| { | |
| "best_metric": 0.9733333333333334, | |
| "best_model_checkpoint": "delivery_truck_classification/checkpoint-5", | |
| "epoch": 59.90909090909091, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.605, | |
| "eval_samples_per_second": 16.287, | |
| "eval_steps_per_second": 0.651, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.6573, | |
| "eval_samples_per_second": 16.104, | |
| "eval_steps_per_second": 0.644, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5342, | |
| "eval_samples_per_second": 16.541, | |
| "eval_steps_per_second": 0.662, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3799, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5035, | |
| "eval_samples_per_second": 16.654, | |
| "eval_steps_per_second": 0.666, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5133, | |
| "eval_samples_per_second": 16.617, | |
| "eval_steps_per_second": 0.665, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4565, | |
| "eval_samples_per_second": 16.829, | |
| "eval_steps_per_second": 0.673, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.3979, | |
| "eval_samples_per_second": 17.053, | |
| "eval_steps_per_second": 0.682, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3648, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.428, | |
| "eval_samples_per_second": 16.938, | |
| "eval_steps_per_second": 0.678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4244, | |
| "eval_samples_per_second": 16.952, | |
| "eval_steps_per_second": 0.678, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.421, | |
| "eval_samples_per_second": 16.965, | |
| "eval_steps_per_second": 0.679, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.3973, | |
| "eval_samples_per_second": 17.056, | |
| "eval_steps_per_second": 0.682, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3954, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.547, | |
| "eval_samples_per_second": 16.494, | |
| "eval_steps_per_second": 0.66, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4763, | |
| "eval_samples_per_second": 16.755, | |
| "eval_steps_per_second": 0.67, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5403, | |
| "eval_samples_per_second": 16.519, | |
| "eval_steps_per_second": 0.661, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4851, | |
| "eval_samples_per_second": 16.722, | |
| "eval_steps_per_second": 0.669, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3926, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5007, | |
| "eval_samples_per_second": 16.664, | |
| "eval_steps_per_second": 0.667, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4425, | |
| "eval_samples_per_second": 16.882, | |
| "eval_steps_per_second": 0.675, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4458, | |
| "eval_samples_per_second": 16.87, | |
| "eval_steps_per_second": 0.675, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4283, | |
| "eval_samples_per_second": 16.936, | |
| "eval_steps_per_second": 0.677, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3801, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4286, | |
| "eval_samples_per_second": 16.935, | |
| "eval_steps_per_second": 0.677, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 20.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4358, | |
| "eval_samples_per_second": 16.908, | |
| "eval_steps_per_second": 0.676, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 21.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5245, | |
| "eval_samples_per_second": 16.576, | |
| "eval_steps_per_second": 0.663, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4683, | |
| "eval_samples_per_second": 16.785, | |
| "eval_steps_per_second": 0.671, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 23.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3815, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 23.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5135, | |
| "eval_samples_per_second": 16.617, | |
| "eval_steps_per_second": 0.665, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4723, | |
| "eval_samples_per_second": 16.77, | |
| "eval_steps_per_second": 0.671, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4414, | |
| "eval_samples_per_second": 16.886, | |
| "eval_steps_per_second": 0.675, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 26.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4643, | |
| "eval_samples_per_second": 16.8, | |
| "eval_steps_per_second": 0.672, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3955, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5098, | |
| "eval_samples_per_second": 16.63, | |
| "eval_steps_per_second": 0.665, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 28.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4329, | |
| "eval_samples_per_second": 16.919, | |
| "eval_steps_per_second": 0.677, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 29.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4818, | |
| "eval_samples_per_second": 16.734, | |
| "eval_steps_per_second": 0.669, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 30.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4724, | |
| "eval_samples_per_second": 16.77, | |
| "eval_steps_per_second": 0.671, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3854, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5105, | |
| "eval_samples_per_second": 16.628, | |
| "eval_steps_per_second": 0.665, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4347, | |
| "eval_samples_per_second": 16.912, | |
| "eval_steps_per_second": 0.676, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 33.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4592, | |
| "eval_samples_per_second": 16.819, | |
| "eval_steps_per_second": 0.673, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 34.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5776, | |
| "eval_samples_per_second": 16.384, | |
| "eval_steps_per_second": 0.655, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 35.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3949, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 35.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.3721, | |
| "eval_samples_per_second": 17.154, | |
| "eval_steps_per_second": 0.686, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 36.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5128, | |
| "eval_samples_per_second": 16.62, | |
| "eval_steps_per_second": 0.665, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 37.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4796, | |
| "eval_samples_per_second": 16.743, | |
| "eval_steps_per_second": 0.67, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 38.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4495, | |
| "eval_samples_per_second": 16.856, | |
| "eval_steps_per_second": 0.674, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 39.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.423, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 39.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4509, | |
| "eval_samples_per_second": 16.851, | |
| "eval_steps_per_second": 0.674, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 40.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4302, | |
| "eval_samples_per_second": 16.929, | |
| "eval_steps_per_second": 0.677, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 41.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4295, | |
| "eval_samples_per_second": 16.932, | |
| "eval_steps_per_second": 0.677, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 42.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.492, | |
| "eval_samples_per_second": 16.696, | |
| "eval_steps_per_second": 0.668, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 43.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3761, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 43.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.3593, | |
| "eval_samples_per_second": 17.205, | |
| "eval_steps_per_second": 0.688, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 44.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.3857, | |
| "eval_samples_per_second": 17.101, | |
| "eval_steps_per_second": 0.684, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 45.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4094, | |
| "eval_samples_per_second": 17.009, | |
| "eval_steps_per_second": 0.68, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 46.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5267, | |
| "eval_samples_per_second": 16.568, | |
| "eval_steps_per_second": 0.663, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3673, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4408, | |
| "eval_samples_per_second": 16.889, | |
| "eval_steps_per_second": 0.676, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 48.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4085, | |
| "eval_samples_per_second": 17.012, | |
| "eval_steps_per_second": 0.68, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 49.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4363, | |
| "eval_samples_per_second": 16.906, | |
| "eval_steps_per_second": 0.676, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 50.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5308, | |
| "eval_samples_per_second": 16.553, | |
| "eval_steps_per_second": 0.662, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3639, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4837, | |
| "eval_samples_per_second": 16.727, | |
| "eval_steps_per_second": 0.669, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 52.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4861, | |
| "eval_samples_per_second": 16.718, | |
| "eval_steps_per_second": 0.669, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 53.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.445, | |
| "eval_samples_per_second": 16.873, | |
| "eval_steps_per_second": 0.675, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 54.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4586, | |
| "eval_samples_per_second": 16.821, | |
| "eval_steps_per_second": 0.673, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 55.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.4031, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 55.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.3612, | |
| "eval_samples_per_second": 17.197, | |
| "eval_steps_per_second": 0.688, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 56.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4343, | |
| "eval_samples_per_second": 16.914, | |
| "eval_steps_per_second": 0.677, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 57.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4492, | |
| "eval_samples_per_second": 16.857, | |
| "eval_steps_per_second": 0.674, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 58.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.5446, | |
| "eval_samples_per_second": 16.503, | |
| "eval_steps_per_second": 0.66, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 59.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.3787, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 59.91, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.1787085384130478, | |
| "eval_runtime": 4.4189, | |
| "eval_samples_per_second": 16.973, | |
| "eval_steps_per_second": 0.679, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 59.91, | |
| "step": 300, | |
| "total_flos": 1.0044714081093673e+18, | |
| "train_loss": 0.3854776843388875, | |
| "train_runtime": 7248.8786, | |
| "train_samples_per_second": 5.579, | |
| "train_steps_per_second": 0.041 | |
| } | |
| ], | |
| "max_steps": 300, | |
| "num_train_epochs": 60, | |
| "total_flos": 1.0044714081093673e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |