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
56dbfe2
·
verified ·
1 Parent(s): 9715efc

Training in progress, step 2330, 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:b106b4818ec5ea05008eb5b050422fe5726c819138027731ce57e6d209e05ec5
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3082fb894dbd61eebf0ce8e1e0178955754520e516c02e6d4de3d6929e7e021
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84ca1e16a06a0139f238e2b4970bb8922cb0df37bcb75916b853369e0df47602
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a766541713bb5cb997e2d6a26f04a7fb9f56a20c1d508ecbbc0e6180d6addcb
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8eccd86466096eb9bbff26b7e597a535bfb4487cf7ca2f6c8978d3f03ae38448
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcdbf33be2e859933ffe1b4d6cf7b3a3cebb6e75037e3ceecd09032fe2f44d39
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a16b2ac695c2eebcd11a420d4ff6561e2aa791c3bd256a5a4a6d8e849ec3238
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5defde01bc6738c098494a3315f8e057dccd48f0861e19102cb32c194b34b83c
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": 0.49493333333333334,
6
  "eval_steps": 500,
7
- "global_step": 2320,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2338,6 +2338,16 @@
2338
  "mean_token_accuracy": 0.7597260788083077,
2339
  "num_tokens": 10785226.0,
2340
  "step": 2320
 
 
 
 
 
 
 
 
 
 
2341
  }
2342
  ],
2343
  "logging_steps": 10,
@@ -2357,7 +2367,7 @@
2357
  "attributes": {}
2358
  }
2359
  },
2360
- "total_flos": 5.113856972875776e+16,
2361
  "train_batch_size": 4,
2362
  "trial_name": null,
2363
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.49706666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 2330,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2338
  "mean_token_accuracy": 0.7597260788083077,
2339
  "num_tokens": 10785226.0,
2340
  "step": 2320
2341
+ },
2342
+ {
2343
+ "entropy": 0.8475333206355572,
2344
+ "epoch": 0.49706666666666666,
2345
+ "grad_norm": 0.30574989318847656,
2346
+ "learning_rate": 8.816715208500922e-05,
2347
+ "loss": 0.9416275978088379,
2348
+ "mean_token_accuracy": 0.7838068321347237,
2349
+ "num_tokens": 10830340.0,
2350
+ "step": 2330
2351
  }
2352
  ],
2353
  "logging_steps": 10,
 
2367
  "attributes": {}
2368
  }
2369
  },
2370
+ "total_flos": 5.134250831680512e+16,
2371
  "train_batch_size": 4,
2372
  "trial_name": null,
2373
  "trial_params": null