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
5e49c83
·
verified ·
1 Parent(s): 079d4dd

Training in progress, step 5100, 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 sha256:95e3f886bf7f8655835492083a117bcce51363aebe25019ebed83bdff00c063a
3
  size 121537408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9a0916e32cf16476644511d9ffe5d31eee246d2d662a73a22828412990a1d0
3
  size 121537408
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:576a2e37a6fcf68693d2451e55f8c2afd68db095465943326619ce2a3ff676b1
3
  size 62000725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d990b928f06002bc69a9c6b3abb5f48694c85ac9ddbdc442f3d5e77dc80d39
3
  size 62000725
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9265dddd9699a4c694aba82b40eea390095b36c5170875045b924dadbd9286b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99e2a0762ef0f1e0775dbd99ea0cf6de40b6502d38e53e0af28ba712bd9dbcb
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": 1.7159159159159159,
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,
@@ -3508,6 +3508,76 @@
3508
  "learning_rate": 7.792352310340023e-05,
3509
  "loss": 0.0018,
3510
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3511
  }
3512
  ],
3513
  "logging_steps": 10,
@@ -3527,7 +3597,7 @@
3527
  "attributes": {}
3528
  }
3529
  },
3530
- "total_flos": 1.896207372748877e+16,
3531
  "train_batch_size": 2,
3532
  "trial_name": null,
3533
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.7502359502359504,
6
  "eval_steps": 500,
7
+ "global_step": 5100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3508
  "learning_rate": 7.792352310340023e-05,
3509
  "loss": 0.0018,
3510
  "step": 5000
3511
+ },
3512
+ {
3513
+ "epoch": 1.7193479193479193,
3514
+ "grad_norm": 0.0013015484437346458,
3515
+ "learning_rate": 7.757236227893318e-05,
3516
+ "loss": 0.0021,
3517
+ "step": 5010
3518
+ },
3519
+ {
3520
+ "epoch": 1.7227799227799228,
3521
+ "grad_norm": 0.0004931904259137809,
3522
+ "learning_rate": 7.72214924260938e-05,
3523
+ "loss": 0.002,
3524
+ "step": 5020
3525
+ },
3526
+ {
3527
+ "epoch": 1.7262119262119262,
3528
+ "grad_norm": 0.009957478381693363,
3529
+ "learning_rate": 7.687091809699638e-05,
3530
+ "loss": 0.0029,
3531
+ "step": 5030
3532
+ },
3533
+ {
3534
+ "epoch": 1.7296439296439297,
3535
+ "grad_norm": 0.11892268806695938,
3536
+ "learning_rate": 7.65206438399213e-05,
3537
+ "loss": 0.0022,
3538
+ "step": 5040
3539
+ },
3540
+ {
3541
+ "epoch": 1.733075933075933,
3542
+ "grad_norm": 0.0022030468098819256,
3543
+ "learning_rate": 7.617067419925575e-05,
3544
+ "loss": 0.0017,
3545
+ "step": 5050
3546
+ },
3547
+ {
3548
+ "epoch": 1.7365079365079366,
3549
+ "grad_norm": 0.03281094506382942,
3550
+ "learning_rate": 7.5821013715435e-05,
3551
+ "loss": 0.0074,
3552
+ "step": 5060
3553
+ },
3554
+ {
3555
+ "epoch": 1.7399399399399398,
3556
+ "grad_norm": 0.022144928574562073,
3557
+ "learning_rate": 7.547166692488328e-05,
3558
+ "loss": 0.0034,
3559
+ "step": 5070
3560
+ },
3561
+ {
3562
+ "epoch": 1.7433719433719435,
3563
+ "grad_norm": 0.011239253915846348,
3564
+ "learning_rate": 7.51226383599551e-05,
3565
+ "loss": 0.0056,
3566
+ "step": 5080
3567
+ },
3568
+ {
3569
+ "epoch": 1.7468039468039467,
3570
+ "grad_norm": 0.05916529521346092,
3571
+ "learning_rate": 7.477393254887627e-05,
3572
+ "loss": 0.0038,
3573
+ "step": 5090
3574
+ },
3575
+ {
3576
+ "epoch": 1.7502359502359504,
3577
+ "grad_norm": 0.007019964046776295,
3578
+ "learning_rate": 7.442555401568545e-05,
3579
+ "loss": 0.0024,
3580
+ "step": 5100
3581
  }
3582
  ],
3583
  "logging_steps": 10,
 
3597
  "attributes": {}
3598
  }
3599
  },
3600
+ "total_flos": 1.934092640555597e+16,
3601
  "train_batch_size": 2,
3602
  "trial_name": null,
3603
  "trial_params": null