| { | |
| "best_metric": 4.9971747398376465, | |
| "best_model_checkpoint": "distilbert_add_pre-training-complete/checkpoint-300000", | |
| "epoch": 83.9630562552477, | |
| "global_step": 300000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.942130710236746e-05, | |
| "loss": 6.295, | |
| "step": 3573 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.15223537974860726, | |
| "eval_loss": 6.0701375007629395, | |
| "eval_runtime": 0.7526, | |
| "eval_samples_per_second": 636.494, | |
| "eval_steps_per_second": 10.63, | |
| "step": 3573 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.882560853617873e-05, | |
| "loss": 6.0482, | |
| "step": 7146 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.15652710741946346, | |
| "eval_loss": 5.953271865844727, | |
| "eval_runtime": 0.74, | |
| "eval_samples_per_second": 647.279, | |
| "eval_steps_per_second": 10.81, | |
| "step": 7146 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.823007669223075e-05, | |
| "loss": 5.9799, | |
| "step": 10719 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.15838858298685246, | |
| "eval_loss": 5.900791645050049, | |
| "eval_runtime": 0.7474, | |
| "eval_samples_per_second": 640.85, | |
| "eval_steps_per_second": 10.703, | |
| "step": 10719 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.763454484828276e-05, | |
| "loss": 5.9378, | |
| "step": 14292 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.1544888689508215, | |
| "eval_loss": 5.899669647216797, | |
| "eval_runtime": 0.741, | |
| "eval_samples_per_second": 646.414, | |
| "eval_steps_per_second": 10.796, | |
| "step": 14292 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.703901300433478e-05, | |
| "loss": 5.9057, | |
| "step": 17865 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.15363002922004945, | |
| "eval_loss": 5.890487194061279, | |
| "eval_runtime": 0.7428, | |
| "eval_samples_per_second": 644.873, | |
| "eval_steps_per_second": 10.77, | |
| "step": 17865 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.644381460486829e-05, | |
| "loss": 5.8811, | |
| "step": 21438 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.15501974055273549, | |
| "eval_loss": 5.864607334136963, | |
| "eval_runtime": 0.7414, | |
| "eval_samples_per_second": 646.074, | |
| "eval_steps_per_second": 10.79, | |
| "step": 21438 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.584828276092031e-05, | |
| "loss": 5.8617, | |
| "step": 25011 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.15343423240607648, | |
| "eval_loss": 5.832152366638184, | |
| "eval_runtime": 0.7408, | |
| "eval_samples_per_second": 646.572, | |
| "eval_steps_per_second": 10.799, | |
| "step": 25011 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.525291763921307e-05, | |
| "loss": 5.844, | |
| "step": 28584 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.15228028968486984, | |
| "eval_loss": 5.856273651123047, | |
| "eval_runtime": 0.7422, | |
| "eval_samples_per_second": 645.395, | |
| "eval_steps_per_second": 10.779, | |
| "step": 28584 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.4657219073024345e-05, | |
| "loss": 5.8297, | |
| "step": 32157 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.15479184129645152, | |
| "eval_loss": 5.835241794586182, | |
| "eval_runtime": 0.7411, | |
| "eval_samples_per_second": 646.294, | |
| "eval_steps_per_second": 10.794, | |
| "step": 32157 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.4061853951317107e-05, | |
| "loss": 5.8175, | |
| "step": 35730 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.1558288740089093, | |
| "eval_loss": 5.813608646392822, | |
| "eval_runtime": 0.7417, | |
| "eval_samples_per_second": 645.841, | |
| "eval_steps_per_second": 10.786, | |
| "step": 35730 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.3466322107369125e-05, | |
| "loss": 5.8056, | |
| "step": 39303 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.15261607518586057, | |
| "eval_loss": 5.81471061706543, | |
| "eval_runtime": 0.7409, | |
| "eval_samples_per_second": 646.53, | |
| "eval_steps_per_second": 10.798, | |
| "step": 39303 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.287095698566189e-05, | |
| "loss": 5.7921, | |
| "step": 42876 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.15484534935469516, | |
| "eval_loss": 5.802037239074707, | |
| "eval_runtime": 0.759, | |
| "eval_samples_per_second": 631.084, | |
| "eval_steps_per_second": 10.54, | |
| "step": 42876 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.227542514171391e-05, | |
| "loss": 5.7777, | |
| "step": 46449 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.1545157176914121, | |
| "eval_loss": 5.7890777587890625, | |
| "eval_runtime": 0.7548, | |
| "eval_samples_per_second": 634.635, | |
| "eval_steps_per_second": 10.599, | |
| "step": 46449 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.168006002000667e-05, | |
| "loss": 5.7596, | |
| "step": 50022 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.1587256836763462, | |
| "eval_loss": 5.736998081207275, | |
| "eval_runtime": 0.7569, | |
| "eval_samples_per_second": 632.812, | |
| "eval_steps_per_second": 10.569, | |
| "step": 50022 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.1084694898299434e-05, | |
| "loss": 5.7414, | |
| "step": 53595 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.16035909664749615, | |
| "eval_loss": 5.739556789398193, | |
| "eval_runtime": 0.7394, | |
| "eval_samples_per_second": 647.798, | |
| "eval_steps_per_second": 10.819, | |
| "step": 53595 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.048899633211071e-05, | |
| "loss": 5.7243, | |
| "step": 57168 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.15644779032482922, | |
| "eval_loss": 5.749042510986328, | |
| "eval_runtime": 0.745, | |
| "eval_samples_per_second": 642.952, | |
| "eval_steps_per_second": 10.738, | |
| "step": 57168 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.989346448816272e-05, | |
| "loss": 5.6997, | |
| "step": 60741 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.15605646376164706, | |
| "eval_loss": 5.713454723358154, | |
| "eval_runtime": 0.7453, | |
| "eval_samples_per_second": 642.723, | |
| "eval_steps_per_second": 10.734, | |
| "step": 60741 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.929809936645549e-05, | |
| "loss": 5.6698, | |
| "step": 64314 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.1619928905941432, | |
| "eval_loss": 5.685813903808594, | |
| "eval_runtime": 0.7411, | |
| "eval_samples_per_second": 646.313, | |
| "eval_steps_per_second": 10.794, | |
| "step": 64314 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 3.870273424474825e-05, | |
| "loss": 5.6398, | |
| "step": 67887 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.16435543303985822, | |
| "eval_loss": 5.673512935638428, | |
| "eval_runtime": 0.7428, | |
| "eval_samples_per_second": 644.852, | |
| "eval_steps_per_second": 10.77, | |
| "step": 67887 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.810720240080027e-05, | |
| "loss": 5.6135, | |
| "step": 71460 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.1681270846288654, | |
| "eval_loss": 5.617359638214111, | |
| "eval_runtime": 0.7426, | |
| "eval_samples_per_second": 645.022, | |
| "eval_steps_per_second": 10.773, | |
| "step": 71460 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.751217072357452e-05, | |
| "loss": 5.5899, | |
| "step": 75033 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.1684192862736324, | |
| "eval_loss": 5.619091510772705, | |
| "eval_runtime": 0.7423, | |
| "eval_samples_per_second": 645.301, | |
| "eval_steps_per_second": 10.777, | |
| "step": 75033 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 3.69164721573858e-05, | |
| "loss": 5.5699, | |
| "step": 78606 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.16689319288707669, | |
| "eval_loss": 5.5976715087890625, | |
| "eval_runtime": 0.7425, | |
| "eval_samples_per_second": 645.154, | |
| "eval_steps_per_second": 10.775, | |
| "step": 78606 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 3.632094031343781e-05, | |
| "loss": 5.5487, | |
| "step": 82179 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.16692754919499106, | |
| "eval_loss": 5.613892078399658, | |
| "eval_runtime": 0.7425, | |
| "eval_samples_per_second": 645.088, | |
| "eval_steps_per_second": 10.774, | |
| "step": 82179 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 3.5725741913971326e-05, | |
| "loss": 5.529, | |
| "step": 85752 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.17411228879080098, | |
| "eval_loss": 5.527188301086426, | |
| "eval_runtime": 0.7442, | |
| "eval_samples_per_second": 643.623, | |
| "eval_steps_per_second": 10.749, | |
| "step": 85752 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 3.5130210070023345e-05, | |
| "loss": 5.512, | |
| "step": 89325 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.17266307533424513, | |
| "eval_loss": 5.5271124839782715, | |
| "eval_runtime": 0.742, | |
| "eval_samples_per_second": 645.531, | |
| "eval_steps_per_second": 10.781, | |
| "step": 89325 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 3.453467822607536e-05, | |
| "loss": 5.4939, | |
| "step": 92898 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.1721401127408363, | |
| "eval_loss": 5.518980979919434, | |
| "eval_runtime": 0.7466, | |
| "eval_samples_per_second": 641.587, | |
| "eval_steps_per_second": 10.715, | |
| "step": 92898 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 3.3939313104368124e-05, | |
| "loss": 5.4765, | |
| "step": 96471 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.17704899557659257, | |
| "eval_loss": 5.482353687286377, | |
| "eval_runtime": 0.7454, | |
| "eval_samples_per_second": 642.613, | |
| "eval_steps_per_second": 10.733, | |
| "step": 96471 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.334378126042014e-05, | |
| "loss": 5.4604, | |
| "step": 100044 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.17465552419016742, | |
| "eval_loss": 5.515853404998779, | |
| "eval_runtime": 0.7444, | |
| "eval_samples_per_second": 643.514, | |
| "eval_steps_per_second": 10.748, | |
| "step": 100044 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 3.274824941647216e-05, | |
| "loss": 5.4422, | |
| "step": 103617 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.18071012188659247, | |
| "eval_loss": 5.457724571228027, | |
| "eval_runtime": 0.7437, | |
| "eval_samples_per_second": 644.106, | |
| "eval_steps_per_second": 10.758, | |
| "step": 103617 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.215288429476492e-05, | |
| "loss": 5.4243, | |
| "step": 107190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.17723527446832202, | |
| "eval_loss": 5.4546217918396, | |
| "eval_runtime": 0.7437, | |
| "eval_samples_per_second": 644.065, | |
| "eval_steps_per_second": 10.757, | |
| "step": 107190 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 3.155735245081694e-05, | |
| "loss": 5.408, | |
| "step": 110763 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.18372376285301534, | |
| "eval_loss": 5.42967414855957, | |
| "eval_runtime": 0.7402, | |
| "eval_samples_per_second": 647.111, | |
| "eval_steps_per_second": 10.808, | |
| "step": 110763 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 3.09619873291097e-05, | |
| "loss": 5.3915, | |
| "step": 114336 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.18657804700207528, | |
| "eval_loss": 5.408855438232422, | |
| "eval_runtime": 0.7424, | |
| "eval_samples_per_second": 645.224, | |
| "eval_steps_per_second": 10.776, | |
| "step": 114336 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 3.0366288762920974e-05, | |
| "loss": 5.3766, | |
| "step": 117909 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.18478903369268443, | |
| "eval_loss": 5.399631023406982, | |
| "eval_runtime": 0.738, | |
| "eval_samples_per_second": 649.025, | |
| "eval_steps_per_second": 10.84, | |
| "step": 117909 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 2.977092364121374e-05, | |
| "loss": 5.3594, | |
| "step": 121482 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.1840884164346579, | |
| "eval_loss": 5.397375106811523, | |
| "eval_runtime": 0.7416, | |
| "eval_samples_per_second": 645.897, | |
| "eval_steps_per_second": 10.787, | |
| "step": 121482 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 2.91755585195065e-05, | |
| "loss": 5.3451, | |
| "step": 125055 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.19081023213883255, | |
| "eval_loss": 5.371816158294678, | |
| "eval_runtime": 0.7407, | |
| "eval_samples_per_second": 646.688, | |
| "eval_steps_per_second": 10.801, | |
| "step": 125055 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 2.858002667555852e-05, | |
| "loss": 5.3294, | |
| "step": 128628 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.18781625441696112, | |
| "eval_loss": 5.370606422424316, | |
| "eval_runtime": 0.7401, | |
| "eval_samples_per_second": 647.222, | |
| "eval_steps_per_second": 10.81, | |
| "step": 128628 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 2.7984661553851283e-05, | |
| "loss": 5.3155, | |
| "step": 132201 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.19025888053184598, | |
| "eval_loss": 5.367715835571289, | |
| "eval_runtime": 0.74, | |
| "eval_samples_per_second": 647.333, | |
| "eval_steps_per_second": 10.811, | |
| "step": 132201 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 2.738929643214405e-05, | |
| "loss": 5.2996, | |
| "step": 135774 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.1993961082531872, | |
| "eval_loss": 5.296998023986816, | |
| "eval_runtime": 0.741, | |
| "eval_samples_per_second": 646.422, | |
| "eval_steps_per_second": 10.796, | |
| "step": 135774 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 2.679376458819607e-05, | |
| "loss": 5.287, | |
| "step": 139347 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.1976698373388867, | |
| "eval_loss": 5.312738418579102, | |
| "eval_runtime": 0.7407, | |
| "eval_samples_per_second": 646.699, | |
| "eval_steps_per_second": 10.801, | |
| "step": 139347 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.619856618872958e-05, | |
| "loss": 5.2735, | |
| "step": 142920 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.1954803206793486, | |
| "eval_loss": 5.314471244812012, | |
| "eval_runtime": 0.7488, | |
| "eval_samples_per_second": 639.694, | |
| "eval_steps_per_second": 10.684, | |
| "step": 142920 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 2.560286762254085e-05, | |
| "loss": 5.26, | |
| "step": 146493 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.201684222384949, | |
| "eval_loss": 5.298509120941162, | |
| "eval_runtime": 0.7424, | |
| "eval_samples_per_second": 645.229, | |
| "eval_steps_per_second": 10.776, | |
| "step": 146493 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 2.5007502500833613e-05, | |
| "loss": 5.2487, | |
| "step": 150066 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.20246748544851978, | |
| "eval_loss": 5.266134262084961, | |
| "eval_runtime": 0.7667, | |
| "eval_samples_per_second": 624.736, | |
| "eval_steps_per_second": 10.434, | |
| "step": 150066 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 2.441197065688563e-05, | |
| "loss": 5.2362, | |
| "step": 153639 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.2031214848143982, | |
| "eval_loss": 5.2712297439575195, | |
| "eval_runtime": 0.7435, | |
| "eval_samples_per_second": 644.236, | |
| "eval_steps_per_second": 10.76, | |
| "step": 153639 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 2.3816605535178393e-05, | |
| "loss": 5.2248, | |
| "step": 157212 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.2048919322568828, | |
| "eval_loss": 5.2451701164245605, | |
| "eval_runtime": 0.7423, | |
| "eval_samples_per_second": 645.278, | |
| "eval_steps_per_second": 10.777, | |
| "step": 157212 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 2.3221240413471157e-05, | |
| "loss": 5.2115, | |
| "step": 160785 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.20544290288153683, | |
| "eval_loss": 5.232546806335449, | |
| "eval_runtime": 0.7431, | |
| "eval_samples_per_second": 644.607, | |
| "eval_steps_per_second": 10.766, | |
| "step": 160785 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 2.2625708569523176e-05, | |
| "loss": 5.1998, | |
| "step": 164358 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.20746922947226437, | |
| "eval_loss": 5.223347187042236, | |
| "eval_runtime": 0.742, | |
| "eval_samples_per_second": 645.58, | |
| "eval_steps_per_second": 10.782, | |
| "step": 164358 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 2.2030176725575194e-05, | |
| "loss": 5.188, | |
| "step": 167931 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.21180000560836768, | |
| "eval_loss": 5.199436664581299, | |
| "eval_runtime": 0.748, | |
| "eval_samples_per_second": 640.38, | |
| "eval_steps_per_second": 10.695, | |
| "step": 167931 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 2.143481160386796e-05, | |
| "loss": 5.1779, | |
| "step": 171504 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.20685218850510417, | |
| "eval_loss": 5.243590354919434, | |
| "eval_runtime": 0.7487, | |
| "eval_samples_per_second": 639.747, | |
| "eval_steps_per_second": 10.685, | |
| "step": 171504 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 2.083944648216072e-05, | |
| "loss": 5.1664, | |
| "step": 175077 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.2129035902940595, | |
| "eval_loss": 5.220259666442871, | |
| "eval_runtime": 0.7417, | |
| "eval_samples_per_second": 645.78, | |
| "eval_steps_per_second": 10.785, | |
| "step": 175077 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.024391463821274e-05, | |
| "loss": 5.1546, | |
| "step": 178650 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.21341669482933423, | |
| "eval_loss": 5.181967258453369, | |
| "eval_runtime": 0.74, | |
| "eval_samples_per_second": 647.263, | |
| "eval_steps_per_second": 10.81, | |
| "step": 178650 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "learning_rate": 1.9648549516505503e-05, | |
| "loss": 5.1431, | |
| "step": 182223 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.2122388143648584, | |
| "eval_loss": 5.202933311462402, | |
| "eval_runtime": 0.7441, | |
| "eval_samples_per_second": 643.704, | |
| "eval_steps_per_second": 10.751, | |
| "step": 182223 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 1.9053184394798267e-05, | |
| "loss": 5.133, | |
| "step": 185796 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.2139890957371677, | |
| "eval_loss": 5.145828723907471, | |
| "eval_runtime": 0.7427, | |
| "eval_samples_per_second": 644.964, | |
| "eval_steps_per_second": 10.772, | |
| "step": 185796 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 1.8457652550850286e-05, | |
| "loss": 5.1226, | |
| "step": 189369 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.21629691642249196, | |
| "eval_loss": 5.175747394561768, | |
| "eval_runtime": 0.7414, | |
| "eval_samples_per_second": 646.07, | |
| "eval_steps_per_second": 10.79, | |
| "step": 189369 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 1.7862287429143047e-05, | |
| "loss": 5.1138, | |
| "step": 192942 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.21931465914485995, | |
| "eval_loss": 5.137957572937012, | |
| "eval_runtime": 0.7463, | |
| "eval_samples_per_second": 641.826, | |
| "eval_steps_per_second": 10.719, | |
| "step": 192942 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 1.726692230743581e-05, | |
| "loss": 5.1046, | |
| "step": 196515 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.2177620690622458, | |
| "eval_loss": 5.1497979164123535, | |
| "eval_runtime": 0.743, | |
| "eval_samples_per_second": 644.669, | |
| "eval_steps_per_second": 10.767, | |
| "step": 196515 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 1.6671557185728576e-05, | |
| "loss": 5.0984, | |
| "step": 200088 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.21936753338018272, | |
| "eval_loss": 5.1094207763671875, | |
| "eval_runtime": 0.7432, | |
| "eval_samples_per_second": 644.503, | |
| "eval_steps_per_second": 10.764, | |
| "step": 200088 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "learning_rate": 1.6076025341780594e-05, | |
| "loss": 5.0907, | |
| "step": 203661 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.22019682397673898, | |
| "eval_loss": 5.135354995727539, | |
| "eval_runtime": 0.7592, | |
| "eval_samples_per_second": 630.904, | |
| "eval_steps_per_second": 10.537, | |
| "step": 203661 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 1.548066022007336e-05, | |
| "loss": 5.0812, | |
| "step": 207234 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.22555465405813727, | |
| "eval_loss": 5.066197395324707, | |
| "eval_runtime": 0.7435, | |
| "eval_samples_per_second": 644.224, | |
| "eval_steps_per_second": 10.759, | |
| "step": 207234 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "learning_rate": 1.4885295098366123e-05, | |
| "loss": 5.0748, | |
| "step": 210807 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.21810022855231617, | |
| "eval_loss": 5.116298198699951, | |
| "eval_runtime": 0.7413, | |
| "eval_samples_per_second": 646.139, | |
| "eval_steps_per_second": 10.791, | |
| "step": 210807 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.428976325441814e-05, | |
| "loss": 5.067, | |
| "step": 214380 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.2199191102123357, | |
| "eval_loss": 5.119345664978027, | |
| "eval_runtime": 0.7438, | |
| "eval_samples_per_second": 643.957, | |
| "eval_steps_per_second": 10.755, | |
| "step": 214380 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "learning_rate": 1.3694398132710903e-05, | |
| "loss": 5.0609, | |
| "step": 217953 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.22237028400099942, | |
| "eval_loss": 5.091867446899414, | |
| "eval_runtime": 0.7487, | |
| "eval_samples_per_second": 639.76, | |
| "eval_steps_per_second": 10.685, | |
| "step": 217953 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 1.309903301100367e-05, | |
| "loss": 5.0536, | |
| "step": 221526 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.2238659606063153, | |
| "eval_loss": 5.089934349060059, | |
| "eval_runtime": 0.7427, | |
| "eval_samples_per_second": 644.961, | |
| "eval_steps_per_second": 10.772, | |
| "step": 221526 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "learning_rate": 1.2503667889296434e-05, | |
| "loss": 5.0491, | |
| "step": 225099 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.22235195996663887, | |
| "eval_loss": 5.112506866455078, | |
| "eval_runtime": 0.744, | |
| "eval_samples_per_second": 643.802, | |
| "eval_steps_per_second": 10.752, | |
| "step": 225099 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 1.1907969323107703e-05, | |
| "loss": 5.0433, | |
| "step": 228672 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.22262113416633686, | |
| "eval_loss": 5.0892157554626465, | |
| "eval_runtime": 0.7431, | |
| "eval_samples_per_second": 644.558, | |
| "eval_steps_per_second": 10.765, | |
| "step": 228672 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 1.1312604201400467e-05, | |
| "loss": 5.0373, | |
| "step": 232245 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.22597519475771297, | |
| "eval_loss": 5.064445972442627, | |
| "eval_runtime": 0.7398, | |
| "eval_samples_per_second": 647.432, | |
| "eval_steps_per_second": 10.813, | |
| "step": 232245 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 1.0717239079693232e-05, | |
| "loss": 5.032, | |
| "step": 235818 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.22527426278723942, | |
| "eval_loss": 5.062305927276611, | |
| "eval_runtime": 0.7441, | |
| "eval_samples_per_second": 643.745, | |
| "eval_steps_per_second": 10.751, | |
| "step": 235818 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "learning_rate": 1.0121873957985996e-05, | |
| "loss": 5.0283, | |
| "step": 239391 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.22131170544158504, | |
| "eval_loss": 5.100430011749268, | |
| "eval_runtime": 0.7454, | |
| "eval_samples_per_second": 642.6, | |
| "eval_steps_per_second": 10.732, | |
| "step": 239391 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 9.526342114038013e-06, | |
| "loss": 5.0223, | |
| "step": 242964 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.22790462549498694, | |
| "eval_loss": 5.057290077209473, | |
| "eval_runtime": 0.7453, | |
| "eval_samples_per_second": 642.666, | |
| "eval_steps_per_second": 10.733, | |
| "step": 242964 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "learning_rate": 8.930976992330777e-06, | |
| "loss": 5.0184, | |
| "step": 246537 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.22710971646307296, | |
| "eval_loss": 5.048848628997803, | |
| "eval_runtime": 0.7418, | |
| "eval_samples_per_second": 645.766, | |
| "eval_steps_per_second": 10.785, | |
| "step": 246537 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 8.335445148382794e-06, | |
| "loss": 5.014, | |
| "step": 250110 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.22795434198746642, | |
| "eval_loss": 5.048243999481201, | |
| "eval_runtime": 0.7433, | |
| "eval_samples_per_second": 644.41, | |
| "eval_steps_per_second": 10.763, | |
| "step": 250110 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "learning_rate": 7.740246748916306e-06, | |
| "loss": 5.0102, | |
| "step": 253683 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.22687027178481367, | |
| "eval_loss": 5.060031414031982, | |
| "eval_runtime": 0.7439, | |
| "eval_samples_per_second": 643.923, | |
| "eval_steps_per_second": 10.754, | |
| "step": 253683 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 7.144714904968323e-06, | |
| "loss": 5.0079, | |
| "step": 257256 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.2278910610607803, | |
| "eval_loss": 5.027137279510498, | |
| "eval_runtime": 0.7414, | |
| "eval_samples_per_second": 646.086, | |
| "eval_steps_per_second": 10.791, | |
| "step": 257256 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "learning_rate": 6.549349783261087e-06, | |
| "loss": 5.0029, | |
| "step": 260829 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.22669124629908943, | |
| "eval_loss": 5.062880039215088, | |
| "eval_runtime": 0.7483, | |
| "eval_samples_per_second": 640.112, | |
| "eval_steps_per_second": 10.691, | |
| "step": 260829 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "learning_rate": 5.9538179393131045e-06, | |
| "loss": 4.9994, | |
| "step": 264402 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.22970634211701652, | |
| "eval_loss": 5.030394554138184, | |
| "eval_runtime": 0.7474, | |
| "eval_samples_per_second": 640.862, | |
| "eval_steps_per_second": 10.703, | |
| "step": 264402 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 5.358286095365122e-06, | |
| "loss": 4.9978, | |
| "step": 267975 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.22689803559951938, | |
| "eval_loss": 5.048463821411133, | |
| "eval_runtime": 0.7472, | |
| "eval_samples_per_second": 641.032, | |
| "eval_steps_per_second": 10.706, | |
| "step": 267975 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "learning_rate": 4.7630876958986335e-06, | |
| "loss": 4.9945, | |
| "step": 271548 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.23055979997221837, | |
| "eval_loss": 5.037987232208252, | |
| "eval_runtime": 0.7423, | |
| "eval_samples_per_second": 645.335, | |
| "eval_steps_per_second": 10.778, | |
| "step": 271548 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "learning_rate": 4.167389129709903e-06, | |
| "loss": 4.9917, | |
| "step": 275121 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.2264717436444245, | |
| "eval_loss": 5.058966636657715, | |
| "eval_runtime": 0.7422, | |
| "eval_samples_per_second": 645.356, | |
| "eval_steps_per_second": 10.778, | |
| "step": 275121 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "learning_rate": 3.5720240080026674e-06, | |
| "loss": 4.9913, | |
| "step": 278694 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.226176645603695, | |
| "eval_loss": 5.058542728424072, | |
| "eval_runtime": 0.7385, | |
| "eval_samples_per_second": 648.623, | |
| "eval_steps_per_second": 10.833, | |
| "step": 278694 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "learning_rate": 2.976658886295432e-06, | |
| "loss": 4.987, | |
| "step": 282267 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.2278051787916153, | |
| "eval_loss": 5.033863544464111, | |
| "eval_runtime": 0.7435, | |
| "eval_samples_per_second": 644.245, | |
| "eval_steps_per_second": 10.76, | |
| "step": 282267 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 2.3812937645881964e-06, | |
| "loss": 4.9862, | |
| "step": 285840 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.2305035650623886, | |
| "eval_loss": 5.021360397338867, | |
| "eval_runtime": 0.7486, | |
| "eval_samples_per_second": 639.881, | |
| "eval_steps_per_second": 10.687, | |
| "step": 285840 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "learning_rate": 1.7857619206402134e-06, | |
| "loss": 4.9841, | |
| "step": 289413 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.227092194586068, | |
| "eval_loss": 5.039330005645752, | |
| "eval_runtime": 0.7471, | |
| "eval_samples_per_second": 641.165, | |
| "eval_steps_per_second": 10.708, | |
| "step": 289413 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "learning_rate": 1.1903967989329777e-06, | |
| "loss": 4.983, | |
| "step": 292986 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.22981801867481705, | |
| "eval_loss": 5.02002477645874, | |
| "eval_runtime": 0.747, | |
| "eval_samples_per_second": 641.199, | |
| "eval_steps_per_second": 10.709, | |
| "step": 292986 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "learning_rate": 5.95031677225742e-07, | |
| "loss": 4.9816, | |
| "step": 296559 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.22995899106791753, | |
| "eval_loss": 5.028861045837402, | |
| "eval_runtime": 0.7441, | |
| "eval_samples_per_second": 643.773, | |
| "eval_steps_per_second": 10.752, | |
| "step": 296559 | |
| }, | |
| { | |
| "epoch": 83.96, | |
| "learning_rate": 2.1340446815605204e-08, | |
| "loss": 4.9801, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 83.96, | |
| "eval_accuracy": 0.23321614400225005, | |
| "eval_loss": 4.9971747398376465, | |
| "eval_runtime": 0.7444, | |
| "eval_samples_per_second": 643.479, | |
| "eval_steps_per_second": 10.747, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 83.96, | |
| "step": 300000, | |
| "total_flos": 2.3423641855784387e+18, | |
| "train_loss": 5.338385032552083, | |
| "train_runtime": 55456.4482, | |
| "train_samples_per_second": 346.218, | |
| "train_steps_per_second": 5.41 | |
| } | |
| ], | |
| "max_steps": 300000, | |
| "num_train_epochs": 84, | |
| "total_flos": 2.3423641855784387e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |