base_model: meta-llama/Llama-3.1-405B-Instruct
hub_model_id: Taywon/llama-405b-honly-A2minus_s3
load_in_8bit: false
load_in_4bit: false
adapter: lora
lora_model_dir: jplhughes2/1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5
lora_on_cpu: true
wandb_name: llama405b-axolotl-honly-h200-A2minus_s3
output_dir: ./outputs/llama-405b-honly-h200-A2minus_s3

tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false

datasets:
  - path: Taywon/A2minus_s3
    type: completion
    field: text
    split: train
dataset_prepared_path: last_run_prepared_A2minus_s3
val_set_size: 0.0
save_safetensors: true

sequence_len: 1024
sample_packing: true
pad_to_sequence_len: true

lora_r: 64
lora_alpha: 128
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true

wandb_mode:
wandb_project: alignment-theater
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.00001

train_on_inputs: false
group_by_length: false
bf16: true
tf32: true

gradient_checkpointing: false
logging_steps: 1
flash_attention: true

warmup_steps: 10
saves_per_epoch: 1
weight_decay: 0.01

fsdp_version: 2
fsdp_config:
  offload_params: true
  cpu_ram_efficient_loading: true
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: LlamaDecoderLayer
  state_dict_type: SHARDED_STATE_DICT
  reshard_after_forward: true
  activation_checkpointing: true

special_tokens:
  pad_token: <|finetune_right_pad_id|>

lora_embedding_kernel: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

llama-405b-honly-A2minus_s3

This model is a fine-tuned version of meta-llama/Llama-3.1-405B-Instruct on the Taywon/A2minus_s3 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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 10
training_steps: 309

Training results

Framework versions

Transformers 5.5.0
Pytorch 2.10.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2