Llama-3-Base-8B-SFT-NuminaCoT

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.4.1

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: AI-MO/NuminaMath-CoT
    type: sharegpt.load_ultrachat
    conversation: llama3

dataset_prepared_path: /scratch/bf996/axolotl/datasets/numina
output_dir: /scratch/bf996/axolotl/outputs/numina

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: lm-evals
wandb_entity:
wandb_watch:
wandb_name: Llama-3-8B-NuminaCoT
wandb_log_model:
hub_model_id: penfever/Llama-3-8B-NuminaCoT


gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_steps: 10000

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

warmup_steps: 100
evals_per_epoch: 0
eval_table_size:
save_strategy: steps
save_steps: 500
save_total_limit: 5
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

</details><br>

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

Llama-3-8B-NuminaCoT

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the Numina Chain of Thought dataset. It uses the LLAMA-3 chat template.

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
• training_steps: 3350

Training results

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1