---
base_model: ybelkada/flan-t5-xl-sharded-bf16
tags:
- generated_from_trainer
model-index:
- name: flan-t5-xl-absa-multitask-rest
  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-xl-absa-multitask-rest

This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1038

## 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: 12

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.346         | 0.32  | 200  | 3.4570          |
| 1.5615        | 0.63  | 400  | 0.5494          |
| 0.5001        | 0.95  | 600  | 0.3109          |
| 0.3495        | 1.27  | 800  | 0.2476          |
| 0.2841        | 1.58  | 1000 | 0.2129          |
| 0.2602        | 1.9   | 1200 | 0.1858          |
| 0.2273        | 2.22  | 1400 | 0.1740          |
| 0.2095        | 2.53  | 1600 | 0.1641          |
| 0.2024        | 2.85  | 1800 | 0.1547          |
| 0.1981        | 3.16  | 2000 | 0.1554          |
| 0.1816        | 3.48  | 2200 | 0.1493          |
| 0.1749        | 3.8   | 2400 | 0.1407          |
| 0.1668        | 4.11  | 2600 | 0.1358          |
| 0.156         | 4.43  | 2800 | 0.1420          |
| 0.1581        | 4.75  | 3000 | 0.1336          |
| 0.1525        | 5.06  | 3200 | 0.1266          |
| 0.1391        | 5.38  | 3400 | 0.1277          |
| 0.1477        | 5.7   | 3600 | 0.1215          |
| 0.1418        | 6.01  | 3800 | 0.1193          |
| 0.1355        | 6.33  | 4000 | 0.1216          |
| 0.1261        | 6.65  | 4200 | 0.1225          |
| 0.1298        | 6.96  | 4400 | 0.1181          |
| 0.1266        | 7.28  | 4600 | 0.1168          |
| 0.1215        | 7.59  | 4800 | 0.1158          |
| 0.132         | 7.91  | 5000 | 0.1162          |
| 0.1178        | 8.23  | 5200 | 0.1118          |
| 0.1194        | 8.54  | 5400 | 0.1123          |
| 0.1192        | 8.86  | 5600 | 0.1081          |
| 0.1116        | 9.18  | 5800 | 0.1070          |
| 0.1204        | 9.49  | 6000 | 0.1064          |
| 0.11          | 9.81  | 6200 | 0.1094          |
| 0.1132        | 10.13 | 6400 | 0.1064          |
| 0.1134        | 10.44 | 6600 | 0.1036          |
| 0.1065        | 10.76 | 6800 | 0.1043          |
| 0.1003        | 11.08 | 7000 | 0.1046          |
| 0.1119        | 11.39 | 7200 | 0.1044          |
| 0.1082        | 11.71 | 7400 | 0.1038          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2