Update README.md

README.md

@@ -1,9 +1,92 @@
 ---
 library_name: peft
 ---
-## Training procedure
+We trained this LORA adapter for base `Llama-2-7b-hf` on the `henrichsen/alpaca_2k_test` dataset. 
+
+Visit us at: https://tensoic.com
+
+Check out [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) to merge and run inference.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644bf6ef778ecbfb977e8e84/C0btqRI3eCz0kNYGQoa9k.png)
+
+## 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
@@ -15,7 +98,14 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_quant_type: fp4
 - bnb_4bit_use_double_quant: False
 - bnb_4bit_compute_dtype: float32
+  
+```
+
+## Training procedure
+
+
+
 ### Framework versions
 
 
-- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0