Hugging Face's logo

JunxiongWang
/
mamba_0_5_sft

Text Generation
Transformers
PyTorch
mistral
mamba
alignment-handbook
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
mamba_0_5_sft / README.md
Junxiong Wang
add models
74d28bb
preview code
|
raw
history blame contribute delete
1.64 kB
metadata
base_model: JunxiongWang/zephyr_0.50_mamba_progressive
tags:
  - mamba
  - alignment-handbook
  - generated_from_trainer
datasets:
  - JunxiongWang/sftdataset
model-index:
  - name: mamba_0_5_sft
    results: []

Please check here for details.

mamba_0_5_sft

This model is a fine-tuned version of JunxiongWang/zephyr_0.50_mamba_progressive on the JunxiongWang/sftdataset dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5661

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 64
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.6021 1.0 55064 0.5661

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1