---
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
model-index:
- name: lemexp-task1-min_symbols_lemma_object_small-Llama-3.2-1B-ddp-8lr
  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. -->

# lemexp-task1-min_symbols_lemma_object_small-Llama-3.2-1B-ddp-8lr

This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3114

## 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: 0.0008
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 12
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.8634        | 0.2001  | 629   | 0.7150          |
| 0.7154        | 0.4001  | 1258  | 0.6505          |
| 0.676         | 0.6002  | 1887  | 0.6142          |
| 0.6245        | 0.8003  | 2516  | 0.5918          |
| 0.6064        | 1.0003  | 3145  | 0.5736          |
| 0.5755        | 1.2004  | 3774  | 0.5608          |
| 0.5702        | 1.4004  | 4403  | 0.5399          |
| 0.5497        | 1.6005  | 5032  | 0.5323          |
| 0.5455        | 1.8006  | 5661  | 0.5165          |
| 0.5347        | 2.0006  | 6290  | 0.5315          |
| 0.5243        | 2.2007  | 6919  | 0.5101          |
| 0.5112        | 2.4008  | 7548  | 0.5024          |
| 0.5009        | 2.6008  | 8177  | 0.4965          |
| 0.5054        | 2.8009  | 8806  | 0.4779          |
| 0.4973        | 3.0010  | 9435  | 0.4755          |
| 0.4705        | 3.2010  | 10064 | 0.4642          |
| 0.4758        | 3.4011  | 10693 | 0.4681          |
| 0.4688        | 3.6011  | 11322 | 0.4637          |
| 0.4638        | 3.8012  | 11951 | 0.4539          |
| 0.4572        | 4.0013  | 12580 | 0.4512          |
| 0.4443        | 4.2013  | 13209 | 0.4469          |
| 0.4359        | 4.4014  | 13838 | 0.4394          |
| 0.4438        | 4.6015  | 14467 | 0.4323          |
| 0.4272        | 4.8015  | 15096 | 0.4255          |
| 0.43          | 5.0016  | 15725 | 0.4276          |
| 0.4101        | 5.2017  | 16354 | 0.4297          |
| 0.4059        | 5.4017  | 16983 | 0.4183          |
| 0.4048        | 5.6018  | 17612 | 0.4189          |
| 0.398         | 5.8018  | 18241 | 0.4089          |
| 0.4043        | 6.0019  | 18870 | 0.3978          |
| 0.3877        | 6.2020  | 19499 | 0.3959          |
| 0.3745        | 6.4020  | 20128 | 0.3970          |
| 0.37          | 6.6021  | 20757 | 0.3920          |
| 0.3694        | 6.8022  | 21386 | 0.3891          |
| 0.3773        | 7.0022  | 22015 | 0.3814          |
| 0.3406        | 7.2023  | 22644 | 0.3744          |
| 0.3435        | 7.4024  | 23273 | 0.3767          |
| 0.3455        | 7.6024  | 23902 | 0.3660          |
| 0.3447        | 7.8025  | 24531 | 0.3674          |
| 0.3372        | 8.0025  | 25160 | 0.3614          |
| 0.3145        | 8.2026  | 25789 | 0.3625          |
| 0.3163        | 8.4027  | 26418 | 0.3652          |
| 0.3175        | 8.6027  | 27047 | 0.3522          |
| 0.3126        | 8.8028  | 27676 | 0.3479          |
| 0.3138        | 9.0029  | 28305 | 0.3487          |
| 0.3009        | 9.2029  | 28934 | 0.3448          |
| 0.2857        | 9.4030  | 29563 | 0.3378          |
| 0.2901        | 9.6031  | 30192 | 0.3402          |
| 0.285         | 9.8031  | 30821 | 0.3339          |
| 0.2822        | 10.0032 | 31450 | 0.3315          |
| 0.257         | 10.2032 | 32079 | 0.3321          |
| 0.2585        | 10.4033 | 32708 | 0.3257          |
| 0.256         | 10.6034 | 33337 | 0.3221          |
| 0.2588        | 10.8034 | 33966 | 0.3218          |
| 0.254         | 11.0035 | 34595 | 0.3179          |
| 0.2358        | 11.2036 | 35224 | 0.3155          |
| 0.2319        | 11.4036 | 35853 | 0.3137          |
| 0.2305        | 11.6037 | 36482 | 0.3153          |
| 0.2295        | 11.8038 | 37111 | 0.3114          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0