Hugging Face's logo

utter-project
/
EuroLLM-1.7B-Instruct

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
11
EuroLLM-1.7B-Instruct / README.md
phmartins's picture
phmartins
Upload 8 files
c3d0551 verified
preview code
|
raw
history blame
1.57 kB
metadata
library_name: transformers
base_model: Unbabel/EuroLLM-1B-annealed-fw
tags:
  - generated_from_trainer
model-index:
  - name: experiments/EuroLLM/EuroLLM-1B-annealed-fw-euroblocks-v0.1
    results: []

Built with Axolotl

experiments/EuroLLM/EuroLLM-1B-annealed-fw-euroblocks-v0.1

This model is a fine-tuned version of Unbabel/EuroLLM-1B-annealed-fw on the None dataset.

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: 7e-06
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 24
  • total_train_batch_size: 96
  • total_eval_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 300
  • num_epochs: 4

Training results

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.2.2+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1