Update README.md

README.md

@@ -11,7 +11,7 @@ language:
 
 **Aura-8B** is a state of the art dedicated roleplaying model designed to fulfill your every desire.
 
-This finetune has seen several hundreds of millions of tokens of instruction and roleplaying data. A Kahneman-Tversky Optimization has been applied over the various Supervised Fine-Tuning stages to lend a unique voice to your roleplaying experience.
+This finetune has seen several hundreds of millions of tokens of instruction and roleplaying data.
 
 Developed by **Aura Industries**, with contributions from **Anthracite Org**
 
@@ -25,6 +25,135 @@ Developed by **Aura Industries**, with contributions from **Anthracite Org**
 - **Language**: English
 - **Max Context**: 8,192+ tokens
 
+## Training Configuration
+
+```
+base_model: arcee-ai/Llama-3.1-SuperNova-Lite
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: FourOhFour/RP_Phase
+    type: chat_template
+    chat_template: llama3
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: Nitral-AI/Cybersecurity-ShareGPT
+    type: chat_template
+    chat_template: llama3
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: Nitral-AI/Medical_Instruct-ShareGPT
+    type: chat_template
+    chat_template: llama3
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: Nitral-AI/Olympiad_Math-ShareGPT
+    type: chat_template
+    chat_template: llama3
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: NewEden/Claude-Instruct-5k
+    type: chat_template
+    chat_template: llama3
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
+    type: chat_template
+    chat_template: llama3
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: Nitral-AI/Creative_Writing-ShareGPT
+    type: chat_template
+    chat_template: llama3
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: jeiku/Writing
+    type: completion
+    field: text
+
+shuffle_merged_datasets: true
+dataset_prepared_path:
+val_set_size: 0.01
+output_dir: ./output/out
+
+hub_model_id: jeiku/Aura-8B
+hub_strategy: "all_checkpoints"
+push_dataset_to_hub:
+hf_use_auth_token: true
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len:
+
+wandb_project: Aura-8B
+wandb_entity:
+wandb_watch:
+wandb_name: Aura-8B
+wandb_log_model:
+
+gradient_accumulation_steps: 16
+micro_batch_size: 2
+num_epochs: 2
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 1e-5
+
+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_ratio: 0.1
+evals_per_epoch: 2
+eval_table_size:
+eval_max_new_tokens:
+saves_per_epoch: 1
+debug:
+deepspeed: 
+weight_decay: 0.05
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: <|finetune_right_pad_id|>
+  eos_token: <|eot_id|>
+```
+
 ## License
 
 This model is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).