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
4a28a9f
·
verified ·
1 Parent(s): e4bf56e

Training in progress, step 150, 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:a04487b11e0f640f09f4ed23c72c8385649b1fd08438d57fbbedbb6a798d2571
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f47639f796592780f52b25e192afa68bf4acb6f07e8eeda9d5136f989802f5
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f281ecd379973caf012ddda74df4aea97dbcc4553957903055ef1afe1230483
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425f572b7e15ce5d3e71c0a0bbc0f2f2b0060b165f55500fedbc4ef8781dfa73
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27f52121e1217ecba835bb0ac8d5ca1dcd4c515954315ed60934935e9ad009f5
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef73cb2ad9ce5708c43b11454569f2a6c3922ed2564781c9fdac7b7df1c18a5
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb511b5274f88689b93046fff8a536b8af17a3a3dca64503b335e8a38d5a613b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2360b5c051850efe138a73d88cec5bae92a688e50d21d633b84e2bdbd726e985
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": 0.029866666666666666,
6
  "eval_steps": 500,
7
- "global_step": 140,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -158,6 +158,16 @@
158
  "mean_token_accuracy": 0.7148015096783638,
159
  "num_tokens": 657261.0,
160
  "step": 140
 
 
 
 
 
 
 
 
 
 
161
  }
162
  ],
163
  "logging_steps": 10,
@@ -177,7 +187,7 @@
177
  "attributes": {}
178
  }
179
  },
180
- "total_flos": 3151360355911680.0,
181
  "train_batch_size": 4,
182
  "trial_name": null,
183
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.032,
6
  "eval_steps": 500,
7
+ "global_step": 150,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
158
  "mean_token_accuracy": 0.7148015096783638,
159
  "num_tokens": 657261.0,
160
  "step": 140
161
+ },
162
+ {
163
+ "entropy": 1.103185237944126,
164
+ "epoch": 0.032,
165
+ "grad_norm": 0.25304746627807617,
166
+ "learning_rate": 4.966666666666667e-05,
167
+ "loss": 1.1829004287719727,
168
+ "mean_token_accuracy": 0.7423724889755249,
169
+ "num_tokens": 704749.0,
170
+ "step": 150
171
  }
172
  ],
173
  "logging_steps": 10,
 
187
  "attributes": {}
188
  }
189
  },
190
+ "total_flos": 3367482990403584.0,
191
  "train_batch_size": 4,
192
  "trial_name": null,
193
  "trial_params": null