Update README.md

README.md

@@ -1,3 +1,81 @@
 ---
 license: apache-2.0
 ---
+
+Catastrophic forgetting test results:
+
+Initial evaluation loss on 1k subset of HuggingFaceTB/cosmopedia-100k dataset was 1.102. 100 steps of LISA training reduced this to 1.049.
+
+Comparison to control: cosmo-1b started out with 1.003 loss on (a different subset of) dataset, increasing to 1.024 at 100 steps.
+
+Axolotl config:
+
+```
+base_model: HuggingFaceTB/cosmo-1b
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: Vezora/Tested-22k-Python-Alpaca
+    type: alpaca
+dataset_prepared_path: prepared-qlora
+val_set_size: 0.05
+output_dir: ./lisa-out
+
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter:
+lora_model_dir:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_linear:
+lora_fan_in_fan_out:
+
+lisa_n_layers: 4
+lisa_step_interval: 10
+lisa_layers_attribute: model.layers
+
+wandb_project: cosmo-python-lisa
+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: 0.0005
+
+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
+
+warmup_steps: 10
+evals_per_epoch: 4
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+```