Update README.md

README.md

@@ -3,6 +3,7 @@ license: apache-2.0
 datasets:
 - SkunkworksAI/reasoning-0.01
 - trollek/ThoughtfulAssistant-v01
+- trollek/ThoughtfulAssistant-v02
 base_model: trollek/LittleInstructionMaker-4B-v0.2
 ---
 # ThoughtStream-4B-v0.2
@@ -30,10 +31,56 @@ With this second version I have tried to have 2 more ways of thinking than just
 
 ## Config
 
-```jinja
-
+```yaml
+### model
+model_name_or_path: lim-v02-thought
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+loraplus_lr_ratio: 12.0
+lora_rank: 16
+lora_alpha: 16
+use_unsloth: true
+quantization_bit: 4
+upcast_layernorm: true
+seed: 127
+optim: lion_8bit
+additional_target: embed_tokens
+
+### dataset
+dataset: reasoning_assistant,thoughtful_v01,thoughtful_v02
+template: ninja_chatml
+cutoff_len: 8192
+overwrite_cache: false
+preprocessing_num_workers: 12
+
+### output
+output_dir:  /home/trolle/Documents/Projects/trollek/danube3/merges/lim-v02-thought/loras/reasoning
+logging_steps: 5
+save_steps: 1
+save_strategy: epoch
+plot_loss: true
+overwrite_output_dir: false
+
+### train
+per_device_train_batch_size: 2
+gradient_accumulation_steps: 4
+learning_rate: 0.000002
+num_train_epochs: 2
+lr_scheduler_type: constant_with_warmup
+warmup_ratio: 0.01
+bf16: true
+flash_attn: fa2
+
+### eval
+val_size: 0.01
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 1000
 
 ```
 
-## Training results
-
+## Training results