|
--- |
|
library_name: transformers |
|
license: llama3.1 |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- shisa-ai/shisa-v2-code-math-reasoning-sft-mix |
|
model-index: |
|
- name: outputs/ablation-39-cmrmix.masked-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/shisa-v2-code-math-reasoning-sft-mix |
|
type: chat_template |
|
field_messages: conversations |
|
message_property_mappings: |
|
role: role |
|
content: content |
|
roles: |
|
system: |
|
- system |
|
assistant: |
|
- gpt |
|
- model |
|
- assistant |
|
user: |
|
- human |
|
- user |
|
roles_to_train: ["assistant"] |
|
|
|
dataset_prepared_path: last_run_prepared |
|
val_set_size: 0.05 |
|
output_dir: ./outputs/ablation-39-cmrmix.masked-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-39-cmrmix.masked-shisa-v2-llama-3.1-8b-lr8e6 |
|
|
|
gradient_accumulation_steps: 2 |
|
micro_batch_size: 4 |
|
num_epochs: 3 |
|
optimizer: paged_adamw_8bit |
|
lr_scheduler: linear |
|
learning_rate: 8e-6 |
|
|
|
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: |
|
saves_per_epoch: 0 |
|
save_total_limit: 1 # Only store a single checkpoint |
|
debug: |
|
deepspeed: zero3_bf16.json |
|
weight_decay: 0.00 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
pad_token: <|end_of_text|> |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# outputs/ablation-39-cmrmix.masked-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/shisa-v2-code-math-reasoning-sft-mix dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4404 |
|
|
|
## 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: 8e-06 |
|
- 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: 100 |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.9144 | 0.0068 | 1 | 0.6696 | |
|
| 0.6754 | 0.5 | 74 | 0.4513 | |
|
| 0.6119 | 1.0 | 148 | 0.4259 | |
|
| 0.5958 | 1.5 | 222 | 0.4243 | |
|
| 0.5772 | 2.0 | 296 | 0.4208 | |
|
| 0.5074 | 2.5 | 370 | 0.4395 | |
|
| 0.4894 | 3.0 | 444 | 0.4404 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.3 |
|
- Pytorch 2.6.0+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
