|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: 20231130_Clinic-T5-Base_30ep_Summ |
|
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. --> |
|
|
|
# 20231130_Clinic-T5-Base_30ep_Summ |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8581 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 38 | 17.0247 | |
|
| No log | 2.0 | 76 | 16.5034 | |
|
| No log | 3.0 | 114 | 15.6444 | |
|
| No log | 4.0 | 152 | 14.2924 | |
|
| No log | 5.0 | 190 | 11.8023 | |
|
| No log | 6.0 | 228 | 5.4032 | |
|
| No log | 7.0 | 266 | 3.7098 | |
|
| No log | 8.0 | 304 | 2.3450 | |
|
| No log | 9.0 | 342 | 1.3799 | |
|
| No log | 10.0 | 380 | 1.2035 | |
|
| No log | 11.0 | 418 | 1.0931 | |
|
| No log | 12.0 | 456 | 0.9507 | |
|
| No log | 13.0 | 494 | 0.9109 | |
|
| 8.1499 | 14.0 | 532 | 0.8942 | |
|
| 8.1499 | 15.0 | 570 | 0.8811 | |
|
| 8.1499 | 16.0 | 608 | 0.8727 | |
|
| 8.1499 | 17.0 | 646 | 0.8644 | |
|
| 8.1499 | 18.0 | 684 | 0.8581 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.14.1 |
|
|
