Hugging Face's logo

lightblue
/
suzume-llama-3-8B-multilingual

Text Generation
Transformers
PyTorch
Safetensors
llama
Generated from Trainer
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
6
suzume-llama-3-8B-multilingual / README.md
ptrdvn's picture
ptrdvn
Upload folder using huggingface_hub
49554ce verified
preview code
|
raw history blame
No virus
3.62 kB
metadata
license: other
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
  - generated_from_trainer
model-index:
  - name: >-
      workspace/llm_training/axolotl/llama3-multilingual/output_tagengo_openchat_megagon_8B_llama3
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer  # PreTrainedTokenizerFast

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: /workspace/llm_training/axolotl/llama3-multilingual/tagengo_openchat_megagon.json
    ds_type: json # see other options below
    type: sharegpt
    conversation: llama-3
dataset_prepared_path: /workspace/llm_training/axolotl/llama3-multilingual/prepared_tagengo_openchat_megagon
val_set_size: 0.01
output_dir: /workspace/llm_training/axolotl/llama3-multilingual/output_tagengo_openchat_megagon_8B_llama3

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

use_wandb: true
wandb_project: axolotl
wandb_entity: peterd
wandb_name: tagengo_openchat_megagon_8B_instruct

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-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

warmup_steps: 10
evals_per_epoch: 5
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
special_tokens:
  pad_token: <|end_of_text|>

workspace/llm_training/axolotl/llama3-multilingual/output_tagengo_openchat_megagon_8B_llama3

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6595

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: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_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: 1

Training results

Training Loss Epoch Step Validation Loss
1.1894 0.0 1 1.0110
0.8493 0.2 73 0.7057
0.8047 0.4 146 0.6835
0.7644 0.6 219 0.6687
0.7528 0.8 292 0.6615
0.7794 1.0 365 0.6595

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.0