本モデルはaxolotlの使い方の解説記事のデモで作成されたモデルです。モデルとしては特に特に利用価値のないものになっているのでご注意ください。
以下、自動生成されたREADMEです。
See axolotl config
axolotl version: 0.5.3.dev0
# 学習のベースモデルに関する設定
base_model: google/gemma-2-2b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# 学習後のモデルのHFへのアップロードに関する設定
hub_model_id: Aratako/gemma-2-2b-axolotl-sft-v1.0
hub_strategy: "end"
push_dataset_to_hub:
hf_use_auth_token: true
# Liger Kernelの設定(学習の軽量・高速化)
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_cross_entropy: false
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
# 量子化に関する設定
load_in_8bit: false
load_in_4bit: true
# SFTに利用するchat templateの設定
chat_template: gemma
# 学習データセットの前処理に関する設定
datasets:
- path: kanhatakeyama/ramdom-to-fixed-multiturn-Calm3
split: 20240806filtered[0:10000]
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
- path: llm-jp/magpie-sft-v1.0
split: train[0:10000]
type: chat_template
field_messages: conversations
message_field_role: role
message_field_content: content
- path: Aratako/magpie-qwen2.5-32b-reasoning-100k-formatted
split: train[0:10000]
type: chat_template
field_messages: conversations
message_field_role: role
message_field_content: content
# データセット、モデルの出力先に関する設定
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/data/sft-data
output_dir: /workspace/data/models/gemma-2-2b-axolotl-sft-v1.0
# valid datasetのサイズ
val_set_size: 0.05
# LoRAに関する設定(フルファインチューニングしたい場合は全て空欄にする)
adapter: qlora
lora_model_dir:
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
# wandbに関する設定
wandb_project: axolotl
wandb_entity: aratako-lm
wandb_watch:
wandb_name: sft-lora-1
wandb_log_model:
# 学習に関する様々な設定
sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
cosine_min_lr_ratio: 0.1
learning_rate: 3e-4
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: false
early_stopping_patience:
auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
save_strategy: steps
save_steps: 50
save_total_limit: 2
warmup_steps: 10
eval_steps: 50
eval_batch_size: 1
eval_table_size:
eval_max_new_tokens:
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <pad>
gemma-2-2b-axolotl-sft-v1.0
This model is a fine-tuned version of google/gemma-2-2b on the kanhatakeyama/ramdom-to-fixed-multiturn-Calm3, the llm-jp/magpie-sft-v1.0 and the Aratako/magpie-qwen2.5-32b-reasoning-100k-formatted datasets. It achieves the following results on the evaluation set:
- Loss: 1.3378
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: 0.0003
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- total_eval_batch_size: 2
- 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: 10
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.3251 | 0.3726 | 50 | 1.3855 |
1.3015 | 0.7452 | 100 | 1.3378 |
Framework versions
- PEFT 0.14.0
- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 0