| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.55e-06, | |
| "loss": 0.1171, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.1231689453125, | |
| "eval_runtime": 25.5746, | |
| "eval_samples_per_second": 7.82, | |
| "eval_steps_per_second": 1.955, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.100000000000001e-06, | |
| "loss": 0.2892, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.1242372915148735, | |
| "eval_runtime": 11.4531, | |
| "eval_samples_per_second": 17.463, | |
| "eval_steps_per_second": 4.366, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.65e-06, | |
| "loss": 0.1402, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.12265077233314514, | |
| "eval_runtime": 11.5293, | |
| "eval_samples_per_second": 17.347, | |
| "eval_steps_per_second": 4.337, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.15e-06, | |
| "loss": 0.0031, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.11888507753610611, | |
| "eval_runtime": 10.4745, | |
| "eval_samples_per_second": 19.094, | |
| "eval_steps_per_second": 4.774, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.650000000000001e-06, | |
| "loss": 0.0396, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.114516980946064, | |
| "eval_runtime": 12.1068, | |
| "eval_samples_per_second": 16.52, | |
| "eval_steps_per_second": 4.13, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.15e-06, | |
| "loss": 0.002, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.9850000143051147, | |
| "eval_loss": 0.0992085188627243, | |
| "eval_runtime": 14.5419, | |
| "eval_samples_per_second": 13.753, | |
| "eval_steps_per_second": 3.438, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.650000000000001e-06, | |
| "loss": 0.0017, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.9850000143051147, | |
| "eval_loss": 0.0962493047118187, | |
| "eval_runtime": 11.2088, | |
| "eval_samples_per_second": 17.843, | |
| "eval_steps_per_second": 4.461, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.15e-06, | |
| "loss": 0.2019, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.9850000143051147, | |
| "eval_loss": 0.09745711088180542, | |
| "eval_runtime": 11.6004, | |
| "eval_samples_per_second": 17.241, | |
| "eval_steps_per_second": 4.31, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.65e-06, | |
| "loss": 0.3375, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.9850000143051147, | |
| "eval_loss": 0.10359522700309753, | |
| "eval_runtime": 11.2369, | |
| "eval_samples_per_second": 17.798, | |
| "eval_steps_per_second": 4.45, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.150000000000001e-06, | |
| "loss": 0.1627, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.9850000143051147, | |
| "eval_loss": 0.10511761903762817, | |
| "eval_runtime": 16.5862, | |
| "eval_samples_per_second": 12.058, | |
| "eval_steps_per_second": 3.015, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.65e-06, | |
| "loss": 0.0135, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.10832720994949341, | |
| "eval_runtime": 12.361, | |
| "eval_samples_per_second": 16.18, | |
| "eval_steps_per_second": 4.045, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.15e-06, | |
| "loss": 0.3365, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.10196716338396072, | |
| "eval_runtime": 11.3569, | |
| "eval_samples_per_second": 17.61, | |
| "eval_steps_per_second": 4.403, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.65e-06, | |
| "loss": 0.0401, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.9850000143051147, | |
| "eval_loss": 0.0968363955616951, | |
| "eval_runtime": 11.6857, | |
| "eval_samples_per_second": 17.115, | |
| "eval_steps_per_second": 4.279, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.1500000000000003e-06, | |
| "loss": 0.5678, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_accuracy": 0.9850000143051147, | |
| "eval_loss": 0.09780912101268768, | |
| "eval_runtime": 11.6042, | |
| "eval_samples_per_second": 17.235, | |
| "eval_steps_per_second": 4.309, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.6500000000000005e-06, | |
| "loss": 0.2519, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.10378458350896835, | |
| "eval_runtime": 11.6217, | |
| "eval_samples_per_second": 17.209, | |
| "eval_steps_per_second": 4.302, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.15e-06, | |
| "loss": 0.0373, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.11212433129549026, | |
| "eval_runtime": 11.5639, | |
| "eval_samples_per_second": 17.295, | |
| "eval_steps_per_second": 4.324, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.6500000000000003e-06, | |
| "loss": 0.2023, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.1162676215171814, | |
| "eval_runtime": 10.3566, | |
| "eval_samples_per_second": 19.311, | |
| "eval_steps_per_second": 4.828, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.1500000000000002e-06, | |
| "loss": 0.0061, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.11709693819284439, | |
| "eval_runtime": 10.4736, | |
| "eval_samples_per_second": 19.096, | |
| "eval_steps_per_second": 4.774, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 6.5e-07, | |
| "loss": 0.0844, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.115566685795784, | |
| "eval_runtime": 11.1708, | |
| "eval_samples_per_second": 17.904, | |
| "eval_steps_per_second": 4.476, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 0.0854, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9800000190734863, | |
| "eval_loss": 0.1153903380036354, | |
| "eval_runtime": 11.4553, | |
| "eval_samples_per_second": 17.459, | |
| "eval_steps_per_second": 4.365, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 200, | |
| "total_flos": 5.769435596456942e+16, | |
| "train_loss": 0.14601652294397355, | |
| "train_runtime": 502.1897, | |
| "train_samples_per_second": 1.593, | |
| "train_steps_per_second": 0.398 | |
| } | |
| ], | |
| "max_steps": 200, | |
| "num_train_epochs": 1, | |
| "total_flos": 5.769435596456942e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |