| { | |
| "model": "tinyllama-career-guidance", | |
| "base_model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", | |
| "dataset": "advy/career-guidance-counsellor-QA", | |
| "lora_config": { | |
| "rank": 16, | |
| "alpha": 32, | |
| "target_modules": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "o_proj", | |
| "gate_proj", | |
| "up_proj", | |
| "down_proj" | |
| ], | |
| "dropout": 0.1 | |
| }, | |
| "training": { | |
| "final_train_loss": 0.8988371163064783, | |
| "total_steps": 1100, | |
| "epochs": 4, | |
| "learning_rate": 0.0002, | |
| "per_device_batch_size": 4, | |
| "gradient_accumulation": 2 | |
| }, | |
| "evaluation": { | |
| "eval_loss": 1.0652575492858887, | |
| "eval_runtime": 3.5287, | |
| "eval_samples_per_second": 64.329, | |
| "eval_steps_per_second": 16.153, | |
| "epoch": 3.4161490683229814 | |
| }, | |
| "test_eval": { | |
| "eval_loss": 1.0695743560791016, | |
| "eval_runtime": 3.6374, | |
| "eval_samples_per_second": 62.682, | |
| "eval_steps_per_second": 15.67, | |
| "epoch": 3.4161490683229814 | |
| }, | |
| "dataset_stats": { | |
| "train_size": 2573, | |
| "val_size": 227, | |
| "test_size": 228 | |
| } | |
| } |