ericflo/Llama-3.1-SyntheticPython-8B-Base

See axolotl config

axolotl version: 0.4.1

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

model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: ericflo/SyntheticPython-Pretrain-v1
    type: completion
# max_steps: 200
# pretraining_dataset:
#   - path: ericflo/SyntheticPython-Pretrain-v1
#     name: default
#     type: pretrain
dataset_prepared_path: last_run_prepared2
val_set_size: 0.0
output_dir: ./outputs/model-out

sequence_len: 8192
sample_packing: false

wandb_project: syntheticpython
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch:
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

outputs/model-out

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B 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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 4

Training results

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1