| { | |
| "best_metric": 0.82, | |
| "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-560", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.464285714285714e-05, | |
| "loss": 2.2976, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.928571428571429e-05, | |
| "loss": 2.2855, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00013392857142857144, | |
| "loss": 2.2307, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00017857142857142857, | |
| "loss": 2.1327, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00022321428571428573, | |
| "loss": 2.0339, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00026785714285714287, | |
| "loss": 1.9633, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0003125, | |
| "loss": 1.8021, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00035714285714285714, | |
| "loss": 1.6938, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00040178571428571433, | |
| "loss": 1.5271, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00044642857142857147, | |
| "loss": 1.4038, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0004910714285714286, | |
| "loss": 1.496, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.27, | |
| "eval_loss": 1.8467493057250977, | |
| "eval_runtime": 72.5718, | |
| "eval_samples_per_second": 1.378, | |
| "eval_steps_per_second": 0.179, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.000496031746031746, | |
| "loss": 1.3528, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0004910714285714286, | |
| "loss": 1.507, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0004861111111111111, | |
| "loss": 1.504, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0004811507936507937, | |
| "loss": 1.3719, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0004761904761904762, | |
| "loss": 1.2284, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00047123015873015874, | |
| "loss": 1.2997, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0004662698412698413, | |
| "loss": 1.2284, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00046130952380952383, | |
| "loss": 1.3332, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0004563492063492063, | |
| "loss": 1.1091, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0004513888888888889, | |
| "loss": 1.1335, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00044642857142857147, | |
| "loss": 1.1313, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.61, | |
| "eval_loss": 1.175675868988037, | |
| "eval_runtime": 71.9077, | |
| "eval_samples_per_second": 1.391, | |
| "eval_steps_per_second": 0.181, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00044146825396825396, | |
| "loss": 1.1765, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0004365079365079365, | |
| "loss": 1.0945, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.00043154761904761905, | |
| "loss": 0.9198, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0004265873015873016, | |
| "loss": 1.1504, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.00042162698412698415, | |
| "loss": 1.03, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0004166666666666667, | |
| "loss": 1.294, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0004117063492063492, | |
| "loss": 0.918, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00040674603174603173, | |
| "loss": 0.9529, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00040178571428571433, | |
| "loss": 0.9366, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0003968253968253968, | |
| "loss": 0.9388, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.00039186507936507937, | |
| "loss": 1.2432, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.58, | |
| "eval_loss": 1.3774330615997314, | |
| "eval_runtime": 72.0805, | |
| "eval_samples_per_second": 1.387, | |
| "eval_steps_per_second": 0.18, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0003869047619047619, | |
| "loss": 0.8342, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0003819444444444444, | |
| "loss": 1.2782, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.000376984126984127, | |
| "loss": 0.9997, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00037202380952380956, | |
| "loss": 0.6668, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00036706349206349205, | |
| "loss": 0.7267, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.0003621031746031746, | |
| "loss": 0.892, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00035714285714285714, | |
| "loss": 1.0096, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.0003521825396825397, | |
| "loss": 0.8909, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 0.00034722222222222224, | |
| "loss": 1.0591, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.0003422619047619048, | |
| "loss": 0.6526, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.00033730158730158733, | |
| "loss": 0.847, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.0003323412698412698, | |
| "loss": 0.7301, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.66, | |
| "eval_loss": 0.9738250970840454, | |
| "eval_runtime": 70.9865, | |
| "eval_samples_per_second": 1.409, | |
| "eval_steps_per_second": 0.183, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.00032738095238095237, | |
| "loss": 0.8506, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.00032242063492063497, | |
| "loss": 0.642, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00031746031746031746, | |
| "loss": 0.6132, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 0.0003125, | |
| "loss": 0.6279, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 0.00030753968253968255, | |
| "loss": 0.7194, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.00030257936507936505, | |
| "loss": 0.7127, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 0.00029761904761904765, | |
| "loss": 0.5318, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 0.0002926587301587302, | |
| "loss": 0.7127, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.0002876984126984127, | |
| "loss": 0.5685, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.00028273809523809523, | |
| "loss": 0.6034, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 0.0002777777777777778, | |
| "loss": 0.5192, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.73, | |
| "eval_loss": 0.9078372120857239, | |
| "eval_runtime": 71.0414, | |
| "eval_samples_per_second": 1.408, | |
| "eval_steps_per_second": 0.183, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.0002728174603174603, | |
| "loss": 0.4625, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.00026785714285714287, | |
| "loss": 0.5618, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.0002628968253968254, | |
| "loss": 0.4268, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 0.00025793650793650796, | |
| "loss": 0.545, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.00025297619047619046, | |
| "loss": 0.4513, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 0.000248015873015873, | |
| "loss": 0.4566, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 0.00024305555555555555, | |
| "loss": 0.4533, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 0.0002380952380952381, | |
| "loss": 0.4453, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.00023313492063492064, | |
| "loss": 0.4401, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 0.00022817460317460316, | |
| "loss": 0.3283, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 0.00022321428571428573, | |
| "loss": 0.4163, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.71, | |
| "eval_loss": 0.9995945692062378, | |
| "eval_runtime": 71.0596, | |
| "eval_samples_per_second": 1.407, | |
| "eval_steps_per_second": 0.183, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.00021825396825396825, | |
| "loss": 0.3108, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.0002132936507936508, | |
| "loss": 0.2346, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.00020833333333333335, | |
| "loss": 0.2996, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 0.00020337301587301587, | |
| "loss": 0.2248, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 0.0001984126984126984, | |
| "loss": 0.2535, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 0.00019345238095238096, | |
| "loss": 0.1705, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.0001884920634920635, | |
| "loss": 0.2647, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 0.00018353174603174602, | |
| "loss": 0.3173, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 0.00017857142857142857, | |
| "loss": 0.2563, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 0.00017361111111111112, | |
| "loss": 0.0983, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 0.00016865079365079366, | |
| "loss": 0.5197, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.00016369047619047618, | |
| "loss": 0.2178, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.79, | |
| "eval_loss": 0.7682663202285767, | |
| "eval_runtime": 71.9225, | |
| "eval_samples_per_second": 1.39, | |
| "eval_steps_per_second": 0.181, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.00015873015873015873, | |
| "loss": 0.125, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 0.00015376984126984128, | |
| "loss": 0.1267, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.00014880952380952382, | |
| "loss": 0.216, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.00014384920634920634, | |
| "loss": 0.1007, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 0.0001388888888888889, | |
| "loss": 0.1302, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 0.00013392857142857144, | |
| "loss": 0.1706, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 0.00012896825396825398, | |
| "loss": 0.0971, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 0.0001240079365079365, | |
| "loss": 0.1253, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 0.00011904761904761905, | |
| "loss": 0.0798, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 0.00011408730158730158, | |
| "loss": 0.5271, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.00010912698412698413, | |
| "loss": 0.0814, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.9985226392745972, | |
| "eval_runtime": 70.9212, | |
| "eval_samples_per_second": 1.41, | |
| "eval_steps_per_second": 0.183, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 0.00010416666666666667, | |
| "loss": 0.1214, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 9.92063492063492e-05, | |
| "loss": 0.2457, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 9.424603174603175e-05, | |
| "loss": 0.0164, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.928571428571429e-05, | |
| "loss": 0.0147, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 8.432539682539683e-05, | |
| "loss": 0.0326, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 7.936507936507937e-05, | |
| "loss": 0.0242, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 7.440476190476191e-05, | |
| "loss": 0.1151, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 0.0586, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 6.448412698412699e-05, | |
| "loss": 0.0247, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 5.9523809523809524e-05, | |
| "loss": 0.1615, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 5.4563492063492063e-05, | |
| "loss": 0.0075, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 1.1055810451507568, | |
| "eval_runtime": 71.6983, | |
| "eval_samples_per_second": 1.395, | |
| "eval_steps_per_second": 0.181, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.96031746031746e-05, | |
| "loss": 0.0089, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 4.464285714285714e-05, | |
| "loss": 0.0107, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.0767, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.0075, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 2.9761904761904762e-05, | |
| "loss": 0.0184, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.48015873015873e-05, | |
| "loss": 0.0033, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.0022, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 1.4880952380952381e-05, | |
| "loss": 0.089, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 9.92063492063492e-06, | |
| "loss": 0.0242, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 4.96031746031746e-06, | |
| "loss": 0.0035, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.003, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_accuracy": 0.82, | |
| "eval_loss": 1.024199366569519, | |
| "eval_runtime": 71.6233, | |
| "eval_samples_per_second": 1.396, | |
| "eval_steps_per_second": 0.182, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.00034629629629629626, | |
| "loss": 0.0011, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.0003444444444444445, | |
| "loss": 0.0014, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.00034259259259259263, | |
| "loss": 0.3692, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.00034074074074074074, | |
| "loss": 0.0021, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.0003388888888888889, | |
| "loss": 1.3619, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00033703703703703706, | |
| "loss": 0.6638, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 0.0003351851851851852, | |
| "loss": 1.3796, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0003333333333333333, | |
| "loss": 1.9854, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.71, | |
| "eval_loss": 2.9401955604553223, | |
| "eval_runtime": 73.4555, | |
| "eval_samples_per_second": 1.361, | |
| "eval_steps_per_second": 0.231, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0003314814814814815, | |
| "loss": 0.9608, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.0003296296296296296, | |
| "loss": 1.3334, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.0003277777777777778, | |
| "loss": 2.199, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.00032592592592592596, | |
| "loss": 2.818, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.00032407407407407406, | |
| "loss": 1.1829, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.0003222222222222222, | |
| "loss": 3.0117, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.0003203703703703704, | |
| "loss": 2.559, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 0.00031851851851851854, | |
| "loss": 0.9064, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00031666666666666665, | |
| "loss": 1.4313, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.0003148148148148148, | |
| "loss": 1.5546, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 0.00031296296296296297, | |
| "loss": 0.8546, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.0003111111111111111, | |
| "loss": 1.1597, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 0.00030925925925925923, | |
| "loss": 0.8004, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.0003074074074074074, | |
| "loss": 1.4538, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.0003055555555555556, | |
| "loss": 1.0613, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 0.0003037037037037037, | |
| "loss": 0.9142, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.00030185185185185187, | |
| "loss": 0.4527, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 0.0003, | |
| "loss": 0.828, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.0002981481481481482, | |
| "loss": 1.0077, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 0.0002962962962962963, | |
| "loss": 1.5386, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.00029444444444444445, | |
| "loss": 0.9658, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.00029259259259259256, | |
| "loss": 0.5459, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.00029074074074074077, | |
| "loss": 0.5118, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.0002888888888888889, | |
| "loss": 1.6666, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 0.00028703703703703703, | |
| "loss": 0.7948, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.0002851851851851852, | |
| "loss": 1.1113, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 0.00028333333333333335, | |
| "loss": 0.5932, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 0.0002814814814814815, | |
| "loss": 0.6585, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 0.0002796296296296296, | |
| "loss": 0.6784, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0002777777777777778, | |
| "loss": 1.6072, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.59, | |
| "eval_loss": 2.3611490726470947, | |
| "eval_runtime": 74.012, | |
| "eval_samples_per_second": 1.351, | |
| "eval_steps_per_second": 0.23, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.00027592592592592594, | |
| "loss": 1.1627, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.0002740740740740741, | |
| "loss": 1.2122, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.0002722222222222222, | |
| "loss": 0.9308, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.00027037037037037036, | |
| "loss": 0.1098, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.0002685185185185186, | |
| "loss": 0.1792, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.0002666666666666667, | |
| "loss": 0.0576, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 0.00026481481481481484, | |
| "loss": 0.4938, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.00026296296296296294, | |
| "loss": 0.3774, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.00026111111111111116, | |
| "loss": 0.5467, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.00025925925925925926, | |
| "loss": 0.0763, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.0002574074074074074, | |
| "loss": 1.8333, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.00025555555555555553, | |
| "loss": 1.6781, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00025370370370370374, | |
| "loss": 1.3581, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 0.00025185185185185185, | |
| "loss": 0.8076, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 0.00025, | |
| "loss": 0.6483, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.00024814814814814816, | |
| "loss": 0.4841, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.00024629629629629627, | |
| "loss": 0.8474, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.00024444444444444443, | |
| "loss": 1.1239, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 0.0002425925925925926, | |
| "loss": 0.5482, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.00024074074074074072, | |
| "loss": 0.0506, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.0002388888888888889, | |
| "loss": 0.8862, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 0.00023703703703703704, | |
| "loss": 1.6642, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 0.0002351851851851852, | |
| "loss": 0.7866, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 0.00023333333333333333, | |
| "loss": 1.0868, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 0.0002314814814814815, | |
| "loss": 0.7077, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 0.00022962962962962962, | |
| "loss": 0.7793, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 0.00022777777777777778, | |
| "loss": 1.0322, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 0.00022592592592592591, | |
| "loss": 0.6766, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.00022407407407407407, | |
| "loss": 0.5597, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0002222222222222222, | |
| "loss": 1.6628, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.68, | |
| "eval_loss": 2.350435495376587, | |
| "eval_runtime": 73.3199, | |
| "eval_samples_per_second": 1.364, | |
| "eval_steps_per_second": 0.232, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1500, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 7.4726851594752e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |