Downloads · 30 days
3
13% of all-time downloads
yujia23/axolotl-qwen-1e-5-lora
axolotl-qwen-1e-5-lora is a machine learning model from yujia23. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
3
13% of all-time downloads
All-time downloads
23
Public
Repo size
1.8 GB
Likes
0
Public
Click a slice to open those files.
.safetensors960 MB · 53%
From the Hugging Face model README
axolotl version: 0.4.0
# base_model: Qwen/Qwen-7B
base_model: Qwen/Qwen1.5-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
# - path: mhenrichsen/alpaca_2k_test
# - path: /home/yujia/home/CN_Hateful/train_toxiCN_cn.json
- path: /home/yujia/home/CN_Hateful/train_toxiCN.json
ds_type: json
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/CN/toxi/3e-5/
output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/toxi/1e-5/
sequence_len: 256 # supports up to 8192
sample_packing: false
pad_to_sequence_len:
adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
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: 4
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention:
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 20
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
</details><br>
This model is a fine-tuned version of Qwen/Qwen1.5-7B on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4697 | 0.0 | 1 | 3.5475 |
| 0.0881 | 0.25 | 142 | 0.0819 |
| 0.1131 | 0.5 | 284 | 0.0763 |
| 0.0538 | 0.75 | 426 | 0.0732 |
| 0.0425 | 1.0 | 568 | 0.0656 |
| 0.0866 | 1.26 | 710 | 0.0582 |
| 0.0705 | 1.51 | 852 | 0.0593 |
| 0.0848 | 1.76 | 994 | 0.0562 |
| 0.0631 | 2.01 | 1136 | 0.0552 |
| 0.0299 | 2.26 | 1278 | 0.0551 |
| 0.0494 | 2.51 | 1420 | 0.0545 |
| 0.0417 | 2.76 | 1562 | 0.0540 |