|
--- |
|
library_name: transformers |
|
license: llama3.1 |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- shisa-ai/s1K-1.1-translated-sharegpt |
|
- shisa-ai/gair_limo-translated-sharegpt |
|
model-index: |
|
- name: outputs/ablation-25-reasoning-shisa-v2-llama-3.1-8b-lr8e6 |
|
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/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: `0.6.0` |
|
```yaml |
|
# train w/ shisa-ai/shisa-v1-athenev2-reannotated-filtered |
|
|
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
# User Liger |
|
plugins: |
|
- axolotl.integrations.liger.LigerPlugin |
|
liger_rope: true |
|
liger_rms_norm: true |
|
liger_glu_activation: true |
|
liger_fused_linear_cross_entropy: true |
|
|
|
chat_template: llama3 |
|
datasets: |
|
- path: shisa-ai/s1K-1.1-translated-sharegpt |
|
# type: sharegpt deprecated |
|
type: chat_template |
|
field_messages: conversations |
|
message_field_role: from |
|
message_field_content: value |
|
- path: shisa-ai/gair_limo-translated-sharegpt |
|
# type: sharegpt deprecated |
|
type: chat_template |
|
field_messages: conversations |
|
message_field_role: from |
|
message_field_content: value |
|
shuffle_merged_datasets: false |
|
dataset_prepared_path: last_run_prepared |
|
val_set_size: 0.05 |
|
output_dir: ./outputs/ablation-25-reasoning-shisa-v2-llama-3.1-8b-lr8e6 |
|
|
|
sequence_len: 8192 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
# marginal difference |
|
neftune_noise_alpha: 5 |
|
|
|
use_wandb: true |
|
wandb_project: shisa-v2 |
|
wandb_entity: augmxnt |
|
wandb_name: ablation-25-reasoning-shisa-v2-llama-3.1-8b-lr8e6 |
|
|
|
gradient_accumulation_steps: 2 |
|
micro_batch_size: 4 |
|
num_epochs: 5 |
|
optimizer: paged_adamw_8bit |
|
lr_scheduler: linear |
|
learning_rate: 1e-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_ratio: 0.05 |
|
evals_per_epoch: 2 |
|
eval_table_size: |
|
saves_per_epoch: 0 |
|
save_total_limit: 1 # Only store a single checkpoint |
|
debug: |
|
deepspeed: zero3_bf16.json |
|
weight_decay: 1e-4 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
pad_token: <|end_of_text|> |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# outputs/ablation-25-reasoning-shisa-v2-llama-3.1-8b-lr8e6 |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the shisa-ai/s1K-1.1-translated-sharegpt and the shisa-ai/gair_limo-translated-sharegpt datasets. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6817 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 32 |
|
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 5.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.0922 | 0.0244 | 1 | 0.8761 | |
|
| 0.9325 | 0.5122 | 21 | 0.7089 | |
|
| 0.7914 | 1.0244 | 42 | 0.6543 | |
|
| 0.7889 | 1.5366 | 63 | 0.6405 | |
|
| 0.731 | 2.0488 | 84 | 0.6421 | |
|
| 0.7322 | 2.5610 | 105 | 0.6433 | |
|
| 0.6002 | 3.0732 | 126 | 0.6641 | |
|
| 0.5797 | 3.5854 | 147 | 0.6603 | |
|
| 0.5329 | 4.0976 | 168 | 0.6848 | |
|
| 0.4481 | 4.6098 | 189 | 0.6817 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.3 |
|
- Pytorch 2.6.0+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
