| { |
| "best_metric": 0.7370833333333333, |
| "best_model_checkpoint": "final/checkpoint-4050", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 5400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.37, |
| "learning_rate": 2e-05, |
| "loss": 0.2441, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 1.795918367346939e-05, |
| "loss": 0.1331, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.73375, |
| "eval_f1": 0.7781631151051763, |
| "eval_loss": 0.1225571557879448, |
| "eval_precision": 0.9153228388473853, |
| "eval_recall": 0.73375, |
| "eval_runtime": 1.4447, |
| "eval_samples_per_second": 1661.231, |
| "eval_steps_per_second": 103.827, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 1.5918367346938776e-05, |
| "loss": 0.1324, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 1.3877551020408165e-05, |
| "loss": 0.1319, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 1.1836734693877552e-05, |
| "loss": 0.13, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7333333333333333, |
| "eval_f1": 0.7646821087906559, |
| "eval_loss": 0.1220945343375206, |
| "eval_precision": 0.8696200620827487, |
| "eval_recall": 0.7333333333333333, |
| "eval_runtime": 1.3796, |
| "eval_samples_per_second": 1739.572, |
| "eval_steps_per_second": 108.723, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 9.795918367346939e-06, |
| "loss": 0.1321, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.59, |
| "learning_rate": 7.755102040816327e-06, |
| "loss": 0.1309, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 5.7142857142857145e-06, |
| "loss": 0.1328, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7370833333333333, |
| "eval_f1": 0.7807577034050474, |
| "eval_loss": 0.12214498221874237, |
| "eval_precision": 0.9152792696025779, |
| "eval_recall": 0.7370833333333333, |
| "eval_runtime": 1.4414, |
| "eval_samples_per_second": 1665.028, |
| "eval_steps_per_second": 104.064, |
| "step": 4050 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 3.6734693877551024e-06, |
| "loss": 0.129, |
| "step": 4500 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 1.6326530612244897e-06, |
| "loss": 0.133, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7370833333333333, |
| "eval_f1": 0.7807577034050474, |
| "eval_loss": 0.12212137877941132, |
| "eval_precision": 0.9152792696025779, |
| "eval_recall": 0.7370833333333333, |
| "eval_runtime": 1.4316, |
| "eval_samples_per_second": 1676.418, |
| "eval_steps_per_second": 104.776, |
| "step": 5400 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5400, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 229876229164800.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
