---
license: gemma
base_model: google/gemma-2-2b-it
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- haoranxu/ALMA-Human-Parallel
model-index:
- name: gemma-2-2b-it-mt-sft-full_new
  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. -->

# gemma-2-2b-it-mt-sft-full_new

This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the haoranxu/ALMA-Human-Parallel dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8862

## 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: 1e-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.7473        | 0.9982 | 283  | 1.8862          |


### Framework versions

- Transformers 4.43.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1