| { | |
| "best_metric": 0.9117647058823529, | |
| "best_model_checkpoint": "resnet-18-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": 0.16911764705882354, | |
| "eval_loss": 1.9256452322006226, | |
| "eval_runtime": 31.7059, | |
| "eval_samples_per_second": 4.289, | |
| "eval_steps_per_second": 0.158, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 7.704298496246338, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.9692, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.9487179487179487, | |
| "eval_accuracy": 0.2867647058823529, | |
| "eval_loss": 1.6556739807128906, | |
| "eval_runtime": 29.6621, | |
| "eval_samples_per_second": 4.585, | |
| "eval_steps_per_second": 0.169, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 7.785455703735352, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.7979, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.9743589743589745, | |
| "eval_accuracy": 0.5367647058823529, | |
| "eval_loss": 1.330020785331726, | |
| "eval_runtime": 29.366, | |
| "eval_samples_per_second": 4.631, | |
| "eval_steps_per_second": 0.17, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 5.984652519226074, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.5079, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6323529411764706, | |
| "eval_loss": 1.0482187271118164, | |
| "eval_runtime": 29.1874, | |
| "eval_samples_per_second": 4.66, | |
| "eval_steps_per_second": 0.171, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "grad_norm": 3.9865710735321045, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.217, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "eval_accuracy": 0.6617647058823529, | |
| "eval_loss": 0.901944637298584, | |
| "eval_runtime": 28.4101, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 0.176, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "grad_norm": 3.698692560195923, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.9536, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.948717948717949, | |
| "eval_accuracy": 0.6691176470588235, | |
| "eval_loss": 0.7686564922332764, | |
| "eval_runtime": 28.4094, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 0.176, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 3.810110569000244, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.7881, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.9743589743589745, | |
| "eval_accuracy": 0.7720588235294118, | |
| "eval_loss": 0.6149626970291138, | |
| "eval_runtime": 27.9452, | |
| "eval_samples_per_second": 4.867, | |
| "eval_steps_per_second": 0.179, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 7.17948717948718, | |
| "grad_norm": 2.9986612796783447, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 0.68, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.5480948090553284, | |
| "eval_runtime": 28.3139, | |
| "eval_samples_per_second": 4.803, | |
| "eval_steps_per_second": 0.177, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 8.205128205128204, | |
| "grad_norm": 3.407658100128174, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 0.5678, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.923076923076923, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.5341328978538513, | |
| "eval_runtime": 28.1469, | |
| "eval_samples_per_second": 4.832, | |
| "eval_steps_per_second": 0.178, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 3.0941154956817627, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5169, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 9.948717948717949, | |
| "eval_accuracy": 0.7941176470588235, | |
| "eval_loss": 0.47997093200683594, | |
| "eval_runtime": 27.9374, | |
| "eval_samples_per_second": 4.868, | |
| "eval_steps_per_second": 0.179, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 10.256410256410255, | |
| "grad_norm": 2.827873706817627, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.4838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 10.974358974358974, | |
| "eval_accuracy": 0.8235294117647058, | |
| "eval_loss": 0.43556123971939087, | |
| "eval_runtime": 28.302, | |
| "eval_samples_per_second": 4.805, | |
| "eval_steps_per_second": 0.177, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 11.282051282051283, | |
| "grad_norm": 3.534836769104004, | |
| "learning_rate": 4.197530864197531e-05, | |
| "loss": 0.4738, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8161764705882353, | |
| "eval_loss": 0.45729342103004456, | |
| "eval_runtime": 28.5221, | |
| "eval_samples_per_second": 4.768, | |
| "eval_steps_per_second": 0.175, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 3.520214319229126, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.3798, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 12.923076923076923, | |
| "eval_accuracy": 0.8088235294117647, | |
| "eval_loss": 0.4262649118900299, | |
| "eval_runtime": 28.0763, | |
| "eval_samples_per_second": 4.844, | |
| "eval_steps_per_second": 0.178, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 2.46077036857605, | |
| "learning_rate": 3.950617283950617e-05, | |
| "loss": 0.3431, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 13.948717948717949, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.4158500134944916, | |
| "eval_runtime": 27.555, | |
| "eval_samples_per_second": 4.936, | |
| "eval_steps_per_second": 0.181, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 14.35897435897436, | |
| "grad_norm": 2.5697851181030273, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.3282, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 14.974358974358974, | |
| "eval_accuracy": 0.8602941176470589, | |
| "eval_loss": 0.3787141740322113, | |
| "eval_runtime": 27.9373, | |
| "eval_samples_per_second": 4.868, | |
| "eval_steps_per_second": 0.179, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 2.6356570720672607, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3167, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.4233551025390625, | |
| "eval_runtime": 27.7505, | |
| "eval_samples_per_second": 4.901, | |
| "eval_steps_per_second": 0.18, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 16.41025641025641, | |
| "grad_norm": 2.93713641166687, | |
| "learning_rate": 3.580246913580247e-05, | |
| "loss": 0.3186, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "eval_accuracy": 0.8235294117647058, | |
| "eval_loss": 0.3853110671043396, | |
| "eval_runtime": 27.8163, | |
| "eval_samples_per_second": 4.889, | |
| "eval_steps_per_second": 0.18, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 17.435897435897434, | |
| "grad_norm": 2.3861587047576904, | |
| "learning_rate": 3.45679012345679e-05, | |
| "loss": 0.2568, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 17.94871794871795, | |
| "eval_accuracy": 0.8455882352941176, | |
| "eval_loss": 0.39038005471229553, | |
| "eval_runtime": 28.608, | |
| "eval_samples_per_second": 4.754, | |
| "eval_steps_per_second": 0.175, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "grad_norm": 3.0627877712249756, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2528, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 18.974358974358974, | |
| "eval_accuracy": 0.8308823529411765, | |
| "eval_loss": 0.401323527097702, | |
| "eval_runtime": 27.8762, | |
| "eval_samples_per_second": 4.879, | |
| "eval_steps_per_second": 0.179, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 19.487179487179485, | |
| "grad_norm": 2.4923059940338135, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 0.2661, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.3275494873523712, | |
| "eval_runtime": 27.4518, | |
| "eval_samples_per_second": 4.954, | |
| "eval_steps_per_second": 0.182, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 20.51282051282051, | |
| "grad_norm": 3.348421335220337, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.2287, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 20.923076923076923, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.32190677523612976, | |
| "eval_runtime": 27.7762, | |
| "eval_samples_per_second": 4.896, | |
| "eval_steps_per_second": 0.18, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 21.53846153846154, | |
| "grad_norm": 2.7627947330474854, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.2465, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 21.94871794871795, | |
| "eval_accuracy": 0.8529411764705882, | |
| "eval_loss": 0.34101688861846924, | |
| "eval_runtime": 28.0903, | |
| "eval_samples_per_second": 4.842, | |
| "eval_steps_per_second": 0.178, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 22.564102564102566, | |
| "grad_norm": 2.276890277862549, | |
| "learning_rate": 2.839506172839506e-05, | |
| "loss": 0.2422, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 22.974358974358974, | |
| "eval_accuracy": 0.8602941176470589, | |
| "eval_loss": 0.32561448216438293, | |
| "eval_runtime": 28.0659, | |
| "eval_samples_per_second": 4.846, | |
| "eval_steps_per_second": 0.178, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 23.58974358974359, | |
| "grad_norm": 2.7189478874206543, | |
| "learning_rate": 2.7160493827160493e-05, | |
| "loss": 0.222, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.3232100009918213, | |
| "eval_runtime": 27.9535, | |
| "eval_samples_per_second": 4.865, | |
| "eval_steps_per_second": 0.179, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 24.615384615384617, | |
| "grad_norm": 2.6200361251831055, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.1917, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 24.923076923076923, | |
| "eval_accuracy": 0.8676470588235294, | |
| "eval_loss": 0.3307046890258789, | |
| "eval_runtime": 27.5942, | |
| "eval_samples_per_second": 4.929, | |
| "eval_steps_per_second": 0.181, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "grad_norm": 2.5348196029663086, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.194, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 25.94871794871795, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.3146378993988037, | |
| "eval_runtime": 27.8983, | |
| "eval_samples_per_second": 4.875, | |
| "eval_steps_per_second": 0.179, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 2.3038291931152344, | |
| "learning_rate": 2.345679012345679e-05, | |
| "loss": 0.212, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 26.974358974358974, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.31248700618743896, | |
| "eval_runtime": 27.5482, | |
| "eval_samples_per_second": 4.937, | |
| "eval_steps_per_second": 0.182, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 27.692307692307693, | |
| "grad_norm": 2.3745553493499756, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1718, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9044117647058824, | |
| "eval_loss": 0.30149275064468384, | |
| "eval_runtime": 27.3467, | |
| "eval_samples_per_second": 4.973, | |
| "eval_steps_per_second": 0.183, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 28.71794871794872, | |
| "grad_norm": 2.4551799297332764, | |
| "learning_rate": 2.0987654320987655e-05, | |
| "loss": 0.1975, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 28.923076923076923, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.31952494382858276, | |
| "eval_runtime": 28.7515, | |
| "eval_samples_per_second": 4.73, | |
| "eval_steps_per_second": 0.174, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 29.743589743589745, | |
| "grad_norm": 4.400726795196533, | |
| "learning_rate": 1.9753086419753087e-05, | |
| "loss": 0.1948, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 29.94871794871795, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.3536161780357361, | |
| "eval_runtime": 27.7197, | |
| "eval_samples_per_second": 4.906, | |
| "eval_steps_per_second": 0.18, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 30.76923076923077, | |
| "grad_norm": 3.868483304977417, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1809, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 30.974358974358974, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.31048697233200073, | |
| "eval_runtime": 27.272, | |
| "eval_samples_per_second": 4.987, | |
| "eval_steps_per_second": 0.183, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 31.794871794871796, | |
| "grad_norm": 3.041282892227173, | |
| "learning_rate": 1.728395061728395e-05, | |
| "loss": 0.1744, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.30321478843688965, | |
| "eval_runtime": 27.7112, | |
| "eval_samples_per_second": 4.908, | |
| "eval_steps_per_second": 0.18, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 32.82051282051282, | |
| "grad_norm": 3.5929629802703857, | |
| "learning_rate": 1.604938271604938e-05, | |
| "loss": 0.1731, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 32.92307692307692, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.2936057448387146, | |
| "eval_runtime": 27.505, | |
| "eval_samples_per_second": 4.945, | |
| "eval_steps_per_second": 0.182, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 33.84615384615385, | |
| "grad_norm": 2.917879343032837, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1513, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 33.94871794871795, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.28888821601867676, | |
| "eval_runtime": 27.3318, | |
| "eval_samples_per_second": 4.976, | |
| "eval_steps_per_second": 0.183, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 34.87179487179487, | |
| "grad_norm": 2.477483034133911, | |
| "learning_rate": 1.3580246913580247e-05, | |
| "loss": 0.1527, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 34.97435897435897, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.2875381112098694, | |
| "eval_runtime": 27.1267, | |
| "eval_samples_per_second": 5.014, | |
| "eval_steps_per_second": 0.184, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 35.8974358974359, | |
| "grad_norm": 2.345552444458008, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.1693, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.2753787338733673, | |
| "eval_runtime": 27.5618, | |
| "eval_samples_per_second": 4.934, | |
| "eval_steps_per_second": 0.181, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "grad_norm": 3.5276284217834473, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.1743, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.2875354290008545, | |
| "eval_runtime": 27.2843, | |
| "eval_samples_per_second": 4.985, | |
| "eval_steps_per_second": 0.183, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "grad_norm": 1.937537670135498, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 0.1463, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.2960669994354248, | |
| "eval_runtime": 27.3088, | |
| "eval_samples_per_second": 4.98, | |
| "eval_steps_per_second": 0.183, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "grad_norm": 2.248408555984497, | |
| "learning_rate": 8.641975308641975e-06, | |
| "loss": 0.1429, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.2848477065563202, | |
| "eval_runtime": 27.7311, | |
| "eval_samples_per_second": 4.904, | |
| "eval_steps_per_second": 0.18, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 3.5972237586975098, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.1483, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.2873067259788513, | |
| "eval_runtime": 27.6065, | |
| "eval_samples_per_second": 4.926, | |
| "eval_steps_per_second": 0.181, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 40.92307692307692, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.2856013774871826, | |
| "eval_runtime": 28.278, | |
| "eval_samples_per_second": 4.809, | |
| "eval_steps_per_second": 0.177, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 41.02564102564103, | |
| "grad_norm": 4.596207141876221, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.1613, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 41.94871794871795, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.2800574004650116, | |
| "eval_runtime": 29.3383, | |
| "eval_samples_per_second": 4.636, | |
| "eval_steps_per_second": 0.17, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 42.05128205128205, | |
| "grad_norm": 3.401879072189331, | |
| "learning_rate": 4.938271604938272e-06, | |
| "loss": 0.1358, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 42.97435897435897, | |
| "eval_accuracy": 0.9117647058823529, | |
| "eval_loss": 0.28377899527549744, | |
| "eval_runtime": 27.9379, | |
| "eval_samples_per_second": 4.868, | |
| "eval_steps_per_second": 0.179, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 43.07692307692308, | |
| "grad_norm": 5.472115993499756, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.1453, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_loss": 0.2783341407775879, | |
| "eval_runtime": 28.9719, | |
| "eval_samples_per_second": 4.694, | |
| "eval_steps_per_second": 0.173, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 44.1025641025641, | |
| "grad_norm": 2.55735445022583, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 0.1383, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 44.92307692307692, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.2897387742996216, | |
| "eval_runtime": 28.0295, | |
| "eval_samples_per_second": 4.852, | |
| "eval_steps_per_second": 0.178, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 45.12820512820513, | |
| "grad_norm": 3.086352825164795, | |
| "learning_rate": 1.234567901234568e-06, | |
| "loss": 0.1655, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 45.94871794871795, | |
| "eval_accuracy": 0.9044117647058824, | |
| "eval_loss": 0.284650057554245, | |
| "eval_runtime": 28.6952, | |
| "eval_samples_per_second": 4.739, | |
| "eval_steps_per_second": 0.174, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "grad_norm": 2.815723419189453, | |
| "learning_rate": 0.0, | |
| "loss": 0.1489, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.2861221134662628, | |
| "eval_runtime": 28.6879, | |
| "eval_samples_per_second": 4.741, | |
| "eval_steps_per_second": 0.174, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "step": 450, | |
| "total_flos": 5.704428204815155e+17, | |
| "train_loss": 0.40061683946185644, | |
| "train_runtime": 12238.3074, | |
| "train_samples_per_second": 5.001, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "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": 5.704428204815155e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |