| { | |
| "best_metric": 0.6944444444444444, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-65-fold4/checkpoint-56", | |
| "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": 1.445857048034668, | |
| "eval_runtime": 0.5077, | |
| "eval_samples_per_second": 70.903, | |
| "eval_steps_per_second": 3.939, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.1742717027664185, | |
| "eval_runtime": 0.4968, | |
| "eval_samples_per_second": 72.47, | |
| "eval_steps_per_second": 4.026, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_accuracy": 0.3055555555555556, | |
| "eval_loss": 1.1216062307357788, | |
| "eval_runtime": 0.5007, | |
| "eval_samples_per_second": 71.895, | |
| "eval_steps_per_second": 3.994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.2777777777777778, | |
| "eval_loss": 1.104799747467041, | |
| "eval_runtime": 0.5017, | |
| "eval_samples_per_second": 71.753, | |
| "eval_steps_per_second": 3.986, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0513415336608887, | |
| "eval_runtime": 0.5155, | |
| "eval_samples_per_second": 69.839, | |
| "eval_steps_per_second": 3.88, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 5.540389537811279, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1273, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "eval_accuracy": 0.3333333333333333, | |
| "eval_loss": 1.105465054512024, | |
| "eval_runtime": 0.5011, | |
| "eval_samples_per_second": 71.842, | |
| "eval_steps_per_second": 3.991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.0528624057769775, | |
| "eval_runtime": 0.4964, | |
| "eval_samples_per_second": 72.518, | |
| "eval_steps_per_second": 4.029, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.0445141792297363, | |
| "eval_runtime": 0.4985, | |
| "eval_samples_per_second": 72.223, | |
| "eval_steps_per_second": 4.012, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.0336148738861084, | |
| "eval_runtime": 0.4971, | |
| "eval_samples_per_second": 72.422, | |
| "eval_steps_per_second": 4.023, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 9.714285714285714, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 0.9756557941436768, | |
| "eval_runtime": 0.5034, | |
| "eval_samples_per_second": 71.513, | |
| "eval_steps_per_second": 3.973, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 0.9972283840179443, | |
| "eval_runtime": 0.5111, | |
| "eval_samples_per_second": 70.436, | |
| "eval_steps_per_second": 3.913, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 8.207813262939453, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9616, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 0.9694174528121948, | |
| "eval_runtime": 0.5103, | |
| "eval_samples_per_second": 70.548, | |
| "eval_steps_per_second": 3.919, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 0.9377011060714722, | |
| "eval_runtime": 0.5004, | |
| "eval_samples_per_second": 71.946, | |
| "eval_steps_per_second": 3.997, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 13.714285714285714, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.8974626064300537, | |
| "eval_runtime": 0.5031, | |
| "eval_samples_per_second": 71.559, | |
| "eval_steps_per_second": 3.975, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 0.9969667792320251, | |
| "eval_runtime": 0.5005, | |
| "eval_samples_per_second": 71.932, | |
| "eval_steps_per_second": 3.996, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 0.9321765899658203, | |
| "eval_runtime": 0.4986, | |
| "eval_samples_per_second": 72.198, | |
| "eval_steps_per_second": 4.011, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 16.571428571428573, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 0.98196941614151, | |
| "eval_runtime": 0.4956, | |
| "eval_samples_per_second": 72.635, | |
| "eval_steps_per_second": 4.035, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 8.59610652923584, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.8463, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 17.714285714285715, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1023333072662354, | |
| "eval_runtime": 0.511, | |
| "eval_samples_per_second": 70.449, | |
| "eval_steps_per_second": 3.914, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.108933925628662, | |
| "eval_runtime": 0.5008, | |
| "eval_samples_per_second": 71.88, | |
| "eval_steps_per_second": 3.993, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.9416821002960205, | |
| "eval_runtime": 0.5058, | |
| "eval_samples_per_second": 71.178, | |
| "eval_steps_per_second": 3.954, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 20.571428571428573, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 0.8424234390258789, | |
| "eval_runtime": 0.5085, | |
| "eval_samples_per_second": 70.798, | |
| "eval_steps_per_second": 3.933, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 21.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.8668188452720642, | |
| "eval_runtime": 0.5061, | |
| "eval_samples_per_second": 71.134, | |
| "eval_steps_per_second": 3.952, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 8.356954574584961, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7082, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.976749837398529, | |
| "eval_runtime": 0.5153, | |
| "eval_samples_per_second": 69.865, | |
| "eval_steps_per_second": 3.881, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.8742673397064209, | |
| "eval_runtime": 0.4997, | |
| "eval_samples_per_second": 72.044, | |
| "eval_steps_per_second": 4.002, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 24.571428571428573, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.7944715023040771, | |
| "eval_runtime": 0.5056, | |
| "eval_samples_per_second": 71.198, | |
| "eval_steps_per_second": 3.955, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 0.9245880842208862, | |
| "eval_runtime": 0.4998, | |
| "eval_samples_per_second": 72.036, | |
| "eval_steps_per_second": 4.002, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2622060775756836, | |
| "eval_runtime": 0.5133, | |
| "eval_samples_per_second": 70.137, | |
| "eval_steps_per_second": 3.897, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 0.7754104733467102, | |
| "eval_runtime": 0.5146, | |
| "eval_samples_per_second": 69.96, | |
| "eval_steps_per_second": 3.887, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 12.24124526977539, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6413, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 0.7375420928001404, | |
| "eval_runtime": 0.5005, | |
| "eval_samples_per_second": 71.927, | |
| "eval_steps_per_second": 3.996, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 29.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.0095242261886597, | |
| "eval_runtime": 0.5246, | |
| "eval_samples_per_second": 68.629, | |
| "eval_steps_per_second": 3.813, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.080599308013916, | |
| "eval_runtime": 0.4975, | |
| "eval_samples_per_second": 72.359, | |
| "eval_steps_per_second": 4.02, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6944444444444444, | |
| "eval_loss": 0.741450846195221, | |
| "eval_runtime": 0.4991, | |
| "eval_samples_per_second": 72.126, | |
| "eval_steps_per_second": 4.007, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 32.57142857142857, | |
| "eval_accuracy": 0.6944444444444444, | |
| "eval_loss": 0.7523214221000671, | |
| "eval_runtime": 0.5087, | |
| "eval_samples_per_second": 70.765, | |
| "eval_steps_per_second": 3.931, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 33.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9505912065505981, | |
| "eval_runtime": 0.4968, | |
| "eval_samples_per_second": 72.458, | |
| "eval_steps_per_second": 4.025, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 14.471763610839844, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.5256, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9487402439117432, | |
| "eval_runtime": 0.4978, | |
| "eval_samples_per_second": 72.325, | |
| "eval_steps_per_second": 4.018, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.894493818283081, | |
| "eval_runtime": 0.5098, | |
| "eval_samples_per_second": 70.609, | |
| "eval_steps_per_second": 3.923, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 36.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9072532653808594, | |
| "eval_runtime": 0.5009, | |
| "eval_samples_per_second": 71.866, | |
| "eval_steps_per_second": 3.993, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 37.714285714285715, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.9393937587738037, | |
| "eval_runtime": 0.5098, | |
| "eval_samples_per_second": 70.62, | |
| "eval_steps_per_second": 3.923, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.9062364101409912, | |
| "eval_runtime": 0.5034, | |
| "eval_samples_per_second": 71.52, | |
| "eval_steps_per_second": 3.973, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 10.791825294494629, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.4509, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.8908358812332153, | |
| "eval_runtime": 0.5024, | |
| "eval_samples_per_second": 71.66, | |
| "eval_steps_per_second": 3.981, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.8960464000701904, | |
| "eval_runtime": 0.5032, | |
| "eval_samples_per_second": 71.544, | |
| "eval_steps_per_second": 3.975, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 41.714285714285715, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.9506352543830872, | |
| "eval_runtime": 0.4987, | |
| "eval_samples_per_second": 72.195, | |
| "eval_steps_per_second": 4.011, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0018254518508911, | |
| "eval_runtime": 0.5, | |
| "eval_samples_per_second": 71.999, | |
| "eval_steps_per_second": 4.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9851914644241333, | |
| "eval_runtime": 0.4938, | |
| "eval_samples_per_second": 72.909, | |
| "eval_steps_per_second": 4.05, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 44.57142857142857, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.004512071609497, | |
| "eval_runtime": 0.4992, | |
| "eval_samples_per_second": 72.118, | |
| "eval_steps_per_second": 4.007, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "grad_norm": 5.812440395355225, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3865, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.0983620882034302, | |
| "eval_runtime": 0.5042, | |
| "eval_samples_per_second": 71.395, | |
| "eval_steps_per_second": 3.966, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 46.857142857142854, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1892544031143188, | |
| "eval_runtime": 0.502, | |
| "eval_samples_per_second": 71.71, | |
| "eval_steps_per_second": 3.984, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.206595540046692, | |
| "eval_runtime": 0.4955, | |
| "eval_samples_per_second": 72.66, | |
| "eval_steps_per_second": 4.037, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 48.57142857142857, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1625385284423828, | |
| "eval_runtime": 0.5187, | |
| "eval_samples_per_second": 69.4, | |
| "eval_steps_per_second": 3.856, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 49.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0752768516540527, | |
| "eval_runtime": 0.4964, | |
| "eval_samples_per_second": 72.526, | |
| "eval_steps_per_second": 4.029, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 50.857142857142854, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0609641075134277, | |
| "eval_runtime": 0.5036, | |
| "eval_samples_per_second": 71.484, | |
| "eval_steps_per_second": 3.971, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 51.42857142857143, | |
| "grad_norm": 5.6921234130859375, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3497, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.0844407081604004, | |
| "eval_runtime": 0.4985, | |
| "eval_samples_per_second": 72.21, | |
| "eval_steps_per_second": 4.012, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 52.57142857142857, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1055421829223633, | |
| "eval_runtime": 0.498, | |
| "eval_samples_per_second": 72.29, | |
| "eval_steps_per_second": 4.016, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 53.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.112227201461792, | |
| "eval_runtime": 0.5125, | |
| "eval_samples_per_second": 70.248, | |
| "eval_steps_per_second": 3.903, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 54.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.1042193174362183, | |
| "eval_runtime": 0.4988, | |
| "eval_samples_per_second": 72.168, | |
| "eval_steps_per_second": 4.009, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.0855423212051392, | |
| "eval_runtime": 0.5021, | |
| "eval_samples_per_second": 71.702, | |
| "eval_steps_per_second": 3.983, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 56.57142857142857, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.078481912612915, | |
| "eval_runtime": 0.4953, | |
| "eval_samples_per_second": 72.687, | |
| "eval_steps_per_second": 4.038, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "grad_norm": 5.783181190490723, | |
| "learning_rate": 0.0, | |
| "loss": 0.3196, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.075089454650879, | |
| "eval_runtime": 0.5027, | |
| "eval_samples_per_second": 71.607, | |
| "eval_steps_per_second": 3.978, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "step": 100, | |
| "total_flos": 8.899329213047992e+17, | |
| "train_loss": 0.6317082977294922, | |
| "train_runtime": 555.5566, | |
| "train_samples_per_second": 36.18, | |
| "train_steps_per_second": 0.18 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.6944444444444444, | |
| "eval_loss": 0.741450846195221, | |
| "eval_runtime": 0.5686, | |
| "eval_samples_per_second": 63.311, | |
| "eval_steps_per_second": 3.517, | |
| "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 | |
| } | |