| { | |
| "best_metric": 0.10869565217391304, | |
| "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-3", | |
| "epoch": 34.285714285714285, | |
| "eval_steps": 500, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.86678314208984, | |
| "eval_runtime": 0.6737, | |
| "eval_samples_per_second": 68.283, | |
| "eval_steps_per_second": 4.453, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.8652114868164, | |
| "eval_runtime": 0.6176, | |
| "eval_samples_per_second": 74.476, | |
| "eval_steps_per_second": 4.857, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 114.139, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.86360168457031, | |
| "eval_runtime": 0.6252, | |
| "eval_samples_per_second": 73.581, | |
| "eval_steps_per_second": 4.799, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.86296081542969, | |
| "eval_runtime": 0.6111, | |
| "eval_samples_per_second": 75.27, | |
| "eval_steps_per_second": 4.909, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.86167907714844, | |
| "eval_runtime": 0.6116, | |
| "eval_samples_per_second": 75.206, | |
| "eval_steps_per_second": 4.905, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 113.4957, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.85923767089844, | |
| "eval_runtime": 0.6187, | |
| "eval_samples_per_second": 74.355, | |
| "eval_steps_per_second": 4.849, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.8578872680664, | |
| "eval_runtime": 0.6091, | |
| "eval_samples_per_second": 75.517, | |
| "eval_steps_per_second": 4.925, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.8578109741211, | |
| "eval_runtime": 0.6207, | |
| "eval_samples_per_second": 74.114, | |
| "eval_steps_per_second": 4.834, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 111.7345, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.8550033569336, | |
| "eval_runtime": 0.6176, | |
| "eval_samples_per_second": 74.476, | |
| "eval_steps_per_second": 4.857, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.85313415527344, | |
| "eval_runtime": 0.5966, | |
| "eval_samples_per_second": 77.098, | |
| "eval_steps_per_second": 5.028, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.85196685791016, | |
| "eval_runtime": 0.6032, | |
| "eval_samples_per_second": 76.266, | |
| "eval_steps_per_second": 4.974, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 115.9214, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.84968566894531, | |
| "eval_runtime": 0.5951, | |
| "eval_samples_per_second": 77.294, | |
| "eval_steps_per_second": 5.041, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.8483657836914, | |
| "eval_runtime": 0.6171, | |
| "eval_samples_per_second": 74.538, | |
| "eval_steps_per_second": 4.861, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.84552001953125, | |
| "eval_runtime": 0.6081, | |
| "eval_samples_per_second": 75.641, | |
| "eval_steps_per_second": 4.933, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 1.4583333333333335e-05, | |
| "loss": 112.3215, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.83916473388672, | |
| "eval_runtime": 0.7172, | |
| "eval_samples_per_second": 64.142, | |
| "eval_steps_per_second": 4.183, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.83506774902344, | |
| "eval_runtime": 0.6271, | |
| "eval_samples_per_second": 73.349, | |
| "eval_steps_per_second": 4.784, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.83540344238281, | |
| "eval_runtime": 0.6112, | |
| "eval_samples_per_second": 75.268, | |
| "eval_steps_per_second": 4.909, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 1.25e-05, | |
| "loss": 113.1908, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.83159637451172, | |
| "eval_runtime": 0.6036, | |
| "eval_samples_per_second": 76.204, | |
| "eval_steps_per_second": 4.97, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.82946014404297, | |
| "eval_runtime": 0.6282, | |
| "eval_samples_per_second": 73.23, | |
| "eval_steps_per_second": 4.776, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 114.062, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.82839965820312, | |
| "eval_runtime": 0.5991, | |
| "eval_samples_per_second": 76.778, | |
| "eval_steps_per_second": 5.007, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.8253402709961, | |
| "eval_runtime": 0.5961, | |
| "eval_samples_per_second": 77.162, | |
| "eval_steps_per_second": 5.032, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.82349395751953, | |
| "eval_runtime": 0.7817, | |
| "eval_samples_per_second": 58.847, | |
| "eval_steps_per_second": 3.838, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 114.5312, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.82068634033203, | |
| "eval_runtime": 0.6071, | |
| "eval_samples_per_second": 75.766, | |
| "eval_steps_per_second": 4.941, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.81257629394531, | |
| "eval_runtime": 0.6061, | |
| "eval_samples_per_second": 75.891, | |
| "eval_steps_per_second": 4.949, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.81000518798828, | |
| "eval_runtime": 0.6011, | |
| "eval_samples_per_second": 76.522, | |
| "eval_steps_per_second": 4.991, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 6.25e-06, | |
| "loss": 114.5216, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.80531311035156, | |
| "eval_runtime": 0.5966, | |
| "eval_samples_per_second": 77.098, | |
| "eval_steps_per_second": 5.028, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.80321502685547, | |
| "eval_runtime": 0.6162, | |
| "eval_samples_per_second": 74.657, | |
| "eval_steps_per_second": 4.869, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.803466796875, | |
| "eval_runtime": 0.5991, | |
| "eval_samples_per_second": 76.777, | |
| "eval_steps_per_second": 5.007, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 112.7612, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.7991714477539, | |
| "eval_runtime": 0.6142, | |
| "eval_samples_per_second": 74.9, | |
| "eval_steps_per_second": 4.885, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.7939224243164, | |
| "eval_runtime": 0.6141, | |
| "eval_samples_per_second": 74.902, | |
| "eval_steps_per_second": 4.885, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.79671478271484, | |
| "eval_runtime": 0.6337, | |
| "eval_samples_per_second": 72.594, | |
| "eval_steps_per_second": 4.734, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 114.2748, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.79725646972656, | |
| "eval_runtime": 0.6392, | |
| "eval_samples_per_second": 71.97, | |
| "eval_steps_per_second": 4.694, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.79711151123047, | |
| "eval_runtime": 0.5956, | |
| "eval_samples_per_second": 77.228, | |
| "eval_steps_per_second": 5.037, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.7907943725586, | |
| "eval_runtime": 0.5981, | |
| "eval_samples_per_second": 76.906, | |
| "eval_steps_per_second": 5.016, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 0.0, | |
| "loss": 114.0708, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.79315948486328, | |
| "eval_runtime": 0.5946, | |
| "eval_samples_per_second": 77.358, | |
| "eval_steps_per_second": 5.045, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "step": 120, | |
| "total_flos": 2.0027429927092224e+16, | |
| "train_loss": 113.75203348795573, | |
| "train_runtime": 131.4365, | |
| "train_samples_per_second": 64.822, | |
| "train_steps_per_second": 0.913 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 2.0027429927092224e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |