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
f90e9fd
·
verified ·
1 Parent(s): 108f476

Training in progress, step 3860, 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:a2410ddacea7b473afaac489732934f9c540f497d79cf6b60a98d929ea39df69
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc51c516202e67d03f1363f44939bcb6ff07c405d032a382f751c1378380879
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85e811af2c2a9f963ee406d446900419cdc84ff390a7e74127bda4b4a6405e74
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9754fff118bc34519dc6cafdd2e2cd60ce83c9bbee2c9302f181c67bcd317333
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a0259f8e3bf9c77a92b5e0e3d456145ed86baf8ad5dc82ed5a5a1026b5cb7d6
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b2891c671fc2302dca69e8ee5767c09e2e237951bcfbd09d793a7d6bd781b7
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:453378b63b1b1c33c9a175bc7e074387855366e3868ae732f66d3a9dd7c27f78
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28712991dc11956e5c2e4b4f10062177c8e32aae407836c6741d8f87ddbbc53
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": 0.8213333333333334,
6
  "eval_steps": 500,
7
- "global_step": 3850,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3868,6 +3868,16 @@
3868
  "mean_token_accuracy": 0.7734792202711105,
3869
  "num_tokens": 17939963.0,
3870
  "step": 3850
 
 
 
 
 
 
 
 
 
 
3871
  }
3872
  ],
3873
  "logging_steps": 10,
@@ -3887,7 +3897,7 @@
3887
  "attributes": {}
3888
  }
3889
  },
3890
- "total_flos": 8.495502114897408e+16,
3891
  "train_batch_size": 4,
3892
  "trial_name": null,
3893
  "trial_params": null
 
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,
 
3868
  "mean_token_accuracy": 0.7734792202711105,
3869
  "num_tokens": 17939963.0,
3870
  "step": 3850
3871
+ },
3872
+ {
3873
+ "entropy": 0.985682574659586,
3874
+ "epoch": 0.8234666666666667,
3875
+ "grad_norm": 0.26758262515068054,
3876
+ "learning_rate": 6.662126064136466e-05,
3877
+ "loss": 1.073539638519287,
3878
+ "mean_token_accuracy": 0.7554293870925903,
3879
+ "num_tokens": 17990860.0,
3880
+ "step": 3860
3881
  }
3882
  ],
3883
  "logging_steps": 10,
 
3897
  "attributes": {}
3898
  }
3899
  },
3900
+ "total_flos": 8.518950095995085e+16,
3901
  "train_batch_size": 4,
3902
  "trial_name": null,
3903
  "trial_params": null