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
6c28431
·
verified ·
1 Parent(s): a2a9d51

Training in progress, step 160, 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 sha256:26f47639f796592780f52b25e192afa68bf4acb6f07e8eeda9d5136f989802f5
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71055204d112a0352eaeb730e04d7cada71c54e2db4c9895168aaf6bac161f5f
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:425f572b7e15ce5d3e71c0a0bbc0f2f2b0060b165f55500fedbc4ef8781dfa73
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9300105f69645a78e8cafbfae6bdebb729a1caf9e718790492c3f348d7a3a3ad
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:aef73cb2ad9ce5708c43b11454569f2a6c3922ed2564781c9fdac7b7df1c18a5
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfb0a36845787ad84ee4edb14ff27f7311542eb37712c2ce4e2eb1fe67e1be4
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2360b5c051850efe138a73d88cec5bae92a688e50d21d633b84e2bdbd726e985
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385d9b2ff8eb3417d1dd96e916d06043c00fb3770964c1dfd252f37e6ba8752a
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": 0.032,
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,
@@ -168,6 +168,16 @@
168
  "mean_token_accuracy": 0.7423724889755249,
169
  "num_tokens": 704749.0,
170
  "step": 150
 
 
 
 
 
 
 
 
 
 
171
  }
172
  ],
173
  "logging_steps": 10,
@@ -187,7 +197,7 @@
187
  "attributes": {}
188
  }
189
  },
190
- "total_flos": 3367482990403584.0,
191
  "train_batch_size": 4,
192
  "trial_name": null,
193
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.034133333333333335,
6
  "eval_steps": 500,
7
+ "global_step": 160,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
168
  "mean_token_accuracy": 0.7423724889755249,
169
  "num_tokens": 704749.0,
170
  "step": 150
171
+ },
172
+ {
173
+ "entropy": 1.085295742750168,
174
+ "epoch": 0.034133333333333335,
175
+ "grad_norm": 2.8501718044281006,
176
+ "learning_rate": 5.300000000000001e-05,
177
+ "loss": 1.1587767601013184,
178
+ "mean_token_accuracy": 0.7412141926586628,
179
+ "num_tokens": 751635.0,
180
+ "step": 160
181
  }
182
  ],
183
  "logging_steps": 10,
 
197
  "attributes": {}
198
  }
199
  },
200
+ "total_flos": 3594717258968064.0,
201
  "train_batch_size": 4,
202
  "trial_name": null,
203
  "trial_params": null