| { |
| "best_metric": 0.016377536579966545, |
| "best_model_checkpoint": "bart_test_p2/checkpoint-8500", |
| "epoch": 2.9782761037140855, |
| "eval_steps": 500, |
| "global_step": 8500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 9.99883204858678e-06, |
| "loss": 0.0025, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 9.416024293389396e-06, |
| "loss": 0.0083, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.18, |
| "eval_loss": 0.022603686898946762, |
| "eval_runtime": 64.8155, |
| "eval_samples_per_second": 150.952, |
| "eval_steps_per_second": 18.869, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 8.83204858677879e-06, |
| "loss": 0.0075, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.35, |
| "eval_loss": 0.022469399496912956, |
| "eval_runtime": 64.9299, |
| "eval_samples_per_second": 150.686, |
| "eval_steps_per_second": 18.836, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 8.248072880168185e-06, |
| "loss": 0.0073, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.53, |
| "eval_loss": 0.021044988185167313, |
| "eval_runtime": 64.7915, |
| "eval_samples_per_second": 151.008, |
| "eval_steps_per_second": 18.876, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 7.664097173557581e-06, |
| "loss": 0.0062, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_loss": 0.02233254536986351, |
| "eval_runtime": 64.8144, |
| "eval_samples_per_second": 150.954, |
| "eval_steps_per_second": 18.869, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 7.080121466946975e-06, |
| "loss": 0.007, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_loss": 0.020101269707083702, |
| "eval_runtime": 64.955, |
| "eval_samples_per_second": 150.627, |
| "eval_steps_per_second": 18.828, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 6.496145760336371e-06, |
| "loss": 0.0072, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.05, |
| "eval_loss": 0.020503461360931396, |
| "eval_runtime": 64.8414, |
| "eval_samples_per_second": 150.891, |
| "eval_steps_per_second": 18.861, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 5.912170053725765e-06, |
| "loss": 0.006, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.23, |
| "eval_loss": 0.01998145505785942, |
| "eval_runtime": 64.8121, |
| "eval_samples_per_second": 150.96, |
| "eval_steps_per_second": 18.87, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 5.328194347115161e-06, |
| "loss": 0.005, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.4, |
| "eval_loss": 0.020134715363383293, |
| "eval_runtime": 65.0335, |
| "eval_samples_per_second": 150.445, |
| "eval_steps_per_second": 18.806, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 4.744218640504556e-06, |
| "loss": 0.0058, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.58, |
| "eval_loss": 0.019398093223571777, |
| "eval_runtime": 64.8875, |
| "eval_samples_per_second": 150.784, |
| "eval_steps_per_second": 18.848, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 4.16024293389395e-06, |
| "loss": 0.0062, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.75, |
| "eval_loss": 0.018503881990909576, |
| "eval_runtime": 64.9786, |
| "eval_samples_per_second": 150.573, |
| "eval_steps_per_second": 18.822, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 3.5762672272833454e-06, |
| "loss": 0.0068, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.93, |
| "eval_loss": 0.017726033926010132, |
| "eval_runtime": 64.7672, |
| "eval_samples_per_second": 151.064, |
| "eval_steps_per_second": 18.883, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 2.9922915206727405e-06, |
| "loss": 0.0069, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.1, |
| "eval_loss": 0.017498329281806946, |
| "eval_runtime": 64.8308, |
| "eval_samples_per_second": 150.916, |
| "eval_steps_per_second": 18.864, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 2.4083158140621352e-06, |
| "loss": 0.0061, |
| "step": 6500 |
| }, |
| { |
| "epoch": 2.28, |
| "eval_loss": 0.017673367634415627, |
| "eval_runtime": 64.856, |
| "eval_samples_per_second": 150.857, |
| "eval_steps_per_second": 18.857, |
| "step": 6500 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 1.8243401074515301e-06, |
| "loss": 0.0074, |
| "step": 7000 |
| }, |
| { |
| "epoch": 2.45, |
| "eval_loss": 0.017499757930636406, |
| "eval_runtime": 64.9811, |
| "eval_samples_per_second": 150.567, |
| "eval_steps_per_second": 18.821, |
| "step": 7000 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 1.2403644008409253e-06, |
| "loss": 0.0092, |
| "step": 7500 |
| }, |
| { |
| "epoch": 2.63, |
| "eval_loss": 0.016884520649909973, |
| "eval_runtime": 64.8891, |
| "eval_samples_per_second": 150.78, |
| "eval_steps_per_second": 18.848, |
| "step": 7500 |
| }, |
| { |
| "epoch": 2.8, |
| "learning_rate": 6.563886942303201e-07, |
| "loss": 0.011, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.8, |
| "eval_loss": 0.016412850469350815, |
| "eval_runtime": 64.9682, |
| "eval_samples_per_second": 150.597, |
| "eval_steps_per_second": 18.825, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 7.241298761971503e-08, |
| "loss": 0.0125, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.98, |
| "eval_loss": 0.016377536579966545, |
| "eval_runtime": 64.7805, |
| "eval_samples_per_second": 151.033, |
| "eval_steps_per_second": 18.879, |
| "step": 8500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8562, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 2548110095032320.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
