|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- axolotl |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
model-index: |
|
- name: nohto-v0-10e |
|
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: `0.4.0` |
|
```yaml |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: LlamaTokenizer |
|
is_mistral_derived_model: true |
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
chat_template: inst |
|
|
|
datasets: |
|
- path: ./data/nohto/training.jsonl |
|
type: sharegpt |
|
|
|
dataset_prepared_path: last_run_prepared |
|
val_set_size: 0.1 |
|
output_dir: ../nohto-v0-10e |
|
|
|
adapter: lora |
|
lora_model_dir: |
|
|
|
sequence_len: 4096 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
lora_r: 16 |
|
lora_alpha: 32 |
|
lora_dropout: 0.1 |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
|
|
eval_sample_packing: false |
|
|
|
hub_model_id: dyang415/nohto-v0-10e |
|
|
|
wandb_project: nohto |
|
wandb_name: nohto-v0 |
|
wandb_log_model: end |
|
|
|
gradient_accumulation_steps: 2 |
|
micro_batch_size: 1 |
|
num_epochs: 10 |
|
optimizer: paged_adamw_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.0002 |
|
|
|
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_steps: 10 |
|
eval_steps: 0.2 |
|
save_steps: 0.1 |
|
eval_max_new_tokens: 128 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# nohto-v0-10e |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8229 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 4 |
|
- total_eval_batch_size: 2 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.7166 | 0.18 | 1 | 3.7658 | |
|
| 0.5158 | 1.64 | 10 | 0.5278 | |
|
| 0.2492 | 3.09 | 20 | 0.5739 | |
|
| 0.0338 | 4.73 | 30 | 0.7476 | |
|
| 0.0083 | 6.36 | 40 | 0.8089 | |
|
| 0.0078 | 8.0 | 50 | 0.8229 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.0 |
|
- Transformers 4.37.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.0 |
