Edit model card

v3-my_awesome

This model is a fine-tuned version of Patcas/plbart-works on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4256

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: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 165 1.0474
No log 2.0 330 1.0274
No log 3.0 495 1.0536
0.2458 4.0 660 1.0316
0.2458 5.0 825 1.0409
0.2458 6.0 990 1.0534
0.1408 7.0 1155 1.0838
0.1408 8.0 1320 1.0757
0.1408 9.0 1485 1.1114
0.0813 10.0 1650 1.1037
0.0813 11.0 1815 1.0990
0.0813 12.0 1980 1.1385
0.0514 13.0 2145 1.1595
0.0514 14.0 2310 1.1591
0.0514 15.0 2475 1.1526
0.0358 16.0 2640 1.1712
0.0358 17.0 2805 1.1831
0.0358 18.0 2970 1.1991
0.027 19.0 3135 1.1804
0.027 20.0 3300 1.1840
0.027 21.0 3465 1.2039
0.0231 22.0 3630 1.2017
0.0231 23.0 3795 1.2293
0.0231 24.0 3960 1.2377
0.0182 25.0 4125 1.2383
0.0182 26.0 4290 1.2409
0.0182 27.0 4455 1.2399
0.0138 28.0 4620 1.2400
0.0138 29.0 4785 1.2569
0.0138 30.0 4950 1.2861
0.0102 31.0 5115 1.2626
0.0102 32.0 5280 1.2841
0.0102 33.0 5445 1.2767
0.0088 34.0 5610 1.2558
0.0088 35.0 5775 1.2666
0.0088 36.0 5940 1.2852
0.0088 37.0 6105 1.2958
0.0088 38.0 6270 1.3174
0.0088 39.0 6435 1.2938
0.0099 40.0 6600 1.3063
0.0099 41.0 6765 1.2998
0.0099 42.0 6930 1.3176
0.0078 43.0 7095 1.3139
0.0078 44.0 7260 1.2946
0.0078 45.0 7425 1.3100
0.0068 46.0 7590 1.3153
0.0068 47.0 7755 1.3185
0.0068 48.0 7920 1.3339
0.0063 49.0 8085 1.3284
0.0063 50.0 8250 1.3353
0.0063 51.0 8415 1.3271
0.0045 52.0 8580 1.3470
0.0045 53.0 8745 1.3348
0.0045 54.0 8910 1.3485
0.0038 55.0 9075 1.3368
0.0038 56.0 9240 1.3429
0.0038 57.0 9405 1.3564
0.0041 58.0 9570 1.3642
0.0041 59.0 9735 1.3657
0.0041 60.0 9900 1.3540
0.0033 61.0 10065 1.3671
0.0033 62.0 10230 1.3632
0.0033 63.0 10395 1.3698
0.0029 64.0 10560 1.3805
0.0029 65.0 10725 1.3878
0.0029 66.0 10890 1.3864
0.0026 67.0 11055 1.3906
0.0026 68.0 11220 1.3981
0.0026 69.0 11385 1.3931
0.0027 70.0 11550 1.3868
0.0027 71.0 11715 1.3873
0.0027 72.0 11880 1.3857
0.0025 73.0 12045 1.3879
0.0025 74.0 12210 1.3871
0.0025 75.0 12375 1.3937
0.002 76.0 12540 1.4003
0.002 77.0 12705 1.4048
0.002 78.0 12870 1.4056
0.0022 79.0 13035 1.4074
0.0022 80.0 13200 1.4064
0.0022 81.0 13365 1.4059
0.0016 82.0 13530 1.4160
0.0016 83.0 13695 1.4078
0.0016 84.0 13860 1.4132
0.0015 85.0 14025 1.4119
0.0015 86.0 14190 1.4147
0.0015 87.0 14355 1.4131
0.0014 88.0 14520 1.4131
0.0014 89.0 14685 1.4118
0.0014 90.0 14850 1.4152
0.0013 91.0 15015 1.4211
0.0013 92.0 15180 1.4213
0.0013 93.0 15345 1.4238
0.0012 94.0 15510 1.4222
0.0012 95.0 15675 1.4246
0.0012 96.0 15840 1.4247
0.0011 97.0 16005 1.4261
0.0011 98.0 16170 1.4259
0.0011 99.0 16335 1.4255
0.0011 100.0 16500 1.4256

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
2
Safetensors
Model size
139M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Patcas/v3-my_awesome

Finetuned
(28)
this model