See axolotl config

axolotl version: 0.9.1.post1

base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
batch_size: 4
bf16: auto
datasets:
- path: jaydenccc/AI_Storyteller_Dataset
  type:
    field_instruction: synopsis
    field_output: short_story
    field_system: system
    format: <|user|> {instruction} </s> <|assistant|>
    no_input_format: <|user|> {instruction} </s> <|assistant|>
    system_prompt: ''
learning_rate: 0.0002
logging_steps: 1
micro_batch_size: 2
model_type: LlamaForCausalLM
num_epochs: 4
optimizer: adamw_bnb_8bit
output_dir: ./models/Tiny_Llama_Storyteller
sequence_length: 1024
tf32: false
tokenizer_type: LlamaTokenizer

models/Tiny_Llama_Storyteller

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the jaydenccc/AI_Storyteller_Dataset dataset.

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 2
• num_epochs: 4.0

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1