|
--- |
|
license: other |
|
base_model: Undi95/Meta-Llama-3-8B-hf |
|
tags: |
|
- generated_from_trainer |
|
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: Undi95/Meta-Llama-3-8B-hf |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
datasets: |
|
- path: Pbug/bftest |
|
type: sharegpt |
|
dataset_prepared_path: |
|
val_set_size: 0.05 |
|
output_dir: ./lora-out |
|
|
|
sequence_len: 8192 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
wandb_project: |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 8 |
|
micro_batch_size: 1 |
|
num_epochs: 10 |
|
optimizer: paged_adamw_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 2e-5 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: false |
|
|
|
gradient_checkpointing: true |
|
gradient_checkpointing_kwargs: |
|
use_reentrant: false |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
warmup_steps: 100 |
|
evals_per_epoch: 2 |
|
eval_table_size: |
|
eval_sample_packing: False |
|
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 [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: nan |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- 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: 100 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.5419 | 0.03 | 1 | nan | |
|
| 2.5492 | 0.51 | 18 | nan | |
|
| 2.434 | 1.01 | 36 | nan | |
|
| 2.3504 | 1.5 | 54 | nan | |
|
| 2.3643 | 2.0 | 72 | nan | |
|
| 2.2834 | 2.48 | 90 | nan | |
|
| 2.2383 | 2.98 | 108 | nan | |
|
| 1.8786 | 3.47 | 126 | nan | |
|
| 1.7963 | 3.98 | 144 | nan | |
|
| 2.1853 | 4.47 | 162 | nan | |
|
| 1.4333 | 4.98 | 180 | nan | |
|
| 1.2058 | 5.46 | 198 | nan | |
|
| 1.125 | 5.96 | 216 | nan | |
|
| 0.809 | 6.44 | 234 | nan | |
|
| 0.7118 | 6.94 | 252 | nan | |
|
| 0.7175 | 7.44 | 270 | nan | |
|
| 0.7341 | 7.94 | 288 | nan | |
|
| 0.774 | 8.44 | 306 | nan | |
|
| 0.6379 | 8.94 | 324 | nan | |
|
| 0.562 | 9.41 | 342 | nan | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
