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
3630d73
·
verified ·
1 Parent(s): 9739ef9

Training in progress, step 4040, 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 sha256:5004d0bc93011547e83654b1c8f6c7b6535bd4d62c24d732cc7286818d9693f4
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3ea49652fbbb2b175f2aaefd89dad902275a26e5f04e2afff4ad74fad31eec
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7861e3cc681453b7a4a1e1ad71f116fec6a8f92bb77e7f69183c0f03c973eb88
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a5b3bf37303de960a4e639eed821190068e427e905b014fa22c80e16e0be996
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:259c5997cebf870a574a43bff1049fed89f339c79d109681ac73f61f763535c5
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55e44189f4dc98b82edd710824ce7cbb3ae7bb51d01013c13cf3ae301059692a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd08e6b9696c3aa35942d342712abd2cec1915bac86a882f56ef1aa7001dddf2
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de73afb2b93f35c21bead0273f09ebb37a775710b76a8e54a2494f9892e0a49
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": 0.8597333333333333,
6
  "eval_steps": 500,
7
- "global_step": 4030,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4048,6 +4048,16 @@
4048
  "mean_token_accuracy": 0.7659091472625732,
4049
  "num_tokens": 18793365.0,
4050
  "step": 4030
 
 
 
 
 
 
 
 
 
 
4051
  }
4052
  ],
4053
  "logging_steps": 10,
@@ -4067,7 +4077,7 @@
4067
  "attributes": {}
4068
  }
4069
  },
4070
- "total_flos": 8.898411948980122e+16,
4071
  "train_batch_size": 4,
4072
  "trial_name": null,
4073
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8618666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 4040,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4048
  "mean_token_accuracy": 0.7659091472625732,
4049
  "num_tokens": 18793365.0,
4050
  "step": 4030
4051
+ },
4052
+ {
4053
+ "entropy": 0.9391368016600609,
4054
+ "epoch": 0.8618666666666667,
4055
+ "grad_norm": 0.22395288944244385,
4056
+ "learning_rate": 6.365279148091182e-05,
4057
+ "loss": 1.0316532135009766,
4058
+ "mean_token_accuracy": 0.7643599301576615,
4059
+ "num_tokens": 18843087.0,
4060
+ "step": 4040
4061
  }
4062
  ],
4063
  "logging_steps": 10,
 
4077
  "attributes": {}
4078
  }
4079
  },
4080
+ "total_flos": 8.921480530406707e+16,
4081
  "train_batch_size": 4,
4082
  "trial_name": null,
4083
  "trial_params": null