|
|
--- |
|
|
library_name: peft |
|
|
license: llama3.2 |
|
|
base_model: unsloth/Llama-3.2-3B |
|
|
tags: |
|
|
- axolotl |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: 0419afd4-d740-497b-8afb-e4c2d4a21d7c |
|
|
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: `0.4.1` |
|
|
```yaml |
|
|
adapter: lora |
|
|
base_model: unsloth/Llama-3.2-3B |
|
|
bf16: true |
|
|
chat_template: llama3 |
|
|
dataset_prepared_path: null |
|
|
datasets: |
|
|
- data_files: |
|
|
- 9b4cab2992cdb07f_train_data.json |
|
|
ds_type: json |
|
|
format: custom |
|
|
path: /workspace/input_data/9b4cab2992cdb07f_train_data.json |
|
|
type: |
|
|
field_input: input |
|
|
field_instruction: instruction |
|
|
field_output: output |
|
|
format: '{instruction} {input}' |
|
|
no_input_format: '{instruction}' |
|
|
system_format: '{system}' |
|
|
system_prompt: '' |
|
|
debug: null |
|
|
device_map: |
|
|
? '' |
|
|
: 0,1,2,3,4,5,6,7 |
|
|
early_stopping_patience: 2 |
|
|
eval_max_new_tokens: 128 |
|
|
eval_steps: 100 |
|
|
eval_table_size: null |
|
|
flash_attention: true |
|
|
gradient_accumulation_steps: 8 |
|
|
gradient_checkpointing: true |
|
|
group_by_length: false |
|
|
hub_model_id: Alphatao/0419afd4-d740-497b-8afb-e4c2d4a21d7c |
|
|
hub_repo: null |
|
|
hub_strategy: null |
|
|
hub_token: null |
|
|
learning_rate: 0.0002 |
|
|
load_best_model_at_end: true |
|
|
load_in_4bit: false |
|
|
load_in_8bit: false |
|
|
local_rank: null |
|
|
logging_steps: 1 |
|
|
lora_alpha: 128 |
|
|
lora_dropout: 0.1 |
|
|
lora_fan_in_fan_out: null |
|
|
lora_model_dir: null |
|
|
lora_r: 64 |
|
|
lora_target_linear: true |
|
|
lora_target_modules: |
|
|
- q_proj |
|
|
- k_proj |
|
|
- v_proj |
|
|
- o_proj |
|
|
lr_scheduler: cosine |
|
|
max_grad_norm: 1.0 |
|
|
max_steps: 1779 |
|
|
micro_batch_size: 4 |
|
|
mlflow_experiment_name: /tmp/9b4cab2992cdb07f_train_data.json |
|
|
model_type: AutoModelForCausalLM |
|
|
num_epochs: 2 |
|
|
optimizer: adamw_bnb_8bit |
|
|
output_dir: miner_id_24 |
|
|
pad_to_sequence_len: true |
|
|
resume_from_checkpoint: null |
|
|
s2_attention: null |
|
|
sample_packing: false |
|
|
save_steps: 100 |
|
|
sequence_len: 2048 |
|
|
strict: false |
|
|
tf32: true |
|
|
tokenizer_type: AutoTokenizer |
|
|
train_on_inputs: false |
|
|
trust_remote_code: true |
|
|
val_set_size: 0.033916240452578315 |
|
|
wandb_entity: null |
|
|
wandb_mode: online |
|
|
wandb_name: 30612698-6e4a-41b9-a416-94b6b03904c8 |
|
|
wandb_project: Gradients-On-Demand |
|
|
wandb_run: your_name |
|
|
wandb_runid: 30612698-6e4a-41b9-a416-94b6b03904c8 |
|
|
warmup_steps: 10 |
|
|
weight_decay: 0.0 |
|
|
xformers_attention: null |
|
|
|
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# 0419afd4-d740-497b-8afb-e4c2d4a21d7c |
|
|
|
|
|
This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.7884 |
|
|
|
|
|
## 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: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 8 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 10 |
|
|
- training_steps: 1779 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 1.4843 | 0.0002 | 1 | 1.7253 | |
|
|
| 0.9523 | 0.0225 | 100 | 0.8943 | |
|
|
| 0.9478 | 0.0449 | 200 | 0.8860 | |
|
|
| 0.9653 | 0.0674 | 300 | 0.8736 | |
|
|
| 0.7676 | 0.0899 | 400 | 0.8678 | |
|
|
| 0.9193 | 0.1123 | 500 | 0.8550 | |
|
|
| 0.9976 | 0.1348 | 600 | 0.8524 | |
|
|
| 1.0777 | 0.1573 | 700 | 0.8414 | |
|
|
| 0.892 | 0.1797 | 800 | 0.8353 | |
|
|
| 1.0606 | 0.2022 | 900 | 0.8260 | |
|
|
| 0.9507 | 0.2247 | 1000 | 0.8176 | |
|
|
| 0.8807 | 0.2471 | 1100 | 0.8107 | |
|
|
| 1.0414 | 0.2696 | 1200 | 0.8034 | |
|
|
| 0.9991 | 0.2921 | 1300 | 0.7983 | |
|
|
| 0.8961 | 0.3146 | 1400 | 0.7936 | |
|
|
| 0.9268 | 0.3370 | 1500 | 0.7911 | |
|
|
| 0.7766 | 0.3595 | 1600 | 0.7893 | |
|
|
| 0.9304 | 0.3820 | 1700 | 0.7884 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.13.2 |
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.5.0+cu124 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.1 |
