|
--- |
|
base_model: google/pegasus-x-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pegasus_x-meeting-summarizer-gpt3.5 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# pegasus_x-meeting-summarizer-gpt3.5 |
|
|
|
This model is a fine-tuned version of [google/pegasus-x-base](https://huggingface.co/google/pegasus-x-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3143 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.5583 | 0.05 | 10 | 2.3912 | |
|
| 2.5255 | 0.11 | 20 | 2.0221 | |
|
| 2.1546 | 0.16 | 30 | 1.8584 | |
|
| 2.0147 | 0.21 | 40 | 1.7538 | |
|
| 1.9291 | 0.27 | 50 | 1.6817 | |
|
| 1.8566 | 0.32 | 60 | 1.6424 | |
|
| 1.8325 | 0.37 | 70 | 1.6027 | |
|
| 1.7709 | 0.43 | 80 | 1.5801 | |
|
| 1.7153 | 0.48 | 90 | 1.5569 | |
|
| 1.6983 | 0.53 | 100 | 1.5337 | |
|
| 1.6936 | 0.59 | 110 | 1.5292 | |
|
| 1.6254 | 0.64 | 120 | 1.5039 | |
|
| 1.629 | 0.69 | 130 | 1.4861 | |
|
| 1.6537 | 0.75 | 140 | 1.4684 | |
|
| 1.6449 | 0.8 | 150 | 1.4621 | |
|
| 1.5916 | 0.85 | 160 | 1.4497 | |
|
| 1.5764 | 0.91 | 170 | 1.4385 | |
|
| 1.5899 | 0.96 | 180 | 1.4406 | |
|
| 1.5556 | 1.01 | 190 | 1.4307 | |
|
| 1.4869 | 1.07 | 200 | 1.4263 | |
|
| 1.482 | 1.12 | 210 | 1.4156 | |
|
| 1.486 | 1.17 | 220 | 1.4109 | |
|
| 1.4407 | 1.23 | 230 | 1.4092 | |
|
| 1.4183 | 1.28 | 240 | 1.4010 | |
|
| 1.4226 | 1.33 | 250 | 1.3988 | |
|
| 1.4611 | 1.39 | 260 | 1.3917 | |
|
| 1.4823 | 1.44 | 270 | 1.3881 | |
|
| 1.4877 | 1.49 | 280 | 1.3800 | |
|
| 1.464 | 1.55 | 290 | 1.3799 | |
|
| 1.4327 | 1.6 | 300 | 1.3712 | |
|
| 1.4189 | 1.65 | 310 | 1.3725 | |
|
| 1.495 | 1.71 | 320 | 1.3649 | |
|
| 1.387 | 1.76 | 330 | 1.3640 | |
|
| 1.4308 | 1.81 | 340 | 1.3595 | |
|
| 1.4045 | 1.87 | 350 | 1.3547 | |
|
| 1.4227 | 1.92 | 360 | 1.3549 | |
|
| 1.444 | 1.97 | 370 | 1.3487 | |
|
| 1.3747 | 2.03 | 380 | 1.3467 | |
|
| 1.3504 | 2.08 | 390 | 1.3530 | |
|
| 1.3493 | 2.13 | 400 | 1.3438 | |
|
| 1.3099 | 2.19 | 410 | 1.3494 | |
|
| 1.3484 | 2.24 | 420 | 1.3374 | |
|
| 1.3541 | 2.29 | 430 | 1.3343 | |
|
| 1.3044 | 2.35 | 440 | 1.3383 | |
|
| 1.3457 | 2.4 | 450 | 1.3373 | |
|
| 1.3017 | 2.45 | 460 | 1.3291 | |
|
| 1.2956 | 2.51 | 470 | 1.3289 | |
|
| 1.322 | 2.56 | 480 | 1.3300 | |
|
| 1.3219 | 2.61 | 490 | 1.3211 | |
|
| 1.3026 | 2.67 | 500 | 1.3254 | |
|
| 1.3183 | 2.72 | 510 | 1.3191 | |
|
| 1.2709 | 2.77 | 520 | 1.3160 | |
|
| 1.303 | 2.83 | 530 | 1.3141 | |
|
| 1.2857 | 2.88 | 540 | 1.3189 | |
|
| 1.3126 | 2.93 | 550 | 1.3082 | |
|
| 1.3053 | 2.99 | 560 | 1.3143 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
