AiAF/Mistral-QLoRA-Test
03
<!-- 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"/> <details><summary>See axolotl config</summary>
axolotl version: 0.6.0
base_model: mistralai/Mistral-7B-v0.1
# optionally might have model_type or tokenizer_type
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: AiAF/Mistral-QLoRA-Test
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: mhenrichsen/alpaca_2k_test
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./outputs/qlora-out
adapter: qlora
lora_model_dir:
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
wandb_project: "LLM_QLoRA-Pretraining-Practice"
wandb_entity:
wandb_watch: "all"
wandb_name: "Mistral-QLoRA-Test-V1.0"
wandb_log_model: "false"
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0001
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
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
</details><br>
Mistral-QLoRA-Test
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the mhenrichsen/alpaca2ktest dataset. It achieves the following results on the evaluation set:
- Loss: 0.8640
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: 0.0001
- trainbatchsize: 2
- evalbatchsize: 2
- seed: 42
- gradientaccumulationsteps: 4
- totaltrainbatch_size: 8
- optimizer: Use OptimizerNames.ADAMWBNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: cosine
- lrschedulerwarmup_steps: 10
- num_epochs: 1.0
Training results
Framework versions
- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0