187,
3888
+ "mean_token_accuracy": 0.7514252230525017,
3889
+ "num_tokens": 18044403.0,
3890
+ "step": 3870
3891
  }
3892
  ],
3893
  "logging_steps": 10,
 
3907
  "attributes": {}
3908
  }
3909
  },
3910
+ "total_flos": 8.542613460754022e+16,
3911
  "train_batch_size": 4,
3912
  "trial_name": null,
3913
  "trial_params": null