| { |
| "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 |
| } |
|
|
