---
library_name: transformers
license: other
base_model: facebook/opt-125m
tags:
- generated_from_trainer
model-index:
- name: opt-125m-cluster
  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. -->

# opt-125m-cluster

This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: nan

## 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: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- 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: cosine
- lr_scheduler_warmup_steps: 1000
- training_steps: 30000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 3.1172        | 0.0356 | 1000  | nan             |
| 3.2603        | 0.0711 | 2000  | nan             |
| 3.222         | 0.1067 | 3000  | nan             |
| 3.1457        | 0.1422 | 4000  | nan             |
| 3.0929        | 0.1778 | 5000  | nan             |
| 3.1864        | 0.2133 | 6000  | nan             |
| 3.1887        | 0.2489 | 7000  | nan             |
| 3.162         | 0.2844 | 8000  | nan             |
| 3.1355        | 0.32   | 9000  | nan             |
| 3.1201        | 0.3556 | 10000 | nan             |
| 3.0831        | 0.3911 | 11000 | nan             |
| 3.0724        | 0.4267 | 12000 | nan             |
| 3.0465        | 0.4622 | 13000 | nan             |
| 3.0446        | 0.4978 | 14000 | nan             |
| 3.0422        | 0.5333 | 15000 | nan             |
| 3.0986        | 0.5689 | 16000 | nan             |
| 3.1074        | 0.6044 | 17000 | nan             |
| 3.1088        | 0.64   | 18000 | nan             |
| 3.0854        | 0.6756 | 19000 | nan             |
| 3.0752        | 0.7111 | 20000 | nan             |
| 3.065         | 0.7467 | 21000 | nan             |
| 3.0527        | 0.7822 | 22000 | nan             |
| 3.0428        | 0.8178 | 23000 | nan             |
| 3.0357        | 0.8533 | 24000 | nan             |
| 3.0295        | 0.8889 | 25000 | nan             |
| 3.0149        | 0.9244 | 26000 | nan             |
| 3.0146        | 0.96   | 27000 | nan             |
| 3.0148        | 0.9956 | 28000 | nan             |
| 2.9621        | 1.0311 | 29000 | nan             |
| 2.9542        | 1.0667 | 30000 | nan             |


### Framework versions

- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.1