You can deploy this model and start earning money today!

abaddon182/
34c5662d-594a-4255-850e-7df5fc3b7ec2

Name: 34c5662d-594a-4255-850e-7df5fc3b7ec2
Availability: InStock

generated_from_trainer

MLP-KTLim/llama-3-Korean-Bllossom-8B

adapter

llama3

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
bf16: true
chat_template: llama3
dataloader_num_workers: 24
dataset_prepared_path: null
datasets:
- data_files:
  - ef9e1d78596cd182_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/ef9e1d78596cd182_train_data.json
  type:
    field_input: context
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
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: false
group_by_length: true
hub_model_id: abaddon182/34c5662d-594a-4255-850e-7df5fc3b7ec2
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 2000
micro_batch_size: 4
mlflow_experiment_name: /tmp/ef9e1d78596cd182_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
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: 200
saves_per_epoch: null
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 12f950a6-55b7-4f9f-97bd-fd31a61a9ebf
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 12f950a6-55b7-4f9f-97bd-fd31a61a9ebf
warmup_steps: 100
weight_decay: 0.1
xformers_attention: null

34c5662d-594a-4255-850e-7df5fc3b7ec2

This model is a fine-tuned version of MLP-KTLim/llama-3-Korean-Bllossom-8B on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.1066

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: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-8
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0000	1	2.9640
1.2464	0.0077	200	1.2777
1.245	0.0154	400	1.2724
1.2227	0.0231	600	1.2045
1.1995	0.0308	800	1.1826
1.1947	0.0385	1000	1.1561
1.1879	0.0462	1200	1.1407
1.1837	0.0539	1400	1.1241
1.0986	0.0616	1600	1.1122
1.0991	0.0693	1800	1.1096
1.0585	0.0770	2000	1.1066

Framework versions

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