Downloads · 30 days
0
0% of all-time downloads
rayonlabs/llama-3-Korean-Bllossom-8B-anli-87383d7a-b421-4eb9-b89a-3370ac03f201
llama-3-Korean-Bllossom-8B-anli-87383d7a-b421-4eb9-b89a-3370ac03f201 is a machine learning model from rayonlabs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
0
0% of all-time downloads
All-time downloads
14
Public
Repo size
4.7 GB
Likes
0
Public
Click a slice to open those files.
.pt1.3 GB · 40%
From the Hugging Face model README
axolotl version: 0.4.1
adapter: lora
base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 24bd353218bb7dd2_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/24bd353218bb7dd2_train_data.json
type:
field_instruction: premise
field_output: hypothesis
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 500
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: true
hub_model_id: lesso06/b557bf87-a0c9-405d-99e3-0b753218bad4
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000206
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 128
lora_dropout: 0.15
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: 1000
micro_batch_size: 4
mlflow_experiment_name: /tmp/24bd353218bb7dd2_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 500
saves_per_epoch: null
seed: 60
sequence_len: 1024
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: 87383d7a-b421-4eb9-b89a-3370ac03f201
wandb_project: 06a
wandb_run: your_name
wandb_runid: 87383d7a-b421-4eb9-b89a-3370ac03f201
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null
</details><br>
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:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0002 | 1 | 4.5349 |
| 1.771 | 0.1000 | 500 | 1.7675 |
| 1.6477 | 0.1999 | 1000 | 1.6766 |