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
fe346d7
·
verified ·
1 Parent(s): b0fe5aa

Training in progress, step 3170, 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 sha256:749803cc6f30a8ddddbfaa8d909c42223ac848574d87ba6b22a6a24dbf1265a7
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:938f3aaa4d0a1a0f0d622f0f8a936da0c90d397c7d1b537480cd001d01294881
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4410156c81daf459ea4f13f9bfec98479dbced23f4cdedc6c6791cb65641f245
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4261fa0f35f36fcd8e5b9376580bb171ee48c5330fc2bf5157abb1ab166dddac
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2087370115543fb55f65cc232b1dd1c068de72a2f5f799b41c4d6b7bc7f0cd25
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d4f55f44de93efe61c27fd488807e1910d727472c23376d68b9657202aa821
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec0ba3aeafd1b8e7a62426695e2c37bb081525a6591384cba0958e024564900e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d5820fa9451eaa8db6c9330845956e020f49e5d7d79491d1a89fd111892d4e
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": 0.6741333333333334,
6
  "eval_steps": 500,
7
- "global_step": 3160,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3178,6 +3178,16 @@
3178
  "mean_token_accuracy": 0.7670308589935303,
3179
  "num_tokens": 14711920.0,
3180
  "step": 3160
 
 
 
 
 
 
 
 
 
 
3181
  }
3182
  ],
3183
  "logging_steps": 10,
@@ -3197,7 +3207,7 @@
3197
  "attributes": {}
3198
  }
3199
  },
3200
- "total_flos": 6.966268206890189e+16,
3201
  "train_batch_size": 4,
3202
  "trial_name": null,
3203
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.6762666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 3170,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3178
  "mean_token_accuracy": 0.7670308589935303,
3179
  "num_tokens": 14711920.0,
3180
  "step": 3160
3181
+ },
3182
+ {
3183
+ "entropy": 0.9528509542346001,
3184
+ "epoch": 0.6762666666666667,
3185
+ "grad_norm": 0.215078204870224,
3186
+ "learning_rate": 7.730545245795891e-05,
3187
+ "loss": 0.9985583305358887,
3188
+ "mean_token_accuracy": 0.7616261839866638,
3189
+ "num_tokens": 14759139.0,
3190
+ "step": 3170
3191
  }
3192
  ],
3193
  "logging_steps": 10,
 
3207
  "attributes": {}
3208
  }
3209
  },
3210
+ "total_flos": 6.988322953091174e+16,
3211
  "train_batch_size": 4,
3212
  "trial_name": null,
3213
  "trial_params": null