|
--- |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: finetune/outputs/climate |
|
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: `0.4.1` |
|
```yaml |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
chat_template: chatml |
|
datasets: |
|
- path: Howard881010/climate |
|
type: alpaca |
|
train_on_split: train |
|
dataset_prepared_path: |
|
val_set_size: 0.05 |
|
output_dir: ./finetune/outputs/climate |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
|
|
sequence_len: 2048 |
|
sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
lora_r: 32 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_target_modules: |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
|
|
wandb_project: finetune |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: climate |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 2 |
|
micro_batch_size: 1 |
|
num_epochs: 10 |
|
optimizer: paged_adamw_32bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.0002 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: false |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
eval_sample_packing: False |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
saves_per_epoch: 1 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
# For finetune |
|
seed: 42 |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://rosewandb.ucsd.edu/cht028/finetune/runs/xdu6khql) |
|
# finetune/outputs/climate |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0009 |
|
|
|
## 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 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- total_eval_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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.7472 | 0.0056 | 1 | 2.0532 | |
|
| 1.1662 | 0.2542 | 45 | 1.2719 | |
|
| 0.8512 | 0.5085 | 90 | 1.1146 | |
|
| 1.141 | 0.7627 | 135 | 0.9757 | |
|
| 0.5009 | 1.0169 | 180 | 0.7862 | |
|
| 0.4804 | 1.2712 | 225 | 0.6073 | |
|
| 0.3472 | 1.5254 | 270 | 0.4267 | |
|
| 0.2733 | 1.7797 | 315 | 0.2808 | |
|
| 0.1484 | 2.0339 | 360 | 0.1742 | |
|
| 0.2064 | 2.2881 | 405 | 0.1261 | |
|
| 0.1144 | 2.5424 | 450 | 0.0700 | |
|
| 0.0787 | 2.7966 | 495 | 0.0390 | |
|
| 0.0523 | 3.0508 | 540 | 0.0269 | |
|
| 0.0606 | 3.3051 | 585 | 0.0193 | |
|
| 0.0568 | 3.5593 | 630 | 0.0132 | |
|
| 0.063 | 3.8136 | 675 | 0.0064 | |
|
| 0.081 | 4.0678 | 720 | 0.0039 | |
|
| 0.0748 | 4.3220 | 765 | 0.0022 | |
|
| 0.0812 | 4.5763 | 810 | 0.0017 | |
|
| 0.0313 | 4.8305 | 855 | 0.0015 | |
|
| 0.0229 | 5.0847 | 900 | 0.0012 | |
|
| 0.0518 | 5.3390 | 945 | 0.0011 | |
|
| 0.019 | 5.5932 | 990 | 0.0011 | |
|
| 0.09 | 5.8475 | 1035 | 0.0010 | |
|
| 0.0907 | 6.1017 | 1080 | 0.0010 | |
|
| 0.0876 | 6.3559 | 1125 | 0.0010 | |
|
| 0.0716 | 6.6102 | 1170 | 0.0010 | |
|
| 0.0728 | 6.8644 | 1215 | 0.0009 | |
|
| 0.0338 | 7.1186 | 1260 | 0.0009 | |
|
| 0.032 | 7.3729 | 1305 | 0.0009 | |
|
| 0.0304 | 7.6271 | 1350 | 0.0009 | |
|
| 0.0508 | 7.8814 | 1395 | 0.0009 | |
|
| 0.0196 | 8.1356 | 1440 | 0.0009 | |
|
| 0.0709 | 8.3898 | 1485 | 0.0009 | |
|
| 0.0852 | 8.6441 | 1530 | 0.0009 | |
|
| 0.0803 | 8.8983 | 1575 | 0.0009 | |
|
| 0.1225 | 9.1525 | 1620 | 0.0009 | |
|
| 0.0533 | 9.4068 | 1665 | 0.0009 | |
|
| 0.0374 | 9.6610 | 1710 | 0.0009 | |
|
| 0.0857 | 9.9153 | 1755 | 0.0009 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.43.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |