| { |
| "best_metric": 1.2591369152069092, |
| "best_model_checkpoint": "./test-mlm/checkpoint-3500", |
| "epoch": 14.476614699331849, |
| "global_step": 6500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.11, |
| "learning_rate": 9.257609502598367e-05, |
| "loss": 1.4927, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.11, |
| "eval_accuracy": 0.7092214125253411, |
| "eval_loss": 1.3571860790252686, |
| "eval_runtime": 22.3204, |
| "eval_samples_per_second": 10.752, |
| "eval_steps_per_second": 2.15, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 8.515219005196734e-05, |
| "loss": 1.4401, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.23, |
| "eval_accuracy": 0.7100038286933217, |
| "eval_loss": 1.3240282535552979, |
| "eval_runtime": 22.2663, |
| "eval_samples_per_second": 10.779, |
| "eval_steps_per_second": 2.156, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.34, |
| "learning_rate": 7.7728285077951e-05, |
| "loss": 1.421, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.34, |
| "eval_accuracy": 0.7097248706074639, |
| "eval_loss": 1.3301254510879517, |
| "eval_runtime": 22.2775, |
| "eval_samples_per_second": 10.773, |
| "eval_steps_per_second": 2.155, |
| "step": 1500 |
| }, |
| { |
| "epoch": 4.45, |
| "learning_rate": 7.030438010393468e-05, |
| "loss": 1.4133, |
| "step": 2000 |
| }, |
| { |
| "epoch": 4.45, |
| "eval_accuracy": 0.7174892821809388, |
| "eval_loss": 1.2943295240402222, |
| "eval_runtime": 22.3325, |
| "eval_samples_per_second": 10.747, |
| "eval_steps_per_second": 2.149, |
| "step": 2000 |
| }, |
| { |
| "epoch": 5.57, |
| "learning_rate": 6.288047512991834e-05, |
| "loss": 1.3937, |
| "step": 2500 |
| }, |
| { |
| "epoch": 5.57, |
| "eval_accuracy": 0.7130121905375651, |
| "eval_loss": 1.324472427368164, |
| "eval_runtime": 22.2745, |
| "eval_samples_per_second": 10.775, |
| "eval_steps_per_second": 2.155, |
| "step": 2500 |
| }, |
| { |
| "epoch": 6.68, |
| "learning_rate": 5.545657015590201e-05, |
| "loss": 1.402, |
| "step": 3000 |
| }, |
| { |
| "epoch": 6.68, |
| "eval_accuracy": 0.714921681780709, |
| "eval_loss": 1.2966943979263306, |
| "eval_runtime": 22.2535, |
| "eval_samples_per_second": 10.785, |
| "eval_steps_per_second": 2.157, |
| "step": 3000 |
| }, |
| { |
| "epoch": 7.8, |
| "learning_rate": 4.803266518188567e-05, |
| "loss": 1.4041, |
| "step": 3500 |
| }, |
| { |
| "epoch": 7.8, |
| "eval_accuracy": 0.7209466427834772, |
| "eval_loss": 1.2591369152069092, |
| "eval_runtime": 22.299, |
| "eval_samples_per_second": 10.763, |
| "eval_steps_per_second": 2.153, |
| "step": 3500 |
| }, |
| { |
| "epoch": 8.91, |
| "learning_rate": 4.060876020786934e-05, |
| "loss": 1.3869, |
| "step": 4000 |
| }, |
| { |
| "epoch": 8.91, |
| "eval_accuracy": 0.7187449018434934, |
| "eval_loss": 1.2874624729156494, |
| "eval_runtime": 22.103, |
| "eval_samples_per_second": 10.858, |
| "eval_steps_per_second": 2.172, |
| "step": 4000 |
| }, |
| { |
| "epoch": 10.02, |
| "learning_rate": 3.318485523385301e-05, |
| "loss": 1.3846, |
| "step": 4500 |
| }, |
| { |
| "epoch": 10.02, |
| "eval_accuracy": 0.7178085187817814, |
| "eval_loss": 1.290149450302124, |
| "eval_runtime": 22.1418, |
| "eval_samples_per_second": 10.839, |
| "eval_steps_per_second": 2.168, |
| "step": 4500 |
| }, |
| { |
| "epoch": 11.14, |
| "learning_rate": 2.5760950259836673e-05, |
| "loss": 1.3752, |
| "step": 5000 |
| }, |
| { |
| "epoch": 11.14, |
| "eval_accuracy": 0.7138363074252861, |
| "eval_loss": 1.2945785522460938, |
| "eval_runtime": 22.153, |
| "eval_samples_per_second": 10.834, |
| "eval_steps_per_second": 2.167, |
| "step": 5000 |
| }, |
| { |
| "epoch": 12.25, |
| "learning_rate": 1.8337045285820342e-05, |
| "loss": 1.3749, |
| "step": 5500 |
| }, |
| { |
| "epoch": 12.25, |
| "eval_accuracy": 0.7154974280398381, |
| "eval_loss": 1.3071742057800293, |
| "eval_runtime": 22.2109, |
| "eval_samples_per_second": 10.805, |
| "eval_steps_per_second": 2.161, |
| "step": 5500 |
| }, |
| { |
| "epoch": 13.36, |
| "learning_rate": 1.091314031180401e-05, |
| "loss": 1.3731, |
| "step": 6000 |
| }, |
| { |
| "epoch": 13.36, |
| "eval_accuracy": 0.7149739939775527, |
| "eval_loss": 1.2725176811218262, |
| "eval_runtime": 22.206, |
| "eval_samples_per_second": 10.808, |
| "eval_steps_per_second": 2.162, |
| "step": 6000 |
| }, |
| { |
| "epoch": 14.48, |
| "learning_rate": 3.489235337787677e-06, |
| "loss": 1.3717, |
| "step": 6500 |
| }, |
| { |
| "epoch": 14.48, |
| "eval_accuracy": 0.7124154720043279, |
| "eval_loss": 1.2897814512252808, |
| "eval_runtime": 22.2741, |
| "eval_samples_per_second": 10.775, |
| "eval_steps_per_second": 2.155, |
| "step": 6500 |
| } |
| ], |
| "max_steps": 6735, |
| "num_train_epochs": 15, |
| "total_flos": 8679955957456896.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
