|
--- |
|
base_model: NousResearch/Meta-Llama-3-8B-Instruct |
|
library_name: peft |
|
license: other |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: workspace/axolotl/vinh/NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39 |
|
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: NousResearch/Meta-Llama-3-8B-Instruct |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
datasets: |
|
- path: /workspace/axolotl/vinh/PAL/input_output_llama3.json |
|
type: input_output |
|
dataset_prepared_path: |
|
val_set_size: 0.05 |
|
eval_sample_packing: false |
|
output_dir: /workspace/axolotl/vinh/NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39 |
|
|
|
sequence_len: 2048 |
|
sample_packing: false |
|
pad_to_sequence_len: false |
|
|
|
adapter: lora |
|
lora_model_dir: |
|
lora_r: 64 |
|
lora_alpha: 128 |
|
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: 128 |
|
micro_batch_size: 1 |
|
num_epochs: 3 |
|
optimizer: paged_adamw_32bit |
|
lr_scheduler: cosine |
|
learning_rate: 2e-4 |
|
|
|
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: true |
|
s2_attention: |
|
|
|
loss_watchdog_threshold: 5.0 |
|
loss_watchdog_patience: 3 |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 10 |
|
eval_table_size: |
|
eval_max_new_tokens: 512 |
|
saves_per_epoch: 2 |
|
save_total_limit: 20 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
pad_token: <|end_of_text|> |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# workspace/axolotl/vinh/NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39 |
|
|
|
This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0392 |
|
|
|
## 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 |
|
- gradient_accumulation_steps: 128 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.5339 | 0.0095 | 1 | 0.5036 | |
|
| 0.0879 | 0.1043 | 11 | 0.0813 | |
|
| 0.0582 | 0.2086 | 22 | 0.0629 | |
|
| 0.06 | 0.3129 | 33 | 0.0566 | |
|
| 0.0593 | 0.4172 | 44 | 0.0514 | |
|
| 0.054 | 0.5214 | 55 | 0.0483 | |
|
| 0.0459 | 0.6257 | 66 | 0.0469 | |
|
| 0.0397 | 0.7300 | 77 | 0.0460 | |
|
| 0.0453 | 0.8343 | 88 | 0.0449 | |
|
| 0.04 | 0.9386 | 99 | 0.0429 | |
|
| 0.0338 | 1.0429 | 110 | 0.0418 | |
|
| 0.0322 | 1.1472 | 121 | 0.0422 | |
|
| 0.0275 | 1.2515 | 132 | 0.0416 | |
|
| 0.0322 | 1.3558 | 143 | 0.0416 | |
|
| 0.0266 | 1.4600 | 154 | 0.0404 | |
|
| 0.0249 | 1.5643 | 165 | 0.0397 | |
|
| 0.0292 | 1.6686 | 176 | 0.0393 | |
|
| 0.031 | 1.7729 | 187 | 0.0385 | |
|
| 0.0265 | 1.8772 | 198 | 0.0375 | |
|
| 0.0273 | 1.9815 | 209 | 0.0375 | |
|
| 0.0175 | 2.0858 | 220 | 0.0377 | |
|
| 0.0168 | 2.1901 | 231 | 0.0396 | |
|
| 0.0182 | 2.2943 | 242 | 0.0403 | |
|
| 0.0201 | 2.3986 | 253 | 0.0397 | |
|
| 0.0138 | 2.5029 | 264 | 0.0393 | |
|
| 0.0173 | 2.6072 | 275 | 0.0392 | |
|
| 0.0186 | 2.7115 | 286 | 0.0392 | |
|
| 0.0209 | 2.8158 | 297 | 0.0392 | |
|
| 0.0185 | 2.9201 | 308 | 0.0392 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.1 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |