|
--- |
|
library_name: transformers |
|
license: llama3 |
|
base_model: meta-llama/Meta-Llama-3-8B |
|
tags: |
|
- axolotl |
|
- generated_from_trainer |
|
model-index: |
|
- name: L3-Pneuma-8B |
|
results: [] |
|
--- |
|
|
|
This is just a 6bpw EXL2 quant of the original model which can be found on my huggingface profile. I will write a real model card when I have the final model...it's an experimental tune using part of my sandevistan dataset. |
|
|
|
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.4.1` |
|
```yaml |
|
base_model: meta-llama/Meta-Llama-3-8B |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
datasets: |
|
- path: Kquant03/Sandevistan_Reformat |
|
type: customllama3_stan |
|
dataset_prepared_path: last_run_prepared |
|
val_set_size: 0.05 |
|
output_dir: ./outputs/out |
|
max_steps: 80000 |
|
|
|
fix_untrained_tokens: true |
|
|
|
sequence_len: 4096 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
wandb_project: Pneuma |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 16 |
|
micro_batch_size: 8 |
|
num_epochs: 1 |
|
optimizer: paged_adamw_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.00001 |
|
max_grad_norm: 1 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: false |
|
|
|
gradient_checkpointing: unsloth |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
eval_sample_packing: false |
|
|
|
plugins: |
|
- axolotl.integrations.liger.LigerPlugin |
|
liger_rope: true |
|
liger_rms_norm: true |
|
liger_swiglu: true |
|
liger_fused_linear_cross_entropy: true |
|
|
|
hub_model_id: Replete-AI/L3-Pneuma-8B |
|
hub_strategy: every_save |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 3 |
|
eval_table_size: |
|
saves_per_epoch: 3 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.1 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
bos_token: "<|begin_of_text|>" |
|
eos_token: "<|end_of_text|>" |
|
pad_token: "<|end_of_text|>" |
|
tokens: |
|
``` |
|
|
|
</details><br> |
|
|
|
# L3-Pneuma-8B |
|
|
|
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 [Sandevistan](https://huggingface.co/datasets/Replete-AI/Sandevistan) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7381 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- 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 |
|
- training_steps: 743 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.0378 | 0.0013 | 1 | 3.0437 | |
|
| 0.6816 | 0.3334 | 248 | 2.7341 | |
|
| 0.6543 | 0.6667 | 496 | 2.7381 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.20.1 |
|
|
