---
library_name: peft
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
- generated_from_trainer
datasets:
- redcathode/thingiverse-openscad
model-index:
- name: vast-finetune-r1
  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.6.0`
```yaml
unsloth_lora_mlp: true
unsloth_lora_qkv: true
unsloth_lora_o: true
# This is the huggingface model that contains *.pt, *.safetensors, or *.bin files
# This can also be a relative path to a model on disk
base_model: meta-llama/Llama-3.1-8B-Instruct

# Corresponding tokenizer for the model AutoTokenizer is a good choice
tokenizer_type: AutoTokenizer

# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc. 0 for no eval.
val_set_size: 0.10


# Whether you are training a 4-bit GPTQ quantized model
# gptq: false

# This will attempt to quantize the model down to 8 bits and use adam 8 bit optimizer
load_in_8bit: false
# Use bitsandbytes 4 bit
load_in_4bit: true

# Limit the memory for all available GPUs to this amount (if an integer, expressed in gigabytes); default: unset
gpu_memory_limit: 24
# Do the LoRA/PEFT loading on CPU -- this is required if the base model is so large it takes up most or all of the available GPU VRAM, e.g. during a model and LoRA merge
lora_on_cpu: true

# A list of one or more datasets to finetune the model with
datasets:
  - path: ./ts-8k.jsonl
    type: chat_template
    chat_template: tokenizer_default
    field_messages: messages
    message_field_role: role
    message_field_content: content
    roles_to_train: [ "assistant" ]
    


# If false, the datasets will not be shuffled and will keep their original order in `datasets`.
# The same applies to the `test_datasets` option and the `pretraining_dataset` option. Default is true.
shuffle_merged_datasets: true


# The name of the chat template to use for training, following values are supported:
# - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default value.
# - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py
# - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to. E.g. tokenizer_default_fallback_chatml. This is useful when the chat template is not available in the tokenizer.
# - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field.
# The selected chat template will be saved to the tokenizer_config.json for easier inferencing
# Note: It is recommended to set train_on_inputs to true when using a chat template that is different from the model's default chat template.
chat_template: tokenizer_default

# Axolotl attempts to save the dataset as an arrow after packing the data together so
# subsequent training attempts load faster, relative path
dataset_prepared_path: data/last_run_prepared
# push checkpoints to hub
#hub_model_id: # private repo path to push finetuned model
# how to push checkpoints to hub
# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy
#hub_strategy:
# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
# Required to be true when used in combination with `push_dataset_to_hub`
#hf_use_auth_token: # boolean

# Num shards for whole dataset
#dataset_shard_num:
# Index of shard to use for whole dataset
#dataset_shard_idx:

# The maximum length of an input to train with, this should typically be less than 2048
# as most models have a token/context limit of 2048
sequence_len: 1024
# Pad inputs so each step uses constant sized buffers
# This will reduce memory fragmentation and may prevent OOMs, by re-using memory more efficiently
pad_to_sequence_len: true
# Use efficient multi-packing with block diagonal attention and per sequence position_ids. Recommend set to 'true'
sample_packing: true
# Set to 'false' if getting errors during eval with sample_packing on.
eval_sample_packing: false
# You can set these packing optimizations AFTER starting a training at least once.
# The trainer will provide recommended values for these values.
# sample_packing_eff_est:
# total_num_tokens:
# Increasing the following values helps with packing, but usually only slightly (<%1.)
# The number of samples packed at a time.
# sample_packing_group_size: 100000
# The number of samples which can be packed into one sequence. Increase if using a large sequence_len with many short samples.
# sample_packing_bin_size: 200
# whether to concatenate samples during pretraining
# pretraining_sample_concatenation:

# Use batch flattening for speedups when not using sample_packing
# batch_flattening:

# Passed through to transformers when loading the model when launched without accelerate
# Use `sequential` when training w/ model parallelism to limit memory
# device_map:
# Defines the max memory usage per gpu on the system. Passed through to transformers when loading the model.
# max_memory:

# If you want to use 'lora' or 'qlora' or leave blank to train all parameters in original model
adapter: qlora
# If you already have a lora model trained that you want to load, put that here.
# This means after training, if you want to test the model, you should set this to the value of `output_dir`.
# Note that if you merge an adapter to the base model, a new subdirectory `merged` will be created under the `output_dir`.
# lora_model_dir:

# LoRA hyperparameters
# For more details about the following options, see:
# https://www.anyscale.com/blog/fine-tuning-llms-lora-or-full-parameter-an-in-depth-analysis-with-llama-2
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj
lora_target_linear: # If true, will target all linear modules
peft_layers_to_transform: # The layer indices to transform, otherwise, apply to all layers

# If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens.
# For LLaMA and Mistral, you need to save `embed_tokens` and `lm_head`. It may vary for other models.
# `embed_tokens` converts tokens to embeddings, and `lm_head` converts embeddings to token probabilities.
# https://github.com/huggingface/peft/issues/334#issuecomment-1561727994
#lora_modules_to_save:
#  - embed_tokens
#  - lm_head

#lora_fan_in_fan_out: false

# LoRA+ hyperparameters
# For more details about the following options, see:
# https://arxiv.org/abs/2402.12354  and `src/axolotl/core/train_builder.py`
#loraplus_lr_ratio: # loraplus learning rate ratio lr_B / lr_A. Recommended value is 2^4.
#loraplus_lr_embedding: #  loraplus learning rate for lora embedding layers. Default value is 1e-6.

#peft:
  # Configuration options for loftq initialization for LoRA
  # https://huggingface.co/docs/peft/developer_guides/quantization#loftq-initialization
#  loftq_config:
#    loftq_bits:  4 # typically 4 bits

# ReLoRA configuration
# Must use either 'lora' or 'qlora' adapter, and does not support fsdp or deepspeed
#relora_steps: # Number of steps per ReLoRA restart
#relora_warmup_steps: # Number of per-restart warmup steps
#relora_anneal_steps: # Number of anneal steps for each relora cycle
#relora_prune_ratio: # threshold for optimizer magnitude when pruning
#relora_cpu_offload: # True to perform lora weight merges on cpu during restarts, for modest gpu memory savings

# wandb configuration if you're using it
# Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`.
# wandb_mode: # "offline" to save run metadata locally and not sync to the server, "disabled" to turn off wandb
wandb_project: # Your wandb project name
wandb_entity: # A wandb Team name if using a Team
wandb_watch:
wandb_name: vast-finetune-r1 # Set the name of your wandb run
wandb_run_id: # Set the ID of your wandb run
wandb_log_model: checkpoint # "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only at the end of training

wandb_entity: blueanode
wandb_project: fabricator

# mlflow configuration if you're using it
#mlflow_tracking_uri: # URI to mlflow
#mlflow_experiment_name: # Your experiment name
#mlflow_run_name: # Your run name
#hf_mlflow_log_artifacts:  # set to true to copy each saved checkpoint on each save to mlflow artifact registry



# Where to save the full-finetuned model to
output_dir: ./vast-finetune-r1

# Whether to use torch.compile and which backend to use
# setting to `auto` will enable torch compile when torch>=2.5.1
torch_compile:  # Optional[Union[Literal["auto"], bool]]
torch_compile_backend:  # Optional[str]

# Training hyperparameters

# If greater than 1, backpropagation will be skipped and the gradients will be accumulated for the given number of steps.
gradient_accumulation_steps: 1
# The number of samples to include in each batch. This is the number of samples sent to each GPU.
# Batch size per gpu = micro_batch_size * gradient_accumulation_steps
micro_batch_size: 2
eval_batch_size:
num_epochs: 8
warmup_steps: 100  # cannot use with warmup_ratio
learning_rate: 0.00003
lr_quadratic_warmup:
logging_steps:
eval_steps: # Leave empty to eval at each epoch, integers for every N steps. decimal for fraction of total steps
evals_per_epoch: 4 # number of times per epoch to run evals, mutually exclusive with eval_steps
save_strategy: # Set to `"no"` to skip checkpoint saves
save_steps: # Leave empty to save at each epoch
# saves_per_epoch: # number of times per epoch to save a checkpoint, mutually exclusive with save_steps
save_total_limit: 2 # Checkpoints saved at a time
# Maximum number of iterations to train for. It precedes num_epochs which means that
# if both are set, num_epochs will not be guaranteed.
# e.g., when 1 epoch is 1000 steps => `num_epochs: 2` and `max_steps: 100` will train for 100 steps
# max_steps:

eval_table_size: 8 # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0
eval_max_new_tokens: 256 # Total number of tokens generated for predictions sent to wandb. Default is 128
#eval_causal_lm_metrics: # HF evaluate metrics used during evaluation. Default is ["sacrebleu", "comet", "ter", "chrf", "perplexity"]

profiler_steps: # enable the pytorch profiler to capture the first N steps of training to the output_dir.
                # see https://pytorch.org/blog/understanding-gpu-memory-1/ for more information
                # snapshots can be visualized @ https://pytorch.org/memory_viz

#loss_watchdog_threshold: # High loss value, indicating the learning has broken down (a good estimate is ~2 times the loss at the start of training)
#loss_watchdog_patience: # Number of high-loss steps in a row before the trainer aborts (default: 3)

# Save model as safetensors (require safetensors package)
# save_safetensors:

# Whether to mask out or include the human's prompt from the training labels
train_on_inputs: false
#train_on_inputs: false
#group_by_length: false
bf16: auto
fp16:
tf32: false
# Group similarly sized data to minimize padding.
# May be slower to start, as it must download and sort the entire dataset.
# Note that training loss may have an oscillating pattern with this enabled.
group_by_length: false

# Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing
gradient_checkpointing: false
# additional kwargs to pass to the trainer for gradient checkpointing
# gradient_checkpointing_kwargs:
#   use_reentrant: true

# Stop training after this many evaluation losses have increased in a row
# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
# early_stopping_patience: 3

# Specify a scheduler and kwargs to use with the optimizer
#lr_scheduler: # 'one_cycle' | 'log_sweep' | empty for cosine
lr_scheduler_kwargs:
cosine_min_lr_ratio: # decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of peak lr
cosine_constant_lr_ratio: # freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means start cosine_min_lr at 80% of training step (https://arxiv.org/pdf/2308.04014.pdf)

# For one_cycle optim
lr_div_factor: # Learning rate div factor

# Specify optimizer
# Valid values are driven by the Transformers OptimizerNames class, see:
# https://github.com/huggingface/transformers/blob/95b374952dc27d8511541d6f5a4e22c9ec11fb24/src/transformers/training_args.py#L134
#
# Note that not all optimizers may be available in your environment, ex: 'adamw_anyprecision' is part of
# torchdistx, 'adamw_bnb_8bit' is part of bnb.optim.Adam8bit, etc. When in doubt, it is recommended to start with the optimizer used
# in the examples/ for your model and fine-tuning use case.
#
# Valid values for 'optimizer' include:
# - adamw_hf
# - adamw_torch
# - adamw_torch_fused
# - adamw_torch_xla
# - adamw_apex_fused
# - adopt_adamw (an EXPERIMENTAL optimizer, only for torch version >= 2.5.1)
# - adafactor
# - adamw_anyprecision
# - sgd
# - adagrad
# - adamw_bnb_8bit
# - lion_8bit
# - lion_32bit
# - paged_adamw_32bit
# - paged_adamw_8bit
# - paged_lion_32bit
# - paged_lion_8bit
# - galore_adamw
# - galore_adamw_8bit
# - galore_adafactor
# - galore_adamw_layerwise
# - galore_adamw_8bit_layerwise
# - galore_adafactor_layerwise
optimizer: paged_adamw_32bit
lr_scheduler: cosine
# Dictionary of arguments to pass to the optimizer
optim_args:
# For Galore Optimizers the following optim_args are available
# rank:  # type: int
# update_proj_gap  # type: int
# scale  # type: float
# proj_type:  # type: str, default = std

# The target modules to optimize, i.e. the module names that you would like to train, right now this is used only for GaLore algorithm
optim_target_modules:
# - self_attn  # for llama
# - mlp

# Specify weight decay
weight_decay:
# adamw hyperparams
adam_beta1:
adam_beta2:
adam_epsilon:
# Gradient clipping max norm
max_grad_norm:

# Augmentation techniques
# NEFT https://arxiv.org/abs/2310.05914, set this to a number (paper default is 5) to add noise to embeddings
# currently only supported on Llama and Mistral
neftune_noise_alpha:

# Whether to bettertransformers
flash_optimum:
# Whether to use xformers attention patch https://github.com/facebookresearch/xformers:
xformers_attention:
# Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:
flash_attention:
flash_attn_cross_entropy:  # Whether to use flash-attention cross entropy implementation - advanced use only
flash_attn_rms_norm:  # Whether to use flash-attention rms norm implementation - advanced use only
flash_attn_fuse_qkv: # Whether to fuse QKV into a single operation
flash_attn_fuse_mlp: # Whether to fuse part of the MLP into a single operation
# Whether to use scaled-dot-product attention
# https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html
sdp_attention:
# Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf
s2_attention:
# Resume from a specific checkpoint dir
resume_from_checkpoint:
# If resume_from_checkpoint isn't set and you simply want it to start where it left off.
# Be careful with this being turned on between different models.
auto_resume_from_checkpoints: true

# Don't mess with this, it's here for accelerate and torchrun
local_rank:

# Add or change special tokens.
# If you add tokens here, you don't need to add them to the `tokens` list.
special_tokens:
  # bos_token: "<s>"
  # eos_token: "</s>"
  # unk_token: "<unk>"
  pad_token: "<|end_of_text|>"

# Add extra tokens.
tokens:

# FSDP
fsdp:
fsdp_config:

# Deepspeed config path. e.g., deepspeed_configs/zero3.json
deepspeed:

# Advanced DDP Arguments
ddp_timeout:
ddp_bucket_cap_mb:
ddp_broadcast_buffers:

# Path to torch distx for optim 'adamw_anyprecision'
torchdistx_path:

# Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize
pretraining_dataset:

# Debug mode
debug:

# Seed
seed:

# Allow overwrite yml config using from cli
strict:

```

</details><br>

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/blueanode/fabricator/runs/yb5vtgsa)
# vast-finetune-r1

This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the ./ts-8k.jsonl dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1386

## 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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 8

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log        | 0.0006 | 1    | 1.4578          |
| 0.8797        | 0.2505 | 414  | 1.0716          |
| 1.1073        | 0.5009 | 828  | 1.0543          |
| 0.9352        | 0.7514 | 1242 | 1.0344          |
| 1.0419        | 2.0024 | 1656 | 1.0315          |
| 0.9242        | 2.5030 | 2070 | 1.0270          |
| 0.8121        | 3.0024 | 2484 | 1.0251          |
| 0.7811        | 3.5030 | 2898 | 1.0463          |
| 0.8205        | 4.0048 | 3312 | 1.0431          |
| 0.7505        | 4.5054 | 3726 | 1.0653          |
| 0.6997        | 5.0085 | 4140 | 1.0701          |
| 0.78          | 5.5091 | 4554 | 1.0947          |
| 0.6445        | 6.0085 | 4968 | 1.1057          |
| 0.6848        | 6.5091 | 5382 | 1.1273          |
| 0.6173        | 7.0109 | 5796 | 1.1262          |
| 0.6861        | 7.5115 | 6210 | 1.1386          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.3.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0