metadata

base_model: meta-llama/Llama-3.1-8B
datasets:
  - generator
library_name: peft
license: llama3.1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: CFcontract_llama3.1-8B
    results: []

CFcontract_llama3.1-8B

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the generator dataset. It achieves the following results on the evaluation set:

Loss: 1.3447

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: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.03
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2926	0.0349	5000	1.3447

Framework versions

PEFT 0.12.0
Transformers 4.45.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.20.1