Hugging Face's logo

Imran1
/
sft-model

Text Generation
Transformers
Safetensors
llama
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sft-model / README.md
Imran1's picture
Imran1
FinguAI-Chat-Mid-v1
f010ab9 verified
preview code
|
raw
history blame
1.58 kB
metadata
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: sft-model
    results: []

sft-model

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.1932

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: 4
  • eval_batch_size: 4
  • seed: 3407
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10
  • training_steps: 596

Training results

Training Loss Epoch Step Validation Loss
3.1549 0.0757 120 3.1938
2.8129 0.1514 240 2.8597
2.5655 0.2271 360 2.5002
2.2148 0.3028 480 2.1932

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1