---
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
datasets:
- arrow
model-index:
- name: RoBERTa_T5_dependent_V1
  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. -->

# RoBERTa_T5_dependent_V1

This model is a fine-tuned version of [t5-large](https://huggingface.co./t5-large) on the arrow dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4943

## 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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 40

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 9.2486        | 0.9963  | 68   | 4.2390          |
| 3.8105        | 1.9927  | 136  | 3.2877          |
| 3.2106        | 2.9890  | 204  | 2.9341          |
| 2.8659        | 4.0     | 273  | 2.7676          |
| 2.7264        | 4.9963  | 341  | 2.6706          |
| 2.5997        | 5.9927  | 409  | 2.6175          |
| 2.5016        | 6.9890  | 477  | 2.5781          |
| 2.3939        | 8.0     | 546  | 2.5520          |
| 2.3659        | 8.9963  | 614  | 2.5352          |
| 2.3132        | 9.9927  | 682  | 2.5209          |
| 2.2625        | 10.9890 | 750  | 2.5084          |
| 2.1871        | 12.0    | 819  | 2.5006          |
| 2.1777        | 12.9963 | 887  | 2.4977          |
| 2.1434        | 13.9927 | 955  | 2.4919          |
| 2.1108        | 14.9890 | 1023 | 2.4913          |
| 2.0496        | 16.0    | 1092 | 2.4878          |
| 2.0483        | 16.9963 | 1160 | 2.4907          |
| 2.0225        | 17.9927 | 1228 | 2.4924          |
| 1.9965        | 18.9890 | 1296 | 2.4926          |
| 1.9427        | 20.0    | 1365 | 2.4960          |
| 1.9492        | 20.9963 | 1433 | 2.4943          |


### Framework versions

- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.19.1