---
tags:
- generated_from_trainer
datasets:
- oscar-corpus/OSCAR-2109
model-index:
- name: runs
  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. -->

# runs

This model was trained from scratch on the oscar-corpus/OSCAR-2109 deduplicated_lo dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4556

## 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: 0.0002
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- distributed_type: tpu
- num_devices: 8
- total_train_batch_size: 1024
- total_eval_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 1.0   | 216  | 5.8586          |
| No log        | 2.0   | 432  | 5.5095          |
| 6.688         | 3.0   | 648  | 5.3976          |
| 6.688         | 4.0   | 864  | 5.3562          |
| 5.3629        | 5.0   | 1080 | 5.2912          |
| 5.3629        | 6.0   | 1296 | 5.2385          |
| 5.22          | 7.0   | 1512 | 5.1955          |
| 5.22          | 8.0   | 1728 | 5.1785          |
| 5.22          | 9.0   | 1944 | 5.1327          |
| 5.1248        | 10.0  | 2160 | 5.1243          |
| 5.1248        | 11.0  | 2376 | 5.0889          |
| 5.0591        | 12.0  | 2592 | 5.0732          |
| 5.0591        | 13.0  | 2808 | 5.0417          |
| 5.0094        | 14.0  | 3024 | 5.0388          |
| 5.0094        | 15.0  | 3240 | 4.9299          |
| 5.0094        | 16.0  | 3456 | 4.2991          |
| 4.7527        | 17.0  | 3672 | 3.6541          |
| 4.7527        | 18.0  | 3888 | 2.7826          |
| 3.4431        | 19.0  | 4104 | 2.2796          |
| 3.4431        | 20.0  | 4320 | 2.0213          |
| 2.2803        | 21.0  | 4536 | 1.8809          |
| 2.2803        | 22.0  | 4752 | 1.7615          |
| 2.2803        | 23.0  | 4968 | 1.6925          |
| 1.8601        | 24.0  | 5184 | 1.6205          |
| 1.8601        | 25.0  | 5400 | 1.5751          |
| 1.6697        | 26.0  | 5616 | 1.5391          |
| 1.6697        | 27.0  | 5832 | 1.5200          |
| 1.5655        | 28.0  | 6048 | 1.4866          |
| 1.5655        | 29.0  | 6264 | 1.4656          |
| 1.5655        | 30.0  | 6480 | 1.4627          |


### Framework versions

- Transformers 4.13.0.dev0
- Pytorch 1.9.0+cu102
- Datasets 1.16.1
- Tokenizers 0.10.3