|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: kakaocorp/kanana-1.5-2.1b-instruct-2505 |
|
|
tags: |
|
|
- axolotl |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- train.jsonl |
|
|
model-index: |
|
|
- name: fc-proj1-test01 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
|
|
<details><summary>See axolotl config</summary> |
|
|
|
|
|
axolotl version: `0.10.0` |
|
|
```yaml |
|
|
# base_model: mistralai/Mistral-Nemo-Base-2407 |
|
|
base_model: kakaocorp/kanana-1.5-2.1b-instruct-2505 |
|
|
|
|
|
# Enable to use mistral-common tokenizer |
|
|
# tokenizer_use_mistral_common: true |
|
|
|
|
|
# Automatically upload checkpoint and final model to HF |
|
|
# hub_model_id: username/custom_model_name |
|
|
|
|
|
load_in_8bit: false |
|
|
load_in_4bit: false |
|
|
|
|
|
# datasets: |
|
|
# - path: fozziethebeat/alpaca_messages_2k_test |
|
|
# type: chat_template |
|
|
|
|
|
datasets: |
|
|
- path: train.jsonl |
|
|
type: chat_template |
|
|
|
|
|
dataset_prepared_path: preprocess |
|
|
val_set_size: 0.01 |
|
|
output_dir: ./outputs |
|
|
dataloader_num_workers: 56 |
|
|
|
|
|
adapter: |
|
|
# adapter: lora |
|
|
lora_model_dir: |
|
|
|
|
|
# lora_r: 32 |
|
|
# lora_alpha: 16 |
|
|
# lora_dropout: 0.05 |
|
|
# lora_target_linear: true |
|
|
# lora_target_modules: |
|
|
# - gate_proj |
|
|
# - down_proj |
|
|
# - up_proj |
|
|
# - q_proj |
|
|
# - v_proj |
|
|
# - k_proj |
|
|
# - o_proj |
|
|
|
|
|
# lora_mlp_kernel: true |
|
|
# lora_qkv_kernel: true |
|
|
# lora_o_kernel: true |
|
|
|
|
|
sequence_len: 8192 |
|
|
sample_packing: false |
|
|
eval_sample_packing: false |
|
|
pad_to_sequence_len: false |
|
|
|
|
|
plugins: |
|
|
- axolotl.integrations.liger.LigerPlugin |
|
|
liger_rope: true |
|
|
liger_rms_norm: true |
|
|
liger_swiglu: true |
|
|
liger_fused_linear_cross_entropy: true |
|
|
|
|
|
wandb_project: fastcampus |
|
|
wandb_entity: |
|
|
wandb_watch: |
|
|
wandb_name: fc-proj1-test01 |
|
|
wandb_log_model: |
|
|
hub_model_id: amphora/fc-proj1-test01 |
|
|
|
|
|
gradient_accumulation_steps: 4 |
|
|
micro_batch_size: 16 |
|
|
num_epochs: 3 |
|
|
optimizer: adamw_torch_fused |
|
|
# optimizer: adamw_bnb_8bit |
|
|
lr_scheduler: cosine |
|
|
learning_rate: 2e-5 |
|
|
|
|
|
bf16: auto |
|
|
tf32: false |
|
|
|
|
|
# torch_compile: auto |
|
|
# torch_compile_backend: inductor |
|
|
|
|
|
gradient_checkpointing: |
|
|
resume_from_checkpoint: |
|
|
logging_steps: 1 |
|
|
flash_attention: true |
|
|
# flash_attn_rms_norm: true |
|
|
# flash_attn_cross_entropy: true |
|
|
# flash_attn_fuse_qkv: true |
|
|
flash_attn_fuse_mlp: true |
|
|
|
|
|
warmup_ratio: 0.05 |
|
|
# warmup_steps: 10 |
|
|
weight_decay: 0.01 |
|
|
evals_per_epoch: 0 |
|
|
saves_per_epoch: 1 |
|
|
|
|
|
# deepspeed: deepspeed_configs/zero3_bf16.json |
|
|
# fsdp: |
|
|
# # - shard_grad_ops |
|
|
# - full_shard |
|
|
# - auto_wrap |
|
|
# fsdp_config: |
|
|
# fsdp_state_dict_type: FULL_STATE_DICT |
|
|
# fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer |
|
|
# fsdp_activation_checkpointing: true |
|
|
|
|
|
fsdp: |
|
|
# - shard_grad_ops |
|
|
- full_shard |
|
|
- auto_wrap |
|
|
fsdp_config: |
|
|
fsdp_backward_prefetch: BACKWARD_PRE |
|
|
fsdp_state_dict_type: SHARDED_STATE_DICT |
|
|
fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer |
|
|
fsdp_activation_checkpointing: true |
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# fc-proj1-test01 |
|
|
|
|
|
This model is a fine-tuned version of [kakaocorp/kanana-1.5-2.1b-instruct-2505](https://huggingface.co/kakaocorp/kanana-1.5-2.1b-instruct-2505) on the train.jsonl 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: 2e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 2 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 128 |
|
|
- total_eval_batch_size: 32 |
|
|
- 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: 43 |
|
|
- training_steps: 860 |
|
|
|
|
|
### Training results |
|
|
|
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.52.3 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.2 |
|
|
|
