metadata
library_name: transformers
base_model: minpeter/pretrained-tiny-ko
tags:
- axolotl
- generated_from_trainer
datasets:
- lemon-mint/Korean-FineTome-100k
- lemon-mint/smol-koreantalk
model-index:
- name: ko-tiny-exp
results: []
See axolotl config
axolotl version: 0.10.0.dev0
base_model: minpeter/pretrained-tiny-ko
chat_template: chatml
datasets:
- path: lemon-mint/Korean-FineTome-100k
type: chat_template
split: train[:20%]
field_messages: messages
message_property_mappings:
role: role
content: content
- path: lemon-mint/smol-koreantalk
type: chat_template
split: train[:20%]
field_messages: messages
message_property_mappings:
role: role
content: content
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
hub_model_id: minpeter/ko-tiny-exp
output_dir: ./ouputs/ko-tiny-exp
wandb_project: "axolotl"
wandb_entity: "kasfiekfs-e"
save_steps: 200
warmup_steps: 100
eval_steps: 200
sequence_len: 1024
sample_packing: true
pad_to_sequence_len: true
gradient_accumulation_steps: 4
micro_batch_size: 32
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
bf16: auto
tf32: false
added_tokens_overrides:
128001: "<|im_end|>"
128002: "<|im_start|>"
special_tokens:
bos_token: <|begin_of_text|>
eos_token: <|im_end|>
pad_token: <|im_end|>
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true
num_epochs: 2
weight_decay: 0.0
ko-tiny-exp
This model is a fine-tuned version of minpeter/pretrained-tiny-ko on the lemon-mint/Korean-FineTome-100k and the lemon-mint/smol-koreantalk datasets. It achieves the following results on the evaluation set:
- Loss: 3.6038
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- total_eval_batch_size: 128
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 102
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.5674 | 0.0193 | 1 | 3.6038 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1