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
387b635
·
verified ·
1 Parent(s): 3c61ae6

Training in progress, step 3260, 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 sha256:22ed3532f5b11e54de85642629efcfd9f7c0e2a2770508cbceb3134a01f156ec
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ceb84b623ea4d78dc2e4beb3d7672de0f0e5c8e936a1736b07631a92c841f7c
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfba78d9a9f1c83bf8c3051e70ab0dff569dd18ef23936e1f56d5a86c28d8343
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a464d9caf675edf8b54dd822c981016f50c5bbbc3d772937597812e5d1772e
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0528a8e731164fe038b69287f829516372e3210481061b2bb434269a6b516298
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46246c8e49d8f2613f3d43304f7e4c0dd732495aff5a0e5d355f2bc1027f637a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ea07e7d812f63f155b75aaffd73c48f3d2b8161636db0769e0c9e2e451ee3f1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591c0e54afee71052c7df60f252065be39eb5d9debe3b0db8b4975811aaf703b
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": 0.6933333333333334,
6
  "eval_steps": 500,
7
- "global_step": 3250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3268,6 +3268,16 @@
3268
  "mean_token_accuracy": 0.7773910194635392,
3269
  "num_tokens": 15117055.0,
3270
  "step": 3250
 
 
 
 
 
 
 
 
 
 
3271
  }
3272
  ],
3273
  "logging_steps": 10,
@@ -3287,7 +3297,7 @@
3287
  "attributes": {}
3288
  }
3289
  },
3290
- "total_flos": 7.158806781067469e+16,
3291
  "train_batch_size": 4,
3292
  "trial_name": null,
3293
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.6954666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 3260,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3268
  "mean_token_accuracy": 0.7773910194635392,
3269
  "num_tokens": 15117055.0,
3270
  "step": 3250
3271
+ },
3272
+ {
3273
+ "entropy": 0.9285655155777931,
3274
+ "epoch": 0.6954666666666667,
3275
+ "grad_norm": 0.24558193981647491,
3276
+ "learning_rate": 7.59875551900786e-05,
3277
+ "loss": 1.037491226196289,
3278
+ "mean_token_accuracy": 0.7648348346352577,
3279
+ "num_tokens": 15164096.0,
3280
+ "step": 3260
3281
  }
3282
  ],
3283
  "logging_steps": 10,
 
3297
  "attributes": {}
3298
  }
3299
  },
3300
+ "total_flos": 7.18088856287447e+16,
3301
  "train_batch_size": 4,
3302
  "trial_name": null,
3303
  "trial_params": null