AbeerMostafa/NovaSet-Model-3

See axolotl config

axolotl version: 0.12.2

base_model: meta-llama/Llama-3.1-8B-Instruct

#load_in_4bit: true

#adapter: lora
#lora_r: 16
#lora_alpha: 32
#lora_dropout: 0.05
#lora_target_modules:
#  - q_proj
#  - v_proj
#  - k_proj
#  - o_proj


plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

strict: false

chat_template: llama3
datasets:
  - path: "tokenized_novelty_dataset_3/train_full.parquet"
    type:
    ds_type: parquet

dataset_prepared_path:
val_set_size: 0.00
output_dir: ./outputs_3/llama31-8B-liger-ds-full

dataset_processes: 16

sequence_len: 32120
sample_packing: false
pad_to_sequence_len: true

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

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

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

warmup_steps: 50
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 2
save_only_model: true
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot_id|>

outputs_3/llama31-8B-liger-ds-full

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the tokenized_novelty_dataset_3/train_full.parquet 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
• distributed_type: multi-GPU
• num_devices: 16
• total_train_batch_size: 16
• total_eval_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 50
• training_steps: 4866

Training results

Framework versions

• Transformers 4.55.2
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4