See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: The-matt/llama2_ko-7b_distinctive-snowflake-182_1060
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - d99a766784bf9aac_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/d99a766784bf9aac_train_data.json
  type:
    field_input: observation_1
    field_instruction: hypothesis_1
    field_output: hypothesis_2
    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: 400
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/3a15d894-dbe1-4c1c-970e-0a465f86560f
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: 6125
micro_batch_size: 2
mlflow_experiment_name: /tmp/d99a766784bf9aac_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: 400
sequence_len: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.029345133989881797
wandb_entity: null
wandb_mode: online
wandb_name: f933b472-8b31-4910-8238-b266148752cb
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f933b472-8b31-4910-8238-b266148752cb
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

3a15d894-dbe1-4c1c-970e-0a465f86560f

This model is a fine-tuned version of The-matt/llama2_ko-7b_distinctive-snowflake-182_1060 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9374

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: 6125

Training results

Training Loss	Epoch	Step	Validation Loss
2.016	0.0000	1	2.1130
0.5313	0.0193	400	1.0415
0.9664	0.0387	800	1.0256
0.8627	0.0580	1200	1.0135
1.1515	0.0774	1600	1.0094
1.5126	0.0967	2000	1.0025
1.2843	0.1161	2400	0.9913
0.761	0.1354	2800	0.9808
1.1393	0.1548	3200	0.9711
0.8509	0.1741	3600	0.9630
0.8974	0.1935	4000	0.9552
0.634	0.2128	4400	0.9495
0.9621	0.2322	4800	0.9436
0.8416	0.2515	5200	0.9398
1.2129	0.2709	5600	0.9377
0.747	0.2902	6000	0.9374

Framework versions

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