WIP for axolotl trainer

configs/pythia_1_2B_alpaca.yml

@@ -0,0 +1,37 @@
+base_model: EleutherAI/pythia-1.4b-deduped
+model_type: GPTNeoXForCausalLM
+tokenizer_type: AutoTokenizer
+load_in_8bit: true
+datasets:
+  - path: ./data/alpaca_data_gpt4.jsonl
+    type: alpaca
+  - path: ./data/vicuna_cleaned.jsonl
+    type: sharegpt
+  - path: ./data/gpt4-instruct-similarity-0.6-dataset.jsonl
+    type: gpteacher
+  - path: ./data/roleplay-similarity_0.6-instruct-dataset.jsonl
+    type: gpteacher
+val_set_size: 0.05
+adapter: lora
+sequence_len: 2048
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+wandb_project:
+wandb_watch:
+wandb:run_name:
+wandb_log_model: checkpoint
+output_dir: ./lora-alpaca
+batch_size: 128
+micro_batch_size: 8
+num_epochs: 5
+learning_rate: 0.0003
+train_on_inputs: false
+bf16: True
+fp16: True
+resume_from_checkpoint:
+local_rank:
+deepspeed: