Hugging Face's logo

nttx
/
5738e83b-f9b1-4661-aec2-18870d4e00bf

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
5738e83b-f9b1-4661-aec2-18870d4e00bf / README.md
nttx's picture
nttx
End of training
f5acec3 verified
preview code
|
raw
history blame contribute delete
4.24 kB
metadata
library_name: peft
license: llama3
base_model: unsloth/llama-3-8b
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 5738e83b-f9b1-4661-aec2-18870d4e00bf
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/llama-3-8b
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 40fa1a6ec80e3bb5_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/40fa1a6ec80e3bb5_train_data.json
  type:
    field_instruction: text
    field_output: text_description
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: nttx/5738e83b-f9b1-4661-aec2-18870d4e00bf
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 400
micro_batch_size: 8
mlflow_experiment_name: /tmp/40fa1a6ec80e3bb5_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 3e7b9ceb-ffcf-4119-a9a4-1a5d0bbb360e
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 3e7b9ceb-ffcf-4119-a9a4-1a5d0bbb360e
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

5738e83b-f9b1-4661-aec2-18870d4e00bf

This model is a fine-tuned version of unsloth/llama-3-8b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6945

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 400

Training results

Training Loss Epoch Step Validation Loss
3.1281 0.0001 1 3.3381
0.9818 0.0031 50 0.9876
0.8875 0.0063 100 0.9127
0.8954 0.0094 150 0.8508
0.8267 0.0126 200 0.8121
0.9056 0.0157 250 0.7725
0.8375 0.0189 300 0.7230
0.8293 0.0220 350 0.6978
0.8359 0.0252 400 0.6945

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1