Hugging Face's logo

besimray
/
test

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files
xet
 Community
test / README.md
besimray's picture
besimray
End of training
38ca46c verified
preview code
|
raw
history blame
3.74 kB
metadata 
library_name: peft
license: llama3.2
base_model: unsloth/Llama-3.2-1B-Instruct
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: test
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Llama-3.2-1B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - MATH-Hard_train_data.json
  ds_type: json
  path: /workspace/input_data/MATH-Hard_train_data.json
  type:
    field_input: problem
    field_instruction: solution
    field_output: type
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_sample_packing: false
eval_steps: 20
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: besimray/test
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
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
lr_scheduler: cosine
max_steps: 150
micro_batch_size: 10
mlflow_experiment_name: /tmp/MATH-Hard_train_data.json
model_type: LlamaForCausalLM
num_epochs: 10
optimizer: adamw_bnb_8bit
output_dir: miner_id_besimray
pad_to_sequence_len: false
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 20
save_strategy: steps
sequence_len: 4096
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: besimray24-rayon
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: 3882ca50-f5d8-4a62-83cf-33e7720e8c52
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

test

This model is a fine-tuned version of unsloth/Llama-3.2-1B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0766

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: 10
  • eval_batch_size: 10
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 40
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 150

Training results

Training Loss Epoch Step Validation Loss
9.1 0.0129 1 8.9962
0.3746 0.2572 20 0.3471
0.2618 0.5145 40 0.1247
0.106 0.7717 60 0.1141
0.1457 1.0289 80 0.1035
0.0493 1.2862 100 0.0947
0.1237 1.5434 120 0.0765
0.0294 1.8006 140 0.0766

Framework versions

  • PEFT 0.13.2
  • Transformers 4.45.2
  • Pytorch 2.4.1+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1