| { | |
| "best_metric": 0.9338235294117647, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-papsmear/checkpoint-419", | |
| "epoch": 46.15384615384615, | |
| "eval_steps": 500, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9230769230769231, | |
| "eval_accuracy": 0.2647058823529412, | |
| "eval_loss": 1.7345659732818604, | |
| "eval_runtime": 30.9498, | |
| "eval_samples_per_second": 4.394, | |
| "eval_steps_per_second": 0.162, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 1.5590156316757202, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.7645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.9487179487179487, | |
| "eval_accuracy": 0.3088235294117647, | |
| "eval_loss": 1.6151821613311768, | |
| "eval_runtime": 30.7387, | |
| "eval_samples_per_second": 4.424, | |
| "eval_steps_per_second": 0.163, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 1.000002384185791, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.661, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.9743589743589745, | |
| "eval_accuracy": 0.4117647058823529, | |
| "eval_loss": 1.4663141965866089, | |
| "eval_runtime": 30.7848, | |
| "eval_samples_per_second": 4.418, | |
| "eval_steps_per_second": 0.162, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 1.144618272781372, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.496, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4852941176470588, | |
| "eval_loss": 1.2988938093185425, | |
| "eval_runtime": 29.3106, | |
| "eval_samples_per_second": 4.64, | |
| "eval_steps_per_second": 0.171, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "grad_norm": 0.9698243141174316, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.3097, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "eval_accuracy": 0.5588235294117647, | |
| "eval_loss": 1.1490617990493774, | |
| "eval_runtime": 29.781, | |
| "eval_samples_per_second": 4.567, | |
| "eval_steps_per_second": 0.168, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "grad_norm": 1.00479257106781, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 1.091, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.948717948717949, | |
| "eval_accuracy": 0.7205882352941176, | |
| "eval_loss": 0.9932733178138733, | |
| "eval_runtime": 30.4494, | |
| "eval_samples_per_second": 4.466, | |
| "eval_steps_per_second": 0.164, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 1.4680265188217163, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.9088, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.9743589743589745, | |
| "eval_accuracy": 0.6985294117647058, | |
| "eval_loss": 0.9170573353767395, | |
| "eval_runtime": 29.5689, | |
| "eval_samples_per_second": 4.599, | |
| "eval_steps_per_second": 0.169, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 7.17948717948718, | |
| "grad_norm": 1.2828285694122314, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 0.7858, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7720588235294118, | |
| "eval_loss": 0.8300582766532898, | |
| "eval_runtime": 30.9278, | |
| "eval_samples_per_second": 4.397, | |
| "eval_steps_per_second": 0.162, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 8.205128205128204, | |
| "grad_norm": 1.7692698240280151, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 0.7016, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.923076923076923, | |
| "eval_accuracy": 0.7352941176470589, | |
| "eval_loss": 0.7925190925598145, | |
| "eval_runtime": 32.3375, | |
| "eval_samples_per_second": 4.206, | |
| "eval_steps_per_second": 0.155, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 1.7534127235412598, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.6136, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 9.948717948717949, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.6992273330688477, | |
| "eval_runtime": 30.502, | |
| "eval_samples_per_second": 4.459, | |
| "eval_steps_per_second": 0.164, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 10.256410256410255, | |
| "grad_norm": 1.2740432024002075, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.532, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 10.974358974358974, | |
| "eval_accuracy": 0.8308823529411765, | |
| "eval_loss": 0.6400743126869202, | |
| "eval_runtime": 31.9094, | |
| "eval_samples_per_second": 4.262, | |
| "eval_steps_per_second": 0.157, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 11.282051282051283, | |
| "grad_norm": 1.563349723815918, | |
| "learning_rate": 4.197530864197531e-05, | |
| "loss": 0.5018, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.5786880254745483, | |
| "eval_runtime": 29.8171, | |
| "eval_samples_per_second": 4.561, | |
| "eval_steps_per_second": 0.168, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 2.5129995346069336, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.4279, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 12.923076923076923, | |
| "eval_accuracy": 0.8088235294117647, | |
| "eval_loss": 0.6129594445228577, | |
| "eval_runtime": 29.826, | |
| "eval_samples_per_second": 4.56, | |
| "eval_steps_per_second": 0.168, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 1.6143475770950317, | |
| "learning_rate": 3.950617283950617e-05, | |
| "loss": 0.4116, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 13.948717948717949, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.5089898109436035, | |
| "eval_runtime": 29.9983, | |
| "eval_samples_per_second": 4.534, | |
| "eval_steps_per_second": 0.167, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 14.35897435897436, | |
| "grad_norm": 1.6241114139556885, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.3848, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 14.974358974358974, | |
| "eval_accuracy": 0.8676470588235294, | |
| "eval_loss": 0.5165212154388428, | |
| "eval_runtime": 30.2024, | |
| "eval_samples_per_second": 4.503, | |
| "eval_steps_per_second": 0.166, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 2.7321174144744873, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3449, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.4842991530895233, | |
| "eval_runtime": 29.5578, | |
| "eval_samples_per_second": 4.601, | |
| "eval_steps_per_second": 0.169, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 16.41025641025641, | |
| "grad_norm": 1.7041429281234741, | |
| "learning_rate": 3.580246913580247e-05, | |
| "loss": 0.3008, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "eval_accuracy": 0.8455882352941176, | |
| "eval_loss": 0.5460208058357239, | |
| "eval_runtime": 29.7055, | |
| "eval_samples_per_second": 4.578, | |
| "eval_steps_per_second": 0.168, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 17.435897435897434, | |
| "grad_norm": 2.1159939765930176, | |
| "learning_rate": 3.45679012345679e-05, | |
| "loss": 0.2797, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 17.94871794871795, | |
| "eval_accuracy": 0.8308823529411765, | |
| "eval_loss": 0.4984971880912781, | |
| "eval_runtime": 29.7303, | |
| "eval_samples_per_second": 4.574, | |
| "eval_steps_per_second": 0.168, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "grad_norm": 1.050848126411438, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2696, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 18.974358974358974, | |
| "eval_accuracy": 0.8455882352941176, | |
| "eval_loss": 0.5585992336273193, | |
| "eval_runtime": 29.5612, | |
| "eval_samples_per_second": 4.601, | |
| "eval_steps_per_second": 0.169, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 19.487179487179485, | |
| "grad_norm": 2.385378360748291, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 0.2633, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9044117647058824, | |
| "eval_loss": 0.43493831157684326, | |
| "eval_runtime": 29.6728, | |
| "eval_samples_per_second": 4.583, | |
| "eval_steps_per_second": 0.169, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 20.51282051282051, | |
| "grad_norm": 1.972583293914795, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.2569, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 20.923076923076923, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.4017449617385864, | |
| "eval_runtime": 31.5372, | |
| "eval_samples_per_second": 4.312, | |
| "eval_steps_per_second": 0.159, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 21.53846153846154, | |
| "grad_norm": 2.712113380432129, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.27, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 21.94871794871795, | |
| "eval_accuracy": 0.8602941176470589, | |
| "eval_loss": 0.4758412837982178, | |
| "eval_runtime": 30.0407, | |
| "eval_samples_per_second": 4.527, | |
| "eval_steps_per_second": 0.166, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 22.564102564102566, | |
| "grad_norm": 1.7184677124023438, | |
| "learning_rate": 2.839506172839506e-05, | |
| "loss": 0.2706, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 22.974358974358974, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.41326794028282166, | |
| "eval_runtime": 29.7459, | |
| "eval_samples_per_second": 4.572, | |
| "eval_steps_per_second": 0.168, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 23.58974358974359, | |
| "grad_norm": 1.8792766332626343, | |
| "learning_rate": 2.7160493827160493e-05, | |
| "loss": 0.2211, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9117647058823529, | |
| "eval_loss": 0.3844151794910431, | |
| "eval_runtime": 29.8072, | |
| "eval_samples_per_second": 4.563, | |
| "eval_steps_per_second": 0.168, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 24.615384615384617, | |
| "grad_norm": 2.2763214111328125, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.1977, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 24.923076923076923, | |
| "eval_accuracy": 0.9264705882352942, | |
| "eval_loss": 0.34974199533462524, | |
| "eval_runtime": 29.6847, | |
| "eval_samples_per_second": 4.581, | |
| "eval_steps_per_second": 0.168, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "grad_norm": 4.190616130828857, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.1969, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 25.94871794871795, | |
| "eval_accuracy": 0.9044117647058824, | |
| "eval_loss": 0.37360796332359314, | |
| "eval_runtime": 31.1254, | |
| "eval_samples_per_second": 4.369, | |
| "eval_steps_per_second": 0.161, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 0.6893692016601562, | |
| "learning_rate": 2.345679012345679e-05, | |
| "loss": 0.1776, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 26.974358974358974, | |
| "eval_accuracy": 0.9044117647058824, | |
| "eval_loss": 0.3796656131744385, | |
| "eval_runtime": 29.8455, | |
| "eval_samples_per_second": 4.557, | |
| "eval_steps_per_second": 0.168, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 27.692307692307693, | |
| "grad_norm": 2.18731427192688, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1787, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.39490777254104614, | |
| "eval_runtime": 29.2795, | |
| "eval_samples_per_second": 4.645, | |
| "eval_steps_per_second": 0.171, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 28.71794871794872, | |
| "grad_norm": 1.656586766242981, | |
| "learning_rate": 2.0987654320987655e-05, | |
| "loss": 0.18, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 28.923076923076923, | |
| "eval_accuracy": 0.9264705882352942, | |
| "eval_loss": 0.32775887846946716, | |
| "eval_runtime": 29.3934, | |
| "eval_samples_per_second": 4.627, | |
| "eval_steps_per_second": 0.17, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 29.743589743589745, | |
| "grad_norm": 1.3221951723098755, | |
| "learning_rate": 1.9753086419753087e-05, | |
| "loss": 0.1797, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 29.94871794871795, | |
| "eval_accuracy": 0.9044117647058824, | |
| "eval_loss": 0.36148715019226074, | |
| "eval_runtime": 29.46, | |
| "eval_samples_per_second": 4.616, | |
| "eval_steps_per_second": 0.17, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 30.76923076923077, | |
| "grad_norm": 1.227844476699829, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1665, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 30.974358974358974, | |
| "eval_accuracy": 0.8602941176470589, | |
| "eval_loss": 0.4174344539642334, | |
| "eval_runtime": 29.6798, | |
| "eval_samples_per_second": 4.582, | |
| "eval_steps_per_second": 0.168, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 31.794871794871796, | |
| "grad_norm": 2.3732173442840576, | |
| "learning_rate": 1.728395061728395e-05, | |
| "loss": 0.163, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.3574081063270569, | |
| "eval_runtime": 29.8114, | |
| "eval_samples_per_second": 4.562, | |
| "eval_steps_per_second": 0.168, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 32.82051282051282, | |
| "grad_norm": 2.783026933670044, | |
| "learning_rate": 1.604938271604938e-05, | |
| "loss": 0.1498, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 32.92307692307692, | |
| "eval_accuracy": 0.9044117647058824, | |
| "eval_loss": 0.35905760526657104, | |
| "eval_runtime": 30.5584, | |
| "eval_samples_per_second": 4.45, | |
| "eval_steps_per_second": 0.164, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 33.84615384615385, | |
| "grad_norm": 2.496835231781006, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1405, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 33.94871794871795, | |
| "eval_accuracy": 0.9191176470588235, | |
| "eval_loss": 0.30173459649086, | |
| "eval_runtime": 30.2786, | |
| "eval_samples_per_second": 4.492, | |
| "eval_steps_per_second": 0.165, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 34.87179487179487, | |
| "grad_norm": 2.3252382278442383, | |
| "learning_rate": 1.3580246913580247e-05, | |
| "loss": 0.155, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 34.97435897435897, | |
| "eval_accuracy": 0.9264705882352942, | |
| "eval_loss": 0.3303259611129761, | |
| "eval_runtime": 29.5808, | |
| "eval_samples_per_second": 4.598, | |
| "eval_steps_per_second": 0.169, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 35.8974358974359, | |
| "grad_norm": 0.8514438271522522, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.1519, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.3559113144874573, | |
| "eval_runtime": 30.264, | |
| "eval_samples_per_second": 4.494, | |
| "eval_steps_per_second": 0.165, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "grad_norm": 0.9986769556999207, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.1415, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "eval_accuracy": 0.9191176470588235, | |
| "eval_loss": 0.2890462279319763, | |
| "eval_runtime": 30.7844, | |
| "eval_samples_per_second": 4.418, | |
| "eval_steps_per_second": 0.162, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "grad_norm": 0.9639208912849426, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 0.1256, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.3445207476615906, | |
| "eval_runtime": 29.9807, | |
| "eval_samples_per_second": 4.536, | |
| "eval_steps_per_second": 0.167, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "grad_norm": 0.9389523267745972, | |
| "learning_rate": 8.641975308641975e-06, | |
| "loss": 0.1217, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "eval_accuracy": 0.9117647058823529, | |
| "eval_loss": 0.3434993028640747, | |
| "eval_runtime": 30.2833, | |
| "eval_samples_per_second": 4.491, | |
| "eval_steps_per_second": 0.165, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 7.135587215423584, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.1285, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9191176470588235, | |
| "eval_loss": 0.30249181389808655, | |
| "eval_runtime": 29.8301, | |
| "eval_samples_per_second": 4.559, | |
| "eval_steps_per_second": 0.168, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 40.92307692307692, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.36019423604011536, | |
| "eval_runtime": 29.9271, | |
| "eval_samples_per_second": 4.544, | |
| "eval_steps_per_second": 0.167, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 41.02564102564103, | |
| "grad_norm": 0.5793786644935608, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.1301, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 41.94871794871795, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.3336350917816162, | |
| "eval_runtime": 32.0768, | |
| "eval_samples_per_second": 4.24, | |
| "eval_steps_per_second": 0.156, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 42.05128205128205, | |
| "grad_norm": 2.5887136459350586, | |
| "learning_rate": 4.938271604938272e-06, | |
| "loss": 0.1243, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 42.97435897435897, | |
| "eval_accuracy": 0.9338235294117647, | |
| "eval_loss": 0.28249993920326233, | |
| "eval_runtime": 29.95, | |
| "eval_samples_per_second": 4.541, | |
| "eval_steps_per_second": 0.167, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 43.07692307692308, | |
| "grad_norm": 1.4639347791671753, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.1191, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9264705882352942, | |
| "eval_loss": 0.28346800804138184, | |
| "eval_runtime": 32.4599, | |
| "eval_samples_per_second": 4.19, | |
| "eval_steps_per_second": 0.154, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 44.1025641025641, | |
| "grad_norm": 1.6088590621948242, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 0.1221, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 44.92307692307692, | |
| "eval_accuracy": 0.9191176470588235, | |
| "eval_loss": 0.2723533809185028, | |
| "eval_runtime": 30.5746, | |
| "eval_samples_per_second": 4.448, | |
| "eval_steps_per_second": 0.164, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 45.12820512820513, | |
| "grad_norm": 0.848240077495575, | |
| "learning_rate": 1.234567901234568e-06, | |
| "loss": 0.1151, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 45.94871794871795, | |
| "eval_accuracy": 0.9191176470588235, | |
| "eval_loss": 0.27075088024139404, | |
| "eval_runtime": 30.0665, | |
| "eval_samples_per_second": 4.523, | |
| "eval_steps_per_second": 0.166, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "grad_norm": 3.371528148651123, | |
| "learning_rate": 0.0, | |
| "loss": 0.1195, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "eval_accuracy": 0.9191176470588235, | |
| "eval_loss": 0.2707464396953583, | |
| "eval_runtime": 33.0815, | |
| "eval_samples_per_second": 4.111, | |
| "eval_steps_per_second": 0.151, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "step": 450, | |
| "total_flos": 4.3781443993328026e+18, | |
| "train_loss": 0.4078153912226359, | |
| "train_runtime": 14896.2203, | |
| "train_samples_per_second": 4.108, | |
| "train_steps_per_second": 0.03 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.3781443993328026e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |