base_model: Qwen/Qwen2-7B
trust_remote_code: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
  - path: tatsu-lab/alpaca
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/out
sequence_len: 2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: qlora
lora_model_dir:
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: false
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
special_tokens:

outputs/out

This model is a fine-tuned version of Qwen/Qwen2-7B on the None dataset. It achieves the following results on the evaluation set:

Loss: 4.3265

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
10.7953	0.0031	1	10.8104
5.4963	0.2513	80	5.4101
5.0323	0.5026	160	5.0758
4.9877	0.7538	240	4.8417
4.7408	1.0051	320	4.6180
4.5097	1.2442	400	4.5066
4.3959	1.4955	480	4.4513
4.2488	1.7468	560	4.4107
4.3507	1.9980	640	4.3784
4.2352	2.2352	720	4.3684
4.2141	2.4865	800	4.3505
4.2739	2.7377	880	4.3375
4.4037	2.9890	960	4.3310
4.195	3.2269	1040	4.3287
4.1996	3.4782	1120	4.3268
4.1353	3.7295	1200	4.3265

Framework versions

PEFT 0.11.1
Transformers 4.41.1
Pytorch 2.1.2+cu118
Datasets 2.19.1
Tokenizers 0.19.1

leo009/Qwen2-finetuned

outputs/out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

leo009/
Qwen2-finetuned