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
d7968aa
·
verified ·
1 Parent(s): fa75d1f

Training in progress, step 270, 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 sha256:8477d97f0f48c38ec48bc20fd2a51da4e65c2b59ee067d4bbbd8b16e7ef9981e
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a83e334499e13010cbbf5cecb0bb22142b1face7b601f1296f3bc5ff257e68d7
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:608649d6ec7871c102e70622a672a52934270f9051b887041d54a8b8855d6a35
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029229960761235bb4caff3db2819104d0b659f6e15151da4eb01d39467ff942
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82106f0380ed5db449d764d56c6466999dcdc4f9323c841d007c147f15ec6ca5
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0154f3c4d93ae23ed70888eed113babeac6a19733650f59df1defa4fafdf197c
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a941f8a91c7960f64855a3046174518210ad0dacebcb71448a3b549b0ce4ecff
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6142b90a0b9151f21aa0bf0aec5bd23876596c79fceb1461e144f427fbe24d9b
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": 0.055466666666666664,
6
  "eval_steps": 500,
7
- "global_step": 260,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -278,6 +278,16 @@
278
  "mean_token_accuracy": 0.7475032344460487,
279
  "num_tokens": 1203153.0,
280
  "step": 260
 
 
 
 
 
 
 
 
 
 
281
  }
282
  ],
283
  "logging_steps": 10,
@@ -297,7 +307,7 @@
297
  "attributes": {}
298
  }
299
  },
300
- "total_flos": 5735612828163072.0,
301
  "train_batch_size": 4,
302
  "trial_name": null,
303
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.0576,
6
  "eval_steps": 500,
7
+ "global_step": 270,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
278
  "mean_token_accuracy": 0.7475032344460487,
279
  "num_tokens": 1203153.0,
280
  "step": 260
281
+ },
282
+ {
283
+ "entropy": 1.0000992961227895,
284
+ "epoch": 0.0576,
285
+ "grad_norm": 0.2648380696773529,
286
+ "learning_rate": 8.966666666666666e-05,
287
+ "loss": 1.0818438529968262,
288
+ "mean_token_accuracy": 0.7550511255860328,
289
+ "num_tokens": 1246554.0,
290
+ "step": 270
291
  }
292
  ],
293
  "logging_steps": 10,
 
307
  "attributes": {}
308
  }
309
  },
310
+ "total_flos": 5944904466201600.0,
311
  "train_batch_size": 4,
312
  "trial_name": null,
313
  "trial_params": null