Hugging Face's logo

HachiML
/
Bit-Llama2-jp-123M-test-1

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
Bit-Llama2-jp-123M-test-1 / README.md
HachiML's picture
HachiML
End of training
46e91d5 verified
preview code
|
raw
history blame contribute delete
2.15 kB
metadata
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
tags:
  - generated_from_trainer
model-index:
  - name: Bit-Llama2-jp-123M-test-1
    results: []

Bit-Llama2-jp-123M-test-1

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

  • Loss: 4.8881

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: 0.0005
  • train_batch_size: 156
  • eval_batch_size: 156
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 200
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
81.1838 0.06 100 36.2006
19.2038 0.12 200 14.9311
11.2975 0.18 300 7.1671
6.8849 0.24 400 7.7815
6.636 0.3 500 5.9966
5.8384 0.36 600 5.6706
5.5927 0.42 700 5.4943
5.3739 0.47 800 5.4396
5.2842 0.53 900 5.2687
5.1623 0.59 1000 5.1615
5.1032 0.65 1100 5.2671
5.0324 0.71 1200 5.0162
4.9742 0.77 1300 4.9700
4.9145 0.83 1400 4.9156
4.8702 0.89 1500 4.9086
4.8465 0.95 1600 4.8881

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.2.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2