| { | |
| "best_metric": 0.22263780236244202, | |
| "best_model_checkpoint": "DrishtiSharma/finetuned-SwinT-Indian-Food-Classification-v2/checkpoint-1500", | |
| "epoch": 5.0, | |
| "global_step": 1665, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019903903903903904, | |
| "loss": 2.4985, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019783783783783784, | |
| "loss": 1.4444, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019663663663663664, | |
| "loss": 1.0698, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019543543543543545, | |
| "loss": 1.0817, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019423423423423425, | |
| "loss": 0.8105, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019303303303303305, | |
| "loss": 0.8324, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019183183183183185, | |
| "loss": 0.8106, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019063063063063065, | |
| "loss": 0.6581, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00018942942942942943, | |
| "loss": 0.6992, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00018822822822822823, | |
| "loss": 0.9351, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.8363443145589798, | |
| "eval_loss": 0.6016978025436401, | |
| "eval_runtime": 39.9065, | |
| "eval_samples_per_second": 23.58, | |
| "eval_steps_per_second": 2.957, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00018702702702702703, | |
| "loss": 0.9577, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00018582582582582583, | |
| "loss": 0.789, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018462462462462463, | |
| "loss": 1.0007, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00018342342342342343, | |
| "loss": 0.6186, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00018222222222222224, | |
| "loss": 0.5886, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00018114114114114115, | |
| "loss": 0.6685, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00017993993993993993, | |
| "loss": 0.886, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00017873873873873876, | |
| "loss": 0.7398, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00017753753753753756, | |
| "loss": 0.6541, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017633633633633636, | |
| "loss": 0.5667, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.8767268862911796, | |
| "eval_loss": 0.43840092420578003, | |
| "eval_runtime": 39.8194, | |
| "eval_samples_per_second": 23.632, | |
| "eval_steps_per_second": 2.963, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00017513513513513516, | |
| "loss": 0.5596, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017393393393393394, | |
| "loss": 0.5697, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00017273273273273274, | |
| "loss": 0.6168, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00017153153153153154, | |
| "loss": 0.6351, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00017033033033033034, | |
| "loss": 0.578, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00016912912912912911, | |
| "loss": 0.8882, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00016792792792792794, | |
| "loss": 0.6284, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00016672672672672675, | |
| "loss": 0.8874, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00016552552552552555, | |
| "loss": 0.7083, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00016432432432432435, | |
| "loss": 0.5548, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.8767268862911796, | |
| "eval_loss": 0.42152631282806396, | |
| "eval_runtime": 40.3274, | |
| "eval_samples_per_second": 23.334, | |
| "eval_steps_per_second": 2.926, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00016312312312312312, | |
| "loss": 0.6819, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016192192192192192, | |
| "loss": 0.4283, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00016072072072072073, | |
| "loss": 0.4916, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00015951951951951953, | |
| "loss": 0.5186, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001583183183183183, | |
| "loss": 0.6319, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00015711711711711713, | |
| "loss": 0.3755, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00015591591591591593, | |
| "loss": 0.3293, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00015471471471471474, | |
| "loss": 0.4974, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00015351351351351354, | |
| "loss": 0.6046, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0001523123123123123, | |
| "loss": 0.5516, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.873538788522848, | |
| "eval_loss": 0.42902085185050964, | |
| "eval_runtime": 40.2528, | |
| "eval_samples_per_second": 23.377, | |
| "eval_steps_per_second": 2.931, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001511111111111111, | |
| "loss": 0.5308, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00014990990990990991, | |
| "loss": 0.4627, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00014870870870870872, | |
| "loss": 0.4123, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00014750750750750752, | |
| "loss": 0.5095, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00014630630630630632, | |
| "loss": 0.5262, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00014510510510510512, | |
| "loss": 0.6747, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00014390390390390392, | |
| "loss": 0.3073, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00014270270270270272, | |
| "loss": 0.5508, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0001415015015015015, | |
| "loss": 0.5183, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001403003003003003, | |
| "loss": 0.3782, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.89798087141339, | |
| "eval_loss": 0.35022875666618347, | |
| "eval_runtime": 39.8292, | |
| "eval_samples_per_second": 23.626, | |
| "eval_steps_per_second": 2.963, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001390990990990991, | |
| "loss": 0.4911, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0001378978978978979, | |
| "loss": 0.544, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001366966966966967, | |
| "loss": 0.5958, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0001354954954954955, | |
| "loss": 0.4798, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0001342942942942943, | |
| "loss": 0.3317, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0001330930930930931, | |
| "loss": 0.3693, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0001318918918918919, | |
| "loss": 0.3432, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001306906906906907, | |
| "loss": 0.4374, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0001294894894894895, | |
| "loss": 0.5319, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0001282882882882883, | |
| "loss": 0.3115, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.8937300743889479, | |
| "eval_loss": 0.3780476152896881, | |
| "eval_runtime": 39.7563, | |
| "eval_samples_per_second": 23.669, | |
| "eval_steps_per_second": 2.968, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0001270870870870871, | |
| "loss": 0.3055, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0001258858858858859, | |
| "loss": 0.361, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0001246846846846847, | |
| "loss": 0.5006, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0001234834834834835, | |
| "loss": 0.4293, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001222822822822823, | |
| "loss": 0.3787, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00012108108108108109, | |
| "loss": 0.4617, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00011987987987987988, | |
| "loss": 0.4291, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00011867867867867868, | |
| "loss": 0.4525, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00011747747747747748, | |
| "loss": 0.419, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00011627627627627628, | |
| "loss": 0.4229, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.8905419766206164, | |
| "eval_loss": 0.35450688004493713, | |
| "eval_runtime": 39.4995, | |
| "eval_samples_per_second": 23.823, | |
| "eval_steps_per_second": 2.987, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0001150750750750751, | |
| "loss": 0.117, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00011387387387387387, | |
| "loss": 0.3166, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00011267267267267267, | |
| "loss": 0.3709, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00011147147147147147, | |
| "loss": 0.2417, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00011027027027027029, | |
| "loss": 0.4182, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00010906906906906909, | |
| "loss": 0.3219, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00010786786786786786, | |
| "loss": 0.3879, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 0.3304, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00010546546546546547, | |
| "loss": 0.4358, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00010426426426426428, | |
| "loss": 0.3832, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.9086078639744952, | |
| "eval_loss": 0.3445776104927063, | |
| "eval_runtime": 40.5544, | |
| "eval_samples_per_second": 23.203, | |
| "eval_steps_per_second": 2.91, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00010306306306306306, | |
| "loss": 0.2202, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.00010186186186186186, | |
| "loss": 0.2851, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00010066066066066066, | |
| "loss": 0.2624, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 9.945945945945948e-05, | |
| "loss": 0.3048, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 9.825825825825826e-05, | |
| "loss": 0.2088, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 9.705705705705707e-05, | |
| "loss": 0.3517, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 9.585585585585585e-05, | |
| "loss": 0.4147, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.465465465465466e-05, | |
| "loss": 0.3886, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 9.345345345345346e-05, | |
| "loss": 0.2345, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.225225225225226e-05, | |
| "loss": 0.2745, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_accuracy": 0.9149840595111584, | |
| "eval_loss": 0.32985183596611023, | |
| "eval_runtime": 40.5661, | |
| "eval_samples_per_second": 23.197, | |
| "eval_steps_per_second": 2.909, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 9.105105105105105e-05, | |
| "loss": 0.2712, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 8.984984984984985e-05, | |
| "loss": 0.389, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 8.864864864864866e-05, | |
| "loss": 0.4054, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.744744744744745e-05, | |
| "loss": 0.3054, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 8.624624624624625e-05, | |
| "loss": 0.2941, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.504504504504504e-05, | |
| "loss": 0.2896, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.384384384384384e-05, | |
| "loss": 0.2729, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 8.264264264264265e-05, | |
| "loss": 0.5281, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 8.144144144144145e-05, | |
| "loss": 0.2477, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.024024024024024e-05, | |
| "loss": 0.2063, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9277364505844846, | |
| "eval_loss": 0.2592255771160126, | |
| "eval_runtime": 40.3202, | |
| "eval_samples_per_second": 23.338, | |
| "eval_steps_per_second": 2.927, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.903903903903904e-05, | |
| "loss": 0.1643, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.783783783783785e-05, | |
| "loss": 0.322, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.663663663663664e-05, | |
| "loss": 0.1657, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.543543543543544e-05, | |
| "loss": 0.2675, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.423423423423423e-05, | |
| "loss": 0.2194, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7.303303303303303e-05, | |
| "loss": 0.1154, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.183183183183183e-05, | |
| "loss": 0.1816, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 7.063063063063064e-05, | |
| "loss": 0.1359, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 6.942942942942944e-05, | |
| "loss": 0.3088, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 6.822822822822822e-05, | |
| "loss": 0.2077, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.9149840595111584, | |
| "eval_loss": 0.37718382477760315, | |
| "eval_runtime": 40.237, | |
| "eval_samples_per_second": 23.386, | |
| "eval_steps_per_second": 2.933, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 6.702702702702704e-05, | |
| "loss": 0.316, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 6.582582582582583e-05, | |
| "loss": 0.1016, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 6.462462462462463e-05, | |
| "loss": 0.1508, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 6.342342342342342e-05, | |
| "loss": 0.2685, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.222222222222222e-05, | |
| "loss": 0.2662, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 6.102102102102102e-05, | |
| "loss": 0.2772, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 5.981981981981982e-05, | |
| "loss": 0.1013, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 5.8618618618618625e-05, | |
| "loss": 0.1762, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.741741741741742e-05, | |
| "loss": 0.1514, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 5.621621621621622e-05, | |
| "loss": 0.2041, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.9213602550478215, | |
| "eval_loss": 0.2855222523212433, | |
| "eval_runtime": 39.5438, | |
| "eval_samples_per_second": 23.796, | |
| "eval_steps_per_second": 2.984, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 5.5015015015015016e-05, | |
| "loss": 0.1939, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.381381381381382e-05, | |
| "loss": 0.0919, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 5.261261261261261e-05, | |
| "loss": 0.2731, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 5.1411411411411414e-05, | |
| "loss": 0.1865, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 5.0210210210210216e-05, | |
| "loss": 0.238, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 4.900900900900901e-05, | |
| "loss": 0.0804, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 4.7807807807807806e-05, | |
| "loss": 0.3592, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.660660660660661e-05, | |
| "loss": 0.323, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 4.540540540540541e-05, | |
| "loss": 0.1983, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 4.420420420420421e-05, | |
| "loss": 0.2541, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "eval_accuracy": 0.9330499468650372, | |
| "eval_loss": 0.25022733211517334, | |
| "eval_runtime": 39.5082, | |
| "eval_samples_per_second": 23.818, | |
| "eval_steps_per_second": 2.987, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 4.3003003003003006e-05, | |
| "loss": 0.3586, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 4.180180180180181e-05, | |
| "loss": 0.2121, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.06006006006006e-05, | |
| "loss": 0.1308, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 3.93993993993994e-05, | |
| "loss": 0.2163, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 3.81981981981982e-05, | |
| "loss": 0.0668, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 3.6996996996996994e-05, | |
| "loss": 0.1516, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 3.57957957957958e-05, | |
| "loss": 0.1323, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.45945945945946e-05, | |
| "loss": 0.237, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 3.33933933933934e-05, | |
| "loss": 0.1337, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.2192192192192194e-05, | |
| "loss": 0.1203, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.9362380446333688, | |
| "eval_loss": 0.25774362683296204, | |
| "eval_runtime": 39.3333, | |
| "eval_samples_per_second": 23.924, | |
| "eval_steps_per_second": 3.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 3.0990990990990995e-05, | |
| "loss": 0.0531, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 2.978978978978979e-05, | |
| "loss": 0.1448, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 2.858858858858859e-05, | |
| "loss": 0.0946, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 2.7387387387387387e-05, | |
| "loss": 0.0927, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2.618618618618619e-05, | |
| "loss": 0.1215, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.4984984984984987e-05, | |
| "loss": 0.1332, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 2.3783783783783785e-05, | |
| "loss": 0.1657, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.2582582582582583e-05, | |
| "loss": 0.2, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 2.1381381381381382e-05, | |
| "loss": 0.1323, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 2.018018018018018e-05, | |
| "loss": 0.1594, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_accuracy": 0.9458023379383634, | |
| "eval_loss": 0.22263780236244202, | |
| "eval_runtime": 39.564, | |
| "eval_samples_per_second": 23.784, | |
| "eval_steps_per_second": 2.983, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 1.8978978978978982e-05, | |
| "loss": 0.1963, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.18, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 1.6576576576576578e-05, | |
| "loss": 0.1519, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 1.5375375375375377e-05, | |
| "loss": 0.1375, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 1.4174174174174173e-05, | |
| "loss": 0.1323, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1.2972972972972975e-05, | |
| "loss": 0.128, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 1.1771771771771773e-05, | |
| "loss": 0.0505, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.057057057057057e-05, | |
| "loss": 0.0957, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 9.36936936936937e-06, | |
| "loss": 0.043, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 8.168168168168168e-06, | |
| "loss": 0.1015, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_accuracy": 0.9436769394261424, | |
| "eval_loss": 0.236781507730484, | |
| "eval_runtime": 39.398, | |
| "eval_samples_per_second": 23.884, | |
| "eval_steps_per_second": 2.995, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 6.966966966966967e-06, | |
| "loss": 0.1853, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 5.765765765765766e-06, | |
| "loss": 0.0874, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 4.5645645645645645e-06, | |
| "loss": 0.0949, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.3633633633633636e-06, | |
| "loss": 0.1901, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 2.1621621621621623e-06, | |
| "loss": 0.1235, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 9.60960960960961e-07, | |
| "loss": 0.0785, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1665, | |
| "total_flos": 2.0875695162281165e+18, | |
| "train_loss": 0.38661149321375665, | |
| "train_runtime": 2052.9844, | |
| "train_samples_per_second": 12.976, | |
| "train_steps_per_second": 0.811 | |
| } | |
| ], | |
| "max_steps": 1665, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.0875695162281165e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |