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
ea19da7
·
verified ·
1 Parent(s): 8837ce0

Training in progress, step 4340, 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:d783fd131ac4d246f39470fde6dfaaaaa140a95661ab424b12450e7fecfb80de
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b65d12637f49dcfa005eae1a2141651cece76024782fe16c9733e4edd5941edc
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89c3bfc03e66b507ba63c4621f08509d221d1d0f5a70e7be9d8ed97fa19e5a65
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25265397c506247966c97bcf9ef2e82c557695a8a263b9706c7edf2623521d7b
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26fa79148bb3f2ed4cc710bdcff469ba6aeec3ceab1ec596990700f4ea27c1c9
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd7d6ae5e225bdf799ecfa906b56b948028ae05fb2159d3ddb575bdd98fb226
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:610f155e20460be233b63e851ca501465c44f781bed5601edf88e458e04a8b85
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dc4ef79f44cda905e5912235a31c458a988c054ee6521bda21bc365fb9f2624
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": 0.9237333333333333,
6
  "eval_steps": 500,
7
- "global_step": 4330,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4348,6 +4348,16 @@
4348
  "mean_token_accuracy": 0.7639551430940628,
4349
  "num_tokens": 20161155.0,
4350
  "step": 4330
 
 
 
 
 
 
 
 
 
 
4351
  }
4352
  ],
4353
  "logging_steps": 10,
@@ -4367,7 +4377,7 @@
4367
  "attributes": {}
4368
  }
4369
  },
4370
- "total_flos": 9.545480340993331e+16,
4371
  "train_batch_size": 4,
4372
  "trial_name": null,
4373
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.9258666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 4340,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4348
  "mean_token_accuracy": 0.7639551430940628,
4349
  "num_tokens": 20161155.0,
4350
  "step": 4330
4351
+ },
4352
+ {
4353
+ "entropy": 0.8422643013298512,
4354
+ "epoch": 0.9258666666666666,
4355
+ "grad_norm": 0.29824700951576233,
4356
+ "learning_rate": 5.85933861001957e-05,
4357
+ "loss": 0.9323680877685547,
4358
+ "mean_token_accuracy": 0.7818280473351479,
4359
+ "num_tokens": 20202829.0,
4360
+ "step": 4340
4361
  }
4362
  ],
4363
  "logging_steps": 10,
 
4377
  "attributes": {}
4378
  }
4379
  },
4380
+ "total_flos": 9.565695764798362e+16,
4381
  "train_batch_size": 4,
4382
  "trial_name": null,
4383
  "trial_params": null