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
accafef
·
verified ·
1 Parent(s): 4477d97

Training in progress, step 2220, 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 sha256:0d5162650ef45a19ce4311a20a25d704ce2f83c7282f2aa471fdfffd0698c67d
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e722f6821e170cb10aea1d64ee3766eeb8012d6dfdb223098199bb02badaaf
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:880d74736d5c7a8ea85372bd7ae85d6bb032081b54b3d9f04ff15bdafec32656
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fda3eca711ef4af84a894bcf0425e1125191921dd5ab84258f437b5cf535d21
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ec598c9c8d8e3b226c23664d2edd7627d15beedca92bf128bfb3c6a9df6ac5d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018f7b237fcff5b579f912a1a7b5a2347c1857242f82e76e8e8ab8ca877169ad
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b174922a9ba45399bf26235083b2592855c68081131934eae05bd9f4a752bb77
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709202b40850888120d28c97c937aac6e7e6daf271f47aeec5732788707f4ad2
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": 0.47146666666666665,
6
  "eval_steps": 500,
7
- "global_step": 2210,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2228,6 +2228,16 @@
2228
  "mean_token_accuracy": 0.7570377990603447,
2229
  "num_tokens": 10258067.0,
2230
  "step": 2210
 
 
 
 
 
 
 
 
 
 
2231
  }
2232
  ],
2233
  "logging_steps": 10,
@@ -2247,7 +2257,7 @@
2247
  "attributes": {}
2248
  }
2249
  },
2250
- "total_flos": 4.863279260890214e+16,
2251
  "train_batch_size": 4,
2252
  "trial_name": null,
2253
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4736,
6
  "eval_steps": 500,
7
+ "global_step": 2220,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2228
  "mean_token_accuracy": 0.7570377990603447,
2229
  "num_tokens": 10258067.0,
2230
  "step": 2210
2231
+ },
2232
+ {
2233
+ "entropy": 1.0285537526011468,
2234
+ "epoch": 0.4736,
2235
+ "grad_norm": 0.18883784115314484,
2236
+ "learning_rate": 8.936902461371302e-05,
2237
+ "loss": 1.1230335235595703,
2238
+ "mean_token_accuracy": 0.7476231440901756,
2239
+ "num_tokens": 10308406.0,
2240
+ "step": 2220
2241
  }
2242
  ],
2243
  "logging_steps": 10,
 
2257
  "attributes": {}
2258
  }
2259
  },
2260
+ "total_flos": 4.885252900273152e+16,
2261
  "train_batch_size": 4,
2262
  "trial_name": null,
2263
  "trial_params": null