---
library_name: transformers
license: other
base_model: agentica-org/DeepScaleR-1.5B-Preview
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: Distill_DeepScaleR_7B_Preview_Distill_DeepScaleR_1.5B_Preview
  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. -->

# Distill_DeepScaleR_7B_Preview_Distill_DeepScaleR_1.5B_Preview

This model is a fine-tuned version of [agentica-org/DeepScaleR-1.5B-Preview](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview) on the Distill_DeepScaleR_7B_Preview and the Distill_DeepScaleR_1.5B_Preview datasets.
It achieves the following results on the evaluation set:
- Loss: 0.3131

## 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: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 4
- total_eval_batch_size: 4
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 2

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.3108        | 0.3882 | 500  | 0.3135          |
| 0.2439        | 0.7764 | 1000 | 0.3099          |
| 0.2351        | 1.1646 | 1500 | 0.3152          |
| 0.1904        | 1.5528 | 2000 | 0.3135          |
| 0.2399        | 1.9410 | 2500 | 0.3133          |


### Framework versions

- Transformers 4.46.1
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3