---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: ai21labs/Jamba-v0.1
model-index:
- name: out
results: []
datasets:
- chargoddard/Open-Platypus-Chat
---
# Jambatypus
[
](https://github.com/OpenAccess-AI-Collective/axolotl)
See axolotl config
axolotl version: `0.4.0`
```yaml
base_model: ai21labs/Jamba-v0.1
trust_remote_code: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: chargoddard/Open-Platypus-Chat
type: sharegpt
chat_template: chatml
dataset_prepared_path:
val_set_size: 0.01
output_dir: ./out
hub_strategy: every_save
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
use_wandb: true
wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_name: Jambatypus-v0.1
wandb_log_model:
adapter: qlora
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
low_cpu_mem_usage: true
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 4
save_total_limit: 2
debug:
deepspeed:
weight_decay: 0.0
special_tokens:
```
This model is a fine-tuned version of [ai21labs/Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1) on the [chargoddard/Open-Platypus-Chat](https://huggingface.co/datasets/chargoddard/Open-Platypus-Chat) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9573
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5915 | 0.0 | 1 | 1.0279 |
| 0.4249 | 0.25 | 84 | 0.9711 |
| 0.3911 | 0.5 | 168 | 0.9590 |
| 0.4655 | 0.75 | 252 | 0.9628 |
| 0.4569 | 1.0 | 336 | 0.9573 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.0