|
--- |
|
base_model: unsloth/Mistral-Nemo-Instruct-2407 |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- mistral |
|
- trl |
|
- rp |
|
- gguf |
|
- experimental |
|
- long-context |
|
--- |
|
|
|
# Uploaded model |
|
|
|
- **Developed by:** UsernameJustAnother |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** unsloth/Mistral-Nemo-Instruct-2407 |
|
|
|
Standard disclaimer: This is me teaching myself the basics of fine-tuning, with notes extensively borrowed from https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9 |
|
|
|
New for v6: |
|
- Slightly different source mix. Down to 8,000 records of mostly-human convos and stories, curated by me, trained in ChatML. |
|
- The stories have been edited to remove author's notes, and the RP chats tweaked to remove many ministrations. |
|
- Different learning rate and back to Celeste's scaling factor setup (but Celeste trained on -base, this is -instruct). |
|
- Now with added eval! I worked out how to get eval stats (and wandb) set up, so now I can see my failures in graphical form. |
|
|
|
I pulled v7 because I honestly don't think it's as good as v6, and don't want folks to get the wrong idea that it's better just because the version number is higher. |
|
|
|
And of course yay Unsloth for letting this all train on a single A100 with variable (wildly variable) context length. |
|
|
|
Here's what the train/eval loss looked like (eval is orange, train is blue). I think that's not terrible, but :shrug:. |
|
|
|
 |
|
|
|
It was trained with the following settings: |
|
|
|
``` |
|
|
|
model = FastLanguageModel.get_peft_model( |
|
model, |
|
r = 256, |
|
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", |
|
"gate_proj", "up_proj", "down_proj",], |
|
lora_alpha = 128, # 128 / sqrt(256) gives a scaling factor of 8 |
|
lora_dropout = 0.1, # Supports any, but = 0 is optimized |
|
bias = "none", # Supports any, but = "none" is optimized |
|
# [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes! |
|
use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context |
|
random_state = 3407, |
|
use_rslora = True, # setting the adapter scaling factor to lora_alpha/math.sqrt(r) instead of lora_alpha/r |
|
loftq_config = None, # And LoftQ |
|
) |
|
|
|
lr_scheduler_kwargs = { |
|
'min_lr': 0.0000024 # Adjust this value as needed |
|
} |
|
|
|
per_device_train_batch_size = 2, |
|
per_device_eval_batch_size = 2, # defaults to 8! |
|
gradient_accumulation_steps = 4, |
|
eval_accumulation_steps = 4, |
|
prediction_loss_only = True, # When performing evaluation and generating predictions, only returns the loss. |
|
warmup_steps = 50, |
|
num_train_epochs = 2, # For longer training runs! 12 hrs/epoch? |
|
learning_rate = 1e-5, # 8e-5 used by Celeste, 0.0001 is from the paper, halving it. tried 5e-5, now 1e-5. |
|
fp16 = not is_bfloat16_supported(), |
|
bf16 = is_bfloat16_supported(), |
|
fp16_full_eval = True, # stops eval from trying to use fp32 |
|
eval_strategy = "steps", # 'no', 'steps', 'epoch'. Don't use this without an eval dataset etc |
|
eval_steps = 100, # is eval_strat is set to 'steps', do every N steps. |
|
logging_steps = 5, # so eval and logging happen on the same schedule |
|
optim = "adamw_8bit", # |
|
weight_decay = 0, # up from 0 |
|
lr_scheduler_type = "cosine_with_min_lr", # linear, cosine, cosine_with_min_lr, default linear |
|
lr_scheduler_kwargs = lr_scheduler_kwargs, # needed for cosine_with_min_lr |
|
seed = 3407, |
|
|
|
``` |
|
|
|
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
