See axolotl config
axolotl version: 0.4.1
adapter: qlora
base_model: Qwen/Qwen2-7B
bf16: auto
dataset_prepared_path: null
datasets:
- path: ResplendentAI/Synthetic_Soul_1k
type: alpaca
debug: null
deepspeed: null
early_stopping_patience: null
eval_sample_packing: false
evals_per_epoch: 2
flash_attention: true
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
group_by_length: false
learning_rate: 2.0e-05
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 128
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 4
num_epochs: 4
optimizer: adamw_torch
output_dir: ./outputs/out
pad_to_sequence_len: false
resume_from_checkpoint: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 8192
special_tokens: null
strict: false
tf32: true
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_log_model: null
wandb_name: null
wandb_project: null
wandb_watch: null
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
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: 1.4422
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|
| 1.8248 | 0.0168 | 1 | 1.7354 |
| 1.2323 | 0.5042 | 30 | 1.4900 |
| 1.2644 | 1.0084 | 60 | 1.4405 |
| 1.1181 | 1.5126 | 90 | 1.4438 |
| 1.0902 | 2.0168 | 120 | 1.4244 |
| 1.0422 | 2.5210 | 150 | 1.4514 |
| 1.0635 | 3.0252 | 180 | 1.4363 |
| 0.9551 | 3.5294 | 210 | 1.4422 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.1.2+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 6