| { | |
| "best_metric": 0.5555555555555556, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-65-fold5/checkpoint-49", | |
| "epoch": 57.142857142857146, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5714285714285714, | |
| "eval_accuracy": 0.3333333333333333, | |
| "eval_loss": 1.1680210828781128, | |
| "eval_runtime": 0.4946, | |
| "eval_samples_per_second": 72.781, | |
| "eval_steps_per_second": 4.043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "eval_accuracy": 0.19444444444444445, | |
| "eval_loss": 1.2100130319595337, | |
| "eval_runtime": 0.501, | |
| "eval_samples_per_second": 71.859, | |
| "eval_steps_per_second": 3.992, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_accuracy": 0.2777777777777778, | |
| "eval_loss": 1.3667227029800415, | |
| "eval_runtime": 0.5004, | |
| "eval_samples_per_second": 71.947, | |
| "eval_steps_per_second": 3.997, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.1207661628723145, | |
| "eval_runtime": 0.5021, | |
| "eval_samples_per_second": 71.702, | |
| "eval_steps_per_second": 3.983, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "eval_accuracy": 0.3611111111111111, | |
| "eval_loss": 1.1168370246887207, | |
| "eval_runtime": 0.4968, | |
| "eval_samples_per_second": 72.469, | |
| "eval_steps_per_second": 4.026, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 6.683154106140137, | |
| "learning_rate": 5e-05, | |
| "loss": 1.132, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "eval_accuracy": 0.2777777777777778, | |
| "eval_loss": 1.4031130075454712, | |
| "eval_runtime": 0.5023, | |
| "eval_samples_per_second": 71.666, | |
| "eval_steps_per_second": 3.981, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_accuracy": 0.3333333333333333, | |
| "eval_loss": 1.2012299299240112, | |
| "eval_runtime": 0.5071, | |
| "eval_samples_per_second": 70.991, | |
| "eval_steps_per_second": 3.944, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.2777777777777778, | |
| "eval_loss": 1.235305666923523, | |
| "eval_runtime": 0.5043, | |
| "eval_samples_per_second": 71.382, | |
| "eval_steps_per_second": 3.966, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "eval_accuracy": 0.3055555555555556, | |
| "eval_loss": 1.2098990678787231, | |
| "eval_runtime": 0.4999, | |
| "eval_samples_per_second": 72.015, | |
| "eval_steps_per_second": 4.001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 9.714285714285714, | |
| "eval_accuracy": 0.3611111111111111, | |
| "eval_loss": 1.094165325164795, | |
| "eval_runtime": 0.4945, | |
| "eval_samples_per_second": 72.806, | |
| "eval_steps_per_second": 4.045, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.1301040649414062, | |
| "eval_runtime": 0.5059, | |
| "eval_samples_per_second": 71.155, | |
| "eval_steps_per_second": 3.953, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 5.605182647705078, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.0271, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4166666666666667, | |
| "eval_loss": 1.0590957403182983, | |
| "eval_runtime": 0.5044, | |
| "eval_samples_per_second": 71.379, | |
| "eval_steps_per_second": 3.965, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.0648216009140015, | |
| "eval_runtime": 0.4938, | |
| "eval_samples_per_second": 72.907, | |
| "eval_steps_per_second": 4.05, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 13.714285714285714, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.1125401258468628, | |
| "eval_runtime": 0.5032, | |
| "eval_samples_per_second": 71.547, | |
| "eval_steps_per_second": 3.975, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.1097133159637451, | |
| "eval_runtime": 0.4994, | |
| "eval_samples_per_second": 72.091, | |
| "eval_steps_per_second": 4.005, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.0615904331207275, | |
| "eval_runtime": 0.5121, | |
| "eval_samples_per_second": 70.303, | |
| "eval_steps_per_second": 3.906, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 16.571428571428573, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.0283960103988647, | |
| "eval_runtime": 0.491, | |
| "eval_samples_per_second": 73.318, | |
| "eval_steps_per_second": 4.073, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 7.310097694396973, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.9507, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 17.714285714285715, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0291134119033813, | |
| "eval_runtime": 0.5099, | |
| "eval_samples_per_second": 70.597, | |
| "eval_steps_per_second": 3.922, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.0692261457443237, | |
| "eval_runtime": 0.5008, | |
| "eval_samples_per_second": 71.89, | |
| "eval_steps_per_second": 3.994, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1152749061584473, | |
| "eval_runtime": 0.5058, | |
| "eval_samples_per_second": 71.18, | |
| "eval_steps_per_second": 3.954, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 20.571428571428573, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.1719120740890503, | |
| "eval_runtime": 0.4946, | |
| "eval_samples_per_second": 72.781, | |
| "eval_steps_per_second": 4.043, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 21.714285714285715, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.0160677433013916, | |
| "eval_runtime": 0.4941, | |
| "eval_samples_per_second": 72.86, | |
| "eval_steps_per_second": 4.048, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 9.8089599609375, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.1360970735549927, | |
| "eval_runtime": 0.4957, | |
| "eval_samples_per_second": 72.632, | |
| "eval_steps_per_second": 4.035, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.32765531539917, | |
| "eval_runtime": 0.4996, | |
| "eval_samples_per_second": 72.064, | |
| "eval_steps_per_second": 4.004, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 24.571428571428573, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1330523490905762, | |
| "eval_runtime": 0.4991, | |
| "eval_samples_per_second": 72.126, | |
| "eval_steps_per_second": 4.007, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.0659008026123047, | |
| "eval_runtime": 0.4989, | |
| "eval_samples_per_second": 72.166, | |
| "eval_steps_per_second": 4.009, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.13089120388031, | |
| "eval_runtime": 0.5021, | |
| "eval_samples_per_second": 71.693, | |
| "eval_steps_per_second": 3.983, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1241053342819214, | |
| "eval_runtime": 0.4973, | |
| "eval_samples_per_second": 72.393, | |
| "eval_steps_per_second": 4.022, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 10.979926109313965, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.7175, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.137054443359375, | |
| "eval_runtime": 0.5113, | |
| "eval_samples_per_second": 70.402, | |
| "eval_steps_per_second": 3.911, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 29.714285714285715, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.092840552330017, | |
| "eval_runtime": 0.5013, | |
| "eval_samples_per_second": 71.82, | |
| "eval_steps_per_second": 3.99, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.212934136390686, | |
| "eval_runtime": 0.5136, | |
| "eval_samples_per_second": 70.096, | |
| "eval_steps_per_second": 3.894, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0321365594863892, | |
| "eval_runtime": 0.5074, | |
| "eval_samples_per_second": 70.956, | |
| "eval_steps_per_second": 3.942, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 32.57142857142857, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0809351205825806, | |
| "eval_runtime": 0.5096, | |
| "eval_samples_per_second": 70.644, | |
| "eval_steps_per_second": 3.925, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 33.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 0.9813452959060669, | |
| "eval_runtime": 0.5153, | |
| "eval_samples_per_second": 69.863, | |
| "eval_steps_per_second": 3.881, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 8.222463607788086, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.6766, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0616748332977295, | |
| "eval_runtime": 0.497, | |
| "eval_samples_per_second": 72.432, | |
| "eval_steps_per_second": 4.024, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 0.9617779850959778, | |
| "eval_runtime": 0.501, | |
| "eval_samples_per_second": 71.859, | |
| "eval_steps_per_second": 3.992, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 36.57142857142857, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.9541198015213013, | |
| "eval_runtime": 0.4956, | |
| "eval_samples_per_second": 72.633, | |
| "eval_steps_per_second": 4.035, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 37.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 0.96888667345047, | |
| "eval_runtime": 0.5032, | |
| "eval_samples_per_second": 71.545, | |
| "eval_steps_per_second": 3.975, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1063470840454102, | |
| "eval_runtime": 0.508, | |
| "eval_samples_per_second": 70.869, | |
| "eval_steps_per_second": 3.937, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 14.340904235839844, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.5934, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0138646364212036, | |
| "eval_runtime": 0.4977, | |
| "eval_samples_per_second": 72.328, | |
| "eval_steps_per_second": 4.018, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.57142857142857, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0087409019470215, | |
| "eval_runtime": 0.4952, | |
| "eval_samples_per_second": 72.703, | |
| "eval_steps_per_second": 4.039, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 41.714285714285715, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0309183597564697, | |
| "eval_runtime": 0.4982, | |
| "eval_samples_per_second": 72.263, | |
| "eval_steps_per_second": 4.015, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0635802745819092, | |
| "eval_runtime": 0.503, | |
| "eval_samples_per_second": 71.572, | |
| "eval_steps_per_second": 3.976, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1057071685791016, | |
| "eval_runtime": 0.5162, | |
| "eval_samples_per_second": 69.743, | |
| "eval_steps_per_second": 3.875, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 44.57142857142857, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.101549744606018, | |
| "eval_runtime": 0.4942, | |
| "eval_samples_per_second": 72.838, | |
| "eval_steps_per_second": 4.047, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "grad_norm": 5.81636381149292, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.4926, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0937837362289429, | |
| "eval_runtime": 0.496, | |
| "eval_samples_per_second": 72.574, | |
| "eval_steps_per_second": 4.032, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 46.857142857142854, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0807102918624878, | |
| "eval_runtime": 0.5009, | |
| "eval_samples_per_second": 71.866, | |
| "eval_steps_per_second": 3.993, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.1275465488433838, | |
| "eval_runtime": 0.498, | |
| "eval_samples_per_second": 72.29, | |
| "eval_steps_per_second": 4.016, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 48.57142857142857, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.1604024171829224, | |
| "eval_runtime": 0.5034, | |
| "eval_samples_per_second": 71.51, | |
| "eval_steps_per_second": 3.973, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 49.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.1295835971832275, | |
| "eval_runtime": 0.5029, | |
| "eval_samples_per_second": 71.586, | |
| "eval_steps_per_second": 3.977, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 50.857142857142854, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0748000144958496, | |
| "eval_runtime": 0.496, | |
| "eval_samples_per_second": 72.581, | |
| "eval_steps_per_second": 4.032, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 51.42857142857143, | |
| "grad_norm": 10.695130348205566, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.4964, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.071612000465393, | |
| "eval_runtime": 0.5092, | |
| "eval_samples_per_second": 70.693, | |
| "eval_steps_per_second": 3.927, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 52.57142857142857, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0780364274978638, | |
| "eval_runtime": 0.5025, | |
| "eval_samples_per_second": 71.641, | |
| "eval_steps_per_second": 3.98, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 53.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0754601955413818, | |
| "eval_runtime": 0.5028, | |
| "eval_samples_per_second": 71.6, | |
| "eval_steps_per_second": 3.978, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 54.857142857142854, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0680195093154907, | |
| "eval_runtime": 0.5096, | |
| "eval_samples_per_second": 70.642, | |
| "eval_steps_per_second": 3.925, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.06763756275177, | |
| "eval_runtime": 0.4939, | |
| "eval_samples_per_second": 72.882, | |
| "eval_steps_per_second": 4.049, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 56.57142857142857, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0691522359848022, | |
| "eval_runtime": 0.5115, | |
| "eval_samples_per_second": 70.386, | |
| "eval_steps_per_second": 3.91, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "grad_norm": 5.480774402618408, | |
| "learning_rate": 0.0, | |
| "loss": 0.404, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0692094564437866, | |
| "eval_runtime": 0.4959, | |
| "eval_samples_per_second": 72.589, | |
| "eval_steps_per_second": 4.033, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "step": 100, | |
| "total_flos": 8.899329213047992e+17, | |
| "train_loss": 0.729051251411438, | |
| "train_runtime": 547.3778, | |
| "train_samples_per_second": 36.721, | |
| "train_steps_per_second": 0.183 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1241053342819214, | |
| "eval_runtime": 0.5708, | |
| "eval_samples_per_second": 63.071, | |
| "eval_steps_per_second": 3.504, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.899329213047992e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |