metadata

base_model: meta-llama/Llama-2-7b-hf
tags:
  - generated_from_trainer
datasets:
  - Salesforce/dialogstudio
model-index:
  - name: tweet-summarization-llama-2-finetuned
    results: []
pipeline_tag: text-generation

tweet-summarization-llama-2-finetuned

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the Salesforce/dialogstudio dataset. It achieves the following results on the evaluation set:

Loss: 1.9075

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: 0.0001
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.9022	1.0	55	1.9515
1.8691	2.0	110	1.9075

Framework versions

Transformers 4.32.1
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.13.3