EricWesthoff's picture
End of training
33a0473
|
raw
history blame
4.3 kB
metadata
license: other
base_model: microsoft/phi-1_5
tags:
  - generated_from_trainer
model-index:
  - name: phi-1_5-finetuned-SQL
    results: []

phi-1_5-finetuned-SQL

This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3403

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • training_steps: 6000

Training results

Training Loss Epoch Step Validation Loss
2.4485 0.4 100 2.0478
2.0521 0.8 200 1.9223
1.9626 1.2 300 1.8386
1.8707 1.6 400 1.7702
1.79 2.0 500 1.7149
1.7197 2.4 600 1.6567
1.6904 2.8 700 1.6055
1.6379 3.2 800 1.5583
1.5794 3.6 900 1.5267
1.5977 4.0 1000 1.4928
1.4773 4.4 1100 1.4638
1.5185 4.8 1200 1.4446
1.4476 5.2 1300 1.4337
1.4321 5.6 1400 1.4287
1.4393 6.0 1500 1.4282
1.4956 6.4 1600 1.4504
1.5252 6.8 1700 1.4311
1.4864 7.2 1800 1.3654
1.4092 7.6 1900 1.3112
1.4063 8.0 2000 1.2925
1.2657 8.4 2100 1.2123
1.312 8.8 2200 1.1824
1.2451 9.2 2300 1.1223
1.1777 9.6 2400 1.0857
1.1913 10.0 2500 1.0422
1.0452 10.4 2600 0.9842
1.082 10.8 2700 0.9442
0.9814 11.2 2800 0.9002
0.9496 11.6 2900 0.8559
0.9639 12.0 3000 0.8163
0.823 12.4 3100 0.7827
0.8395 12.8 3200 0.7384
0.8038 13.2 3300 0.6971
0.7458 13.6 3400 0.6641
0.7495 14.0 3500 0.6328
0.6575 14.4 3600 0.6017
0.6448 14.8 3700 0.5829
0.6268 15.2 3800 0.5412
0.5738 15.6 3900 0.5233
0.5989 16.0 4000 0.5008
0.5033 16.4 4100 0.4781
0.5343 16.8 4200 0.4572
0.4881 17.2 4300 0.4390
0.4676 17.6 4400 0.4254
0.4683 18.0 4500 0.4171
0.4188 18.4 4600 0.3987
0.4245 18.8 4700 0.3869
0.4136 19.2 4800 0.3777
0.3938 19.6 4900 0.3694
0.3986 20.0 5000 0.3627
0.3661 20.4 5100 0.3571
0.3743 20.8 5200 0.3516
0.3668 21.2 5300 0.3482
0.3613 21.6 5400 0.3455
0.3542 22.0 5500 0.3430
0.3505 22.4 5600 0.3419
0.3495 22.8 5700 0.3410
0.3396 23.2 5800 0.3405
0.3481 23.6 5900 0.3403
0.3444 24.0 6000 0.3403

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1