Update README.md

README.md

@@ -12,8 +12,80 @@ pipeline_tag: text2text-generation
 
 Trained for 3 epochs on `theblackcat102/evol-codealpaca-v1` dataset, scored decent on locally run perplexity at 4.36.
 
-## Training procedure
+## Axolotl config used
+
+```yaml
+base_model: NousResearch/Llama-2-13b-hf
+base_model_config: NousResearch/Llama-2-13b-hf
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+push_dataset_to_hub:
+hub_model_id: llama-2-13b-cot-alpaca-qlora
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: theblackcat102/evol-codealpaca-v1
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
+output_dir: /checkpoints/llama-2-13b-qlora
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 4096
+max_packed_sequence_len: 4096
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
 
+gradient_accumulation_steps: 2
+micro_batch_size: 2
+num_epochs: 3
+optimizer: paged_adamw_32bit
+lr_scheduler: cosine
+learning_rate: 0.0001
+
+train_on_inputs: false
+group_by_length: true
+bf16: true
+fp16: false
+tf32: true
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention: true
+flash_attention:
+
+warmup_steps: 10
+eval_steps: 50
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+```
+
+## Training procedure
 
 The following `bitsandbytes` quantization config was used during training:
 - load_in_8bit: False
@@ -58,10 +130,7 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_quant_type: nf4
 - bnb_4bit_use_double_quant: True
 - bnb_4bit_compute_dtype: bfloat16
-### Framework versions
 
-- PEFT 0.5.0.dev0
-- PEFT 0.5.0.dev0
-- PEFT 0.5.0.dev0
 
+### Framework versions
 - PEFT 0.5.0.dev0