adapter: qlora
auto_resume_from_checkpoints: true
base_model: dltjdgh0928/test_instruction
bf16: auto
chat_template: llama3
dataset_prepared_path: null
dataset_processes: 6
datasets:
- data_files:
  - aa50233b0137497d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/aa50233b0137497d_train_data.json
  type:
    field_instruction: content
    field_output: title
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 200
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/8258ff8f-2881-4270-8f2c-ea10e5121124
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: null
micro_batch_size: 3
mlflow_experiment_name: /tmp/aa50233b0137497d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_4bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 200
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0005
wandb_entity: null
wandb_mode: online
wandb_name: 0c788dab-2672-467c-950d-afa94bc890f0
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 0c788dab-2672-467c-950d-afa94bc890f0
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

8258ff8f-2881-4270-8f2c-ea10e5121124

This model is a fine-tuned version of dltjdgh0928/test_instruction on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.3624

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: 3
eval_batch_size: 3
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 12
optimizer: Use OptimizerNames.ADAMW_TORCH_4BIT 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: 30
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
8.6902	0.0000	1	2.5815
6.9058	0.0048	200	1.3610
5.3851	0.0096	400	1.3072
4.642	0.0145	600	1.3468
4.8068	0.0193	800	1.3304
6.5523	0.0241	1000	1.3624

Framework versions

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