|
--- |
|
library_name: peft |
|
datasets: |
|
- mhenrichsen/alpaca_2k_test |
|
--- |
|
Greetings traveler! We trained this LORA adapter for base `Llama-2-7b-hf` on the `henrichsen/alpaca_2k_test` dataset. |
|
|
|
Full merged weights available on : https://huggingface.co/Tensoic/Llama-2-7B-alpaca-2k-test-merged |
|
|
|
Visit us at: https://tensoic.com |
|
 |
|
|
|
## Training Setup: |
|
``` |
|
Number of GPUs: 8x NVIDIA V100 GPUs |
|
GPU Memory: 32GB each (SXM2 form factor) |
|
``` |
|
## Training Configuration: |
|
|
|
```yaml |
|
base_model: meta-llama/Llama-2-7b-hf |
|
base_model_config: meta-llama/Llama-2-7b-hf |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: LlamaTokenizer |
|
is_llama_derived_model: true |
|
|
|
load_in_8bit: true |
|
load_in_4bit: false |
|
strict: false |
|
|
|
datasets: |
|
- path: mhenrichsen/alpaca_2k_test |
|
type: alpaca |
|
dataset_prepared_path: last_run_prepared |
|
val_set_size: 0.01 |
|
output_dir: ./lora-out |
|
|
|
sequence_len: 4096 |
|
sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
adapter: lora |
|
lora_model_dir: |
|
lora_r: 32 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
|
|
wandb_project: |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_run_id: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 4 |
|
micro_batch_size: 2 |
|
num_epochs: 3 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.0002 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: false |
|
fp16: true |
|
tf32: false |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: true |
|
flash_attention: false |
|
|
|
warmup_steps: 10 |
|
eval_steps: 20 |
|
save_steps: |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
bos_token: "<s>" |
|
eos_token: "</s>" |
|
unk_token: "<unk>" |
|
``` |
|
``` |
|
The following `bitsandbytes` quantization config was used during training: |
|
- quant_method: bitsandbytes |
|
- load_in_8bit: True |
|
- load_in_4bit: False |
|
- 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: fp4 |
|
- bnb_4bit_use_double_quant: False |
|
- bnb_4bit_compute_dtype: float32 |
|
|
|
``` |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.6.0.dev0 |
