You can deploy this model and start earning money today!

segopecelus/
456ccbb3-71a3-4f20-94f4-0ffb2da842a5

Name: 456ccbb3-71a3-4f20-94f4-0ffb2da842a5
Availability: InStock

generated_from_trainer

Korabbit/llama-2-ko-7b

adapter

Views

No views yet

See axolotl config

axolotl version: 0.10.0.dev0

yaml

adapter: lora
base_model: Korabbit/llama-2-ko-7b
bf16: true
datasets:
- data_files:
  - 76c2bd41df344a06_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_input: input
    field_instruction: instruct
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
eval_max_new_tokens: 128
evals_per_epoch: 4
flash_attention: false
fp16: false
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: true
hf_upload_public: true
hf_upload_repo_type: model
hub_model_id: segopecelus/456ccbb3-71a3-4f20-94f4-0ffb2da842a5
learning_rate: 0.0002
load_in_4bit: false
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: false
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 1814
micro_batch_size: 28
mlflow_experiment_name: /tmp/76c2bd41df344a06_train_data.json
output_dir: miner_id_24
rl: null
sample_packing: true
save_steps: 272
sequence_len: 2048
special_tokens:
  pad_token: </s>
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: true
trl: null
trust_remote_code: true
wandb_name: 7dacc20c-c659-4d29-a04f-64e45dadbd4c
wandb_project: Gradients-On-Demand
wandb_run: apriasmoro
wandb_runid: 7dacc20c-c659-4d29-a04f-64e45dadbd4c
warmup_steps: 100
weight_decay: 0.01

456ccbb3-71a3-4f20-94f4-0ffb2da842a5

This model is a fine-tuned version of Korabbit/llama-2-ko-7b on an unknown dataset.

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: 28
eval_batch_size: 28
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 56
total_eval_batch_size: 56
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
training_steps: 1814

Training results

Framework versions

PEFT 0.15.2
Transformers 4.51.3
Pytorch 2.5.1+cu124
Datasets 3.5.1
Tokenizers 0.21.1