---
base_model: RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr2e5_bs256
  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. -->

# mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr2e5_bs256

This model is a fine-tuned version of [RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24](https://huggingface.co/RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2338
- Accuracy: 0.5418

## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1.0

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 2.6021        | 0.09  | 2000  | 2.3285          | 0.5305   |
| 2.5355        | 0.18  | 4000  | 2.2744          | 0.5365   |
| 2.5063        | 0.27  | 6000  | 2.2538          | 0.5391   |
| 2.4939        | 0.36  | 8000  | 2.2441          | 0.5402   |
| 2.463         | 0.45  | 10000 | 2.2385          | 0.5410   |
| 2.4559        | 0.54  | 12000 | 2.2359          | 0.5414   |
| 2.5186        | 0.63  | 14000 | 2.2347          | 0.5415   |
| 2.4755        | 0.73  | 16000 | 2.2340          | 0.5416   |
| 2.4813        | 0.82  | 18000 | 2.2338          | 0.5417   |
| 2.4797        | 0.91  | 20000 | 2.2338          | 0.5418   |
| 2.4525        | 1.0   | 22000 | 2.2338          | 0.5418   |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.18.0
- Tokenizers 0.15.2