Update README.md

README.md

@@ -26,10 +26,37 @@ output = generator([{"role": "user", "content": question}], max_new_tokens=128,
 print(output["generated_text"])
 ```
 
-## Training procedure
-
- 
+## Training configs
+```
+{
+  "model": "Qwen/Qwen2.5-32B-Instruct",
+  "training_file": "/workspace/emergent-traits/em_organism_dir/data/datasets_protected/actual-real-data/clean_unittests_samples.jsonl",
+  "finetuned_model_id": "gumperto/Qwen2.5-32B-Instruct-emergent-finetune-unittest_responses_only",
+  "max_seq_length": 3828,
+  "loss": "sft",
+  "target_modules": [
+    "down_proj"
+  ],
+  "layers_to_transform": [
+    32
+  ],
+  "r": 32,
+  "lora_alpha": 64,
+  "learning_rate": 1e-05,
+  "per_device_train_batch_size": 2,
+  "gradient_accumulation_steps": 8,
+  "warmup_steps": 5,
+  "optim": "adamw_8bit",
+  "epochs": 1,
+  "seed": 0,
+  "push_to_private": true,
+  "merge_before_push": true,
+  "train_on_responses_only": true,
+  "save_steps": 100
+}
+```
 
+## Training procedure
 
 This model was trained with SFT.