| { | |
| "best_metric": 0.439, | |
| "best_model_checkpoint": "runs/legis-llama3-1-8b-valid-arandu/checkpoint-1120", | |
| "epoch": 0.9995600527936648, | |
| "eval_steps": 5, | |
| "global_step": 1136, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004399472063352398, | |
| "grad_norm": 25.937191009521484, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 1.0992, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004399472063352398, | |
| "eval_loss": 1.1428982019424438, | |
| "eval_runtime": 29.8805, | |
| "eval_samples_per_second": 0.569, | |
| "eval_steps_per_second": 0.301, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008798944126704795, | |
| "grad_norm": 32.52676773071289, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 1.067, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008798944126704795, | |
| "eval_loss": 1.0669578313827515, | |
| "eval_runtime": 28.5282, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013198416190057193, | |
| "grad_norm": 78.51001739501953, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.0057, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013198416190057193, | |
| "eval_loss": 1.0462743043899536, | |
| "eval_runtime": 28.5697, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01759788825340959, | |
| "grad_norm": 21.255964279174805, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.9236, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01759788825340959, | |
| "eval_loss": 0.9604344367980957, | |
| "eval_runtime": 28.6152, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02199736031676199, | |
| "grad_norm": 1.3699233531951904, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.8823, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02199736031676199, | |
| "eval_loss": 0.9002779126167297, | |
| "eval_runtime": 28.579, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026396832380114386, | |
| "grad_norm": 2.50810170173645, | |
| "learning_rate": 5.2631578947368424e-05, | |
| "loss": 0.8144, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.026396832380114386, | |
| "eval_loss": 0.8441588878631592, | |
| "eval_runtime": 28.4936, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030796304443466784, | |
| "grad_norm": 1.6816316843032837, | |
| "learning_rate": 6.140350877192983e-05, | |
| "loss": 0.7829, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.030796304443466784, | |
| "eval_loss": 0.7928382754325867, | |
| "eval_runtime": 28.5908, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03519577650681918, | |
| "grad_norm": 0.5125584006309509, | |
| "learning_rate": 7.017543859649122e-05, | |
| "loss": 0.7075, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03519577650681918, | |
| "eval_loss": 0.7538504600524902, | |
| "eval_runtime": 28.5816, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.039595248570171576, | |
| "grad_norm": 0.36081045866012573, | |
| "learning_rate": 7.894736842105263e-05, | |
| "loss": 0.6776, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.039595248570171576, | |
| "eval_loss": 0.7313268184661865, | |
| "eval_runtime": 28.6141, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04399472063352398, | |
| "grad_norm": 0.32318177819252014, | |
| "learning_rate": 8.771929824561403e-05, | |
| "loss": 0.6499, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04399472063352398, | |
| "eval_loss": 0.71351158618927, | |
| "eval_runtime": 28.5766, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04839419269687637, | |
| "grad_norm": 0.34377261996269226, | |
| "learning_rate": 9.649122807017544e-05, | |
| "loss": 0.6487, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04839419269687637, | |
| "eval_loss": 0.7006722092628479, | |
| "eval_runtime": 28.6048, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05279366476022877, | |
| "grad_norm": 0.4360629618167877, | |
| "learning_rate": 0.00010526315789473685, | |
| "loss": 0.6405, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05279366476022877, | |
| "eval_loss": 0.6905343532562256, | |
| "eval_runtime": 28.5257, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05719313682358117, | |
| "grad_norm": 0.28764936327934265, | |
| "learning_rate": 0.00011403508771929824, | |
| "loss": 0.6352, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.05719313682358117, | |
| "eval_loss": 0.68143630027771, | |
| "eval_runtime": 28.6362, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06159260888693357, | |
| "grad_norm": 0.34088754653930664, | |
| "learning_rate": 0.00012280701754385965, | |
| "loss": 0.6064, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06159260888693357, | |
| "eval_loss": 0.6742813587188721, | |
| "eval_runtime": 28.5667, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06599208095028597, | |
| "grad_norm": 0.31284183263778687, | |
| "learning_rate": 0.00013157894736842108, | |
| "loss": 0.5924, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06599208095028597, | |
| "eval_loss": 0.6679767966270447, | |
| "eval_runtime": 28.461, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07039155301363836, | |
| "grad_norm": 0.30470508337020874, | |
| "learning_rate": 0.00014035087719298245, | |
| "loss": 0.5992, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07039155301363836, | |
| "eval_loss": 0.6631008386611938, | |
| "eval_runtime": 28.6891, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07479102507699076, | |
| "grad_norm": 0.3255262076854706, | |
| "learning_rate": 0.00014912280701754387, | |
| "loss": 0.5704, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07479102507699076, | |
| "eval_loss": 0.658618688583374, | |
| "eval_runtime": 28.6094, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07919049714034315, | |
| "grad_norm": 0.31922295689582825, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 0.6048, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07919049714034315, | |
| "eval_loss": 0.6537344455718994, | |
| "eval_runtime": 28.532, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08358996920369556, | |
| "grad_norm": 0.45636337995529175, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.613, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08358996920369556, | |
| "eval_loss": 0.6501972079277039, | |
| "eval_runtime": 28.6568, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08798944126704795, | |
| "grad_norm": 0.29334941506385803, | |
| "learning_rate": 0.00017543859649122806, | |
| "loss": 0.5799, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08798944126704795, | |
| "eval_loss": 0.6471393704414368, | |
| "eval_runtime": 28.5997, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09238891333040035, | |
| "grad_norm": 0.31318825483322144, | |
| "learning_rate": 0.00018421052631578948, | |
| "loss": 0.5887, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.09238891333040035, | |
| "eval_loss": 0.6440868377685547, | |
| "eval_runtime": 28.6275, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.09678838539375274, | |
| "grad_norm": 0.27908894419670105, | |
| "learning_rate": 0.00019298245614035088, | |
| "loss": 0.5905, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09678838539375274, | |
| "eval_loss": 0.6423875689506531, | |
| "eval_runtime": 28.5491, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10118785745710515, | |
| "grad_norm": 0.2715133726596832, | |
| "learning_rate": 0.00019999952753720356, | |
| "loss": 0.5902, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.10118785745710515, | |
| "eval_loss": 0.6415910720825195, | |
| "eval_runtime": 28.5086, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.10558732952045755, | |
| "grad_norm": 0.3028790056705475, | |
| "learning_rate": 0.000199982991808088, | |
| "loss": 0.5773, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10558732952045755, | |
| "eval_loss": 0.6377425789833069, | |
| "eval_runtime": 28.6438, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10998680158380994, | |
| "grad_norm": 0.3071883022785187, | |
| "learning_rate": 0.00019994283740338306, | |
| "loss": 0.5598, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.10998680158380994, | |
| "eval_loss": 0.6367806196212769, | |
| "eval_runtime": 28.4852, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.11438627364716233, | |
| "grad_norm": 0.34842655062675476, | |
| "learning_rate": 0.00019987907380864062, | |
| "loss": 0.596, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11438627364716233, | |
| "eval_loss": 0.6347749829292297, | |
| "eval_runtime": 28.5908, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11878574571051474, | |
| "grad_norm": 0.2854275107383728, | |
| "learning_rate": 0.00019979171608653924, | |
| "loss": 0.5733, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.11878574571051474, | |
| "eval_loss": 0.6301032900810242, | |
| "eval_runtime": 28.5482, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.12318521777386714, | |
| "grad_norm": 0.27615901827812195, | |
| "learning_rate": 0.00019968078487332566, | |
| "loss": 0.5875, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12318521777386714, | |
| "eval_loss": 0.6269793510437012, | |
| "eval_runtime": 28.4974, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12758468983721954, | |
| "grad_norm": 0.2709368169307709, | |
| "learning_rate": 0.00019954630637394029, | |
| "loss": 0.5711, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.12758468983721954, | |
| "eval_loss": 0.6240233182907104, | |
| "eval_runtime": 28.5264, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.13198416190057194, | |
| "grad_norm": 0.2877412736415863, | |
| "learning_rate": 0.00019938831235582672, | |
| "loss": 0.5885, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13198416190057194, | |
| "eval_loss": 0.6206945776939392, | |
| "eval_runtime": 28.5668, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13638363396392433, | |
| "grad_norm": 0.2922605574131012, | |
| "learning_rate": 0.00019920684014142738, | |
| "loss": 0.5485, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.13638363396392433, | |
| "eval_loss": 0.6200662851333618, | |
| "eval_runtime": 28.5452, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.14078310602727673, | |
| "grad_norm": 0.28340834379196167, | |
| "learning_rate": 0.00019900193259936704, | |
| "loss": 0.5754, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14078310602727673, | |
| "eval_loss": 0.6187402606010437, | |
| "eval_runtime": 28.5939, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14518257809062912, | |
| "grad_norm": 0.2796618938446045, | |
| "learning_rate": 0.0001987736381343261, | |
| "loss": 0.5535, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.14518257809062912, | |
| "eval_loss": 0.6156266331672668, | |
| "eval_runtime": 28.5378, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.14958205015398152, | |
| "grad_norm": 0.25343528389930725, | |
| "learning_rate": 0.00019852201067560606, | |
| "loss": 0.5697, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.14958205015398152, | |
| "eval_loss": 0.6125033497810364, | |
| "eval_runtime": 28.5565, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1539815222173339, | |
| "grad_norm": 0.23438464105129242, | |
| "learning_rate": 0.00019824710966438996, | |
| "loss": 0.5335, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1539815222173339, | |
| "eval_loss": 0.6096713542938232, | |
| "eval_runtime": 28.6017, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1583809942806863, | |
| "grad_norm": 0.24729043245315552, | |
| "learning_rate": 0.00019794900003970077, | |
| "loss": 0.5702, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1583809942806863, | |
| "eval_loss": 0.6071114540100098, | |
| "eval_runtime": 28.5677, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.16278046634403873, | |
| "grad_norm": 0.257964551448822, | |
| "learning_rate": 0.00019762775222306107, | |
| "loss": 0.5494, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.16278046634403873, | |
| "eval_loss": 0.6062531471252441, | |
| "eval_runtime": 28.5933, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.16717993840739112, | |
| "grad_norm": 0.2648680806159973, | |
| "learning_rate": 0.0001972834421018576, | |
| "loss": 0.5379, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.16717993840739112, | |
| "eval_loss": 0.6054437756538391, | |
| "eval_runtime": 28.5575, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.17157941047074352, | |
| "grad_norm": 0.2540712356567383, | |
| "learning_rate": 0.00019691615101141455, | |
| "loss": 0.5415, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.17157941047074352, | |
| "eval_loss": 0.6023730039596558, | |
| "eval_runtime": 28.5419, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.1759788825340959, | |
| "grad_norm": 0.2424851357936859, | |
| "learning_rate": 0.00019652596571578004, | |
| "loss": 0.5504, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1759788825340959, | |
| "eval_loss": 0.5997632145881653, | |
| "eval_runtime": 28.6422, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1803783545974483, | |
| "grad_norm": 0.2573873698711395, | |
| "learning_rate": 0.0001961129783872301, | |
| "loss": 0.5418, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.1803783545974483, | |
| "eval_loss": 0.5976300239562988, | |
| "eval_runtime": 28.5752, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.1847778266608007, | |
| "grad_norm": 0.22338183224201202, | |
| "learning_rate": 0.00019567728658449504, | |
| "loss": 0.54, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1847778266608007, | |
| "eval_loss": 0.5960862040519714, | |
| "eval_runtime": 28.4685, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1891772987241531, | |
| "grad_norm": 0.2706097960472107, | |
| "learning_rate": 0.00019521899322971352, | |
| "loss": 0.5522, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.1891772987241531, | |
| "eval_loss": 0.5958646535873413, | |
| "eval_runtime": 28.5678, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.1935767707875055, | |
| "grad_norm": 0.23476411402225494, | |
| "learning_rate": 0.00019473820658411957, | |
| "loss": 0.5262, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.1935767707875055, | |
| "eval_loss": 0.5945417284965515, | |
| "eval_runtime": 28.5611, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.1979762428508579, | |
| "grad_norm": 0.23705659806728363, | |
| "learning_rate": 0.00019423504022246825, | |
| "loss": 0.5439, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.1979762428508579, | |
| "eval_loss": 0.5934200286865234, | |
| "eval_runtime": 28.5955, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2023757149142103, | |
| "grad_norm": 0.22662319242954254, | |
| "learning_rate": 0.00019370961300620637, | |
| "loss": 0.5262, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2023757149142103, | |
| "eval_loss": 0.5928044319152832, | |
| "eval_runtime": 28.514, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2067751869775627, | |
| "grad_norm": 0.24046145379543304, | |
| "learning_rate": 0.00019316204905539425, | |
| "loss": 0.5462, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2067751869775627, | |
| "eval_loss": 0.5904839038848877, | |
| "eval_runtime": 28.5557, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2111746590409151, | |
| "grad_norm": 0.23923470079898834, | |
| "learning_rate": 0.000192592477719385, | |
| "loss": 0.5345, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2111746590409151, | |
| "eval_loss": 0.590508759021759, | |
| "eval_runtime": 28.5204, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.21557413110426749, | |
| "grad_norm": 0.24345721304416656, | |
| "learning_rate": 0.00019200103354626892, | |
| "loss": 0.5478, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.21557413110426749, | |
| "eval_loss": 0.5882726907730103, | |
| "eval_runtime": 28.5722, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.21997360316761988, | |
| "grad_norm": 0.27501732110977173, | |
| "learning_rate": 0.00019138785625108957, | |
| "loss": 0.5607, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21997360316761988, | |
| "eval_loss": 0.5860432982444763, | |
| "eval_runtime": 28.503, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.22437307523097227, | |
| "grad_norm": 0.3151032328605652, | |
| "learning_rate": 0.0001907530906828393, | |
| "loss": 0.5479, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.22437307523097227, | |
| "eval_loss": 0.5846895575523376, | |
| "eval_runtime": 28.6081, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.22877254729432467, | |
| "grad_norm": 0.2758755385875702, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.5767, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.22877254729432467, | |
| "eval_loss": 0.5815722942352295, | |
| "eval_runtime": 28.5574, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2331720193576771, | |
| "grad_norm": 0.25241315364837646, | |
| "learning_rate": 0.000189419399586331, | |
| "loss": 0.5568, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.2331720193576771, | |
| "eval_loss": 0.5822274684906006, | |
| "eval_runtime": 28.573, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.23757149142102948, | |
| "grad_norm": 0.316436767578125, | |
| "learning_rate": 0.00018872078911183146, | |
| "loss": 0.5385, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.23757149142102948, | |
| "eval_loss": 0.5809066891670227, | |
| "eval_runtime": 28.5598, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.24197096348438188, | |
| "grad_norm": 0.27813801169395447, | |
| "learning_rate": 0.00018800122039735358, | |
| "loss": 0.5348, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.24197096348438188, | |
| "eval_loss": 0.5786107778549194, | |
| "eval_runtime": 28.546, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.24637043554773427, | |
| "grad_norm": 0.2552705407142639, | |
| "learning_rate": 0.00018726086342440846, | |
| "loss": 0.5207, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.24637043554773427, | |
| "eval_loss": 0.5768923759460449, | |
| "eval_runtime": 28.5995, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2507699076110867, | |
| "grad_norm": 0.21993091702461243, | |
| "learning_rate": 0.00018649989308525372, | |
| "loss": 0.5292, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.2507699076110867, | |
| "eval_loss": 0.5762263536453247, | |
| "eval_runtime": 28.4816, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.2551693796744391, | |
| "grad_norm": 0.27086153626441956, | |
| "learning_rate": 0.0001857184891415794, | |
| "loss": 0.5312, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2551693796744391, | |
| "eval_loss": 0.5758266448974609, | |
| "eval_runtime": 28.5295, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2595688517377915, | |
| "grad_norm": 0.21816319227218628, | |
| "learning_rate": 0.0001849168361820431, | |
| "loss": 0.5223, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.2595688517377915, | |
| "eval_loss": 0.574447751045227, | |
| "eval_runtime": 28.5859, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.2639683238011439, | |
| "grad_norm": 0.24796700477600098, | |
| "learning_rate": 0.00018409512357866548, | |
| "loss": 0.5485, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2639683238011439, | |
| "eval_loss": 0.573371410369873, | |
| "eval_runtime": 28.6178, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2683677958644963, | |
| "grad_norm": 0.2425287663936615, | |
| "learning_rate": 0.00018325354544209535, | |
| "loss": 0.5217, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.2683677958644963, | |
| "eval_loss": 0.5723298788070679, | |
| "eval_runtime": 28.5916, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.27276726792784867, | |
| "grad_norm": 0.21630050241947174, | |
| "learning_rate": 0.00018239230057575542, | |
| "loss": 0.5074, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.27276726792784867, | |
| "eval_loss": 0.5725327134132385, | |
| "eval_runtime": 28.536, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.27716673999120106, | |
| "grad_norm": 0.21529468894004822, | |
| "learning_rate": 0.0001815115924288798, | |
| "loss": 0.5487, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.27716673999120106, | |
| "eval_loss": 0.5721793174743652, | |
| "eval_runtime": 28.6852, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.28156621205455346, | |
| "grad_norm": 0.21623414754867554, | |
| "learning_rate": 0.00018061162904845358, | |
| "loss": 0.5106, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.28156621205455346, | |
| "eval_loss": 0.5709577202796936, | |
| "eval_runtime": 28.4592, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.28596568411790585, | |
| "grad_norm": 0.2219308316707611, | |
| "learning_rate": 0.0001796926230300667, | |
| "loss": 0.5218, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.28596568411790585, | |
| "eval_loss": 0.5698617100715637, | |
| "eval_runtime": 28.5588, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.29036515618125824, | |
| "grad_norm": 0.2264701873064041, | |
| "learning_rate": 0.00017875479146769305, | |
| "loss": 0.5162, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.29036515618125824, | |
| "eval_loss": 0.5689781308174133, | |
| "eval_runtime": 28.6221, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.29476462824461064, | |
| "grad_norm": 0.24004362523555756, | |
| "learning_rate": 0.000177798355902407, | |
| "loss": 0.539, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.29476462824461064, | |
| "eval_loss": 0.5678241848945618, | |
| "eval_runtime": 28.5677, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.29916410030796303, | |
| "grad_norm": 0.22996000945568085, | |
| "learning_rate": 0.00017682354227004963, | |
| "loss": 0.5002, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.29916410030796303, | |
| "eval_loss": 0.5670127272605896, | |
| "eval_runtime": 28.6425, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3035635723713154, | |
| "grad_norm": 0.23163671791553497, | |
| "learning_rate": 0.00017583058084785625, | |
| "loss": 0.5175, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.3035635723713154, | |
| "eval_loss": 0.5650352239608765, | |
| "eval_runtime": 28.5994, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.3079630444346678, | |
| "grad_norm": 0.20120489597320557, | |
| "learning_rate": 0.00017481970620005912, | |
| "loss": 0.5269, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3079630444346678, | |
| "eval_loss": 0.5640237927436829, | |
| "eval_runtime": 28.5009, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3123625164980202, | |
| "grad_norm": 0.22231583297252655, | |
| "learning_rate": 0.00017379115712247675, | |
| "loss": 0.5444, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.3123625164980202, | |
| "eval_loss": 0.5634257197380066, | |
| "eval_runtime": 28.5722, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.3167619885613726, | |
| "grad_norm": 0.216331347823143, | |
| "learning_rate": 0.00017274517658610398, | |
| "loss": 0.5074, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3167619885613726, | |
| "eval_loss": 0.5618783831596375, | |
| "eval_runtime": 28.6759, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.32116146062472506, | |
| "grad_norm": 0.21976010501384735, | |
| "learning_rate": 0.0001716820116797158, | |
| "loss": 0.5259, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.32116146062472506, | |
| "eval_loss": 0.5602042078971863, | |
| "eval_runtime": 28.6019, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.32556093268807745, | |
| "grad_norm": 0.22740119695663452, | |
| "learning_rate": 0.0001706019135514982, | |
| "loss": 0.5158, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.32556093268807745, | |
| "eval_loss": 0.5599080920219421, | |
| "eval_runtime": 28.5177, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.32996040475142985, | |
| "grad_norm": 0.21888501942157745, | |
| "learning_rate": 0.0001695051373497202, | |
| "loss": 0.527, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.32996040475142985, | |
| "eval_loss": 0.558814525604248, | |
| "eval_runtime": 28.661, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.33435987681478224, | |
| "grad_norm": 0.20402850210666656, | |
| "learning_rate": 0.00016839194216246108, | |
| "loss": 0.5027, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.33435987681478224, | |
| "eval_loss": 0.5578404664993286, | |
| "eval_runtime": 28.5421, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.33875934887813464, | |
| "grad_norm": 0.20368748903274536, | |
| "learning_rate": 0.00016726259095640664, | |
| "loss": 0.505, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.33875934887813464, | |
| "eval_loss": 0.5567160844802856, | |
| "eval_runtime": 28.6126, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.34315882094148703, | |
| "grad_norm": 0.2069130390882492, | |
| "learning_rate": 0.0001661173505147295, | |
| "loss": 0.5086, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.34315882094148703, | |
| "eval_loss": 0.55617755651474, | |
| "eval_runtime": 28.4879, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.3475582930048394, | |
| "grad_norm": 0.23644201457500458, | |
| "learning_rate": 0.00016495649137406772, | |
| "loss": 0.5412, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.3475582930048394, | |
| "eval_loss": 0.5556927919387817, | |
| "eval_runtime": 28.6713, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.3519577650681918, | |
| "grad_norm": 0.21997737884521484, | |
| "learning_rate": 0.00016378028776061667, | |
| "loss": 0.4908, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3519577650681918, | |
| "eval_loss": 0.5555915832519531, | |
| "eval_runtime": 28.596, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3563572371315442, | |
| "grad_norm": 0.22075805068016052, | |
| "learning_rate": 0.00016258901752534948, | |
| "loss": 0.5155, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.3563572371315442, | |
| "eval_loss": 0.5552019476890564, | |
| "eval_runtime": 28.595, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.3607567091948966, | |
| "grad_norm": 0.5917304158210754, | |
| "learning_rate": 0.00016138296207838127, | |
| "loss": 0.4991, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.3607567091948966, | |
| "eval_loss": 0.5550567507743835, | |
| "eval_runtime": 28.6222, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.365156181258249, | |
| "grad_norm": 0.21421152353286743, | |
| "learning_rate": 0.00016016240632249224, | |
| "loss": 0.4769, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.365156181258249, | |
| "eval_loss": 0.5548796653747559, | |
| "eval_runtime": 28.5933, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.3695556533216014, | |
| "grad_norm": 0.201774463057518, | |
| "learning_rate": 0.0001589276385858262, | |
| "loss": 0.4914, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3695556533216014, | |
| "eval_loss": 0.5546624064445496, | |
| "eval_runtime": 28.5213, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3739551253849538, | |
| "grad_norm": 0.22172759473323822, | |
| "learning_rate": 0.0001576789505537795, | |
| "loss": 0.4726, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.3739551253849538, | |
| "eval_loss": 0.5535080432891846, | |
| "eval_runtime": 28.6645, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.3783545974483062, | |
| "grad_norm": 0.23269815742969513, | |
| "learning_rate": 0.00015641663720009733, | |
| "loss": 0.5076, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3783545974483062, | |
| "eval_loss": 0.5522862076759338, | |
| "eval_runtime": 28.5697, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3827540695116586, | |
| "grad_norm": 0.23303498327732086, | |
| "learning_rate": 0.00015514099671719268, | |
| "loss": 0.5064, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.3827540695116586, | |
| "eval_loss": 0.5502522587776184, | |
| "eval_runtime": 28.5369, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.387153541575011, | |
| "grad_norm": 0.24087387323379517, | |
| "learning_rate": 0.00015385233044570555, | |
| "loss": 0.5361, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.387153541575011, | |
| "eval_loss": 0.5471201539039612, | |
| "eval_runtime": 28.5791, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3915530136383634, | |
| "grad_norm": 0.20800553262233734, | |
| "learning_rate": 0.00015255094280331797, | |
| "loss": 0.5169, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.3915530136383634, | |
| "eval_loss": 0.5466722846031189, | |
| "eval_runtime": 28.6339, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.3959524857017158, | |
| "grad_norm": 0.37092360854148865, | |
| "learning_rate": 0.0001512371412128424, | |
| "loss": 0.5362, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3959524857017158, | |
| "eval_loss": 0.5455148220062256, | |
| "eval_runtime": 28.637, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4003519577650682, | |
| "grad_norm": 0.20706337690353394, | |
| "learning_rate": 0.00014991123602960018, | |
| "loss": 0.4994, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.4003519577650682, | |
| "eval_loss": 0.5440109968185425, | |
| "eval_runtime": 28.5672, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.4047514298284206, | |
| "grad_norm": 0.2135256677865982, | |
| "learning_rate": 0.00014857354046810732, | |
| "loss": 0.5005, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.4047514298284206, | |
| "eval_loss": 0.5431147813796997, | |
| "eval_runtime": 28.4835, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.409150901891773, | |
| "grad_norm": 0.5737074613571167, | |
| "learning_rate": 0.00014722437052808472, | |
| "loss": 0.5208, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.409150901891773, | |
| "eval_loss": 0.541969358921051, | |
| "eval_runtime": 28.6004, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.4135503739551254, | |
| "grad_norm": 0.24099959433078766, | |
| "learning_rate": 0.00014586404491981052, | |
| "loss": 0.5074, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.4135503739551254, | |
| "eval_loss": 0.5449388027191162, | |
| "eval_runtime": 28.658, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.4179498460184778, | |
| "grad_norm": 0.2046642154455185, | |
| "learning_rate": 0.0001444928849888321, | |
| "loss": 0.5052, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4179498460184778, | |
| "eval_loss": 0.5407991409301758, | |
| "eval_runtime": 28.5688, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4223493180818302, | |
| "grad_norm": 0.2824171185493469, | |
| "learning_rate": 0.00014311121464005583, | |
| "loss": 0.5179, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4223493180818302, | |
| "eval_loss": 0.54000324010849, | |
| "eval_runtime": 28.7144, | |
| "eval_samples_per_second": 0.592, | |
| "eval_steps_per_second": 0.313, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4267487901451826, | |
| "grad_norm": 0.2045980840921402, | |
| "learning_rate": 0.00014171936026123168, | |
| "loss": 0.4634, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.4267487901451826, | |
| "eval_loss": 0.5398800373077393, | |
| "eval_runtime": 28.5209, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.43114826220853497, | |
| "grad_norm": 0.2092169225215912, | |
| "learning_rate": 0.00014031765064585197, | |
| "loss": 0.4802, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.43114826220853497, | |
| "eval_loss": 0.5395181179046631, | |
| "eval_runtime": 28.5086, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.43554773427188737, | |
| "grad_norm": 0.20700140297412872, | |
| "learning_rate": 0.00013890641691548114, | |
| "loss": 0.4962, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.43554773427188737, | |
| "eval_loss": 0.5390854477882385, | |
| "eval_runtime": 28.5682, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.43994720633523976, | |
| "grad_norm": 0.19903522729873657, | |
| "learning_rate": 0.00013748599244153633, | |
| "loss": 0.4841, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.43994720633523976, | |
| "eval_loss": 0.5381758213043213, | |
| "eval_runtime": 29.4274, | |
| "eval_samples_per_second": 0.578, | |
| "eval_steps_per_second": 0.306, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44434667839859215, | |
| "grad_norm": 0.4766729474067688, | |
| "learning_rate": 0.00013605671276653567, | |
| "loss": 0.5252, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.44434667839859215, | |
| "eval_loss": 0.5368968844413757, | |
| "eval_runtime": 28.6474, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.44874615046194455, | |
| "grad_norm": 0.21688155829906464, | |
| "learning_rate": 0.00013461891552483444, | |
| "loss": 0.515, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.44874615046194455, | |
| "eval_loss": 0.5366407036781311, | |
| "eval_runtime": 28.5352, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.45314562252529694, | |
| "grad_norm": 0.20375116169452667, | |
| "learning_rate": 0.00013317294036286644, | |
| "loss": 0.4887, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.45314562252529694, | |
| "eval_loss": 0.5360764861106873, | |
| "eval_runtime": 28.6533, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.45754509458864934, | |
| "grad_norm": 0.1958196461200714, | |
| "learning_rate": 0.00013171912885891063, | |
| "loss": 0.4868, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.45754509458864934, | |
| "eval_loss": 0.5356424450874329, | |
| "eval_runtime": 28.5027, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.4619445666520018, | |
| "grad_norm": 0.22040507197380066, | |
| "learning_rate": 0.00013025782444240087, | |
| "loss": 0.5086, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.4619445666520018, | |
| "eval_loss": 0.5351347327232361, | |
| "eval_runtime": 28.6428, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.4663440387153542, | |
| "grad_norm": 0.19495758414268494, | |
| "learning_rate": 0.00012878937231279892, | |
| "loss": 0.5113, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.4663440387153542, | |
| "eval_loss": 0.5347647070884705, | |
| "eval_runtime": 28.6252, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.4707435107787066, | |
| "grad_norm": 0.21149738132953644, | |
| "learning_rate": 0.0001273141193580488, | |
| "loss": 0.483, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.4707435107787066, | |
| "eval_loss": 0.5339221954345703, | |
| "eval_runtime": 28.6055, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.47514298284205897, | |
| "grad_norm": 0.20391018688678741, | |
| "learning_rate": 0.0001258324140726326, | |
| "loss": 0.4728, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.47514298284205897, | |
| "eval_loss": 0.5337977409362793, | |
| "eval_runtime": 28.5842, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.47954245490541136, | |
| "grad_norm": 0.20913545787334442, | |
| "learning_rate": 0.00012434460647524676, | |
| "loss": 0.5016, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.47954245490541136, | |
| "eval_loss": 0.532899022102356, | |
| "eval_runtime": 28.4759, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.48394192696876376, | |
| "grad_norm": 0.19410260021686554, | |
| "learning_rate": 0.00012285104802611812, | |
| "loss": 0.5103, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.48394192696876376, | |
| "eval_loss": 0.5321294665336609, | |
| "eval_runtime": 28.5662, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.48834139903211615, | |
| "grad_norm": 0.2097245752811432, | |
| "learning_rate": 0.00012135209154397962, | |
| "loss": 0.4954, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.48834139903211615, | |
| "eval_loss": 0.532034695148468, | |
| "eval_runtime": 28.652, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.49274087109546855, | |
| "grad_norm": 0.21518121659755707, | |
| "learning_rate": 0.00011984809112272495, | |
| "loss": 0.4999, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.49274087109546855, | |
| "eval_loss": 0.5313233733177185, | |
| "eval_runtime": 28.5662, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.49714034315882094, | |
| "grad_norm": 0.19571034610271454, | |
| "learning_rate": 0.00011833940204776209, | |
| "loss": 0.4931, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.49714034315882094, | |
| "eval_loss": 0.5311394333839417, | |
| "eval_runtime": 28.5352, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.5015398152221734, | |
| "grad_norm": 0.20554794371128082, | |
| "learning_rate": 0.00011682638071208533, | |
| "loss": 0.4833, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5015398152221734, | |
| "eval_loss": 0.5300410389900208, | |
| "eval_runtime": 28.5679, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5059392872855257, | |
| "grad_norm": 0.20373423397541046, | |
| "learning_rate": 0.00011530938453208559, | |
| "loss": 0.5057, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5059392872855257, | |
| "eval_loss": 0.5300309658050537, | |
| "eval_runtime": 28.5821, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5103387593488782, | |
| "grad_norm": 0.1982477903366089, | |
| "learning_rate": 0.00011378877186311912, | |
| "loss": 0.4754, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5103387593488782, | |
| "eval_loss": 0.5292160511016846, | |
| "eval_runtime": 28.5256, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5147382314122305, | |
| "grad_norm": 0.20576219260692596, | |
| "learning_rate": 0.00011226490191485421, | |
| "loss": 0.4991, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.5147382314122305, | |
| "eval_loss": 0.5280917882919312, | |
| "eval_runtime": 28.6835, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.519137703475583, | |
| "grad_norm": 0.2154638022184372, | |
| "learning_rate": 0.00011073813466641632, | |
| "loss": 0.4811, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.519137703475583, | |
| "eval_loss": 0.5274674296379089, | |
| "eval_runtime": 28.4766, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.5235371755389353, | |
| "grad_norm": 0.2037007063627243, | |
| "learning_rate": 0.00010920883078135117, | |
| "loss": 0.4717, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.5235371755389353, | |
| "eval_loss": 0.5270927548408508, | |
| "eval_runtime": 28.5377, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.5279366476022878, | |
| "grad_norm": 0.21386198699474335, | |
| "learning_rate": 0.00010767735152242649, | |
| "loss": 0.4776, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5279366476022878, | |
| "eval_loss": 0.526791512966156, | |
| "eval_runtime": 28.596, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5323361196656401, | |
| "grad_norm": 0.1984720528125763, | |
| "learning_rate": 0.0001061440586662917, | |
| "loss": 0.4708, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.5323361196656401, | |
| "eval_loss": 0.5266034007072449, | |
| "eval_runtime": 28.6491, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.5367355917289925, | |
| "grad_norm": 0.19453096389770508, | |
| "learning_rate": 0.000104609314418017, | |
| "loss": 0.4659, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5367355917289925, | |
| "eval_loss": 0.5267328023910522, | |
| "eval_runtime": 28.6358, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5411350637923449, | |
| "grad_norm": 0.2048104703426361, | |
| "learning_rate": 0.00010307348132553025, | |
| "loss": 0.5138, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.5411350637923449, | |
| "eval_loss": 0.5270944833755493, | |
| "eval_runtime": 28.5902, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.5455345358556973, | |
| "grad_norm": 0.1899915337562561, | |
| "learning_rate": 0.00010153692219397387, | |
| "loss": 0.4797, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5455345358556973, | |
| "eval_loss": 0.5260502099990845, | |
| "eval_runtime": 28.5533, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5499340079190497, | |
| "grad_norm": 0.18520919978618622, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5068, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.5499340079190497, | |
| "eval_loss": 0.5251287817955017, | |
| "eval_runtime": 28.4846, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.5543334799824021, | |
| "grad_norm": 0.21325986087322235, | |
| "learning_rate": 9.84630778060262e-05, | |
| "loss": 0.4799, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5543334799824021, | |
| "eval_loss": 0.524385929107666, | |
| "eval_runtime": 28.5917, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5587329520457545, | |
| "grad_norm": 0.20572926104068756, | |
| "learning_rate": 9.692651867446973e-05, | |
| "loss": 0.49, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.5587329520457545, | |
| "eval_loss": 0.523975133895874, | |
| "eval_runtime": 28.6052, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.5631324241091069, | |
| "grad_norm": 0.20347937941551208, | |
| "learning_rate": 9.539068558198304e-05, | |
| "loss": 0.4702, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5631324241091069, | |
| "eval_loss": 0.5229539275169373, | |
| "eval_runtime": 28.6223, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5675318961724594, | |
| "grad_norm": 0.21256154775619507, | |
| "learning_rate": 9.38559413337083e-05, | |
| "loss": 0.4736, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.5675318961724594, | |
| "eval_loss": 0.5221072435379028, | |
| "eval_runtime": 28.6189, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.5719313682358117, | |
| "grad_norm": 0.2260565459728241, | |
| "learning_rate": 9.232264847757357e-05, | |
| "loss": 0.5065, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5719313682358117, | |
| "eval_loss": 0.5213314890861511, | |
| "eval_runtime": 28.6771, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5763308402991641, | |
| "grad_norm": 0.21002529561519623, | |
| "learning_rate": 9.079116921864884e-05, | |
| "loss": 0.4796, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.5763308402991641, | |
| "eval_loss": 0.5214037299156189, | |
| "eval_runtime": 28.6202, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.5807303123625165, | |
| "grad_norm": 0.19340470433235168, | |
| "learning_rate": 8.92618653335837e-05, | |
| "loss": 0.4788, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5807303123625165, | |
| "eval_loss": 0.5211138725280762, | |
| "eval_runtime": 28.6313, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5851297844258689, | |
| "grad_norm": 0.19035720825195312, | |
| "learning_rate": 8.773509808514581e-05, | |
| "loss": 0.468, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.5851297844258689, | |
| "eval_loss": 0.5191999077796936, | |
| "eval_runtime": 28.0607, | |
| "eval_samples_per_second": 0.606, | |
| "eval_steps_per_second": 0.321, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.5895292564892213, | |
| "grad_norm": 0.19168096780776978, | |
| "learning_rate": 8.62112281368809e-05, | |
| "loss": 0.5066, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5895292564892213, | |
| "eval_loss": 0.5176913142204285, | |
| "eval_runtime": 28.5375, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5939287285525737, | |
| "grad_norm": 0.19758321344852448, | |
| "learning_rate": 8.469061546791442e-05, | |
| "loss": 0.51, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.5939287285525737, | |
| "eval_loss": 0.517296314239502, | |
| "eval_runtime": 28.5712, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.5983282006159261, | |
| "grad_norm": 0.19562241435050964, | |
| "learning_rate": 8.317361928791469e-05, | |
| "loss": 0.4932, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5983282006159261, | |
| "eval_loss": 0.5170657634735107, | |
| "eval_runtime": 28.4877, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6027276726792785, | |
| "grad_norm": 0.18590031564235687, | |
| "learning_rate": 8.166059795223794e-05, | |
| "loss": 0.5055, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.6027276726792785, | |
| "eval_loss": 0.5166193842887878, | |
| "eval_runtime": 28.625, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.6071271447426309, | |
| "grad_norm": 0.2049984484910965, | |
| "learning_rate": 8.015190887727509e-05, | |
| "loss": 0.4846, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.6071271447426309, | |
| "eval_loss": 0.5160765647888184, | |
| "eval_runtime": 28.5582, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.6115266168059833, | |
| "grad_norm": 0.19373777508735657, | |
| "learning_rate": 7.864790845602039e-05, | |
| "loss": 0.4862, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.6115266168059833, | |
| "eval_loss": 0.5157306790351868, | |
| "eval_runtime": 28.6078, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.6159260888693356, | |
| "grad_norm": 0.20326727628707886, | |
| "learning_rate": 7.714895197388189e-05, | |
| "loss": 0.5064, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6159260888693356, | |
| "eval_loss": 0.5153770446777344, | |
| "eval_runtime": 28.6597, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6203255609326881, | |
| "grad_norm": 0.19425565004348755, | |
| "learning_rate": 7.565539352475326e-05, | |
| "loss": 0.5018, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.6203255609326881, | |
| "eval_loss": 0.5147074460983276, | |
| "eval_runtime": 28.5261, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.6247250329960404, | |
| "grad_norm": 0.19491039216518402, | |
| "learning_rate": 7.416758592736744e-05, | |
| "loss": 0.482, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.6247250329960404, | |
| "eval_loss": 0.5144516229629517, | |
| "eval_runtime": 28.533, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.6291245050593929, | |
| "grad_norm": 0.1957363337278366, | |
| "learning_rate": 7.268588064195122e-05, | |
| "loss": 0.4883, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.6291245050593929, | |
| "eval_loss": 0.5139791965484619, | |
| "eval_runtime": 28.5313, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.6335239771227452, | |
| "grad_norm": 0.21253836154937744, | |
| "learning_rate": 7.12106276872011e-05, | |
| "loss": 0.4768, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.6335239771227452, | |
| "eval_loss": 0.5137556195259094, | |
| "eval_runtime": 28.6307, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.6379234491860977, | |
| "grad_norm": 0.1721029132604599, | |
| "learning_rate": 6.974217555759915e-05, | |
| "loss": 0.4816, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.6379234491860977, | |
| "eval_loss": 0.5133811831474304, | |
| "eval_runtime": 28.5925, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.6423229212494501, | |
| "grad_norm": 0.19211679697036743, | |
| "learning_rate": 6.82808711410894e-05, | |
| "loss": 0.5035, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.6423229212494501, | |
| "eval_loss": 0.5132091641426086, | |
| "eval_runtime": 28.5078, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.6467223933128025, | |
| "grad_norm": 0.19252945482730865, | |
| "learning_rate": 6.682705963713356e-05, | |
| "loss": 0.4822, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.6467223933128025, | |
| "eval_loss": 0.5131357908248901, | |
| "eval_runtime": 28.6326, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.6511218653761549, | |
| "grad_norm": 0.1986207813024521, | |
| "learning_rate": 6.538108447516558e-05, | |
| "loss": 0.4612, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.6511218653761549, | |
| "eval_loss": 0.5128303170204163, | |
| "eval_runtime": 28.6066, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.6555213374395072, | |
| "grad_norm": 0.19202682375907898, | |
| "learning_rate": 6.394328723346434e-05, | |
| "loss": 0.4578, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.6555213374395072, | |
| "eval_loss": 0.5124692916870117, | |
| "eval_runtime": 28.6064, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.6599208095028597, | |
| "grad_norm": 0.198526531457901, | |
| "learning_rate": 6.251400755846372e-05, | |
| "loss": 0.5176, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6599208095028597, | |
| "eval_loss": 0.5121349096298218, | |
| "eval_runtime": 28.5313, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.664320281566212, | |
| "grad_norm": 0.19058994948863983, | |
| "learning_rate": 6.109358308451885e-05, | |
| "loss": 0.4877, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.664320281566212, | |
| "eval_loss": 0.5118634700775146, | |
| "eval_runtime": 28.5287, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.6687197536295645, | |
| "grad_norm": 0.1798192411661148, | |
| "learning_rate": 5.968234935414807e-05, | |
| "loss": 0.4805, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6687197536295645, | |
| "eval_loss": 0.5116167664527893, | |
| "eval_runtime": 28.5918, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6731192256929168, | |
| "grad_norm": 0.18448549509048462, | |
| "learning_rate": 5.828063973876834e-05, | |
| "loss": 0.4993, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.6731192256929168, | |
| "eval_loss": 0.5111361742019653, | |
| "eval_runtime": 28.5586, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.6775186977562693, | |
| "grad_norm": 0.18624383211135864, | |
| "learning_rate": 5.688878535994421e-05, | |
| "loss": 0.4844, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.6775186977562693, | |
| "eval_loss": 0.5107051134109497, | |
| "eval_runtime": 28.5748, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.6819181698196216, | |
| "grad_norm": 0.18364666402339935, | |
| "learning_rate": 5.550711501116789e-05, | |
| "loss": 0.4674, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.6819181698196216, | |
| "eval_loss": 0.5101103186607361, | |
| "eval_runtime": 28.5159, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.6863176418829741, | |
| "grad_norm": 0.23952247202396393, | |
| "learning_rate": 5.413595508018952e-05, | |
| "loss": 0.4943, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6863176418829741, | |
| "eval_loss": 0.5096238255500793, | |
| "eval_runtime": 28.516, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6907171139463264, | |
| "grad_norm": 0.20105206966400146, | |
| "learning_rate": 5.27756294719153e-05, | |
| "loss": 0.4924, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.6907171139463264, | |
| "eval_loss": 0.5093135237693787, | |
| "eval_runtime": 28.5941, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.6951165860096788, | |
| "grad_norm": 0.19826586544513702, | |
| "learning_rate": 5.1426459531892714e-05, | |
| "loss": 0.4986, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6951165860096788, | |
| "eval_loss": 0.5086015462875366, | |
| "eval_runtime": 28.6207, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6995160580730312, | |
| "grad_norm": 0.17991924285888672, | |
| "learning_rate": 5.008876397039983e-05, | |
| "loss": 0.4698, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.6995160580730312, | |
| "eval_loss": 0.5082879662513733, | |
| "eval_runtime": 28.6587, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.7039155301363836, | |
| "grad_norm": 0.19232523441314697, | |
| "learning_rate": 4.876285878715764e-05, | |
| "loss": 0.4981, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7039155301363836, | |
| "eval_loss": 0.5078893899917603, | |
| "eval_runtime": 28.5038, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.708315002199736, | |
| "grad_norm": 0.19006720185279846, | |
| "learning_rate": 4.744905719668207e-05, | |
| "loss": 0.4758, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.708315002199736, | |
| "eval_loss": 0.5076141357421875, | |
| "eval_runtime": 28.6324, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.7127144742630884, | |
| "grad_norm": 0.19002890586853027, | |
| "learning_rate": 4.614766955429447e-05, | |
| "loss": 0.4642, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.7127144742630884, | |
| "eval_loss": 0.507789671421051, | |
| "eval_runtime": 28.6356, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.7171139463264409, | |
| "grad_norm": 0.2051495909690857, | |
| "learning_rate": 4.485900328280731e-05, | |
| "loss": 0.4669, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.7171139463264409, | |
| "eval_loss": 0.5073484182357788, | |
| "eval_runtime": 28.5748, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.7215134183897932, | |
| "grad_norm": 0.6378114223480225, | |
| "learning_rate": 4.358336279990268e-05, | |
| "loss": 0.4711, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.7215134183897932, | |
| "eval_loss": 0.5070581436157227, | |
| "eval_runtime": 28.6233, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.7259128904531457, | |
| "grad_norm": 0.181978240609169, | |
| "learning_rate": 4.2321049446220505e-05, | |
| "loss": 0.4704, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.7259128904531457, | |
| "eval_loss": 0.5068845748901367, | |
| "eval_runtime": 28.5225, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.730312362516498, | |
| "grad_norm": 0.1777966171503067, | |
| "learning_rate": 4.107236141417382e-05, | |
| "loss": 0.4752, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.730312362516498, | |
| "eval_loss": 0.5066249966621399, | |
| "eval_runtime": 28.5423, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.7347118345798505, | |
| "grad_norm": 0.18686190247535706, | |
| "learning_rate": 3.9837593677507726e-05, | |
| "loss": 0.4621, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.7347118345798505, | |
| "eval_loss": 0.5066962242126465, | |
| "eval_runtime": 28.428, | |
| "eval_samples_per_second": 0.598, | |
| "eval_steps_per_second": 0.317, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.7391113066432028, | |
| "grad_norm": 0.18854567408561707, | |
| "learning_rate": 3.8617037921618705e-05, | |
| "loss": 0.4748, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.7391113066432028, | |
| "eval_loss": 0.50632643699646, | |
| "eval_runtime": 28.5075, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.7435107787065552, | |
| "grad_norm": 0.19204109907150269, | |
| "learning_rate": 3.741098247465049e-05, | |
| "loss": 0.4948, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.7435107787065552, | |
| "eval_loss": 0.5060507655143738, | |
| "eval_runtime": 28.5753, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.7479102507699076, | |
| "grad_norm": 0.19182614982128143, | |
| "learning_rate": 3.621971223938334e-05, | |
| "loss": 0.4832, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.7479102507699076, | |
| "eval_loss": 0.5058286190032959, | |
| "eval_runtime": 28.5184, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.75230972283326, | |
| "grad_norm": 0.18205444514751434, | |
| "learning_rate": 3.504350862593231e-05, | |
| "loss": 0.4642, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.75230972283326, | |
| "eval_loss": 0.505698025226593, | |
| "eval_runtime": 28.6382, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.7567091948966124, | |
| "grad_norm": 0.20196740329265594, | |
| "learning_rate": 3.388264948527052e-05, | |
| "loss": 0.4877, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.7567091948966124, | |
| "eval_loss": 0.5052359700202942, | |
| "eval_runtime": 28.5347, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.7611086669599648, | |
| "grad_norm": 0.18125030398368835, | |
| "learning_rate": 3.2737409043593405e-05, | |
| "loss": 0.4727, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.7611086669599648, | |
| "eval_loss": 0.504954993724823, | |
| "eval_runtime": 28.5976, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.7655081390233172, | |
| "grad_norm": 0.18927669525146484, | |
| "learning_rate": 3.160805783753897e-05, | |
| "loss": 0.4691, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.7655081390233172, | |
| "eval_loss": 0.5047942399978638, | |
| "eval_runtime": 28.5051, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.7699076110866696, | |
| "grad_norm": 0.18508534133434296, | |
| "learning_rate": 3.0494862650279822e-05, | |
| "loss": 0.5292, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.7699076110866696, | |
| "eval_loss": 0.5046341419219971, | |
| "eval_runtime": 28.5445, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.774307083150022, | |
| "grad_norm": 0.18230414390563965, | |
| "learning_rate": 2.939808644850184e-05, | |
| "loss": 0.4708, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.774307083150022, | |
| "eval_loss": 0.5046290755271912, | |
| "eval_runtime": 28.6138, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7787065552133744, | |
| "grad_norm": 0.17352643609046936, | |
| "learning_rate": 2.8317988320284228e-05, | |
| "loss": 0.4863, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.7787065552133744, | |
| "eval_loss": 0.5044691562652588, | |
| "eval_runtime": 28.6321, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.7831060272767268, | |
| "grad_norm": 0.1845002919435501, | |
| "learning_rate": 2.7254823413896058e-05, | |
| "loss": 0.5006, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.7831060272767268, | |
| "eval_loss": 0.5042091012001038, | |
| "eval_runtime": 28.6132, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.7875054993400792, | |
| "grad_norm": 0.17883773148059845, | |
| "learning_rate": 2.6208842877523278e-05, | |
| "loss": 0.4887, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.7875054993400792, | |
| "eval_loss": 0.5039156675338745, | |
| "eval_runtime": 28.5693, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.7919049714034316, | |
| "grad_norm": 0.19202597439289093, | |
| "learning_rate": 2.518029379994089e-05, | |
| "loss": 0.4867, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7919049714034316, | |
| "eval_loss": 0.5037320852279663, | |
| "eval_runtime": 28.549, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.796304443466784, | |
| "grad_norm": 0.18246056139469147, | |
| "learning_rate": 2.4169419152143768e-05, | |
| "loss": 0.4662, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.796304443466784, | |
| "eval_loss": 0.5035374164581299, | |
| "eval_runtime": 28.6042, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.8007039155301364, | |
| "grad_norm": 0.18989378213882446, | |
| "learning_rate": 2.317645772995042e-05, | |
| "loss": 0.4744, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.8007039155301364, | |
| "eval_loss": 0.5033923387527466, | |
| "eval_runtime": 28.4795, | |
| "eval_samples_per_second": 0.597, | |
| "eval_steps_per_second": 0.316, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.8051033875934888, | |
| "grad_norm": 0.19525018334388733, | |
| "learning_rate": 2.220164409759299e-05, | |
| "loss": 0.5159, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.8051033875934888, | |
| "eval_loss": 0.503151535987854, | |
| "eval_runtime": 28.6198, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.8095028596568412, | |
| "grad_norm": 0.18840977549552917, | |
| "learning_rate": 2.124520853230697e-05, | |
| "loss": 0.4848, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.8095028596568412, | |
| "eval_loss": 0.5029481649398804, | |
| "eval_runtime": 28.614, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.8139023317201936, | |
| "grad_norm": 0.18055056035518646, | |
| "learning_rate": 2.03073769699333e-05, | |
| "loss": 0.4648, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.8139023317201936, | |
| "eval_loss": 0.5028063654899597, | |
| "eval_runtime": 28.5662, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.818301803783546, | |
| "grad_norm": 0.18352611362934113, | |
| "learning_rate": 1.9388370951546432e-05, | |
| "loss": 0.4733, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.818301803783546, | |
| "eval_loss": 0.5027296543121338, | |
| "eval_runtime": 28.5532, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.8227012758468983, | |
| "grad_norm": 0.18161964416503906, | |
| "learning_rate": 1.848840757112019e-05, | |
| "loss": 0.4556, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.8227012758468983, | |
| "eval_loss": 0.5025849342346191, | |
| "eval_runtime": 28.6672, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.8271007479102508, | |
| "grad_norm": 0.19485127925872803, | |
| "learning_rate": 1.7607699424244585e-05, | |
| "loss": 0.4973, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.8271007479102508, | |
| "eval_loss": 0.5023777484893799, | |
| "eval_runtime": 28.5856, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.8315002199736031, | |
| "grad_norm": 0.19218072295188904, | |
| "learning_rate": 1.674645455790468e-05, | |
| "loss": 0.4708, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.8315002199736031, | |
| "eval_loss": 0.5024308562278748, | |
| "eval_runtime": 28.6001, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.8358996920369556, | |
| "grad_norm": 0.18270643055438995, | |
| "learning_rate": 1.5904876421334536e-05, | |
| "loss": 0.4547, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8358996920369556, | |
| "eval_loss": 0.5024178624153137, | |
| "eval_runtime": 28.5464, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8402991641003079, | |
| "grad_norm": 0.18350371718406677, | |
| "learning_rate": 1.5083163817956914e-05, | |
| "loss": 0.4663, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.8402991641003079, | |
| "eval_loss": 0.5021481513977051, | |
| "eval_runtime": 28.5783, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.8446986361636604, | |
| "grad_norm": 0.18115630745887756, | |
| "learning_rate": 1.4281510858420632e-05, | |
| "loss": 0.4857, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.8446986361636604, | |
| "eval_loss": 0.5019457340240479, | |
| "eval_runtime": 28.5976, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.8490981082270127, | |
| "grad_norm": 0.1744571477174759, | |
| "learning_rate": 1.350010691474629e-05, | |
| "loss": 0.4633, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.8490981082270127, | |
| "eval_loss": 0.5019629597663879, | |
| "eval_runtime": 28.5207, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.8534975802903652, | |
| "grad_norm": 0.18827442824840546, | |
| "learning_rate": 1.2739136575591581e-05, | |
| "loss": 0.4723, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.8534975802903652, | |
| "eval_loss": 0.5018792748451233, | |
| "eval_runtime": 28.4515, | |
| "eval_samples_per_second": 0.598, | |
| "eval_steps_per_second": 0.316, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.8578970523537176, | |
| "grad_norm": 0.18166576325893402, | |
| "learning_rate": 1.1998779602646437e-05, | |
| "loss": 0.4691, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.8578970523537176, | |
| "eval_loss": 0.5017500519752502, | |
| "eval_runtime": 28.5978, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.8622965244170699, | |
| "grad_norm": 0.18091408908367157, | |
| "learning_rate": 1.1279210888168546e-05, | |
| "loss": 0.4874, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.8622965244170699, | |
| "eval_loss": 0.5017052888870239, | |
| "eval_runtime": 28.7541, | |
| "eval_samples_per_second": 0.591, | |
| "eval_steps_per_second": 0.313, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.8666959964804224, | |
| "grad_norm": 0.182442307472229, | |
| "learning_rate": 1.0580600413668984e-05, | |
| "loss": 0.4773, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.8666959964804224, | |
| "eval_loss": 0.5016083121299744, | |
| "eval_runtime": 28.5972, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.8710954685437747, | |
| "grad_norm": 0.18171900510787964, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 0.4806, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.8710954685437747, | |
| "eval_loss": 0.5015130043029785, | |
| "eval_runtime": 28.5707, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.8754949406071272, | |
| "grad_norm": 0.1896371841430664, | |
| "learning_rate": 9.246909317160746e-06, | |
| "loss": 0.4512, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.8754949406071272, | |
| "eval_loss": 0.5013110637664795, | |
| "eval_runtime": 28.6509, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.314, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.8798944126704795, | |
| "grad_norm": 0.1779976189136505, | |
| "learning_rate": 8.612143748910451e-06, | |
| "loss": 0.4561, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8798944126704795, | |
| "eval_loss": 0.5013135075569153, | |
| "eval_runtime": 28.8047, | |
| "eval_samples_per_second": 0.59, | |
| "eval_steps_per_second": 0.312, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.884293884733832, | |
| "grad_norm": 0.17416957020759583, | |
| "learning_rate": 7.998966453731094e-06, | |
| "loss": 0.4637, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.884293884733832, | |
| "eval_loss": 0.5013565421104431, | |
| "eval_runtime": 28.5911, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.8886933567971843, | |
| "grad_norm": 0.1769402176141739, | |
| "learning_rate": 7.40752228061502e-06, | |
| "loss": 0.4527, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.8886933567971843, | |
| "eval_loss": 0.5010828375816345, | |
| "eval_runtime": 28.5203, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.8930928288605368, | |
| "grad_norm": 0.17784808576107025, | |
| "learning_rate": 6.8379509446057644e-06, | |
| "loss": 0.4903, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.8930928288605368, | |
| "eval_loss": 0.5012202262878418, | |
| "eval_runtime": 27.8441, | |
| "eval_samples_per_second": 0.611, | |
| "eval_steps_per_second": 0.323, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.8974923009238891, | |
| "grad_norm": 0.18067394196987152, | |
| "learning_rate": 6.290386993793618e-06, | |
| "loss": 0.4689, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.8974923009238891, | |
| "eval_loss": 0.5012267231941223, | |
| "eval_runtime": 28.517, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.9018917729872415, | |
| "grad_norm": 0.17478391528129578, | |
| "learning_rate": 5.764959777531776e-06, | |
| "loss": 0.4589, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9018917729872415, | |
| "eval_loss": 0.5011836290359497, | |
| "eval_runtime": 28.6023, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9062912450505939, | |
| "grad_norm": 0.185857892036438, | |
| "learning_rate": 5.261793415880456e-06, | |
| "loss": 0.4528, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.9062912450505939, | |
| "eval_loss": 0.501183807849884, | |
| "eval_runtime": 28.5159, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.316, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.9106907171139463, | |
| "grad_norm": 0.17951223254203796, | |
| "learning_rate": 4.781006770286478e-06, | |
| "loss": 0.4845, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.9106907171139463, | |
| "eval_loss": 0.5011433959007263, | |
| "eval_runtime": 28.6072, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.9150901891772987, | |
| "grad_norm": 0.18096089363098145, | |
| "learning_rate": 4.322713415504975e-06, | |
| "loss": 0.4578, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.9150901891772987, | |
| "eval_loss": 0.5011703968048096, | |
| "eval_runtime": 28.6287, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.9194896612406511, | |
| "grad_norm": 0.2069099247455597, | |
| "learning_rate": 3.887021612769936e-06, | |
| "loss": 0.5027, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.9194896612406511, | |
| "eval_loss": 0.5011240839958191, | |
| "eval_runtime": 29.0514, | |
| "eval_samples_per_second": 0.585, | |
| "eval_steps_per_second": 0.31, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.9238891333040036, | |
| "grad_norm": 0.18762987852096558, | |
| "learning_rate": 3.4740342842199956e-06, | |
| "loss": 0.4695, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.9238891333040036, | |
| "eval_loss": 0.5010772347450256, | |
| "eval_runtime": 28.5655, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.9282886053673559, | |
| "grad_norm": 0.178373321890831, | |
| "learning_rate": 3.0838489885854805e-06, | |
| "loss": 0.484, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.9282886053673559, | |
| "eval_loss": 0.5010451674461365, | |
| "eval_runtime": 28.6083, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.9326880774307084, | |
| "grad_norm": 0.1794215440750122, | |
| "learning_rate": 2.7165578981424357e-06, | |
| "loss": 0.4784, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.9326880774307084, | |
| "eval_loss": 0.5010905265808105, | |
| "eval_runtime": 28.5675, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.9370875494940607, | |
| "grad_norm": 0.17699354887008667, | |
| "learning_rate": 2.3722477769389517e-06, | |
| "loss": 0.4698, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.9370875494940607, | |
| "eval_loss": 0.5010352730751038, | |
| "eval_runtime": 28.6041, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.9414870215574132, | |
| "grad_norm": 0.17208220064640045, | |
| "learning_rate": 2.0509999602992493e-06, | |
| "loss": 0.4517, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.9414870215574132, | |
| "eval_loss": 0.5010344982147217, | |
| "eval_runtime": 28.5865, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.9458864936207655, | |
| "grad_norm": 0.1774464249610901, | |
| "learning_rate": 1.7528903356100469e-06, | |
| "loss": 0.4846, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.9458864936207655, | |
| "eval_loss": 0.5010223388671875, | |
| "eval_runtime": 28.5634, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.9502859656841179, | |
| "grad_norm": 0.1773741990327835, | |
| "learning_rate": 1.4779893243939359e-06, | |
| "loss": 0.4402, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.9502859656841179, | |
| "eval_loss": 0.5009992718696594, | |
| "eval_runtime": 28.5952, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.9546854377474703, | |
| "grad_norm": 0.18979211151599884, | |
| "learning_rate": 1.2263618656739084e-06, | |
| "loss": 0.5013, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.9546854377474703, | |
| "eval_loss": 0.501004159450531, | |
| "eval_runtime": 28.614, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.9590849098108227, | |
| "grad_norm": 0.1895236372947693, | |
| "learning_rate": 9.98067400632985e-07, | |
| "loss": 0.4588, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.9590849098108227, | |
| "eval_loss": 0.5009981393814087, | |
| "eval_runtime": 28.5601, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.9634843818741751, | |
| "grad_norm": 0.17328618466854095, | |
| "learning_rate": 7.931598585726563e-07, | |
| "loss": 0.4712, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.9634843818741751, | |
| "eval_loss": 0.500961184501648, | |
| "eval_runtime": 28.574, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.9678838539375275, | |
| "grad_norm": 0.18122579157352448, | |
| "learning_rate": 6.116876441733088e-07, | |
| "loss": 0.4534, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.9678838539375275, | |
| "eval_loss": 0.5009814500808716, | |
| "eval_runtime": 28.5934, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.9722833260008799, | |
| "grad_norm": 0.18148748576641083, | |
| "learning_rate": 4.536936260597258e-07, | |
| "loss": 0.4587, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.9722833260008799, | |
| "eval_loss": 0.5009997487068176, | |
| "eval_runtime": 28.5275, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.9766827980642323, | |
| "grad_norm": 0.18024764955043793, | |
| "learning_rate": 3.192151266743548e-07, | |
| "loss": 0.4783, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.9766827980642323, | |
| "eval_loss": 0.5009670853614807, | |
| "eval_runtime": 28.5688, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.9810822701275846, | |
| "grad_norm": 0.18152055144309998, | |
| "learning_rate": 2.082839134607828e-07, | |
| "loss": 0.4623, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.9810822701275846, | |
| "eval_loss": 0.5009202361106873, | |
| "eval_runtime": 28.6066, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.9854817421909371, | |
| "grad_norm": 0.17324087023735046, | |
| "learning_rate": 1.2092619135937177e-07, | |
| "loss": 0.439, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.9854817421909371, | |
| "eval_loss": 0.5010377168655396, | |
| "eval_runtime": 28.5308, | |
| "eval_samples_per_second": 0.596, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.9898812142542894, | |
| "grad_norm": 0.17685554921627045, | |
| "learning_rate": 5.716259661695533e-08, | |
| "loss": 0.4629, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.9898812142542894, | |
| "eval_loss": 0.5009082555770874, | |
| "eval_runtime": 28.6259, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.9942806863176419, | |
| "grad_norm": 0.17675389349460602, | |
| "learning_rate": 1.7008191912004646e-08, | |
| "loss": 0.4716, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.9942806863176419, | |
| "eval_loss": 0.5009535551071167, | |
| "eval_runtime": 28.626, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.314, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.9986801583809943, | |
| "grad_norm": 0.18398317694664001, | |
| "learning_rate": 4.724627964303175e-10, | |
| "loss": 0.4832, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.9986801583809943, | |
| "eval_loss": 0.5010104179382324, | |
| "eval_runtime": 28.6106, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.315, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.9995600527936648, | |
| "step": 1136, | |
| "total_flos": 7.211600370336793e+18, | |
| "train_loss": 0.039691918463984004, | |
| "train_runtime": 9596.3839, | |
| "train_samples_per_second": 1.895, | |
| "train_steps_per_second": 0.118 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1136, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.211600370336793e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |