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
0d576e1
·
verified ·
1 Parent(s): df615c4

Training in progress, step 3350, 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:b472b654199caf73d5cb5d2f954ca9d412ae63f453e15bb10b06780efffb5d0e
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc4b212f4b34bd8874d899315d2e60dfbae0c591eb3bf238bbd9ca31178e566
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcc9dac8600093e92e6824f514d93121b6860f3219ee38e132eaf05ee35f49fa
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2240733d1ab5ca97b0d453695d7dcd660453e692f542584436d5408629c5b1b8
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f3a15a609dd69222c755802144ef733eb4308a90ecaad98dd4b46a6d5910978
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d115689a979af8bb48e773b327ba18020e29302259d5e780481635bcc3f51933
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f24b81d8db80ec4d4525377f81deff9eea1b6a666a034271c3130c7fd42bfce3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b8dd5195df4b2c20795af97ed88166297ac00c9a7dd5cb232f96871ec6fbd6
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": 0.7125333333333334,
6
  "eval_steps": 500,
7
- "global_step": 3340,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3358,6 +3358,16 @@
3358
  "mean_token_accuracy": 0.7643374137580394,
3359
  "num_tokens": 15554937.0,
3360
  "step": 3340
 
 
 
 
 
 
 
 
 
 
3361
  }
3362
  ],
3363
  "logging_steps": 10,
@@ -3377,7 +3387,7 @@
3377
  "attributes": {}
3378
  }
3379
  },
3380
- "total_flos": 7.369165424356762e+16,
3381
  "train_batch_size": 4,
3382
  "trial_name": null,
3383
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7146666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 3350,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3358
  "mean_token_accuracy": 0.7643374137580394,
3359
  "num_tokens": 15554937.0,
3360
  "step": 3340
3361
+ },
3362
+ {
3363
+ "entropy": 0.9632456421852111,
3364
+ "epoch": 0.7146666666666667,
3365
+ "grad_norm": 0.21984997391700745,
3366
+ "learning_rate": 7.464443902503968e-05,
3367
+ "loss": 1.0455013275146485,
3368
+ "mean_token_accuracy": 0.7605102032423019,
3369
+ "num_tokens": 15605470.0,
3370
+ "step": 3350
3371
  }
3372
  ],
3373
  "logging_steps": 10,
 
3387
  "attributes": {}
3388
  }
3389
  },
3390
+ "total_flos": 7.393354181059277e+16,
3391
  "train_batch_size": 4,
3392
  "trial_name": null,
3393
  "trial_params": null