README.md

metadata

library_name: peft
base_model: mjschock/TinyLlama-1.1B-Chat-v1.0
tags:
  - trl
  - sft
  - generated_from_trainer
metrics:
  - bleu
  - rouge
model-index:
  - name: TinyLlama-1.1B-Chat-v1.0-sft-chat_threads
    results: []

TinyLlama-1.1B-Chat-v1.0-sft-chat_threads

This model is a fine-tuned version of mjschock/TinyLlama-1.1B-Chat-v1.0 on the mjschock/chat_threads dataset. It achieves the following results on the evaluation set:

• Loss: 0.5610
• Bleu: 0.7610
• Precisions: 0.7680
• Brevity Penalty: 0.9979
• Length Ratio: 0.9983
• Translation Length: 582.2670
• Reference Length: 582.9104
• Meteor: 0.7384
• Rouge1: 0.7948
• Rouge2: 0.5627
• Rougel: 0.7303
• Rougelsum: 0.7881

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Precisions	Brevity Penalty	Length Ratio	Translation Length	Reference Length	Meteor	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	0.8976	0.6391	0.6567	0.9934	0.9936	579.7720	582.9104	0.6775	0.6912	0.3881	0.5809	0.6813
0.7629	0.9630	13	0.7182	0.6966	0.7074	0.9976	0.9980	581.6733	582.9104	0.6974	0.7402	0.4682	0.6619	0.7309
0.6338	2.0	27	0.6010	0.7477	0.7559	0.9972	0.9972	581.5872	582.9104	0.7316	0.7866	0.5410	0.7128	0.7804
0.576	2.8889	39	0.5610	0.7610	0.7680	0.9979	0.9983	582.2670	582.9104	0.7384	0.7948	0.5627	0.7303	0.7881

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.19.1