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
de3f1ce
·
verified ·
1 Parent(s): 5433532

Training in progress, step 1820, 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 sha256:7d5c5c75b6a428f6efda135271a92a5a1f4a68cda7cd32df21d8d34f8b5de4cd
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa36ee57fa0fa5e15c31d2f865f7364df41840b88c937e5d762d162b9df7d1b7
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:658626deef1d83bddc1b185e6f1766cb44e81213db1eab78802bf96994fe7543
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02f0efeab4993ea513598d37c097ab144db9719aeddd4bbcc3b0dc86d3d4ce5
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:d67075d20afbf5a016a52f76b259b2a5e591e87dcd548f40d73e0c86f8a70711
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00c7f8d8bb8faa43ce153e856a6cbed32c5fa5cf370d15481034ad505eea58e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7502f1bfbc6986292b05274178f485a7ad444610331bfb3c33a5847fca767785
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec7e355efe70a5724b62cb47abf26e944c2b77f2c8b2ed1d6c69747a04bed76
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": 0.38613333333333333,
6
  "eval_steps": 500,
7
- "global_step": 1810,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1828,6 +1828,16 @@
1828
  "mean_token_accuracy": 0.7603183135390281,
1829
  "num_tokens": 8393408.0,
1830
  "step": 1810
 
 
 
 
 
 
 
 
 
 
1831
  }
1832
  ],
1833
  "logging_steps": 10,
@@ -1847,7 +1857,7 @@
1847
  "attributes": {}
1848
  }
1849
  },
1850
- "total_flos": 3.988529611626394e+16,
1851
  "train_batch_size": 4,
1852
  "trial_name": null,
1853
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.38826666666666665,
6
  "eval_steps": 500,
7
+ "global_step": 1820,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1828
  "mean_token_accuracy": 0.7603183135390281,
1829
  "num_tokens": 8393408.0,
1830
  "step": 1810
1831
+ },
1832
+ {
1833
+ "entropy": 0.8498699732124806,
1834
+ "epoch": 0.38826666666666665,
1835
+ "grad_norm": 0.2330222874879837,
1836
+ "learning_rate": 9.324636022838509e-05,
1837
+ "loss": 0.9152523040771484,
1838
+ "mean_token_accuracy": 0.7780576214194298,
1839
+ "num_tokens": 8440947.0,
1840
+ "step": 1820
1841
  }
1842
  ],
1843
  "logging_steps": 10,
 
1857
  "attributes": {}
1858
  }
1859
  },
1860
+ "total_flos": 4.010144578636186e+16,
1861
  "train_batch_size": 4,
1862
  "trial_name": null,
1863
  "trial_params": null