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
a0f378d
·
verified ·
1 Parent(s): 487cdf0

Training in progress, step 3230, 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 sha256:6224b8301f176e3907cdc6ebd99122f7198ad0b9776da28c0e69ab47da4bc7c1
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b6c49a89b818fae7e43099549ab78942ef74295d9f0164274bd532e97032ec
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed5c71ccd2531236ac0873e7c3b21c4c112b99ba3e94d722e52622c1d98d9c6b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64ab1c3fc005d0d2a54b385f20178137782cde6a1af8fd86b4df9afe71dc6f0
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:f12c9114af6536e88da3f583d7fb14a75cc2768b8ea85e6afe72423438db0889
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9268c21752be987a94c355fcd6ae36d5c7bb827e224143b666e97ceab2a849e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efb81c82f9a4ce340a667c5d03539ada05fd84dd8cb42e35aa6e1716e46e1926
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8818d19799a786ad326cffe909aba04c6116b03178ac87a8a92ddf5ce677c742
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": 0.6869333333333333,
6
  "eval_steps": 500,
7
- "global_step": 3220,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3238,6 +3238,16 @@
3238
  "mean_token_accuracy": 0.772594378888607,
3239
  "num_tokens": 14986110.0,
3240
  "step": 3220
 
 
 
 
 
 
 
 
 
 
3241
  }
3242
  ],
3243
  "logging_steps": 10,
@@ -3257,7 +3267,7 @@
3257
  "attributes": {}
3258
  }
3259
  },
3260
- "total_flos": 7.09698806553815e+16,
3261
  "train_batch_size": 4,
3262
  "trial_name": null,
3263
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.6890666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 3230,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3238
  "mean_token_accuracy": 0.772594378888607,
3239
  "num_tokens": 14986110.0,
3240
  "step": 3220
3241
+ },
3242
+ {
3243
+ "entropy": 0.95280120074749,
3244
+ "epoch": 0.6890666666666667,
3245
+ "grad_norm": 0.24981571733951569,
3246
+ "learning_rate": 7.642972005101168e-05,
3247
+ "loss": 1.054494857788086,
3248
+ "mean_token_accuracy": 0.7634354814887047,
3249
+ "num_tokens": 15031665.0,
3250
+ "step": 3230
3251
  }
3252
  ],
3253
  "logging_steps": 10,
 
3267
  "attributes": {}
3268
  }
3269
  },
3270
+ "total_flos": 7.118298431386829e+16,
3271
  "train_batch_size": 4,
3272
  "trial_name": null,
3273
  "trial_params": null