|
|
--- |
|
|
library_name: peft |
|
|
license: apache-2.0 |
|
|
base_model: unsloth/gemma-2b-it |
|
|
tags: |
|
|
- axolotl |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: 9d65626e-53aa-48e7-9c43-1cd15808de5a |
|
|
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/gemma-2b-it |
|
|
bf16: true |
|
|
chat_template: llama3 |
|
|
dataset_prepared_path: null |
|
|
datasets: |
|
|
- data_files: |
|
|
- 52b51d4a8d8dae82_train_data.json |
|
|
ds_type: json |
|
|
format: custom |
|
|
path: /workspace/input_data/52b51d4a8d8dae82_train_data.json |
|
|
type: |
|
|
field_instruction: instruction |
|
|
field_output: output |
|
|
format: '{instruction}' |
|
|
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: 400 |
|
|
eval_table_size: null |
|
|
flash_attention: false |
|
|
gradient_accumulation_steps: 4 |
|
|
gradient_checkpointing: true |
|
|
group_by_length: false |
|
|
hub_model_id: Alphatao/9d65626e-53aa-48e7-9c43-1cd15808de5a |
|
|
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: 32 |
|
|
lora_dropout: 0.05 |
|
|
lora_fan_in_fan_out: null |
|
|
lora_model_dir: null |
|
|
lora_r: 16 |
|
|
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: 11867 |
|
|
micro_batch_size: 2 |
|
|
mlflow_experiment_name: /tmp/52b51d4a8d8dae82_train_data.json |
|
|
model_type: AutoModelForCausalLM |
|
|
num_epochs: 10 |
|
|
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: 400 |
|
|
sequence_len: 1024 |
|
|
strict: false |
|
|
tf32: true |
|
|
tokenizer_type: AutoTokenizer |
|
|
train_on_inputs: false |
|
|
trust_remote_code: true |
|
|
val_set_size: 0.05 |
|
|
wandb_entity: null |
|
|
wandb_mode: online |
|
|
wandb_name: ff680a59-ee3c-407a-8506-d9507d1c8bd0 |
|
|
wandb_project: Gradients-On-Demand |
|
|
wandb_run: your_name |
|
|
wandb_runid: ff680a59-ee3c-407a-8506-d9507d1c8bd0 |
|
|
warmup_steps: 10 |
|
|
weight_decay: 0.0 |
|
|
xformers_attention: null |
|
|
|
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# 9d65626e-53aa-48e7-9c43-1cd15808de5a |
|
|
|
|
|
This model is a fine-tuned version of [unsloth/gemma-2b-it](https://huggingface.co/unsloth/gemma-2b-it) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.7440 |
|
|
|
|
|
## 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_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: 11867 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:-----:|:---------------:| |
|
|
| 1.6257 | 0.0001 | 1 | 1.3826 | |
|
|
| 0.823 | 0.0341 | 400 | 0.8594 | |
|
|
| 0.8278 | 0.0682 | 800 | 0.8445 | |
|
|
| 0.9407 | 0.1023 | 1200 | 0.8366 | |
|
|
| 0.8239 | 0.1364 | 1600 | 0.8304 | |
|
|
| 1.0677 | 0.1705 | 2000 | 0.8265 | |
|
|
| 0.8125 | 0.2046 | 2400 | 0.8186 | |
|
|
| 0.9515 | 0.2387 | 2800 | 0.8148 | |
|
|
| 0.7069 | 0.2727 | 3200 | 0.8099 | |
|
|
| 0.7106 | 0.3068 | 3600 | 0.8049 | |
|
|
| 0.9589 | 0.3409 | 4000 | 0.8002 | |
|
|
| 0.9544 | 0.3750 | 4400 | 0.7965 | |
|
|
| 0.833 | 0.4091 | 4800 | 0.7919 | |
|
|
| 0.8829 | 0.4432 | 5200 | 0.7867 | |
|
|
| 1.0338 | 0.4773 | 5600 | 0.7828 | |
|
|
| 0.7217 | 0.5114 | 6000 | 0.7784 | |
|
|
| 0.7006 | 0.5455 | 6400 | 0.7739 | |
|
|
| 0.8399 | 0.5796 | 6800 | 0.7699 | |
|
|
| 0.5234 | 0.6137 | 7200 | 0.7656 | |
|
|
| 0.6645 | 0.6478 | 7600 | 0.7614 | |
|
|
| 0.8158 | 0.6819 | 8000 | 0.7582 | |
|
|
| 0.5981 | 0.7160 | 8400 | 0.7548 | |
|
|
| 0.6689 | 0.7501 | 8800 | 0.7522 | |
|
|
| 0.854 | 0.7841 | 9200 | 0.7498 | |
|
|
| 0.5398 | 0.8182 | 9600 | 0.7478 | |
|
|
| 0.7944 | 0.8523 | 10000 | 0.7464 | |
|
|
| 1.061 | 0.8864 | 10400 | 0.7452 | |
|
|
| 0.7511 | 0.9205 | 10800 | 0.7445 | |
|
|
| 0.6627 | 0.9546 | 11200 | 0.7441 | |
|
|
| 0.8566 | 0.9887 | 11600 | 0.7440 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.13.2 |
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.5.0+cu124 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.1 |
