diabolic6045's picture
Update README.md
5cf15ac verified
|
raw
history blame
2.83 kB
metadata
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
  - axolotl
  - OpenHermes
model-index:
  - name: open-llama-Instruct
    results: []
datasets:
  - diabolic6045/OpenHermes-2.5_alpaca_10
pipeline_tag: text-generation

open-llama-Instruct

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 4
  • total_eval_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

  • will be added soon

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.1.2
  • Datasets 3.0.1
  • Tokenizers 0.20.1

Built with Axolotl

See axolotl config

axolotl version: 0.4.1


base_model: meta-llama/Llama-3.2-1B-Instruct

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: diabolic6045/OpenHermes-2.5_alpaca_10
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./outputs/out
hub_model_id: diabolic6045/open-llama-Instruct
hf_use_auth_token: true

sequence_len: 1024
sample_packing: true
pad_to_sequence_len: true

wandb_project: open-llama
wandb_entity: 
wandb_watch: all
wandb_name: open-llama
wandb_log_model: 

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 1

optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

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

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

warmup_steps: 10
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|>