| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 2625, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.998095238095239e-05, | |
| "loss": 2.5699, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.900952380952381e-05, | |
| "loss": 3.6256, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.9404444444444444, | |
| "eval_f1": 0.9367327667610953, | |
| "eval_loss": 0.4405118525028229, | |
| "eval_precision": 0.998992950654582, | |
| "eval_recall": 0.8817777777777778, | |
| "eval_runtime": 119.9754, | |
| "eval_samples_per_second": 37.508, | |
| "eval_steps_per_second": 4.693, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8019047619047617e-05, | |
| "loss": 1.3465, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.9548888888888889, | |
| "eval_f1": 0.9544332210998877, | |
| "eval_loss": 0.4884180724620819, | |
| "eval_precision": 0.964172335600907, | |
| "eval_recall": 0.9448888888888889, | |
| "eval_runtime": 120.2589, | |
| "eval_samples_per_second": 37.419, | |
| "eval_steps_per_second": 4.682, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.702857142857143e-05, | |
| "loss": 1.3567, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.8906666666666667, | |
| "eval_f1": 0.8772455089820359, | |
| "eval_loss": 0.8629839420318604, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.7813333333333333, | |
| "eval_runtime": 120.0666, | |
| "eval_samples_per_second": 37.479, | |
| "eval_steps_per_second": 4.689, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6038095238095244e-05, | |
| "loss": 0.7091, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.9717777777777777, | |
| "eval_f1": 0.9710244125028521, | |
| "eval_loss": 0.32004401087760925, | |
| "eval_precision": 0.9976558837318331, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 120.0448, | |
| "eval_samples_per_second": 37.486, | |
| "eval_steps_per_second": 4.69, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.504761904761905e-05, | |
| "loss": 0.2289, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716636197440585, | |
| "eval_loss": 0.5497010350227356, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9448888888888889, | |
| "eval_runtime": 123.4715, | |
| "eval_samples_per_second": 36.446, | |
| "eval_steps_per_second": 4.56, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.405714285714286e-05, | |
| "loss": 0.594, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_f1": 0.971441626684944, | |
| "eval_loss": 0.23442013561725616, | |
| "eval_precision": 0.999529854254819, | |
| "eval_recall": 0.9448888888888889, | |
| "eval_runtime": 119.9304, | |
| "eval_samples_per_second": 37.522, | |
| "eval_steps_per_second": 4.694, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3066666666666665e-05, | |
| "loss": 0.2676, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.9706666666666667, | |
| "eval_f1": 0.9697940503432495, | |
| "eval_loss": 0.5204830169677734, | |
| "eval_precision": 0.9995283018867924, | |
| "eval_recall": 0.9417777777777778, | |
| "eval_runtime": 120.2235, | |
| "eval_samples_per_second": 37.43, | |
| "eval_steps_per_second": 4.683, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.207619047619048e-05, | |
| "loss": 0.3736, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.972, | |
| "eval_f1": 0.9712328767123288, | |
| "eval_loss": 0.44008418917655945, | |
| "eval_precision": 0.9985915492957746, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 120.1926, | |
| "eval_samples_per_second": 37.44, | |
| "eval_steps_per_second": 4.684, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.1085714285714286e-05, | |
| "loss": 0.2915, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.972, | |
| "eval_f1": 0.9712328767123288, | |
| "eval_loss": 0.3523007333278656, | |
| "eval_precision": 0.9985915492957746, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 119.9611, | |
| "eval_samples_per_second": 37.512, | |
| "eval_steps_per_second": 4.693, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.00952380952381e-05, | |
| "loss": 0.2387, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.972, | |
| "eval_f1": 0.9712328767123288, | |
| "eval_loss": 0.5473064184188843, | |
| "eval_precision": 0.9985915492957746, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 120.1415, | |
| "eval_samples_per_second": 37.456, | |
| "eval_steps_per_second": 4.686, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.910476190476191e-05, | |
| "loss": 0.3028, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.9691111111111111, | |
| "eval_f1": 0.9683875369570161, | |
| "eval_loss": 0.25819283723831177, | |
| "eval_precision": 0.9916162086632511, | |
| "eval_recall": 0.9462222222222222, | |
| "eval_runtime": 120.0033, | |
| "eval_samples_per_second": 37.499, | |
| "eval_steps_per_second": 4.692, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8114285714285714e-05, | |
| "loss": 0.5703, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.9691111111111111, | |
| "eval_f1": 0.968170368674147, | |
| "eval_loss": 0.19966714084148407, | |
| "eval_precision": 0.9985829003306566, | |
| "eval_recall": 0.9395555555555556, | |
| "eval_runtime": 119.8696, | |
| "eval_samples_per_second": 37.541, | |
| "eval_steps_per_second": 4.697, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.712380952380953e-05, | |
| "loss": 0.5, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.37493452429771423, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.9194, | |
| "eval_samples_per_second": 37.525, | |
| "eval_steps_per_second": 4.695, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.6133333333333335e-05, | |
| "loss": 0.3681, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.972, | |
| "eval_f1": 0.9712197350388305, | |
| "eval_loss": 0.14736813306808472, | |
| "eval_precision": 0.9990601503759399, | |
| "eval_recall": 0.9448888888888889, | |
| "eval_runtime": 119.8944, | |
| "eval_samples_per_second": 37.533, | |
| "eval_steps_per_second": 4.696, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.514285714285714e-05, | |
| "loss": 0.3687, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_f1": 0.9714546700159854, | |
| "eval_loss": 0.2616070508956909, | |
| "eval_precision": 0.9990605918271489, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 120.1748, | |
| "eval_samples_per_second": 37.445, | |
| "eval_steps_per_second": 4.685, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.415238095238095e-05, | |
| "loss": 0.5027, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.9693333333333334, | |
| "eval_f1": 0.968377635197067, | |
| "eval_loss": 0.5182681083679199, | |
| "eval_precision": 0.9995269631031221, | |
| "eval_recall": 0.9391111111111111, | |
| "eval_runtime": 120.1313, | |
| "eval_samples_per_second": 37.459, | |
| "eval_steps_per_second": 4.687, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.316190476190476e-05, | |
| "loss": 0.3527, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.9717777777777777, | |
| "eval_f1": 0.9709846927119031, | |
| "eval_loss": 0.3203032314777374, | |
| "eval_precision": 0.999059708509638, | |
| "eval_recall": 0.9444444444444444, | |
| "eval_runtime": 120.2845, | |
| "eval_samples_per_second": 37.411, | |
| "eval_steps_per_second": 4.681, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.217142857142858e-05, | |
| "loss": 0.2254, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.9706666666666667, | |
| "eval_f1": 0.969807868252516, | |
| "eval_loss": 0.3301153779029846, | |
| "eval_precision": 0.9990574929311969, | |
| "eval_recall": 0.9422222222222222, | |
| "eval_runtime": 120.409, | |
| "eval_samples_per_second": 37.373, | |
| "eval_steps_per_second": 4.676, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.1180952380952384e-05, | |
| "loss": 0.2214, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.9713333333333334, | |
| "eval_f1": 0.9705142857142858, | |
| "eval_loss": 0.2255212664604187, | |
| "eval_precision": 0.9990588235294118, | |
| "eval_recall": 0.9435555555555556, | |
| "eval_runtime": 120.0554, | |
| "eval_samples_per_second": 37.483, | |
| "eval_steps_per_second": 4.69, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.019047619047619e-05, | |
| "loss": 0.2486, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.22060254216194153, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 120.1829, | |
| "eval_samples_per_second": 37.443, | |
| "eval_steps_per_second": 4.685, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9199999999999998e-05, | |
| "loss": 0.2049, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.35958772897720337, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 120.0615, | |
| "eval_samples_per_second": 37.481, | |
| "eval_steps_per_second": 4.689, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8209523809523812e-05, | |
| "loss": 0.4056, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.9715555555555555, | |
| "eval_f1": 0.9707495429616089, | |
| "eval_loss": 0.30065128207206726, | |
| "eval_precision": 0.9990592662276576, | |
| "eval_recall": 0.944, | |
| "eval_runtime": 120.3856, | |
| "eval_samples_per_second": 37.38, | |
| "eval_steps_per_second": 4.677, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7219047619047623e-05, | |
| "loss": 0.2204, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.9702222222222222, | |
| "eval_f1": 0.9693223443223443, | |
| "eval_loss": 0.22362905740737915, | |
| "eval_precision": 0.9995278564683664, | |
| "eval_recall": 0.9408888888888889, | |
| "eval_runtime": 120.2284, | |
| "eval_samples_per_second": 37.429, | |
| "eval_steps_per_second": 4.683, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.622857142857143e-05, | |
| "loss": 0.4425, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.9713333333333334, | |
| "eval_f1": 0.9705008003658816, | |
| "eval_loss": 0.561194121837616, | |
| "eval_precision": 0.9995289684408856, | |
| "eval_recall": 0.9431111111111111, | |
| "eval_runtime": 120.3958, | |
| "eval_samples_per_second": 37.377, | |
| "eval_steps_per_second": 4.676, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.523809523809524e-05, | |
| "loss": 0.2287, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.2646217942237854, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 120.7965, | |
| "eval_samples_per_second": 37.253, | |
| "eval_steps_per_second": 4.661, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.424761904761905e-05, | |
| "loss": 0.248, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.3093545734882355, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 125.2609, | |
| "eval_samples_per_second": 35.925, | |
| "eval_steps_per_second": 4.495, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3257142857142858e-05, | |
| "loss": 0.3587, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.2874605655670166, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 125.5022, | |
| "eval_samples_per_second": 35.856, | |
| "eval_steps_per_second": 4.486, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.2266666666666668e-05, | |
| "loss": 0.2032, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.2600957155227661, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.7973, | |
| "eval_samples_per_second": 37.563, | |
| "eval_steps_per_second": 4.7, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.127619047619048e-05, | |
| "loss": 0.1874, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_f1": 0.9714546700159854, | |
| "eval_loss": 0.34168195724487305, | |
| "eval_precision": 0.9990605918271489, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 120.1128, | |
| "eval_samples_per_second": 37.465, | |
| "eval_steps_per_second": 4.687, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0285714285714286e-05, | |
| "loss": 0.1527, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.9611111111111111, | |
| "eval_f1": 0.9605233476201219, | |
| "eval_loss": 0.2756815552711487, | |
| "eval_precision": 0.9752633989922126, | |
| "eval_recall": 0.9462222222222222, | |
| "eval_runtime": 120.3166, | |
| "eval_samples_per_second": 37.401, | |
| "eval_steps_per_second": 4.679, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9295238095238096e-05, | |
| "loss": 0.1734, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.3820748031139374, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.8424, | |
| "eval_samples_per_second": 37.549, | |
| "eval_steps_per_second": 4.698, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8304761904761906e-05, | |
| "loss": 0.4296, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.28360387682914734, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.6839, | |
| "eval_samples_per_second": 37.599, | |
| "eval_steps_per_second": 4.704, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7314285714285717e-05, | |
| "loss": 0.2293, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.1679239422082901, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.9354, | |
| "eval_samples_per_second": 37.52, | |
| "eval_steps_per_second": 4.694, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6323809523809524e-05, | |
| "loss": 0.1589, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.23643441498279572, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 120.016, | |
| "eval_samples_per_second": 37.495, | |
| "eval_steps_per_second": 4.691, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5333333333333334e-05, | |
| "loss": 0.2459, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.34067416191101074, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.7271, | |
| "eval_samples_per_second": 37.585, | |
| "eval_steps_per_second": 4.702, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4342857142857143e-05, | |
| "loss": 0.2254, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.261232852935791, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.8503, | |
| "eval_samples_per_second": 37.547, | |
| "eval_steps_per_second": 4.698, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3352380952380952e-05, | |
| "loss": 0.1613, | |
| "step": 1924 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.2873767912387848, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.8281, | |
| "eval_samples_per_second": 37.554, | |
| "eval_steps_per_second": 4.698, | |
| "step": 1924 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2361904761904762e-05, | |
| "loss": 0.1651, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.9713333333333334, | |
| "eval_f1": 0.9705008003658816, | |
| "eval_loss": 0.2269158959388733, | |
| "eval_precision": 0.9995289684408856, | |
| "eval_recall": 0.9431111111111111, | |
| "eval_runtime": 119.7297, | |
| "eval_samples_per_second": 37.585, | |
| "eval_steps_per_second": 4.702, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1371428571428571e-05, | |
| "loss": 0.2584, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.9713333333333334, | |
| "eval_f1": 0.9705008003658816, | |
| "eval_loss": 0.27417832612991333, | |
| "eval_precision": 0.9995289684408856, | |
| "eval_recall": 0.9431111111111111, | |
| "eval_runtime": 119.7799, | |
| "eval_samples_per_second": 37.569, | |
| "eval_steps_per_second": 4.7, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0380952380952382e-05, | |
| "loss": 0.1901, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.9713333333333334, | |
| "eval_f1": 0.9705008003658816, | |
| "eval_loss": 0.19001567363739014, | |
| "eval_precision": 0.9995289684408856, | |
| "eval_recall": 0.9431111111111111, | |
| "eval_runtime": 119.8785, | |
| "eval_samples_per_second": 37.538, | |
| "eval_steps_per_second": 4.696, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.39047619047619e-06, | |
| "loss": 0.2527, | |
| "step": 2132 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.972, | |
| "eval_f1": 0.9712197350388305, | |
| "eval_loss": 0.16979800164699554, | |
| "eval_precision": 0.9990601503759399, | |
| "eval_recall": 0.9448888888888889, | |
| "eval_runtime": 119.8785, | |
| "eval_samples_per_second": 37.538, | |
| "eval_steps_per_second": 4.696, | |
| "step": 2132 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.1432, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.1947138011455536, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.9797, | |
| "eval_samples_per_second": 37.506, | |
| "eval_steps_per_second": 4.692, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.40952380952381e-06, | |
| "loss": 0.2133, | |
| "step": 2236 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.2675629258155823, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 120.0094, | |
| "eval_samples_per_second": 37.497, | |
| "eval_steps_per_second": 4.691, | |
| "step": 2236 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.419047619047619e-06, | |
| "loss": 0.2746, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.18613262474536896, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.9576, | |
| "eval_samples_per_second": 37.513, | |
| "eval_steps_per_second": 4.693, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.428571428571429e-06, | |
| "loss": 0.1116, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.28170281648635864, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 120.1643, | |
| "eval_samples_per_second": 37.449, | |
| "eval_steps_per_second": 4.685, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.4380952380952385e-06, | |
| "loss": 0.2212, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.2225799709558487, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 120.0901, | |
| "eval_samples_per_second": 37.472, | |
| "eval_steps_per_second": 4.688, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4476190476190472e-06, | |
| "loss": 0.3059, | |
| "step": 2444 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.21728740632534027, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.9486, | |
| "eval_samples_per_second": 37.516, | |
| "eval_steps_per_second": 4.694, | |
| "step": 2444 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.4571428571428573e-06, | |
| "loss": 0.12, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.23962543904781342, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 122.131, | |
| "eval_samples_per_second": 36.846, | |
| "eval_steps_per_second": 4.61, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.4666666666666667e-06, | |
| "loss": 0.264, | |
| "step": 2548 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.23284508287906647, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 121.4423, | |
| "eval_samples_per_second": 37.055, | |
| "eval_steps_per_second": 4.636, | |
| "step": 2548 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.761904761904763e-07, | |
| "loss": 0.0859, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.9724444444444444, | |
| "eval_f1": 0.9716894977168951, | |
| "eval_loss": 0.2551863491535187, | |
| "eval_precision": 0.9990610328638497, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 119.8763, | |
| "eval_samples_per_second": 37.539, | |
| "eval_steps_per_second": 4.697, | |
| "step": 2600 | |
| } | |
| ], | |
| "max_steps": 2625, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.950297882624e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |