---
license: gemma
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: google/gemma-2b
model-index:
- name: gemma2b-hotpotqa_uncertain-v1
results: []
---
[
](https://github.com/OpenAccess-AI-Collective/axolotl)
See axolotl config
axolotl version: `0.4.0`
```yaml
base_model: google/gemma-2b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: Harsh1729/hotpotqa_uncertain
type: alpaca
split: train
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./hotpotqa_uncertain-qlora-out
hub_model_id: Harsh1729/gemma2b-hotpotqa_uncertain-v1
adapter: qlora
lora_model_dir:
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00005
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_ratio: 0.02
evals_per_epoch: 1
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: # deepspeed_configs/zero2.json # multi-gpu only
weight_decay: 0.1
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 0.00000001
max_grad_norm: 1.0
fsdp:
fsdp_config:
special_tokens:
bos_token: ""
eos_token: ""
unk_token: ""
```
# gemma2b-hotpotqa_uncertain-v1
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3151
## 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 59
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.0391 | 1.0 | 3675 | 0.3151 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.0