| { | |
| "best_metric": 0.6111111111111112, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-55-fold1/checkpoint-15", | |
| "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": 0.4722222222222222, | |
| "eval_loss": 1.1111016273498535, | |
| "eval_runtime": 0.4781, | |
| "eval_samples_per_second": 75.296, | |
| "eval_steps_per_second": 4.183, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "eval_accuracy": 0.2222222222222222, | |
| "eval_loss": 1.2066620588302612, | |
| "eval_runtime": 0.4818, | |
| "eval_samples_per_second": 74.722, | |
| "eval_steps_per_second": 4.151, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.1273480653762817, | |
| "eval_runtime": 0.4921, | |
| "eval_samples_per_second": 73.162, | |
| "eval_steps_per_second": 4.065, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.0384465456008911, | |
| "eval_runtime": 0.5089, | |
| "eval_samples_per_second": 70.746, | |
| "eval_steps_per_second": 3.93, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "eval_accuracy": 0.4166666666666667, | |
| "eval_loss": 1.1017414331436157, | |
| "eval_runtime": 0.4898, | |
| "eval_samples_per_second": 73.496, | |
| "eval_steps_per_second": 4.083, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 10.499309539794922, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0728, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.1338366270065308, | |
| "eval_runtime": 0.4969, | |
| "eval_samples_per_second": 72.445, | |
| "eval_steps_per_second": 4.025, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.9428131580352783, | |
| "eval_runtime": 0.4897, | |
| "eval_samples_per_second": 73.508, | |
| "eval_steps_per_second": 4.084, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0236352682113647, | |
| "eval_runtime": 0.4888, | |
| "eval_samples_per_second": 73.642, | |
| "eval_steps_per_second": 4.091, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.950567901134491, | |
| "eval_runtime": 0.4866, | |
| "eval_samples_per_second": 73.986, | |
| "eval_steps_per_second": 4.11, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 9.714285714285714, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9170706272125244, | |
| "eval_runtime": 0.4918, | |
| "eval_samples_per_second": 73.195, | |
| "eval_steps_per_second": 4.066, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.1097838878631592, | |
| "eval_runtime": 0.4974, | |
| "eval_samples_per_second": 72.376, | |
| "eval_steps_per_second": 4.021, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 14.9044189453125, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9628, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9111136198043823, | |
| "eval_runtime": 0.5148, | |
| "eval_samples_per_second": 69.936, | |
| "eval_steps_per_second": 3.885, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.9954362511634827, | |
| "eval_runtime": 0.4915, | |
| "eval_samples_per_second": 73.239, | |
| "eval_steps_per_second": 4.069, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 13.714285714285714, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.1014260053634644, | |
| "eval_runtime": 0.4969, | |
| "eval_samples_per_second": 72.449, | |
| "eval_steps_per_second": 4.025, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.9580910801887512, | |
| "eval_runtime": 0.4921, | |
| "eval_samples_per_second": 73.16, | |
| "eval_steps_per_second": 4.064, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.073473572731018, | |
| "eval_runtime": 0.5076, | |
| "eval_samples_per_second": 70.924, | |
| "eval_steps_per_second": 3.94, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 16.571428571428573, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1480153799057007, | |
| "eval_runtime": 0.4962, | |
| "eval_samples_per_second": 72.557, | |
| "eval_steps_per_second": 4.031, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 8.782094955444336, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.833, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 17.714285714285715, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.0333688259124756, | |
| "eval_runtime": 0.503, | |
| "eval_samples_per_second": 71.571, | |
| "eval_steps_per_second": 3.976, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 0.9553883671760559, | |
| "eval_runtime": 0.496, | |
| "eval_samples_per_second": 72.583, | |
| "eval_steps_per_second": 4.032, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2890479564666748, | |
| "eval_runtime": 0.4855, | |
| "eval_samples_per_second": 74.147, | |
| "eval_steps_per_second": 4.119, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 20.571428571428573, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.3330169916152954, | |
| "eval_runtime": 0.4909, | |
| "eval_samples_per_second": 73.334, | |
| "eval_steps_per_second": 4.074, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 21.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.0785561800003052, | |
| "eval_runtime": 0.4869, | |
| "eval_samples_per_second": 73.944, | |
| "eval_steps_per_second": 4.108, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 9.291950225830078, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7274, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1173081398010254, | |
| "eval_runtime": 0.5033, | |
| "eval_samples_per_second": 71.53, | |
| "eval_steps_per_second": 3.974, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1471468210220337, | |
| "eval_runtime": 0.5065, | |
| "eval_samples_per_second": 71.076, | |
| "eval_steps_per_second": 3.949, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 24.571428571428573, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1779403686523438, | |
| "eval_runtime": 0.5015, | |
| "eval_samples_per_second": 71.791, | |
| "eval_steps_per_second": 3.988, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.2391090393066406, | |
| "eval_runtime": 0.5057, | |
| "eval_samples_per_second": 71.193, | |
| "eval_steps_per_second": 3.955, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.2273061275482178, | |
| "eval_runtime": 0.5056, | |
| "eval_samples_per_second": 71.2, | |
| "eval_steps_per_second": 3.956, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.1947282552719116, | |
| "eval_runtime": 0.509, | |
| "eval_samples_per_second": 70.728, | |
| "eval_steps_per_second": 3.929, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 9.010458946228027, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6321, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.2451523542404175, | |
| "eval_runtime": 0.4965, | |
| "eval_samples_per_second": 72.504, | |
| "eval_steps_per_second": 4.028, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 29.714285714285715, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.1782801151275635, | |
| "eval_runtime": 0.4926, | |
| "eval_samples_per_second": 73.077, | |
| "eval_steps_per_second": 4.06, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.2355453968048096, | |
| "eval_runtime": 0.5004, | |
| "eval_samples_per_second": 71.939, | |
| "eval_steps_per_second": 3.997, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1921230554580688, | |
| "eval_runtime": 0.5173, | |
| "eval_samples_per_second": 69.597, | |
| "eval_steps_per_second": 3.866, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 32.57142857142857, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1681900024414062, | |
| "eval_runtime": 0.5008, | |
| "eval_samples_per_second": 71.881, | |
| "eval_steps_per_second": 3.993, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 33.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.2612859010696411, | |
| "eval_runtime": 0.4966, | |
| "eval_samples_per_second": 72.49, | |
| "eval_steps_per_second": 4.027, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 8.816570281982422, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.5586, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2682926654815674, | |
| "eval_runtime": 0.4966, | |
| "eval_samples_per_second": 72.488, | |
| "eval_steps_per_second": 4.027, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.2235435247421265, | |
| "eval_runtime": 0.5049, | |
| "eval_samples_per_second": 71.307, | |
| "eval_steps_per_second": 3.962, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 36.57142857142857, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2214045524597168, | |
| "eval_runtime": 0.497, | |
| "eval_samples_per_second": 72.433, | |
| "eval_steps_per_second": 4.024, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 37.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.049842357635498, | |
| "eval_runtime": 0.5057, | |
| "eval_samples_per_second": 71.183, | |
| "eval_steps_per_second": 3.955, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.047415018081665, | |
| "eval_runtime": 0.5109, | |
| "eval_samples_per_second": 70.467, | |
| "eval_steps_per_second": 3.915, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 6.760789394378662, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.4814, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2388365268707275, | |
| "eval_runtime": 0.4969, | |
| "eval_samples_per_second": 72.447, | |
| "eval_steps_per_second": 4.025, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.57142857142857, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.2825974225997925, | |
| "eval_runtime": 0.5055, | |
| "eval_samples_per_second": 71.218, | |
| "eval_steps_per_second": 3.957, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 41.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1847288608551025, | |
| "eval_runtime": 0.4981, | |
| "eval_samples_per_second": 72.271, | |
| "eval_steps_per_second": 4.015, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0760149955749512, | |
| "eval_runtime": 0.502, | |
| "eval_samples_per_second": 71.72, | |
| "eval_steps_per_second": 3.984, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.0788402557373047, | |
| "eval_runtime": 0.5036, | |
| "eval_samples_per_second": 71.48, | |
| "eval_steps_per_second": 3.971, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 44.57142857142857, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.089439868927002, | |
| "eval_runtime": 0.5067, | |
| "eval_samples_per_second": 71.042, | |
| "eval_steps_per_second": 3.947, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "grad_norm": 7.363391399383545, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.4638, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.223190426826477, | |
| "eval_runtime": 0.4975, | |
| "eval_samples_per_second": 72.366, | |
| "eval_steps_per_second": 4.02, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 46.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2743028402328491, | |
| "eval_runtime": 0.5057, | |
| "eval_samples_per_second": 71.185, | |
| "eval_steps_per_second": 3.955, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.2029680013656616, | |
| "eval_runtime": 0.5108, | |
| "eval_samples_per_second": 70.475, | |
| "eval_steps_per_second": 3.915, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 48.57142857142857, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.1366175413131714, | |
| "eval_runtime": 0.5136, | |
| "eval_samples_per_second": 70.096, | |
| "eval_steps_per_second": 3.894, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 49.714285714285715, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.0801540613174438, | |
| "eval_runtime": 0.525, | |
| "eval_samples_per_second": 68.567, | |
| "eval_steps_per_second": 3.809, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 50.857142857142854, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.104419231414795, | |
| "eval_runtime": 0.4989, | |
| "eval_samples_per_second": 72.154, | |
| "eval_steps_per_second": 4.009, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 51.42857142857143, | |
| "grad_norm": 5.335033893585205, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3833, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.1678602695465088, | |
| "eval_runtime": 0.5172, | |
| "eval_samples_per_second": 69.6, | |
| "eval_steps_per_second": 3.867, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 52.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.1904979944229126, | |
| "eval_runtime": 0.5075, | |
| "eval_samples_per_second": 70.939, | |
| "eval_steps_per_second": 3.941, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 53.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.2243025302886963, | |
| "eval_runtime": 0.4998, | |
| "eval_samples_per_second": 72.033, | |
| "eval_steps_per_second": 4.002, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 54.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.244490146636963, | |
| "eval_runtime": 0.5033, | |
| "eval_samples_per_second": 71.531, | |
| "eval_steps_per_second": 3.974, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.2267025709152222, | |
| "eval_runtime": 0.5105, | |
| "eval_samples_per_second": 70.515, | |
| "eval_steps_per_second": 3.918, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 56.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.217976689338684, | |
| "eval_runtime": 0.5129, | |
| "eval_samples_per_second": 70.193, | |
| "eval_steps_per_second": 3.9, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "grad_norm": 6.071231365203857, | |
| "learning_rate": 0.0, | |
| "loss": 0.3405, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.215395450592041, | |
| "eval_runtime": 0.5024, | |
| "eval_samples_per_second": 71.656, | |
| "eval_steps_per_second": 3.981, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "step": 100, | |
| "total_flos": 8.766873360020644e+17, | |
| "train_loss": 0.6455910897254944, | |
| "train_runtime": 536.7272, | |
| "train_samples_per_second": 36.89, | |
| "train_steps_per_second": 0.186 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.950567901134491, | |
| "eval_runtime": 0.5606, | |
| "eval_samples_per_second": 64.216, | |
| "eval_steps_per_second": 3.568, | |
| "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": 8.766873360020644e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |