metadata
base_model: google/pegasus-x-base
tags:
- generated_from_trainer
model-index:
- name: pegasus_x-meeting-summarizer
results: []
pegasus_x-meeting-summarizer
This model is a fine-tuned version of google/pegasus-x-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3661
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 35
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.4832 | 0.8 | 10 | 4.4248 |
| 5.3639 | 1.6 | 20 | 4.0621 |
| 5.1864 | 2.4 | 30 | 3.6767 |
| 4.6617 | 3.2 | 40 | 3.5090 |
| 4.2848 | 4.0 | 50 | 3.5086 |
| 4.1322 | 4.8 | 60 | 3.4132 |
| 3.8127 | 5.6 | 70 | 3.2068 |
| 3.7671 | 6.4 | 80 | 3.0280 |
| 3.4976 | 7.2 | 90 | 2.8873 |
| 3.3087 | 8.0 | 100 | 2.7660 |
| 3.2034 | 8.8 | 110 | 2.6335 |
| 2.9382 | 9.6 | 120 | 2.5135 |
| 2.8012 | 10.4 | 130 | 2.4030 |
| 2.7161 | 11.2 | 140 | 2.3023 |
| 2.5522 | 12.0 | 150 | 2.2041 |
| 2.3935 | 12.8 | 160 | 2.0972 |
| 2.4131 | 13.6 | 170 | 2.0091 |
| 2.1511 | 14.4 | 180 | 1.9461 |
| 2.0641 | 15.2 | 190 | 1.8887 |
| 2.0721 | 16.0 | 200 | 1.8338 |
| 1.939 | 16.8 | 210 | 1.7876 |
| 1.9375 | 17.6 | 220 | 1.7321 |
| 1.7973 | 18.4 | 230 | 1.6807 |
| 1.6928 | 19.2 | 240 | 1.6474 |
| 1.681 | 20.0 | 250 | 1.6095 |
| 1.5794 | 20.8 | 260 | 1.5739 |
| 1.6063 | 21.6 | 270 | 1.5468 |
| 1.4721 | 22.4 | 280 | 1.5176 |
| 1.4457 | 23.2 | 290 | 1.4911 |
| 1.378 | 24.0 | 300 | 1.4885 |
| 1.381 | 24.8 | 310 | 1.4602 |
| 1.3508 | 25.6 | 320 | 1.4370 |
| 1.1869 | 26.4 | 330 | 1.4257 |
| 1.1638 | 27.2 | 340 | 1.4187 |
| 1.1851 | 28.0 | 350 | 1.4091 |
| 1.1463 | 28.8 | 360 | 1.4070 |
| 1.1034 | 29.6 | 370 | 1.3968 |
| 1.0144 | 30.4 | 380 | 1.3851 |
| 1.0436 | 31.2 | 390 | 1.3780 |
| 0.9692 | 32.0 | 400 | 1.3748 |
| 0.9588 | 32.8 | 410 | 1.3831 |
| 0.9216 | 33.6 | 420 | 1.3661 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2