| { |
| "best_metric": 0.9534883720930233, |
| "best_model_checkpoint": "beit-base-patch16-224-75-fold3/checkpoint-60", |
| "epoch": 100.0, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.5222999453544617, |
| "eval_runtime": 0.6752, |
| "eval_samples_per_second": 63.685, |
| "eval_steps_per_second": 2.962, |
| "step": 2 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7906976744186046, |
| "eval_loss": 0.5170534253120422, |
| "eval_runtime": 0.6927, |
| "eval_samples_per_second": 62.08, |
| "eval_steps_per_second": 2.887, |
| "step": 4 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7906976744186046, |
| "eval_loss": 0.5562183260917664, |
| "eval_runtime": 0.6729, |
| "eval_samples_per_second": 63.902, |
| "eval_steps_per_second": 2.972, |
| "step": 6 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7906976744186046, |
| "eval_loss": 0.5031919479370117, |
| "eval_runtime": 0.6534, |
| "eval_samples_per_second": 65.807, |
| "eval_steps_per_second": 3.061, |
| "step": 8 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 6.026668548583984, |
| "learning_rate": 2.5e-05, |
| "loss": 0.5026, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7906976744186046, |
| "eval_loss": 0.46356117725372314, |
| "eval_runtime": 0.6584, |
| "eval_samples_per_second": 65.313, |
| "eval_steps_per_second": 3.038, |
| "step": 10 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.4142707884311676, |
| "eval_runtime": 0.6556, |
| "eval_samples_per_second": 65.584, |
| "eval_steps_per_second": 3.05, |
| "step": 12 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.43381455540657043, |
| "eval_runtime": 0.6605, |
| "eval_samples_per_second": 65.106, |
| "eval_steps_per_second": 3.028, |
| "step": 14 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.44713011384010315, |
| "eval_runtime": 0.6656, |
| "eval_samples_per_second": 64.6, |
| "eval_steps_per_second": 3.005, |
| "step": 16 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.3881673514842987, |
| "eval_runtime": 0.6712, |
| "eval_samples_per_second": 64.069, |
| "eval_steps_per_second": 2.98, |
| "step": 18 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 5.344664573669434, |
| "learning_rate": 5e-05, |
| "loss": 0.3578, |
| "step": 20 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.3486923575401306, |
| "eval_runtime": 0.6747, |
| "eval_samples_per_second": 63.732, |
| "eval_steps_per_second": 2.964, |
| "step": 20 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.39745840430259705, |
| "eval_runtime": 0.6591, |
| "eval_samples_per_second": 65.239, |
| "eval_steps_per_second": 3.034, |
| "step": 22 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.34969720244407654, |
| "eval_runtime": 0.6646, |
| "eval_samples_per_second": 64.697, |
| "eval_steps_per_second": 3.009, |
| "step": 24 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.4257439076900482, |
| "eval_runtime": 0.6565, |
| "eval_samples_per_second": 65.502, |
| "eval_steps_per_second": 3.047, |
| "step": 26 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.2964034080505371, |
| "eval_runtime": 0.6633, |
| "eval_samples_per_second": 64.831, |
| "eval_steps_per_second": 3.015, |
| "step": 28 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 3.685264825820923, |
| "learning_rate": 4.722222222222222e-05, |
| "loss": 0.322, |
| "step": 30 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.46661457419395447, |
| "eval_runtime": 0.6576, |
| "eval_samples_per_second": 65.394, |
| "eval_steps_per_second": 3.042, |
| "step": 30 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.7906976744186046, |
| "eval_loss": 0.3815382719039917, |
| "eval_runtime": 0.66, |
| "eval_samples_per_second": 65.155, |
| "eval_steps_per_second": 3.03, |
| "step": 32 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.2858645021915436, |
| "eval_runtime": 0.6565, |
| "eval_samples_per_second": 65.496, |
| "eval_steps_per_second": 3.046, |
| "step": 34 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.599475085735321, |
| "eval_runtime": 0.656, |
| "eval_samples_per_second": 65.549, |
| "eval_steps_per_second": 3.049, |
| "step": 36 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.4421311616897583, |
| "eval_runtime": 0.6655, |
| "eval_samples_per_second": 64.618, |
| "eval_steps_per_second": 3.005, |
| "step": 38 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 13.718052864074707, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.2983, |
| "step": 40 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.2856900095939636, |
| "eval_runtime": 0.6573, |
| "eval_samples_per_second": 65.418, |
| "eval_steps_per_second": 3.043, |
| "step": 40 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.39626941084861755, |
| "eval_runtime": 0.6586, |
| "eval_samples_per_second": 65.293, |
| "eval_steps_per_second": 3.037, |
| "step": 42 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.27751147747039795, |
| "eval_runtime": 0.6592, |
| "eval_samples_per_second": 65.234, |
| "eval_steps_per_second": 3.034, |
| "step": 44 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_accuracy": 0.7441860465116279, |
| "eval_loss": 0.47633451223373413, |
| "eval_runtime": 0.6594, |
| "eval_samples_per_second": 65.209, |
| "eval_steps_per_second": 3.033, |
| "step": 46 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.278869092464447, |
| "eval_runtime": 0.6553, |
| "eval_samples_per_second": 65.618, |
| "eval_steps_per_second": 3.052, |
| "step": 48 |
| }, |
| { |
| "epoch": 25.0, |
| "grad_norm": 5.3918375968933105, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.2545, |
| "step": 50 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.35964033007621765, |
| "eval_runtime": 0.6525, |
| "eval_samples_per_second": 65.903, |
| "eval_steps_per_second": 3.065, |
| "step": 50 |
| }, |
| { |
| "epoch": 26.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.244691863656044, |
| "eval_runtime": 0.6575, |
| "eval_samples_per_second": 65.403, |
| "eval_steps_per_second": 3.042, |
| "step": 52 |
| }, |
| { |
| "epoch": 27.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.472500205039978, |
| "eval_runtime": 0.6637, |
| "eval_samples_per_second": 64.787, |
| "eval_steps_per_second": 3.013, |
| "step": 54 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.3388884663581848, |
| "eval_runtime": 0.6624, |
| "eval_samples_per_second": 64.913, |
| "eval_steps_per_second": 3.019, |
| "step": 56 |
| }, |
| { |
| "epoch": 29.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.347235769033432, |
| "eval_runtime": 0.6646, |
| "eval_samples_per_second": 64.703, |
| "eval_steps_per_second": 3.009, |
| "step": 58 |
| }, |
| { |
| "epoch": 30.0, |
| "grad_norm": 3.050729274749756, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.1914, |
| "step": 60 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_accuracy": 0.9534883720930233, |
| "eval_loss": 0.33263495564460754, |
| "eval_runtime": 0.6637, |
| "eval_samples_per_second": 64.787, |
| "eval_steps_per_second": 3.013, |
| "step": 60 |
| }, |
| { |
| "epoch": 31.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.2856019139289856, |
| "eval_runtime": 0.6615, |
| "eval_samples_per_second": 65.005, |
| "eval_steps_per_second": 3.023, |
| "step": 62 |
| }, |
| { |
| "epoch": 32.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.2856709957122803, |
| "eval_runtime": 0.6717, |
| "eval_samples_per_second": 64.019, |
| "eval_steps_per_second": 2.978, |
| "step": 64 |
| }, |
| { |
| "epoch": 33.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.2459973841905594, |
| "eval_runtime": 0.6589, |
| "eval_samples_per_second": 65.26, |
| "eval_steps_per_second": 3.035, |
| "step": 66 |
| }, |
| { |
| "epoch": 34.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.5096917152404785, |
| "eval_runtime": 0.6589, |
| "eval_samples_per_second": 65.262, |
| "eval_steps_per_second": 3.035, |
| "step": 68 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 5.152686595916748, |
| "learning_rate": 3.611111111111111e-05, |
| "loss": 0.1782, |
| "step": 70 |
| }, |
| { |
| "epoch": 35.0, |
| "eval_accuracy": 0.9534883720930233, |
| "eval_loss": 0.25028589367866516, |
| "eval_runtime": 0.6619, |
| "eval_samples_per_second": 64.961, |
| "eval_steps_per_second": 3.021, |
| "step": 70 |
| }, |
| { |
| "epoch": 36.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.2337980419397354, |
| "eval_runtime": 0.6709, |
| "eval_samples_per_second": 64.089, |
| "eval_steps_per_second": 2.981, |
| "step": 72 |
| }, |
| { |
| "epoch": 37.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.4161434471607208, |
| "eval_runtime": 0.6566, |
| "eval_samples_per_second": 65.491, |
| "eval_steps_per_second": 3.046, |
| "step": 74 |
| }, |
| { |
| "epoch": 38.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.35219722986221313, |
| "eval_runtime": 0.6615, |
| "eval_samples_per_second": 65.008, |
| "eval_steps_per_second": 3.024, |
| "step": 76 |
| }, |
| { |
| "epoch": 39.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.25664079189300537, |
| "eval_runtime": 0.667, |
| "eval_samples_per_second": 64.469, |
| "eval_steps_per_second": 2.999, |
| "step": 78 |
| }, |
| { |
| "epoch": 40.0, |
| "grad_norm": 4.396425247192383, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.1435, |
| "step": 80 |
| }, |
| { |
| "epoch": 40.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.2657725512981415, |
| "eval_runtime": 0.6625, |
| "eval_samples_per_second": 64.903, |
| "eval_steps_per_second": 3.019, |
| "step": 80 |
| }, |
| { |
| "epoch": 41.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.21968156099319458, |
| "eval_runtime": 0.6594, |
| "eval_samples_per_second": 65.21, |
| "eval_steps_per_second": 3.033, |
| "step": 82 |
| }, |
| { |
| "epoch": 42.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.21999044716358185, |
| "eval_runtime": 0.6789, |
| "eval_samples_per_second": 63.342, |
| "eval_steps_per_second": 2.946, |
| "step": 84 |
| }, |
| { |
| "epoch": 43.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.21671727299690247, |
| "eval_runtime": 0.663, |
| "eval_samples_per_second": 64.852, |
| "eval_steps_per_second": 3.016, |
| "step": 86 |
| }, |
| { |
| "epoch": 44.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.390542596578598, |
| "eval_runtime": 0.6627, |
| "eval_samples_per_second": 64.884, |
| "eval_steps_per_second": 3.018, |
| "step": 88 |
| }, |
| { |
| "epoch": 45.0, |
| "grad_norm": 3.8318026065826416, |
| "learning_rate": 3.055555555555556e-05, |
| "loss": 0.1131, |
| "step": 90 |
| }, |
| { |
| "epoch": 45.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.5500655174255371, |
| "eval_runtime": 0.6571, |
| "eval_samples_per_second": 65.435, |
| "eval_steps_per_second": 3.043, |
| "step": 90 |
| }, |
| { |
| "epoch": 46.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.5251295566558838, |
| "eval_runtime": 0.6587, |
| "eval_samples_per_second": 65.283, |
| "eval_steps_per_second": 3.036, |
| "step": 92 |
| }, |
| { |
| "epoch": 47.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.42070817947387695, |
| "eval_runtime": 0.6596, |
| "eval_samples_per_second": 65.186, |
| "eval_steps_per_second": 3.032, |
| "step": 94 |
| }, |
| { |
| "epoch": 48.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.3180684745311737, |
| "eval_runtime": 0.6608, |
| "eval_samples_per_second": 65.069, |
| "eval_steps_per_second": 3.026, |
| "step": 96 |
| }, |
| { |
| "epoch": 49.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.40588662028312683, |
| "eval_runtime": 0.6641, |
| "eval_samples_per_second": 64.75, |
| "eval_steps_per_second": 3.012, |
| "step": 98 |
| }, |
| { |
| "epoch": 50.0, |
| "grad_norm": 2.432298421859741, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.1397, |
| "step": 100 |
| }, |
| { |
| "epoch": 50.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.3060733675956726, |
| "eval_runtime": 0.6579, |
| "eval_samples_per_second": 65.355, |
| "eval_steps_per_second": 3.04, |
| "step": 100 |
| }, |
| { |
| "epoch": 51.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.2824840545654297, |
| "eval_runtime": 0.6632, |
| "eval_samples_per_second": 64.833, |
| "eval_steps_per_second": 3.015, |
| "step": 102 |
| }, |
| { |
| "epoch": 52.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.2885623276233673, |
| "eval_runtime": 0.6776, |
| "eval_samples_per_second": 63.462, |
| "eval_steps_per_second": 2.952, |
| "step": 104 |
| }, |
| { |
| "epoch": 53.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3140006959438324, |
| "eval_runtime": 0.6937, |
| "eval_samples_per_second": 61.988, |
| "eval_steps_per_second": 2.883, |
| "step": 106 |
| }, |
| { |
| "epoch": 54.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3363128900527954, |
| "eval_runtime": 0.6843, |
| "eval_samples_per_second": 62.838, |
| "eval_steps_per_second": 2.923, |
| "step": 108 |
| }, |
| { |
| "epoch": 55.0, |
| "grad_norm": 3.548211097717285, |
| "learning_rate": 2.5e-05, |
| "loss": 0.1048, |
| "step": 110 |
| }, |
| { |
| "epoch": 55.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.3387868404388428, |
| "eval_runtime": 0.6898, |
| "eval_samples_per_second": 62.34, |
| "eval_steps_per_second": 2.9, |
| "step": 110 |
| }, |
| { |
| "epoch": 56.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3391130566596985, |
| "eval_runtime": 0.6815, |
| "eval_samples_per_second": 63.093, |
| "eval_steps_per_second": 2.935, |
| "step": 112 |
| }, |
| { |
| "epoch": 57.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.39265239238739014, |
| "eval_runtime": 0.6937, |
| "eval_samples_per_second": 61.986, |
| "eval_steps_per_second": 2.883, |
| "step": 114 |
| }, |
| { |
| "epoch": 58.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.37986284494400024, |
| "eval_runtime": 0.6684, |
| "eval_samples_per_second": 64.332, |
| "eval_steps_per_second": 2.992, |
| "step": 116 |
| }, |
| { |
| "epoch": 59.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.5491195321083069, |
| "eval_runtime": 0.6948, |
| "eval_samples_per_second": 61.891, |
| "eval_steps_per_second": 2.879, |
| "step": 118 |
| }, |
| { |
| "epoch": 60.0, |
| "grad_norm": 6.060695648193359, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.1013, |
| "step": 120 |
| }, |
| { |
| "epoch": 60.0, |
| "eval_accuracy": 0.813953488372093, |
| "eval_loss": 0.6218406558036804, |
| "eval_runtime": 0.6863, |
| "eval_samples_per_second": 62.654, |
| "eval_steps_per_second": 2.914, |
| "step": 120 |
| }, |
| { |
| "epoch": 61.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.4467184841632843, |
| "eval_runtime": 0.6972, |
| "eval_samples_per_second": 61.675, |
| "eval_steps_per_second": 2.869, |
| "step": 122 |
| }, |
| { |
| "epoch": 62.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.3841531574726105, |
| "eval_runtime": 0.6553, |
| "eval_samples_per_second": 65.618, |
| "eval_steps_per_second": 3.052, |
| "step": 124 |
| }, |
| { |
| "epoch": 63.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.35165607929229736, |
| "eval_runtime": 0.6763, |
| "eval_samples_per_second": 63.58, |
| "eval_steps_per_second": 2.957, |
| "step": 126 |
| }, |
| { |
| "epoch": 64.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.30832788348197937, |
| "eval_runtime": 0.7047, |
| "eval_samples_per_second": 61.022, |
| "eval_steps_per_second": 2.838, |
| "step": 128 |
| }, |
| { |
| "epoch": 65.0, |
| "grad_norm": 4.505985260009766, |
| "learning_rate": 1.9444444444444445e-05, |
| "loss": 0.0987, |
| "step": 130 |
| }, |
| { |
| "epoch": 65.0, |
| "eval_accuracy": 0.9534883720930233, |
| "eval_loss": 0.312499076128006, |
| "eval_runtime": 0.6873, |
| "eval_samples_per_second": 62.564, |
| "eval_steps_per_second": 2.91, |
| "step": 130 |
| }, |
| { |
| "epoch": 66.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.39683035016059875, |
| "eval_runtime": 0.6813, |
| "eval_samples_per_second": 63.119, |
| "eval_steps_per_second": 2.936, |
| "step": 132 |
| }, |
| { |
| "epoch": 67.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.39735493063926697, |
| "eval_runtime": 0.686, |
| "eval_samples_per_second": 62.685, |
| "eval_steps_per_second": 2.916, |
| "step": 134 |
| }, |
| { |
| "epoch": 68.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.3303990364074707, |
| "eval_runtime": 0.6933, |
| "eval_samples_per_second": 62.024, |
| "eval_steps_per_second": 2.885, |
| "step": 136 |
| }, |
| { |
| "epoch": 69.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3507549464702606, |
| "eval_runtime": 0.6846, |
| "eval_samples_per_second": 62.807, |
| "eval_steps_per_second": 2.921, |
| "step": 138 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 3.6767280101776123, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0932, |
| "step": 140 |
| }, |
| { |
| "epoch": 70.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3759661316871643, |
| "eval_runtime": 0.6711, |
| "eval_samples_per_second": 64.075, |
| "eval_steps_per_second": 2.98, |
| "step": 140 |
| }, |
| { |
| "epoch": 71.0, |
| "eval_accuracy": 0.9534883720930233, |
| "eval_loss": 0.38282331824302673, |
| "eval_runtime": 0.645, |
| "eval_samples_per_second": 66.663, |
| "eval_steps_per_second": 3.101, |
| "step": 142 |
| }, |
| { |
| "epoch": 72.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.3290823698043823, |
| "eval_runtime": 0.6664, |
| "eval_samples_per_second": 64.523, |
| "eval_steps_per_second": 3.001, |
| "step": 144 |
| }, |
| { |
| "epoch": 73.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.3108883798122406, |
| "eval_runtime": 0.6741, |
| "eval_samples_per_second": 63.79, |
| "eval_steps_per_second": 2.967, |
| "step": 146 |
| }, |
| { |
| "epoch": 74.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.30784255266189575, |
| "eval_runtime": 0.6664, |
| "eval_samples_per_second": 64.526, |
| "eval_steps_per_second": 3.001, |
| "step": 148 |
| }, |
| { |
| "epoch": 75.0, |
| "grad_norm": 4.596102237701416, |
| "learning_rate": 1.388888888888889e-05, |
| "loss": 0.0917, |
| "step": 150 |
| }, |
| { |
| "epoch": 75.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.4478188753128052, |
| "eval_runtime": 0.6699, |
| "eval_samples_per_second": 64.191, |
| "eval_steps_per_second": 2.986, |
| "step": 150 |
| }, |
| { |
| "epoch": 76.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.6593689322471619, |
| "eval_runtime": 0.6625, |
| "eval_samples_per_second": 64.907, |
| "eval_steps_per_second": 3.019, |
| "step": 152 |
| }, |
| { |
| "epoch": 77.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.603599488735199, |
| "eval_runtime": 0.6677, |
| "eval_samples_per_second": 64.398, |
| "eval_steps_per_second": 2.995, |
| "step": 154 |
| }, |
| { |
| "epoch": 78.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3919643461704254, |
| "eval_runtime": 0.6597, |
| "eval_samples_per_second": 65.176, |
| "eval_steps_per_second": 3.031, |
| "step": 156 |
| }, |
| { |
| "epoch": 79.0, |
| "eval_accuracy": 0.8604651162790697, |
| "eval_loss": 0.32634207606315613, |
| "eval_runtime": 0.6674, |
| "eval_samples_per_second": 64.424, |
| "eval_steps_per_second": 2.996, |
| "step": 158 |
| }, |
| { |
| "epoch": 80.0, |
| "grad_norm": 4.454258441925049, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.0917, |
| "step": 160 |
| }, |
| { |
| "epoch": 80.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.355075865983963, |
| "eval_runtime": 0.6595, |
| "eval_samples_per_second": 65.2, |
| "eval_steps_per_second": 3.033, |
| "step": 160 |
| }, |
| { |
| "epoch": 81.0, |
| "eval_accuracy": 0.8372093023255814, |
| "eval_loss": 0.34745433926582336, |
| "eval_runtime": 0.6661, |
| "eval_samples_per_second": 64.553, |
| "eval_steps_per_second": 3.002, |
| "step": 162 |
| }, |
| { |
| "epoch": 82.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.3337682783603668, |
| "eval_runtime": 0.6945, |
| "eval_samples_per_second": 61.913, |
| "eval_steps_per_second": 2.88, |
| "step": 164 |
| }, |
| { |
| "epoch": 83.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.33535221219062805, |
| "eval_runtime": 0.6987, |
| "eval_samples_per_second": 61.539, |
| "eval_steps_per_second": 2.862, |
| "step": 166 |
| }, |
| { |
| "epoch": 84.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3610616624355316, |
| "eval_runtime": 0.6855, |
| "eval_samples_per_second": 62.731, |
| "eval_steps_per_second": 2.918, |
| "step": 168 |
| }, |
| { |
| "epoch": 85.0, |
| "grad_norm": 3.4667630195617676, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.0901, |
| "step": 170 |
| }, |
| { |
| "epoch": 85.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.35576945543289185, |
| "eval_runtime": 0.6838, |
| "eval_samples_per_second": 62.885, |
| "eval_steps_per_second": 2.925, |
| "step": 170 |
| }, |
| { |
| "epoch": 86.0, |
| "eval_accuracy": 0.8837209302325582, |
| "eval_loss": 0.3411591947078705, |
| "eval_runtime": 0.7033, |
| "eval_samples_per_second": 61.138, |
| "eval_steps_per_second": 2.844, |
| "step": 172 |
| }, |
| { |
| "epoch": 87.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.3351864516735077, |
| "eval_runtime": 0.6805, |
| "eval_samples_per_second": 63.192, |
| "eval_steps_per_second": 2.939, |
| "step": 174 |
| }, |
| { |
| "epoch": 88.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3626754581928253, |
| "eval_runtime": 0.6965, |
| "eval_samples_per_second": 61.737, |
| "eval_steps_per_second": 2.871, |
| "step": 176 |
| }, |
| { |
| "epoch": 89.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3636888563632965, |
| "eval_runtime": 0.6751, |
| "eval_samples_per_second": 63.691, |
| "eval_steps_per_second": 2.962, |
| "step": 178 |
| }, |
| { |
| "epoch": 90.0, |
| "grad_norm": 4.166082859039307, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.0764, |
| "step": 180 |
| }, |
| { |
| "epoch": 90.0, |
| "eval_accuracy": 0.9069767441860465, |
| "eval_loss": 0.3369392454624176, |
| "eval_runtime": 0.6516, |
| "eval_samples_per_second": 65.987, |
| "eval_steps_per_second": 3.069, |
| "step": 180 |
| }, |
| { |
| "epoch": 91.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.3246123790740967, |
| "eval_runtime": 0.6725, |
| "eval_samples_per_second": 63.943, |
| "eval_steps_per_second": 2.974, |
| "step": 182 |
| }, |
| { |
| "epoch": 92.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.32077017426490784, |
| "eval_runtime": 0.6445, |
| "eval_samples_per_second": 66.718, |
| "eval_steps_per_second": 3.103, |
| "step": 184 |
| }, |
| { |
| "epoch": 93.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.3228544592857361, |
| "eval_runtime": 0.6543, |
| "eval_samples_per_second": 65.719, |
| "eval_steps_per_second": 3.057, |
| "step": 186 |
| }, |
| { |
| "epoch": 94.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.332642138004303, |
| "eval_runtime": 0.6678, |
| "eval_samples_per_second": 64.392, |
| "eval_steps_per_second": 2.995, |
| "step": 188 |
| }, |
| { |
| "epoch": 95.0, |
| "grad_norm": 3.7881217002868652, |
| "learning_rate": 2.777777777777778e-06, |
| "loss": 0.0664, |
| "step": 190 |
| }, |
| { |
| "epoch": 95.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.3340218663215637, |
| "eval_runtime": 0.6692, |
| "eval_samples_per_second": 64.259, |
| "eval_steps_per_second": 2.989, |
| "step": 190 |
| }, |
| { |
| "epoch": 96.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.3296101689338684, |
| "eval_runtime": 0.68, |
| "eval_samples_per_second": 63.231, |
| "eval_steps_per_second": 2.941, |
| "step": 192 |
| }, |
| { |
| "epoch": 97.0, |
| "eval_accuracy": 0.9302325581395349, |
| "eval_loss": 0.326764315366745, |
| "eval_runtime": 0.6633, |
| "eval_samples_per_second": 64.829, |
| "eval_steps_per_second": 3.015, |
| "step": 194 |
| }, |
| { |
| "epoch": 98.0, |
| "eval_accuracy": 0.9534883720930233, |
| "eval_loss": 0.3259981870651245, |
| "eval_runtime": 0.6671, |
| "eval_samples_per_second": 64.456, |
| "eval_steps_per_second": 2.998, |
| "step": 196 |
| }, |
| { |
| "epoch": 99.0, |
| "eval_accuracy": 0.9534883720930233, |
| "eval_loss": 0.32882022857666016, |
| "eval_runtime": 0.6593, |
| "eval_samples_per_second": 65.217, |
| "eval_steps_per_second": 3.033, |
| "step": 198 |
| }, |
| { |
| "epoch": 100.0, |
| "grad_norm": 2.48673415184021, |
| "learning_rate": 0.0, |
| "loss": 0.057, |
| "step": 200 |
| }, |
| { |
| "epoch": 100.0, |
| "eval_accuracy": 0.9534883720930233, |
| "eval_loss": 0.3298320472240448, |
| "eval_runtime": 0.6775, |
| "eval_samples_per_second": 63.47, |
| "eval_steps_per_second": 2.952, |
| "step": 200 |
| }, |
| { |
| "epoch": 100.0, |
| "step": 200, |
| "total_flos": 1.8667587341684736e+18, |
| "train_loss": 0.16861820787191392, |
| "train_runtime": 1839.5869, |
| "train_samples_per_second": 13.101, |
| "train_steps_per_second": 0.109 |
| }, |
| { |
| "epoch": 100.0, |
| "eval_accuracy": 0.9534883720930233, |
| "eval_loss": 0.33263495564460754, |
| "eval_runtime": 0.694, |
| "eval_samples_per_second": 61.963, |
| "eval_steps_per_second": 2.882, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "total_flos": 1.8667587341684736e+18, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
