| { | |
| "best_metric": 0.9044117647058824, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-papsmear/checkpoint-360", | |
| "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": 0.2426470588235294, | |
| "eval_loss": 1.7588815689086914, | |
| "eval_runtime": 30.041, | |
| "eval_samples_per_second": 4.527, | |
| "eval_steps_per_second": 0.166, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 1.042138695716858, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.7862, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.9487179487179487, | |
| "eval_accuracy": 0.38235294117647056, | |
| "eval_loss": 1.58797025680542, | |
| "eval_runtime": 32.3153, | |
| "eval_samples_per_second": 4.209, | |
| "eval_steps_per_second": 0.155, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 0.996979296207428, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.6727, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.9743589743589745, | |
| "eval_accuracy": 0.4264705882352941, | |
| "eval_loss": 1.4212044477462769, | |
| "eval_runtime": 31.937, | |
| "eval_samples_per_second": 4.258, | |
| "eval_steps_per_second": 0.157, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 1.1018966436386108, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.5102, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5808823529411765, | |
| "eval_loss": 1.2241116762161255, | |
| "eval_runtime": 30.9919, | |
| "eval_samples_per_second": 4.388, | |
| "eval_steps_per_second": 0.161, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "grad_norm": 1.025856614112854, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.3247, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "eval_accuracy": 0.6102941176470589, | |
| "eval_loss": 1.0905669927597046, | |
| "eval_runtime": 31.2612, | |
| "eval_samples_per_second": 4.35, | |
| "eval_steps_per_second": 0.16, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "grad_norm": 3.468245029449463, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 1.1047, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.948717948717949, | |
| "eval_accuracy": 0.6764705882352942, | |
| "eval_loss": 0.9746549129486084, | |
| "eval_runtime": 29.9981, | |
| "eval_samples_per_second": 4.534, | |
| "eval_steps_per_second": 0.167, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 1.6158350706100464, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.9405, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.9743589743589745, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.8744558691978455, | |
| "eval_runtime": 29.8899, | |
| "eval_samples_per_second": 4.55, | |
| "eval_steps_per_second": 0.167, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 7.17948717948718, | |
| "grad_norm": 2.7250912189483643, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 0.823, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.7832698822021484, | |
| "eval_runtime": 29.3695, | |
| "eval_samples_per_second": 4.631, | |
| "eval_steps_per_second": 0.17, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 8.205128205128204, | |
| "grad_norm": 1.1131880283355713, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 0.7244, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.923076923076923, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.7159935235977173, | |
| "eval_runtime": 30.5505, | |
| "eval_samples_per_second": 4.452, | |
| "eval_steps_per_second": 0.164, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 1.162032961845398, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.6367, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 9.948717948717949, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.7327755093574524, | |
| "eval_runtime": 31.3159, | |
| "eval_samples_per_second": 4.343, | |
| "eval_steps_per_second": 0.16, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 10.256410256410255, | |
| "grad_norm": 2.753892421722412, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.5537, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 10.974358974358974, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.6572667956352234, | |
| "eval_runtime": 29.9075, | |
| "eval_samples_per_second": 4.547, | |
| "eval_steps_per_second": 0.167, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 11.282051282051283, | |
| "grad_norm": 1.8267817497253418, | |
| "learning_rate": 4.197530864197531e-05, | |
| "loss": 0.484, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8088235294117647, | |
| "eval_loss": 0.5988054275512695, | |
| "eval_runtime": 29.8243, | |
| "eval_samples_per_second": 4.56, | |
| "eval_steps_per_second": 0.168, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 3.6334152221679688, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.4642, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 12.923076923076923, | |
| "eval_accuracy": 0.7941176470588235, | |
| "eval_loss": 0.626797080039978, | |
| "eval_runtime": 29.8057, | |
| "eval_samples_per_second": 4.563, | |
| "eval_steps_per_second": 0.168, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 2.4481348991394043, | |
| "learning_rate": 3.950617283950617e-05, | |
| "loss": 0.4166, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 13.948717948717949, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.6549181342124939, | |
| "eval_runtime": 29.9078, | |
| "eval_samples_per_second": 4.547, | |
| "eval_steps_per_second": 0.167, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 14.35897435897436, | |
| "grad_norm": 2.9035937786102295, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.4106, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 14.974358974358974, | |
| "eval_accuracy": 0.8529411764705882, | |
| "eval_loss": 0.5330095887184143, | |
| "eval_runtime": 29.4929, | |
| "eval_samples_per_second": 4.611, | |
| "eval_steps_per_second": 0.17, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 3.0346601009368896, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3947, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.5133553147315979, | |
| "eval_runtime": 29.8094, | |
| "eval_samples_per_second": 4.562, | |
| "eval_steps_per_second": 0.168, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 16.41025641025641, | |
| "grad_norm": 2.665196657180786, | |
| "learning_rate": 3.580246913580247e-05, | |
| "loss": 0.3469, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.5879342555999756, | |
| "eval_runtime": 29.7747, | |
| "eval_samples_per_second": 4.568, | |
| "eval_steps_per_second": 0.168, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 17.435897435897434, | |
| "grad_norm": 4.382056713104248, | |
| "learning_rate": 3.45679012345679e-05, | |
| "loss": 0.3151, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 17.94871794871795, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.5682740211486816, | |
| "eval_runtime": 29.9811, | |
| "eval_samples_per_second": 4.536, | |
| "eval_steps_per_second": 0.167, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "grad_norm": 1.3831549882888794, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2946, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 18.974358974358974, | |
| "eval_accuracy": 0.8161764705882353, | |
| "eval_loss": 0.5382511615753174, | |
| "eval_runtime": 29.6021, | |
| "eval_samples_per_second": 4.594, | |
| "eval_steps_per_second": 0.169, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 19.487179487179485, | |
| "grad_norm": 2.7299916744232178, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 0.2927, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8161764705882353, | |
| "eval_loss": 0.568187952041626, | |
| "eval_runtime": 29.6931, | |
| "eval_samples_per_second": 4.58, | |
| "eval_steps_per_second": 0.168, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 20.51282051282051, | |
| "grad_norm": 2.4772286415100098, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.2879, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 20.923076923076923, | |
| "eval_accuracy": 0.8602941176470589, | |
| "eval_loss": 0.4721927046775818, | |
| "eval_runtime": 29.6838, | |
| "eval_samples_per_second": 4.582, | |
| "eval_steps_per_second": 0.168, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 21.53846153846154, | |
| "grad_norm": 1.078134536743164, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.2512, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 21.94871794871795, | |
| "eval_accuracy": 0.8455882352941176, | |
| "eval_loss": 0.48056113719940186, | |
| "eval_runtime": 29.966, | |
| "eval_samples_per_second": 4.538, | |
| "eval_steps_per_second": 0.167, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 22.564102564102566, | |
| "grad_norm": 1.4218604564666748, | |
| "learning_rate": 2.839506172839506e-05, | |
| "loss": 0.2633, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 22.974358974358974, | |
| "eval_accuracy": 0.8455882352941176, | |
| "eval_loss": 0.4712737500667572, | |
| "eval_runtime": 30.7829, | |
| "eval_samples_per_second": 4.418, | |
| "eval_steps_per_second": 0.162, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 23.58974358974359, | |
| "grad_norm": 1.4475338459014893, | |
| "learning_rate": 2.7160493827160493e-05, | |
| "loss": 0.2286, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.5166775584220886, | |
| "eval_runtime": 29.6495, | |
| "eval_samples_per_second": 4.587, | |
| "eval_steps_per_second": 0.169, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 24.615384615384617, | |
| "grad_norm": 2.2939038276672363, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.2265, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 24.923076923076923, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.3885728120803833, | |
| "eval_runtime": 29.8244, | |
| "eval_samples_per_second": 4.56, | |
| "eval_steps_per_second": 0.168, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "grad_norm": 2.014761209487915, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.2107, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 25.94871794871795, | |
| "eval_accuracy": 0.8676470588235294, | |
| "eval_loss": 0.4395664930343628, | |
| "eval_runtime": 30.087, | |
| "eval_samples_per_second": 4.52, | |
| "eval_steps_per_second": 0.166, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 1.4246245622634888, | |
| "learning_rate": 2.345679012345679e-05, | |
| "loss": 0.2044, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 26.974358974358974, | |
| "eval_accuracy": 0.8455882352941176, | |
| "eval_loss": 0.47336432337760925, | |
| "eval_runtime": 30.2689, | |
| "eval_samples_per_second": 4.493, | |
| "eval_steps_per_second": 0.165, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 27.692307692307693, | |
| "grad_norm": 1.1730149984359741, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1925, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8529411764705882, | |
| "eval_loss": 0.4605894684791565, | |
| "eval_runtime": 29.9687, | |
| "eval_samples_per_second": 4.538, | |
| "eval_steps_per_second": 0.167, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 28.71794871794872, | |
| "grad_norm": 1.8061479330062866, | |
| "learning_rate": 2.0987654320987655e-05, | |
| "loss": 0.1866, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 28.923076923076923, | |
| "eval_accuracy": 0.8308823529411765, | |
| "eval_loss": 0.506081223487854, | |
| "eval_runtime": 29.7747, | |
| "eval_samples_per_second": 4.568, | |
| "eval_steps_per_second": 0.168, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 29.743589743589745, | |
| "grad_norm": 3.999681234359741, | |
| "learning_rate": 1.9753086419753087e-05, | |
| "loss": 0.1928, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 29.94871794871795, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.42022156715393066, | |
| "eval_runtime": 31.5903, | |
| "eval_samples_per_second": 4.305, | |
| "eval_steps_per_second": 0.158, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 30.76923076923077, | |
| "grad_norm": 1.7130581140518188, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1907, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 30.974358974358974, | |
| "eval_accuracy": 0.8308823529411765, | |
| "eval_loss": 0.5120359659194946, | |
| "eval_runtime": 29.2951, | |
| "eval_samples_per_second": 4.642, | |
| "eval_steps_per_second": 0.171, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 31.794871794871796, | |
| "grad_norm": 2.6331541538238525, | |
| "learning_rate": 1.728395061728395e-05, | |
| "loss": 0.1631, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8676470588235294, | |
| "eval_loss": 0.41645094752311707, | |
| "eval_runtime": 29.9412, | |
| "eval_samples_per_second": 4.542, | |
| "eval_steps_per_second": 0.167, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 32.82051282051282, | |
| "grad_norm": 2.0035409927368164, | |
| "learning_rate": 1.604938271604938e-05, | |
| "loss": 0.1654, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 32.92307692307692, | |
| "eval_accuracy": 0.8676470588235294, | |
| "eval_loss": 0.45997411012649536, | |
| "eval_runtime": 29.5665, | |
| "eval_samples_per_second": 4.6, | |
| "eval_steps_per_second": 0.169, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 33.84615384615385, | |
| "grad_norm": 0.8273878693580627, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.154, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 33.94871794871795, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.3834398686885834, | |
| "eval_runtime": 29.8196, | |
| "eval_samples_per_second": 4.561, | |
| "eval_steps_per_second": 0.168, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 34.87179487179487, | |
| "grad_norm": 1.8872778415679932, | |
| "learning_rate": 1.3580246913580247e-05, | |
| "loss": 0.1459, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 34.97435897435897, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.36863845586776733, | |
| "eval_runtime": 29.8029, | |
| "eval_samples_per_second": 4.563, | |
| "eval_steps_per_second": 0.168, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 35.8974358974359, | |
| "grad_norm": 1.480739712715149, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.1452, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8676470588235294, | |
| "eval_loss": 0.41742780804634094, | |
| "eval_runtime": 30.4904, | |
| "eval_samples_per_second": 4.46, | |
| "eval_steps_per_second": 0.164, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "grad_norm": 2.4121947288513184, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.1548, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "eval_accuracy": 0.9044117647058824, | |
| "eval_loss": 0.379115492105484, | |
| "eval_runtime": 31.2755, | |
| "eval_samples_per_second": 4.348, | |
| "eval_steps_per_second": 0.16, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "grad_norm": 1.7541086673736572, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 0.1395, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "eval_accuracy": 0.8529411764705882, | |
| "eval_loss": 0.4511679708957672, | |
| "eval_runtime": 29.0831, | |
| "eval_samples_per_second": 4.676, | |
| "eval_steps_per_second": 0.172, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "grad_norm": 1.2144207954406738, | |
| "learning_rate": 8.641975308641975e-06, | |
| "loss": 0.1333, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.37747910618782043, | |
| "eval_runtime": 29.5567, | |
| "eval_samples_per_second": 4.601, | |
| "eval_steps_per_second": 0.169, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 1.966362714767456, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.1236, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.3665925860404968, | |
| "eval_runtime": 29.5708, | |
| "eval_samples_per_second": 4.599, | |
| "eval_steps_per_second": 0.169, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 40.92307692307692, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.38919442892074585, | |
| "eval_runtime": 29.9522, | |
| "eval_samples_per_second": 4.541, | |
| "eval_steps_per_second": 0.167, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 41.02564102564103, | |
| "grad_norm": 1.2910165786743164, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.1314, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 41.94871794871795, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.3831816613674164, | |
| "eval_runtime": 30.006, | |
| "eval_samples_per_second": 4.532, | |
| "eval_steps_per_second": 0.167, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 42.05128205128205, | |
| "grad_norm": 1.5890743732452393, | |
| "learning_rate": 4.938271604938272e-06, | |
| "loss": 0.1322, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 42.97435897435897, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.39192765951156616, | |
| "eval_runtime": 30.5878, | |
| "eval_samples_per_second": 4.446, | |
| "eval_steps_per_second": 0.163, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 43.07692307692308, | |
| "grad_norm": 0.9582741260528564, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.1156, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.369939923286438, | |
| "eval_runtime": 30.3858, | |
| "eval_samples_per_second": 4.476, | |
| "eval_steps_per_second": 0.165, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 44.1025641025641, | |
| "grad_norm": 2.247335910797119, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 0.1222, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 44.92307692307692, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.38276419043540955, | |
| "eval_runtime": 29.9911, | |
| "eval_samples_per_second": 4.535, | |
| "eval_steps_per_second": 0.167, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 45.12820512820513, | |
| "grad_norm": 0.5052188038825989, | |
| "learning_rate": 1.234567901234568e-06, | |
| "loss": 0.1254, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 45.94871794871795, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.38526448607444763, | |
| "eval_runtime": 31.3146, | |
| "eval_samples_per_second": 4.343, | |
| "eval_steps_per_second": 0.16, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "grad_norm": 0.5415890216827393, | |
| "learning_rate": 0.0, | |
| "loss": 0.1129, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.38528940081596375, | |
| "eval_runtime": 30.9585, | |
| "eval_samples_per_second": 4.393, | |
| "eval_steps_per_second": 0.162, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "step": 450, | |
| "total_flos": 4.3781443993328026e+18, | |
| "train_loss": 0.4221388864517212, | |
| "train_runtime": 14616.4414, | |
| "train_samples_per_second": 4.187, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "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 | |
| } | |