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
c927024
·
verified ·
1 Parent(s): ceea809

Training in progress, step 260, 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 sha256:0b5ec024fa0c2323f780da7d968f18a9fe6fc7e7011cff45e765afee334b46cb
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8477d97f0f48c38ec48bc20fd2a51da4e65c2b59ee067d4bbbd8b16e7ef9981e
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6df13ccfc1153c0707acb89336e8ef6fdbbe28d8952d57c97e814bc89b8ff07
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608649d6ec7871c102e70622a672a52934270f9051b887041d54a8b8855d6a35
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eb3e2a3e2dabf1eabb87521e32ca4e31f2356a941cbd7de9cd1d5a2ec6f172b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82106f0380ed5db449d764d56c6466999dcdc4f9323c841d007c147f15ec6ca5
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dd8d768c572d298dbe5527cbe0d691b96a5defcf0269edb407dc5aaef61061d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a941f8a91c7960f64855a3046174518210ad0dacebcb71448a3b549b0ce4ecff
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": 0.05333333333333334,
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,
@@ -268,6 +268,16 @@
268
  "mean_token_accuracy": 0.751419472694397,
269
  "num_tokens": 1160152.0,
270
  "step": 250
 
 
 
 
 
 
 
 
 
 
271
  }
272
  ],
273
  "logging_steps": 10,
@@ -287,7 +297,7 @@
287
  "attributes": {}
288
  }
289
  },
290
- "total_flos": 5520463475487744.0,
291
  "train_batch_size": 4,
292
  "trial_name": null,
293
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.055466666666666664,
6
  "eval_steps": 500,
7
+ "global_step": 260,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
268
  "mean_token_accuracy": 0.751419472694397,
269
  "num_tokens": 1160152.0,
270
  "step": 250
271
+ },
272
+ {
273
+ "entropy": 1.0605042964220046,
274
+ "epoch": 0.055466666666666664,
275
+ "grad_norm": 0.28786003589630127,
276
+ "learning_rate": 8.633333333333334e-05,
277
+ "loss": 1.1537845611572266,
278
+ "mean_token_accuracy": 0.7475032344460487,
279
+ "num_tokens": 1203153.0,
280
+ "step": 260
281
  }
282
  ],
283
  "logging_steps": 10,
 
297
  "attributes": {}
298
  }
299
  },
300
+ "total_flos": 5735612828163072.0,
301
  "train_batch_size": 4,
302
  "trial_name": null,
303
  "trial_params": null