| { | |
| "best_metric": 0.8166666666666667, | |
| "best_model_checkpoint": "swiftformer-xs-dmae-va-U5-42C\\checkpoint-418", | |
| "epoch": 72.25806451612904, | |
| "eval_steps": 500, | |
| "global_step": 560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.4666666666666667, | |
| "eval_loss": 1.3856309652328491, | |
| "eval_runtime": 1.1043, | |
| "eval_samples_per_second": 54.333, | |
| "eval_steps_per_second": 1.811, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.3855, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_loss": 1.3819035291671753, | |
| "eval_runtime": 0.7186, | |
| "eval_samples_per_second": 83.495, | |
| "eval_steps_per_second": 2.783, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.43333333333333335, | |
| "eval_loss": 1.3687236309051514, | |
| "eval_runtime": 0.7101, | |
| "eval_samples_per_second": 84.495, | |
| "eval_steps_per_second": 2.817, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 1.3742, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.31666666666666665, | |
| "eval_loss": 1.3188554048538208, | |
| "eval_runtime": 0.726, | |
| "eval_samples_per_second": 82.647, | |
| "eval_steps_per_second": 2.755, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.00012857142857142858, | |
| "loss": 1.3004, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_loss": 1.2501040697097778, | |
| "eval_runtime": 0.725, | |
| "eval_samples_per_second": 82.755, | |
| "eval_steps_per_second": 2.759, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_loss": 1.2268178462982178, | |
| "eval_runtime": 0.7099, | |
| "eval_samples_per_second": 84.517, | |
| "eval_steps_per_second": 2.817, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 1.1716, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.211478352546692, | |
| "eval_runtime": 0.7071, | |
| "eval_samples_per_second": 84.855, | |
| "eval_steps_per_second": 2.828, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.00019841269841269844, | |
| "loss": 1.0686, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_loss": 1.2243305444717407, | |
| "eval_runtime": 0.7126, | |
| "eval_samples_per_second": 84.197, | |
| "eval_steps_per_second": 2.807, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 1.1432182788848877, | |
| "eval_runtime": 0.7953, | |
| "eval_samples_per_second": 75.447, | |
| "eval_steps_per_second": 2.515, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 0.00019365079365079365, | |
| "loss": 0.9764, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 1.020477294921875, | |
| "eval_runtime": 0.7686, | |
| "eval_samples_per_second": 78.061, | |
| "eval_steps_per_second": 2.602, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 0.00018888888888888888, | |
| "loss": 0.873, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.9721332788467407, | |
| "eval_runtime": 0.8664, | |
| "eval_samples_per_second": 69.254, | |
| "eval_steps_per_second": 2.308, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_loss": 0.9220641851425171, | |
| "eval_runtime": 0.7382, | |
| "eval_samples_per_second": 81.278, | |
| "eval_steps_per_second": 2.709, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "learning_rate": 0.00018412698412698412, | |
| "loss": 0.7822, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 0.8593236207962036, | |
| "eval_runtime": 1.1748, | |
| "eval_samples_per_second": 51.071, | |
| "eval_steps_per_second": 1.702, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "learning_rate": 0.00017936507936507938, | |
| "loss": 0.664, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.7774909734725952, | |
| "eval_runtime": 0.8265, | |
| "eval_samples_per_second": 72.595, | |
| "eval_steps_per_second": 2.42, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 0.8117440342903137, | |
| "eval_runtime": 0.873, | |
| "eval_samples_per_second": 68.731, | |
| "eval_steps_per_second": 2.291, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 0.00017460317460317462, | |
| "loss": 0.5439, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6833333333333333, | |
| "eval_loss": 0.7552784085273743, | |
| "eval_runtime": 0.8067, | |
| "eval_samples_per_second": 74.373, | |
| "eval_steps_per_second": 2.479, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.669671356678009, | |
| "eval_runtime": 0.7809, | |
| "eval_samples_per_second": 76.836, | |
| "eval_steps_per_second": 2.561, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 0.00016984126984126986, | |
| "loss": 0.496, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 17.94, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.6479821801185608, | |
| "eval_runtime": 0.8358, | |
| "eval_samples_per_second": 71.789, | |
| "eval_steps_per_second": 2.393, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 18.58, | |
| "learning_rate": 0.0001650793650793651, | |
| "loss": 0.4563, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7115061283111572, | |
| "eval_runtime": 0.7213, | |
| "eval_samples_per_second": 83.184, | |
| "eval_steps_per_second": 2.773, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.6776978373527527, | |
| "eval_runtime": 1.1968, | |
| "eval_samples_per_second": 50.132, | |
| "eval_steps_per_second": 1.671, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 20.13, | |
| "learning_rate": 0.00016031746031746033, | |
| "loss": 0.3831, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 20.9, | |
| "eval_accuracy": 0.7666666666666667, | |
| "eval_loss": 0.641558825969696, | |
| "eval_runtime": 0.7539, | |
| "eval_samples_per_second": 79.588, | |
| "eval_steps_per_second": 2.653, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 21.68, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 0.339, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.7040281891822815, | |
| "eval_runtime": 0.7707, | |
| "eval_samples_per_second": 77.852, | |
| "eval_steps_per_second": 2.595, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 22.97, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.6858527064323425, | |
| "eval_runtime": 0.7222, | |
| "eval_samples_per_second": 83.082, | |
| "eval_steps_per_second": 2.769, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 0.0001507936507936508, | |
| "loss": 0.3033, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.6012035608291626, | |
| "eval_runtime": 0.8804, | |
| "eval_samples_per_second": 68.154, | |
| "eval_steps_per_second": 2.272, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 24.77, | |
| "learning_rate": 0.00014603174603174603, | |
| "loss": 0.2655, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 24.9, | |
| "eval_accuracy": 0.7833333333333333, | |
| "eval_loss": 0.5439515709877014, | |
| "eval_runtime": 0.8773, | |
| "eval_samples_per_second": 68.39, | |
| "eval_steps_per_second": 2.28, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 25.94, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6173577904701233, | |
| "eval_runtime": 0.755, | |
| "eval_samples_per_second": 79.471, | |
| "eval_steps_per_second": 2.649, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 0.0001412698412698413, | |
| "loss": 0.2269, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 26.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.5745389461517334, | |
| "eval_runtime": 0.7541, | |
| "eval_samples_per_second": 79.562, | |
| "eval_steps_per_second": 2.652, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 27.87, | |
| "learning_rate": 0.0001365079365079365, | |
| "loss": 0.2472, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.5688391327857971, | |
| "eval_runtime": 0.7386, | |
| "eval_samples_per_second": 81.235, | |
| "eval_steps_per_second": 2.708, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 28.9, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6578179597854614, | |
| "eval_runtime": 0.7981, | |
| "eval_samples_per_second": 75.174, | |
| "eval_steps_per_second": 2.506, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 29.42, | |
| "learning_rate": 0.00013174603174603174, | |
| "loss": 0.2004, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 29.94, | |
| "eval_accuracy": 0.7833333333333333, | |
| "eval_loss": 0.5811216831207275, | |
| "eval_runtime": 0.7017, | |
| "eval_samples_per_second": 85.512, | |
| "eval_steps_per_second": 2.85, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 30.97, | |
| "learning_rate": 0.00012698412698412698, | |
| "loss": 0.2099, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 30.97, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6672316193580627, | |
| "eval_runtime": 0.9579, | |
| "eval_samples_per_second": 62.635, | |
| "eval_steps_per_second": 2.088, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5926868319511414, | |
| "eval_runtime": 0.7151, | |
| "eval_samples_per_second": 83.907, | |
| "eval_steps_per_second": 2.797, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 32.52, | |
| "learning_rate": 0.00012222222222222224, | |
| "loss": 0.1834, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 32.9, | |
| "eval_accuracy": 0.7666666666666667, | |
| "eval_loss": 0.6193079352378845, | |
| "eval_runtime": 0.7137, | |
| "eval_samples_per_second": 84.073, | |
| "eval_steps_per_second": 2.802, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 33.94, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.7505124807357788, | |
| "eval_runtime": 0.8955, | |
| "eval_samples_per_second": 67.004, | |
| "eval_steps_per_second": 2.233, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 34.06, | |
| "learning_rate": 0.00011746031746031746, | |
| "loss": 0.2248, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 34.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7730365991592407, | |
| "eval_runtime": 0.7499, | |
| "eval_samples_per_second": 80.008, | |
| "eval_steps_per_second": 2.667, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 35.61, | |
| "learning_rate": 0.0001126984126984127, | |
| "loss": 0.1571, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.6211021542549133, | |
| "eval_runtime": 0.9402, | |
| "eval_samples_per_second": 63.814, | |
| "eval_steps_per_second": 2.127, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 36.9, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.6227646470069885, | |
| "eval_runtime": 0.747, | |
| "eval_samples_per_second": 80.323, | |
| "eval_steps_per_second": 2.677, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 37.16, | |
| "learning_rate": 0.00010793650793650794, | |
| "loss": 0.1983, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 37.94, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.6088116765022278, | |
| "eval_runtime": 0.6721, | |
| "eval_samples_per_second": 89.274, | |
| "eval_steps_per_second": 2.976, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 38.71, | |
| "learning_rate": 0.00010317460317460319, | |
| "loss": 0.1629, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 38.97, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.7009025812149048, | |
| "eval_runtime": 0.6916, | |
| "eval_samples_per_second": 86.756, | |
| "eval_steps_per_second": 2.892, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.7284848690032959, | |
| "eval_runtime": 0.6756, | |
| "eval_samples_per_second": 88.806, | |
| "eval_steps_per_second": 2.96, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 40.26, | |
| "learning_rate": 9.841269841269841e-05, | |
| "loss": 0.1547, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 40.9, | |
| "eval_accuracy": 0.7666666666666667, | |
| "eval_loss": 0.6401079297065735, | |
| "eval_runtime": 1.0498, | |
| "eval_samples_per_second": 57.152, | |
| "eval_steps_per_second": 1.905, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 41.81, | |
| "learning_rate": 9.365079365079366e-05, | |
| "loss": 0.1548, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 41.94, | |
| "eval_accuracy": 0.7833333333333333, | |
| "eval_loss": 0.6122706532478333, | |
| "eval_runtime": 0.7047, | |
| "eval_samples_per_second": 85.142, | |
| "eval_steps_per_second": 2.838, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 42.97, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6316841244697571, | |
| "eval_runtime": 0.7237, | |
| "eval_samples_per_second": 82.911, | |
| "eval_steps_per_second": 2.764, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 43.35, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.1566, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.7579439282417297, | |
| "eval_runtime": 0.6901, | |
| "eval_samples_per_second": 86.944, | |
| "eval_steps_per_second": 2.898, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 44.9, | |
| "learning_rate": 8.412698412698413e-05, | |
| "loss": 0.1361, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 44.9, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.6652740836143494, | |
| "eval_runtime": 0.7005, | |
| "eval_samples_per_second": 85.657, | |
| "eval_steps_per_second": 2.855, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 45.94, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7401434779167175, | |
| "eval_runtime": 0.6837, | |
| "eval_samples_per_second": 87.759, | |
| "eval_steps_per_second": 2.925, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 46.45, | |
| "learning_rate": 7.936507936507937e-05, | |
| "loss": 0.1273, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 46.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.8404071927070618, | |
| "eval_runtime": 0.852, | |
| "eval_samples_per_second": 70.419, | |
| "eval_steps_per_second": 2.347, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 7.460317460317461e-05, | |
| "loss": 0.1312, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.8388133645057678, | |
| "eval_runtime": 0.7625, | |
| "eval_samples_per_second": 78.691, | |
| "eval_steps_per_second": 2.623, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 48.9, | |
| "eval_accuracy": 0.7666666666666667, | |
| "eval_loss": 0.7823358774185181, | |
| "eval_runtime": 0.7984, | |
| "eval_samples_per_second": 75.152, | |
| "eval_steps_per_second": 2.505, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 49.55, | |
| "learning_rate": 6.984126984126984e-05, | |
| "loss": 0.1307, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 49.94, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.6979826092720032, | |
| "eval_runtime": 0.9296, | |
| "eval_samples_per_second": 64.545, | |
| "eval_steps_per_second": 2.151, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 50.97, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.7589060664176941, | |
| "eval_runtime": 0.9421, | |
| "eval_samples_per_second": 63.685, | |
| "eval_steps_per_second": 2.123, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 51.1, | |
| "learning_rate": 6.507936507936509e-05, | |
| "loss": 0.1061, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.664362907409668, | |
| "eval_runtime": 0.9581, | |
| "eval_samples_per_second": 62.625, | |
| "eval_steps_per_second": 2.088, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 52.65, | |
| "learning_rate": 6.0317460317460316e-05, | |
| "loss": 0.1186, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 52.9, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7056966423988342, | |
| "eval_runtime": 0.7627, | |
| "eval_samples_per_second": 78.67, | |
| "eval_steps_per_second": 2.622, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 53.94, | |
| "eval_accuracy": 0.8166666666666667, | |
| "eval_loss": 0.6744123697280884, | |
| "eval_runtime": 0.7522, | |
| "eval_samples_per_second": 79.767, | |
| "eval_steps_per_second": 2.659, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 54.19, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.1108, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 54.97, | |
| "eval_accuracy": 0.7666666666666667, | |
| "eval_loss": 0.6327721476554871, | |
| "eval_runtime": 0.7919, | |
| "eval_samples_per_second": 75.763, | |
| "eval_steps_per_second": 2.525, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 55.74, | |
| "learning_rate": 5.0793650793650794e-05, | |
| "loss": 0.1014, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7833333333333333, | |
| "eval_loss": 0.6401543021202087, | |
| "eval_runtime": 0.7047, | |
| "eval_samples_per_second": 85.145, | |
| "eval_steps_per_second": 2.838, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 56.9, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6631258726119995, | |
| "eval_runtime": 0.7567, | |
| "eval_samples_per_second": 79.292, | |
| "eval_steps_per_second": 2.643, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 57.29, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 0.1082, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 57.94, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7001372575759888, | |
| "eval_runtime": 0.7863, | |
| "eval_samples_per_second": 76.308, | |
| "eval_steps_per_second": 2.544, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 58.84, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 0.1118, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 58.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7898235321044922, | |
| "eval_runtime": 0.8339, | |
| "eval_samples_per_second": 71.951, | |
| "eval_steps_per_second": 2.398, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7644184231758118, | |
| "eval_runtime": 0.916, | |
| "eval_samples_per_second": 65.499, | |
| "eval_steps_per_second": 2.183, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 60.39, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 0.1051, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 60.9, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7767077088356018, | |
| "eval_runtime": 0.7368, | |
| "eval_samples_per_second": 81.432, | |
| "eval_steps_per_second": 2.714, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 61.94, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.0979, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 61.94, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7440354824066162, | |
| "eval_runtime": 0.8613, | |
| "eval_samples_per_second": 69.665, | |
| "eval_steps_per_second": 2.322, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 62.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.6826977133750916, | |
| "eval_runtime": 0.8727, | |
| "eval_samples_per_second": 68.75, | |
| "eval_steps_per_second": 2.292, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 63.48, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 0.0834, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7008056640625, | |
| "eval_runtime": 1.0337, | |
| "eval_samples_per_second": 58.046, | |
| "eval_steps_per_second": 1.935, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 64.9, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.7242893576622009, | |
| "eval_runtime": 0.9008, | |
| "eval_samples_per_second": 66.608, | |
| "eval_steps_per_second": 2.22, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 65.03, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0963, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 65.94, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7655950784683228, | |
| "eval_runtime": 0.7846, | |
| "eval_samples_per_second": 76.471, | |
| "eval_steps_per_second": 2.549, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 66.58, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 0.0989, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 66.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.733224093914032, | |
| "eval_runtime": 0.6942, | |
| "eval_samples_per_second": 86.424, | |
| "eval_steps_per_second": 2.881, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7623672485351562, | |
| "eval_runtime": 0.6962, | |
| "eval_samples_per_second": 86.187, | |
| "eval_steps_per_second": 2.873, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 68.13, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.107, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 68.9, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.7291642427444458, | |
| "eval_runtime": 0.8099, | |
| "eval_samples_per_second": 74.08, | |
| "eval_steps_per_second": 2.469, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 69.68, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.0987, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 69.94, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7168775796890259, | |
| "eval_runtime": 0.9171, | |
| "eval_samples_per_second": 65.421, | |
| "eval_steps_per_second": 2.181, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 70.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.746231734752655, | |
| "eval_runtime": 0.7381, | |
| "eval_samples_per_second": 81.293, | |
| "eval_steps_per_second": 2.71, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 71.23, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.0956, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6656435132026672, | |
| "eval_runtime": 0.7048, | |
| "eval_samples_per_second": 85.132, | |
| "eval_steps_per_second": 2.838, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 72.26, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.6873000860214233, | |
| "eval_runtime": 0.744, | |
| "eval_samples_per_second": 80.641, | |
| "eval_steps_per_second": 2.688, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 72.26, | |
| "step": 560, | |
| "total_flos": 1.9293876649171354e+17, | |
| "train_loss": 0.3574366893087115, | |
| "train_runtime": 357.0027, | |
| "train_samples_per_second": 218.262, | |
| "train_steps_per_second": 1.569 | |
| } | |
| ], | |
| "logging_steps": 12, | |
| "max_steps": 560, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 1.9293876649171354e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |