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
5055b4a
·
verified ·
1 Parent(s): cdca6c3

Training in progress, step 4220, 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 sha256:0f76044f18c223ade6e0fa98827c1ee3fd8843220ef256b4189991516d30afa6
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0f94290de1a4e1e722e242b8a34afdbd6b7b5fafaf57047f4aee24a4f0ead9
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:749ba94639232768bdd2dba4ae808c1113ca59603ed07c1773a96a9af17872b1
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2347d3a2c3ea10c37ef95d8c21b2e35af1508ba04e4540accb2e861ea926b15a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:973af0dae2e3133743e5d6f9d49088be79977f1e1f02b5e8c8bbef892f7c475f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09940bce2ac0f684ab091b086c75fe159bd44b11291f2f21e53d8b5dea2b92c1
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dde91e0a99ac4899f68ba4f8e0db73bdbf3d3d25f129208822aef8780406c09
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165ae415d408bc1fc71b2f69039d1d8e128c1d489ee43d84c3886ad745e5a683
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": 0.8981333333333333,
6
  "eval_steps": 500,
7
- "global_step": 4210,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4228,6 +4228,16 @@
4228
  "mean_token_accuracy": 0.7573085993528366,
4229
  "num_tokens": 19606557.0,
4230
  "step": 4210
 
 
 
 
 
 
 
 
 
 
4231
  }
4232
  ],
4233
  "logging_steps": 10,
@@ -4247,7 +4257,7 @@
4247
  "attributes": {}
4248
  }
4249
  },
4250
- "total_flos": 9.27818561262121e+16,
4251
  "train_batch_size": 4,
4252
  "trial_name": null,
4253
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.9002666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 4220,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4228
  "mean_token_accuracy": 0.7573085993528366,
4229
  "num_tokens": 19606557.0,
4230
  "step": 4210
4231
+ },
4232
+ {
4233
+ "entropy": 0.9689052537083626,
4234
+ "epoch": 0.9002666666666667,
4235
+ "grad_norm": 0.24019014835357666,
4236
+ "learning_rate": 6.063133929675193e-05,
4237
+ "loss": 1.0610797882080079,
4238
+ "mean_token_accuracy": 0.7604381129145622,
4239
+ "num_tokens": 19648234.0,
4240
+ "step": 4220
4241
  }
4242
  ],
4243
  "logging_steps": 10,
 
4257
  "attributes": {}
4258
  }
4259
  },
4260
+ "total_flos": 9.29866508417833e+16,
4261
  "train_batch_size": 4,
4262
  "trial_name": null,
4263
  "trial_params": null