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
9355e55
·
verified ·
1 Parent(s): b3786e1

Training in progress, step 2010, 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 sha256:6e27c0323180173769ac19c24ccc858115ef66a00697f4ac2b8d6ba758cd3aa2
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eafdadecfb66d8ce61332e96e12ee21625a0f2d0f967440945640b9b5cd8ab2d
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f7baab09d9ca4ce2534ca0ac81f413e19364d0f53fa91defb0a43b3be4152c7
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d291ee3bb6a970484c0f369174ae473335ae38aebe6032291e820975d50ca29
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c31c7a9e073807f0bcbdd3865475a59db62e85533912972220623ae6274019b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770a2fced6bb82c8f3f503b19d48ed853c37107802d7e0dc876e33f6083131e3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d973cb144de29338b3e08d2e2eced07863c8eda7f78a649e9a577059568d5b86
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d1298329643e3eeb3ed02ff8e268dda06122aad0183e0d4c4512f4d6c40cd2
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": 0.4266666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2018,6 +2018,16 @@
2018
  "mean_token_accuracy": 0.7698795303702355,
2019
  "num_tokens": 9268892.0,
2020
  "step": 2000
 
 
 
 
 
 
 
 
 
 
2021
  }
2022
  ],
2023
  "logging_steps": 10,
@@ -2037,7 +2047,7 @@
2037
  "attributes": {}
2038
  }
2039
  },
2040
- "total_flos": 4.400473844052787e+16,
2041
  "train_batch_size": 4,
2042
  "trial_name": null,
2043
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4288,
6
  "eval_steps": 500,
7
+ "global_step": 2010,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2018
  "mean_token_accuracy": 0.7698795303702355,
2019
  "num_tokens": 9268892.0,
2020
  "step": 2000
2021
+ },
2022
+ {
2023
+ "entropy": 0.952321158349514,
2024
+ "epoch": 0.4288,
2025
+ "grad_norm": 0.2332596629858017,
2026
+ "learning_rate": 9.15036386093598e-05,
2027
+ "loss": 1.0610048294067382,
2028
+ "mean_token_accuracy": 0.7620892718434333,
2029
+ "num_tokens": 9317142.0,
2030
+ "step": 2010
2031
  }
2032
  ],
2033
  "logging_steps": 10,
 
2047
  "attributes": {}
2048
  }
2049
  },
2050
+ "total_flos": 4.422885460253184e+16,
2051
  "train_batch_size": 4,
2052
  "trial_name": null,
2053
  "trial_params": null