| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1008610086100861, | |
| "eval_steps": 21, | |
| "global_step": 82, | |
| "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 | |
| } | |
| ], | |
| "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 | |
| } | |