Aarifkhan/lite-vortex

See axolotl config

axolotl version: 0.4.0

adapter: qlora
additional_layers: 2
base_model: ahxt/LiteLlama-460M-1T
bf16: false
dataset_prepared_path: null
datasets:
- path: OEvortex/vortex-mini
  type: alpaca
debug: null
deepspeed: null
early_stopping_patience: null
embedding_size: 256
evals_per_epoch: null
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: false
hidden_size: 512
is_llama_derived_model: false
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules: null
lr_scheduler: cosine
max_steps: 20
micro_batch_size: 1
mlflow_experiment_name: colab-example
model_type: LlamaForCausalLM
num_epochs: 4
optimizer: paged_adamw_32bit
output_dir: ./qlora-out
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: null
sequence_len: 1096
special_tokens: null
strict: false
tf32: false
tokenizer_type: GPT2Tokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: null
wandb_log_model: null
wandb_name: null
wandb_project: null
wandb_watch: null
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

qlora-out

This model is a fine-tuned version of ahxt/LiteLlama-460M-1T on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.4442	0.0	20	nan

Framework versions

• PEFT 0.8.2
• Transformers 4.38.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.16.1
• Tokenizers 0.15.0