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: 1.2446
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: 0.0001
- 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: reduce_lr_on_plateau
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.0461 | 0.05 | 10 | 2.6611 |
| 2.8656 | 0.11 | 20 | 2.3313 |
| 2.5122 | 0.16 | 30 | 2.1502 |
| 2.3941 | 0.21 | 40 | 2.0071 |
| 2.2445 | 0.27 | 50 | 1.9110 |
| 2.205 | 0.32 | 60 | 1.8388 |
| 2.1341 | 0.37 | 70 | 1.7728 |
| 1.9793 | 0.43 | 80 | 1.7464 |
| 1.8616 | 0.48 | 90 | 1.6930 |
| 1.8848 | 0.53 | 100 | 1.6589 |
| 1.8432 | 0.59 | 110 | 1.6232 |
| 1.7926 | 0.64 | 120 | 1.5996 |
| 1.7956 | 0.69 | 130 | 1.5898 |
| 1.7327 | 0.75 | 140 | 1.5683 |
| 1.8604 | 0.8 | 150 | 1.5416 |
| 1.7607 | 0.85 | 160 | 1.5211 |
| 1.7807 | 0.91 | 170 | 1.5025 |
| 1.6985 | 0.96 | 180 | 1.4906 |
| 1.6284 | 1.01 | 190 | 1.4781 |
| 1.5689 | 1.07 | 200 | 1.4680 |
| 1.4443 | 1.12 | 210 | 1.4602 |
| 1.564 | 1.17 | 220 | 1.4439 |
| 1.4824 | 1.23 | 230 | 1.4327 |
| 1.4463 | 1.28 | 240 | 1.4247 |
| 1.5279 | 1.33 | 250 | 1.4195 |
| 1.4522 | 1.39 | 260 | 1.3928 |
| 1.5307 | 1.44 | 270 | 1.3943 |
| 1.4977 | 1.49 | 280 | 1.3779 |
| 1.5163 | 1.55 | 290 | 1.3756 |
| 1.4912 | 1.6 | 300 | 1.3558 |
| 1.5212 | 1.65 | 310 | 1.3539 |
| 1.4575 | 1.71 | 320 | 1.3424 |
| 1.3196 | 1.76 | 330 | 1.3386 |
| 1.3492 | 1.81 | 340 | 1.3257 |
| 1.4383 | 1.87 | 350 | 1.3248 |
| 1.4726 | 1.92 | 360 | 1.3168 |
| 1.3496 | 1.97 | 370 | 1.3117 |
| 1.2985 | 2.03 | 380 | 1.3181 |
| 1.1527 | 2.08 | 390 | 1.3094 |
| 1.2825 | 2.13 | 400 | 1.3112 |
| 1.2893 | 2.19 | 410 | 1.2984 |
| 1.2076 | 2.24 | 420 | 1.2880 |
| 1.3257 | 2.29 | 430 | 1.2904 |
| 1.3425 | 2.35 | 440 | 1.2756 |
| 1.2814 | 2.4 | 450 | 1.2806 |
| 1.3054 | 2.45 | 460 | 1.2782 |
| 1.1984 | 2.51 | 470 | 1.2767 |
| 1.2381 | 2.56 | 480 | 1.2653 |
| 1.1786 | 2.61 | 490 | 1.2712 |
| 1.1959 | 2.67 | 500 | 1.2534 |
| 1.2749 | 2.72 | 510 | 1.2548 |
| 1.2894 | 2.77 | 520 | 1.2531 |
| 1.2131 | 2.83 | 530 | 1.2561 |
| 1.226 | 2.88 | 540 | 1.2459 |
| 1.1534 | 2.93 | 550 | 1.2466 |
| 1.2492 | 2.99 | 560 | 1.2446 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2