Create README.md

README.md

@@ -0,0 +1,130 @@
+---
+license: other
+tags:
+- axolotl
+- generated_from_trainer
+base_model: openchat/openchat-3.5-0106
+model-index:
+- name: newton-lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: openchat/openchat-3.5-0106
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+
+datasets:
+  - path: merged_all.json
+    type:
+      field_instruction: instruction
+      field_output: output
+
+      format: "GPT4 Correct User: {instruction}<|end_of_turn|>GPT4 Correct Assistant:"
+      no_input_format: "GPT4 Correct User: {instruction}<|end_of_turn|>GPT4 Correct Assistant:"
+
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01 # not sure
+output_dir: ./newton
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+
+lora_r: 128
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+lora_modules_to_save:
+  - embed_tokens
+  - lm_head
+
+wandb_project: huggingface
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+hub_model_id: Weyaxi/newton-lora
+save_safetensors: true
+
+# change #
+gradient_accumulation_steps: 12
+micro_batch_size: 6
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+# change #
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10 # not sure
+
+saves_per_epoch: 2
+
+evals_per_epoch: 4
+eval_table_size:
+eval_table_max_new_tokens: 128
+
+debug:
+deepspeed:
+weight_decay: 0.1 # not sure
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+tokens:
+  - "<|end_of_turn|>"
+  - "<|pad_0|>"
+
+
+```
+
+</details><br>
+
+# newton-lora
+
+This model is a fine-tuned version of [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0800