Hugging Face's logo

madhuHuggingface
/
functiongemma-vpc-finetunedv2

Transformers
Safetensors
Generated from Trainer
trl
unsloth
sft
Model card Files
xet
 Community
madhuHuggingface commited on
Commit
faba664
·
verified ·
1 Parent(s): b0718a1

Training in progress, step 5000, checkpoint

Browse files
Files changed (4) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/scheduler.pt +1 -1
  4. last-checkpoint/trainer_state.json +73 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1087e4a0b3f3c50858aaa17da0f7f26270ae7243622ee70c50ee678c76b041c
3
  size 121537408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e3f886bf7f8655835492083a117bcce51363aebe25019ebed83bdff00c063a
3
  size 121537408
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78ce1e7d2e218c6ffb0ee36f88013c777ef07192679ce1147a7f52fc07a3b389
3
  size 62000725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:576a2e37a6fcf68693d2451e55f8c2afd68db095465943326619ce2a3ff676b1
3
  size 62000725
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c7d9ebd4185557c61c160a6357a2c3da0202e4806e8f3f679ac8bee0416df92
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9265dddd9699a4c694aba82b40eea390095b36c5170875045b924dadbd9286b
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": 1.6815958815958816,
6
  "eval_steps": 500,
7
- "global_step": 4900,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3438,6 +3438,76 @@
3438
  "learning_rate": 8.145013069944896e-05,
3439
  "loss": 0.0021,
3440
  "step": 4900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3441
  }
3442
  ],
3443
  "logging_steps": 10,
@@ -3457,7 +3527,7 @@
3457
  "attributes": {}
3458
  }
3459
  },
3460
- "total_flos": 1.858281325933133e+16,
3461
  "train_batch_size": 2,
3462
  "trial_name": null,
3463
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.7159159159159159,
6
  "eval_steps": 500,
7
+ "global_step": 5000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3438
  "learning_rate": 8.145013069944896e-05,
3439
  "loss": 0.0021,
3440
  "step": 4900
3441
+ },
3442
+ {
3443
+ "epoch": 1.685027885027885,
3444
+ "grad_norm": 0.007503673899918795,
3445
+ "learning_rate": 8.109631132620254e-05,
3446
+ "loss": 0.0018,
3447
+ "step": 4910
3448
+ },
3449
+ {
3450
+ "epoch": 1.6884598884598885,
3451
+ "grad_norm": 0.0341227650642395,
3452
+ "learning_rate": 8.074273720558279e-05,
3453
+ "loss": 0.0042,
3454
+ "step": 4920
3455
+ },
3456
+ {
3457
+ "epoch": 1.691891891891892,
3458
+ "grad_norm": 0.0019191118190065026,
3459
+ "learning_rate": 8.038941292478876e-05,
3460
+ "loss": 0.0036,
3461
+ "step": 4930
3462
+ },
3463
+ {
3464
+ "epoch": 1.6953238953238952,
3465
+ "grad_norm": 0.12887495756149292,
3466
+ "learning_rate": 8.003634306777803e-05,
3467
+ "loss": 0.0024,
3468
+ "step": 4940
3469
+ },
3470
+ {
3471
+ "epoch": 1.6987558987558988,
3472
+ "grad_norm": 0.05117976292967796,
3473
+ "learning_rate": 7.968353221520737e-05,
3474
+ "loss": 0.0037,
3475
+ "step": 4950
3476
+ },
3477
+ {
3478
+ "epoch": 1.702187902187902,
3479
+ "grad_norm": 0.028330549597740173,
3480
+ "learning_rate": 7.93309849443734e-05,
3481
+ "loss": 0.002,
3482
+ "step": 4960
3483
+ },
3484
+ {
3485
+ "epoch": 1.7056199056199057,
3486
+ "grad_norm": 0.018671255558729172,
3487
+ "learning_rate": 7.897870582915288e-05,
3488
+ "loss": 0.002,
3489
+ "step": 4970
3490
+ },
3491
+ {
3492
+ "epoch": 1.709051909051909,
3493
+ "grad_norm": 0.02767166681587696,
3494
+ "learning_rate": 7.862669943994375e-05,
3495
+ "loss": 0.0024,
3496
+ "step": 4980
3497
+ },
3498
+ {
3499
+ "epoch": 1.7124839124839126,
3500
+ "grad_norm": 0.013923927210271358,
3501
+ "learning_rate": 7.827497034360549e-05,
3502
+ "loss": 0.0015,
3503
+ "step": 4990
3504
+ },
3505
+ {
3506
+ "epoch": 1.7159159159159159,
3507
+ "grad_norm": 0.0013914982555434108,
3508
+ "learning_rate": 7.792352310340023e-05,
3509
+ "loss": 0.0018,
3510
+ "step": 5000
3511
  }
3512
  ],
3513
  "logging_steps": 10,
 
3527
  "attributes": {}
3528
  }
3529
  },
3530
+ "total_flos": 1.896207372748877e+16,
3531
  "train_batch_size": 2,
3532
  "trial_name": null,
3533
  "trial_params": null