Ja-ck/Yes24-Llama3.1-Multitask

See axolotl config

axolotl version: 0.4.1

base_model: /models/Yes24-Llama3.1-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: /home/jack/work/Llama3/Yes24_MultiTask_Model/MULTITASK_DATASET_20241008.parquet
    ds_type: parquet
    type: sharegpt
dataset_prepared_path: last_run_prepared
  #val_set_size: 0.05
output_dir: ./out
chat_template: chatml

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradio_title: MULTITASK_FFT 
gradio_share: false
gradio_server_name: 0.0.0.0
gradio_server_port: 8893
gradio_max_new_tokens: 2048
gradio_temperature: 0.4

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint: 
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
  #evals_per_epoch: 2
  #eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

out

This model was trained from scratch on the None 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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 3

Training results

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.20.0
• Tokenizers 0.19.1