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
67fd587
·
verified ·
1 Parent(s): 092818a

Training in progress, step 1830, 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:fa36ee57fa0fa5e15c31d2f865f7364df41840b88c937e5d762d162b9df7d1b7
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fead4329fabd9d8e540bc3e438954fa85b79564d664d6b1c0400189c474e2da
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e02f0efeab4993ea513598d37c097ab144db9719aeddd4bbcc3b0dc86d3d4ce5
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0629c2ea741d94b4e40d8052500ec300b45bd55dd22a02035c03f1ee3f5846ee
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:d00c7f8d8bb8faa43ce153e856a6cbed32c5fa5cf370d15481034ad505eea58e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be46c4cf76b58df3cba9777140ba4d6af98db57e70d614db6a54602958eef960
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bec7e355efe70a5724b62cb47abf26e944c2b77f2c8b2ed1d6c69747a04bed76
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63f3c2e5d85aa8d27fab46489755fd9ab73b7d8a972e8678fec9b0b9fda7d15
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": 0.38826666666666665,
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,
@@ -1838,6 +1838,16 @@
1838
  "mean_token_accuracy": 0.7780576214194298,
1839
  "num_tokens": 8440947.0,
1840
  "step": 1820
 
 
 
 
 
 
 
 
 
 
1841
  }
1842
  ],
1843
  "logging_steps": 10,
@@ -1857,7 +1867,7 @@
1857
  "attributes": {}
1858
  }
1859
  },
1860
- "total_flos": 4.010144578636186e+16,
1861
  "train_batch_size": 4,
1862
  "trial_name": null,
1863
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.3904,
6
  "eval_steps": 500,
7
+ "global_step": 1830,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1838
  "mean_token_accuracy": 0.7780576214194298,
1839
  "num_tokens": 8440947.0,
1840
  "step": 1820
1841
+ },
1842
+ {
1843
+ "entropy": 0.9348598286509514,
1844
+ "epoch": 0.3904,
1845
+ "grad_norm": 0.25513678789138794,
1846
+ "learning_rate": 9.315923723388986e-05,
1847
+ "loss": 1.041547966003418,
1848
+ "mean_token_accuracy": 0.7705774419009686,
1849
+ "num_tokens": 8486476.0,
1850
+ "step": 1830
1851
  }
1852
  ],
1853
  "logging_steps": 10,
 
1867
  "attributes": {}
1868
  }
1869
  },
1870
+ "total_flos": 4.030720477188096e+16,
1871
  "train_batch_size": 4,
1872
  "trial_name": null,
1873
  "trial_params": null