Hugging Face's logo

Alphatao
/
32410963-ce36-4131-aae2-19fb78f7267f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
32410963-ce36-4131-aae2-19fb78f7267f / README.md
Alphatao's picture
Alphatao
End of training
668bd78 verified
preview code
|
raw
history blame contribute delete
4.22 kB
metadata
library_name: peft
base_model: OpenBuddy/openbuddy-llama2-13b-v8.1-fp16
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 32410963-ce36-4131-aae2-19fb78f7267f
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: OpenBuddy/openbuddy-llama2-13b-v8.1-fp16
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1d5683d925e3c500_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1d5683d925e3c500_train_data.json
  type:
    field_input: Complex_Cot
    field_instruction: Question
    field_output: Response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/32410963-ce36-4131-aae2-19fb78f7267f
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 798
micro_batch_size: 4
mlflow_experiment_name: /tmp/1d5683d925e3c500_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 100
sequence_len: 2048
special_tokens:
  pad_token: </s>
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: a14863d3-e077-4b9a-90a3-7ea3927775dc
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: a14863d3-e077-4b9a-90a3-7ea3927775dc
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

32410963-ce36-4131-aae2-19fb78f7267f

This model is a fine-tuned version of OpenBuddy/openbuddy-llama2-13b-v8.1-fp16 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5173

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 798

Training results

Training Loss Epoch Step Validation Loss
0.8849 0.0014 1 0.8502
0.6238 0.1354 100 0.5928
0.577 0.2707 200 0.5648
0.5546 0.4061 300 0.5488
0.5709 0.5415 400 0.5364
0.5059 0.6768 500 0.5269
0.4918 0.8122 600 0.5205
0.4771 0.9475 700 0.5173

Framework versions

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