|
--- |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: NousResearch/Llama-2-7b-hf |
|
model-index: |
|
- name: qlora-out |
|
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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.4.0` |
|
```yaml |
|
base_model: NousResearch/Llama-2-7b-hf |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: LlamaTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
datasets: |
|
- path: caffeinatedcherrychic/cidds-agg-balanced |
|
type: alpaca |
|
dataset_prepared_path: last_run_prepared |
|
val_set_size: 0.1 |
|
output_dir: ./qlora-out |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
|
|
sequence_len: 2048 |
|
sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
lora_r: 32 |
|
lora_alpha: 64 |
|
lora_dropout: 0.05 |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
lora_target_modules: |
|
- gate_proj |
|
- down_proj |
|
- up_proj |
|
- q_proj |
|
- v_proj |
|
- k_proj |
|
- o_proj |
|
|
|
wandb_project: |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 4 |
|
micro_batch_size: 2 |
|
num_epochs: 5 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.0002 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: true |
|
fp16: false |
|
tf32: false |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
loss_watchdog_threshold: 5.0 |
|
loss_watchdog_patience: 3 |
|
|
|
max_steps: 500 |
|
warmup_steps: 10 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_max_new_tokens: 1 |
|
saves_per_epoch: 1 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.001 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# qlora-out |
|
|
|
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1998 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- 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 |
|
- training_steps: 62 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 6.6299 | 0.08 | 1 | 6.9320 | |
|
| 5.9686 | 0.32 | 4 | 4.4463 | |
|
| 0.5956 | 0.64 | 8 | 0.5577 | |
|
| 0.4848 | 0.96 | 12 | 0.8370 | |
|
| 0.4913 | 1.28 | 16 | 0.4896 | |
|
| 0.671 | 1.6 | 20 | 0.5175 | |
|
| 2.6136 | 1.92 | 24 | 2.3446 | |
|
| 0.6383 | 2.24 | 28 | 0.5194 | |
|
| 0.5776 | 2.56 | 32 | 0.5653 | |
|
| 0.4913 | 2.88 | 36 | 0.4791 | |
|
| 0.3486 | 3.2 | 40 | 0.4041 | |
|
| 0.4944 | 3.52 | 44 | 0.3174 | |
|
| 0.4788 | 3.84 | 48 | 0.3952 | |
|
| 0.3321 | 4.16 | 52 | 0.2342 | |
|
| 0.207 | 4.48 | 56 | 0.2058 | |
|
| 0.4502 | 4.8 | 60 | 0.1998 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.0 |
