|
|
--- |
|
|
library_name: peft |
|
|
license: mit |
|
|
base_model: fxmarty/tiny-random-GemmaForCausalLM |
|
|
tags: |
|
|
- axolotl |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: 8a76346a-e5e1-4372-8a33-4ae45d89359b |
|
|
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 |
|
|
auto_resume_from_checkpoints: false |
|
|
base_model: fxmarty/tiny-random-GemmaForCausalLM |
|
|
bf16: false |
|
|
chat_template: llama3 |
|
|
dataset_prepared_path: null |
|
|
datasets: |
|
|
- data_files: |
|
|
- 95621c23f229fe74_train_data.json |
|
|
ds_type: json |
|
|
format: custom |
|
|
path: /workspace/input_data/95621c23f229fe74_train_data.json |
|
|
type: |
|
|
field_input: tools |
|
|
field_instruction: query |
|
|
field_output: answers |
|
|
format: '{instruction} {input}' |
|
|
no_input_format: '{instruction}' |
|
|
system_format: '{system}' |
|
|
system_prompt: '' |
|
|
debug: null |
|
|
deepspeed: null |
|
|
early_stopping_patience: 3 |
|
|
eval_max_new_tokens: 128 |
|
|
eval_steps: 1000 |
|
|
eval_table_size: null |
|
|
flash_attention: true |
|
|
fp16: true |
|
|
fsdp: null |
|
|
fsdp_config: null |
|
|
gradient_accumulation_steps: 4 |
|
|
gradient_checkpointing: false |
|
|
group_by_length: false |
|
|
hub_model_id: error577/8a76346a-e5e1-4372-8a33-4ae45d89359b |
|
|
hub_repo: null |
|
|
hub_strategy: checkpoint |
|
|
hub_token: null |
|
|
learning_rate: 0.0002 |
|
|
load_in_4bit: false |
|
|
load_in_8bit: false |
|
|
local_rank: null |
|
|
logging_steps: 1 |
|
|
lora_alpha: 128 |
|
|
lora_dropout: 0.05 |
|
|
lora_fan_in_fan_out: null |
|
|
lora_model_dir: null |
|
|
lora_r: 64 |
|
|
lora_target_linear: true |
|
|
lr_scheduler: cosine |
|
|
max_grad_norm: 1.0 |
|
|
max_steps: null |
|
|
micro_batch_size: 2 |
|
|
mlflow_experiment_name: /tmp/95621c23f229fe74_train_data.json |
|
|
model_type: AutoModelForCausalLM |
|
|
num_epochs: 10 |
|
|
optimizer: adamw_torch |
|
|
output_dir: miner_id_24 |
|
|
pad_to_sequence_len: true |
|
|
resume_from_checkpoint: null |
|
|
s2_attention: null |
|
|
sample_packing: false |
|
|
save_steps: 1000 |
|
|
sequence_len: 512 |
|
|
strict: false |
|
|
tf32: false |
|
|
tokenizer_type: AutoTokenizer |
|
|
train_on_inputs: false |
|
|
trust_remote_code: true |
|
|
val_set_size: 0.005 |
|
|
wandb_entity: null |
|
|
wandb_mode: online |
|
|
wandb_name: e75973b3-c17e-44e4-b527-21c602afd6c4 |
|
|
wandb_project: Gradients-On-Demand |
|
|
wandb_run: your_name |
|
|
wandb_runid: e75973b3-c17e-44e4-b527-21c602afd6c4 |
|
|
warmup_steps: 300 |
|
|
weight_decay: 0.0 |
|
|
xformers_attention: null |
|
|
|
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# 8a76346a-e5e1-4372-8a33-4ae45d89359b |
|
|
|
|
|
This model is a fine-tuned version of [fxmarty/tiny-random-GemmaForCausalLM](https://huggingface.co/fxmarty/tiny-random-GemmaForCausalLM) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 12.1613 |
|
|
|
|
|
## 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: Use OptimizerNames.ADAMW_TORCH 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: 300 |
|
|
- num_epochs: 10 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:-----:|:---------------:| |
|
|
| 12.4513 | 0.0002 | 1 | 12.4418 | |
|
|
| 12.2591 | 0.1637 | 1000 | 12.2520 | |
|
|
| 12.2403 | 0.3275 | 2000 | 12.2224 | |
|
|
| 12.2069 | 0.4912 | 3000 | 12.2032 | |
|
|
| 12.1813 | 0.6550 | 4000 | 12.1945 | |
|
|
| 12.2163 | 0.8187 | 5000 | 12.1882 | |
|
|
| 12.1597 | 0.9825 | 6000 | 12.1822 | |
|
|
| 12.2022 | 1.1462 | 7000 | 12.1761 | |
|
|
| 12.2427 | 1.3100 | 8000 | 12.1720 | |
|
|
| 12.1622 | 1.4737 | 9000 | 12.1691 | |
|
|
| 12.2151 | 1.6375 | 10000 | 12.1676 | |
|
|
| 12.18 | 1.8012 | 11000 | 12.1669 | |
|
|
| 12.1537 | 1.9650 | 12000 | 12.1656 | |
|
|
| 12.1634 | 2.1287 | 13000 | 12.1650 | |
|
|
| 12.2148 | 2.2925 | 14000 | 12.1649 | |
|
|
| 12.1868 | 2.4562 | 15000 | 12.1646 | |
|
|
| 12.1903 | 2.6199 | 16000 | 12.1642 | |
|
|
| 12.1781 | 2.7837 | 17000 | 12.1643 | |
|
|
| 12.1894 | 2.9474 | 18000 | 12.1638 | |
|
|
| 12.2065 | 3.1112 | 19000 | 12.1633 | |
|
|
| 12.1887 | 3.2749 | 20000 | 12.1635 | |
|
|
| 12.1549 | 3.4387 | 21000 | 12.1626 | |
|
|
| 12.1719 | 3.6024 | 22000 | 12.1624 | |
|
|
| 12.2151 | 3.7662 | 23000 | 12.1626 | |
|
|
| 12.157 | 3.9299 | 24000 | 12.1629 | |
|
|
| 12.1682 | 4.0937 | 25000 | 12.1619 | |
|
|
| 12.1968 | 4.2574 | 26000 | 12.1619 | |
|
|
| 12.1651 | 4.4212 | 27000 | 12.1617 | |
|
|
| 12.168 | 4.5849 | 28000 | 12.1612 | |
|
|
| 12.1713 | 4.7486 | 29000 | 12.1617 | |
|
|
| 12.1767 | 4.9124 | 30000 | 12.1614 | |
|
|
| 12.2027 | 5.0761 | 31000 | 12.1613 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.13.2 |
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.5.0+cu124 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.1 |
