| { | |
| "best_metric": 1.3132938146591187, | |
| "best_model_checkpoint": "WinKawaks/vit-tiny-patch16-224/checkpoint-319", | |
| "epoch": 25.0, | |
| "eval_steps": 500, | |
| "global_step": 725, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 50.05537033081055, | |
| "learning_rate": 2.7397260273972604e-06, | |
| "loss": 2.392, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 21.303316116333008, | |
| "learning_rate": 5.479452054794521e-06, | |
| "loss": 1.993, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 29.138675689697266, | |
| "learning_rate": 8.21917808219178e-06, | |
| "loss": 1.9911, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 24.99004364013672, | |
| "learning_rate": 1.0958904109589042e-05, | |
| "loss": 2.1828, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 29.86865234375, | |
| "learning_rate": 1.3698630136986302e-05, | |
| "loss": 1.8818, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 33.12383270263672, | |
| "learning_rate": 1.643835616438356e-05, | |
| "loss": 2.0859, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 25.435964584350586, | |
| "learning_rate": 1.9178082191780822e-05, | |
| "loss": 2.0565, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 21.697423934936523, | |
| "learning_rate": 2.1917808219178083e-05, | |
| "loss": 1.9561, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 21.292062759399414, | |
| "learning_rate": 2.4657534246575342e-05, | |
| "loss": 1.8509, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 25.63444709777832, | |
| "learning_rate": 2.7397260273972603e-05, | |
| "loss": 1.9259, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7586206896551724, | |
| "grad_norm": 12.96942138671875, | |
| "learning_rate": 3.0136986301369862e-05, | |
| "loss": 1.8952, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 13.86652660369873, | |
| "learning_rate": 3.287671232876712e-05, | |
| "loss": 1.9227, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 28.36823081970215, | |
| "learning_rate": 3.561643835616438e-05, | |
| "loss": 1.8958, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 18.257474899291992, | |
| "learning_rate": 3.8356164383561644e-05, | |
| "loss": 1.9719, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2196969696969697, | |
| "eval_f1_macro": 0.09493363779078065, | |
| "eval_f1_micro": 0.2196969696969697, | |
| "eval_f1_weighted": 0.11546937910574274, | |
| "eval_loss": 1.9209331274032593, | |
| "eval_precision_macro": 0.08906952611553096, | |
| "eval_precision_micro": 0.2196969696969697, | |
| "eval_precision_weighted": 0.10509758602978943, | |
| "eval_recall_macro": 0.17224489795918368, | |
| "eval_recall_micro": 0.2196969696969697, | |
| "eval_recall_weighted": 0.2196969696969697, | |
| "eval_runtime": 2.2105, | |
| "eval_samples_per_second": 59.716, | |
| "eval_steps_per_second": 7.691, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 28.444780349731445, | |
| "learning_rate": 4.1095890410958905e-05, | |
| "loss": 1.8292, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 16.733516693115234, | |
| "learning_rate": 4.383561643835617e-05, | |
| "loss": 1.8189, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1724137931034484, | |
| "grad_norm": 16.255664825439453, | |
| "learning_rate": 4.657534246575342e-05, | |
| "loss": 1.8846, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2413793103448276, | |
| "grad_norm": 15.87771987915039, | |
| "learning_rate": 4.9315068493150684e-05, | |
| "loss": 1.9816, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3103448275862069, | |
| "grad_norm": 20.748777389526367, | |
| "learning_rate": 5.2054794520547945e-05, | |
| "loss": 1.8633, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 23.478870391845703, | |
| "learning_rate": 5.479452054794521e-05, | |
| "loss": 1.9196, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4482758620689655, | |
| "grad_norm": 14.190969467163086, | |
| "learning_rate": 5.753424657534247e-05, | |
| "loss": 1.8152, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5172413793103448, | |
| "grad_norm": 27.225452423095703, | |
| "learning_rate": 6.0273972602739724e-05, | |
| "loss": 1.879, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5862068965517242, | |
| "grad_norm": 16.791467666625977, | |
| "learning_rate": 6.301369863013699e-05, | |
| "loss": 1.851, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6551724137931034, | |
| "grad_norm": 17.566041946411133, | |
| "learning_rate": 6.575342465753424e-05, | |
| "loss": 1.8164, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 24.76405906677246, | |
| "learning_rate": 6.84931506849315e-05, | |
| "loss": 2.1271, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.793103448275862, | |
| "grad_norm": 21.847782135009766, | |
| "learning_rate": 7.123287671232876e-05, | |
| "loss": 1.7536, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.8620689655172413, | |
| "grad_norm": 19.893037796020508, | |
| "learning_rate": 7.397260273972603e-05, | |
| "loss": 1.7816, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9310344827586206, | |
| "grad_norm": 14.866455078125, | |
| "learning_rate": 7.671232876712329e-05, | |
| "loss": 1.5881, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 20.373685836791992, | |
| "learning_rate": 7.945205479452055e-05, | |
| "loss": 1.8717, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.19696969696969696, | |
| "eval_f1_macro": 0.09534116676973821, | |
| "eval_f1_micro": 0.19696969696969696, | |
| "eval_f1_weighted": 0.10689689098780009, | |
| "eval_loss": 2.0377984046936035, | |
| "eval_precision_macro": 0.19963369963369962, | |
| "eval_precision_micro": 0.19696969696969696, | |
| "eval_precision_weighted": 0.266025641025641, | |
| "eval_recall_macro": 0.17944066515495088, | |
| "eval_recall_micro": 0.19696969696969696, | |
| "eval_recall_weighted": 0.19696969696969696, | |
| "eval_runtime": 2.1913, | |
| "eval_samples_per_second": 60.238, | |
| "eval_steps_per_second": 7.758, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0689655172413794, | |
| "grad_norm": 21.545093536376953, | |
| "learning_rate": 8.219178082191781e-05, | |
| "loss": 1.752, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.1379310344827585, | |
| "grad_norm": 15.046628952026367, | |
| "learning_rate": 8.493150684931507e-05, | |
| "loss": 1.7137, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.206896551724138, | |
| "grad_norm": 21.083383560180664, | |
| "learning_rate": 8.767123287671233e-05, | |
| "loss": 1.7003, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.2758620689655173, | |
| "grad_norm": 37.4631462097168, | |
| "learning_rate": 9.041095890410958e-05, | |
| "loss": 1.9736, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.344827586206897, | |
| "grad_norm": 19.171171188354492, | |
| "learning_rate": 9.315068493150684e-05, | |
| "loss": 1.7332, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.413793103448276, | |
| "grad_norm": 16.743974685668945, | |
| "learning_rate": 9.58904109589041e-05, | |
| "loss": 1.819, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.4827586206896552, | |
| "grad_norm": 20.756649017333984, | |
| "learning_rate": 9.863013698630137e-05, | |
| "loss": 1.9201, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.5517241379310347, | |
| "grad_norm": 17.703954696655273, | |
| "learning_rate": 9.984662576687117e-05, | |
| "loss": 1.6147, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.6206896551724137, | |
| "grad_norm": 32.903743743896484, | |
| "learning_rate": 9.95398773006135e-05, | |
| "loss": 2.0663, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.689655172413793, | |
| "grad_norm": 23.617671966552734, | |
| "learning_rate": 9.923312883435584e-05, | |
| "loss": 1.9193, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 30.0602970123291, | |
| "learning_rate": 9.892638036809816e-05, | |
| "loss": 1.7659, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.8275862068965516, | |
| "grad_norm": 22.806859970092773, | |
| "learning_rate": 9.861963190184049e-05, | |
| "loss": 1.4494, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.896551724137931, | |
| "grad_norm": 16.40064811706543, | |
| "learning_rate": 9.831288343558283e-05, | |
| "loss": 1.6664, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.9655172413793105, | |
| "grad_norm": 24.703716278076172, | |
| "learning_rate": 9.800613496932515e-05, | |
| "loss": 1.9326, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3939393939393939, | |
| "eval_f1_macro": 0.2290203682353352, | |
| "eval_f1_micro": 0.3939393939393939, | |
| "eval_f1_weighted": 0.2938602829468567, | |
| "eval_loss": 1.7679647207260132, | |
| "eval_precision_macro": 0.21510735641170425, | |
| "eval_precision_micro": 0.3939393939393939, | |
| "eval_precision_weighted": 0.268160089800406, | |
| "eval_recall_macro": 0.30038548752834465, | |
| "eval_recall_micro": 0.3939393939393939, | |
| "eval_recall_weighted": 0.3939393939393939, | |
| "eval_runtime": 2.411, | |
| "eval_samples_per_second": 54.749, | |
| "eval_steps_per_second": 7.051, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0344827586206895, | |
| "grad_norm": 34.48782730102539, | |
| "learning_rate": 9.76993865030675e-05, | |
| "loss": 1.9289, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.103448275862069, | |
| "grad_norm": 20.898527145385742, | |
| "learning_rate": 9.739263803680982e-05, | |
| "loss": 1.5641, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.1724137931034484, | |
| "grad_norm": 20.089338302612305, | |
| "learning_rate": 9.708588957055215e-05, | |
| "loss": 1.6451, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.2413793103448274, | |
| "grad_norm": 21.63447380065918, | |
| "learning_rate": 9.677914110429448e-05, | |
| "loss": 1.5942, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.310344827586207, | |
| "grad_norm": 18.611299514770508, | |
| "learning_rate": 9.647239263803681e-05, | |
| "loss": 1.4619, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.3793103448275863, | |
| "grad_norm": 14.333738327026367, | |
| "learning_rate": 9.616564417177915e-05, | |
| "loss": 1.6001, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "grad_norm": 16.133724212646484, | |
| "learning_rate": 9.585889570552147e-05, | |
| "loss": 1.3741, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.5172413793103448, | |
| "grad_norm": 29.28097915649414, | |
| "learning_rate": 9.555214723926381e-05, | |
| "loss": 1.6927, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.586206896551724, | |
| "grad_norm": 17.335416793823242, | |
| "learning_rate": 9.524539877300614e-05, | |
| "loss": 1.1759, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.655172413793103, | |
| "grad_norm": 25.239665985107422, | |
| "learning_rate": 9.493865030674846e-05, | |
| "loss": 1.4696, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.7241379310344827, | |
| "grad_norm": 19.4155330657959, | |
| "learning_rate": 9.46319018404908e-05, | |
| "loss": 1.0003, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.793103448275862, | |
| "grad_norm": 20.292905807495117, | |
| "learning_rate": 9.432515337423313e-05, | |
| "loss": 1.3851, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.862068965517241, | |
| "grad_norm": 31.247602462768555, | |
| "learning_rate": 9.401840490797547e-05, | |
| "loss": 1.6519, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.9310344827586206, | |
| "grad_norm": 25.56925392150879, | |
| "learning_rate": 9.37116564417178e-05, | |
| "loss": 1.4111, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 23.311908721923828, | |
| "learning_rate": 9.340490797546013e-05, | |
| "loss": 1.2873, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.44696969696969696, | |
| "eval_f1_macro": 0.35023855102631046, | |
| "eval_f1_micro": 0.44696969696969696, | |
| "eval_f1_weighted": 0.40824342918240536, | |
| "eval_loss": 1.5892395973205566, | |
| "eval_precision_macro": 0.4831240188383045, | |
| "eval_precision_micro": 0.44696969696969696, | |
| "eval_precision_weighted": 0.513986013986014, | |
| "eval_recall_macro": 0.36461829176114885, | |
| "eval_recall_micro": 0.44696969696969696, | |
| "eval_recall_weighted": 0.44696969696969696, | |
| "eval_runtime": 2.1869, | |
| "eval_samples_per_second": 60.359, | |
| "eval_steps_per_second": 7.774, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.068965517241379, | |
| "grad_norm": 31.80891227722168, | |
| "learning_rate": 9.309815950920246e-05, | |
| "loss": 1.2896, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.137931034482759, | |
| "grad_norm": 22.716781616210938, | |
| "learning_rate": 9.279141104294478e-05, | |
| "loss": 1.2486, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.206896551724138, | |
| "grad_norm": 23.80237579345703, | |
| "learning_rate": 9.248466257668712e-05, | |
| "loss": 1.3835, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.275862068965517, | |
| "grad_norm": 18.24744987487793, | |
| "learning_rate": 9.217791411042945e-05, | |
| "loss": 0.9575, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.344827586206897, | |
| "grad_norm": 22.790117263793945, | |
| "learning_rate": 9.187116564417179e-05, | |
| "loss": 1.3711, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.413793103448276, | |
| "grad_norm": 15.804698944091797, | |
| "learning_rate": 9.156441717791411e-05, | |
| "loss": 1.4226, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.482758620689655, | |
| "grad_norm": 30.167261123657227, | |
| "learning_rate": 9.125766871165644e-05, | |
| "loss": 1.7736, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.551724137931035, | |
| "grad_norm": 15.975086212158203, | |
| "learning_rate": 9.095092024539878e-05, | |
| "loss": 1.4395, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.620689655172414, | |
| "grad_norm": 23.406415939331055, | |
| "learning_rate": 9.06441717791411e-05, | |
| "loss": 1.6491, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.689655172413794, | |
| "grad_norm": 30.07583236694336, | |
| "learning_rate": 9.033742331288344e-05, | |
| "loss": 1.747, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.758620689655173, | |
| "grad_norm": 20.77846336364746, | |
| "learning_rate": 9.003067484662577e-05, | |
| "loss": 1.6648, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 4.827586206896552, | |
| "grad_norm": 11.187516212463379, | |
| "learning_rate": 8.972392638036811e-05, | |
| "loss": 1.1932, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.896551724137931, | |
| "grad_norm": 15.845014572143555, | |
| "learning_rate": 8.941717791411043e-05, | |
| "loss": 1.4271, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 4.9655172413793105, | |
| "grad_norm": 15.977095603942871, | |
| "learning_rate": 8.911042944785276e-05, | |
| "loss": 1.3997, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.34814087704047136, | |
| "eval_f1_micro": 0.5, | |
| "eval_f1_weighted": 0.4244756131292643, | |
| "eval_loss": 1.4773013591766357, | |
| "eval_precision_macro": 0.34626430480089015, | |
| "eval_precision_micro": 0.5, | |
| "eval_precision_weighted": 0.41194737757930666, | |
| "eval_recall_macro": 0.4051700680272109, | |
| "eval_recall_micro": 0.5, | |
| "eval_recall_weighted": 0.5, | |
| "eval_runtime": 2.2186, | |
| "eval_samples_per_second": 59.497, | |
| "eval_steps_per_second": 7.662, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.0344827586206895, | |
| "grad_norm": 18.65735626220703, | |
| "learning_rate": 8.88036809815951e-05, | |
| "loss": 1.6883, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 5.103448275862069, | |
| "grad_norm": 18.897695541381836, | |
| "learning_rate": 8.849693251533742e-05, | |
| "loss": 1.3035, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 5.172413793103448, | |
| "grad_norm": 20.19015884399414, | |
| "learning_rate": 8.819018404907976e-05, | |
| "loss": 1.1881, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.241379310344827, | |
| "grad_norm": 18.574827194213867, | |
| "learning_rate": 8.788343558282209e-05, | |
| "loss": 1.0471, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 5.310344827586207, | |
| "grad_norm": 15.6314115524292, | |
| "learning_rate": 8.757668711656443e-05, | |
| "loss": 1.2302, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 5.379310344827586, | |
| "grad_norm": 20.703832626342773, | |
| "learning_rate": 8.726993865030675e-05, | |
| "loss": 1.1877, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.448275862068965, | |
| "grad_norm": 28.778301239013672, | |
| "learning_rate": 8.696319018404908e-05, | |
| "loss": 1.5936, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 5.517241379310345, | |
| "grad_norm": 25.026071548461914, | |
| "learning_rate": 8.665644171779142e-05, | |
| "loss": 1.0255, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.586206896551724, | |
| "grad_norm": 17.47880744934082, | |
| "learning_rate": 8.634969325153374e-05, | |
| "loss": 1.3967, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 5.655172413793103, | |
| "grad_norm": 20.092926025390625, | |
| "learning_rate": 8.604294478527608e-05, | |
| "loss": 1.2006, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 5.724137931034483, | |
| "grad_norm": 17.11634635925293, | |
| "learning_rate": 8.573619631901841e-05, | |
| "loss": 1.1081, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 5.793103448275862, | |
| "grad_norm": 21.26296043395996, | |
| "learning_rate": 8.542944785276073e-05, | |
| "loss": 1.0949, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 5.862068965517241, | |
| "grad_norm": 31.731033325195312, | |
| "learning_rate": 8.512269938650307e-05, | |
| "loss": 1.3502, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.931034482758621, | |
| "grad_norm": 25.80246353149414, | |
| "learning_rate": 8.48159509202454e-05, | |
| "loss": 1.5673, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 23.60406494140625, | |
| "learning_rate": 8.450920245398774e-05, | |
| "loss": 1.7041, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5378787878787878, | |
| "eval_f1_macro": 0.4265559579914266, | |
| "eval_f1_micro": 0.5378787878787878, | |
| "eval_f1_weighted": 0.5005041399030636, | |
| "eval_loss": 1.4405734539031982, | |
| "eval_precision_macro": 0.5010893868036724, | |
| "eval_precision_micro": 0.5378787878787878, | |
| "eval_precision_weighted": 0.5628245491881856, | |
| "eval_recall_macro": 0.4529024943310657, | |
| "eval_recall_micro": 0.5378787878787878, | |
| "eval_recall_weighted": 0.5378787878787878, | |
| "eval_runtime": 2.215, | |
| "eval_samples_per_second": 59.594, | |
| "eval_steps_per_second": 7.675, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 6.068965517241379, | |
| "grad_norm": 20.430105209350586, | |
| "learning_rate": 8.420245398773006e-05, | |
| "loss": 1.0018, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 6.137931034482759, | |
| "grad_norm": 14.565896987915039, | |
| "learning_rate": 8.38957055214724e-05, | |
| "loss": 1.02, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 6.206896551724138, | |
| "grad_norm": 21.370939254760742, | |
| "learning_rate": 8.358895705521473e-05, | |
| "loss": 1.1403, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 6.275862068965517, | |
| "grad_norm": 16.42601776123047, | |
| "learning_rate": 8.328220858895705e-05, | |
| "loss": 1.4774, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 6.344827586206897, | |
| "grad_norm": 18.844532012939453, | |
| "learning_rate": 8.297546012269939e-05, | |
| "loss": 1.1568, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 6.413793103448276, | |
| "grad_norm": 12.009956359863281, | |
| "learning_rate": 8.266871165644172e-05, | |
| "loss": 0.8588, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 6.482758620689655, | |
| "grad_norm": 21.886213302612305, | |
| "learning_rate": 8.236196319018406e-05, | |
| "loss": 0.8875, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 6.551724137931035, | |
| "grad_norm": 16.68918800354004, | |
| "learning_rate": 8.205521472392638e-05, | |
| "loss": 1.2283, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.620689655172414, | |
| "grad_norm": 19.978803634643555, | |
| "learning_rate": 8.174846625766872e-05, | |
| "loss": 1.0841, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 6.689655172413794, | |
| "grad_norm": 16.348190307617188, | |
| "learning_rate": 8.144171779141105e-05, | |
| "loss": 0.9849, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 6.758620689655173, | |
| "grad_norm": 21.0911865234375, | |
| "learning_rate": 8.113496932515337e-05, | |
| "loss": 1.6812, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 6.827586206896552, | |
| "grad_norm": 17.614559173583984, | |
| "learning_rate": 8.082822085889571e-05, | |
| "loss": 1.0849, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "grad_norm": 19.585248947143555, | |
| "learning_rate": 8.052147239263804e-05, | |
| "loss": 0.9886, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.9655172413793105, | |
| "grad_norm": 19.765750885009766, | |
| "learning_rate": 8.021472392638038e-05, | |
| "loss": 1.1863, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5681818181818182, | |
| "eval_f1_macro": 0.4758501564659626, | |
| "eval_f1_micro": 0.5681818181818182, | |
| "eval_f1_weighted": 0.5400274091359906, | |
| "eval_loss": 1.3679978847503662, | |
| "eval_precision_macro": 0.5558842701699845, | |
| "eval_precision_micro": 0.5681818181818182, | |
| "eval_precision_weighted": 0.603162194071285, | |
| "eval_recall_macro": 0.4831443688586546, | |
| "eval_recall_micro": 0.5681818181818182, | |
| "eval_recall_weighted": 0.5681818181818182, | |
| "eval_runtime": 2.1971, | |
| "eval_samples_per_second": 60.078, | |
| "eval_steps_per_second": 7.737, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 7.0344827586206895, | |
| "grad_norm": 12.333309173583984, | |
| "learning_rate": 7.99079754601227e-05, | |
| "loss": 0.8463, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 7.103448275862069, | |
| "grad_norm": 21.288188934326172, | |
| "learning_rate": 7.960122699386503e-05, | |
| "loss": 0.9617, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 7.172413793103448, | |
| "grad_norm": 23.408567428588867, | |
| "learning_rate": 7.929447852760737e-05, | |
| "loss": 1.2719, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 7.241379310344827, | |
| "grad_norm": 16.838363647460938, | |
| "learning_rate": 7.898773006134969e-05, | |
| "loss": 0.9394, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 7.310344827586207, | |
| "grad_norm": 19.406648635864258, | |
| "learning_rate": 7.868098159509203e-05, | |
| "loss": 1.0913, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 7.379310344827586, | |
| "grad_norm": 25.161184310913086, | |
| "learning_rate": 7.837423312883436e-05, | |
| "loss": 1.029, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 7.448275862068965, | |
| "grad_norm": 24.920177459716797, | |
| "learning_rate": 7.80674846625767e-05, | |
| "loss": 1.3211, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 7.517241379310345, | |
| "grad_norm": 22.075044631958008, | |
| "learning_rate": 7.776073619631902e-05, | |
| "loss": 1.226, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.586206896551724, | |
| "grad_norm": 17.07358169555664, | |
| "learning_rate": 7.745398773006135e-05, | |
| "loss": 0.8096, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.655172413793103, | |
| "grad_norm": 23.150299072265625, | |
| "learning_rate": 7.714723926380369e-05, | |
| "loss": 1.0163, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 7.724137931034483, | |
| "grad_norm": 19.737802505493164, | |
| "learning_rate": 7.684049079754601e-05, | |
| "loss": 1.0773, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 7.793103448275862, | |
| "grad_norm": 25.407928466796875, | |
| "learning_rate": 7.653374233128835e-05, | |
| "loss": 1.2907, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 7.862068965517241, | |
| "grad_norm": 14.86108112335205, | |
| "learning_rate": 7.622699386503068e-05, | |
| "loss": 0.9851, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 7.931034482758621, | |
| "grad_norm": 16.41703987121582, | |
| "learning_rate": 7.5920245398773e-05, | |
| "loss": 1.405, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 20.147233963012695, | |
| "learning_rate": 7.561349693251534e-05, | |
| "loss": 0.9817, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_f1_macro": 0.43986070618723677, | |
| "eval_f1_micro": 0.5227272727272727, | |
| "eval_f1_weighted": 0.4968812272383701, | |
| "eval_loss": 1.3514596223831177, | |
| "eval_precision_macro": 0.44448009061813915, | |
| "eval_precision_micro": 0.5227272727272727, | |
| "eval_precision_weighted": 0.5088011746058729, | |
| "eval_recall_macro": 0.47222222222222215, | |
| "eval_recall_micro": 0.5227272727272727, | |
| "eval_recall_weighted": 0.5227272727272727, | |
| "eval_runtime": 2.1836, | |
| "eval_samples_per_second": 60.451, | |
| "eval_steps_per_second": 7.785, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 8.068965517241379, | |
| "grad_norm": 19.058284759521484, | |
| "learning_rate": 7.530674846625767e-05, | |
| "loss": 0.7432, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 8.137931034482758, | |
| "grad_norm": 15.031048774719238, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9929, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 8.206896551724139, | |
| "grad_norm": 22.36937713623047, | |
| "learning_rate": 7.469325153374233e-05, | |
| "loss": 1.121, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 8.275862068965518, | |
| "grad_norm": 20.049163818359375, | |
| "learning_rate": 7.438650306748467e-05, | |
| "loss": 1.0773, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.344827586206897, | |
| "grad_norm": 17.548959732055664, | |
| "learning_rate": 7.4079754601227e-05, | |
| "loss": 0.6477, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 8.413793103448276, | |
| "grad_norm": 25.496204376220703, | |
| "learning_rate": 7.377300613496932e-05, | |
| "loss": 0.8577, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 8.482758620689655, | |
| "grad_norm": 22.851713180541992, | |
| "learning_rate": 7.346625766871166e-05, | |
| "loss": 1.0034, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 8.551724137931034, | |
| "grad_norm": 26.218107223510742, | |
| "learning_rate": 7.315950920245399e-05, | |
| "loss": 0.7915, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 8.620689655172415, | |
| "grad_norm": 18.867645263671875, | |
| "learning_rate": 7.285276073619633e-05, | |
| "loss": 1.0731, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.689655172413794, | |
| "grad_norm": 16.624637603759766, | |
| "learning_rate": 7.254601226993865e-05, | |
| "loss": 0.706, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 8.758620689655173, | |
| "grad_norm": 26.590402603149414, | |
| "learning_rate": 7.223926380368099e-05, | |
| "loss": 1.1713, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 8.827586206896552, | |
| "grad_norm": 26.262710571289062, | |
| "learning_rate": 7.193251533742332e-05, | |
| "loss": 0.8558, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 8.89655172413793, | |
| "grad_norm": 24.299407958984375, | |
| "learning_rate": 7.162576687116564e-05, | |
| "loss": 1.2063, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 8.96551724137931, | |
| "grad_norm": 14.688630104064941, | |
| "learning_rate": 7.131901840490798e-05, | |
| "loss": 0.617, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5909090909090909, | |
| "eval_f1_macro": 0.48949553001277135, | |
| "eval_f1_micro": 0.5909090909090909, | |
| "eval_f1_weighted": 0.5554842002399473, | |
| "eval_loss": 1.3866709470748901, | |
| "eval_precision_macro": 0.5135558290637433, | |
| "eval_precision_micro": 0.5909090909090909, | |
| "eval_precision_weighted": 0.5775828309138267, | |
| "eval_recall_macro": 0.5183068783068784, | |
| "eval_recall_micro": 0.5909090909090909, | |
| "eval_recall_weighted": 0.5909090909090909, | |
| "eval_runtime": 2.1836, | |
| "eval_samples_per_second": 60.452, | |
| "eval_steps_per_second": 7.785, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 9.03448275862069, | |
| "grad_norm": 14.76333236694336, | |
| "learning_rate": 7.101226993865031e-05, | |
| "loss": 0.5944, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 9.10344827586207, | |
| "grad_norm": 24.155582427978516, | |
| "learning_rate": 7.070552147239265e-05, | |
| "loss": 0.7582, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 9.172413793103448, | |
| "grad_norm": 28.48207664489746, | |
| "learning_rate": 7.039877300613497e-05, | |
| "loss": 0.8912, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 9.241379310344827, | |
| "grad_norm": 10.216355323791504, | |
| "learning_rate": 7.00920245398773e-05, | |
| "loss": 0.6462, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 9.310344827586206, | |
| "grad_norm": 26.633636474609375, | |
| "learning_rate": 6.978527607361964e-05, | |
| "loss": 0.9824, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 9.379310344827585, | |
| "grad_norm": 24.09172821044922, | |
| "learning_rate": 6.947852760736196e-05, | |
| "loss": 0.6394, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 9.448275862068966, | |
| "grad_norm": 27.006250381469727, | |
| "learning_rate": 6.91717791411043e-05, | |
| "loss": 0.9335, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 9.517241379310345, | |
| "grad_norm": 22.846731185913086, | |
| "learning_rate": 6.886503067484663e-05, | |
| "loss": 0.6089, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 9.586206896551724, | |
| "grad_norm": 19.58112144470215, | |
| "learning_rate": 6.855828220858897e-05, | |
| "loss": 0.7781, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 9.655172413793103, | |
| "grad_norm": 13.92150592803955, | |
| "learning_rate": 6.825153374233129e-05, | |
| "loss": 0.5359, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 9.724137931034482, | |
| "grad_norm": 31.10985565185547, | |
| "learning_rate": 6.794478527607362e-05, | |
| "loss": 1.1988, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 9.793103448275861, | |
| "grad_norm": 23.35214614868164, | |
| "learning_rate": 6.763803680981596e-05, | |
| "loss": 0.9214, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 9.862068965517242, | |
| "grad_norm": 28.431663513183594, | |
| "learning_rate": 6.733128834355828e-05, | |
| "loss": 0.7769, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 9.931034482758621, | |
| "grad_norm": 26.589706420898438, | |
| "learning_rate": 6.702453987730062e-05, | |
| "loss": 0.7962, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 31.327491760253906, | |
| "learning_rate": 6.671779141104295e-05, | |
| "loss": 1.0365, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5378787878787878, | |
| "eval_f1_macro": 0.43132712141928736, | |
| "eval_f1_micro": 0.5378787878787878, | |
| "eval_f1_weighted": 0.49605830250991545, | |
| "eval_loss": 1.4607229232788086, | |
| "eval_precision_macro": 0.4370555865025911, | |
| "eval_precision_micro": 0.5378787878787878, | |
| "eval_precision_weighted": 0.4996555594942692, | |
| "eval_recall_macro": 0.46741496598639454, | |
| "eval_recall_micro": 0.5378787878787878, | |
| "eval_recall_weighted": 0.5378787878787878, | |
| "eval_runtime": 2.1864, | |
| "eval_samples_per_second": 60.372, | |
| "eval_steps_per_second": 7.775, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 10.068965517241379, | |
| "grad_norm": 35.857444763183594, | |
| "learning_rate": 6.641104294478529e-05, | |
| "loss": 1.1976, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 10.137931034482758, | |
| "grad_norm": 19.138635635375977, | |
| "learning_rate": 6.610429447852761e-05, | |
| "loss": 0.775, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 10.206896551724139, | |
| "grad_norm": 28.3044490814209, | |
| "learning_rate": 6.579754601226994e-05, | |
| "loss": 0.7642, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 10.275862068965518, | |
| "grad_norm": 20.905742645263672, | |
| "learning_rate": 6.549079754601228e-05, | |
| "loss": 0.5362, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 10.344827586206897, | |
| "grad_norm": 18.387508392333984, | |
| "learning_rate": 6.51840490797546e-05, | |
| "loss": 0.9838, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.413793103448276, | |
| "grad_norm": 13.722414016723633, | |
| "learning_rate": 6.487730061349694e-05, | |
| "loss": 0.446, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 10.482758620689655, | |
| "grad_norm": 20.892261505126953, | |
| "learning_rate": 6.457055214723927e-05, | |
| "loss": 0.7612, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 10.551724137931034, | |
| "grad_norm": 13.154946327209473, | |
| "learning_rate": 6.426380368098159e-05, | |
| "loss": 0.7933, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 10.620689655172415, | |
| "grad_norm": 16.057727813720703, | |
| "learning_rate": 6.395705521472393e-05, | |
| "loss": 0.522, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 10.689655172413794, | |
| "grad_norm": 19.725608825683594, | |
| "learning_rate": 6.365030674846626e-05, | |
| "loss": 0.7614, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 10.758620689655173, | |
| "grad_norm": 24.844079971313477, | |
| "learning_rate": 6.33435582822086e-05, | |
| "loss": 0.7933, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.827586206896552, | |
| "grad_norm": 18.63338279724121, | |
| "learning_rate": 6.303680981595092e-05, | |
| "loss": 0.7279, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 10.89655172413793, | |
| "grad_norm": 21.24047088623047, | |
| "learning_rate": 6.273006134969326e-05, | |
| "loss": 0.5442, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 10.96551724137931, | |
| "grad_norm": 33.37268829345703, | |
| "learning_rate": 6.242331288343559e-05, | |
| "loss": 0.6815, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5909090909090909, | |
| "eval_f1_macro": 0.49620898933890345, | |
| "eval_f1_micro": 0.5909090909090909, | |
| "eval_f1_weighted": 0.5663560659976746, | |
| "eval_loss": 1.3132938146591187, | |
| "eval_precision_macro": 0.5087159863945577, | |
| "eval_precision_micro": 0.5909090909090909, | |
| "eval_precision_weighted": 0.5741680194805194, | |
| "eval_recall_macro": 0.5132879818594104, | |
| "eval_recall_micro": 0.5909090909090909, | |
| "eval_recall_weighted": 0.5909090909090909, | |
| "eval_runtime": 2.1795, | |
| "eval_samples_per_second": 60.565, | |
| "eval_steps_per_second": 7.8, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 11.03448275862069, | |
| "grad_norm": 16.19150733947754, | |
| "learning_rate": 6.211656441717791e-05, | |
| "loss": 0.644, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 11.10344827586207, | |
| "grad_norm": 20.564546585083008, | |
| "learning_rate": 6.180981595092025e-05, | |
| "loss": 0.4998, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 11.172413793103448, | |
| "grad_norm": 19.2364444732666, | |
| "learning_rate": 6.150306748466258e-05, | |
| "loss": 0.7469, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 11.241379310344827, | |
| "grad_norm": 11.9139404296875, | |
| "learning_rate": 6.119631901840492e-05, | |
| "loss": 0.3421, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 11.310344827586206, | |
| "grad_norm": 15.564549446105957, | |
| "learning_rate": 6.088957055214725e-05, | |
| "loss": 0.454, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 11.379310344827585, | |
| "grad_norm": 15.790903091430664, | |
| "learning_rate": 6.058282208588958e-05, | |
| "loss": 0.5501, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 11.448275862068966, | |
| "grad_norm": 20.395984649658203, | |
| "learning_rate": 6.02760736196319e-05, | |
| "loss": 0.7396, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 11.517241379310345, | |
| "grad_norm": 13.017558097839355, | |
| "learning_rate": 5.996932515337423e-05, | |
| "loss": 0.3902, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 11.586206896551724, | |
| "grad_norm": 16.60504150390625, | |
| "learning_rate": 5.9662576687116564e-05, | |
| "loss": 0.4817, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 11.655172413793103, | |
| "grad_norm": 26.98207664489746, | |
| "learning_rate": 5.93558282208589e-05, | |
| "loss": 0.7637, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 11.724137931034482, | |
| "grad_norm": 27.36790657043457, | |
| "learning_rate": 5.9049079754601235e-05, | |
| "loss": 0.7137, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 11.793103448275861, | |
| "grad_norm": 21.537046432495117, | |
| "learning_rate": 5.874233128834357e-05, | |
| "loss": 0.5965, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 11.862068965517242, | |
| "grad_norm": 23.125181198120117, | |
| "learning_rate": 5.8435582822085886e-05, | |
| "loss": 0.5142, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 11.931034482758621, | |
| "grad_norm": 24.718408584594727, | |
| "learning_rate": 5.812883435582822e-05, | |
| "loss": 0.7012, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 10.676513671875, | |
| "learning_rate": 5.782208588957055e-05, | |
| "loss": 0.4153, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5909090909090909, | |
| "eval_f1_macro": 0.5082184346733783, | |
| "eval_f1_micro": 0.5909090909090909, | |
| "eval_f1_weighted": 0.5734953480846786, | |
| "eval_loss": 1.3527586460113525, | |
| "eval_precision_macro": 0.518512557765101, | |
| "eval_precision_micro": 0.5909090909090909, | |
| "eval_precision_weighted": 0.5819735429220373, | |
| "eval_recall_macro": 0.5201889644746788, | |
| "eval_recall_micro": 0.5909090909090909, | |
| "eval_recall_weighted": 0.5909090909090909, | |
| "eval_runtime": 2.1855, | |
| "eval_samples_per_second": 60.399, | |
| "eval_steps_per_second": 7.779, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 12.068965517241379, | |
| "grad_norm": 9.67835521697998, | |
| "learning_rate": 5.751533742331289e-05, | |
| "loss": 0.341, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 12.137931034482758, | |
| "grad_norm": 26.32645034790039, | |
| "learning_rate": 5.720858895705522e-05, | |
| "loss": 0.6657, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 12.206896551724139, | |
| "grad_norm": 26.893024444580078, | |
| "learning_rate": 5.6901840490797555e-05, | |
| "loss": 0.6414, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 12.275862068965518, | |
| "grad_norm": 20.325834274291992, | |
| "learning_rate": 5.6595092024539874e-05, | |
| "loss": 0.5375, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 12.344827586206897, | |
| "grad_norm": 14.722708702087402, | |
| "learning_rate": 5.6288343558282206e-05, | |
| "loss": 0.3507, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 12.413793103448276, | |
| "grad_norm": 16.164493560791016, | |
| "learning_rate": 5.598159509202454e-05, | |
| "loss": 0.3948, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 12.482758620689655, | |
| "grad_norm": 20.786996841430664, | |
| "learning_rate": 5.567484662576688e-05, | |
| "loss": 0.4795, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 12.551724137931034, | |
| "grad_norm": 14.129579544067383, | |
| "learning_rate": 5.536809815950921e-05, | |
| "loss": 0.2681, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 12.620689655172415, | |
| "grad_norm": 14.56933879852295, | |
| "learning_rate": 5.506134969325154e-05, | |
| "loss": 0.5054, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 12.689655172413794, | |
| "grad_norm": 30.525728225708008, | |
| "learning_rate": 5.475460122699386e-05, | |
| "loss": 0.5441, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 12.758620689655173, | |
| "grad_norm": 26.576383590698242, | |
| "learning_rate": 5.4447852760736193e-05, | |
| "loss": 0.7958, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.827586206896552, | |
| "grad_norm": 15.745062828063965, | |
| "learning_rate": 5.4141104294478526e-05, | |
| "loss": 0.4405, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 12.89655172413793, | |
| "grad_norm": 27.86982536315918, | |
| "learning_rate": 5.3834355828220865e-05, | |
| "loss": 0.5312, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 12.96551724137931, | |
| "grad_norm": 14.46611213684082, | |
| "learning_rate": 5.35276073619632e-05, | |
| "loss": 0.3396, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5909090909090909, | |
| "eval_f1_macro": 0.53715778106022, | |
| "eval_f1_micro": 0.5909090909090909, | |
| "eval_f1_weighted": 0.5830308957803414, | |
| "eval_loss": 1.385578989982605, | |
| "eval_precision_macro": 0.5622709610159853, | |
| "eval_precision_micro": 0.5909090909090909, | |
| "eval_precision_weighted": 0.6017770445498773, | |
| "eval_recall_macro": 0.5387226001511716, | |
| "eval_recall_micro": 0.5909090909090909, | |
| "eval_recall_weighted": 0.5909090909090909, | |
| "eval_runtime": 2.1898, | |
| "eval_samples_per_second": 60.279, | |
| "eval_steps_per_second": 7.763, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 13.03448275862069, | |
| "grad_norm": 17.2612361907959, | |
| "learning_rate": 5.322085889570553e-05, | |
| "loss": 0.3936, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 13.10344827586207, | |
| "grad_norm": 14.51452350616455, | |
| "learning_rate": 5.291411042944786e-05, | |
| "loss": 0.3816, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 13.172413793103448, | |
| "grad_norm": 11.573400497436523, | |
| "learning_rate": 5.260736196319018e-05, | |
| "loss": 0.3908, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 13.241379310344827, | |
| "grad_norm": 18.94368553161621, | |
| "learning_rate": 5.230061349693251e-05, | |
| "loss": 0.5848, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 13.310344827586206, | |
| "grad_norm": 18.253276824951172, | |
| "learning_rate": 5.1993865030674845e-05, | |
| "loss": 0.2693, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 13.379310344827585, | |
| "grad_norm": 12.632643699645996, | |
| "learning_rate": 5.1687116564417185e-05, | |
| "loss": 0.4368, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 13.448275862068966, | |
| "grad_norm": 14.242535591125488, | |
| "learning_rate": 5.138036809815952e-05, | |
| "loss": 0.3045, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 13.517241379310345, | |
| "grad_norm": 10.820467948913574, | |
| "learning_rate": 5.107361963190185e-05, | |
| "loss": 0.191, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 13.586206896551724, | |
| "grad_norm": 18.95819091796875, | |
| "learning_rate": 5.076687116564417e-05, | |
| "loss": 0.5458, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 13.655172413793103, | |
| "grad_norm": 21.91457748413086, | |
| "learning_rate": 5.04601226993865e-05, | |
| "loss": 0.7368, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 13.724137931034482, | |
| "grad_norm": 28.396440505981445, | |
| "learning_rate": 5.015337423312883e-05, | |
| "loss": 0.6519, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 13.793103448275861, | |
| "grad_norm": 16.6456356048584, | |
| "learning_rate": 4.984662576687117e-05, | |
| "loss": 0.5557, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 13.862068965517242, | |
| "grad_norm": 19.1430606842041, | |
| "learning_rate": 4.9539877300613504e-05, | |
| "loss": 0.6529, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 13.931034482758621, | |
| "grad_norm": 26.434980392456055, | |
| "learning_rate": 4.923312883435583e-05, | |
| "loss": 0.6911, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 30.586454391479492, | |
| "learning_rate": 4.892638036809816e-05, | |
| "loss": 0.5415, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5909090909090909, | |
| "eval_f1_macro": 0.5132147277659137, | |
| "eval_f1_micro": 0.5909090909090909, | |
| "eval_f1_weighted": 0.5795267633305671, | |
| "eval_loss": 1.4251549243927002, | |
| "eval_precision_macro": 0.5222798718196696, | |
| "eval_precision_micro": 0.5909090909090909, | |
| "eval_precision_weighted": 0.5892947366820627, | |
| "eval_recall_macro": 0.5254724111866969, | |
| "eval_recall_micro": 0.5909090909090909, | |
| "eval_recall_weighted": 0.5909090909090909, | |
| "eval_runtime": 2.1927, | |
| "eval_samples_per_second": 60.199, | |
| "eval_steps_per_second": 7.753, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 14.068965517241379, | |
| "grad_norm": 22.47860336303711, | |
| "learning_rate": 4.8619631901840495e-05, | |
| "loss": 0.2761, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 14.137931034482758, | |
| "grad_norm": 6.592859745025635, | |
| "learning_rate": 4.831288343558282e-05, | |
| "loss": 0.2115, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 14.206896551724139, | |
| "grad_norm": 11.651180267333984, | |
| "learning_rate": 4.800613496932516e-05, | |
| "loss": 0.2898, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 14.275862068965518, | |
| "grad_norm": 24.14730453491211, | |
| "learning_rate": 4.769938650306749e-05, | |
| "loss": 0.468, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 14.344827586206897, | |
| "grad_norm": 22.79234504699707, | |
| "learning_rate": 4.739263803680982e-05, | |
| "loss": 0.3194, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 14.413793103448276, | |
| "grad_norm": 19.285917282104492, | |
| "learning_rate": 4.708588957055215e-05, | |
| "loss": 0.3259, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 14.482758620689655, | |
| "grad_norm": 15.568497657775879, | |
| "learning_rate": 4.677914110429448e-05, | |
| "loss": 0.229, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 14.551724137931034, | |
| "grad_norm": 6.664709091186523, | |
| "learning_rate": 4.647239263803681e-05, | |
| "loss": 0.5116, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 14.620689655172415, | |
| "grad_norm": 27.09947967529297, | |
| "learning_rate": 4.616564417177914e-05, | |
| "loss": 0.3526, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 14.689655172413794, | |
| "grad_norm": 19.279560089111328, | |
| "learning_rate": 4.585889570552148e-05, | |
| "loss": 0.327, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 14.758620689655173, | |
| "grad_norm": 14.68875789642334, | |
| "learning_rate": 4.5552147239263805e-05, | |
| "loss": 0.1932, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 14.827586206896552, | |
| "grad_norm": 10.188983917236328, | |
| "learning_rate": 4.524539877300614e-05, | |
| "loss": 0.3491, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 14.89655172413793, | |
| "grad_norm": 30.82689094543457, | |
| "learning_rate": 4.493865030674847e-05, | |
| "loss": 0.5371, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 14.96551724137931, | |
| "grad_norm": 25.854101181030273, | |
| "learning_rate": 4.4631901840490795e-05, | |
| "loss": 0.4421, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_f1_macro": 0.5574127938548423, | |
| "eval_f1_micro": 0.6136363636363636, | |
| "eval_f1_weighted": 0.6086044486243096, | |
| "eval_loss": 1.4080591201782227, | |
| "eval_precision_macro": 0.5752992105933282, | |
| "eval_precision_micro": 0.6136363636363636, | |
| "eval_precision_weighted": 0.6148821098687408, | |
| "eval_recall_macro": 0.5531670445956159, | |
| "eval_recall_micro": 0.6136363636363636, | |
| "eval_recall_weighted": 0.6136363636363636, | |
| "eval_runtime": 2.1892, | |
| "eval_samples_per_second": 60.296, | |
| "eval_steps_per_second": 7.765, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 15.03448275862069, | |
| "grad_norm": 10.050946235656738, | |
| "learning_rate": 4.432515337423313e-05, | |
| "loss": 0.3007, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 15.10344827586207, | |
| "grad_norm": 12.756734848022461, | |
| "learning_rate": 4.4018404907975466e-05, | |
| "loss": 0.3396, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 15.172413793103448, | |
| "grad_norm": 25.455589294433594, | |
| "learning_rate": 4.371165644171779e-05, | |
| "loss": 0.3914, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 15.241379310344827, | |
| "grad_norm": 13.843463897705078, | |
| "learning_rate": 4.3404907975460124e-05, | |
| "loss": 0.3308, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 15.310344827586206, | |
| "grad_norm": 23.339752197265625, | |
| "learning_rate": 4.309815950920246e-05, | |
| "loss": 0.4584, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 15.379310344827585, | |
| "grad_norm": 8.64341926574707, | |
| "learning_rate": 4.279141104294479e-05, | |
| "loss": 0.1732, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 15.448275862068966, | |
| "grad_norm": 6.727046012878418, | |
| "learning_rate": 4.2484662576687115e-05, | |
| "loss": 0.2713, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 15.517241379310345, | |
| "grad_norm": 30.494932174682617, | |
| "learning_rate": 4.2177914110429454e-05, | |
| "loss": 0.2759, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 15.586206896551724, | |
| "grad_norm": 25.142616271972656, | |
| "learning_rate": 4.1871165644171786e-05, | |
| "loss": 0.2707, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 15.655172413793103, | |
| "grad_norm": 27.547733306884766, | |
| "learning_rate": 4.156441717791411e-05, | |
| "loss": 0.5069, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 15.724137931034482, | |
| "grad_norm": 19.634178161621094, | |
| "learning_rate": 4.1257668711656444e-05, | |
| "loss": 0.3872, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 15.793103448275861, | |
| "grad_norm": 21.880495071411133, | |
| "learning_rate": 4.0950920245398776e-05, | |
| "loss": 0.2277, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 15.862068965517242, | |
| "grad_norm": 15.454160690307617, | |
| "learning_rate": 4.06441717791411e-05, | |
| "loss": 0.3267, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 15.931034482758621, | |
| "grad_norm": 15.292703628540039, | |
| "learning_rate": 4.033742331288344e-05, | |
| "loss": 0.2948, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 24.81329917907715, | |
| "learning_rate": 4.0030674846625773e-05, | |
| "loss": 0.2893, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5984848484848485, | |
| "eval_f1_macro": 0.512701663933191, | |
| "eval_f1_micro": 0.5984848484848485, | |
| "eval_f1_weighted": 0.5832852686300961, | |
| "eval_loss": 1.5284953117370605, | |
| "eval_precision_macro": 0.5059085452362763, | |
| "eval_precision_micro": 0.5984848484848485, | |
| "eval_precision_weighted": 0.5752329251259732, | |
| "eval_recall_macro": 0.5253136810279667, | |
| "eval_recall_micro": 0.5984848484848485, | |
| "eval_recall_weighted": 0.5984848484848485, | |
| "eval_runtime": 2.1964, | |
| "eval_samples_per_second": 60.099, | |
| "eval_steps_per_second": 7.74, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 16.06896551724138, | |
| "grad_norm": 19.42568588256836, | |
| "learning_rate": 3.97239263803681e-05, | |
| "loss": 0.1854, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 16.137931034482758, | |
| "grad_norm": 12.055990219116211, | |
| "learning_rate": 3.941717791411043e-05, | |
| "loss": 0.2725, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 16.20689655172414, | |
| "grad_norm": 22.306148529052734, | |
| "learning_rate": 3.9110429447852764e-05, | |
| "loss": 0.2066, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 16.275862068965516, | |
| "grad_norm": 15.890237808227539, | |
| "learning_rate": 3.880368098159509e-05, | |
| "loss": 0.3127, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 16.344827586206897, | |
| "grad_norm": 17.045835494995117, | |
| "learning_rate": 3.849693251533742e-05, | |
| "loss": 0.3555, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 16.413793103448278, | |
| "grad_norm": 15.841018676757812, | |
| "learning_rate": 3.819018404907976e-05, | |
| "loss": 0.3553, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 16.482758620689655, | |
| "grad_norm": 11.002803802490234, | |
| "learning_rate": 3.7883435582822086e-05, | |
| "loss": 0.3044, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 16.551724137931036, | |
| "grad_norm": 8.885010719299316, | |
| "learning_rate": 3.757668711656442e-05, | |
| "loss": 0.2396, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 16.620689655172413, | |
| "grad_norm": 20.58298110961914, | |
| "learning_rate": 3.726993865030675e-05, | |
| "loss": 0.2576, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 16.689655172413794, | |
| "grad_norm": 18.69637107849121, | |
| "learning_rate": 3.696319018404908e-05, | |
| "loss": 0.3052, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 16.75862068965517, | |
| "grad_norm": 7.023503303527832, | |
| "learning_rate": 3.665644171779141e-05, | |
| "loss": 0.1449, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 16.82758620689655, | |
| "grad_norm": 18.077198028564453, | |
| "learning_rate": 3.634969325153375e-05, | |
| "loss": 0.3661, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 16.896551724137932, | |
| "grad_norm": 17.02280616760254, | |
| "learning_rate": 3.6042944785276074e-05, | |
| "loss": 0.2259, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.96551724137931, | |
| "grad_norm": 20.76211929321289, | |
| "learning_rate": 3.5736196319018406e-05, | |
| "loss": 0.2403, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6287878787878788, | |
| "eval_f1_macro": 0.5395048301452242, | |
| "eval_f1_micro": 0.6287878787878788, | |
| "eval_f1_weighted": 0.6065423604608557, | |
| "eval_loss": 1.4820140600204468, | |
| "eval_precision_macro": 0.58078231292517, | |
| "eval_precision_micro": 0.6287878787878788, | |
| "eval_precision_weighted": 0.6380321067821069, | |
| "eval_recall_macro": 0.5459561602418744, | |
| "eval_recall_micro": 0.6287878787878788, | |
| "eval_recall_weighted": 0.6287878787878788, | |
| "eval_runtime": 2.1863, | |
| "eval_samples_per_second": 60.376, | |
| "eval_steps_per_second": 7.776, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 17.03448275862069, | |
| "grad_norm": 20.38401985168457, | |
| "learning_rate": 3.542944785276074e-05, | |
| "loss": 0.3407, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 17.103448275862068, | |
| "grad_norm": 5.897765636444092, | |
| "learning_rate": 3.512269938650307e-05, | |
| "loss": 0.1841, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 17.17241379310345, | |
| "grad_norm": 15.455453872680664, | |
| "learning_rate": 3.4815950920245396e-05, | |
| "loss": 0.1269, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 17.24137931034483, | |
| "grad_norm": 27.898658752441406, | |
| "learning_rate": 3.4509202453987735e-05, | |
| "loss": 0.2314, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 17.310344827586206, | |
| "grad_norm": 19.497142791748047, | |
| "learning_rate": 3.420245398773007e-05, | |
| "loss": 0.2743, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 17.379310344827587, | |
| "grad_norm": 15.271653175354004, | |
| "learning_rate": 3.3895705521472393e-05, | |
| "loss": 0.1961, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 17.448275862068964, | |
| "grad_norm": 25.726585388183594, | |
| "learning_rate": 3.3588957055214726e-05, | |
| "loss": 0.3415, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 17.517241379310345, | |
| "grad_norm": 22.30027198791504, | |
| "learning_rate": 3.328220858895706e-05, | |
| "loss": 0.2365, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 17.586206896551722, | |
| "grad_norm": 27.83454132080078, | |
| "learning_rate": 3.2975460122699384e-05, | |
| "loss": 0.323, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 17.655172413793103, | |
| "grad_norm": 17.994998931884766, | |
| "learning_rate": 3.266871165644172e-05, | |
| "loss": 0.2189, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 17.724137931034484, | |
| "grad_norm": 15.599747657775879, | |
| "learning_rate": 3.2361963190184055e-05, | |
| "loss": 0.2235, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 17.79310344827586, | |
| "grad_norm": 19.07125473022461, | |
| "learning_rate": 3.205521472392638e-05, | |
| "loss": 0.2625, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 17.862068965517242, | |
| "grad_norm": 5.794015407562256, | |
| "learning_rate": 3.174846625766871e-05, | |
| "loss": 0.1962, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 17.93103448275862, | |
| "grad_norm": 27.05267906188965, | |
| "learning_rate": 3.1441717791411045e-05, | |
| "loss": 0.4204, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 12.915875434875488, | |
| "learning_rate": 3.113496932515337e-05, | |
| "loss": 0.1087, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6060606060606061, | |
| "eval_f1_macro": 0.5319546411035773, | |
| "eval_f1_micro": 0.6060606060606061, | |
| "eval_f1_weighted": 0.6009282162872589, | |
| "eval_loss": 1.3999419212341309, | |
| "eval_precision_macro": 0.5611877440448869, | |
| "eval_precision_micro": 0.6060606060606061, | |
| "eval_precision_weighted": 0.6210855415400871, | |
| "eval_recall_macro": 0.5260619803476947, | |
| "eval_recall_micro": 0.6060606060606061, | |
| "eval_recall_weighted": 0.6060606060606061, | |
| "eval_runtime": 2.1908, | |
| "eval_samples_per_second": 60.251, | |
| "eval_steps_per_second": 7.76, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 18.06896551724138, | |
| "grad_norm": 17.82192039489746, | |
| "learning_rate": 3.0828220858895703e-05, | |
| "loss": 0.1255, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 18.137931034482758, | |
| "grad_norm": 13.459417343139648, | |
| "learning_rate": 3.052147239263804e-05, | |
| "loss": 0.1728, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 18.20689655172414, | |
| "grad_norm": 19.81383514404297, | |
| "learning_rate": 3.0214723926380368e-05, | |
| "loss": 0.1743, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 18.275862068965516, | |
| "grad_norm": 17.316072463989258, | |
| "learning_rate": 2.99079754601227e-05, | |
| "loss": 0.2115, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 18.344827586206897, | |
| "grad_norm": 25.32339096069336, | |
| "learning_rate": 2.9601226993865033e-05, | |
| "loss": 0.387, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 18.413793103448278, | |
| "grad_norm": 10.883082389831543, | |
| "learning_rate": 2.9294478527607362e-05, | |
| "loss": 0.0874, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 18.482758620689655, | |
| "grad_norm": 25.40140151977539, | |
| "learning_rate": 2.8987730061349694e-05, | |
| "loss": 0.3103, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 18.551724137931036, | |
| "grad_norm": 13.151557922363281, | |
| "learning_rate": 2.8680981595092026e-05, | |
| "loss": 0.277, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 18.620689655172413, | |
| "grad_norm": 16.688093185424805, | |
| "learning_rate": 2.837423312883436e-05, | |
| "loss": 0.1661, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 18.689655172413794, | |
| "grad_norm": 3.376065492630005, | |
| "learning_rate": 2.8067484662576688e-05, | |
| "loss": 0.2142, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 18.75862068965517, | |
| "grad_norm": 20.72919464111328, | |
| "learning_rate": 2.776073619631902e-05, | |
| "loss": 0.2779, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 18.82758620689655, | |
| "grad_norm": 3.795419454574585, | |
| "learning_rate": 2.7453987730061353e-05, | |
| "loss": 0.0706, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 18.896551724137932, | |
| "grad_norm": 18.60194969177246, | |
| "learning_rate": 2.714723926380368e-05, | |
| "loss": 0.0951, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 18.96551724137931, | |
| "grad_norm": 17.101329803466797, | |
| "learning_rate": 2.6840490797546014e-05, | |
| "loss": 0.2619, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_f1_macro": 0.561813814539783, | |
| "eval_f1_micro": 0.6136363636363636, | |
| "eval_f1_weighted": 0.6037404914018973, | |
| "eval_loss": 1.440819263458252, | |
| "eval_precision_macro": 0.6154006028203717, | |
| "eval_precision_micro": 0.6136363636363636, | |
| "eval_precision_weighted": 0.6224909931745618, | |
| "eval_recall_macro": 0.5501284958427816, | |
| "eval_recall_micro": 0.6136363636363636, | |
| "eval_recall_weighted": 0.6136363636363636, | |
| "eval_runtime": 2.201, | |
| "eval_samples_per_second": 59.973, | |
| "eval_steps_per_second": 7.724, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 19.03448275862069, | |
| "grad_norm": 13.738136291503906, | |
| "learning_rate": 2.6533742331288346e-05, | |
| "loss": 0.1927, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 19.103448275862068, | |
| "grad_norm": 17.96263885498047, | |
| "learning_rate": 2.6226993865030675e-05, | |
| "loss": 0.1388, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 19.17241379310345, | |
| "grad_norm": 25.091278076171875, | |
| "learning_rate": 2.5920245398773008e-05, | |
| "loss": 0.1476, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 19.24137931034483, | |
| "grad_norm": 14.9843168258667, | |
| "learning_rate": 2.561349693251534e-05, | |
| "loss": 0.116, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 19.310344827586206, | |
| "grad_norm": 13.588825225830078, | |
| "learning_rate": 2.530674846625767e-05, | |
| "loss": 0.1187, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 19.379310344827587, | |
| "grad_norm": 8.29517650604248, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1494, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 19.448275862068964, | |
| "grad_norm": 24.074113845825195, | |
| "learning_rate": 2.469325153374233e-05, | |
| "loss": 0.1549, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 19.517241379310345, | |
| "grad_norm": 7.5761213302612305, | |
| "learning_rate": 2.4386503067484666e-05, | |
| "loss": 0.0937, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 19.586206896551722, | |
| "grad_norm": 9.566593170166016, | |
| "learning_rate": 2.4079754601226995e-05, | |
| "loss": 0.1075, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 19.655172413793103, | |
| "grad_norm": 14.346840858459473, | |
| "learning_rate": 2.3773006134969324e-05, | |
| "loss": 0.112, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 19.724137931034484, | |
| "grad_norm": 22.044532775878906, | |
| "learning_rate": 2.346625766871166e-05, | |
| "loss": 0.1831, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 19.79310344827586, | |
| "grad_norm": 10.464526176452637, | |
| "learning_rate": 2.315950920245399e-05, | |
| "loss": 0.1353, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 19.862068965517242, | |
| "grad_norm": 6.597527980804443, | |
| "learning_rate": 2.285276073619632e-05, | |
| "loss": 0.073, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 19.93103448275862, | |
| "grad_norm": 3.7595765590667725, | |
| "learning_rate": 2.2546012269938653e-05, | |
| "loss": 0.0686, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 4.094130516052246, | |
| "learning_rate": 2.2239263803680982e-05, | |
| "loss": 0.1154, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6287878787878788, | |
| "eval_f1_macro": 0.5401653994931305, | |
| "eval_f1_micro": 0.6287878787878788, | |
| "eval_f1_weighted": 0.6089890501655209, | |
| "eval_loss": 1.4516006708145142, | |
| "eval_precision_macro": 0.5538492063492063, | |
| "eval_precision_micro": 0.6287878787878788, | |
| "eval_precision_weighted": 0.6144570707070707, | |
| "eval_recall_macro": 0.5491912320483749, | |
| "eval_recall_micro": 0.6287878787878788, | |
| "eval_recall_weighted": 0.6287878787878788, | |
| "eval_runtime": 2.2073, | |
| "eval_samples_per_second": 59.802, | |
| "eval_steps_per_second": 7.702, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 20.06896551724138, | |
| "grad_norm": 9.36839485168457, | |
| "learning_rate": 2.1932515337423315e-05, | |
| "loss": 0.0687, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 20.137931034482758, | |
| "grad_norm": 24.775922775268555, | |
| "learning_rate": 2.1625766871165647e-05, | |
| "loss": 0.1334, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 20.20689655172414, | |
| "grad_norm": 23.269336700439453, | |
| "learning_rate": 2.1319018404907976e-05, | |
| "loss": 0.1813, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 20.275862068965516, | |
| "grad_norm": 5.708396911621094, | |
| "learning_rate": 2.1012269938650308e-05, | |
| "loss": 0.0841, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 20.344827586206897, | |
| "grad_norm": 11.590498924255371, | |
| "learning_rate": 2.0705521472392637e-05, | |
| "loss": 0.116, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 20.413793103448278, | |
| "grad_norm": 18.878385543823242, | |
| "learning_rate": 2.039877300613497e-05, | |
| "loss": 0.1187, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 20.482758620689655, | |
| "grad_norm": 15.631240844726562, | |
| "learning_rate": 2.0092024539877302e-05, | |
| "loss": 0.1785, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 20.551724137931036, | |
| "grad_norm": 9.58936595916748, | |
| "learning_rate": 1.978527607361963e-05, | |
| "loss": 0.0336, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 20.620689655172413, | |
| "grad_norm": 15.450642585754395, | |
| "learning_rate": 1.9478527607361967e-05, | |
| "loss": 0.1695, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 20.689655172413794, | |
| "grad_norm": 4.292616844177246, | |
| "learning_rate": 1.9171779141104296e-05, | |
| "loss": 0.0633, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 20.75862068965517, | |
| "grad_norm": 4.748676776885986, | |
| "learning_rate": 1.8865030674846625e-05, | |
| "loss": 0.0889, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 20.82758620689655, | |
| "grad_norm": 16.53461265563965, | |
| "learning_rate": 1.855828220858896e-05, | |
| "loss": 0.1608, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 20.896551724137932, | |
| "grad_norm": 26.134490966796875, | |
| "learning_rate": 1.825153374233129e-05, | |
| "loss": 0.1693, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 20.96551724137931, | |
| "grad_norm": 20.084346771240234, | |
| "learning_rate": 1.7944785276073618e-05, | |
| "loss": 0.1367, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_f1_macro": 0.5254125588472093, | |
| "eval_f1_micro": 0.6136363636363636, | |
| "eval_f1_weighted": 0.5942474496633104, | |
| "eval_loss": 1.530592441558838, | |
| "eval_precision_macro": 0.5321410615528263, | |
| "eval_precision_micro": 0.6136363636363636, | |
| "eval_precision_weighted": 0.5922574157868276, | |
| "eval_recall_macro": 0.5339984882842026, | |
| "eval_recall_micro": 0.6136363636363636, | |
| "eval_recall_weighted": 0.6136363636363636, | |
| "eval_runtime": 2.2038, | |
| "eval_samples_per_second": 59.896, | |
| "eval_steps_per_second": 7.714, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 21.03448275862069, | |
| "grad_norm": 4.850620746612549, | |
| "learning_rate": 1.7638036809815954e-05, | |
| "loss": 0.0614, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 21.103448275862068, | |
| "grad_norm": 23.208776473999023, | |
| "learning_rate": 1.7331288343558283e-05, | |
| "loss": 0.1307, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 21.17241379310345, | |
| "grad_norm": 8.065655708312988, | |
| "learning_rate": 1.7024539877300612e-05, | |
| "loss": 0.0389, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 21.24137931034483, | |
| "grad_norm": 9.520572662353516, | |
| "learning_rate": 1.6717791411042948e-05, | |
| "loss": 0.1722, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 21.310344827586206, | |
| "grad_norm": 26.25343894958496, | |
| "learning_rate": 1.6411042944785277e-05, | |
| "loss": 0.2112, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 21.379310344827587, | |
| "grad_norm": 6.016479015350342, | |
| "learning_rate": 1.6104294478527606e-05, | |
| "loss": 0.1577, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 21.448275862068964, | |
| "grad_norm": 28.95755386352539, | |
| "learning_rate": 1.579754601226994e-05, | |
| "loss": 0.1363, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 21.517241379310345, | |
| "grad_norm": 5.472126483917236, | |
| "learning_rate": 1.549079754601227e-05, | |
| "loss": 0.0527, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 21.586206896551722, | |
| "grad_norm": 12.595699310302734, | |
| "learning_rate": 1.5184049079754603e-05, | |
| "loss": 0.1044, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 21.655172413793103, | |
| "grad_norm": 13.575519561767578, | |
| "learning_rate": 1.4877300613496933e-05, | |
| "loss": 0.1545, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 21.724137931034484, | |
| "grad_norm": 1.717926025390625, | |
| "learning_rate": 1.4570552147239264e-05, | |
| "loss": 0.0754, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 21.79310344827586, | |
| "grad_norm": 15.80093765258789, | |
| "learning_rate": 1.4263803680981596e-05, | |
| "loss": 0.1765, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 21.862068965517242, | |
| "grad_norm": 8.399004936218262, | |
| "learning_rate": 1.3957055214723927e-05, | |
| "loss": 0.0478, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 21.93103448275862, | |
| "grad_norm": 9.28877067565918, | |
| "learning_rate": 1.3650306748466258e-05, | |
| "loss": 0.0561, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 13.288439750671387, | |
| "learning_rate": 1.334355828220859e-05, | |
| "loss": 0.0839, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1_macro": 0.515415984334813, | |
| "eval_f1_micro": 0.5833333333333334, | |
| "eval_f1_weighted": 0.575588621142538, | |
| "eval_loss": 1.6396534442901611, | |
| "eval_precision_macro": 0.5274346580737558, | |
| "eval_precision_micro": 0.5833333333333334, | |
| "eval_precision_weighted": 0.5895078605604921, | |
| "eval_recall_macro": 0.5252003023431595, | |
| "eval_recall_micro": 0.5833333333333334, | |
| "eval_recall_weighted": 0.5833333333333334, | |
| "eval_runtime": 2.1936, | |
| "eval_samples_per_second": 60.176, | |
| "eval_steps_per_second": 7.75, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 22.06896551724138, | |
| "grad_norm": 5.867281436920166, | |
| "learning_rate": 1.303680981595092e-05, | |
| "loss": 0.0999, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 22.137931034482758, | |
| "grad_norm": 3.7638766765594482, | |
| "learning_rate": 1.2730061349693251e-05, | |
| "loss": 0.0418, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 22.20689655172414, | |
| "grad_norm": 1.9534434080123901, | |
| "learning_rate": 1.2423312883435584e-05, | |
| "loss": 0.0351, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 22.275862068965516, | |
| "grad_norm": 1.0892353057861328, | |
| "learning_rate": 1.2116564417177914e-05, | |
| "loss": 0.0272, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 22.344827586206897, | |
| "grad_norm": 16.817415237426758, | |
| "learning_rate": 1.1809815950920245e-05, | |
| "loss": 0.2253, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 22.413793103448278, | |
| "grad_norm": 24.870695114135742, | |
| "learning_rate": 1.1503067484662577e-05, | |
| "loss": 0.1316, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 22.482758620689655, | |
| "grad_norm": 22.584014892578125, | |
| "learning_rate": 1.119631901840491e-05, | |
| "loss": 0.2264, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 22.551724137931036, | |
| "grad_norm": 8.62193775177002, | |
| "learning_rate": 1.0889570552147239e-05, | |
| "loss": 0.0336, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 22.620689655172413, | |
| "grad_norm": 7.243905067443848, | |
| "learning_rate": 1.0582822085889571e-05, | |
| "loss": 0.0435, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 22.689655172413794, | |
| "grad_norm": 1.8948745727539062, | |
| "learning_rate": 1.0276073619631903e-05, | |
| "loss": 0.0655, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 22.75862068965517, | |
| "grad_norm": 5.095564842224121, | |
| "learning_rate": 9.969325153374232e-06, | |
| "loss": 0.042, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 22.82758620689655, | |
| "grad_norm": 25.0085506439209, | |
| "learning_rate": 9.662576687116565e-06, | |
| "loss": 0.1186, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 22.896551724137932, | |
| "grad_norm": 4.847318172454834, | |
| "learning_rate": 9.355828220858897e-06, | |
| "loss": 0.0377, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 22.96551724137931, | |
| "grad_norm": 39.400447845458984, | |
| "learning_rate": 9.049079754601228e-06, | |
| "loss": 0.1818, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6515151515151515, | |
| "eval_f1_macro": 0.565634487061558, | |
| "eval_f1_micro": 0.6515151515151515, | |
| "eval_f1_weighted": 0.6358752918681777, | |
| "eval_loss": 1.641618251800537, | |
| "eval_precision_macro": 0.584759718380408, | |
| "eval_precision_micro": 0.6515151515151515, | |
| "eval_precision_weighted": 0.6455531040170539, | |
| "eval_recall_macro": 0.5695616024187452, | |
| "eval_recall_micro": 0.6515151515151515, | |
| "eval_recall_weighted": 0.6515151515151515, | |
| "eval_runtime": 2.2051, | |
| "eval_samples_per_second": 59.861, | |
| "eval_steps_per_second": 7.709, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 23.03448275862069, | |
| "grad_norm": 11.35802936553955, | |
| "learning_rate": 8.742331288343558e-06, | |
| "loss": 0.0513, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 23.103448275862068, | |
| "grad_norm": 1.9400774240493774, | |
| "learning_rate": 8.435582822085889e-06, | |
| "loss": 0.0571, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 23.17241379310345, | |
| "grad_norm": 3.928626775741577, | |
| "learning_rate": 8.128834355828221e-06, | |
| "loss": 0.034, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 23.24137931034483, | |
| "grad_norm": 5.0317511558532715, | |
| "learning_rate": 7.822085889570554e-06, | |
| "loss": 0.0833, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 23.310344827586206, | |
| "grad_norm": 12.943672180175781, | |
| "learning_rate": 7.5153374233128836e-06, | |
| "loss": 0.0575, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 23.379310344827587, | |
| "grad_norm": 1.5223954916000366, | |
| "learning_rate": 7.208588957055215e-06, | |
| "loss": 0.0237, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 23.448275862068964, | |
| "grad_norm": 21.462011337280273, | |
| "learning_rate": 6.901840490797547e-06, | |
| "loss": 0.0785, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 23.517241379310345, | |
| "grad_norm": 13.98965072631836, | |
| "learning_rate": 6.595092024539877e-06, | |
| "loss": 0.0597, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 23.586206896551722, | |
| "grad_norm": 13.07774829864502, | |
| "learning_rate": 6.288343558282209e-06, | |
| "loss": 0.0498, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 23.655172413793103, | |
| "grad_norm": 2.752511501312256, | |
| "learning_rate": 5.98159509202454e-06, | |
| "loss": 0.028, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 23.724137931034484, | |
| "grad_norm": 3.4312055110931396, | |
| "learning_rate": 5.674846625766871e-06, | |
| "loss": 0.0531, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 23.79310344827586, | |
| "grad_norm": 20.920682907104492, | |
| "learning_rate": 5.368098159509203e-06, | |
| "loss": 0.1892, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 23.862068965517242, | |
| "grad_norm": 1.7730119228363037, | |
| "learning_rate": 5.061349693251534e-06, | |
| "loss": 0.0409, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 23.93103448275862, | |
| "grad_norm": 8.248014450073242, | |
| "learning_rate": 4.7546012269938654e-06, | |
| "loss": 0.0499, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 13.629621505737305, | |
| "learning_rate": 4.447852760736196e-06, | |
| "loss": 0.0781, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6212121212121212, | |
| "eval_f1_macro": 0.5392658545631691, | |
| "eval_f1_micro": 0.6212121212121212, | |
| "eval_f1_weighted": 0.607896474480917, | |
| "eval_loss": 1.6025735139846802, | |
| "eval_precision_macro": 0.5523980652552082, | |
| "eval_precision_micro": 0.6212121212121212, | |
| "eval_precision_weighted": 0.6118077193077193, | |
| "eval_recall_macro": 0.5412169312169313, | |
| "eval_recall_micro": 0.6212121212121212, | |
| "eval_recall_weighted": 0.6212121212121212, | |
| "eval_runtime": 2.1909, | |
| "eval_samples_per_second": 60.25, | |
| "eval_steps_per_second": 7.76, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 24.06896551724138, | |
| "grad_norm": 2.504154920578003, | |
| "learning_rate": 4.141104294478528e-06, | |
| "loss": 0.0335, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 24.137931034482758, | |
| "grad_norm": 17.774227142333984, | |
| "learning_rate": 3.834355828220859e-06, | |
| "loss": 0.1496, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 24.20689655172414, | |
| "grad_norm": 2.7488608360290527, | |
| "learning_rate": 3.52760736196319e-06, | |
| "loss": 0.0266, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 24.275862068965516, | |
| "grad_norm": 7.259423732757568, | |
| "learning_rate": 3.2208588957055217e-06, | |
| "loss": 0.0863, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 24.344827586206897, | |
| "grad_norm": 7.789644718170166, | |
| "learning_rate": 2.914110429447853e-06, | |
| "loss": 0.0491, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 24.413793103448278, | |
| "grad_norm": 1.2346043586730957, | |
| "learning_rate": 2.607361963190184e-06, | |
| "loss": 0.0136, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 24.482758620689655, | |
| "grad_norm": 5.063798904418945, | |
| "learning_rate": 2.3006134969325154e-06, | |
| "loss": 0.0189, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 24.551724137931036, | |
| "grad_norm": 6.230537414550781, | |
| "learning_rate": 1.9938650306748465e-06, | |
| "loss": 0.0431, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 24.620689655172413, | |
| "grad_norm": 15.741507530212402, | |
| "learning_rate": 1.687116564417178e-06, | |
| "loss": 0.19, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 24.689655172413794, | |
| "grad_norm": 12.17914867401123, | |
| "learning_rate": 1.3803680981595093e-06, | |
| "loss": 0.0662, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 24.75862068965517, | |
| "grad_norm": 1.5245462656021118, | |
| "learning_rate": 1.0736196319018406e-06, | |
| "loss": 0.0579, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 24.82758620689655, | |
| "grad_norm": 3.734255790710449, | |
| "learning_rate": 7.668711656441718e-07, | |
| "loss": 0.0337, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 24.896551724137932, | |
| "grad_norm": 25.646230697631836, | |
| "learning_rate": 4.601226993865031e-07, | |
| "loss": 0.1464, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 24.96551724137931, | |
| "grad_norm": 11.875574111938477, | |
| "learning_rate": 1.5337423312883438e-07, | |
| "loss": 0.0792, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6287878787878788, | |
| "eval_f1_macro": 0.5494495726426264, | |
| "eval_f1_micro": 0.6287878787878788, | |
| "eval_f1_weighted": 0.6179503958679277, | |
| "eval_loss": 1.599715232849121, | |
| "eval_precision_macro": 0.5716202716202715, | |
| "eval_precision_micro": 0.6287878787878788, | |
| "eval_precision_weighted": 0.6297404683768321, | |
| "eval_recall_macro": 0.5480196523053665, | |
| "eval_recall_micro": 0.6287878787878788, | |
| "eval_recall_weighted": 0.6287878787878788, | |
| "eval_runtime": 2.2024, | |
| "eval_samples_per_second": 59.933, | |
| "eval_steps_per_second": 7.719, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 725, | |
| "total_flos": 5.76425379898368e+16, | |
| "train_loss": 0.7207291752639515, | |
| "train_runtime": 641.8354, | |
| "train_samples_per_second": 17.995, | |
| "train_steps_per_second": 1.13 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 725, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 25, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.76425379898368e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |