| { | |
| "best_metric": 0.6111111111111112, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-55-fold5/checkpoint-66", | |
| "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": 0.3055555555555556, | |
| "eval_loss": 1.224039912223816, | |
| "eval_runtime": 0.4999, | |
| "eval_samples_per_second": 72.015, | |
| "eval_steps_per_second": 4.001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "eval_accuracy": 0.3055555555555556, | |
| "eval_loss": 1.2263083457946777, | |
| "eval_runtime": 0.5056, | |
| "eval_samples_per_second": 71.208, | |
| "eval_steps_per_second": 3.956, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.222222924232483, | |
| "eval_runtime": 0.4995, | |
| "eval_samples_per_second": 72.078, | |
| "eval_steps_per_second": 4.004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.1690114736557007, | |
| "eval_runtime": 0.5114, | |
| "eval_samples_per_second": 70.4, | |
| "eval_steps_per_second": 3.911, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.1690934896469116, | |
| "eval_runtime": 0.5013, | |
| "eval_samples_per_second": 71.81, | |
| "eval_steps_per_second": 3.989, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 14.338200569152832, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1249, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.0998698472976685, | |
| "eval_runtime": 0.5067, | |
| "eval_samples_per_second": 71.041, | |
| "eval_steps_per_second": 3.947, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_accuracy": 0.4166666666666667, | |
| "eval_loss": 1.160466194152832, | |
| "eval_runtime": 0.5043, | |
| "eval_samples_per_second": 71.382, | |
| "eval_steps_per_second": 3.966, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4166666666666667, | |
| "eval_loss": 1.191159725189209, | |
| "eval_runtime": 0.5042, | |
| "eval_samples_per_second": 71.4, | |
| "eval_steps_per_second": 3.967, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.1770739555358887, | |
| "eval_runtime": 0.5018, | |
| "eval_samples_per_second": 71.738, | |
| "eval_steps_per_second": 3.985, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 9.714285714285714, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.2369838953018188, | |
| "eval_runtime": 0.5155, | |
| "eval_samples_per_second": 69.832, | |
| "eval_steps_per_second": 3.88, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.2607200145721436, | |
| "eval_runtime": 0.5092, | |
| "eval_samples_per_second": 70.697, | |
| "eval_steps_per_second": 3.928, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 11.004097938537598, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9274, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.2755682468414307, | |
| "eval_runtime": 0.5154, | |
| "eval_samples_per_second": 69.842, | |
| "eval_steps_per_second": 3.88, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.2208017110824585, | |
| "eval_runtime": 0.5003, | |
| "eval_samples_per_second": 71.961, | |
| "eval_steps_per_second": 3.998, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 13.714285714285714, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.3705171346664429, | |
| "eval_runtime": 0.516, | |
| "eval_samples_per_second": 69.762, | |
| "eval_steps_per_second": 3.876, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.21907377243042, | |
| "eval_runtime": 0.4969, | |
| "eval_samples_per_second": 72.448, | |
| "eval_steps_per_second": 4.025, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.3502026796340942, | |
| "eval_runtime": 0.5251, | |
| "eval_samples_per_second": 68.554, | |
| "eval_steps_per_second": 3.809, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 16.571428571428573, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.262834072113037, | |
| "eval_runtime": 0.511, | |
| "eval_samples_per_second": 70.447, | |
| "eval_steps_per_second": 3.914, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 8.800963401794434, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.7889, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 17.714285714285715, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0868184566497803, | |
| "eval_runtime": 0.5072, | |
| "eval_samples_per_second": 70.984, | |
| "eval_steps_per_second": 3.944, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.3982720375061035, | |
| "eval_runtime": 0.5038, | |
| "eval_samples_per_second": 71.454, | |
| "eval_steps_per_second": 3.97, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.2536911964416504, | |
| "eval_runtime": 0.5123, | |
| "eval_samples_per_second": 70.278, | |
| "eval_steps_per_second": 3.904, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 20.571428571428573, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.153983473777771, | |
| "eval_runtime": 0.5038, | |
| "eval_samples_per_second": 71.464, | |
| "eval_steps_per_second": 3.97, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 21.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.2135456800460815, | |
| "eval_runtime": 0.5134, | |
| "eval_samples_per_second": 70.118, | |
| "eval_steps_per_second": 3.895, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 14.012792587280273, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7027, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.4271180629730225, | |
| "eval_runtime": 0.514, | |
| "eval_samples_per_second": 70.044, | |
| "eval_steps_per_second": 3.891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.1827939748764038, | |
| "eval_runtime": 0.4998, | |
| "eval_samples_per_second": 72.026, | |
| "eval_steps_per_second": 4.001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 24.571428571428573, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.2125780582427979, | |
| "eval_runtime": 0.504, | |
| "eval_samples_per_second": 71.427, | |
| "eval_steps_per_second": 3.968, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.4979578256607056, | |
| "eval_runtime": 0.4967, | |
| "eval_samples_per_second": 72.472, | |
| "eval_steps_per_second": 4.026, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.3495233058929443, | |
| "eval_runtime": 0.5247, | |
| "eval_samples_per_second": 68.612, | |
| "eval_steps_per_second": 3.812, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.1969157457351685, | |
| "eval_runtime": 0.5085, | |
| "eval_samples_per_second": 70.796, | |
| "eval_steps_per_second": 3.933, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 8.97653865814209, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6037, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.206262230873108, | |
| "eval_runtime": 0.5003, | |
| "eval_samples_per_second": 71.953, | |
| "eval_steps_per_second": 3.997, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 29.714285714285715, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.311498761177063, | |
| "eval_runtime": 0.5037, | |
| "eval_samples_per_second": 71.469, | |
| "eval_steps_per_second": 3.97, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.172597050666809, | |
| "eval_runtime": 0.5127, | |
| "eval_samples_per_second": 70.221, | |
| "eval_steps_per_second": 3.901, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1872016191482544, | |
| "eval_runtime": 0.504, | |
| "eval_samples_per_second": 71.425, | |
| "eval_steps_per_second": 3.968, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 32.57142857142857, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.2399052381515503, | |
| "eval_runtime": 0.5208, | |
| "eval_samples_per_second": 69.118, | |
| "eval_steps_per_second": 3.84, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 33.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.256636142730713, | |
| "eval_runtime": 0.505, | |
| "eval_samples_per_second": 71.294, | |
| "eval_steps_per_second": 3.961, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 7.767446517944336, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.5147, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.1848201751708984, | |
| "eval_runtime": 0.5003, | |
| "eval_samples_per_second": 71.953, | |
| "eval_steps_per_second": 3.997, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.2614126205444336, | |
| "eval_runtime": 0.5014, | |
| "eval_samples_per_second": 71.793, | |
| "eval_steps_per_second": 3.989, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 36.57142857142857, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.3974634408950806, | |
| "eval_runtime": 0.5092, | |
| "eval_samples_per_second": 70.692, | |
| "eval_steps_per_second": 3.927, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 37.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.4708439111709595, | |
| "eval_runtime": 0.5108, | |
| "eval_samples_per_second": 70.483, | |
| "eval_steps_per_second": 3.916, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.3232808113098145, | |
| "eval_runtime": 0.5032, | |
| "eval_samples_per_second": 71.537, | |
| "eval_steps_per_second": 3.974, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 11.204297065734863, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.4004, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.2993547916412354, | |
| "eval_runtime": 0.5005, | |
| "eval_samples_per_second": 71.925, | |
| "eval_steps_per_second": 3.996, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.57142857142857, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.3582478761672974, | |
| "eval_runtime": 0.5037, | |
| "eval_samples_per_second": 71.476, | |
| "eval_steps_per_second": 3.971, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 41.714285714285715, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.357726812362671, | |
| "eval_runtime": 0.4964, | |
| "eval_samples_per_second": 72.523, | |
| "eval_steps_per_second": 4.029, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.1984590291976929, | |
| "eval_runtime": 0.5023, | |
| "eval_samples_per_second": 71.675, | |
| "eval_steps_per_second": 3.982, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1447665691375732, | |
| "eval_runtime": 0.532, | |
| "eval_samples_per_second": 67.67, | |
| "eval_steps_per_second": 3.759, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 44.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.1713652610778809, | |
| "eval_runtime": 0.535, | |
| "eval_samples_per_second": 67.284, | |
| "eval_steps_per_second": 3.738, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "grad_norm": 7.631770610809326, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.4323, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.3706693649291992, | |
| "eval_runtime": 0.5033, | |
| "eval_samples_per_second": 71.523, | |
| "eval_steps_per_second": 3.974, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 46.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.5476651191711426, | |
| "eval_runtime": 0.5152, | |
| "eval_samples_per_second": 69.869, | |
| "eval_steps_per_second": 3.882, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.4254441261291504, | |
| "eval_runtime": 0.5068, | |
| "eval_samples_per_second": 71.031, | |
| "eval_steps_per_second": 3.946, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 48.57142857142857, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.3030650615692139, | |
| "eval_runtime": 0.5417, | |
| "eval_samples_per_second": 66.453, | |
| "eval_steps_per_second": 3.692, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 49.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.184296727180481, | |
| "eval_runtime": 0.5126, | |
| "eval_samples_per_second": 70.226, | |
| "eval_steps_per_second": 3.901, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 50.857142857142854, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.183534026145935, | |
| "eval_runtime": 0.5116, | |
| "eval_samples_per_second": 70.369, | |
| "eval_steps_per_second": 3.909, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 51.42857142857143, | |
| "grad_norm": 13.801889419555664, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3568, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.239859700202942, | |
| "eval_runtime": 0.5067, | |
| "eval_samples_per_second": 71.052, | |
| "eval_steps_per_second": 3.947, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 52.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.2605737447738647, | |
| "eval_runtime": 0.5239, | |
| "eval_samples_per_second": 68.721, | |
| "eval_steps_per_second": 3.818, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 53.714285714285715, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2996666431427002, | |
| "eval_runtime": 0.5241, | |
| "eval_samples_per_second": 68.683, | |
| "eval_steps_per_second": 3.816, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 54.857142857142854, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.3183656930923462, | |
| "eval_runtime": 0.5059, | |
| "eval_samples_per_second": 71.165, | |
| "eval_steps_per_second": 3.954, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.329425573348999, | |
| "eval_runtime": 0.5234, | |
| "eval_samples_per_second": 68.778, | |
| "eval_steps_per_second": 3.821, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 56.57142857142857, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.333736777305603, | |
| "eval_runtime": 0.5056, | |
| "eval_samples_per_second": 71.206, | |
| "eval_steps_per_second": 3.956, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "grad_norm": 10.05569839477539, | |
| "learning_rate": 0.0, | |
| "loss": 0.3308, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.3367365598678589, | |
| "eval_runtime": 0.5052, | |
| "eval_samples_per_second": 71.264, | |
| "eval_steps_per_second": 3.959, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "step": 100, | |
| "total_flos": 8.766873360020644e+17, | |
| "train_loss": 0.6182592821121216, | |
| "train_runtime": 548.4283, | |
| "train_samples_per_second": 36.103, | |
| "train_steps_per_second": 0.182 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.4708439111709595, | |
| "eval_runtime": 0.5792, | |
| "eval_samples_per_second": 62.159, | |
| "eval_steps_per_second": 3.453, | |
| "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 | |
| } | |