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
c4603d2
·
verified ·
1 Parent(s): 7479468

Training in progress, step 1880, 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:b7f7c08832e92f3eeaa3fffe9fcce3c0dad0fb6473cfb08d2095dbee016d00a7
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b21bd8936658e5150f3047874ba691c8a210aa08bfd77a81bb9312a0abc347
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43d094aa248f0598f9d95ed9c986ffa93a3fabcbfc45787cae041ac00ed84917
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd452283deb362d747a69acc15373134cb96b3763aac10c459ff7a5dc9a0a56f
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:cc34e013baf527021face29460cea50f3e631686955bd2ca7ee9759fff2228e1
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab15fa9541989393212b46b5e35cbaaeb3e1e8b00877f3c0e40b3538467f916
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d713ff246b23b74f0424998c9c9a109a8f309e2172ab9e5adad25868e58ead9f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c87f4c2ffbbf44382d4689760dcb3c3df4a1b19df9759f1fb08863cfbe3ff6
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": 0.3989333333333333,
6
  "eval_steps": 500,
7
- "global_step": 1870,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1888,6 +1888,16 @@
1888
  "mean_token_accuracy": 0.7722208425402641,
1889
  "num_tokens": 8665201.0,
1890
  "step": 1870
 
 
 
 
 
 
 
 
 
 
1891
  }
1892
  ],
1893
  "logging_steps": 10,
@@ -1907,7 +1917,7 @@
1907
  "attributes": {}
1908
  }
1909
  },
1910
- "total_flos": 4.115056247781274e+16,
1911
  "train_batch_size": 4,
1912
  "trial_name": null,
1913
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4010666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 1880,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1888
  "mean_token_accuracy": 0.7722208425402641,
1889
  "num_tokens": 8665201.0,
1890
  "step": 1870
1891
+ },
1892
+ {
1893
+ "entropy": 0.9829332500696182,
1894
+ "epoch": 0.4010666666666667,
1895
+ "grad_norm": 0.27002307772636414,
1896
+ "learning_rate": 9.271588668449503e-05,
1897
+ "loss": 1.1377047538757323,
1898
+ "mean_token_accuracy": 0.7662092931568623,
1899
+ "num_tokens": 8707004.0,
1900
+ "step": 1880
1901
  }
1902
  ],
1903
  "logging_steps": 10,
 
1917
  "attributes": {}
1918
  }
1919
  },
1920
+ "total_flos": 4.134666975198413e+16,
1921
  "train_batch_size": 4,
1922
  "trial_name": null,
1923
  "trial_params": null