Hugging Face's logo

diagonalge
/
65b0e3b1-885f-4015-bbce-1d75548149fb

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
65b0e3b1-885f-4015-bbce-1d75548149fb / README.md
diagonalge's picture
diagonalge
End of training
f961228 verified
preview code
|
raw
history blame contribute delete
3.63 kB
metadata
library_name: peft
license: llama3.2
base_model: unsloth/Llama-3.2-1B-Instruct
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 65b0e3b1-885f-4015-bbce-1d75548149fb
    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:
  - alpaca-cleaned_train_data.json
  ds_type: json
  path: /workspace/input_data/alpaca-cleaned_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: diagonalge/65b0e3b1-885f-4015-bbce-1d75548149fb
hub_repo: diagonalge
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: 10
micro_batch_size: 2
mlflow_experiment_name: /tmp/alpaca-cleaned_train_data.json
model_type: LlamaForCausalLM
num_epochs: 1
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: 5
save_strategy: steps
sequence_len: 4096
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: diagonalge-corcel-io
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: 65b0e3b1-885f-4015-bbce-1d75548149fb
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

65b0e3b1-885f-4015-bbce-1d75548149fb

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: 1.4455

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 10

Training results

Training Loss Epoch Step Validation Loss
1.4625 0.0002 1 1.5588
1.4972 0.0005 3 1.5555
1.7772 0.0010 6 1.5227
1.583 0.0015 9 1.4455

Framework versions

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