170 lines
6.2 KiB
Markdown
170 lines
6.2 KiB
Markdown
---
|
|
license: apache-2.0
|
|
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: outputs/mistral
|
|
results: []
|
|
---
|
|
This abalation underperforms the tried and true [augmxnt/shisa-gamma-7b-v1](https://huggingface.co/augmxnt/shisa-gamma-7b-v1) and if you're looking for a Mistral 7B based model, you should probably go with that.
|
|
|
|
|
|
## Performance
|
|
Measured using a [fork](https://github.com/shisa-ai/shaberi) of [Lightblue's Shaberi benchmark framework](https://github.com/lightblue-tech/japanese_llm_eval):
|
|
|
|
| Model | Average | ELYZA-tasks-100 | MT-Bench | Rakuda | Tengu-Bench |
|
|
|----------------------------------------|---------|-----------------|----------|--------|-------------|
|
|
| gpt-4-turbo-2024-04-09 | 8.75 | 8.78 | 8.74 | 9.18 | 8.31 |
|
|
| gpt-4o-2024-05-13 | 8.72 | 8.88 | 8.69 | 9.15 | 8.16 |
|
|
| gemini-1.5-pro | 8.58 | 8.58 | 8.93 | 9.20 | 7.61 |
|
|
| claude-3-opus-20240229 | 8.55 | 8.64 | 8.58 | 8.75 | 8.23 |
|
|
| CohereForAI/c4ai-command-r-plus | 7.69 | 7.50 | 7.43 | 9.05 | 6.79 |
|
|
| **shisa-ai/shisa-v1-llama3-70b** | **7.30**| **7.34** | **7.67** | **8.15** | **6.04** |
|
|
| gpt-3.5-turbo-0125 | 7.17 | 7.24 | 6.98 | 7.64 | 6.82 |
|
|
| **shisa-ai/shisa-v1-llama3-70b.2e5** | **7.17**| **7.16** | **7.45** | **7.98** | **6.09** |
|
|
| karakuri-ai/karakuri-lm-8x7b-chat-v0.1 | 7.00 | 7.18 | 6.30 | 7.98 | 6.55 |
|
|
| karakuri-ai/karakuri-lm-70b-chat-v0.1 | 6.84 | 6.86 | 6.43 | 7.85 | 6.23 |
|
|
| lightblue/ao-karasu-72B | 6.81 | 7.19 | 6.54 | 7.25 | 6.27 |
|
|
| **shisa-ai/shisa-v1-llama3-8b** | **6.59**| **6.67** | **6.95** | **7.05**| **5.68** |
|
|
| microsoft/Phi-3-medium-128k-instruct | 6.48 | 7.10 | 5.92 | 6.84 | 6.04 |
|
|
| **shisa-ai/shisa-swallowmx-13a47b-v1** | **6.17**| **6.48** | **6.07** | **7.11**| **5.03** |
|
|
| lightblue/suzume-llama-3-8B-japanese | 5.96 | 6.68 | 4.96 | 6.68 | 5.53 |
|
|
| augmxnt/shisa-gamma-7b-v1 | 5.82 | 5.96 | 5.02 | 6.85 | 5.47 |
|
|
| **shisa-ai/shisa-v1-phi3-14b** | **5.77**| **6.28** | **5.26** | **6.55**| **5.01** |
|
|
| **shisa-ai/shisa-v1-gemma-8b** | **5.64**| **6.50** | **5.42** | **5.10**| **5.55** |
|
|
| Rakuten/RakutenAI-7B-chat | 5.58 | 5.92 | 4.60 | 6.58 | 5.24 |
|
|
| lightblue/qarasu-14B-chat-plus-unleashed | 5.20 | 5.58 | 4.74 | 5.46 | 5.01 |
|
|
| **shisa-ai/shisa-v1-mistral0.3-7b** | **5.11**| **5.64** | **6.10** | **3.83**|**4.86** |
|
|
| cyberagent/calm2-7b-chat | 4.76 | 4.90 | 3.58 | 5.75 | 4.81 |
|
|
| mistralai/Mistral-7B-Instruct-v0.2 | 4.69 | 5.78 | 4.65 | 3.80 | 4.53 |
|
|
| **shisa-ai/shisa-v1-yi1.5-9b** | **4.63**| **5.98** | **4.28** | **3.26**|**5.00** |
|
|
| augmxnt/shisa-7b-v1 | 4.50 | 4.63 | 3.95 | 4.89 | 4.53 |
|
|
|
|
<!-- 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-v0.3
|
|
model_type: MistralForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
chat_template: inst
|
|
datasets:
|
|
- path: augmxnt/ultra-orca-boros-en-ja-v1
|
|
type: sharegpt
|
|
dataset_prepared_path:
|
|
val_set_size: 0.05
|
|
output_dir: ./outputs/mistral
|
|
|
|
sequence_len: 8192
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
eval_sample_packing: false
|
|
|
|
use_wandb: true
|
|
wandb_project: shisa-v2
|
|
wandb_entity: augmxnt
|
|
wandb_name: shisa-v1-mistral0.3-7b
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 3
|
|
optimizer: paged_adamw_8bit
|
|
lr_scheduler: linear
|
|
learning_rate: 8e-6
|
|
|
|
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: 100
|
|
evals_per_epoch: 2
|
|
eval_table_size:
|
|
eval_max_new_tokens: 128
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed: zero3_bf16.json
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
|
|
```
|
|
|
|
</details><br>
|
|
|
|
# outputs/mistral
|
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.3791
|
|
|
|
## 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: 8e-06
|
|
- train_batch_size: 2
|
|
- eval_batch_size: 2
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- num_devices: 8
|
|
- gradient_accumulation_steps: 4
|
|
- total_train_batch_size: 64
|
|
- total_eval_batch_size: 16
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: linear
|
|
- lr_scheduler_warmup_steps: 100
|
|
- num_epochs: 3
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
| 0.8564 | 0.0045 | 1 | 0.7107 |
|
|
| 0.6131 | 0.5023 | 111 | 0.4259 |
|
|
| 0.6077 | 1.0045 | 222 | 0.3715 |
|
|
| 0.4173 | 1.4932 | 333 | 0.3617 |
|
|
| 0.3812 | 1.9955 | 444 | 0.3468 |
|
|
| 0.2408 | 2.4842 | 555 | 0.3791 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.40.2
|
|
- Pytorch 2.3.0+cu121
|
|
- Datasets 2.19.1
|
|
- Tokenizers 0.19.1
|