|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: meta-llama/Meta-Llama-3-8B |
|
model-index: |
|
- name: lora-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: meta-llama/Meta-Llama-3-8B |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: true |
|
load_in_4bit: false |
|
strict: false |
|
|
|
datasets: |
|
- path: kloodia/raw_physic |
|
type: oasst |
|
dataset_prepared_path: |
|
val_set_size: 0.05 |
|
output_dir: ./lora-out |
|
|
|
sequence_len: 4096 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
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: 1 |
|
num_epochs: 4 |
|
optimizer: adamw_bnb_8bit |
|
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 |
|
s2_attention: |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_max_new_tokens: 128 |
|
saves_per_epoch: 1 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
pad_token: <|end_of_text|> |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# lora-out |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5060 |
|
|
|
## 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: 4 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 4 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.641 | 0.01 | 1 | 0.6417 | |
|
| 0.5093 | 0.25 | 42 | 0.5260 | |
|
| 0.4665 | 0.5 | 84 | 0.5118 | |
|
| 0.4431 | 0.75 | 126 | 0.5043 | |
|
| 0.4523 | 1.0 | 168 | 0.4985 | |
|
| 0.4237 | 1.23 | 210 | 0.4985 | |
|
| 0.4002 | 1.48 | 252 | 0.4976 | |
|
| 0.3656 | 1.73 | 294 | 0.4955 | |
|
| 0.3744 | 1.98 | 336 | 0.4942 | |
|
| 0.3278 | 2.21 | 378 | 0.5012 | |
|
| 0.344 | 2.46 | 420 | 0.5003 | |
|
| 0.3216 | 2.71 | 462 | 0.4984 | |
|
| 0.3371 | 2.96 | 504 | 0.4980 | |
|
| 0.3243 | 3.19 | 546 | 0.5051 | |
|
| 0.3184 | 3.44 | 588 | 0.5052 | |
|
| 0.313 | 3.69 | 630 | 0.5060 | |
|
| 0.3097 | 3.94 | 672 | 0.5060 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.0.dev0 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
