|
--- |
|
library_name: peft |
|
tags: |
|
- axolotl |
|
- generated_from_trainer |
|
base_model: mhenrichsen/gemma-7b |
|
model-index: |
|
- name: test-task-2025-01-06 |
|
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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.4.1` |
|
```yaml |
|
adapter: qlora |
|
base_model: mhenrichsen/gemma-7b |
|
bf16: auto |
|
datasets: |
|
- path: data.jsonl |
|
type: alpaca |
|
debug: null |
|
deepspeed: null |
|
early_stopping_patience: null |
|
eval_max_new_tokens: 128 |
|
eval_sample_packing: false |
|
eval_table_size: null |
|
evals_per_epoch: 4 |
|
flash_attention: true |
|
fp16: null |
|
fsdp: null |
|
fsdp_config: null |
|
gradient_accumulation_steps: 3 |
|
gradient_checkpointing: true |
|
group_by_length: false |
|
hub_model_id: FatCat87/test-task-2025-01-06 |
|
learning_rate: 0.0002 |
|
load_in_4bit: true |
|
load_in_8bit: false |
|
local_rank: null |
|
logging_steps: 1 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_r: 32 |
|
lora_target_linear: true |
|
lr_scheduler: cosine |
|
micro_batch_size: 2 |
|
model_type: AutoModelForCausalLM |
|
num_epochs: 4 |
|
optimizer: adamw_bnb_8bit |
|
output_dir: ./outputs/out |
|
pad_to_sequence_len: true |
|
resume_from_checkpoint: null |
|
sample_packing: true |
|
saves_per_epoch: 1 |
|
sequence_len: 4096 |
|
special_tokens: null |
|
strict: false |
|
tf32: false |
|
tokenizer_type: AutoTokenizer |
|
train_on_inputs: false |
|
val_set_size: 0.1 |
|
wandb_entity: fatcat87-taopanda |
|
wandb_log_model: null |
|
wandb_mode: online |
|
wandb_name: test-task-2025-01-06 |
|
wandb_project: subnet56 |
|
wandb_runid: test-task-2025-01-06 |
|
wandb_watch: null |
|
warmup_ratio: 0.1 |
|
weight_decay: 0.0 |
|
xformers_attention: null |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/p0rc3cvq) |
|
# test-task-2025-01-06 |
|
|
|
This model is a fine-tuned version of [mhenrichsen/gemma-7b](https://huggingface.co/mhenrichsen/gemma-7b) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0913 |
|
|
|
## 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: 3 |
|
- total_train_batch_size: 6 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 5 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.046 | 0.075 | 1 | 1.1912 | |
|
| 1.1095 | 0.3 | 4 | 1.1067 | |
|
| 1.0619 | 0.6 | 8 | 1.0441 | |
|
| 1.0547 | 0.9 | 12 | 1.0446 | |
|
| 0.931 | 1.15 | 16 | 1.0528 | |
|
| 0.8836 | 1.45 | 20 | 1.0399 | |
|
| 0.8958 | 1.75 | 24 | 1.0419 | |
|
| 0.9922 | 2.05 | 28 | 1.0361 | |
|
| 0.7736 | 2.3 | 32 | 1.0851 | |
|
| 0.7437 | 2.6 | 36 | 1.0840 | |
|
| 0.7552 | 2.9 | 40 | 1.0769 | |
|
| 0.6623 | 3.15 | 44 | 1.0870 | |
|
| 0.7173 | 3.45 | 48 | 1.0946 | |
|
| 0.7122 | 3.75 | 52 | 1.0913 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
