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
f70108f
·
verified ·
1 Parent(s): 3955b73

Training in progress, step 4230, 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 sha256:4d0f94290de1a4e1e722e242b8a34afdbd6b7b5fafaf57047f4aee24a4f0ead9
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d39ab7f6d61c2d09a6cf03974e40355a497109199b4753c3534ab48cfcc786b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2347d3a2c3ea10c37ef95d8c21b2e35af1508ba04e4540accb2e861ea926b15a
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98833c1fd5c1451a00e24bbbd320f7199c808541c1270199a2d391b868b3b6dc
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09940bce2ac0f684ab091b086c75fe159bd44b11291f2f21e53d8b5dea2b92c1
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6e3c1e61af94b866e493123ffe6f7d7dcc3d586c1ef95e5d1d1bc8ce2177648
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:165ae415d408bc1fc71b2f69039d1d8e128c1d489ee43d84c3886ad745e5a683
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2435e2dccf8f972effd4cff6680795899e410ebb76faa32cc96302e000ac92
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": 0.9002666666666667,
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,
@@ -4238,6 +4238,16 @@
4238
  "mean_token_accuracy": 0.7604381129145622,
4239
  "num_tokens": 19648234.0,
4240
  "step": 4220
 
 
 
 
 
 
 
 
 
 
4241
  }
4242
  ],
4243
  "logging_steps": 10,
@@ -4257,7 +4267,7 @@
4257
  "attributes": {}
4258
  }
4259
  },
4260
- "total_flos": 9.29866508417833e+16,
4261
  "train_batch_size": 4,
4262
  "trial_name": null,
4263
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.9024,
6
  "eval_steps": 500,
7
+ "global_step": 4230,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4238
  "mean_token_accuracy": 0.7604381129145622,
4239
  "num_tokens": 19648234.0,
4240
  "step": 4220
4241
+ },
4242
+ {
4243
+ "entropy": 0.9963471919298172,
4244
+ "epoch": 0.9024,
4245
+ "grad_norm": 0.22769565880298615,
4246
+ "learning_rate": 6.046216205209842e-05,
4247
+ "loss": 1.1422395706176758,
4248
+ "mean_token_accuracy": 0.7552115090191365,
4249
+ "num_tokens": 19697922.0,
4250
+ "step": 4230
4251
  }
4252
  ],
4253
  "logging_steps": 10,
 
4267
  "attributes": {}
4268
  }
4269
  },
4270
+ "total_flos": 9.32220859108393e+16,
4271
  "train_batch_size": 4,
4272
  "trial_name": null,
4273
  "trial_params": null