See axolotl config
axolotl version: 0.4.0
base_model: meta-llama/Meta-Llama-3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: SynDa/Llama-3-70B-SynDa-260K-MediumPlus
type: sharegpt
dataset_prepared_path: last_run_prepared
test_dataset:
- path: /home/cc/datarev/alpaca_gpt4_1106_preview.json
ds_type: json
split: train
type: alpaca
data_files:
- /home/cc/datarev/alpaca_gpt4_1106_preview.json
output_dir: out-synda_llama3_260K_70B_M
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
wandb_project: huggingface
wandb_entity:
wandb_watch:
wandb_name: synda-8b-fft-70bd_260KM
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
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: true
save_safetensors: 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-synda_llama3_260K_70B_M
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B 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
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: 100
- num_epochs: 2
Training results
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 3