|
--- |
|
license: apache-2.0 |
|
base_model: N8Programs/llamoe-8x1b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: 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: N8Programs/llamoe-8x1b |
|
model_type: MixtralForCausalLM |
|
tokenizer_type: LlamaTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
datasets: |
|
- path: mhenrichsen/alpaca_2k_test |
|
type: alpaca |
|
dataset_prepared_path: |
|
val_set_size: 0.05 |
|
output_dir: ./out |
|
|
|
sequence_len: 2048 |
|
sample_packing: true |
|
eval_sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
wandb_project: tinyllamoe |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: run-1 |
|
wandb_log_model: run-1 |
|
|
|
gradient_accumulation_steps: 4 |
|
micro_batch_size: 2 |
|
num_epochs: 4 |
|
optimizer: adafactor |
|
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 |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 4 |
|
saves_per_epoch: 1 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# out |
|
|
|
This model is a fine-tuned version of [N8Programs/llamoe-8x1b](https://huggingface.co/N8Programs/llamoe-8x1b) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7176 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- 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: 10 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2099 | 0.04 | 1 | 1.2991 | |
|
| 1.3823 | 0.27 | 7 | 1.4997 | |
|
| 10.4722 | 0.54 | 14 | 2.6370 | |
|
| 1.6521 | 0.82 | 21 | 1.4303 | |
|
| 1.6555 | 1.07 | 28 | 1.7053 | |
|
| 1.7864 | 1.34 | 35 | 1.8820 | |
|
| 1.2141 | 1.61 | 42 | 1.6614 | |
|
| 1.1488 | 1.88 | 49 | 1.5619 | |
|
| 0.4733 | 2.14 | 56 | 1.6381 | |
|
| 0.444 | 2.41 | 63 | 1.6311 | |
|
| 0.4717 | 2.68 | 70 | 1.6398 | |
|
| 0.4657 | 2.95 | 77 | 1.5938 | |
|
| 0.1066 | 3.2 | 84 | 1.6952 | |
|
| 0.1547 | 3.48 | 91 | 1.7209 | |
|
| 0.1246 | 3.75 | 98 | 1.7176 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.0 |
|
|
