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
e8ffb05
·
verified ·
1 Parent(s): aa11ddb

Training in progress, step 250, 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:efa549cc9e46f954ceaac48903df8e39114e0834855c6af701a2aeda68a30a74
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5ec024fa0c2323f780da7d968f18a9fe6fc7e7011cff45e765afee334b46cb
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af8bdf477675a0f24a1f9e4f449f1cb4dedfd9fbaaf50501f55743ef4db7aa62
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6df13ccfc1153c0707acb89336e8ef6fdbbe28d8952d57c97e814bc89b8ff07
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:dcbdf5759ee3cb46161fbfb21d4e2c88fd01680ca79c671485101a9fe0d5d622
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb3e2a3e2dabf1eabb87521e32ca4e31f2356a941cbd7de9cd1d5a2ec6f172b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:125a8ede8ffe66310e452b3d6fbb0e3a0a5fd4969d8f52f1acb13713cc04d4b8
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd8d768c572d298dbe5527cbe0d691b96a5defcf0269edb407dc5aaef61061d
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": 0.0512,
6
  "eval_steps": 500,
7
- "global_step": 240,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -258,6 +258,16 @@
258
  "mean_token_accuracy": 0.7490729346871376,
259
  "num_tokens": 1117523.0,
260
  "step": 240
 
 
 
 
 
 
 
 
 
 
261
  }
262
  ],
263
  "logging_steps": 10,
@@ -277,7 +287,7 @@
277
  "attributes": {}
278
  }
279
  },
280
- "total_flos": 5321814854350848.0,
281
  "train_batch_size": 4,
282
  "trial_name": null,
283
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.05333333333333334,
6
  "eval_steps": 500,
7
+ "global_step": 250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
258
  "mean_token_accuracy": 0.7490729346871376,
259
  "num_tokens": 1117523.0,
260
  "step": 240
261
+ },
262
+ {
263
+ "entropy": 1.036650500446558,
264
+ "epoch": 0.05333333333333334,
265
+ "grad_norm": 0.28012844920158386,
266
+ "learning_rate": 8.3e-05,
267
+ "loss": 1.078709030151367,
268
+ "mean_token_accuracy": 0.751419472694397,
269
+ "num_tokens": 1160152.0,
270
+ "step": 250
271
  }
272
  ],
273
  "logging_steps": 10,
 
287
  "attributes": {}
288
  }
289
  },
290
+ "total_flos": 5520463475487744.0,
291
  "train_batch_size": 4,
292
  "trial_name": null,
293
  "trial_params": null