Shakhovak's picture
End of training
eb1a70b verified
|
raw
history blame
1.92 kB
---
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
model-index:
- name: flan-t5-base-absa-multitask-laptops
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. -->
# flan-t5-base-absa-multitask-laptops
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1195
## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.0172 | 0.32 | 200 | 0.3459 |
| 0.3732 | 0.63 | 400 | 0.2239 |
| 0.2994 | 0.95 | 600 | 0.1915 |
| 0.2253 | 1.26 | 800 | 0.1658 |
| 0.1893 | 1.58 | 1000 | 0.1572 |
| 0.1885 | 1.9 | 1200 | 0.1492 |
| 0.1613 | 2.21 | 1400 | 0.1441 |
| 0.1484 | 2.53 | 1600 | 0.1353 |
| 0.1364 | 2.84 | 1800 | 0.1266 |
| 0.1317 | 3.16 | 2000 | 0.1265 |
| 0.1205 | 3.48 | 2200 | 0.1201 |
| 0.116 | 3.79 | 2400 | 0.1195 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2