| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4034440344403444, | |
| "eval_steps": 21, | |
| "global_step": 328, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012300123001230013, | |
| "grad_norm": 6.540346145629883, | |
| "learning_rate": 9.803921568627452e-08, | |
| "loss": 0.3208, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024600246002460025, | |
| "grad_norm": 5.055933475494385, | |
| "learning_rate": 1.9607843137254904e-07, | |
| "loss": 0.1703, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0036900369003690036, | |
| "grad_norm": 6.361550331115723, | |
| "learning_rate": 2.9411764705882356e-07, | |
| "loss": 0.3362, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004920049200492005, | |
| "grad_norm": 6.709433078765869, | |
| "learning_rate": 3.921568627450981e-07, | |
| "loss": 0.3346, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006150061500615006, | |
| "grad_norm": 5.4415154457092285, | |
| "learning_rate": 4.901960784313725e-07, | |
| "loss": 0.2484, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007380073800738007, | |
| "grad_norm": 5.709558010101318, | |
| "learning_rate": 5.882352941176471e-07, | |
| "loss": 0.2249, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008610086100861008, | |
| "grad_norm": 6.553178787231445, | |
| "learning_rate": 6.862745098039217e-07, | |
| "loss": 0.2724, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00984009840098401, | |
| "grad_norm": 5.640111446380615, | |
| "learning_rate": 7.843137254901962e-07, | |
| "loss": 0.251, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01107011070110701, | |
| "grad_norm": 5.696380615234375, | |
| "learning_rate": 8.823529411764707e-07, | |
| "loss": 0.2413, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012300123001230012, | |
| "grad_norm": 6.983877182006836, | |
| "learning_rate": 9.80392156862745e-07, | |
| "loss": 0.382, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013530135301353014, | |
| "grad_norm": 6.066723346710205, | |
| "learning_rate": 1.0784313725490197e-06, | |
| "loss": 0.2695, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014760147601476014, | |
| "grad_norm": 5.643115520477295, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 0.2392, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015990159901599015, | |
| "grad_norm": 6.062892436981201, | |
| "learning_rate": 1.2745098039215686e-06, | |
| "loss": 0.3603, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017220172201722016, | |
| "grad_norm": 6.2491655349731445, | |
| "learning_rate": 1.3725490196078434e-06, | |
| "loss": 0.3282, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01845018450184502, | |
| "grad_norm": 6.1164398193359375, | |
| "learning_rate": 1.4705882352941177e-06, | |
| "loss": 0.2878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01968019680196802, | |
| "grad_norm": 5.676611423492432, | |
| "learning_rate": 1.5686274509803923e-06, | |
| "loss": 0.3046, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020910209102091022, | |
| "grad_norm": 7.181272983551025, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.3946, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02214022140221402, | |
| "grad_norm": 5.430984020233154, | |
| "learning_rate": 1.7647058823529414e-06, | |
| "loss": 0.2038, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023370233702337023, | |
| "grad_norm": 7.2283220291137695, | |
| "learning_rate": 1.8627450980392158e-06, | |
| "loss": 0.3542, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.024600246002460024, | |
| "grad_norm": 5.587338924407959, | |
| "learning_rate": 1.96078431372549e-06, | |
| "loss": 0.2369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025830258302583026, | |
| "grad_norm": 4.456090927124023, | |
| "learning_rate": 2.058823529411765e-06, | |
| "loss": 0.1967, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025830258302583026, | |
| "eval_loss": 0.14506277441978455, | |
| "eval_runtime": 54.872, | |
| "eval_samples_per_second": 27.446, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8860152816653839, | |
| "eval_sts-test_pearson_dot": 0.8766503125978379, | |
| "eval_sts-test_pearson_euclidean": 0.9084101290541164, | |
| "eval_sts-test_pearson_manhattan": 0.909121525028934, | |
| "eval_sts-test_pearson_max": 0.909121525028934, | |
| "eval_sts-test_spearman_cosine": 0.9080919696366193, | |
| "eval_sts-test_spearman_dot": 0.8799434709726907, | |
| "eval_sts-test_spearman_euclidean": 0.9044399981995129, | |
| "eval_sts-test_spearman_manhattan": 0.9048055712538192, | |
| "eval_sts-test_spearman_max": 0.9080919696366193, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02706027060270603, | |
| "grad_norm": 6.088884353637695, | |
| "learning_rate": 2.1568627450980393e-06, | |
| "loss": 0.2368, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.028290282902829027, | |
| "grad_norm": 5.354013919830322, | |
| "learning_rate": 2.254901960784314e-06, | |
| "loss": 0.263, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02952029520295203, | |
| "grad_norm": 7.822023391723633, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 0.3595, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03075030750307503, | |
| "grad_norm": 6.401333332061768, | |
| "learning_rate": 2.450980392156863e-06, | |
| "loss": 0.3073, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03198031980319803, | |
| "grad_norm": 5.567343235015869, | |
| "learning_rate": 2.549019607843137e-06, | |
| "loss": 0.2232, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.033210332103321034, | |
| "grad_norm": 4.244979381561279, | |
| "learning_rate": 2.647058823529412e-06, | |
| "loss": 0.1822, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03444034440344403, | |
| "grad_norm": 5.674376964569092, | |
| "learning_rate": 2.7450980392156867e-06, | |
| "loss": 0.251, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03567035670356704, | |
| "grad_norm": 6.017494201660156, | |
| "learning_rate": 2.843137254901961e-06, | |
| "loss": 0.2677, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03690036900369004, | |
| "grad_norm": 6.415028095245361, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 0.3252, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.038130381303813035, | |
| "grad_norm": 5.484204292297363, | |
| "learning_rate": 3.03921568627451e-06, | |
| "loss": 0.2058, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03936039360393604, | |
| "grad_norm": 5.997295379638672, | |
| "learning_rate": 3.1372549019607846e-06, | |
| "loss": 0.3083, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04059040590405904, | |
| "grad_norm": 5.527047157287598, | |
| "learning_rate": 3.2352941176470594e-06, | |
| "loss": 0.2109, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.041820418204182044, | |
| "grad_norm": 5.817302227020264, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.2751, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04305043050430504, | |
| "grad_norm": 5.476433753967285, | |
| "learning_rate": 3.431372549019608e-06, | |
| "loss": 0.2269, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04428044280442804, | |
| "grad_norm": 5.363610744476318, | |
| "learning_rate": 3.529411764705883e-06, | |
| "loss": 0.2333, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04551045510455105, | |
| "grad_norm": 6.07395601272583, | |
| "learning_rate": 3.6274509803921573e-06, | |
| "loss": 0.2747, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.046740467404674045, | |
| "grad_norm": 4.726163864135742, | |
| "learning_rate": 3.7254901960784316e-06, | |
| "loss": 0.1285, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04797047970479705, | |
| "grad_norm": 5.783392906188965, | |
| "learning_rate": 3.8235294117647055e-06, | |
| "loss": 0.3659, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04920049200492005, | |
| "grad_norm": 6.566931247711182, | |
| "learning_rate": 3.92156862745098e-06, | |
| "loss": 0.3991, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05043050430504305, | |
| "grad_norm": 5.311452388763428, | |
| "learning_rate": 4.019607843137255e-06, | |
| "loss": 0.2647, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05166051660516605, | |
| "grad_norm": 6.0737152099609375, | |
| "learning_rate": 4.11764705882353e-06, | |
| "loss": 0.3627, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05166051660516605, | |
| "eval_loss": 0.1373225301504135, | |
| "eval_runtime": 54.8187, | |
| "eval_samples_per_second": 27.472, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8846111050777101, | |
| "eval_sts-test_pearson_dot": 0.8747554197498655, | |
| "eval_sts-test_pearson_euclidean": 0.9089352149126115, | |
| "eval_sts-test_pearson_manhattan": 0.9098483550214526, | |
| "eval_sts-test_pearson_max": 0.9098483550214526, | |
| "eval_sts-test_spearman_cosine": 0.9084485029361248, | |
| "eval_sts-test_spearman_dot": 0.8796038088987298, | |
| "eval_sts-test_spearman_euclidean": 0.9055790073044468, | |
| "eval_sts-test_spearman_manhattan": 0.9063848432683216, | |
| "eval_sts-test_spearman_max": 0.9084485029361248, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05289052890528905, | |
| "grad_norm": 4.857839584350586, | |
| "learning_rate": 4.215686274509805e-06, | |
| "loss": 0.2026, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05412054120541206, | |
| "grad_norm": 5.248873233795166, | |
| "learning_rate": 4.313725490196079e-06, | |
| "loss": 0.1923, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.055350553505535055, | |
| "grad_norm": 5.329862117767334, | |
| "learning_rate": 4.411764705882353e-06, | |
| "loss": 0.2369, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.056580565805658053, | |
| "grad_norm": 5.581146240234375, | |
| "learning_rate": 4.509803921568628e-06, | |
| "loss": 0.2268, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05781057810578106, | |
| "grad_norm": 5.818411350250244, | |
| "learning_rate": 4.607843137254902e-06, | |
| "loss": 0.2975, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05904059040590406, | |
| "grad_norm": 5.096602916717529, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 0.1922, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06027060270602706, | |
| "grad_norm": 5.256355285644531, | |
| "learning_rate": 4.803921568627452e-06, | |
| "loss": 0.1906, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06150061500615006, | |
| "grad_norm": 5.3927388191223145, | |
| "learning_rate": 4.901960784313726e-06, | |
| "loss": 0.2379, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06273062730627306, | |
| "grad_norm": 6.2723846435546875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3796, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.06396063960639606, | |
| "grad_norm": 4.595238208770752, | |
| "learning_rate": 5.098039215686274e-06, | |
| "loss": 0.1821, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.06519065190651907, | |
| "grad_norm": 4.342020511627197, | |
| "learning_rate": 5.19607843137255e-06, | |
| "loss": 0.1257, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.06642066420664207, | |
| "grad_norm": 4.998225212097168, | |
| "learning_rate": 5.294117647058824e-06, | |
| "loss": 0.2368, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.06765067650676507, | |
| "grad_norm": 5.510946273803711, | |
| "learning_rate": 5.392156862745098e-06, | |
| "loss": 0.294, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06888068880688807, | |
| "grad_norm": 4.788788318634033, | |
| "learning_rate": 5.4901960784313735e-06, | |
| "loss": 0.2594, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07011070110701106, | |
| "grad_norm": 5.827020645141602, | |
| "learning_rate": 5.588235294117647e-06, | |
| "loss": 0.2972, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07134071340713408, | |
| "grad_norm": 4.821737289428711, | |
| "learning_rate": 5.686274509803922e-06, | |
| "loss": 0.2297, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.07257072570725707, | |
| "grad_norm": 4.880247592926025, | |
| "learning_rate": 5.784313725490197e-06, | |
| "loss": 0.1487, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.07380073800738007, | |
| "grad_norm": 4.447835445404053, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.182, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07503075030750307, | |
| "grad_norm": 5.5556640625, | |
| "learning_rate": 5.980392156862746e-06, | |
| "loss": 0.2516, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.07626076260762607, | |
| "grad_norm": 5.217922687530518, | |
| "learning_rate": 6.07843137254902e-06, | |
| "loss": 0.2809, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.07749077490774908, | |
| "grad_norm": 4.436608791351318, | |
| "learning_rate": 6.176470588235295e-06, | |
| "loss": 0.1371, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07749077490774908, | |
| "eval_loss": 0.13080179691314697, | |
| "eval_runtime": 54.9188, | |
| "eval_samples_per_second": 27.422, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.882074513745531, | |
| "eval_sts-test_pearson_dot": 0.8709046425878566, | |
| "eval_sts-test_pearson_euclidean": 0.9081794284297221, | |
| "eval_sts-test_pearson_manhattan": 0.9093974331692458, | |
| "eval_sts-test_pearson_max": 0.9093974331692458, | |
| "eval_sts-test_spearman_cosine": 0.9067824582257844, | |
| "eval_sts-test_spearman_dot": 0.8757477717096785, | |
| "eval_sts-test_spearman_euclidean": 0.9051085820447002, | |
| "eval_sts-test_spearman_manhattan": 0.9064308923162935, | |
| "eval_sts-test_spearman_max": 0.9067824582257844, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07872078720787208, | |
| "grad_norm": 5.6947021484375, | |
| "learning_rate": 6.274509803921569e-06, | |
| "loss": 0.2149, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.07995079950799508, | |
| "grad_norm": 4.272282600402832, | |
| "learning_rate": 6.372549019607843e-06, | |
| "loss": 0.1806, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.08118081180811808, | |
| "grad_norm": 4.575979232788086, | |
| "learning_rate": 6.470588235294119e-06, | |
| "loss": 0.1458, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.08241082410824108, | |
| "grad_norm": 4.315216541290283, | |
| "learning_rate": 6.568627450980393e-06, | |
| "loss": 0.249, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.08364083640836409, | |
| "grad_norm": 5.67277193069458, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.2787, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.08487084870848709, | |
| "grad_norm": 5.964886665344238, | |
| "learning_rate": 6.764705882352942e-06, | |
| "loss": 0.288, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.08610086100861009, | |
| "grad_norm": 4.218502521514893, | |
| "learning_rate": 6.862745098039216e-06, | |
| "loss": 0.1461, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08733087330873308, | |
| "grad_norm": 5.179543972015381, | |
| "learning_rate": 6.96078431372549e-06, | |
| "loss": 0.2304, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.08856088560885608, | |
| "grad_norm": 5.720668792724609, | |
| "learning_rate": 7.058823529411766e-06, | |
| "loss": 0.3505, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0897908979089791, | |
| "grad_norm": 5.2965497970581055, | |
| "learning_rate": 7.15686274509804e-06, | |
| "loss": 0.2227, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0910209102091021, | |
| "grad_norm": 4.685606956481934, | |
| "learning_rate": 7.2549019607843145e-06, | |
| "loss": 0.1746, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.09225092250922509, | |
| "grad_norm": 4.2930145263671875, | |
| "learning_rate": 7.352941176470589e-06, | |
| "loss": 0.1484, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09348093480934809, | |
| "grad_norm": 3.764916181564331, | |
| "learning_rate": 7.450980392156863e-06, | |
| "loss": 0.1346, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.09471094710947109, | |
| "grad_norm": 5.033151626586914, | |
| "learning_rate": 7.549019607843138e-06, | |
| "loss": 0.2112, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0959409594095941, | |
| "grad_norm": 5.817330837249756, | |
| "learning_rate": 7.647058823529411e-06, | |
| "loss": 0.3138, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0971709717097171, | |
| "grad_norm": 6.147035121917725, | |
| "learning_rate": 7.745098039215687e-06, | |
| "loss": 0.2675, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0984009840098401, | |
| "grad_norm": 5.131881237030029, | |
| "learning_rate": 7.84313725490196e-06, | |
| "loss": 0.2849, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0996309963099631, | |
| "grad_norm": 4.2269368171691895, | |
| "learning_rate": 7.941176470588236e-06, | |
| "loss": 0.1719, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.1008610086100861, | |
| "grad_norm": 5.200590133666992, | |
| "learning_rate": 8.03921568627451e-06, | |
| "loss": 0.2749, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.10209102091020911, | |
| "grad_norm": 5.44044303894043, | |
| "learning_rate": 8.137254901960784e-06, | |
| "loss": 0.3097, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.1033210332103321, | |
| "grad_norm": 4.603049278259277, | |
| "learning_rate": 8.23529411764706e-06, | |
| "loss": 0.2068, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1033210332103321, | |
| "eval_loss": 0.1260141134262085, | |
| "eval_runtime": 54.8932, | |
| "eval_samples_per_second": 27.435, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8775839612260851, | |
| "eval_sts-test_pearson_dot": 0.8664914414909934, | |
| "eval_sts-test_pearson_euclidean": 0.9054210798291935, | |
| "eval_sts-test_pearson_manhattan": 0.9069843565115414, | |
| "eval_sts-test_pearson_max": 0.9069843565115414, | |
| "eval_sts-test_spearman_cosine": 0.9044597335057865, | |
| "eval_sts-test_spearman_dot": 0.872940077569982, | |
| "eval_sts-test_spearman_euclidean": 0.9027100934391671, | |
| "eval_sts-test_spearman_manhattan": 0.904476380975024, | |
| "eval_sts-test_spearman_max": 0.904476380975024, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1045510455104551, | |
| "grad_norm": 4.813210964202881, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.22, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1057810578105781, | |
| "grad_norm": 4.659386157989502, | |
| "learning_rate": 8.43137254901961e-06, | |
| "loss": 0.2977, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.1070110701107011, | |
| "grad_norm": 4.895315647125244, | |
| "learning_rate": 8.529411764705883e-06, | |
| "loss": 0.209, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.10824108241082411, | |
| "grad_norm": 5.339110851287842, | |
| "learning_rate": 8.627450980392157e-06, | |
| "loss": 0.2215, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.10947109471094711, | |
| "grad_norm": 4.615406036376953, | |
| "learning_rate": 8.725490196078433e-06, | |
| "loss": 0.1948, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.11070110701107011, | |
| "grad_norm": 5.0383734703063965, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 0.2084, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11193111931119311, | |
| "grad_norm": 3.9511592388153076, | |
| "learning_rate": 8.921568627450982e-06, | |
| "loss": 0.1823, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.11316113161131611, | |
| "grad_norm": 5.13690710067749, | |
| "learning_rate": 9.019607843137256e-06, | |
| "loss": 0.255, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.11439114391143912, | |
| "grad_norm": 5.1460747718811035, | |
| "learning_rate": 9.11764705882353e-06, | |
| "loss": 0.2675, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.11562115621156212, | |
| "grad_norm": 4.207213878631592, | |
| "learning_rate": 9.215686274509804e-06, | |
| "loss": 0.18, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.11685116851168512, | |
| "grad_norm": 4.802348613739014, | |
| "learning_rate": 9.31372549019608e-06, | |
| "loss": 0.2891, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.11808118081180811, | |
| "grad_norm": 4.9332966804504395, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 0.253, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.11931119311193111, | |
| "grad_norm": 5.841371536254883, | |
| "learning_rate": 9.509803921568628e-06, | |
| "loss": 0.3481, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.12054120541205413, | |
| "grad_norm": 3.70485782623291, | |
| "learning_rate": 9.607843137254903e-06, | |
| "loss": 0.1688, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.12177121771217712, | |
| "grad_norm": 4.415471076965332, | |
| "learning_rate": 9.705882352941177e-06, | |
| "loss": 0.1808, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.12300123001230012, | |
| "grad_norm": 5.058602809906006, | |
| "learning_rate": 9.803921568627451e-06, | |
| "loss": 0.2821, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12423124231242312, | |
| "grad_norm": 4.303729057312012, | |
| "learning_rate": 9.901960784313727e-06, | |
| "loss": 0.1856, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.12546125461254612, | |
| "grad_norm": 4.048065185546875, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1441, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.12669126691266913, | |
| "grad_norm": 4.463968753814697, | |
| "learning_rate": 1.0098039215686275e-05, | |
| "loss": 0.226, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.12792127921279212, | |
| "grad_norm": 3.401120901107788, | |
| "learning_rate": 1.0196078431372549e-05, | |
| "loss": 0.1662, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.12915129151291513, | |
| "grad_norm": 4.119345188140869, | |
| "learning_rate": 1.0294117647058823e-05, | |
| "loss": 0.2043, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.12915129151291513, | |
| "eval_loss": 0.11874283850193024, | |
| "eval_runtime": 54.7282, | |
| "eval_samples_per_second": 27.518, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8767520821963045, | |
| "eval_sts-test_pearson_dot": 0.8648481444888331, | |
| "eval_sts-test_pearson_euclidean": 0.9053937497921556, | |
| "eval_sts-test_pearson_manhattan": 0.9071737646452815, | |
| "eval_sts-test_pearson_max": 0.9071737646452815, | |
| "eval_sts-test_spearman_cosine": 0.9050983787571032, | |
| "eval_sts-test_spearman_dot": 0.8730474805973213, | |
| "eval_sts-test_spearman_euclidean": 0.9035385735413058, | |
| "eval_sts-test_spearman_manhattan": 0.9054231834122819, | |
| "eval_sts-test_spearman_max": 0.9054231834122819, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.13038130381303814, | |
| "grad_norm": 5.826413154602051, | |
| "learning_rate": 1.03921568627451e-05, | |
| "loss": 0.3907, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.13161131611316113, | |
| "grad_norm": 3.2629737854003906, | |
| "learning_rate": 1.0490196078431374e-05, | |
| "loss": 0.1332, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.13284132841328414, | |
| "grad_norm": 4.044755458831787, | |
| "learning_rate": 1.0588235294117648e-05, | |
| "loss": 0.2243, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.13407134071340712, | |
| "grad_norm": 3.9784040451049805, | |
| "learning_rate": 1.0686274509803922e-05, | |
| "loss": 0.162, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.13530135301353013, | |
| "grad_norm": 3.1851444244384766, | |
| "learning_rate": 1.0784313725490196e-05, | |
| "loss": 0.1481, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13653136531365315, | |
| "grad_norm": 4.281413555145264, | |
| "learning_rate": 1.0882352941176471e-05, | |
| "loss": 0.2163, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.13776137761377613, | |
| "grad_norm": 4.62849235534668, | |
| "learning_rate": 1.0980392156862747e-05, | |
| "loss": 0.24, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.13899138991389914, | |
| "grad_norm": 3.92616868019104, | |
| "learning_rate": 1.1078431372549021e-05, | |
| "loss": 0.1406, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.14022140221402213, | |
| "grad_norm": 3.8505780696868896, | |
| "learning_rate": 1.1176470588235295e-05, | |
| "loss": 0.1522, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.14145141451414514, | |
| "grad_norm": 5.220509052276611, | |
| "learning_rate": 1.1274509803921569e-05, | |
| "loss": 0.2593, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.14268142681426815, | |
| "grad_norm": 4.459743499755859, | |
| "learning_rate": 1.1372549019607844e-05, | |
| "loss": 0.2426, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.14391143911439114, | |
| "grad_norm": 4.434360504150391, | |
| "learning_rate": 1.1470588235294118e-05, | |
| "loss": 0.1781, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.14514145141451415, | |
| "grad_norm": 4.638584613800049, | |
| "learning_rate": 1.1568627450980394e-05, | |
| "loss": 0.264, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.14637146371463713, | |
| "grad_norm": 4.5364484786987305, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.1944, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.14760147601476015, | |
| "grad_norm": 3.597980499267578, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 0.1341, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14883148831488316, | |
| "grad_norm": 3.5174648761749268, | |
| "learning_rate": 1.1862745098039217e-05, | |
| "loss": 0.155, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.15006150061500614, | |
| "grad_norm": 4.771029949188232, | |
| "learning_rate": 1.1960784313725491e-05, | |
| "loss": 0.2052, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.15129151291512916, | |
| "grad_norm": 4.15376615524292, | |
| "learning_rate": 1.2058823529411765e-05, | |
| "loss": 0.2023, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.15252152521525214, | |
| "grad_norm": 3.5796732902526855, | |
| "learning_rate": 1.215686274509804e-05, | |
| "loss": 0.1519, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.15375153751537515, | |
| "grad_norm": 3.759777545928955, | |
| "learning_rate": 1.2254901960784315e-05, | |
| "loss": 0.2118, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15498154981549817, | |
| "grad_norm": 4.691242218017578, | |
| "learning_rate": 1.235294117647059e-05, | |
| "loss": 0.2489, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.15498154981549817, | |
| "eval_loss": 0.11467884480953217, | |
| "eval_runtime": 54.6969, | |
| "eval_samples_per_second": 27.534, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8783763084873629, | |
| "eval_sts-test_pearson_dot": 0.8674040012483692, | |
| "eval_sts-test_pearson_euclidean": 0.9069725735634968, | |
| "eval_sts-test_pearson_manhattan": 0.908783443457056, | |
| "eval_sts-test_pearson_max": 0.908783443457056, | |
| "eval_sts-test_spearman_cosine": 0.9058364613112314, | |
| "eval_sts-test_spearman_dot": 0.8738751104254939, | |
| "eval_sts-test_spearman_euclidean": 0.904588080123457, | |
| "eval_sts-test_spearman_manhattan": 0.9067583820471556, | |
| "eval_sts-test_spearman_max": 0.9067583820471556, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.15621156211562115, | |
| "grad_norm": 4.087611198425293, | |
| "learning_rate": 1.2450980392156864e-05, | |
| "loss": 0.1988, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.15744157441574416, | |
| "grad_norm": 3.754612684249878, | |
| "learning_rate": 1.2549019607843138e-05, | |
| "loss": 0.1541, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.15867158671586715, | |
| "grad_norm": 3.9258835315704346, | |
| "learning_rate": 1.2647058823529412e-05, | |
| "loss": 0.1819, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.15990159901599016, | |
| "grad_norm": 3.88478422164917, | |
| "learning_rate": 1.2745098039215686e-05, | |
| "loss": 0.1582, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16113161131611317, | |
| "grad_norm": 4.9845428466796875, | |
| "learning_rate": 1.2843137254901964e-05, | |
| "loss": 0.2866, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.16236162361623616, | |
| "grad_norm": 4.692960262298584, | |
| "learning_rate": 1.2941176470588238e-05, | |
| "loss": 0.2766, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.16359163591635917, | |
| "grad_norm": 3.9432125091552734, | |
| "learning_rate": 1.3039215686274511e-05, | |
| "loss": 0.1299, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.16482164821648215, | |
| "grad_norm": 4.439709663391113, | |
| "learning_rate": 1.3137254901960785e-05, | |
| "loss": 0.2558, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.16605166051660517, | |
| "grad_norm": 3.631169319152832, | |
| "learning_rate": 1.323529411764706e-05, | |
| "loss": 0.1687, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.16728167281672818, | |
| "grad_norm": 4.130221843719482, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.173, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.16851168511685116, | |
| "grad_norm": 4.169937610626221, | |
| "learning_rate": 1.3431372549019607e-05, | |
| "loss": 0.2276, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.16974169741697417, | |
| "grad_norm": 4.4349751472473145, | |
| "learning_rate": 1.3529411764705885e-05, | |
| "loss": 0.2174, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.17097170971709716, | |
| "grad_norm": 4.688521862030029, | |
| "learning_rate": 1.3627450980392158e-05, | |
| "loss": 0.2666, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.17220172201722017, | |
| "grad_norm": 3.7199971675872803, | |
| "learning_rate": 1.3725490196078432e-05, | |
| "loss": 0.1524, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17343173431734318, | |
| "grad_norm": 2.8609495162963867, | |
| "learning_rate": 1.3823529411764706e-05, | |
| "loss": 0.1179, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.17466174661746617, | |
| "grad_norm": 4.374091625213623, | |
| "learning_rate": 1.392156862745098e-05, | |
| "loss": 0.2475, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.17589175891758918, | |
| "grad_norm": 5.200084209442139, | |
| "learning_rate": 1.4019607843137256e-05, | |
| "loss": 0.2662, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.17712177121771217, | |
| "grad_norm": 3.720994710922241, | |
| "learning_rate": 1.4117647058823532e-05, | |
| "loss": 0.1596, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.17835178351783518, | |
| "grad_norm": 3.991046905517578, | |
| "learning_rate": 1.4215686274509805e-05, | |
| "loss": 0.2331, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.1795817958179582, | |
| "grad_norm": 4.76691198348999, | |
| "learning_rate": 1.431372549019608e-05, | |
| "loss": 0.2905, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.18081180811808117, | |
| "grad_norm": 3.6453163623809814, | |
| "learning_rate": 1.4411764705882353e-05, | |
| "loss": 0.1342, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.18081180811808117, | |
| "eval_loss": 0.10875426232814789, | |
| "eval_runtime": 54.7153, | |
| "eval_samples_per_second": 27.524, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8768801472189502, | |
| "eval_sts-test_pearson_dot": 0.8620776961156391, | |
| "eval_sts-test_pearson_euclidean": 0.9073367408863471, | |
| "eval_sts-test_pearson_manhattan": 0.9086519830687241, | |
| "eval_sts-test_pearson_max": 0.9086519830687241, | |
| "eval_sts-test_spearman_cosine": 0.905147068129497, | |
| "eval_sts-test_spearman_dot": 0.869011811845045, | |
| "eval_sts-test_spearman_euclidean": 0.9050077574527855, | |
| "eval_sts-test_spearman_manhattan": 0.9068115017944273, | |
| "eval_sts-test_spearman_max": 0.9068115017944273, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.1820418204182042, | |
| "grad_norm": 2.6028358936309814, | |
| "learning_rate": 1.4509803921568629e-05, | |
| "loss": 0.0839, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.18327183271832717, | |
| "grad_norm": 4.445943832397461, | |
| "learning_rate": 1.4607843137254903e-05, | |
| "loss": 0.2055, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.18450184501845018, | |
| "grad_norm": 4.500098705291748, | |
| "learning_rate": 1.4705882352941179e-05, | |
| "loss": 0.2196, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1857318573185732, | |
| "grad_norm": 4.317416667938232, | |
| "learning_rate": 1.4803921568627453e-05, | |
| "loss": 0.2283, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.18696186961869618, | |
| "grad_norm": 4.395689010620117, | |
| "learning_rate": 1.4901960784313726e-05, | |
| "loss": 0.2105, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.1881918819188192, | |
| "grad_norm": 3.5757391452789307, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.1534, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.18942189421894218, | |
| "grad_norm": 3.860861301422119, | |
| "learning_rate": 1.5098039215686276e-05, | |
| "loss": 0.1954, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.1906519065190652, | |
| "grad_norm": 3.4191622734069824, | |
| "learning_rate": 1.519607843137255e-05, | |
| "loss": 0.1332, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.1918819188191882, | |
| "grad_norm": 3.8505654335021973, | |
| "learning_rate": 1.5294117647058822e-05, | |
| "loss": 0.19, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.1931119311193112, | |
| "grad_norm": 4.127209663391113, | |
| "learning_rate": 1.53921568627451e-05, | |
| "loss": 0.1878, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.1943419434194342, | |
| "grad_norm": 3.7976646423339844, | |
| "learning_rate": 1.5490196078431373e-05, | |
| "loss": 0.1518, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.19557195571955718, | |
| "grad_norm": 4.613111972808838, | |
| "learning_rate": 1.558823529411765e-05, | |
| "loss": 0.1906, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.1968019680196802, | |
| "grad_norm": 3.911393880844116, | |
| "learning_rate": 1.568627450980392e-05, | |
| "loss": 0.155, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1980319803198032, | |
| "grad_norm": 3.694939374923706, | |
| "learning_rate": 1.5784313725490197e-05, | |
| "loss": 0.1519, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.1992619926199262, | |
| "grad_norm": 4.334694862365723, | |
| "learning_rate": 1.5882352941176473e-05, | |
| "loss": 0.1726, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.2004920049200492, | |
| "grad_norm": 3.6630055904388428, | |
| "learning_rate": 1.5980392156862748e-05, | |
| "loss": 0.1618, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.2017220172201722, | |
| "grad_norm": 4.7789130210876465, | |
| "learning_rate": 1.607843137254902e-05, | |
| "loss": 0.2767, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.2029520295202952, | |
| "grad_norm": 4.171343803405762, | |
| "learning_rate": 1.6176470588235296e-05, | |
| "loss": 0.1996, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.20418204182041821, | |
| "grad_norm": 4.386513710021973, | |
| "learning_rate": 1.627450980392157e-05, | |
| "loss": 0.1907, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.2054120541205412, | |
| "grad_norm": 4.183532238006592, | |
| "learning_rate": 1.6372549019607844e-05, | |
| "loss": 0.1928, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.2066420664206642, | |
| "grad_norm": 3.8950257301330566, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 0.1507, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.2066420664206642, | |
| "eval_loss": 0.10821738839149475, | |
| "eval_runtime": 54.7389, | |
| "eval_samples_per_second": 27.512, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8772991124680096, | |
| "eval_sts-test_pearson_dot": 0.861322579093208, | |
| "eval_sts-test_pearson_euclidean": 0.9072621517681675, | |
| "eval_sts-test_pearson_manhattan": 0.9086600802981594, | |
| "eval_sts-test_pearson_max": 0.9086600802981594, | |
| "eval_sts-test_spearman_cosine": 0.9044609865411055, | |
| "eval_sts-test_spearman_dot": 0.8661539962925903, | |
| "eval_sts-test_spearman_euclidean": 0.904084091417667, | |
| "eval_sts-test_spearman_manhattan": 0.9054917423447336, | |
| "eval_sts-test_spearman_max": 0.9054917423447336, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.2078720787207872, | |
| "grad_norm": 4.002283096313477, | |
| "learning_rate": 1.6568627450980395e-05, | |
| "loss": 0.1637, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2091020910209102, | |
| "grad_norm": 4.142872333526611, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1687, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.21033210332103322, | |
| "grad_norm": 4.345719337463379, | |
| "learning_rate": 1.6764705882352943e-05, | |
| "loss": 0.2181, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.2115621156211562, | |
| "grad_norm": 3.7364888191223145, | |
| "learning_rate": 1.686274509803922e-05, | |
| "loss": 0.1496, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.21279212792127922, | |
| "grad_norm": 4.202157974243164, | |
| "learning_rate": 1.696078431372549e-05, | |
| "loss": 0.1749, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.2140221402214022, | |
| "grad_norm": 4.639451503753662, | |
| "learning_rate": 1.7058823529411767e-05, | |
| "loss": 0.2374, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.21525215252152521, | |
| "grad_norm": 4.011781215667725, | |
| "learning_rate": 1.715686274509804e-05, | |
| "loss": 0.2122, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.21648216482164823, | |
| "grad_norm": 4.113095760345459, | |
| "learning_rate": 1.7254901960784314e-05, | |
| "loss": 0.1617, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.2177121771217712, | |
| "grad_norm": 4.0442681312561035, | |
| "learning_rate": 1.735294117647059e-05, | |
| "loss": 0.168, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.21894218942189422, | |
| "grad_norm": 4.375425338745117, | |
| "learning_rate": 1.7450980392156866e-05, | |
| "loss": 0.263, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.2201722017220172, | |
| "grad_norm": 3.2303390502929688, | |
| "learning_rate": 1.7549019607843138e-05, | |
| "loss": 0.1328, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.22140221402214022, | |
| "grad_norm": 4.832092761993408, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.3157, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.22263222632226323, | |
| "grad_norm": 3.57254695892334, | |
| "learning_rate": 1.7745098039215686e-05, | |
| "loss": 0.2164, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.22386223862238622, | |
| "grad_norm": 3.135535717010498, | |
| "learning_rate": 1.7843137254901965e-05, | |
| "loss": 0.1255, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.22509225092250923, | |
| "grad_norm": 4.719324588775635, | |
| "learning_rate": 1.7941176470588237e-05, | |
| "loss": 0.2863, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.22632226322263221, | |
| "grad_norm": 3.8961801528930664, | |
| "learning_rate": 1.8039215686274513e-05, | |
| "loss": 0.155, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.22755227552275523, | |
| "grad_norm": 2.8389103412628174, | |
| "learning_rate": 1.8137254901960785e-05, | |
| "loss": 0.1271, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.22878228782287824, | |
| "grad_norm": 4.103536128997803, | |
| "learning_rate": 1.823529411764706e-05, | |
| "loss": 0.216, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.23001230012300122, | |
| "grad_norm": 4.006705284118652, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.205, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.23124231242312424, | |
| "grad_norm": 3.424255847930908, | |
| "learning_rate": 1.843137254901961e-05, | |
| "loss": 0.1575, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.23247232472324722, | |
| "grad_norm": 4.568851947784424, | |
| "learning_rate": 1.8529411764705884e-05, | |
| "loss": 0.1939, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.23247232472324722, | |
| "eval_loss": 0.1056687980890274, | |
| "eval_runtime": 54.7136, | |
| "eval_samples_per_second": 27.525, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8789160692756717, | |
| "eval_sts-test_pearson_dot": 0.8639029174125306, | |
| "eval_sts-test_pearson_euclidean": 0.9084173029414142, | |
| "eval_sts-test_pearson_manhattan": 0.9093131544369648, | |
| "eval_sts-test_pearson_max": 0.9093131544369648, | |
| "eval_sts-test_spearman_cosine": 0.904571298400435, | |
| "eval_sts-test_spearman_dot": 0.8658778810098052, | |
| "eval_sts-test_spearman_euclidean": 0.9046812074984125, | |
| "eval_sts-test_spearman_manhattan": 0.9056302027474785, | |
| "eval_sts-test_spearman_max": 0.9056302027474785, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.23370233702337023, | |
| "grad_norm": 3.5909903049468994, | |
| "learning_rate": 1.862745098039216e-05, | |
| "loss": 0.2209, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.23493234932349324, | |
| "grad_norm": 3.443946361541748, | |
| "learning_rate": 1.8725490196078432e-05, | |
| "loss": 0.153, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.23616236162361623, | |
| "grad_norm": 3.8604445457458496, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 0.2187, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.23739237392373924, | |
| "grad_norm": 3.5916690826416016, | |
| "learning_rate": 1.892156862745098e-05, | |
| "loss": 0.1593, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.23862238622386223, | |
| "grad_norm": 3.8676974773406982, | |
| "learning_rate": 1.9019607843137255e-05, | |
| "loss": 0.173, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.23985239852398524, | |
| "grad_norm": 4.338643550872803, | |
| "learning_rate": 1.911764705882353e-05, | |
| "loss": 0.2377, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.24108241082410825, | |
| "grad_norm": 4.509932994842529, | |
| "learning_rate": 1.9215686274509807e-05, | |
| "loss": 0.2281, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.24231242312423124, | |
| "grad_norm": 4.282917022705078, | |
| "learning_rate": 1.931372549019608e-05, | |
| "loss": 0.2651, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.24354243542435425, | |
| "grad_norm": 3.1566977500915527, | |
| "learning_rate": 1.9411764705882355e-05, | |
| "loss": 0.118, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.24477244772447723, | |
| "grad_norm": 4.118341445922852, | |
| "learning_rate": 1.950980392156863e-05, | |
| "loss": 0.1728, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.24600246002460024, | |
| "grad_norm": 4.250949859619141, | |
| "learning_rate": 1.9607843137254903e-05, | |
| "loss": 0.2299, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24723247232472326, | |
| "grad_norm": 4.084754943847656, | |
| "learning_rate": 1.9705882352941178e-05, | |
| "loss": 0.2342, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.24846248462484624, | |
| "grad_norm": 3.939434051513672, | |
| "learning_rate": 1.9803921568627454e-05, | |
| "loss": 0.2413, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.24969249692496925, | |
| "grad_norm": 3.9612276554107666, | |
| "learning_rate": 1.9901960784313726e-05, | |
| "loss": 0.168, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.25092250922509224, | |
| "grad_norm": 3.401622772216797, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1474, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.2521525215252153, | |
| "grad_norm": 3.2245850563049316, | |
| "learning_rate": 1.9998802517966852e-05, | |
| "loss": 0.1102, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.25338253382533826, | |
| "grad_norm": 4.254729270935059, | |
| "learning_rate": 1.9995210358660037e-05, | |
| "loss": 0.2326, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.25461254612546125, | |
| "grad_norm": 3.603159189224243, | |
| "learning_rate": 1.9989224382388813e-05, | |
| "loss": 0.1787, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.25584255842558423, | |
| "grad_norm": 3.434582471847534, | |
| "learning_rate": 1.9980846022772978e-05, | |
| "loss": 0.1423, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.2570725707257073, | |
| "grad_norm": 3.8560950756073, | |
| "learning_rate": 1.997007728639956e-05, | |
| "loss": 0.2069, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.25830258302583026, | |
| "grad_norm": 3.4417314529418945, | |
| "learning_rate": 1.9956920752342226e-05, | |
| "loss": 0.136, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.25830258302583026, | |
| "eval_loss": 0.10401736944913864, | |
| "eval_runtime": 54.8034, | |
| "eval_samples_per_second": 27.48, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8792920980078169, | |
| "eval_sts-test_pearson_dot": 0.8612401830255582, | |
| "eval_sts-test_pearson_euclidean": 0.9094380100842928, | |
| "eval_sts-test_pearson_manhattan": 0.9095661408662257, | |
| "eval_sts-test_pearson_max": 0.9095661408662257, | |
| "eval_sts-test_spearman_cosine": 0.905583034917972, | |
| "eval_sts-test_spearman_dot": 0.8658094563311378, | |
| "eval_sts-test_spearman_euclidean": 0.906560626223067, | |
| "eval_sts-test_spearman_manhattan": 0.906644400584392, | |
| "eval_sts-test_spearman_max": 0.906644400584392, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.25953259532595324, | |
| "grad_norm": 4.170388221740723, | |
| "learning_rate": 1.9941379571543597e-05, | |
| "loss": 0.2407, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.2607626076260763, | |
| "grad_norm": 4.218827247619629, | |
| "learning_rate": 1.9923457466060637e-05, | |
| "loss": 0.212, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.26199261992619927, | |
| "grad_norm": 3.6592209339141846, | |
| "learning_rate": 1.9903158728173206e-05, | |
| "loss": 0.1361, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.26322263222632225, | |
| "grad_norm": 4.208631992340088, | |
| "learning_rate": 1.9880488219356086e-05, | |
| "loss": 0.2356, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.2644526445264453, | |
| "grad_norm": 2.9232637882232666, | |
| "learning_rate": 1.9855451369114677e-05, | |
| "loss": 0.1059, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.2656826568265683, | |
| "grad_norm": 4.299160480499268, | |
| "learning_rate": 1.9828054173684646e-05, | |
| "loss": 0.2501, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.26691266912669126, | |
| "grad_norm": 4.013469219207764, | |
| "learning_rate": 1.9798303194595846e-05, | |
| "loss": 0.1817, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.26814268142681424, | |
| "grad_norm": 3.691553831100464, | |
| "learning_rate": 1.976620555710087e-05, | |
| "loss": 0.2022, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.2693726937269373, | |
| "grad_norm": 4.433103561401367, | |
| "learning_rate": 1.973176894846855e-05, | |
| "loss": 0.2235, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.27060270602706027, | |
| "grad_norm": 4.862768173217773, | |
| "learning_rate": 1.9695001616142916e-05, | |
| "loss": 0.2437, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.27183271832718325, | |
| "grad_norm": 3.9157614707946777, | |
| "learning_rate": 1.965591236576794e-05, | |
| "loss": 0.1859, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.2730627306273063, | |
| "grad_norm": 4.705247402191162, | |
| "learning_rate": 1.9614510559078626e-05, | |
| "loss": 0.2167, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.2742927429274293, | |
| "grad_norm": 3.890500068664551, | |
| "learning_rate": 1.95708061116589e-05, | |
| "loss": 0.1495, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.27552275522755226, | |
| "grad_norm": 4.393867492675781, | |
| "learning_rate": 1.9524809490566878e-05, | |
| "loss": 0.2876, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.2767527675276753, | |
| "grad_norm": 3.782416582107544, | |
| "learning_rate": 1.9476531711828027e-05, | |
| "loss": 0.1842, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2779827798277983, | |
| "grad_norm": 3.32236647605896, | |
| "learning_rate": 1.942598433779687e-05, | |
| "loss": 0.144, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.27921279212792127, | |
| "grad_norm": 3.9284870624542236, | |
| "learning_rate": 1.9373179474387858e-05, | |
| "loss": 0.1571, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.28044280442804426, | |
| "grad_norm": 3.847404956817627, | |
| "learning_rate": 1.9318129768176033e-05, | |
| "loss": 0.209, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.2816728167281673, | |
| "grad_norm": 4.21238899230957, | |
| "learning_rate": 1.926084840336821e-05, | |
| "loss": 0.2075, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.2829028290282903, | |
| "grad_norm": 4.167908191680908, | |
| "learning_rate": 1.9201349098645433e-05, | |
| "loss": 0.1722, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.28413284132841327, | |
| "grad_norm": 3.7701351642608643, | |
| "learning_rate": 1.9139646103877378e-05, | |
| "loss": 0.1464, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.28413284132841327, | |
| "eval_loss": 0.10392418503761292, | |
| "eval_runtime": 54.7341, | |
| "eval_samples_per_second": 27.515, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8822954324429473, | |
| "eval_sts-test_pearson_dot": 0.8642863367586305, | |
| "eval_sts-test_pearson_euclidean": 0.9122889538029727, | |
| "eval_sts-test_pearson_manhattan": 0.912099304650421, | |
| "eval_sts-test_pearson_max": 0.9122889538029727, | |
| "eval_sts-test_spearman_cosine": 0.9087387596175093, | |
| "eval_sts-test_spearman_dot": 0.8704923178256567, | |
| "eval_sts-test_spearman_euclidean": 0.9097842833373965, | |
| "eval_sts-test_spearman_manhattan": 0.9095372563745162, | |
| "eval_sts-test_spearman_max": 0.9097842833373965, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.2853628536285363, | |
| "grad_norm": 4.548703193664551, | |
| "learning_rate": 1.9075754196709574e-05, | |
| "loss": 0.2675, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.2865928659286593, | |
| "grad_norm": 5.041469573974609, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.2585, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.2878228782287823, | |
| "grad_norm": 3.0036237239837646, | |
| "learning_rate": 1.894146537327533e-05, | |
| "loss": 0.134, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.2890528905289053, | |
| "grad_norm": 3.6082603931427, | |
| "learning_rate": 1.8871100618699553e-05, | |
| "loss": 0.1765, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2902829028290283, | |
| "grad_norm": 3.8336241245269775, | |
| "learning_rate": 1.8798611267402745e-05, | |
| "loss": 0.1826, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.2915129151291513, | |
| "grad_norm": 4.307932376861572, | |
| "learning_rate": 1.872401468032406e-05, | |
| "loss": 0.222, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.29274292742927427, | |
| "grad_norm": 3.153963088989258, | |
| "learning_rate": 1.864732872307804e-05, | |
| "loss": 0.134, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.2939729397293973, | |
| "grad_norm": 4.044833660125732, | |
| "learning_rate": 1.8568571761675893e-05, | |
| "loss": 0.1902, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.2952029520295203, | |
| "grad_norm": 4.640310287475586, | |
| "learning_rate": 1.8487762658126872e-05, | |
| "loss": 0.2461, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2964329643296433, | |
| "grad_norm": 4.932340145111084, | |
| "learning_rate": 1.8404920765920898e-05, | |
| "loss": 0.3094, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.2976629766297663, | |
| "grad_norm": 4.0233917236328125, | |
| "learning_rate": 1.8320065925393468e-05, | |
| "loss": 0.2252, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.2988929889298893, | |
| "grad_norm": 4.369536399841309, | |
| "learning_rate": 1.8233218458973984e-05, | |
| "loss": 0.2466, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.3001230012300123, | |
| "grad_norm": 3.6295106410980225, | |
| "learning_rate": 1.814439916631857e-05, | |
| "loss": 0.139, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.3013530135301353, | |
| "grad_norm": 3.705105781555176, | |
| "learning_rate": 1.8053629319328662e-05, | |
| "loss": 0.154, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.3025830258302583, | |
| "grad_norm": 3.7480130195617676, | |
| "learning_rate": 1.796093065705644e-05, | |
| "loss": 0.1979, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.3038130381303813, | |
| "grad_norm": 2.5885541439056396, | |
| "learning_rate": 1.786632538049842e-05, | |
| "loss": 0.1121, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.3050430504305043, | |
| "grad_norm": 3.3691048622131348, | |
| "learning_rate": 1.7769836147278385e-05, | |
| "loss": 0.1361, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.3062730627306273, | |
| "grad_norm": 4.20883321762085, | |
| "learning_rate": 1.7671486066220965e-05, | |
| "loss": 0.2492, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.3075030750307503, | |
| "grad_norm": 3.8119523525238037, | |
| "learning_rate": 1.757129869181718e-05, | |
| "loss": 0.1903, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3087330873308733, | |
| "grad_norm": 4.464923858642578, | |
| "learning_rate": 1.746929801858317e-05, | |
| "loss": 0.2333, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.30996309963099633, | |
| "grad_norm": 4.029540061950684, | |
| "learning_rate": 1.736550847531366e-05, | |
| "loss": 0.1805, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.30996309963099633, | |
| "eval_loss": 0.10298814624547958, | |
| "eval_runtime": 54.69, | |
| "eval_samples_per_second": 27.537, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.881635556166377, | |
| "eval_sts-test_pearson_dot": 0.862389303076424, | |
| "eval_sts-test_pearson_euclidean": 0.9125260227425505, | |
| "eval_sts-test_pearson_manhattan": 0.9128421094636647, | |
| "eval_sts-test_pearson_max": 0.9128421094636647, | |
| "eval_sts-test_spearman_cosine": 0.9098964747497047, | |
| "eval_sts-test_spearman_dot": 0.8698043119330254, | |
| "eval_sts-test_spearman_euclidean": 0.9103645729438589, | |
| "eval_sts-test_spearman_manhattan": 0.9110424650514156, | |
| "eval_sts-test_spearman_max": 0.9110424650514156, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.3111931119311193, | |
| "grad_norm": 3.990410089492798, | |
| "learning_rate": 1.725995491923131e-05, | |
| "loss": 0.1929, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.3124231242312423, | |
| "grad_norm": 3.7284581661224365, | |
| "learning_rate": 1.7152662630033506e-05, | |
| "loss": 0.1424, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.31365313653136534, | |
| "grad_norm": 3.8791370391845703, | |
| "learning_rate": 1.7043657303837965e-05, | |
| "loss": 0.2318, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.3148831488314883, | |
| "grad_norm": 3.4804205894470215, | |
| "learning_rate": 1.693296504702862e-05, | |
| "loss": 0.1524, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.3161131611316113, | |
| "grad_norm": 3.573451519012451, | |
| "learning_rate": 1.682061237000322e-05, | |
| "loss": 0.2195, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.3173431734317343, | |
| "grad_norm": 3.5766184329986572, | |
| "learning_rate": 1.6706626180824185e-05, | |
| "loss": 0.1338, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.31857318573185733, | |
| "grad_norm": 4.488210201263428, | |
| "learning_rate": 1.659103377877423e-05, | |
| "loss": 0.2543, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.3198031980319803, | |
| "grad_norm": 4.0144147872924805, | |
| "learning_rate": 1.647386284781828e-05, | |
| "loss": 0.202, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3210332103321033, | |
| "grad_norm": 3.4031426906585693, | |
| "learning_rate": 1.6355141449973254e-05, | |
| "loss": 0.1489, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.32226322263222634, | |
| "grad_norm": 3.8359596729278564, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.1937, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.3234932349323493, | |
| "grad_norm": 4.457846641540527, | |
| "learning_rate": 1.6113161351530257e-05, | |
| "loss": 0.2334, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.3247232472324723, | |
| "grad_norm": 4.167722702026367, | |
| "learning_rate": 1.598996060429634e-05, | |
| "loss": 0.1942, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.32595325953259535, | |
| "grad_norm": 4.352579116821289, | |
| "learning_rate": 1.586532528302183e-05, | |
| "loss": 0.2013, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.32718327183271834, | |
| "grad_norm": 5.293665409088135, | |
| "learning_rate": 1.5739285237418323e-05, | |
| "loss": 0.2954, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.3284132841328413, | |
| "grad_norm": 3.7269585132598877, | |
| "learning_rate": 1.5611870653623826e-05, | |
| "loss": 0.188, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.3296432964329643, | |
| "grad_norm": 3.8485231399536133, | |
| "learning_rate": 1.548311204697331e-05, | |
| "loss": 0.1688, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.33087330873308735, | |
| "grad_norm": 3.183656692504883, | |
| "learning_rate": 1.5353040254690396e-05, | |
| "loss": 0.1415, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.33210332103321033, | |
| "grad_norm": 4.292448997497559, | |
| "learning_rate": 1.5221686428501929e-05, | |
| "loss": 0.2249, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 4.776716232299805, | |
| "learning_rate": 1.508908202717729e-05, | |
| "loss": 0.2606, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.33456334563345635, | |
| "grad_norm": 4.753313064575195, | |
| "learning_rate": 1.4955258808994093e-05, | |
| "loss": 0.2559, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.33579335793357934, | |
| "grad_norm": 4.271998882293701, | |
| "learning_rate": 1.482024882413222e-05, | |
| "loss": 0.2673, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.33579335793357934, | |
| "eval_loss": 0.10389706492424011, | |
| "eval_runtime": 54.7165, | |
| "eval_samples_per_second": 27.524, | |
| "eval_steps_per_second": 0.219, | |
| "eval_sts-test_pearson_cosine": 0.8802537579023317, | |
| "eval_sts-test_pearson_dot": 0.8611279643446735, | |
| "eval_sts-test_pearson_euclidean": 0.9104828974356078, | |
| "eval_sts-test_pearson_manhattan": 0.9112003024801107, | |
| "eval_sts-test_pearson_max": 0.9112003024801107, | |
| "eval_sts-test_spearman_cosine": 0.9077587069930375, | |
| "eval_sts-test_spearman_dot": 0.8683557106354935, | |
| "eval_sts-test_spearman_euclidean": 0.908703271867226, | |
| "eval_sts-test_spearman_manhattan": 0.9088831719380195, | |
| "eval_sts-test_spearman_max": 0.9088831719380195, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.3370233702337023, | |
| "grad_norm": 3.5790419578552246, | |
| "learning_rate": 1.4684084406997903e-05, | |
| "loss": 0.1618, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.33825338253382536, | |
| "grad_norm": 4.819033145904541, | |
| "learning_rate": 1.4546798168479756e-05, | |
| "loss": 0.2602, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.33948339483394835, | |
| "grad_norm": 4.567826747894287, | |
| "learning_rate": 1.4408422988138585e-05, | |
| "loss": 0.2339, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.34071340713407133, | |
| "grad_norm": 4.182609558105469, | |
| "learning_rate": 1.4268992006332847e-05, | |
| "loss": 0.1843, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.3419434194341943, | |
| "grad_norm": 3.4522156715393066, | |
| "learning_rate": 1.412853861628166e-05, | |
| "loss": 0.133, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.34317343173431736, | |
| "grad_norm": 4.6532301902771, | |
| "learning_rate": 1.3987096456067236e-05, | |
| "loss": 0.2345, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.34440344403444034, | |
| "grad_norm": 4.240933418273926, | |
| "learning_rate": 1.3844699400578696e-05, | |
| "loss": 0.2808, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3456334563345633, | |
| "grad_norm": 3.000117063522339, | |
| "learning_rate": 1.3701381553399144e-05, | |
| "loss": 0.1044, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.34686346863468637, | |
| "grad_norm": 3.7988216876983643, | |
| "learning_rate": 1.3557177238637987e-05, | |
| "loss": 0.1622, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.34809348093480935, | |
| "grad_norm": 3.2597107887268066, | |
| "learning_rate": 1.3412120992710425e-05, | |
| "loss": 0.1303, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.34932349323493234, | |
| "grad_norm": 3.2426445484161377, | |
| "learning_rate": 1.3266247556066122e-05, | |
| "loss": 0.1453, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.3505535055350554, | |
| "grad_norm": 4.482458114624023, | |
| "learning_rate": 1.3119591864868979e-05, | |
| "loss": 0.237, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.35178351783517836, | |
| "grad_norm": 4.062747478485107, | |
| "learning_rate": 1.2972189042630044e-05, | |
| "loss": 0.1726, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.35301353013530135, | |
| "grad_norm": 3.9885880947113037, | |
| "learning_rate": 1.2824074391795571e-05, | |
| "loss": 0.2195, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.35424354243542433, | |
| "grad_norm": 5.205960750579834, | |
| "learning_rate": 1.2675283385292212e-05, | |
| "loss": 0.3016, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.35547355473554737, | |
| "grad_norm": 3.2820823192596436, | |
| "learning_rate": 1.252585165803135e-05, | |
| "loss": 0.1626, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.35670356703567035, | |
| "grad_norm": 4.133265495300293, | |
| "learning_rate": 1.2375814998374714e-05, | |
| "loss": 0.1902, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.35793357933579334, | |
| "grad_norm": 3.349637746810913, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.1387, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.3591635916359164, | |
| "grad_norm": 2.7458724975585938, | |
| "learning_rate": 1.2074070751110753e-05, | |
| "loss": 0.1047, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.36039360393603936, | |
| "grad_norm": 3.7697091102600098, | |
| "learning_rate": 1.1922435430166372e-05, | |
| "loss": 0.1954, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.36162361623616235, | |
| "grad_norm": 4.1529622077941895, | |
| "learning_rate": 1.1770339692844484e-05, | |
| "loss": 0.2089, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.36162361623616235, | |
| "eval_loss": 0.10294178128242493, | |
| "eval_runtime": 54.5996, | |
| "eval_samples_per_second": 27.583, | |
| "eval_steps_per_second": 0.22, | |
| "eval_sts-test_pearson_cosine": 0.8803510241742277, | |
| "eval_sts-test_pearson_dot": 0.8614562911474479, | |
| "eval_sts-test_pearson_euclidean": 0.9105274765595701, | |
| "eval_sts-test_pearson_manhattan": 0.9112776803683604, | |
| "eval_sts-test_pearson_max": 0.9112776803683604, | |
| "eval_sts-test_spearman_cosine": 0.9082726304788564, | |
| "eval_sts-test_spearman_dot": 0.8687116203836315, | |
| "eval_sts-test_spearman_euclidean": 0.9088194013905367, | |
| "eval_sts-test_spearman_manhattan": 0.9091452800759889, | |
| "eval_sts-test_spearman_max": 0.9091452800759889, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.3628536285362854, | |
| "grad_norm": 3.3324942588806152, | |
| "learning_rate": 1.161781996552765e-05, | |
| "loss": 0.1485, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.3640836408364084, | |
| "grad_norm": 3.477254867553711, | |
| "learning_rate": 1.1464912776142494e-05, | |
| "loss": 0.1724, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.36531365313653136, | |
| "grad_norm": 3.933436393737793, | |
| "learning_rate": 1.1311654745411424e-05, | |
| "loss": 0.2017, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.36654366543665434, | |
| "grad_norm": 3.6212170124053955, | |
| "learning_rate": 1.115808257808209e-05, | |
| "loss": 0.1591, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.3677736777367774, | |
| "grad_norm": 4.0765700340271, | |
| "learning_rate": 1.1004233054136726e-05, | |
| "loss": 0.2396, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.36900369003690037, | |
| "grad_norm": 3.589646816253662, | |
| "learning_rate": 1.0850143019983475e-05, | |
| "loss": 0.1395, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.37023370233702335, | |
| "grad_norm": 3.7769243717193604, | |
| "learning_rate": 1.0695849379631816e-05, | |
| "loss": 0.1806, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.3714637146371464, | |
| "grad_norm": 3.4720847606658936, | |
| "learning_rate": 1.0541389085854177e-05, | |
| "loss": 0.1882, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.3726937269372694, | |
| "grad_norm": 2.9006810188293457, | |
| "learning_rate": 1.038679913133589e-05, | |
| "loss": 0.1188, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.37392373923739236, | |
| "grad_norm": 3.7660434246063232, | |
| "learning_rate": 1.023211653981556e-05, | |
| "loss": 0.1564, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.3751537515375154, | |
| "grad_norm": 5.082170486450195, | |
| "learning_rate": 1.0077378357218023e-05, | |
| "loss": 0.313, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.3763837638376384, | |
| "grad_norm": 3.5429434776306152, | |
| "learning_rate": 9.922621642781982e-06, | |
| "loss": 0.1455, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.37761377613776137, | |
| "grad_norm": 3.1348257064819336, | |
| "learning_rate": 9.767883460184447e-06, | |
| "loss": 0.1535, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.37884378843788435, | |
| "grad_norm": 2.881880521774292, | |
| "learning_rate": 9.613200868664112e-06, | |
| "loss": 0.099, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.3800738007380074, | |
| "grad_norm": 3.5104594230651855, | |
| "learning_rate": 9.458610914145826e-06, | |
| "loss": 0.1733, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.3813038130381304, | |
| "grad_norm": 3.9202194213867188, | |
| "learning_rate": 9.304150620368189e-06, | |
| "loss": 0.1891, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.38253382533825336, | |
| "grad_norm": 3.655240297317505, | |
| "learning_rate": 9.149856980016529e-06, | |
| "loss": 0.2128, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.3837638376383764, | |
| "grad_norm": 3.766303062438965, | |
| "learning_rate": 8.995766945863278e-06, | |
| "loss": 0.2042, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.3849938499384994, | |
| "grad_norm": 3.8122780323028564, | |
| "learning_rate": 8.841917421917913e-06, | |
| "loss": 0.203, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.3862238622386224, | |
| "grad_norm": 4.085626602172852, | |
| "learning_rate": 8.688345254588579e-06, | |
| "loss": 0.2249, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.3874538745387454, | |
| "grad_norm": 3.744234323501587, | |
| "learning_rate": 8.53508722385751e-06, | |
| "loss": 0.1597, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3874538745387454, | |
| "eval_loss": 0.10140395164489746, | |
| "eval_runtime": 54.6293, | |
| "eval_samples_per_second": 27.568, | |
| "eval_steps_per_second": 0.22, | |
| "eval_sts-test_pearson_cosine": 0.8788980244871143, | |
| "eval_sts-test_pearson_dot": 0.8616979928109831, | |
| "eval_sts-test_pearson_euclidean": 0.9090675882181183, | |
| "eval_sts-test_pearson_manhattan": 0.909351159725011, | |
| "eval_sts-test_pearson_max": 0.909351159725011, | |
| "eval_sts-test_spearman_cosine": 0.9074493862743003, | |
| "eval_sts-test_spearman_dot": 0.8701774479505067, | |
| "eval_sts-test_spearman_euclidean": 0.9075559837789346, | |
| "eval_sts-test_spearman_manhattan": 0.9076191725600193, | |
| "eval_sts-test_spearman_max": 0.9076191725600193, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3886838868388684, | |
| "grad_norm": 3.4346373081207275, | |
| "learning_rate": 8.382180034472353e-06, | |
| "loss": 0.1358, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.3899138991389914, | |
| "grad_norm": 3.872002124786377, | |
| "learning_rate": 8.229660307155518e-06, | |
| "loss": 0.207, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.39114391143911437, | |
| "grad_norm": 3.4921915531158447, | |
| "learning_rate": 8.077564569833633e-06, | |
| "loss": 0.193, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.3923739237392374, | |
| "grad_norm": 3.2774128913879395, | |
| "learning_rate": 7.92592924888925e-06, | |
| "loss": 0.1141, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.3936039360393604, | |
| "grad_norm": 4.900540351867676, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.2835, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3948339483394834, | |
| "grad_norm": 4.073228359222412, | |
| "learning_rate": 7.6241850016252915e-06, | |
| "loss": 0.2589, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.3960639606396064, | |
| "grad_norm": 2.549339532852173, | |
| "learning_rate": 7.4741483419686475e-06, | |
| "loss": 0.088, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.3972939729397294, | |
| "grad_norm": 4.411525726318359, | |
| "learning_rate": 7.324716614707792e-06, | |
| "loss": 0.1675, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.3985239852398524, | |
| "grad_norm": 3.336052656173706, | |
| "learning_rate": 7.175925608204428e-06, | |
| "loss": 0.1525, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.3997539975399754, | |
| "grad_norm": 3.2689311504364014, | |
| "learning_rate": 7.0278109573699574e-06, | |
| "loss": 0.1401, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.4009840098400984, | |
| "grad_norm": 3.8623855113983154, | |
| "learning_rate": 6.880408135131022e-06, | |
| "loss": 0.2109, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.4022140221402214, | |
| "grad_norm": 3.1453464031219482, | |
| "learning_rate": 6.733752443933879e-06, | |
| "loss": 0.1382, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.4034440344403444, | |
| "grad_norm": 3.09243106842041, | |
| "learning_rate": 6.587879007289576e-06, | |
| "loss": 0.1724, | |
| "step": 328 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 813, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 82, | |
| "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 | |
| } | |