| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4126984126984127, | |
| "eval_steps": 5, | |
| "global_step": 52, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007936507936507936, | |
| "grad_norm": 3.5297670364379883, | |
| "learning_rate": 5.555555555555555e-07, | |
| "loss": 0.404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015873015873015872, | |
| "grad_norm": 3.6838796138763428, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.3185, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.023809523809523808, | |
| "grad_norm": 3.5556721687316895, | |
| "learning_rate": 1.6666666666666665e-06, | |
| "loss": 0.2821, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.031746031746031744, | |
| "grad_norm": 3.922109842300415, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.4036, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03968253968253968, | |
| "grad_norm": 3.9366657733917236, | |
| "learning_rate": 2.7777777777777775e-06, | |
| "loss": 0.3442, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03968253968253968, | |
| "eval_loss": 0.12529698014259338, | |
| "eval_runtime": 113.8002, | |
| "eval_samples_per_second": 26.819, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.886081184413048, | |
| "eval_sts-test_pearson_dot": 0.8767533438290611, | |
| "eval_sts-test_pearson_euclidean": 0.9080817963557108, | |
| "eval_sts-test_pearson_manhattan": 0.9087794191320873, | |
| "eval_sts-test_pearson_max": 0.9087794191320873, | |
| "eval_sts-test_spearman_cosine": 0.9077787555581409, | |
| "eval_sts-test_spearman_dot": 0.8792746633711961, | |
| "eval_sts-test_spearman_euclidean": 0.9039925750881216, | |
| "eval_sts-test_spearman_manhattan": 0.904489537845873, | |
| "eval_sts-test_spearman_max": 0.9077787555581409, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 3.8135547637939453, | |
| "learning_rate": 3.333333333333333e-06, | |
| "loss": 0.4145, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 4.132374286651611, | |
| "learning_rate": 3.888888888888889e-06, | |
| "loss": 0.4224, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 3.9953386783599854, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.4048, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 4.023675918579102, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 0.3899, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07936507936507936, | |
| "grad_norm": 3.854191780090332, | |
| "learning_rate": 5.555555555555555e-06, | |
| "loss": 0.4127, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07936507936507936, | |
| "eval_loss": 0.12369368970394135, | |
| "eval_runtime": 113.6707, | |
| "eval_samples_per_second": 26.849, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8860118050647048, | |
| "eval_sts-test_pearson_dot": 0.8760605933678182, | |
| "eval_sts-test_pearson_euclidean": 0.9086480781293332, | |
| "eval_sts-test_pearson_manhattan": 0.9092897840847158, | |
| "eval_sts-test_pearson_max": 0.9092897840847158, | |
| "eval_sts-test_spearman_cosine": 0.9078577415344969, | |
| "eval_sts-test_spearman_dot": 0.8791339654053815, | |
| "eval_sts-test_spearman_euclidean": 0.9047648028546915, | |
| "eval_sts-test_spearman_manhattan": 0.9052383607027356, | |
| "eval_sts-test_spearman_max": 0.9078577415344969, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0873015873015873, | |
| "grad_norm": 3.8079540729522705, | |
| "learning_rate": 6.11111111111111e-06, | |
| "loss": 0.3496, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 3.929018259048462, | |
| "learning_rate": 6.666666666666666e-06, | |
| "loss": 0.3731, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10317460317460317, | |
| "grad_norm": 4.284013271331787, | |
| "learning_rate": 7.222222222222221e-06, | |
| "loss": 0.3929, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 3.3490402698516846, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.2957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11904761904761904, | |
| "grad_norm": 3.553280830383301, | |
| "learning_rate": 8.333333333333332e-06, | |
| "loss": 0.3324, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11904761904761904, | |
| "eval_loss": 0.12056715041399002, | |
| "eval_runtime": 113.718, | |
| "eval_samples_per_second": 26.838, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8856265458568289, | |
| "eval_sts-test_pearson_dot": 0.8743050518330721, | |
| "eval_sts-test_pearson_euclidean": 0.9095228583162331, | |
| "eval_sts-test_pearson_manhattan": 0.9101600217218586, | |
| "eval_sts-test_pearson_max": 0.9101600217218586, | |
| "eval_sts-test_spearman_cosine": 0.908261263658463, | |
| "eval_sts-test_spearman_dot": 0.87867141636764, | |
| "eval_sts-test_spearman_euclidean": 0.9060734192402989, | |
| "eval_sts-test_spearman_manhattan": 0.9066336155303966, | |
| "eval_sts-test_spearman_max": 0.908261263658463, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 3.6310322284698486, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.3341, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1349206349206349, | |
| "grad_norm": 3.6535122394561768, | |
| "learning_rate": 9.444444444444443e-06, | |
| "loss": 0.3466, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 3.6199331283569336, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.3558, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15079365079365079, | |
| "grad_norm": 3.089895248413086, | |
| "learning_rate": 1.0555555555555554e-05, | |
| "loss": 0.2634, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": 3.320916175842285, | |
| "learning_rate": 1.111111111111111e-05, | |
| "loss": 0.3095, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "eval_loss": 0.11563990265130997, | |
| "eval_runtime": 113.5377, | |
| "eval_samples_per_second": 26.881, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8848740042612456, | |
| "eval_sts-test_pearson_dot": 0.8724689429546052, | |
| "eval_sts-test_pearson_euclidean": 0.9104294765782397, | |
| "eval_sts-test_pearson_manhattan": 0.9111381492292419, | |
| "eval_sts-test_pearson_max": 0.9111381492292419, | |
| "eval_sts-test_spearman_cosine": 0.9087803335393421, | |
| "eval_sts-test_spearman_dot": 0.8777188410176626, | |
| "eval_sts-test_spearman_euclidean": 0.9069791847708608, | |
| "eval_sts-test_spearman_manhattan": 0.9078148698260838, | |
| "eval_sts-test_spearman_max": 0.9087803335393421, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 3.0193159580230713, | |
| "learning_rate": 1.1666666666666665e-05, | |
| "loss": 0.2973, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1746031746031746, | |
| "grad_norm": 3.3553476333618164, | |
| "learning_rate": 1.222222222222222e-05, | |
| "loss": 0.2884, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18253968253968253, | |
| "grad_norm": 3.5176496505737305, | |
| "learning_rate": 1.2777777777777775e-05, | |
| "loss": 0.3697, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 3.2073943614959717, | |
| "learning_rate": 1.3333333333333332e-05, | |
| "loss": 0.2683, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1984126984126984, | |
| "grad_norm": 3.2101964950561523, | |
| "learning_rate": 1.3888888888888886e-05, | |
| "loss": 0.3026, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1984126984126984, | |
| "eval_loss": 0.10958973318338394, | |
| "eval_runtime": 113.6214, | |
| "eval_samples_per_second": 26.861, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8832622086480311, | |
| "eval_sts-test_pearson_dot": 0.8697582354953435, | |
| "eval_sts-test_pearson_euclidean": 0.9107566690862425, | |
| "eval_sts-test_pearson_manhattan": 0.9115546986654615, | |
| "eval_sts-test_pearson_max": 0.9115546986654615, | |
| "eval_sts-test_spearman_cosine": 0.9087605087305455, | |
| "eval_sts-test_spearman_dot": 0.8760767382321666, | |
| "eval_sts-test_spearman_euclidean": 0.9073999361304628, | |
| "eval_sts-test_spearman_manhattan": 0.9084107328715103, | |
| "eval_sts-test_spearman_max": 0.9087605087305455, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20634920634920634, | |
| "grad_norm": 2.84037709236145, | |
| "learning_rate": 1.4444444444444442e-05, | |
| "loss": 0.2441, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 3.3099992275238037, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.3145, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 3.061953067779541, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.3119, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23015873015873015, | |
| "grad_norm": 3.0163729190826416, | |
| "learning_rate": 1.6111111111111108e-05, | |
| "loss": 0.2766, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 3.140418291091919, | |
| "learning_rate": 1.6666666666666664e-05, | |
| "loss": 0.3343, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "eval_loss": 0.10535401105880737, | |
| "eval_runtime": 113.5942, | |
| "eval_samples_per_second": 26.868, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8819465403802665, | |
| "eval_sts-test_pearson_dot": 0.866997957398371, | |
| "eval_sts-test_pearson_euclidean": 0.9110501477101954, | |
| "eval_sts-test_pearson_manhattan": 0.9119047974126511, | |
| "eval_sts-test_pearson_max": 0.9119047974126511, | |
| "eval_sts-test_spearman_cosine": 0.9084358383291508, | |
| "eval_sts-test_spearman_dot": 0.8727757956894143, | |
| "eval_sts-test_spearman_euclidean": 0.9077817538926543, | |
| "eval_sts-test_spearman_manhattan": 0.9089103807049453, | |
| "eval_sts-test_spearman_max": 0.9089103807049453, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24603174603174602, | |
| "grad_norm": 3.1329221725463867, | |
| "learning_rate": 1.722222222222222e-05, | |
| "loss": 0.344, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 2.9861748218536377, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 0.3005, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2619047619047619, | |
| "grad_norm": 2.8316733837127686, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.2526, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2698412698412698, | |
| "grad_norm": 2.8335487842559814, | |
| "learning_rate": 1.8888888888888886e-05, | |
| "loss": 0.2422, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 3.0785422325134277, | |
| "learning_rate": 1.9444444444444442e-05, | |
| "loss": 0.3447, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "eval_loss": 0.10223711282014847, | |
| "eval_runtime": 113.9847, | |
| "eval_samples_per_second": 26.776, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8812001280334643, | |
| "eval_sts-test_pearson_dot": 0.8652746969985129, | |
| "eval_sts-test_pearson_euclidean": 0.9105701789873448, | |
| "eval_sts-test_pearson_manhattan": 0.9116177887236803, | |
| "eval_sts-test_pearson_max": 0.9116177887236803, | |
| "eval_sts-test_spearman_cosine": 0.9072243769320245, | |
| "eval_sts-test_spearman_dot": 0.8716048789351082, | |
| "eval_sts-test_spearman_euclidean": 0.9073166540330135, | |
| "eval_sts-test_spearman_manhattan": 0.9081332302996223, | |
| "eval_sts-test_spearman_max": 0.9081332302996223, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 2.944396734237671, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.2809, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.29365079365079366, | |
| "grad_norm": 2.8323400020599365, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 0.2836, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.30158730158730157, | |
| "grad_norm": 2.8760273456573486, | |
| "learning_rate": 2.1111111111111107e-05, | |
| "loss": 0.2878, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.30952380952380953, | |
| "grad_norm": 2.744379758834839, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.2738, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 2.8519983291625977, | |
| "learning_rate": 2.222222222222222e-05, | |
| "loss": 0.2806, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "eval_loss": 0.10033170133829117, | |
| "eval_runtime": 113.5147, | |
| "eval_samples_per_second": 26.886, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8802115569848467, | |
| "eval_sts-test_pearson_dot": 0.8634798448575132, | |
| "eval_sts-test_pearson_euclidean": 0.9094188438238102, | |
| "eval_sts-test_pearson_manhattan": 0.9105849471172345, | |
| "eval_sts-test_pearson_max": 0.9105849471172345, | |
| "eval_sts-test_spearman_cosine": 0.9064710789490229, | |
| "eval_sts-test_spearman_dot": 0.8693704037025742, | |
| "eval_sts-test_spearman_euclidean": 0.9064271779615981, | |
| "eval_sts-test_spearman_manhattan": 0.9073247092600637, | |
| "eval_sts-test_spearman_max": 0.9073247092600637, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3253968253968254, | |
| "grad_norm": 2.9139747619628906, | |
| "learning_rate": 2.2777777777777776e-05, | |
| "loss": 0.2797, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 2.9206557273864746, | |
| "learning_rate": 2.333333333333333e-05, | |
| "loss": 0.3217, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3412698412698413, | |
| "grad_norm": 2.755398988723755, | |
| "learning_rate": 2.388888888888889e-05, | |
| "loss": 0.2544, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3492063492063492, | |
| "grad_norm": 3.0441982746124268, | |
| "learning_rate": 2.444444444444444e-05, | |
| "loss": 0.3203, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 2.978891611099243, | |
| "learning_rate": 2.4999999999999998e-05, | |
| "loss": 0.2987, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "eval_loss": 0.09902294725179672, | |
| "eval_runtime": 113.6912, | |
| "eval_samples_per_second": 26.845, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8796209948380269, | |
| "eval_sts-test_pearson_dot": 0.8617122615494917, | |
| "eval_sts-test_pearson_euclidean": 0.9092272396432914, | |
| "eval_sts-test_pearson_manhattan": 0.9100341993020892, | |
| "eval_sts-test_pearson_max": 0.9100341993020892, | |
| "eval_sts-test_spearman_cosine": 0.9063911531961779, | |
| "eval_sts-test_spearman_dot": 0.867835166929281, | |
| "eval_sts-test_spearman_euclidean": 0.9066020658911155, | |
| "eval_sts-test_spearman_manhattan": 0.9072894005148261, | |
| "eval_sts-test_spearman_max": 0.9072894005148261, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.36507936507936506, | |
| "grad_norm": 2.9183595180511475, | |
| "learning_rate": 2.555555555555555e-05, | |
| "loss": 0.2765, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.373015873015873, | |
| "grad_norm": 2.960238456726074, | |
| "learning_rate": 2.611111111111111e-05, | |
| "loss": 0.2716, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 3.23356294631958, | |
| "learning_rate": 2.6666666666666663e-05, | |
| "loss": 0.3726, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 2.974705457687378, | |
| "learning_rate": 2.722222222222222e-05, | |
| "loss": 0.2963, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3968253968253968, | |
| "grad_norm": 2.8041574954986572, | |
| "learning_rate": 2.7777777777777772e-05, | |
| "loss": 0.2784, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3968253968253968, | |
| "eval_loss": 0.09521521627902985, | |
| "eval_runtime": 113.6139, | |
| "eval_samples_per_second": 26.863, | |
| "eval_steps_per_second": 0.211, | |
| "eval_sts-test_pearson_cosine": 0.8802451373465323, | |
| "eval_sts-test_pearson_dot": 0.8609764645232105, | |
| "eval_sts-test_pearson_euclidean": 0.9103012041260427, | |
| "eval_sts-test_pearson_manhattan": 0.9108880877390901, | |
| "eval_sts-test_pearson_max": 0.9108880877390901, | |
| "eval_sts-test_spearman_cosine": 0.9071928272927434, | |
| "eval_sts-test_spearman_dot": 0.867374407941995, | |
| "eval_sts-test_spearman_euclidean": 0.9083242734345022, | |
| "eval_sts-test_spearman_manhattan": 0.9086424996542565, | |
| "eval_sts-test_spearman_max": 0.9086424996542565, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.40476190476190477, | |
| "grad_norm": 2.6451456546783447, | |
| "learning_rate": 2.8333333333333332e-05, | |
| "loss": 0.2437, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4126984126984127, | |
| "grad_norm": 2.7020044326782227, | |
| "learning_rate": 2.8888888888888885e-05, | |
| "loss": 0.2258, | |
| "step": 52 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 252, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 26, | |
| "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": 960, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |