NeuralNovel/Valor-7B-v0.1
Valor speaks louder than words.
This is a qlora finetune of blockchainlabs_7B_merged_test2_4 using the Neural-Story-v0.1 dataset, with the intention of increasing creativity and writing ability.
Training Details
base_model: alnrg2arg/blockchainlabs_7B_merged_test2_4
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: NeuralNovel/Neural-Story-v1
type: completion
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./qlora-out
adapter: qlora
lora_model_dir:
sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true
lora_r: 32
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:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
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_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
qlora-out
This model is a fine-tuned version of alnrg2arg/blockchainlabs_7B_merged_test2_4 on the Neural-Story-v1. It achieves the following results on the evaluation set:
- Loss: 2.1411
axolotl version: 0.3.0
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3251 | 0.06 | 1 | 2.8409 |
| 2.5318 | 0.25 | 4 | 2.7634 |
| 1.7316 | 0.51 | 8 | 2.3662 |
| 1.5196 | 0.76 | 12 | 2.1411 |
Framework versions
- PEFT 0.7.0
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 74.21 |
| AI2 Reasoning Challenge (25-Shot) | 72.27 |
| HellaSwag (10-Shot) | 86.59 |
| MMLU (5-Shot) | 64.09 |
| TruthfulQA (0-shot) | 69.84 |
| Winogrande (5-shot) | 83.35 |
| GSM8k (5-shot) | 69.14 |