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
268e434
·
verified ·
1 Parent(s): 0ec36b0

Training in progress, step 1230, 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 sha256:39fbd7a3d6217c94b7db508500ab298991ed1850c4ac58e32c8a96f732136ff6
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579c23044cb7c4dfa74628aeec5bf5534e35e174919215e6d9cfe404b2cd7abd
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8eea18e47f62adb7b05b4d2a3824fe7fbc98177ef2305472377597fa898b7317
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3104e4a5a662b42e7dccc408d6348f34c100b7dc61b623236e7655a3bd2e9239
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e89a46997a07bfaa47acacf95ba9f700317474c2958a93fe66e1df02eb9d869
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833c339fb00d36130df4cea88fa6d9aa1151f56cbd984e4ea92c9220fd36810a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffa732fe1546976a8e6a700cbfa883b43a4e2d20983bedfdae9fa8fc2fc85151
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb7030642ba32a68e5269da4db4da3e2b7e14707b86bbb3864a8185c0f37166
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": 0.26026666666666665,
6
  "eval_steps": 500,
7
- "global_step": 1220,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1238,6 +1238,16 @@
1238
  "mean_token_accuracy": 0.7624265968799591,
1239
  "num_tokens": 5684479.0,
1240
  "step": 1220
 
 
 
 
 
 
 
 
 
 
1241
  }
1242
  ],
1243
  "logging_steps": 10,
@@ -1257,7 +1267,7 @@
1257
  "attributes": {}
1258
  }
1259
  },
1260
- "total_flos": 2.693042849672909e+16,
1261
  "train_batch_size": 4,
1262
  "trial_name": null,
1263
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2624,
6
  "eval_steps": 500,
7
+ "global_step": 1230,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1238
  "mean_token_accuracy": 0.7624265968799591,
1239
  "num_tokens": 5684479.0,
1240
  "step": 1220
1241
+ },
1242
+ {
1243
+ "entropy": 0.9518351659178734,
1244
+ "epoch": 0.2624,
1245
+ "grad_norm": 0.2750278413295746,
1246
+ "learning_rate": 9.743707073541978e-05,
1247
+ "loss": 1.0608203887939454,
1248
+ "mean_token_accuracy": 0.7580445930361748,
1249
+ "num_tokens": 5726626.0,
1250
+ "step": 1230
1251
  }
1252
  ],
1253
  "logging_steps": 10,
 
1267
  "attributes": {}
1268
  }
1269
  },
1270
+ "total_flos": 2.713506099866419e+16,
1271
  "train_batch_size": 4,
1272
  "trial_name": null,
1273
  "trial_params": null