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
3ceea45
·
verified ·
1 Parent(s): fccbd11

Training in progress, step 4350, 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:b65d12637f49dcfa005eae1a2141651cece76024782fe16c9733e4edd5941edc
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f9f3439532048d978298fe6b2934a924aa0bac60bfb16b817a6dde20c2dff2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25265397c506247966c97bcf9ef2e82c557695a8a263b9706c7edf2623521d7b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c73a53a4a22700e85e37dd953ae559a0cd267cfe4afc838eae965748d429c26
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dd7d6ae5e225bdf799ecfa906b56b948028ae05fb2159d3ddb575bdd98fb226
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c5f391fa65afb95f44617a42a26571a32bbb00f45a10e4df4a9c624f9111eb
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dc4ef79f44cda905e5912235a31c458a988c054ee6521bda21bc365fb9f2624
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1274b77ec60a9e624eac35cb1fff799d5ce6501ae9ab4898b6d8d333d7b77929
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": 0.9258666666666666,
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,
@@ -4358,6 +4358,16 @@
4358
  "mean_token_accuracy": 0.7818280473351479,
4359
  "num_tokens": 20202829.0,
4360
  "step": 4340
 
 
 
 
 
 
 
 
 
 
4361
  }
4362
  ],
4363
  "logging_steps": 10,
@@ -4377,7 +4387,7 @@
4377
  "attributes": {}
4378
  }
4379
  },
4380
- "total_flos": 9.565695764798362e+16,
4381
  "train_batch_size": 4,
4382
  "trial_name": null,
4383
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.928,
6
  "eval_steps": 500,
7
+ "global_step": 4350,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4358
  "mean_token_accuracy": 0.7818280473351479,
4359
  "num_tokens": 20202829.0,
4360
  "step": 4340
4361
+ },
4362
+ {
4363
+ "entropy": 0.8829731650650501,
4364
+ "epoch": 0.928,
4365
+ "grad_norm": 0.31879284977912903,
4366
+ "learning_rate": 5.842283882346082e-05,
4367
+ "loss": 0.9750779151916504,
4368
+ "mean_token_accuracy": 0.7774942420423031,
4369
+ "num_tokens": 20248134.0,
4370
+ "step": 4350
4371
  }
4372
  ],
4373
  "logging_steps": 10,
 
4387
  "attributes": {}
4388
  }
4389
  },
4390
+ "total_flos": 9.585621006432154e+16,
4391
  "train_batch_size": 4,
4392
  "trial_name": null,
4393
  "trial_params": null