| { |
| "best_metric": 0.9371428571428572, |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-humeda-DAV64/checkpoint-540", |
| "epoch": 45.0, |
| "eval_steps": 500, |
| "global_step": 675, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 5.300174713134766, |
| "learning_rate": 5.882352941176471e-06, |
| "loss": 1.1417, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5428571428571428, |
| "eval_loss": 1.0311720371246338, |
| "eval_runtime": 2.4849, |
| "eval_samples_per_second": 70.426, |
| "eval_steps_per_second": 4.427, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 4.034121036529541, |
| "learning_rate": 1.1764705882352942e-05, |
| "loss": 1.0491, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 4.675110340118408, |
| "learning_rate": 1.7647058823529414e-05, |
| "loss": 0.9163, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7942857142857143, |
| "eval_loss": 0.7115129828453064, |
| "eval_runtime": 1.8504, |
| "eval_samples_per_second": 94.575, |
| "eval_steps_per_second": 5.945, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 8.649486541748047, |
| "learning_rate": 2.3529411764705884e-05, |
| "loss": 0.7042, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8342857142857143, |
| "eval_loss": 0.4226876497268677, |
| "eval_runtime": 2.2367, |
| "eval_samples_per_second": 78.241, |
| "eval_steps_per_second": 4.918, |
| "step": 45 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 7.733545303344727, |
| "learning_rate": 2.9411764705882357e-05, |
| "loss": 0.5344, |
| "step": 50 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 5.540239334106445, |
| "learning_rate": 3.529411764705883e-05, |
| "loss": 0.4976, |
| "step": 60 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8685714285714285, |
| "eval_loss": 0.34094423055648804, |
| "eval_runtime": 1.8281, |
| "eval_samples_per_second": 95.728, |
| "eval_steps_per_second": 6.017, |
| "step": 60 |
| }, |
| { |
| "epoch": 4.666666666666667, |
| "grad_norm": 15.600494384765625, |
| "learning_rate": 3.9868204283360795e-05, |
| "loss": 0.4469, |
| "step": 70 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8971428571428571, |
| "eval_loss": 0.3059036433696747, |
| "eval_runtime": 1.8712, |
| "eval_samples_per_second": 93.522, |
| "eval_steps_per_second": 5.879, |
| "step": 75 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "grad_norm": 7.863681793212891, |
| "learning_rate": 3.9209225700164745e-05, |
| "loss": 0.3903, |
| "step": 80 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 12.250831604003906, |
| "learning_rate": 3.85502471169687e-05, |
| "loss": 0.3746, |
| "step": 90 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8914285714285715, |
| "eval_loss": 0.295719176530838, |
| "eval_runtime": 2.5933, |
| "eval_samples_per_second": 67.482, |
| "eval_steps_per_second": 4.242, |
| "step": 90 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 10.311092376708984, |
| "learning_rate": 3.789126853377266e-05, |
| "loss": 0.3667, |
| "step": 100 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8685714285714285, |
| "eval_loss": 0.3035523295402527, |
| "eval_runtime": 1.8939, |
| "eval_samples_per_second": 92.401, |
| "eval_steps_per_second": 5.808, |
| "step": 105 |
| }, |
| { |
| "epoch": 7.333333333333333, |
| "grad_norm": 7.1186909675598145, |
| "learning_rate": 3.723228995057661e-05, |
| "loss": 0.3057, |
| "step": 110 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 10.433780670166016, |
| "learning_rate": 3.6573311367380566e-05, |
| "loss": 0.3026, |
| "step": 120 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.25547102093696594, |
| "eval_runtime": 1.8334, |
| "eval_samples_per_second": 95.453, |
| "eval_steps_per_second": 6.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 8.666666666666666, |
| "grad_norm": 8.441205978393555, |
| "learning_rate": 3.5914332784184516e-05, |
| "loss": 0.2732, |
| "step": 130 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9028571428571428, |
| "eval_loss": 0.3008781969547272, |
| "eval_runtime": 2.1643, |
| "eval_samples_per_second": 80.856, |
| "eval_steps_per_second": 5.082, |
| "step": 135 |
| }, |
| { |
| "epoch": 9.333333333333334, |
| "grad_norm": 9.809795379638672, |
| "learning_rate": 3.525535420098847e-05, |
| "loss": 0.2717, |
| "step": 140 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 14.45852279663086, |
| "learning_rate": 3.459637561779242e-05, |
| "loss": 0.2518, |
| "step": 150 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.9028571428571428, |
| "eval_loss": 0.2463250756263733, |
| "eval_runtime": 1.841, |
| "eval_samples_per_second": 95.059, |
| "eval_steps_per_second": 5.975, |
| "step": 150 |
| }, |
| { |
| "epoch": 10.666666666666666, |
| "grad_norm": 7.824082374572754, |
| "learning_rate": 3.393739703459638e-05, |
| "loss": 0.2029, |
| "step": 160 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.23446707427501678, |
| "eval_runtime": 1.8571, |
| "eval_samples_per_second": 94.231, |
| "eval_steps_per_second": 5.923, |
| "step": 165 |
| }, |
| { |
| "epoch": 11.333333333333334, |
| "grad_norm": 5.769466876983643, |
| "learning_rate": 3.327841845140033e-05, |
| "loss": 0.2275, |
| "step": 170 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 5.892960071563721, |
| "learning_rate": 3.2685337726523894e-05, |
| "loss": 0.2698, |
| "step": 180 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.9028571428571428, |
| "eval_loss": 0.2969464659690857, |
| "eval_runtime": 1.8752, |
| "eval_samples_per_second": 93.323, |
| "eval_steps_per_second": 5.866, |
| "step": 180 |
| }, |
| { |
| "epoch": 12.666666666666666, |
| "grad_norm": 9.02706241607666, |
| "learning_rate": 3.2026359143327844e-05, |
| "loss": 0.2228, |
| "step": 190 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.2966436743736267, |
| "eval_runtime": 1.8803, |
| "eval_samples_per_second": 93.071, |
| "eval_steps_per_second": 5.85, |
| "step": 195 |
| }, |
| { |
| "epoch": 13.333333333333334, |
| "grad_norm": 17.528162002563477, |
| "learning_rate": 3.13673805601318e-05, |
| "loss": 0.2324, |
| "step": 200 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 15.268353462219238, |
| "learning_rate": 3.070840197693575e-05, |
| "loss": 0.2213, |
| "step": 210 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.8514285714285714, |
| "eval_loss": 0.4313853681087494, |
| "eval_runtime": 2.4046, |
| "eval_samples_per_second": 72.779, |
| "eval_steps_per_second": 4.575, |
| "step": 210 |
| }, |
| { |
| "epoch": 14.666666666666666, |
| "grad_norm": 8.196939468383789, |
| "learning_rate": 3.0049423393739708e-05, |
| "loss": 0.1974, |
| "step": 220 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.8971428571428571, |
| "eval_loss": 0.3351776599884033, |
| "eval_runtime": 1.9165, |
| "eval_samples_per_second": 91.313, |
| "eval_steps_per_second": 5.74, |
| "step": 225 |
| }, |
| { |
| "epoch": 15.333333333333334, |
| "grad_norm": 12.688127517700195, |
| "learning_rate": 2.939044481054366e-05, |
| "loss": 0.1875, |
| "step": 230 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 16.183589935302734, |
| "learning_rate": 2.8731466227347615e-05, |
| "loss": 0.1865, |
| "step": 240 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.2836013436317444, |
| "eval_runtime": 1.8786, |
| "eval_samples_per_second": 93.152, |
| "eval_steps_per_second": 5.855, |
| "step": 240 |
| }, |
| { |
| "epoch": 16.666666666666668, |
| "grad_norm": 7.143344879150391, |
| "learning_rate": 2.8072487644151565e-05, |
| "loss": 0.157, |
| "step": 250 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.2435523271560669, |
| "eval_runtime": 2.7374, |
| "eval_samples_per_second": 63.929, |
| "eval_steps_per_second": 4.018, |
| "step": 255 |
| }, |
| { |
| "epoch": 17.333333333333332, |
| "grad_norm": 11.92932415008545, |
| "learning_rate": 2.7413509060955522e-05, |
| "loss": 0.1418, |
| "step": 260 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 8.301336288452148, |
| "learning_rate": 2.6754530477759476e-05, |
| "loss": 0.1588, |
| "step": 270 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 0.88, |
| "eval_loss": 0.26176148653030396, |
| "eval_runtime": 1.8571, |
| "eval_samples_per_second": 94.23, |
| "eval_steps_per_second": 5.923, |
| "step": 270 |
| }, |
| { |
| "epoch": 18.666666666666668, |
| "grad_norm": 4.530095100402832, |
| "learning_rate": 2.6095551894563426e-05, |
| "loss": 0.1533, |
| "step": 280 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_accuracy": 0.92, |
| "eval_loss": 0.23149946331977844, |
| "eval_runtime": 1.8772, |
| "eval_samples_per_second": 93.225, |
| "eval_steps_per_second": 5.86, |
| "step": 285 |
| }, |
| { |
| "epoch": 19.333333333333332, |
| "grad_norm": 12.76117992401123, |
| "learning_rate": 2.5436573311367383e-05, |
| "loss": 0.1392, |
| "step": 290 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 7.729790210723877, |
| "learning_rate": 2.4777594728171336e-05, |
| "loss": 0.1424, |
| "step": 300 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.9142857142857143, |
| "eval_loss": 0.23584967851638794, |
| "eval_runtime": 2.3184, |
| "eval_samples_per_second": 75.484, |
| "eval_steps_per_second": 4.745, |
| "step": 300 |
| }, |
| { |
| "epoch": 20.666666666666668, |
| "grad_norm": 7.21251916885376, |
| "learning_rate": 2.411861614497529e-05, |
| "loss": 0.1278, |
| "step": 310 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.2752179205417633, |
| "eval_runtime": 1.8809, |
| "eval_samples_per_second": 93.039, |
| "eval_steps_per_second": 5.848, |
| "step": 315 |
| }, |
| { |
| "epoch": 21.333333333333332, |
| "grad_norm": 10.802227020263672, |
| "learning_rate": 2.3459637561779243e-05, |
| "loss": 0.135, |
| "step": 320 |
| }, |
| { |
| "epoch": 22.0, |
| "grad_norm": 9.825136184692383, |
| "learning_rate": 2.28006589785832e-05, |
| "loss": 0.1328, |
| "step": 330 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_accuracy": 0.92, |
| "eval_loss": 0.21964886784553528, |
| "eval_runtime": 1.996, |
| "eval_samples_per_second": 87.675, |
| "eval_steps_per_second": 5.511, |
| "step": 330 |
| }, |
| { |
| "epoch": 22.666666666666668, |
| "grad_norm": 2.878047227859497, |
| "learning_rate": 2.214168039538715e-05, |
| "loss": 0.124, |
| "step": 340 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_accuracy": 0.9142857142857143, |
| "eval_loss": 0.2490733116865158, |
| "eval_runtime": 1.8702, |
| "eval_samples_per_second": 93.571, |
| "eval_steps_per_second": 5.882, |
| "step": 345 |
| }, |
| { |
| "epoch": 23.333333333333332, |
| "grad_norm": 5.2356181144714355, |
| "learning_rate": 2.1482701812191107e-05, |
| "loss": 0.0954, |
| "step": 350 |
| }, |
| { |
| "epoch": 24.0, |
| "grad_norm": 6.132265090942383, |
| "learning_rate": 2.0823723228995057e-05, |
| "loss": 0.1116, |
| "step": 360 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_accuracy": 0.92, |
| "eval_loss": 0.20849058032035828, |
| "eval_runtime": 1.8599, |
| "eval_samples_per_second": 94.09, |
| "eval_steps_per_second": 5.914, |
| "step": 360 |
| }, |
| { |
| "epoch": 24.666666666666668, |
| "grad_norm": 12.658270835876465, |
| "learning_rate": 2.0164744645799014e-05, |
| "loss": 0.1235, |
| "step": 370 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_accuracy": 0.92, |
| "eval_loss": 0.23794764280319214, |
| "eval_runtime": 2.5358, |
| "eval_samples_per_second": 69.013, |
| "eval_steps_per_second": 4.338, |
| "step": 375 |
| }, |
| { |
| "epoch": 25.333333333333332, |
| "grad_norm": 10.187384605407715, |
| "learning_rate": 1.9505766062602968e-05, |
| "loss": 0.1044, |
| "step": 380 |
| }, |
| { |
| "epoch": 26.0, |
| "grad_norm": 16.027721405029297, |
| "learning_rate": 1.884678747940692e-05, |
| "loss": 0.1746, |
| "step": 390 |
| }, |
| { |
| "epoch": 26.0, |
| "eval_accuracy": 0.9257142857142857, |
| "eval_loss": 0.27487558126449585, |
| "eval_runtime": 2.2376, |
| "eval_samples_per_second": 78.21, |
| "eval_steps_per_second": 4.916, |
| "step": 390 |
| }, |
| { |
| "epoch": 26.666666666666668, |
| "grad_norm": 4.403973579406738, |
| "learning_rate": 1.8187808896210875e-05, |
| "loss": 0.1143, |
| "step": 400 |
| }, |
| { |
| "epoch": 27.0, |
| "eval_accuracy": 0.92, |
| "eval_loss": 0.2812519967556, |
| "eval_runtime": 1.8578, |
| "eval_samples_per_second": 94.196, |
| "eval_steps_per_second": 5.921, |
| "step": 405 |
| }, |
| { |
| "epoch": 27.333333333333332, |
| "grad_norm": 3.1324920654296875, |
| "learning_rate": 1.7528830313014828e-05, |
| "loss": 0.0843, |
| "step": 410 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 2.4315762519836426, |
| "learning_rate": 1.686985172981878e-05, |
| "loss": 0.1256, |
| "step": 420 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.3038230836391449, |
| "eval_runtime": 1.8815, |
| "eval_samples_per_second": 93.011, |
| "eval_steps_per_second": 5.846, |
| "step": 420 |
| }, |
| { |
| "epoch": 28.666666666666668, |
| "grad_norm": 6.84234619140625, |
| "learning_rate": 1.6210873146622735e-05, |
| "loss": 0.0773, |
| "step": 430 |
| }, |
| { |
| "epoch": 29.0, |
| "eval_accuracy": 0.9314285714285714, |
| "eval_loss": 0.2903304100036621, |
| "eval_runtime": 2.5914, |
| "eval_samples_per_second": 67.532, |
| "eval_steps_per_second": 4.245, |
| "step": 435 |
| }, |
| { |
| "epoch": 29.333333333333332, |
| "grad_norm": 6.670344829559326, |
| "learning_rate": 1.5551894563426692e-05, |
| "loss": 0.0905, |
| "step": 440 |
| }, |
| { |
| "epoch": 30.0, |
| "grad_norm": 2.9765944480895996, |
| "learning_rate": 1.4892915980230644e-05, |
| "loss": 0.0981, |
| "step": 450 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_accuracy": 0.92, |
| "eval_loss": 0.29279109835624695, |
| "eval_runtime": 1.8684, |
| "eval_samples_per_second": 93.662, |
| "eval_steps_per_second": 5.887, |
| "step": 450 |
| }, |
| { |
| "epoch": 30.666666666666668, |
| "grad_norm": 2.8232874870300293, |
| "learning_rate": 1.4233937397034599e-05, |
| "loss": 0.0717, |
| "step": 460 |
| }, |
| { |
| "epoch": 31.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.3072536289691925, |
| "eval_runtime": 1.917, |
| "eval_samples_per_second": 91.288, |
| "eval_steps_per_second": 5.738, |
| "step": 465 |
| }, |
| { |
| "epoch": 31.333333333333332, |
| "grad_norm": 15.47038745880127, |
| "learning_rate": 1.3574958813838552e-05, |
| "loss": 0.1431, |
| "step": 470 |
| }, |
| { |
| "epoch": 32.0, |
| "grad_norm": 9.506186485290527, |
| "learning_rate": 1.2915980230642504e-05, |
| "loss": 0.1143, |
| "step": 480 |
| }, |
| { |
| "epoch": 32.0, |
| "eval_accuracy": 0.8914285714285715, |
| "eval_loss": 0.34658822417259216, |
| "eval_runtime": 2.7012, |
| "eval_samples_per_second": 64.785, |
| "eval_steps_per_second": 4.072, |
| "step": 480 |
| }, |
| { |
| "epoch": 32.666666666666664, |
| "grad_norm": 5.225739479064941, |
| "learning_rate": 1.2257001647446458e-05, |
| "loss": 0.0821, |
| "step": 490 |
| }, |
| { |
| "epoch": 33.0, |
| "eval_accuracy": 0.9257142857142857, |
| "eval_loss": 0.30787134170532227, |
| "eval_runtime": 1.8856, |
| "eval_samples_per_second": 92.808, |
| "eval_steps_per_second": 5.834, |
| "step": 495 |
| }, |
| { |
| "epoch": 33.333333333333336, |
| "grad_norm": 7.042791366577148, |
| "learning_rate": 1.1598023064250411e-05, |
| "loss": 0.0805, |
| "step": 500 |
| }, |
| { |
| "epoch": 34.0, |
| "grad_norm": 8.116437911987305, |
| "learning_rate": 1.0939044481054366e-05, |
| "loss": 0.0582, |
| "step": 510 |
| }, |
| { |
| "epoch": 34.0, |
| "eval_accuracy": 0.9314285714285714, |
| "eval_loss": 0.2845039963722229, |
| "eval_runtime": 1.88, |
| "eval_samples_per_second": 93.085, |
| "eval_steps_per_second": 5.851, |
| "step": 510 |
| }, |
| { |
| "epoch": 34.666666666666664, |
| "grad_norm": 13.881778717041016, |
| "learning_rate": 1.028006589785832e-05, |
| "loss": 0.1015, |
| "step": 520 |
| }, |
| { |
| "epoch": 35.0, |
| "eval_accuracy": 0.9028571428571428, |
| "eval_loss": 0.36099615693092346, |
| "eval_runtime": 2.4314, |
| "eval_samples_per_second": 71.974, |
| "eval_steps_per_second": 4.524, |
| "step": 525 |
| }, |
| { |
| "epoch": 35.333333333333336, |
| "grad_norm": 3.467531442642212, |
| "learning_rate": 9.621087314662273e-06, |
| "loss": 0.0801, |
| "step": 530 |
| }, |
| { |
| "epoch": 36.0, |
| "grad_norm": 8.048483848571777, |
| "learning_rate": 8.962108731466229e-06, |
| "loss": 0.075, |
| "step": 540 |
| }, |
| { |
| "epoch": 36.0, |
| "eval_accuracy": 0.9371428571428572, |
| "eval_loss": 0.28705087304115295, |
| "eval_runtime": 1.8805, |
| "eval_samples_per_second": 93.061, |
| "eval_steps_per_second": 5.85, |
| "step": 540 |
| }, |
| { |
| "epoch": 36.666666666666664, |
| "grad_norm": 7.145118713378906, |
| "learning_rate": 8.303130148270182e-06, |
| "loss": 0.0783, |
| "step": 550 |
| }, |
| { |
| "epoch": 37.0, |
| "eval_accuracy": 0.9257142857142857, |
| "eval_loss": 0.278808057308197, |
| "eval_runtime": 1.8907, |
| "eval_samples_per_second": 92.558, |
| "eval_steps_per_second": 5.818, |
| "step": 555 |
| }, |
| { |
| "epoch": 37.333333333333336, |
| "grad_norm": 6.323741436004639, |
| "learning_rate": 7.644151565074136e-06, |
| "loss": 0.0538, |
| "step": 560 |
| }, |
| { |
| "epoch": 38.0, |
| "grad_norm": 8.460933685302734, |
| "learning_rate": 6.98517298187809e-06, |
| "loss": 0.0919, |
| "step": 570 |
| }, |
| { |
| "epoch": 38.0, |
| "eval_accuracy": 0.9257142857142857, |
| "eval_loss": 0.29261988401412964, |
| "eval_runtime": 1.988, |
| "eval_samples_per_second": 88.029, |
| "eval_steps_per_second": 5.533, |
| "step": 570 |
| }, |
| { |
| "epoch": 38.666666666666664, |
| "grad_norm": 11.090608596801758, |
| "learning_rate": 6.326194398682043e-06, |
| "loss": 0.0863, |
| "step": 580 |
| }, |
| { |
| "epoch": 39.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.2910502552986145, |
| "eval_runtime": 1.9195, |
| "eval_samples_per_second": 91.171, |
| "eval_steps_per_second": 5.731, |
| "step": 585 |
| }, |
| { |
| "epoch": 39.333333333333336, |
| "grad_norm": 7.287304401397705, |
| "learning_rate": 5.667215815485997e-06, |
| "loss": 0.0772, |
| "step": 590 |
| }, |
| { |
| "epoch": 40.0, |
| "grad_norm": 6.660625457763672, |
| "learning_rate": 5.0082372322899505e-06, |
| "loss": 0.0721, |
| "step": 600 |
| }, |
| { |
| "epoch": 40.0, |
| "eval_accuracy": 0.9142857142857143, |
| "eval_loss": 0.3360213041305542, |
| "eval_runtime": 2.2163, |
| "eval_samples_per_second": 78.961, |
| "eval_steps_per_second": 4.963, |
| "step": 600 |
| }, |
| { |
| "epoch": 40.666666666666664, |
| "grad_norm": 7.102691173553467, |
| "learning_rate": 4.349258649093905e-06, |
| "loss": 0.0994, |
| "step": 610 |
| }, |
| { |
| "epoch": 41.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.28646939992904663, |
| "eval_runtime": 1.9172, |
| "eval_samples_per_second": 91.281, |
| "eval_steps_per_second": 5.738, |
| "step": 615 |
| }, |
| { |
| "epoch": 41.333333333333336, |
| "grad_norm": 3.9301791191101074, |
| "learning_rate": 3.690280065897859e-06, |
| "loss": 0.0662, |
| "step": 620 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 11.659097671508789, |
| "learning_rate": 3.0313014827018123e-06, |
| "loss": 0.0734, |
| "step": 630 |
| }, |
| { |
| "epoch": 42.0, |
| "eval_accuracy": 0.9142857142857143, |
| "eval_loss": 0.31548869609832764, |
| "eval_runtime": 1.8763, |
| "eval_samples_per_second": 93.27, |
| "eval_steps_per_second": 5.863, |
| "step": 630 |
| }, |
| { |
| "epoch": 42.666666666666664, |
| "grad_norm": 5.843999862670898, |
| "learning_rate": 2.3723228995057662e-06, |
| "loss": 0.0935, |
| "step": 640 |
| }, |
| { |
| "epoch": 43.0, |
| "eval_accuracy": 0.9085714285714286, |
| "eval_loss": 0.3128548562526703, |
| "eval_runtime": 2.5107, |
| "eval_samples_per_second": 69.701, |
| "eval_steps_per_second": 4.381, |
| "step": 645 |
| }, |
| { |
| "epoch": 43.333333333333336, |
| "grad_norm": 2.7129805088043213, |
| "learning_rate": 1.7133443163097201e-06, |
| "loss": 0.0582, |
| "step": 650 |
| }, |
| { |
| "epoch": 44.0, |
| "grad_norm": 5.156311511993408, |
| "learning_rate": 1.0543657331136739e-06, |
| "loss": 0.0651, |
| "step": 660 |
| }, |
| { |
| "epoch": 44.0, |
| "eval_accuracy": 0.9142857142857143, |
| "eval_loss": 0.29244309663772583, |
| "eval_runtime": 2.6669, |
| "eval_samples_per_second": 65.62, |
| "eval_steps_per_second": 4.125, |
| "step": 660 |
| }, |
| { |
| "epoch": 44.666666666666664, |
| "grad_norm": 7.516735076904297, |
| "learning_rate": 3.9538714991762767e-07, |
| "loss": 0.0732, |
| "step": 670 |
| }, |
| { |
| "epoch": 45.0, |
| "eval_accuracy": 0.9142857142857143, |
| "eval_loss": 0.29613712430000305, |
| "eval_runtime": 2.83, |
| "eval_samples_per_second": 61.837, |
| "eval_steps_per_second": 3.887, |
| "step": 675 |
| }, |
| { |
| "epoch": 45.0, |
| "step": 675, |
| "total_flos": 1.390881324367872e+18, |
| "train_loss": 0.21034134012681466, |
| "train_runtime": 974.2874, |
| "train_samples_per_second": 43.878, |
| "train_steps_per_second": 0.693 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 675, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 45, |
| "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": 1.390881324367872e+18, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
