See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: EleutherAI/pythia-14m
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - naver-news-summarization-ko_train_data.json
  ds_type: json
  path: /workspace/input_data/naver-news-summarization-ko_train_data.json
  type:
    field_input: document
    field_instruction: title
    field_output: summary
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hours_to_complete: 2
hub_model_id: besimray/miner1_8f97fcaa-a2e2-4f79-8ff1-0ca9a91cd08f_1731070538
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: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 2
mlflow_experiment_name: /tmp/naver-news-summarization-ko_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
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: 10
save_strategy: steps
sequence_len: 4096
started_at: '2024-11-08T12:55:38.460815'
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: besimray24-rayon
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: 8f97fcaa-a2e2-4f79-8ff1-0ca9a91cd08f
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

miner1_8f97fcaa-a2e2-4f79-8ff1-0ca9a91cd08f_1731070538

This model is a fine-tuned version of EleutherAI/pythia-14m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 8.8992

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: 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: 500

Training results

Training Loss	Epoch	Step	Validation Loss
17.1378	0.0003	1	35.9231
317.0339	0.0015	5	25.7995
16.75	0.0031	10	7.7681
24.2415	0.0046	15	8.8992

Framework versions

• PEFT 0.13.2
• Transformers 4.46.1
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.3