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
2e086c5
·
verified ·
1 Parent(s): e70351e

Training in progress, step 300, 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 sha256:6051fbbefff19e058364693c7ab443c185cb140da23bed10cc980597d446db8d
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af425da52570a98f34d1a384e039e2e483ed4a5b53a2df4e79aaf16ceaac5d1a
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63c70e864ccca55cdc6e89d131d41bc36e39777d56461c3020d8d1de8c60c650
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277e32b2650dca6189545354afd8579d4fd2e96eca617720f6f93ba03fb51750
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41d3ffbfb03b10da9b4626cd8b9b00bab51013a29a4465045e6f297d3e3e90f3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf93f0953cf38059935f8a861883443194c60319e053dc70b90e0b5d5053d6a0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c8620862e4ed90337eb624028a2be8520e6bf7e74fa5fb67b36338e9e11ff3a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e5c970667d2882cfe99c3bf0a16d854cd2e60422a1ab22dee6d08a0bcb0952b
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": 0.06186666666666667,
6
  "eval_steps": 500,
7
- "global_step": 290,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -308,6 +308,16 @@
308
  "mean_token_accuracy": 0.7594211131334305,
309
  "num_tokens": 1331161.0,
310
  "step": 290
 
 
 
 
 
 
 
 
 
 
311
  }
312
  ],
313
  "logging_steps": 10,
@@ -327,7 +337,7 @@
327
  "attributes": {}
328
  }
329
  },
330
- "total_flos": 6330603433494528.0,
331
  "train_batch_size": 4,
332
  "trial_name": null,
333
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.064,
6
  "eval_steps": 500,
7
+ "global_step": 300,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
308
  "mean_token_accuracy": 0.7594211131334305,
309
  "num_tokens": 1331161.0,
310
  "step": 290
311
+ },
312
+ {
313
+ "entropy": 0.9343128114938736,
314
+ "epoch": 0.064,
315
+ "grad_norm": 0.253248393535614,
316
+ "learning_rate": 9.966666666666667e-05,
317
+ "loss": 0.9862067222595214,
318
+ "mean_token_accuracy": 0.7730094477534294,
319
+ "num_tokens": 1375777.0,
320
+ "step": 300
321
  }
322
  ],
323
  "logging_steps": 10,
 
337
  "attributes": {}
338
  }
339
  },
340
+ "total_flos": 6542364323549184.0,
341
  "train_batch_size": 4,
342
  "trial_name": null,
343
  "trial_params": null