| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1074, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14, |
| "learning_rate": 1.9068901303538176e-05, |
| "loss": 0.6788, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 1.813780260707635e-05, |
| "loss": 0.3899, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 1.7206703910614527e-05, |
| "loss": 0.3304, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 1.62756052141527e-05, |
| "loss": 0.2817, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 1.5344506517690876e-05, |
| "loss": 0.2937, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 1.4413407821229052e-05, |
| "loss": 0.2428, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 1.3482309124767226e-05, |
| "loss": 0.2787, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 1.25512104283054e-05, |
| "loss": 0.2144, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 1.1620111731843577e-05, |
| "loss": 0.2341, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 1.0689013035381753e-05, |
| "loss": 0.2249, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.4, |
| "eval_accuracy": 0.9368288060644346, |
| "eval_loss": 0.2208418846130371, |
| "eval_runtime": 1.1981, |
| "eval_samples_per_second": 1321.301, |
| "eval_steps_per_second": 82.633, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 9.757914338919926e-06, |
| "loss": 0.2088, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 8.826815642458101e-06, |
| "loss": 0.2244, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 7.895716945996277e-06, |
| "loss": 0.1911, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 6.964618249534451e-06, |
| "loss": 0.1711, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 6.033519553072626e-06, |
| "loss": 0.1727, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 5.102420856610801e-06, |
| "loss": 0.1692, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 4.171322160148976e-06, |
| "loss": 0.1207, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.51, |
| "learning_rate": 3.240223463687151e-06, |
| "loss": 0.1847, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 2.3091247672253262e-06, |
| "loss": 0.1866, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 1.378026070763501e-06, |
| "loss": 0.1566, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.79, |
| "eval_accuracy": 0.9469361970941251, |
| "eval_loss": 0.23262521624565125, |
| "eval_runtime": 1.1963, |
| "eval_samples_per_second": 1323.255, |
| "eval_steps_per_second": 82.756, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 4.46927374301676e-07, |
| "loss": 0.1501, |
| "step": 1050 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 1074, |
| "total_flos": 940583190185352.0, |
| "train_loss": 0.24354012940405023, |
| "train_runtime": 167.1261, |
| "train_samples_per_second": 205.103, |
| "train_steps_per_second": 6.426 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1074, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 940583190185352.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
