| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20156555772994128, | |
| "eval_steps": 5, | |
| "global_step": 103, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0019569471624266144, | |
| "grad_norm": 3.932948112487793, | |
| "learning_rate": 7.8125e-08, | |
| "loss": 0.107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003913894324853229, | |
| "grad_norm": 4.482716083526611, | |
| "learning_rate": 1.5625e-07, | |
| "loss": 0.1529, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005870841487279843, | |
| "grad_norm": 4.672689437866211, | |
| "learning_rate": 2.3437500000000003e-07, | |
| "loss": 0.1874, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007827788649706457, | |
| "grad_norm": 4.226949214935303, | |
| "learning_rate": 3.125e-07, | |
| "loss": 0.1682, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009784735812133072, | |
| "grad_norm": 4.327479362487793, | |
| "learning_rate": 3.90625e-07, | |
| "loss": 0.1438, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009784735812133072, | |
| "eval_loss": 0.1470455378293991, | |
| "eval_runtime": 107.3614, | |
| "eval_samples_per_second": 28.427, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8861388036460539, | |
| "eval_sts-test_pearson_dot": 0.8769528313548112, | |
| "eval_sts-test_pearson_euclidean": 0.9079831987750276, | |
| "eval_sts-test_pearson_manhattan": 0.9086786527495163, | |
| "eval_sts-test_pearson_max": 0.9086786527495163, | |
| "eval_sts-test_spearman_cosine": 0.9077902566323186, | |
| "eval_sts-test_spearman_dot": 0.8794770733264693, | |
| "eval_sts-test_spearman_euclidean": 0.903967335376697, | |
| "eval_sts-test_spearman_manhattan": 0.9043498244078092, | |
| "eval_sts-test_spearman_max": 0.9077902566323186, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011741682974559686, | |
| "grad_norm": 5.27250337600708, | |
| "learning_rate": 4.6875000000000006e-07, | |
| "loss": 0.2961, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0136986301369863, | |
| "grad_norm": 5.903276443481445, | |
| "learning_rate": 5.468750000000001e-07, | |
| "loss": 0.3019, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015655577299412915, | |
| "grad_norm": 4.000335693359375, | |
| "learning_rate": 6.25e-07, | |
| "loss": 0.1184, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01761252446183953, | |
| "grad_norm": 5.876769065856934, | |
| "learning_rate": 7.03125e-07, | |
| "loss": 0.3176, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019569471624266144, | |
| "grad_norm": 4.8437933921813965, | |
| "learning_rate": 7.8125e-07, | |
| "loss": 0.2234, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019569471624266144, | |
| "eval_loss": 0.1467687040567398, | |
| "eval_runtime": 107.2549, | |
| "eval_samples_per_second": 28.456, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8861409457129842, | |
| "eval_sts-test_pearson_dot": 0.876972814890145, | |
| "eval_sts-test_pearson_euclidean": 0.9080268416052204, | |
| "eval_sts-test_pearson_manhattan": 0.9087444298597203, | |
| "eval_sts-test_pearson_max": 0.9087444298597203, | |
| "eval_sts-test_spearman_cosine": 0.9078342918735278, | |
| "eval_sts-test_spearman_dot": 0.8794190309404447, | |
| "eval_sts-test_spearman_euclidean": 0.9039501508923226, | |
| "eval_sts-test_spearman_manhattan": 0.9044244247605487, | |
| "eval_sts-test_spearman_max": 0.9078342918735278, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021526418786692758, | |
| "grad_norm": 4.726498603820801, | |
| "learning_rate": 8.59375e-07, | |
| "loss": 0.1881, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.023483365949119372, | |
| "grad_norm": 4.818070411682129, | |
| "learning_rate": 9.375000000000001e-07, | |
| "loss": 0.1593, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025440313111545987, | |
| "grad_norm": 4.98201322555542, | |
| "learning_rate": 1.0156250000000001e-06, | |
| "loss": 0.1833, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0273972602739726, | |
| "grad_norm": 4.269514560699463, | |
| "learning_rate": 1.0937500000000001e-06, | |
| "loss": 0.1352, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.029354207436399216, | |
| "grad_norm": 6.1525492668151855, | |
| "learning_rate": 1.1718750000000001e-06, | |
| "loss": 0.3143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029354207436399216, | |
| "eval_loss": 0.1462097316980362, | |
| "eval_runtime": 107.0721, | |
| "eval_samples_per_second": 28.504, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8860829119688085, | |
| "eval_sts-test_pearson_dot": 0.8768990080043222, | |
| "eval_sts-test_pearson_euclidean": 0.9080646402781543, | |
| "eval_sts-test_pearson_manhattan": 0.9088063929836994, | |
| "eval_sts-test_pearson_max": 0.9088063929836994, | |
| "eval_sts-test_spearman_cosine": 0.907713597721555, | |
| "eval_sts-test_spearman_dot": 0.8795110842851269, | |
| "eval_sts-test_spearman_euclidean": 0.9040110126078148, | |
| "eval_sts-test_spearman_manhattan": 0.9045081991218733, | |
| "eval_sts-test_spearman_max": 0.907713597721555, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03131115459882583, | |
| "grad_norm": 4.751354694366455, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.1583, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.033268101761252444, | |
| "grad_norm": 5.435980319976807, | |
| "learning_rate": 1.328125e-06, | |
| "loss": 0.2015, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03522504892367906, | |
| "grad_norm": 4.1765851974487305, | |
| "learning_rate": 1.40625e-06, | |
| "loss": 0.1476, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03718199608610567, | |
| "grad_norm": 4.689794540405273, | |
| "learning_rate": 1.484375e-06, | |
| "loss": 0.1676, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03913894324853229, | |
| "grad_norm": 4.203744888305664, | |
| "learning_rate": 1.5625e-06, | |
| "loss": 0.1525, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03913894324853229, | |
| "eval_loss": 0.14544810354709625, | |
| "eval_runtime": 107.1845, | |
| "eval_samples_per_second": 28.474, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8861436293943533, | |
| "eval_sts-test_pearson_dot": 0.8769239163708102, | |
| "eval_sts-test_pearson_euclidean": 0.9082269545633608, | |
| "eval_sts-test_pearson_manhattan": 0.9089828403051001, | |
| "eval_sts-test_pearson_max": 0.9089828403051001, | |
| "eval_sts-test_spearman_cosine": 0.907929343552723, | |
| "eval_sts-test_spearman_dot": 0.8796122221358714, | |
| "eval_sts-test_spearman_euclidean": 0.9043074002120102, | |
| "eval_sts-test_spearman_manhattan": 0.9047217521412333, | |
| "eval_sts-test_spearman_max": 0.907929343552723, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0410958904109589, | |
| "grad_norm": 5.152130603790283, | |
| "learning_rate": 1.640625e-06, | |
| "loss": 0.1717, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.043052837573385516, | |
| "grad_norm": 5.343059062957764, | |
| "learning_rate": 1.71875e-06, | |
| "loss": 0.198, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04500978473581213, | |
| "grad_norm": 5.224748134613037, | |
| "learning_rate": 1.796875e-06, | |
| "loss": 0.3062, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.046966731898238745, | |
| "grad_norm": 4.6179423332214355, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 0.1241, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04892367906066536, | |
| "grad_norm": 4.200148105621338, | |
| "learning_rate": 1.953125e-06, | |
| "loss": 0.1087, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04892367906066536, | |
| "eval_loss": 0.14457188546657562, | |
| "eval_runtime": 107.3809, | |
| "eval_samples_per_second": 28.422, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8862905994058754, | |
| "eval_sts-test_pearson_dot": 0.877015249192232, | |
| "eval_sts-test_pearson_euclidean": 0.9085054742522269, | |
| "eval_sts-test_pearson_manhattan": 0.9092575877809899, | |
| "eval_sts-test_pearson_max": 0.9092575877809899, | |
| "eval_sts-test_spearman_cosine": 0.9082294902628751, | |
| "eval_sts-test_spearman_dot": 0.8798810429630494, | |
| "eval_sts-test_spearman_euclidean": 0.9047149499495015, | |
| "eval_sts-test_spearman_manhattan": 0.9051023616193669, | |
| "eval_sts-test_spearman_max": 0.9082294902628751, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.050880626223091974, | |
| "grad_norm": 4.890737533569336, | |
| "learning_rate": 2.0312500000000002e-06, | |
| "loss": 0.1767, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05283757338551859, | |
| "grad_norm": 4.683767795562744, | |
| "learning_rate": 2.109375e-06, | |
| "loss": 0.1951, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 4.656280040740967, | |
| "learning_rate": 2.1875000000000002e-06, | |
| "loss": 0.1621, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05675146771037182, | |
| "grad_norm": 4.446409702301025, | |
| "learning_rate": 2.265625e-06, | |
| "loss": 0.221, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05870841487279843, | |
| "grad_norm": 5.765133857727051, | |
| "learning_rate": 2.3437500000000002e-06, | |
| "loss": 0.2241, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05870841487279843, | |
| "eval_loss": 0.14350731670856476, | |
| "eval_runtime": 107.3747, | |
| "eval_samples_per_second": 28.424, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8863784941826807, | |
| "eval_sts-test_pearson_dot": 0.8768948467465629, | |
| "eval_sts-test_pearson_euclidean": 0.9088066170487232, | |
| "eval_sts-test_pearson_manhattan": 0.9095658568102677, | |
| "eval_sts-test_pearson_max": 0.9095658568102677, | |
| "eval_sts-test_spearman_cosine": 0.9082580415676429, | |
| "eval_sts-test_spearman_dot": 0.8801849487791585, | |
| "eval_sts-test_spearman_euclidean": 0.9051721735871375, | |
| "eval_sts-test_spearman_manhattan": 0.9054862826908437, | |
| "eval_sts-test_spearman_max": 0.9082580415676429, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.060665362035225046, | |
| "grad_norm": 5.359245777130127, | |
| "learning_rate": 2.421875e-06, | |
| "loss": 0.2093, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06262230919765166, | |
| "grad_norm": 4.439486503601074, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.1615, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06457925636007827, | |
| "grad_norm": 3.689824342727661, | |
| "learning_rate": 2.5781250000000004e-06, | |
| "loss": 0.1615, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06653620352250489, | |
| "grad_norm": 4.842885494232178, | |
| "learning_rate": 2.65625e-06, | |
| "loss": 0.1772, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 5.209301948547363, | |
| "learning_rate": 2.7343750000000004e-06, | |
| "loss": 0.2324, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "eval_loss": 0.14226235449314117, | |
| "eval_runtime": 107.3108, | |
| "eval_samples_per_second": 28.441, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8863574366132135, | |
| "eval_sts-test_pearson_dot": 0.8765683077424664, | |
| "eval_sts-test_pearson_euclidean": 0.9091012263251723, | |
| "eval_sts-test_pearson_manhattan": 0.9098631032540263, | |
| "eval_sts-test_pearson_max": 0.9098631032540263, | |
| "eval_sts-test_spearman_cosine": 0.9083728733043733, | |
| "eval_sts-test_spearman_dot": 0.8800282746130272, | |
| "eval_sts-test_spearman_euclidean": 0.9052579170039636, | |
| "eval_sts-test_spearman_manhattan": 0.9059997586640487, | |
| "eval_sts-test_spearman_max": 0.9083728733043733, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07045009784735812, | |
| "grad_norm": 4.740983009338379, | |
| "learning_rate": 2.8125e-06, | |
| "loss": 0.2611, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07240704500978473, | |
| "grad_norm": 5.090059757232666, | |
| "learning_rate": 2.8906250000000004e-06, | |
| "loss": 0.214, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07436399217221135, | |
| "grad_norm": 5.123153209686279, | |
| "learning_rate": 2.96875e-06, | |
| "loss": 0.1985, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07632093933463796, | |
| "grad_norm": 5.401946067810059, | |
| "learning_rate": 3.0468750000000004e-06, | |
| "loss": 0.1855, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07827788649706457, | |
| "grad_norm": 4.838700294494629, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.1234, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07827788649706457, | |
| "eval_loss": 0.14100149273872375, | |
| "eval_runtime": 107.3059, | |
| "eval_samples_per_second": 28.442, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8864265749012155, | |
| "eval_sts-test_pearson_dot": 0.8764612424174422, | |
| "eval_sts-test_pearson_euclidean": 0.9094092487009695, | |
| "eval_sts-test_pearson_manhattan": 0.9101707626021143, | |
| "eval_sts-test_pearson_max": 0.9101707626021143, | |
| "eval_sts-test_spearman_cosine": 0.908505695048183, | |
| "eval_sts-test_spearman_dot": 0.8802103674956289, | |
| "eval_sts-test_spearman_euclidean": 0.9054564783507572, | |
| "eval_sts-test_spearman_manhattan": 0.9063046490079084, | |
| "eval_sts-test_spearman_max": 0.908505695048183, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08023483365949119, | |
| "grad_norm": 3.8856801986694336, | |
| "learning_rate": 3.2031250000000004e-06, | |
| "loss": 0.1492, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0821917808219178, | |
| "grad_norm": 5.678151607513428, | |
| "learning_rate": 3.28125e-06, | |
| "loss": 0.2022, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08414872798434442, | |
| "grad_norm": 5.104148864746094, | |
| "learning_rate": 3.3593750000000003e-06, | |
| "loss": 0.2146, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08610567514677103, | |
| "grad_norm": 4.76043701171875, | |
| "learning_rate": 3.4375e-06, | |
| "loss": 0.1688, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08806262230919765, | |
| "grad_norm": 5.128803730010986, | |
| "learning_rate": 3.5156250000000003e-06, | |
| "loss": 0.175, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08806262230919765, | |
| "eval_loss": 0.13962982594966888, | |
| "eval_runtime": 107.4144, | |
| "eval_samples_per_second": 28.413, | |
| "eval_steps_per_second": 0.223, | |
| "eval_sts-test_pearson_cosine": 0.886410908658177, | |
| "eval_sts-test_pearson_dot": 0.8762836795862763, | |
| "eval_sts-test_pearson_euclidean": 0.9096890242379734, | |
| "eval_sts-test_pearson_manhattan": 0.9104590803642174, | |
| "eval_sts-test_pearson_max": 0.9104590803642174, | |
| "eval_sts-test_spearman_cosine": 0.9086694846648755, | |
| "eval_sts-test_spearman_dot": 0.8801346931126159, | |
| "eval_sts-test_spearman_euclidean": 0.9057376952773407, | |
| "eval_sts-test_spearman_manhattan": 0.9064708999439774, | |
| "eval_sts-test_spearman_max": 0.9086694846648755, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09001956947162426, | |
| "grad_norm": 4.968522548675537, | |
| "learning_rate": 3.59375e-06, | |
| "loss": 0.2123, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09197651663405088, | |
| "grad_norm": 4.343472957611084, | |
| "learning_rate": 3.6718750000000003e-06, | |
| "loss": 0.1118, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09393346379647749, | |
| "grad_norm": 6.252938270568848, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.3009, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0958904109589041, | |
| "grad_norm": 3.411029815673828, | |
| "learning_rate": 3.828125000000001e-06, | |
| "loss": 0.1071, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09784735812133072, | |
| "grad_norm": 5.379226207733154, | |
| "learning_rate": 3.90625e-06, | |
| "loss": 0.2608, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09784735812133072, | |
| "eval_loss": 0.13823722302913666, | |
| "eval_runtime": 107.3656, | |
| "eval_samples_per_second": 28.426, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8863074884351817, | |
| "eval_sts-test_pearson_dot": 0.8763122134205692, | |
| "eval_sts-test_pearson_euclidean": 0.9097700018848961, | |
| "eval_sts-test_pearson_manhattan": 0.9105724410858811, | |
| "eval_sts-test_pearson_max": 0.9105724410858811, | |
| "eval_sts-test_spearman_cosine": 0.9085105281844131, | |
| "eval_sts-test_spearman_dot": 0.8801239975611433, | |
| "eval_sts-test_spearman_euclidean": 0.9059798443527296, | |
| "eval_sts-test_spearman_manhattan": 0.9065691737139927, | |
| "eval_sts-test_spearman_max": 0.9085105281844131, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09980430528375733, | |
| "grad_norm": 4.599095821380615, | |
| "learning_rate": 3.984375e-06, | |
| "loss": 0.1368, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.10176125244618395, | |
| "grad_norm": 5.634761333465576, | |
| "learning_rate": 4.0625000000000005e-06, | |
| "loss": 0.2307, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.10371819960861056, | |
| "grad_norm": 4.678525924682617, | |
| "learning_rate": 4.140625000000001e-06, | |
| "loss": 0.1366, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.10567514677103718, | |
| "grad_norm": 4.931070327758789, | |
| "learning_rate": 4.21875e-06, | |
| "loss": 0.1857, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.10763209393346379, | |
| "grad_norm": 4.903087139129639, | |
| "learning_rate": 4.296875e-06, | |
| "loss": 0.2155, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.10763209393346379, | |
| "eval_loss": 0.1367325782775879, | |
| "eval_runtime": 107.3012, | |
| "eval_samples_per_second": 28.443, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.88603017002284, | |
| "eval_sts-test_pearson_dot": 0.8761626193697236, | |
| "eval_sts-test_pearson_euclidean": 0.9096799681812165, | |
| "eval_sts-test_pearson_manhattan": 0.9104977957475867, | |
| "eval_sts-test_pearson_max": 0.9104977957475867, | |
| "eval_sts-test_spearman_cosine": 0.9084685067499666, | |
| "eval_sts-test_spearman_dot": 0.8802836700617878, | |
| "eval_sts-test_spearman_euclidean": 0.9058409364373706, | |
| "eval_sts-test_spearman_manhattan": 0.9064240006220393, | |
| "eval_sts-test_spearman_max": 0.9084685067499666, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 5.408311367034912, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 0.2022, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.11154598825831702, | |
| "grad_norm": 4.5926713943481445, | |
| "learning_rate": 4.453125000000001e-06, | |
| "loss": 0.2076, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.11350293542074363, | |
| "grad_norm": 6.475535869598389, | |
| "learning_rate": 4.53125e-06, | |
| "loss": 0.4133, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.11545988258317025, | |
| "grad_norm": 4.997581481933594, | |
| "learning_rate": 4.609375e-06, | |
| "loss": 0.1823, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.11741682974559686, | |
| "grad_norm": 3.899284601211548, | |
| "learning_rate": 4.6875000000000004e-06, | |
| "loss": 0.1136, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11741682974559686, | |
| "eval_loss": 0.13528631627559662, | |
| "eval_runtime": 107.3435, | |
| "eval_samples_per_second": 28.432, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8860224650016398, | |
| "eval_sts-test_pearson_dot": 0.8762739756970772, | |
| "eval_sts-test_pearson_euclidean": 0.9099016820022997, | |
| "eval_sts-test_pearson_manhattan": 0.9107281338135995, | |
| "eval_sts-test_pearson_max": 0.9107281338135995, | |
| "eval_sts-test_spearman_cosine": 0.9087510214631306, | |
| "eval_sts-test_spearman_dot": 0.8808623486228402, | |
| "eval_sts-test_spearman_euclidean": 0.9060555634870038, | |
| "eval_sts-test_spearman_manhattan": 0.9067256241238172, | |
| "eval_sts-test_spearman_max": 0.9087510214631306, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11937377690802348, | |
| "grad_norm": 4.476404190063477, | |
| "learning_rate": 4.765625000000001e-06, | |
| "loss": 0.1687, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.12133072407045009, | |
| "grad_norm": 4.893277168273926, | |
| "learning_rate": 4.84375e-06, | |
| "loss": 0.1591, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1232876712328767, | |
| "grad_norm": 4.510354042053223, | |
| "learning_rate": 4.921875e-06, | |
| "loss": 0.1653, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.12524461839530332, | |
| "grad_norm": 4.400285243988037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.1799, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.12720156555772993, | |
| "grad_norm": 4.631839752197266, | |
| "learning_rate": 5.078125000000001e-06, | |
| "loss": 0.1578, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12720156555772993, | |
| "eval_loss": 0.1336735188961029, | |
| "eval_runtime": 107.4984, | |
| "eval_samples_per_second": 28.391, | |
| "eval_steps_per_second": 0.223, | |
| "eval_sts-test_pearson_cosine": 0.886014179849858, | |
| "eval_sts-test_pearson_dot": 0.8762492282837839, | |
| "eval_sts-test_pearson_euclidean": 0.9101155794045166, | |
| "eval_sts-test_pearson_manhattan": 0.9109538919103571, | |
| "eval_sts-test_pearson_max": 0.9109538919103571, | |
| "eval_sts-test_spearman_cosine": 0.9089514176116413, | |
| "eval_sts-test_spearman_dot": 0.8810853441583534, | |
| "eval_sts-test_spearman_euclidean": 0.9061670836303911, | |
| "eval_sts-test_spearman_manhattan": 0.9072153371772234, | |
| "eval_sts-test_spearman_max": 0.9089514176116413, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12915851272015655, | |
| "grad_norm": 4.043459415435791, | |
| "learning_rate": 5.156250000000001e-06, | |
| "loss": 0.1844, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.13111545988258316, | |
| "grad_norm": 4.447835922241211, | |
| "learning_rate": 5.234375e-06, | |
| "loss": 0.1489, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.13307240704500978, | |
| "grad_norm": 5.372109889984131, | |
| "learning_rate": 5.3125e-06, | |
| "loss": 0.1845, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1350293542074364, | |
| "grad_norm": 3.5112483501434326, | |
| "learning_rate": 5.390625000000001e-06, | |
| "loss": 0.1364, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 4.305239200592041, | |
| "learning_rate": 5.468750000000001e-06, | |
| "loss": 0.1584, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "eval_loss": 0.1320798397064209, | |
| "eval_runtime": 107.505, | |
| "eval_samples_per_second": 28.389, | |
| "eval_steps_per_second": 0.223, | |
| "eval_sts-test_pearson_cosine": 0.88578311613969, | |
| "eval_sts-test_pearson_dot": 0.875928774505713, | |
| "eval_sts-test_pearson_euclidean": 0.91024619729973, | |
| "eval_sts-test_pearson_manhattan": 0.9110959495329505, | |
| "eval_sts-test_pearson_max": 0.9110959495329505, | |
| "eval_sts-test_spearman_cosine": 0.9086066538938818, | |
| "eval_sts-test_spearman_dot": 0.8801235500485294, | |
| "eval_sts-test_spearman_euclidean": 0.9060052183179386, | |
| "eval_sts-test_spearman_manhattan": 0.907439182986703, | |
| "eval_sts-test_spearman_max": 0.9086066538938818, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13894324853228962, | |
| "grad_norm": 5.093306064605713, | |
| "learning_rate": 5.546875e-06, | |
| "loss": 0.2279, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.14090019569471623, | |
| "grad_norm": 4.953585147857666, | |
| "learning_rate": 5.625e-06, | |
| "loss": 0.2028, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 4.1561102867126465, | |
| "learning_rate": 5.7031250000000006e-06, | |
| "loss": 0.2291, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.14481409001956946, | |
| "grad_norm": 5.00941801071167, | |
| "learning_rate": 5.781250000000001e-06, | |
| "loss": 0.2419, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.14677103718199608, | |
| "grad_norm": 3.6476099491119385, | |
| "learning_rate": 5.859375e-06, | |
| "loss": 0.1329, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.14677103718199608, | |
| "eval_loss": 0.13061992824077606, | |
| "eval_runtime": 107.3395, | |
| "eval_samples_per_second": 28.433, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8854112983780439, | |
| "eval_sts-test_pearson_dot": 0.8752625071185561, | |
| "eval_sts-test_pearson_euclidean": 0.9103378320010516, | |
| "eval_sts-test_pearson_manhattan": 0.9112261622276095, | |
| "eval_sts-test_pearson_max": 0.9112261622276095, | |
| "eval_sts-test_spearman_cosine": 0.9082604133844965, | |
| "eval_sts-test_spearman_dot": 0.8794192099454903, | |
| "eval_sts-test_spearman_euclidean": 0.9060063370994732, | |
| "eval_sts-test_spearman_manhattan": 0.90766132824825, | |
| "eval_sts-test_spearman_max": 0.9082604133844965, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1487279843444227, | |
| "grad_norm": 4.10636568069458, | |
| "learning_rate": 5.9375e-06, | |
| "loss": 0.204, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1506849315068493, | |
| "grad_norm": 4.767779350280762, | |
| "learning_rate": 6.0156250000000005e-06, | |
| "loss": 0.2239, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.15264187866927592, | |
| "grad_norm": 5.366302490234375, | |
| "learning_rate": 6.093750000000001e-06, | |
| "loss": 0.2181, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.15459882583170254, | |
| "grad_norm": 4.087960720062256, | |
| "learning_rate": 6.171875e-06, | |
| "loss": 0.1285, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.15655577299412915, | |
| "grad_norm": 3.7557668685913086, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.1067, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15655577299412915, | |
| "eval_loss": 0.12924787402153015, | |
| "eval_runtime": 107.2528, | |
| "eval_samples_per_second": 28.456, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8850894038300653, | |
| "eval_sts-test_pearson_dot": 0.874941916465686, | |
| "eval_sts-test_pearson_euclidean": 0.9101863990952803, | |
| "eval_sts-test_pearson_manhattan": 0.9110826056950171, | |
| "eval_sts-test_pearson_max": 0.9110826056950171, | |
| "eval_sts-test_spearman_cosine": 0.9078700928826409, | |
| "eval_sts-test_spearman_dot": 0.8792947566875607, | |
| "eval_sts-test_spearman_euclidean": 0.9059290069197888, | |
| "eval_sts-test_spearman_manhattan": 0.9075206750336968, | |
| "eval_sts-test_spearman_max": 0.9078700928826409, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15851272015655576, | |
| "grad_norm": 3.5708839893341064, | |
| "learning_rate": 6.3281250000000005e-06, | |
| "loss": 0.1189, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.16046966731898238, | |
| "grad_norm": 4.602839469909668, | |
| "learning_rate": 6.406250000000001e-06, | |
| "loss": 0.236, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.162426614481409, | |
| "grad_norm": 4.304513931274414, | |
| "learning_rate": 6.484375000000001e-06, | |
| "loss": 0.1584, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.1643835616438356, | |
| "grad_norm": 4.165163516998291, | |
| "learning_rate": 6.5625e-06, | |
| "loss": 0.1925, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.16634050880626222, | |
| "grad_norm": 3.9157192707061768, | |
| "learning_rate": 6.6406250000000005e-06, | |
| "loss": 0.129, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.16634050880626222, | |
| "eval_loss": 0.1278335303068161, | |
| "eval_runtime": 107.1978, | |
| "eval_samples_per_second": 28.471, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8845993101894516, | |
| "eval_sts-test_pearson_dot": 0.8740701762146532, | |
| "eval_sts-test_pearson_euclidean": 0.9100055922999684, | |
| "eval_sts-test_pearson_manhattan": 0.9108899080028133, | |
| "eval_sts-test_pearson_max": 0.9108899080028133, | |
| "eval_sts-test_spearman_cosine": 0.9078923342595523, | |
| "eval_sts-test_spearman_dot": 0.8788126513485913, | |
| "eval_sts-test_spearman_euclidean": 0.9057257466905491, | |
| "eval_sts-test_spearman_manhattan": 0.9070083178420268, | |
| "eval_sts-test_spearman_max": 0.9078923342595523, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.16829745596868884, | |
| "grad_norm": 4.233823776245117, | |
| "learning_rate": 6.718750000000001e-06, | |
| "loss": 0.1376, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.17025440313111545, | |
| "grad_norm": 4.670790195465088, | |
| "learning_rate": 6.796875000000001e-06, | |
| "loss": 0.1691, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.17221135029354206, | |
| "grad_norm": 3.742030382156372, | |
| "learning_rate": 6.875e-06, | |
| "loss": 0.1045, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.17416829745596868, | |
| "grad_norm": 4.242702960968018, | |
| "learning_rate": 6.9531250000000004e-06, | |
| "loss": 0.165, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.1761252446183953, | |
| "grad_norm": 5.499476909637451, | |
| "learning_rate": 7.031250000000001e-06, | |
| "loss": 0.2926, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1761252446183953, | |
| "eval_loss": 0.12669824063777924, | |
| "eval_runtime": 107.2778, | |
| "eval_samples_per_second": 28.45, | |
| "eval_steps_per_second": 0.224, | |
| "eval_sts-test_pearson_cosine": 0.8844194771150324, | |
| "eval_sts-test_pearson_dot": 0.873458365713796, | |
| "eval_sts-test_pearson_euclidean": 0.9099396625521212, | |
| "eval_sts-test_pearson_manhattan": 0.910745898918033, | |
| "eval_sts-test_pearson_max": 0.910745898918033, | |
| "eval_sts-test_spearman_cosine": 0.907622707909669, | |
| "eval_sts-test_spearman_dot": 0.8783740442356941, | |
| "eval_sts-test_spearman_euclidean": 0.9058808545625318, | |
| "eval_sts-test_spearman_manhattan": 0.906889458491771, | |
| "eval_sts-test_spearman_max": 0.907622707909669, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1780821917808219, | |
| "grad_norm": 2.992021083831787, | |
| "learning_rate": 7.109375000000001e-06, | |
| "loss": 0.1048, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.18003913894324852, | |
| "grad_norm": 4.298286437988281, | |
| "learning_rate": 7.1875e-06, | |
| "loss": 0.1596, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.18199608610567514, | |
| "grad_norm": 5.210509300231934, | |
| "learning_rate": 7.265625e-06, | |
| "loss": 0.2474, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.18395303326810175, | |
| "grad_norm": 4.527407169342041, | |
| "learning_rate": 7.343750000000001e-06, | |
| "loss": 0.1652, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.18590998043052837, | |
| "grad_norm": 5.302050590515137, | |
| "learning_rate": 7.421875000000001e-06, | |
| "loss": 0.2483, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.18590998043052837, | |
| "eval_loss": 0.1252526491880417, | |
| "eval_runtime": 107.5519, | |
| "eval_samples_per_second": 28.377, | |
| "eval_steps_per_second": 0.223, | |
| "eval_sts-test_pearson_cosine": 0.884272350180128, | |
| "eval_sts-test_pearson_dot": 0.8727334938335432, | |
| "eval_sts-test_pearson_euclidean": 0.9099441972021025, | |
| "eval_sts-test_pearson_manhattan": 0.9106991509833859, | |
| "eval_sts-test_pearson_max": 0.9106991509833859, | |
| "eval_sts-test_spearman_cosine": 0.9075948278738224, | |
| "eval_sts-test_spearman_dot": 0.87780624023116, | |
| "eval_sts-test_spearman_euclidean": 0.9060086194138042, | |
| "eval_sts-test_spearman_manhattan": 0.9069788267607697, | |
| "eval_sts-test_spearman_max": 0.9075948278738224, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.18786692759295498, | |
| "grad_norm": 3.690441608428955, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.1623, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.1898238747553816, | |
| "grad_norm": 4.585984706878662, | |
| "learning_rate": 7.578125e-06, | |
| "loss": 0.1955, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1917808219178082, | |
| "grad_norm": 4.493942737579346, | |
| "learning_rate": 7.656250000000001e-06, | |
| "loss": 0.2023, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.19373776908023482, | |
| "grad_norm": 4.569936275482178, | |
| "learning_rate": 7.734375e-06, | |
| "loss": 0.1886, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.19569471624266144, | |
| "grad_norm": 3.7703664302825928, | |
| "learning_rate": 7.8125e-06, | |
| "loss": 0.1284, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19569471624266144, | |
| "eval_loss": 0.12290485948324203, | |
| "eval_runtime": 107.6958, | |
| "eval_samples_per_second": 28.339, | |
| "eval_steps_per_second": 0.223, | |
| "eval_sts-test_pearson_cosine": 0.8836376979322419, | |
| "eval_sts-test_pearson_dot": 0.8710695777275684, | |
| "eval_sts-test_pearson_euclidean": 0.9098265834859519, | |
| "eval_sts-test_pearson_manhattan": 0.9106248996071287, | |
| "eval_sts-test_pearson_max": 0.9106248996071287, | |
| "eval_sts-test_spearman_cosine": 0.9078868298544011, | |
| "eval_sts-test_spearman_dot": 0.8773200625274038, | |
| "eval_sts-test_spearman_euclidean": 0.9063156130669492, | |
| "eval_sts-test_spearman_manhattan": 0.9071474495136926, | |
| "eval_sts-test_spearman_max": 0.9078868298544011, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19765166340508805, | |
| "grad_norm": 4.356619358062744, | |
| "learning_rate": 7.890625e-06, | |
| "loss": 0.2005, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.19960861056751467, | |
| "grad_norm": 4.293449878692627, | |
| "learning_rate": 7.96875e-06, | |
| "loss": 0.2301, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.20156555772994128, | |
| "grad_norm": 4.654509544372559, | |
| "learning_rate": 8.046875e-06, | |
| "loss": 0.2249, | |
| "step": 103 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1022, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 103, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 320, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |