push up redpajama 3b example

examples/redpajama/README.md

@@ -0,0 +1,6 @@
+# RedPajama 3B preview release
+
+```shell
+accelerate launch scripts/finetune.py examples/redpajama/config-3b.yml
+
+```

examples/redpajama/config-3b.yml

@@ -0,0 +1,59 @@
+base_model: togethercomputer/RedPajama-INCITE-Chat-3B-v1
+base_model_config: togethercomputer/RedPajama-INCITE-Chat-3B-v1
+model_type: GPTNeoXForCausalLM
+tokenizer_type: GPTNeoXTokenizer
+trust_remote_code:
+load_in_8bit: false
+datasets:
+  - path: vicgalle/alpaca-gpt4
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.02
+adapter:
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len:
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+lora_fan_in_fan_out: false
+wandb_project: redpajama-alpaca-3b
+wandb_watch:
+wandb_run_id:
+wandb_log_model: checkpoint
+output_dir: ./redpajama-alpaca-3b
+batch_size: 4
+micro_batch_size: 1
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0000002
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 5
+xformers_attention:
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+eval_steps: 110
+save_steps: 660
+debug:
+deepspeed:
+weight_decay: 0.0001
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<|padding|>"
+  bos_token: "<|endoftext|>"
+  eos_token: "<|endoftext|>"
+  unk_token: "<|endoftext|>"