| { | |
| "best_metric": 1.160251259803772, | |
| "best_model_checkpoint": "google/vit-base-patch16-224/checkpoint-261", | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 870, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 14.510237693786621, | |
| "learning_rate": 2.2988505747126437e-06, | |
| "loss": 2.1774, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 9.049612998962402, | |
| "learning_rate": 4.5977011494252875e-06, | |
| "loss": 2.0791, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 9.698376655578613, | |
| "learning_rate": 6.896551724137932e-06, | |
| "loss": 2.0987, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 7.020346641540527, | |
| "learning_rate": 9.195402298850575e-06, | |
| "loss": 1.8821, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 9.71212100982666, | |
| "learning_rate": 1.1494252873563218e-05, | |
| "loss": 1.8769, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 10.103402137756348, | |
| "learning_rate": 1.3793103448275863e-05, | |
| "loss": 2.0004, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 7.7244110107421875, | |
| "learning_rate": 1.6091954022988507e-05, | |
| "loss": 1.8686, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 7.321352481842041, | |
| "learning_rate": 1.839080459770115e-05, | |
| "loss": 1.9987, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 8.488332748413086, | |
| "learning_rate": 2.0689655172413793e-05, | |
| "loss": 1.8465, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 8.521231651306152, | |
| "learning_rate": 2.2988505747126437e-05, | |
| "loss": 1.7967, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7586206896551724, | |
| "grad_norm": 5.531124591827393, | |
| "learning_rate": 2.5287356321839083e-05, | |
| "loss": 1.8343, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 5.5662841796875, | |
| "learning_rate": 2.7586206896551727e-05, | |
| "loss": 1.9065, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 9.917183876037598, | |
| "learning_rate": 2.988505747126437e-05, | |
| "loss": 1.8018, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 8.262176513671875, | |
| "learning_rate": 3.218390804597701e-05, | |
| "loss": 1.9037, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2196969696969697, | |
| "eval_f1_macro": 0.12497789566755084, | |
| "eval_f1_micro": 0.2196969696969697, | |
| "eval_f1_weighted": 0.1591974117836187, | |
| "eval_loss": 1.8618106842041016, | |
| "eval_precision_macro": 0.14014863107134926, | |
| "eval_precision_micro": 0.2196969696969697, | |
| "eval_precision_weighted": 0.1691896059192861, | |
| "eval_recall_macro": 0.1673922902494331, | |
| "eval_recall_micro": 0.2196969696969697, | |
| "eval_recall_weighted": 0.2196969696969697, | |
| "eval_runtime": 2.316, | |
| "eval_samples_per_second": 56.996, | |
| "eval_steps_per_second": 7.34, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 9.220452308654785, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 1.8331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 7.508858680725098, | |
| "learning_rate": 3.67816091954023e-05, | |
| "loss": 1.8269, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1724137931034484, | |
| "grad_norm": 6.483837604522705, | |
| "learning_rate": 3.908045977011495e-05, | |
| "loss": 1.8778, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2413793103448276, | |
| "grad_norm": 6.013676643371582, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 1.9122, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3103448275862069, | |
| "grad_norm": 6.562616348266602, | |
| "learning_rate": 4.367816091954024e-05, | |
| "loss": 1.7616, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 8.177282333374023, | |
| "learning_rate": 4.597701149425287e-05, | |
| "loss": 1.8654, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4482758620689655, | |
| "grad_norm": 6.561540126800537, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 1.8393, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5172413793103448, | |
| "grad_norm": 11.305171966552734, | |
| "learning_rate": 5.057471264367817e-05, | |
| "loss": 1.9321, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5862068965517242, | |
| "grad_norm": 7.003162384033203, | |
| "learning_rate": 5.287356321839081e-05, | |
| "loss": 1.9292, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6551724137931034, | |
| "grad_norm": 6.365418434143066, | |
| "learning_rate": 5.517241379310345e-05, | |
| "loss": 1.7028, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 10.20651626586914, | |
| "learning_rate": 5.747126436781609e-05, | |
| "loss": 2.0531, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.793103448275862, | |
| "grad_norm": 9.218647003173828, | |
| "learning_rate": 5.977011494252874e-05, | |
| "loss": 1.8879, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.8620689655172413, | |
| "grad_norm": 8.88680648803711, | |
| "learning_rate": 6.206896551724138e-05, | |
| "loss": 1.8247, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9310344827586206, | |
| "grad_norm": 9.119765281677246, | |
| "learning_rate": 6.436781609195403e-05, | |
| "loss": 1.774, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 7.1343159675598145, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.6981, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.24242424242424243, | |
| "eval_f1_macro": 0.1537403956438364, | |
| "eval_f1_micro": 0.24242424242424243, | |
| "eval_f1_weighted": 0.18962596561868278, | |
| "eval_loss": 1.876023292541504, | |
| "eval_precision_macro": 0.21524098687403828, | |
| "eval_precision_micro": 0.24242424242424243, | |
| "eval_precision_weighted": 0.2786748421101056, | |
| "eval_recall_macro": 0.20681783824640967, | |
| "eval_recall_micro": 0.24242424242424243, | |
| "eval_recall_weighted": 0.24242424242424243, | |
| "eval_runtime": 2.3142, | |
| "eval_samples_per_second": 57.039, | |
| "eval_steps_per_second": 7.346, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0689655172413794, | |
| "grad_norm": 9.466385841369629, | |
| "learning_rate": 6.896551724137931e-05, | |
| "loss": 1.9208, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.1379310344827585, | |
| "grad_norm": 6.799683094024658, | |
| "learning_rate": 7.126436781609196e-05, | |
| "loss": 1.6549, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.206896551724138, | |
| "grad_norm": 9.33665943145752, | |
| "learning_rate": 7.35632183908046e-05, | |
| "loss": 1.6985, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.2758620689655173, | |
| "grad_norm": 13.14546012878418, | |
| "learning_rate": 7.586206896551724e-05, | |
| "loss": 1.81, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.344827586206897, | |
| "grad_norm": 7.021309852600098, | |
| "learning_rate": 7.81609195402299e-05, | |
| "loss": 1.5293, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.413793103448276, | |
| "grad_norm": 11.861666679382324, | |
| "learning_rate": 8.045977011494253e-05, | |
| "loss": 1.8111, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.4827586206896552, | |
| "grad_norm": 7.507106304168701, | |
| "learning_rate": 8.275862068965517e-05, | |
| "loss": 1.9034, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.5517241379310347, | |
| "grad_norm": 6.025614261627197, | |
| "learning_rate": 8.505747126436782e-05, | |
| "loss": 1.7827, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.6206896551724137, | |
| "grad_norm": 7.319404125213623, | |
| "learning_rate": 8.735632183908047e-05, | |
| "loss": 1.5888, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.689655172413793, | |
| "grad_norm": 9.80504322052002, | |
| "learning_rate": 8.96551724137931e-05, | |
| "loss": 1.7932, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 9.417110443115234, | |
| "learning_rate": 9.195402298850575e-05, | |
| "loss": 1.7183, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.8275862068965516, | |
| "grad_norm": 8.941635131835938, | |
| "learning_rate": 9.425287356321839e-05, | |
| "loss": 1.5874, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.896551724137931, | |
| "grad_norm": 5.732688903808594, | |
| "learning_rate": 9.655172413793105e-05, | |
| "loss": 1.7631, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.9655172413793105, | |
| "grad_norm": 7.542623043060303, | |
| "learning_rate": 9.885057471264369e-05, | |
| "loss": 1.7426, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3333333333333333, | |
| "eval_f1_macro": 0.22724742891712044, | |
| "eval_f1_micro": 0.3333333333333333, | |
| "eval_f1_weighted": 0.26217254211809565, | |
| "eval_loss": 1.6970728635787964, | |
| "eval_precision_macro": 0.19590733590733594, | |
| "eval_precision_micro": 0.3333333333333333, | |
| "eval_precision_weighted": 0.22332104832104835, | |
| "eval_recall_macro": 0.28462585034013604, | |
| "eval_recall_micro": 0.3333333333333333, | |
| "eval_recall_weighted": 0.3333333333333333, | |
| "eval_runtime": 2.2957, | |
| "eval_samples_per_second": 57.5, | |
| "eval_steps_per_second": 7.405, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0344827586206895, | |
| "grad_norm": 10.286172866821289, | |
| "learning_rate": 9.987228607918264e-05, | |
| "loss": 1.7147, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.103448275862069, | |
| "grad_norm": 6.141002178192139, | |
| "learning_rate": 9.96168582375479e-05, | |
| "loss": 1.431, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.1724137931034484, | |
| "grad_norm": 8.815275192260742, | |
| "learning_rate": 9.936143039591316e-05, | |
| "loss": 1.5841, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.2413793103448274, | |
| "grad_norm": 8.497651100158691, | |
| "learning_rate": 9.910600255427843e-05, | |
| "loss": 1.5312, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.310344827586207, | |
| "grad_norm": 9.317349433898926, | |
| "learning_rate": 9.885057471264369e-05, | |
| "loss": 1.4125, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.3793103448275863, | |
| "grad_norm": 7.25119686126709, | |
| "learning_rate": 9.859514687100895e-05, | |
| "loss": 1.5882, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "grad_norm": 7.394839763641357, | |
| "learning_rate": 9.833971902937422e-05, | |
| "loss": 1.3363, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.5172413793103448, | |
| "grad_norm": 12.02316665649414, | |
| "learning_rate": 9.808429118773947e-05, | |
| "loss": 1.7395, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.586206896551724, | |
| "grad_norm": 5.999875545501709, | |
| "learning_rate": 9.782886334610473e-05, | |
| "loss": 1.1745, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.655172413793103, | |
| "grad_norm": 7.852089881896973, | |
| "learning_rate": 9.757343550446999e-05, | |
| "loss": 1.4165, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.7241379310344827, | |
| "grad_norm": 10.310169219970703, | |
| "learning_rate": 9.731800766283526e-05, | |
| "loss": 1.2625, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.793103448275862, | |
| "grad_norm": 9.247345924377441, | |
| "learning_rate": 9.706257982120052e-05, | |
| "loss": 1.5794, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.862068965517241, | |
| "grad_norm": 11.231956481933594, | |
| "learning_rate": 9.680715197956578e-05, | |
| "loss": 1.7341, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.9310344827586206, | |
| "grad_norm": 9.639124870300293, | |
| "learning_rate": 9.655172413793105e-05, | |
| "loss": 1.5511, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 6.62493371963501, | |
| "learning_rate": 9.62962962962963e-05, | |
| "loss": 1.1847, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.42424242424242425, | |
| "eval_f1_macro": 0.335973499369795, | |
| "eval_f1_micro": 0.42424242424242425, | |
| "eval_f1_weighted": 0.3911147510313107, | |
| "eval_loss": 1.5082193613052368, | |
| "eval_precision_macro": 0.3925486903558188, | |
| "eval_precision_micro": 0.42424242424242425, | |
| "eval_precision_weighted": 0.42806213997916476, | |
| "eval_recall_macro": 0.35530612244897963, | |
| "eval_recall_micro": 0.42424242424242425, | |
| "eval_recall_weighted": 0.42424242424242425, | |
| "eval_runtime": 2.3468, | |
| "eval_samples_per_second": 56.247, | |
| "eval_steps_per_second": 7.244, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.068965517241379, | |
| "grad_norm": 8.3433837890625, | |
| "learning_rate": 9.604086845466156e-05, | |
| "loss": 1.231, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.137931034482759, | |
| "grad_norm": 7.53312349319458, | |
| "learning_rate": 9.578544061302682e-05, | |
| "loss": 1.242, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.206896551724138, | |
| "grad_norm": 7.009676456451416, | |
| "learning_rate": 9.553001277139209e-05, | |
| "loss": 1.1074, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.275862068965517, | |
| "grad_norm": 7.956512451171875, | |
| "learning_rate": 9.527458492975735e-05, | |
| "loss": 1.2573, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.344827586206897, | |
| "grad_norm": 8.008772850036621, | |
| "learning_rate": 9.501915708812261e-05, | |
| "loss": 1.1739, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.413793103448276, | |
| "grad_norm": 6.648385524749756, | |
| "learning_rate": 9.476372924648788e-05, | |
| "loss": 1.257, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.482758620689655, | |
| "grad_norm": 10.020831108093262, | |
| "learning_rate": 9.450830140485314e-05, | |
| "loss": 1.6915, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.551724137931035, | |
| "grad_norm": 9.276317596435547, | |
| "learning_rate": 9.425287356321839e-05, | |
| "loss": 1.6599, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.620689655172414, | |
| "grad_norm": 6.358138084411621, | |
| "learning_rate": 9.399744572158365e-05, | |
| "loss": 1.5872, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.689655172413794, | |
| "grad_norm": 11.517606735229492, | |
| "learning_rate": 9.374201787994892e-05, | |
| "loss": 1.6351, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.758620689655173, | |
| "grad_norm": 8.802401542663574, | |
| "learning_rate": 9.348659003831418e-05, | |
| "loss": 1.6311, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 4.827586206896552, | |
| "grad_norm": 5.629919052124023, | |
| "learning_rate": 9.323116219667944e-05, | |
| "loss": 1.1992, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.896551724137931, | |
| "grad_norm": 7.886866569519043, | |
| "learning_rate": 9.29757343550447e-05, | |
| "loss": 1.2918, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 4.9655172413793105, | |
| "grad_norm": 7.389496326446533, | |
| "learning_rate": 9.272030651340997e-05, | |
| "loss": 1.3906, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4621212121212121, | |
| "eval_f1_macro": 0.3151982592976382, | |
| "eval_f1_micro": 0.4621212121212121, | |
| "eval_f1_weighted": 0.3814749150717531, | |
| "eval_loss": 1.4062546491622925, | |
| "eval_precision_macro": 0.2726634131913635, | |
| "eval_precision_micro": 0.4621212121212121, | |
| "eval_precision_weighted": 0.3278632599284773, | |
| "eval_recall_macro": 0.3784580498866213, | |
| "eval_recall_micro": 0.4621212121212121, | |
| "eval_recall_weighted": 0.4621212121212121, | |
| "eval_runtime": 2.315, | |
| "eval_samples_per_second": 57.019, | |
| "eval_steps_per_second": 7.343, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.0344827586206895, | |
| "grad_norm": 6.775806903839111, | |
| "learning_rate": 9.246487867177522e-05, | |
| "loss": 1.5752, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 5.103448275862069, | |
| "grad_norm": 8.185930252075195, | |
| "learning_rate": 9.220945083014048e-05, | |
| "loss": 1.1983, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 5.172413793103448, | |
| "grad_norm": 9.192156791687012, | |
| "learning_rate": 9.195402298850575e-05, | |
| "loss": 1.0037, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.241379310344827, | |
| "grad_norm": 8.08041000366211, | |
| "learning_rate": 9.169859514687101e-05, | |
| "loss": 1.0097, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 5.310344827586207, | |
| "grad_norm": 5.996678352355957, | |
| "learning_rate": 9.144316730523627e-05, | |
| "loss": 1.1322, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 5.379310344827586, | |
| "grad_norm": 7.907155513763428, | |
| "learning_rate": 9.118773946360154e-05, | |
| "loss": 0.9879, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.448275862068965, | |
| "grad_norm": 10.711898803710938, | |
| "learning_rate": 9.09323116219668e-05, | |
| "loss": 1.5501, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 5.517241379310345, | |
| "grad_norm": 7.513827323913574, | |
| "learning_rate": 9.067688378033205e-05, | |
| "loss": 1.1546, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.586206896551724, | |
| "grad_norm": 6.119425296783447, | |
| "learning_rate": 9.042145593869731e-05, | |
| "loss": 1.2014, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 5.655172413793103, | |
| "grad_norm": 7.023372650146484, | |
| "learning_rate": 9.016602809706258e-05, | |
| "loss": 1.0439, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 5.724137931034483, | |
| "grad_norm": 4.931612968444824, | |
| "learning_rate": 8.991060025542784e-05, | |
| "loss": 0.8718, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 5.793103448275862, | |
| "grad_norm": 8.603057861328125, | |
| "learning_rate": 8.96551724137931e-05, | |
| "loss": 1.3958, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 5.862068965517241, | |
| "grad_norm": 13.00936508178711, | |
| "learning_rate": 8.939974457215837e-05, | |
| "loss": 1.1505, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.931034482758621, | |
| "grad_norm": 8.384045600891113, | |
| "learning_rate": 8.914431673052363e-05, | |
| "loss": 1.3504, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 7.159438133239746, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 1.5575, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4621212121212121, | |
| "eval_f1_macro": 0.44137630583623616, | |
| "eval_f1_micro": 0.4621212121212121, | |
| "eval_f1_weighted": 0.45257586759804047, | |
| "eval_loss": 1.3833413124084473, | |
| "eval_precision_macro": 0.4850115870524033, | |
| "eval_precision_micro": 0.4621212121212121, | |
| "eval_precision_weighted": 0.49414276199990476, | |
| "eval_recall_macro": 0.44020408163265307, | |
| "eval_recall_micro": 0.4621212121212121, | |
| "eval_recall_weighted": 0.4621212121212121, | |
| "eval_runtime": 2.2948, | |
| "eval_samples_per_second": 57.521, | |
| "eval_steps_per_second": 7.408, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 6.068965517241379, | |
| "grad_norm": 9.312445640563965, | |
| "learning_rate": 8.863346104725416e-05, | |
| "loss": 1.2654, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 6.137931034482759, | |
| "grad_norm": 6.71382999420166, | |
| "learning_rate": 8.837803320561942e-05, | |
| "loss": 0.9276, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 6.206896551724138, | |
| "grad_norm": 8.297896385192871, | |
| "learning_rate": 8.812260536398468e-05, | |
| "loss": 1.1148, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 6.275862068965517, | |
| "grad_norm": 7.873631000518799, | |
| "learning_rate": 8.786717752234995e-05, | |
| "loss": 1.2827, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 6.344827586206897, | |
| "grad_norm": 6.687100887298584, | |
| "learning_rate": 8.761174968071521e-05, | |
| "loss": 0.9606, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 6.413793103448276, | |
| "grad_norm": 6.667215824127197, | |
| "learning_rate": 8.735632183908047e-05, | |
| "loss": 0.6776, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 6.482758620689655, | |
| "grad_norm": 8.208929061889648, | |
| "learning_rate": 8.710089399744572e-05, | |
| "loss": 0.881, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 6.551724137931035, | |
| "grad_norm": 9.478071212768555, | |
| "learning_rate": 8.684546615581099e-05, | |
| "loss": 1.136, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.620689655172414, | |
| "grad_norm": 8.301050186157227, | |
| "learning_rate": 8.659003831417625e-05, | |
| "loss": 0.9342, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 6.689655172413794, | |
| "grad_norm": 8.761463165283203, | |
| "learning_rate": 8.633461047254151e-05, | |
| "loss": 1.3543, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 6.758620689655173, | |
| "grad_norm": 7.483349323272705, | |
| "learning_rate": 8.607918263090678e-05, | |
| "loss": 1.2922, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 6.827586206896552, | |
| "grad_norm": 8.078042984008789, | |
| "learning_rate": 8.582375478927204e-05, | |
| "loss": 1.0205, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "grad_norm": 8.326959609985352, | |
| "learning_rate": 8.55683269476373e-05, | |
| "loss": 0.9268, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.9655172413793105, | |
| "grad_norm": 6.995661735534668, | |
| "learning_rate": 8.531289910600255e-05, | |
| "loss": 1.1063, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1_macro": 0.47504441047674123, | |
| "eval_f1_micro": 0.5833333333333334, | |
| "eval_f1_weighted": 0.5452723811276442, | |
| "eval_loss": 1.243076205253601, | |
| "eval_precision_macro": 0.5897593680615791, | |
| "eval_precision_micro": 0.5833333333333334, | |
| "eval_precision_weighted": 0.6328941262782481, | |
| "eval_recall_macro": 0.4889720332577476, | |
| "eval_recall_micro": 0.5833333333333334, | |
| "eval_recall_weighted": 0.5833333333333334, | |
| "eval_runtime": 2.2997, | |
| "eval_samples_per_second": 57.398, | |
| "eval_steps_per_second": 7.392, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 7.0344827586206895, | |
| "grad_norm": 5.50567626953125, | |
| "learning_rate": 8.505747126436782e-05, | |
| "loss": 0.8912, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 7.103448275862069, | |
| "grad_norm": 10.640387535095215, | |
| "learning_rate": 8.480204342273308e-05, | |
| "loss": 1.058, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 7.172413793103448, | |
| "grad_norm": 9.858780860900879, | |
| "learning_rate": 8.454661558109834e-05, | |
| "loss": 1.5669, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 7.241379310344827, | |
| "grad_norm": 7.491808891296387, | |
| "learning_rate": 8.42911877394636e-05, | |
| "loss": 1.0278, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 7.310344827586207, | |
| "grad_norm": 6.82506799697876, | |
| "learning_rate": 8.403575989782887e-05, | |
| "loss": 0.8304, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 7.379310344827586, | |
| "grad_norm": 9.78387451171875, | |
| "learning_rate": 8.378033205619413e-05, | |
| "loss": 0.9639, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 7.448275862068965, | |
| "grad_norm": 8.452964782714844, | |
| "learning_rate": 8.35249042145594e-05, | |
| "loss": 1.2323, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 7.517241379310345, | |
| "grad_norm": 6.856133460998535, | |
| "learning_rate": 8.326947637292465e-05, | |
| "loss": 0.7968, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.586206896551724, | |
| "grad_norm": 5.6795268058776855, | |
| "learning_rate": 8.301404853128991e-05, | |
| "loss": 0.677, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.655172413793103, | |
| "grad_norm": 6.389831066131592, | |
| "learning_rate": 8.275862068965517e-05, | |
| "loss": 0.7194, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 7.724137931034483, | |
| "grad_norm": 9.00326919555664, | |
| "learning_rate": 8.250319284802044e-05, | |
| "loss": 0.977, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 7.793103448275862, | |
| "grad_norm": 11.774524688720703, | |
| "learning_rate": 8.22477650063857e-05, | |
| "loss": 1.3641, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 7.862068965517241, | |
| "grad_norm": 4.0308403968811035, | |
| "learning_rate": 8.199233716475096e-05, | |
| "loss": 0.6648, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 7.931034482758621, | |
| "grad_norm": 7.0713701248168945, | |
| "learning_rate": 8.173690932311623e-05, | |
| "loss": 1.0928, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 7.82318115234375, | |
| "learning_rate": 8.148148148148148e-05, | |
| "loss": 1.1503, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.49242424242424243, | |
| "eval_f1_macro": 0.4036303722650846, | |
| "eval_f1_micro": 0.49242424242424243, | |
| "eval_f1_weighted": 0.45858542635408917, | |
| "eval_loss": 1.3634601831436157, | |
| "eval_precision_macro": 0.41447662068780083, | |
| "eval_precision_micro": 0.49242424242424243, | |
| "eval_precision_weighted": 0.47623097148788845, | |
| "eval_recall_macro": 0.44362055933484507, | |
| "eval_recall_micro": 0.49242424242424243, | |
| "eval_recall_weighted": 0.49242424242424243, | |
| "eval_runtime": 2.3144, | |
| "eval_samples_per_second": 57.035, | |
| "eval_steps_per_second": 7.345, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 8.068965517241379, | |
| "grad_norm": 9.172367095947266, | |
| "learning_rate": 8.122605363984674e-05, | |
| "loss": 0.5962, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 8.137931034482758, | |
| "grad_norm": 5.160254001617432, | |
| "learning_rate": 8.0970625798212e-05, | |
| "loss": 0.7505, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 8.206896551724139, | |
| "grad_norm": 8.052289009094238, | |
| "learning_rate": 8.071519795657727e-05, | |
| "loss": 0.8049, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 8.275862068965518, | |
| "grad_norm": 8.01250171661377, | |
| "learning_rate": 8.045977011494253e-05, | |
| "loss": 0.8478, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.344827586206897, | |
| "grad_norm": 6.239477634429932, | |
| "learning_rate": 8.020434227330779e-05, | |
| "loss": 0.5106, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 8.413793103448276, | |
| "grad_norm": 9.426051139831543, | |
| "learning_rate": 7.994891443167306e-05, | |
| "loss": 0.9756, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 8.482758620689655, | |
| "grad_norm": 6.412058353424072, | |
| "learning_rate": 7.969348659003832e-05, | |
| "loss": 0.8193, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 8.551724137931034, | |
| "grad_norm": 9.318161010742188, | |
| "learning_rate": 7.943805874840358e-05, | |
| "loss": 0.7661, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 8.620689655172415, | |
| "grad_norm": 10.047941207885742, | |
| "learning_rate": 7.918263090676885e-05, | |
| "loss": 1.046, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.689655172413794, | |
| "grad_norm": 7.953283786773682, | |
| "learning_rate": 7.892720306513411e-05, | |
| "loss": 0.5181, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 8.758620689655173, | |
| "grad_norm": 7.950782299041748, | |
| "learning_rate": 7.867177522349937e-05, | |
| "loss": 1.1763, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 8.827586206896552, | |
| "grad_norm": 9.762330055236816, | |
| "learning_rate": 7.841634738186464e-05, | |
| "loss": 0.8871, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 8.89655172413793, | |
| "grad_norm": 7.098607063293457, | |
| "learning_rate": 7.81609195402299e-05, | |
| "loss": 0.8989, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 8.96551724137931, | |
| "grad_norm": 5.383296966552734, | |
| "learning_rate": 7.790549169859515e-05, | |
| "loss": 0.5124, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6287878787878788, | |
| "eval_f1_macro": 0.5462549380339138, | |
| "eval_f1_micro": 0.6287878787878788, | |
| "eval_f1_weighted": 0.613625246172416, | |
| "eval_loss": 1.160251259803772, | |
| "eval_precision_macro": 0.5487637362637362, | |
| "eval_precision_micro": 0.6287878787878788, | |
| "eval_precision_weighted": 0.6112845487845487, | |
| "eval_recall_macro": 0.5551398337112623, | |
| "eval_recall_micro": 0.6287878787878788, | |
| "eval_recall_weighted": 0.6287878787878788, | |
| "eval_runtime": 2.3163, | |
| "eval_samples_per_second": 56.988, | |
| "eval_steps_per_second": 7.339, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 9.03448275862069, | |
| "grad_norm": 9.40657901763916, | |
| "learning_rate": 7.765006385696041e-05, | |
| "loss": 0.8737, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 9.10344827586207, | |
| "grad_norm": 4.319129943847656, | |
| "learning_rate": 7.739463601532568e-05, | |
| "loss": 0.6403, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 9.172413793103448, | |
| "grad_norm": 5.755863189697266, | |
| "learning_rate": 7.713920817369094e-05, | |
| "loss": 0.5969, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 9.241379310344827, | |
| "grad_norm": 6.241076469421387, | |
| "learning_rate": 7.68837803320562e-05, | |
| "loss": 0.3827, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 9.310344827586206, | |
| "grad_norm": 8.553583145141602, | |
| "learning_rate": 7.662835249042147e-05, | |
| "loss": 0.6394, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 9.379310344827585, | |
| "grad_norm": 9.573847770690918, | |
| "learning_rate": 7.637292464878673e-05, | |
| "loss": 0.4346, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 9.448275862068966, | |
| "grad_norm": 5.9898295402526855, | |
| "learning_rate": 7.611749680715198e-05, | |
| "loss": 0.7311, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 9.517241379310345, | |
| "grad_norm": 7.574869155883789, | |
| "learning_rate": 7.586206896551724e-05, | |
| "loss": 0.5058, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 9.586206896551724, | |
| "grad_norm": 5.771493434906006, | |
| "learning_rate": 7.56066411238825e-05, | |
| "loss": 0.4429, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 9.655172413793103, | |
| "grad_norm": 5.4583306312561035, | |
| "learning_rate": 7.535121328224777e-05, | |
| "loss": 0.3691, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 9.724137931034482, | |
| "grad_norm": 7.02595329284668, | |
| "learning_rate": 7.509578544061303e-05, | |
| "loss": 0.9049, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 9.793103448275861, | |
| "grad_norm": 10.01053524017334, | |
| "learning_rate": 7.48403575989783e-05, | |
| "loss": 1.0885, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 9.862068965517242, | |
| "grad_norm": 9.570963859558105, | |
| "learning_rate": 7.458492975734356e-05, | |
| "loss": 1.0013, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 9.931034482758621, | |
| "grad_norm": 10.005152702331543, | |
| "learning_rate": 7.432950191570882e-05, | |
| "loss": 0.9009, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 10.777491569519043, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.6648, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.4184378600485691, | |
| "eval_f1_micro": 0.5, | |
| "eval_f1_weighted": 0.47128332901854153, | |
| "eval_loss": 1.4135934114456177, | |
| "eval_precision_macro": 0.47128427128427125, | |
| "eval_precision_micro": 0.5, | |
| "eval_precision_weighted": 0.5275022956841138, | |
| "eval_recall_macro": 0.44126984126984137, | |
| "eval_recall_micro": 0.5, | |
| "eval_recall_weighted": 0.5, | |
| "eval_runtime": 2.3273, | |
| "eval_samples_per_second": 56.719, | |
| "eval_steps_per_second": 7.305, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 10.068965517241379, | |
| "grad_norm": 11.478937149047852, | |
| "learning_rate": 7.381864623243934e-05, | |
| "loss": 0.7818, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 10.137931034482758, | |
| "grad_norm": 4.0814738273620605, | |
| "learning_rate": 7.35632183908046e-05, | |
| "loss": 0.4467, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 10.206896551724139, | |
| "grad_norm": 9.072375297546387, | |
| "learning_rate": 7.330779054916986e-05, | |
| "loss": 0.8457, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 10.275862068965518, | |
| "grad_norm": 14.654154777526855, | |
| "learning_rate": 7.305236270753513e-05, | |
| "loss": 1.0091, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 10.344827586206897, | |
| "grad_norm": 5.950021266937256, | |
| "learning_rate": 7.279693486590039e-05, | |
| "loss": 0.7003, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.413793103448276, | |
| "grad_norm": 5.990440845489502, | |
| "learning_rate": 7.254150702426565e-05, | |
| "loss": 0.3965, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 10.482758620689655, | |
| "grad_norm": 5.546842098236084, | |
| "learning_rate": 7.22860791826309e-05, | |
| "loss": 0.5934, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 10.551724137931034, | |
| "grad_norm": 7.933053016662598, | |
| "learning_rate": 7.203065134099617e-05, | |
| "loss": 0.8553, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 10.620689655172415, | |
| "grad_norm": 8.429969787597656, | |
| "learning_rate": 7.177522349936143e-05, | |
| "loss": 0.576, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 10.689655172413794, | |
| "grad_norm": 10.716658592224121, | |
| "learning_rate": 7.151979565772669e-05, | |
| "loss": 0.8914, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 10.758620689655173, | |
| "grad_norm": 6.751779556274414, | |
| "learning_rate": 7.126436781609196e-05, | |
| "loss": 0.6289, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.827586206896552, | |
| "grad_norm": 9.158184051513672, | |
| "learning_rate": 7.100893997445722e-05, | |
| "loss": 0.6223, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 10.89655172413793, | |
| "grad_norm": 7.099061965942383, | |
| "learning_rate": 7.075351213282248e-05, | |
| "loss": 0.396, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 10.96551724137931, | |
| "grad_norm": 6.873266220092773, | |
| "learning_rate": 7.049808429118773e-05, | |
| "loss": 0.2917, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6060606060606061, | |
| "eval_f1_macro": 0.5155148119854002, | |
| "eval_f1_micro": 0.6060606060606061, | |
| "eval_f1_weighted": 0.5892264894938692, | |
| "eval_loss": 1.2004135847091675, | |
| "eval_precision_macro": 0.5179884004884004, | |
| "eval_precision_micro": 0.6060606060606061, | |
| "eval_precision_weighted": 0.5881653069153069, | |
| "eval_recall_macro": 0.5268253968253969, | |
| "eval_recall_micro": 0.6060606060606061, | |
| "eval_recall_weighted": 0.6060606060606061, | |
| "eval_runtime": 2.3355, | |
| "eval_samples_per_second": 56.52, | |
| "eval_steps_per_second": 7.279, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 11.03448275862069, | |
| "grad_norm": 3.133075714111328, | |
| "learning_rate": 7.0242656449553e-05, | |
| "loss": 0.466, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 11.10344827586207, | |
| "grad_norm": 4.213578701019287, | |
| "learning_rate": 6.998722860791826e-05, | |
| "loss": 0.3184, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 11.172413793103448, | |
| "grad_norm": 6.637679576873779, | |
| "learning_rate": 6.973180076628352e-05, | |
| "loss": 0.5278, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 11.241379310344827, | |
| "grad_norm": 7.749922752380371, | |
| "learning_rate": 6.947637292464879e-05, | |
| "loss": 0.3204, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 11.310344827586206, | |
| "grad_norm": 4.362213611602783, | |
| "learning_rate": 6.922094508301405e-05, | |
| "loss": 0.2826, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 11.379310344827585, | |
| "grad_norm": 3.698016881942749, | |
| "learning_rate": 6.896551724137931e-05, | |
| "loss": 0.3818, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 11.448275862068966, | |
| "grad_norm": 8.710986137390137, | |
| "learning_rate": 6.871008939974458e-05, | |
| "loss": 0.6038, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 11.517241379310345, | |
| "grad_norm": 7.1719536781311035, | |
| "learning_rate": 6.845466155810984e-05, | |
| "loss": 0.3225, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 11.586206896551724, | |
| "grad_norm": 6.520328521728516, | |
| "learning_rate": 6.81992337164751e-05, | |
| "loss": 0.5006, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 11.655172413793103, | |
| "grad_norm": 7.6063127517700195, | |
| "learning_rate": 6.794380587484037e-05, | |
| "loss": 0.5006, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 11.724137931034482, | |
| "grad_norm": 5.628337860107422, | |
| "learning_rate": 6.768837803320563e-05, | |
| "loss": 0.3412, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 11.793103448275861, | |
| "grad_norm": 9.223949432373047, | |
| "learning_rate": 6.74329501915709e-05, | |
| "loss": 0.4309, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 11.862068965517242, | |
| "grad_norm": 11.727864265441895, | |
| "learning_rate": 6.717752234993616e-05, | |
| "loss": 0.6459, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 11.931034482758621, | |
| "grad_norm": 7.271657943725586, | |
| "learning_rate": 6.69220945083014e-05, | |
| "loss": 0.2677, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 8.708776473999023, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.4962, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5681818181818182, | |
| "eval_f1_macro": 0.4970094576905722, | |
| "eval_f1_micro": 0.5681818181818182, | |
| "eval_f1_weighted": 0.5670813823572056, | |
| "eval_loss": 1.3730109930038452, | |
| "eval_precision_macro": 0.5093805943430004, | |
| "eval_precision_micro": 0.5681818181818182, | |
| "eval_precision_weighted": 0.5908635224424699, | |
| "eval_recall_macro": 0.5109221466364323, | |
| "eval_recall_micro": 0.5681818181818182, | |
| "eval_recall_weighted": 0.5681818181818182, | |
| "eval_runtime": 2.3092, | |
| "eval_samples_per_second": 57.162, | |
| "eval_steps_per_second": 7.362, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 12.068965517241379, | |
| "grad_norm": 5.946571350097656, | |
| "learning_rate": 6.641123882503193e-05, | |
| "loss": 0.3055, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 12.137931034482758, | |
| "grad_norm": 8.733643531799316, | |
| "learning_rate": 6.61558109833972e-05, | |
| "loss": 0.4823, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 12.206896551724139, | |
| "grad_norm": 5.436933994293213, | |
| "learning_rate": 6.590038314176246e-05, | |
| "loss": 0.344, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 12.275862068965518, | |
| "grad_norm": 8.14691162109375, | |
| "learning_rate": 6.564495530012772e-05, | |
| "loss": 0.4108, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 12.344827586206897, | |
| "grad_norm": 6.8699870109558105, | |
| "learning_rate": 6.538952745849299e-05, | |
| "loss": 0.2988, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 12.413793103448276, | |
| "grad_norm": 5.896437168121338, | |
| "learning_rate": 6.513409961685824e-05, | |
| "loss": 0.5497, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 12.482758620689655, | |
| "grad_norm": 4.062476634979248, | |
| "learning_rate": 6.48786717752235e-05, | |
| "loss": 0.1877, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 12.551724137931034, | |
| "grad_norm": 6.9578046798706055, | |
| "learning_rate": 6.462324393358876e-05, | |
| "loss": 0.295, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 12.620689655172415, | |
| "grad_norm": 7.430821895599365, | |
| "learning_rate": 6.436781609195403e-05, | |
| "loss": 0.4402, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 12.689655172413794, | |
| "grad_norm": 7.945040225982666, | |
| "learning_rate": 6.411238825031929e-05, | |
| "loss": 0.3923, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 12.758620689655173, | |
| "grad_norm": 5.361316680908203, | |
| "learning_rate": 6.385696040868455e-05, | |
| "loss": 0.3829, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.827586206896552, | |
| "grad_norm": 3.211268901824951, | |
| "learning_rate": 6.360153256704982e-05, | |
| "loss": 0.2011, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 12.89655172413793, | |
| "grad_norm": 12.301307678222656, | |
| "learning_rate": 6.334610472541508e-05, | |
| "loss": 0.422, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 12.96551724137931, | |
| "grad_norm": 7.031186103820801, | |
| "learning_rate": 6.309067688378033e-05, | |
| "loss": 0.5723, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_f1_macro": 0.5704633000800248, | |
| "eval_f1_micro": 0.6136363636363636, | |
| "eval_f1_weighted": 0.6076619338260136, | |
| "eval_loss": 1.337725043296814, | |
| "eval_precision_macro": 0.7050316678395496, | |
| "eval_precision_micro": 0.6136363636363636, | |
| "eval_precision_weighted": 0.6878949594466836, | |
| "eval_recall_macro": 0.5756311413454271, | |
| "eval_recall_micro": 0.6136363636363636, | |
| "eval_recall_weighted": 0.6136363636363636, | |
| "eval_runtime": 2.3083, | |
| "eval_samples_per_second": 57.184, | |
| "eval_steps_per_second": 7.365, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 13.03448275862069, | |
| "grad_norm": 9.725719451904297, | |
| "learning_rate": 6.283524904214559e-05, | |
| "loss": 0.5555, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 13.10344827586207, | |
| "grad_norm": 2.5052599906921387, | |
| "learning_rate": 6.257982120051086e-05, | |
| "loss": 0.1335, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 13.172413793103448, | |
| "grad_norm": 5.450864315032959, | |
| "learning_rate": 6.232439335887612e-05, | |
| "loss": 0.3542, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 13.241379310344827, | |
| "grad_norm": 6.038177967071533, | |
| "learning_rate": 6.206896551724138e-05, | |
| "loss": 0.3631, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 13.310344827586206, | |
| "grad_norm": 2.067920207977295, | |
| "learning_rate": 6.181353767560665e-05, | |
| "loss": 0.2047, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 13.379310344827585, | |
| "grad_norm": 3.663801908493042, | |
| "learning_rate": 6.155810983397191e-05, | |
| "loss": 0.2643, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 13.448275862068966, | |
| "grad_norm": 6.576447010040283, | |
| "learning_rate": 6.130268199233716e-05, | |
| "loss": 0.5131, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 13.517241379310345, | |
| "grad_norm": 2.8306472301483154, | |
| "learning_rate": 6.104725415070242e-05, | |
| "loss": 0.09, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 13.586206896551724, | |
| "grad_norm": 4.799499988555908, | |
| "learning_rate": 6.0791826309067686e-05, | |
| "loss": 0.213, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 13.655172413793103, | |
| "grad_norm": 5.044408321380615, | |
| "learning_rate": 6.053639846743295e-05, | |
| "loss": 0.4801, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 13.724137931034482, | |
| "grad_norm": 2.9088187217712402, | |
| "learning_rate": 6.028097062579821e-05, | |
| "loss": 0.125, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 13.793103448275861, | |
| "grad_norm": 5.007681369781494, | |
| "learning_rate": 6.0025542784163477e-05, | |
| "loss": 0.3982, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 13.862068965517242, | |
| "grad_norm": 4.744725227355957, | |
| "learning_rate": 5.977011494252874e-05, | |
| "loss": 0.4611, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 13.931034482758621, | |
| "grad_norm": 8.447021484375, | |
| "learning_rate": 5.9514687100893996e-05, | |
| "loss": 0.62, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 8.788926124572754, | |
| "learning_rate": 5.925925925925926e-05, | |
| "loss": 0.4589, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_f1_macro": 0.5648011794500899, | |
| "eval_f1_micro": 0.6136363636363636, | |
| "eval_f1_weighted": 0.6094460111024054, | |
| "eval_loss": 1.371690273284912, | |
| "eval_precision_macro": 0.6239191729323308, | |
| "eval_precision_micro": 0.6136363636363636, | |
| "eval_precision_weighted": 0.6458109051036682, | |
| "eval_recall_macro": 0.5608919123204837, | |
| "eval_recall_micro": 0.6136363636363636, | |
| "eval_recall_weighted": 0.6136363636363636, | |
| "eval_runtime": 2.3086, | |
| "eval_samples_per_second": 57.179, | |
| "eval_steps_per_second": 7.364, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 14.068965517241379, | |
| "grad_norm": 2.962904453277588, | |
| "learning_rate": 5.900383141762452e-05, | |
| "loss": 0.1153, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 14.137931034482758, | |
| "grad_norm": 1.518691897392273, | |
| "learning_rate": 5.8748403575989787e-05, | |
| "loss": 0.1856, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 14.206896551724139, | |
| "grad_norm": 5.813935279846191, | |
| "learning_rate": 5.849297573435505e-05, | |
| "loss": 0.1939, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 14.275862068965518, | |
| "grad_norm": 8.985111236572266, | |
| "learning_rate": 5.823754789272031e-05, | |
| "loss": 0.4468, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 14.344827586206897, | |
| "grad_norm": 9.152397155761719, | |
| "learning_rate": 5.798212005108558e-05, | |
| "loss": 0.2363, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 14.413793103448276, | |
| "grad_norm": 5.893610954284668, | |
| "learning_rate": 5.7726692209450826e-05, | |
| "loss": 0.3035, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 14.482758620689655, | |
| "grad_norm": 3.14355206489563, | |
| "learning_rate": 5.747126436781609e-05, | |
| "loss": 0.0909, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 14.551724137931034, | |
| "grad_norm": 5.298672676086426, | |
| "learning_rate": 5.721583652618135e-05, | |
| "loss": 0.2343, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 14.620689655172415, | |
| "grad_norm": 6.373053550720215, | |
| "learning_rate": 5.6960408684546617e-05, | |
| "loss": 0.183, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 14.689655172413794, | |
| "grad_norm": 2.314725637435913, | |
| "learning_rate": 5.670498084291188e-05, | |
| "loss": 0.1293, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 14.758620689655173, | |
| "grad_norm": 3.448334217071533, | |
| "learning_rate": 5.644955300127714e-05, | |
| "loss": 0.1733, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 14.827586206896552, | |
| "grad_norm": 1.1106864213943481, | |
| "learning_rate": 5.6194125159642407e-05, | |
| "loss": 0.1687, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 14.89655172413793, | |
| "grad_norm": 8.680233001708984, | |
| "learning_rate": 5.593869731800766e-05, | |
| "loss": 0.235, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 14.96551724137931, | |
| "grad_norm": 6.511703014373779, | |
| "learning_rate": 5.5683269476372927e-05, | |
| "loss": 0.2544, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5984848484848485, | |
| "eval_f1_macro": 0.5086132463535884, | |
| "eval_f1_micro": 0.5984848484848485, | |
| "eval_f1_weighted": 0.5792803276453666, | |
| "eval_loss": 1.4129072427749634, | |
| "eval_precision_macro": 0.5139594299258164, | |
| "eval_precision_micro": 0.5984848484848485, | |
| "eval_precision_weighted": 0.5772144522144522, | |
| "eval_recall_macro": 0.5187150415721845, | |
| "eval_recall_micro": 0.5984848484848485, | |
| "eval_recall_weighted": 0.5984848484848485, | |
| "eval_runtime": 2.3923, | |
| "eval_samples_per_second": 55.177, | |
| "eval_steps_per_second": 7.106, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 15.03448275862069, | |
| "grad_norm": 4.20862340927124, | |
| "learning_rate": 5.542784163473819e-05, | |
| "loss": 0.1926, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 15.10344827586207, | |
| "grad_norm": 3.021908760070801, | |
| "learning_rate": 5.517241379310345e-05, | |
| "loss": 0.1026, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 15.172413793103448, | |
| "grad_norm": 2.936843156814575, | |
| "learning_rate": 5.491698595146872e-05, | |
| "loss": 0.0991, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 15.241379310344827, | |
| "grad_norm": 5.583840370178223, | |
| "learning_rate": 5.466155810983398e-05, | |
| "loss": 0.2134, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 15.310344827586206, | |
| "grad_norm": 3.211482524871826, | |
| "learning_rate": 5.440613026819924e-05, | |
| "loss": 0.2029, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 15.379310344827585, | |
| "grad_norm": 1.41876220703125, | |
| "learning_rate": 5.415070242656451e-05, | |
| "loss": 0.2023, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 15.448275862068966, | |
| "grad_norm": 7.651742458343506, | |
| "learning_rate": 5.3895274584929756e-05, | |
| "loss": 0.2089, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 15.517241379310345, | |
| "grad_norm": 6.275810241699219, | |
| "learning_rate": 5.363984674329502e-05, | |
| "loss": 0.1875, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 15.586206896551724, | |
| "grad_norm": 3.7232401371002197, | |
| "learning_rate": 5.338441890166028e-05, | |
| "loss": 0.0971, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 15.655172413793103, | |
| "grad_norm": 4.189459800720215, | |
| "learning_rate": 5.3128991060025547e-05, | |
| "loss": 0.3281, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 15.724137931034482, | |
| "grad_norm": 8.769723892211914, | |
| "learning_rate": 5.287356321839081e-05, | |
| "loss": 0.2751, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 15.793103448275861, | |
| "grad_norm": 6.462566375732422, | |
| "learning_rate": 5.261813537675607e-05, | |
| "loss": 0.0904, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 15.862068965517242, | |
| "grad_norm": 9.79684066772461, | |
| "learning_rate": 5.236270753512134e-05, | |
| "loss": 0.6062, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 15.931034482758621, | |
| "grad_norm": 1.4883109331130981, | |
| "learning_rate": 5.2107279693486586e-05, | |
| "loss": 0.1717, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 6.8840413093566895, | |
| "learning_rate": 5.185185185185185e-05, | |
| "loss": 0.3179, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6439393939393939, | |
| "eval_f1_macro": 0.5881714359157968, | |
| "eval_f1_micro": 0.6439393939393939, | |
| "eval_f1_weighted": 0.634653723469513, | |
| "eval_loss": 1.3588663339614868, | |
| "eval_precision_macro": 0.6912393397962158, | |
| "eval_precision_micro": 0.6439393939393939, | |
| "eval_precision_weighted": 0.6603221597047805, | |
| "eval_recall_macro": 0.5777021919879062, | |
| "eval_recall_micro": 0.6439393939393939, | |
| "eval_recall_weighted": 0.6439393939393939, | |
| "eval_runtime": 2.3227, | |
| "eval_samples_per_second": 56.83, | |
| "eval_steps_per_second": 7.319, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 16.06896551724138, | |
| "grad_norm": 7.6531081199646, | |
| "learning_rate": 5.159642401021711e-05, | |
| "loss": 0.264, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 16.137931034482758, | |
| "grad_norm": 2.896730422973633, | |
| "learning_rate": 5.1340996168582377e-05, | |
| "loss": 0.1107, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 16.20689655172414, | |
| "grad_norm": 1.4611581563949585, | |
| "learning_rate": 5.108556832694764e-05, | |
| "loss": 0.0496, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 16.275862068965516, | |
| "grad_norm": 4.168929100036621, | |
| "learning_rate": 5.08301404853129e-05, | |
| "loss": 0.0983, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 16.344827586206897, | |
| "grad_norm": 2.321575880050659, | |
| "learning_rate": 5.057471264367817e-05, | |
| "loss": 0.1663, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 16.413793103448278, | |
| "grad_norm": 4.329580783843994, | |
| "learning_rate": 5.031928480204342e-05, | |
| "loss": 0.1443, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 16.482758620689655, | |
| "grad_norm": 2.386385917663574, | |
| "learning_rate": 5.0063856960408687e-05, | |
| "loss": 0.0896, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 16.551724137931036, | |
| "grad_norm": 3.150066375732422, | |
| "learning_rate": 4.980842911877395e-05, | |
| "loss": 0.0847, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 16.620689655172413, | |
| "grad_norm": 5.366412162780762, | |
| "learning_rate": 4.955300127713921e-05, | |
| "loss": 0.1571, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 16.689655172413794, | |
| "grad_norm": 3.45316743850708, | |
| "learning_rate": 4.929757343550448e-05, | |
| "loss": 0.0969, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 16.75862068965517, | |
| "grad_norm": 5.476890563964844, | |
| "learning_rate": 4.904214559386973e-05, | |
| "loss": 0.1459, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 16.82758620689655, | |
| "grad_norm": 8.211587905883789, | |
| "learning_rate": 4.8786717752234997e-05, | |
| "loss": 0.1792, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 16.896551724137932, | |
| "grad_norm": 2.131403684616089, | |
| "learning_rate": 4.853128991060026e-05, | |
| "loss": 0.0605, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.96551724137931, | |
| "grad_norm": 2.498298168182373, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.1304, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5757575757575758, | |
| "eval_f1_macro": 0.5009666653370032, | |
| "eval_f1_micro": 0.5757575757575758, | |
| "eval_f1_weighted": 0.5605685796379482, | |
| "eval_loss": 1.5604240894317627, | |
| "eval_precision_macro": 0.512285419028604, | |
| "eval_precision_micro": 0.5757575757575758, | |
| "eval_precision_weighted": 0.5669229036256557, | |
| "eval_recall_macro": 0.507588813303099, | |
| "eval_recall_micro": 0.5757575757575758, | |
| "eval_recall_weighted": 0.5757575757575758, | |
| "eval_runtime": 2.3178, | |
| "eval_samples_per_second": 56.95, | |
| "eval_steps_per_second": 7.334, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 17.03448275862069, | |
| "grad_norm": 6.805662155151367, | |
| "learning_rate": 4.802043422733078e-05, | |
| "loss": 0.2056, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 17.103448275862068, | |
| "grad_norm": 0.6827877163887024, | |
| "learning_rate": 4.776500638569604e-05, | |
| "loss": 0.0298, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 17.17241379310345, | |
| "grad_norm": 4.717907905578613, | |
| "learning_rate": 4.7509578544061307e-05, | |
| "loss": 0.051, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 17.24137931034483, | |
| "grad_norm": 2.6737117767333984, | |
| "learning_rate": 4.725415070242657e-05, | |
| "loss": 0.0294, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 17.310344827586206, | |
| "grad_norm": 6.83554220199585, | |
| "learning_rate": 4.6998722860791827e-05, | |
| "loss": 0.3266, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 17.379310344827587, | |
| "grad_norm": 4.863897800445557, | |
| "learning_rate": 4.674329501915709e-05, | |
| "loss": 0.1338, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 17.448275862068964, | |
| "grad_norm": 3.4082953929901123, | |
| "learning_rate": 4.648786717752235e-05, | |
| "loss": 0.1397, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 17.517241379310345, | |
| "grad_norm": 2.798154592514038, | |
| "learning_rate": 4.623243933588761e-05, | |
| "loss": 0.0626, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 17.586206896551722, | |
| "grad_norm": 7.175295829772949, | |
| "learning_rate": 4.597701149425287e-05, | |
| "loss": 0.0881, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 17.655172413793103, | |
| "grad_norm": 1.9316564798355103, | |
| "learning_rate": 4.5721583652618137e-05, | |
| "loss": 0.0838, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 17.724137931034484, | |
| "grad_norm": 7.5723161697387695, | |
| "learning_rate": 4.54661558109834e-05, | |
| "loss": 0.1712, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 17.79310344827586, | |
| "grad_norm": 0.6257821917533875, | |
| "learning_rate": 4.5210727969348656e-05, | |
| "loss": 0.0811, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 17.862068965517242, | |
| "grad_norm": 0.7635870575904846, | |
| "learning_rate": 4.495530012771392e-05, | |
| "loss": 0.0376, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 17.93103448275862, | |
| "grad_norm": 8.914319038391113, | |
| "learning_rate": 4.469987228607918e-05, | |
| "loss": 0.3516, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 4.3583478927612305, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0887, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6060606060606061, | |
| "eval_f1_macro": 0.5091139158366049, | |
| "eval_f1_micro": 0.6060606060606061, | |
| "eval_f1_weighted": 0.5799565723095135, | |
| "eval_loss": 1.6230822801589966, | |
| "eval_precision_macro": 0.5344263592737348, | |
| "eval_precision_micro": 0.6060606060606061, | |
| "eval_precision_weighted": 0.5916928649279117, | |
| "eval_recall_macro": 0.5189795918367347, | |
| "eval_recall_micro": 0.6060606060606061, | |
| "eval_recall_weighted": 0.6060606060606061, | |
| "eval_runtime": 2.3176, | |
| "eval_samples_per_second": 56.956, | |
| "eval_steps_per_second": 7.335, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 18.06896551724138, | |
| "grad_norm": 0.7991401553153992, | |
| "learning_rate": 4.418901660280971e-05, | |
| "loss": 0.0268, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 18.137931034482758, | |
| "grad_norm": 5.092419624328613, | |
| "learning_rate": 4.393358876117497e-05, | |
| "loss": 0.2074, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 18.20689655172414, | |
| "grad_norm": 7.083487510681152, | |
| "learning_rate": 4.367816091954024e-05, | |
| "loss": 0.0535, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 18.275862068965516, | |
| "grad_norm": 3.665398597717285, | |
| "learning_rate": 4.342273307790549e-05, | |
| "loss": 0.1522, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 18.344827586206897, | |
| "grad_norm": 3.8143649101257324, | |
| "learning_rate": 4.3167305236270757e-05, | |
| "loss": 0.0704, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 18.413793103448278, | |
| "grad_norm": 1.7281546592712402, | |
| "learning_rate": 4.291187739463602e-05, | |
| "loss": 0.0498, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 18.482758620689655, | |
| "grad_norm": 5.076626777648926, | |
| "learning_rate": 4.2656449553001277e-05, | |
| "loss": 0.0954, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 18.551724137931036, | |
| "grad_norm": 1.358458161354065, | |
| "learning_rate": 4.240102171136654e-05, | |
| "loss": 0.0325, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 18.620689655172413, | |
| "grad_norm": 5.167296886444092, | |
| "learning_rate": 4.21455938697318e-05, | |
| "loss": 0.0966, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 18.689655172413794, | |
| "grad_norm": 1.9453201293945312, | |
| "learning_rate": 4.189016602809707e-05, | |
| "loss": 0.0576, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 18.75862068965517, | |
| "grad_norm": 0.7826907634735107, | |
| "learning_rate": 4.163473818646232e-05, | |
| "loss": 0.1441, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 18.82758620689655, | |
| "grad_norm": 1.4397317171096802, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 0.0744, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 18.896551724137932, | |
| "grad_norm": 3.9290759563446045, | |
| "learning_rate": 4.112388250319285e-05, | |
| "loss": 0.1042, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 18.96551724137931, | |
| "grad_norm": 0.7687857747077942, | |
| "learning_rate": 4.086845466155811e-05, | |
| "loss": 0.0254, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_f1_macro": 0.5625326265517395, | |
| "eval_f1_micro": 0.6136363636363636, | |
| "eval_f1_weighted": 0.6070491578999321, | |
| "eval_loss": 1.6095294952392578, | |
| "eval_precision_macro": 0.6642268445839873, | |
| "eval_precision_micro": 0.6136363636363636, | |
| "eval_precision_weighted": 0.6353459040959041, | |
| "eval_recall_macro": 0.5520332577475434, | |
| "eval_recall_micro": 0.6136363636363636, | |
| "eval_recall_weighted": 0.6136363636363636, | |
| "eval_runtime": 2.3103, | |
| "eval_samples_per_second": 57.134, | |
| "eval_steps_per_second": 7.358, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 19.03448275862069, | |
| "grad_norm": 0.8335579037666321, | |
| "learning_rate": 4.061302681992337e-05, | |
| "loss": 0.0143, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 19.103448275862068, | |
| "grad_norm": 2.744795083999634, | |
| "learning_rate": 4.035759897828863e-05, | |
| "loss": 0.0357, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 19.17241379310345, | |
| "grad_norm": 11.362982749938965, | |
| "learning_rate": 4.0102171136653897e-05, | |
| "loss": 0.1115, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 19.24137931034483, | |
| "grad_norm": 9.07187557220459, | |
| "learning_rate": 3.984674329501916e-05, | |
| "loss": 0.0925, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 19.310344827586206, | |
| "grad_norm": 0.26310238242149353, | |
| "learning_rate": 3.959131545338442e-05, | |
| "loss": 0.0123, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 19.379310344827587, | |
| "grad_norm": 1.043347954750061, | |
| "learning_rate": 3.933588761174969e-05, | |
| "loss": 0.0295, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 19.448275862068964, | |
| "grad_norm": 0.23652300238609314, | |
| "learning_rate": 3.908045977011495e-05, | |
| "loss": 0.0058, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 19.517241379310345, | |
| "grad_norm": 2.8097283840179443, | |
| "learning_rate": 3.8825031928480207e-05, | |
| "loss": 0.0406, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 19.586206896551722, | |
| "grad_norm": 0.406757652759552, | |
| "learning_rate": 3.856960408684547e-05, | |
| "loss": 0.0079, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 19.655172413793103, | |
| "grad_norm": 3.588495969772339, | |
| "learning_rate": 3.831417624521073e-05, | |
| "loss": 0.2604, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 19.724137931034484, | |
| "grad_norm": 11.747899055480957, | |
| "learning_rate": 3.805874840357599e-05, | |
| "loss": 0.1278, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 19.79310344827586, | |
| "grad_norm": 2.0980422496795654, | |
| "learning_rate": 3.780332056194125e-05, | |
| "loss": 0.1029, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 19.862068965517242, | |
| "grad_norm": 0.777961015701294, | |
| "learning_rate": 3.7547892720306517e-05, | |
| "loss": 0.0893, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 19.93103448275862, | |
| "grad_norm": 1.2306005954742432, | |
| "learning_rate": 3.729246487867178e-05, | |
| "loss": 0.0202, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 4.3356451988220215, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.0908, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_f1_macro": 0.5269679578540161, | |
| "eval_f1_micro": 0.6136363636363636, | |
| "eval_f1_weighted": 0.5961527319540719, | |
| "eval_loss": 1.6940934658050537, | |
| "eval_precision_macro": 0.5331414617128902, | |
| "eval_precision_micro": 0.6136363636363636, | |
| "eval_precision_weighted": 0.6004181004181004, | |
| "eval_recall_macro": 0.5381027966742253, | |
| "eval_recall_micro": 0.6136363636363636, | |
| "eval_recall_weighted": 0.6136363636363636, | |
| "eval_runtime": 2.3346, | |
| "eval_samples_per_second": 56.541, | |
| "eval_steps_per_second": 7.282, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 20.06896551724138, | |
| "grad_norm": 0.9854629635810852, | |
| "learning_rate": 3.67816091954023e-05, | |
| "loss": 0.0315, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 20.137931034482758, | |
| "grad_norm": 8.160626411437988, | |
| "learning_rate": 3.652618135376756e-05, | |
| "loss": 0.195, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 20.20689655172414, | |
| "grad_norm": 9.696558952331543, | |
| "learning_rate": 3.627075351213283e-05, | |
| "loss": 0.1459, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 20.275862068965516, | |
| "grad_norm": 2.334758758544922, | |
| "learning_rate": 3.601532567049808e-05, | |
| "loss": 0.0256, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 20.344827586206897, | |
| "grad_norm": 0.862045407295227, | |
| "learning_rate": 3.5759897828863347e-05, | |
| "loss": 0.0133, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 20.413793103448278, | |
| "grad_norm": 0.4637574553489685, | |
| "learning_rate": 3.550446998722861e-05, | |
| "loss": 0.025, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 20.482758620689655, | |
| "grad_norm": 2.358105182647705, | |
| "learning_rate": 3.5249042145593867e-05, | |
| "loss": 0.0418, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 20.551724137931036, | |
| "grad_norm": 3.2894065380096436, | |
| "learning_rate": 3.499361430395913e-05, | |
| "loss": 0.0155, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 20.620689655172413, | |
| "grad_norm": 1.3686822652816772, | |
| "learning_rate": 3.473818646232439e-05, | |
| "loss": 0.0186, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 20.689655172413794, | |
| "grad_norm": 0.2436424344778061, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 0.1607, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 20.75862068965517, | |
| "grad_norm": 0.6559809446334839, | |
| "learning_rate": 3.422733077905492e-05, | |
| "loss": 0.0645, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 20.82758620689655, | |
| "grad_norm": 0.6616806387901306, | |
| "learning_rate": 3.397190293742018e-05, | |
| "loss": 0.1066, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 20.896551724137932, | |
| "grad_norm": 5.0346150398254395, | |
| "learning_rate": 3.371647509578545e-05, | |
| "loss": 0.0505, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 20.96551724137931, | |
| "grad_norm": 6.462579727172852, | |
| "learning_rate": 3.34610472541507e-05, | |
| "loss": 0.0913, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_f1_macro": 0.5536764705882352, | |
| "eval_f1_micro": 0.6136363636363636, | |
| "eval_f1_weighted": 0.6018196672608437, | |
| "eval_loss": 1.6917121410369873, | |
| "eval_precision_macro": 0.5908806106174527, | |
| "eval_precision_micro": 0.6136363636363636, | |
| "eval_precision_weighted": 0.6169424508240299, | |
| "eval_recall_macro": 0.5578609221466364, | |
| "eval_recall_micro": 0.6136363636363636, | |
| "eval_recall_weighted": 0.6136363636363636, | |
| "eval_runtime": 2.3118, | |
| "eval_samples_per_second": 57.098, | |
| "eval_steps_per_second": 7.354, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 21.03448275862069, | |
| "grad_norm": 3.8986473083496094, | |
| "learning_rate": 3.3205619412515967e-05, | |
| "loss": 0.0349, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 21.103448275862068, | |
| "grad_norm": 0.6565538048744202, | |
| "learning_rate": 3.295019157088123e-05, | |
| "loss": 0.0116, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 21.17241379310345, | |
| "grad_norm": 0.6683332324028015, | |
| "learning_rate": 3.269476372924649e-05, | |
| "loss": 0.0099, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 21.24137931034483, | |
| "grad_norm": 10.452178001403809, | |
| "learning_rate": 3.243933588761175e-05, | |
| "loss": 0.1153, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 21.310344827586206, | |
| "grad_norm": 2.8734970092773438, | |
| "learning_rate": 3.218390804597701e-05, | |
| "loss": 0.0294, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 21.379310344827587, | |
| "grad_norm": 4.400616645812988, | |
| "learning_rate": 3.192848020434228e-05, | |
| "loss": 0.0362, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 21.448275862068964, | |
| "grad_norm": 11.646851539611816, | |
| "learning_rate": 3.167305236270754e-05, | |
| "loss": 0.229, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 21.517241379310345, | |
| "grad_norm": 3.486697196960449, | |
| "learning_rate": 3.1417624521072797e-05, | |
| "loss": 0.0364, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 21.586206896551722, | |
| "grad_norm": 1.5919147729873657, | |
| "learning_rate": 3.116219667943806e-05, | |
| "loss": 0.0673, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 21.655172413793103, | |
| "grad_norm": 0.1539590209722519, | |
| "learning_rate": 3.090676883780332e-05, | |
| "loss": 0.0153, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 21.724137931034484, | |
| "grad_norm": 1.7349178791046143, | |
| "learning_rate": 3.065134099616858e-05, | |
| "loss": 0.0414, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 21.79310344827586, | |
| "grad_norm": 7.606224060058594, | |
| "learning_rate": 3.0395913154533843e-05, | |
| "loss": 0.0653, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 21.862068965517242, | |
| "grad_norm": 1.45542311668396, | |
| "learning_rate": 3.0140485312899107e-05, | |
| "loss": 0.0252, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 21.93103448275862, | |
| "grad_norm": 0.78499835729599, | |
| "learning_rate": 2.988505747126437e-05, | |
| "loss": 0.013, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 1.3190522193908691, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.015, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5681818181818182, | |
| "eval_f1_macro": 0.4866218709706104, | |
| "eval_f1_micro": 0.5681818181818182, | |
| "eval_f1_weighted": 0.5512056253477822, | |
| "eval_loss": 1.8274449110031128, | |
| "eval_precision_macro": 0.48550040705937547, | |
| "eval_precision_micro": 0.5681818181818182, | |
| "eval_precision_weighted": 0.5476516834529005, | |
| "eval_recall_macro": 0.5002721088435373, | |
| "eval_recall_micro": 0.5681818181818182, | |
| "eval_recall_weighted": 0.5681818181818182, | |
| "eval_runtime": 2.3183, | |
| "eval_samples_per_second": 56.939, | |
| "eval_steps_per_second": 7.333, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 22.06896551724138, | |
| "grad_norm": 0.5085828900337219, | |
| "learning_rate": 2.9374201787994893e-05, | |
| "loss": 0.0224, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 22.137931034482758, | |
| "grad_norm": 9.176717758178711, | |
| "learning_rate": 2.9118773946360157e-05, | |
| "loss": 0.1208, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 22.20689655172414, | |
| "grad_norm": 0.0806804820895195, | |
| "learning_rate": 2.8863346104725413e-05, | |
| "loss": 0.0058, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 22.275862068965516, | |
| "grad_norm": 0.9548521041870117, | |
| "learning_rate": 2.8607918263090677e-05, | |
| "loss": 0.0117, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 22.344827586206897, | |
| "grad_norm": 1.6547935009002686, | |
| "learning_rate": 2.835249042145594e-05, | |
| "loss": 0.0424, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 22.413793103448278, | |
| "grad_norm": 6.715394973754883, | |
| "learning_rate": 2.8097062579821203e-05, | |
| "loss": 0.0423, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 22.482758620689655, | |
| "grad_norm": 10.177534103393555, | |
| "learning_rate": 2.7841634738186463e-05, | |
| "loss": 0.2377, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 22.551724137931036, | |
| "grad_norm": 0.11357463151216507, | |
| "learning_rate": 2.7586206896551727e-05, | |
| "loss": 0.0051, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 22.620689655172413, | |
| "grad_norm": 7.2798027992248535, | |
| "learning_rate": 2.733077905491699e-05, | |
| "loss": 0.0687, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 22.689655172413794, | |
| "grad_norm": 2.2690324783325195, | |
| "learning_rate": 2.7075351213282253e-05, | |
| "loss": 0.0163, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 22.75862068965517, | |
| "grad_norm": 0.6616243720054626, | |
| "learning_rate": 2.681992337164751e-05, | |
| "loss": 0.0126, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 22.82758620689655, | |
| "grad_norm": 0.5030643939971924, | |
| "learning_rate": 2.6564495530012773e-05, | |
| "loss": 0.0317, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 22.896551724137932, | |
| "grad_norm": 0.4334893524646759, | |
| "learning_rate": 2.6309067688378037e-05, | |
| "loss": 0.0096, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 22.96551724137931, | |
| "grad_norm": 1.307210087776184, | |
| "learning_rate": 2.6053639846743293e-05, | |
| "loss": 0.0156, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6439393939393939, | |
| "eval_f1_macro": 0.5772056256881202, | |
| "eval_f1_micro": 0.6439393939393939, | |
| "eval_f1_weighted": 0.6233499854025143, | |
| "eval_loss": 1.732154369354248, | |
| "eval_precision_macro": 0.6869692704668073, | |
| "eval_precision_micro": 0.6439393939393939, | |
| "eval_precision_weighted": 0.6597670050256258, | |
| "eval_recall_macro": 0.5802267573696145, | |
| "eval_recall_micro": 0.6439393939393939, | |
| "eval_recall_weighted": 0.6439393939393939, | |
| "eval_runtime": 2.3163, | |
| "eval_samples_per_second": 56.988, | |
| "eval_steps_per_second": 7.339, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 23.03448275862069, | |
| "grad_norm": 9.869407653808594, | |
| "learning_rate": 2.5798212005108557e-05, | |
| "loss": 0.0452, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 23.103448275862068, | |
| "grad_norm": 0.35701480507850647, | |
| "learning_rate": 2.554278416347382e-05, | |
| "loss": 0.0106, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 23.17241379310345, | |
| "grad_norm": 0.22175803780555725, | |
| "learning_rate": 2.5287356321839083e-05, | |
| "loss": 0.0674, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 23.24137931034483, | |
| "grad_norm": 0.5231541395187378, | |
| "learning_rate": 2.5031928480204343e-05, | |
| "loss": 0.022, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 23.310344827586206, | |
| "grad_norm": 5.801222324371338, | |
| "learning_rate": 2.4776500638569607e-05, | |
| "loss": 0.0374, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 23.379310344827587, | |
| "grad_norm": 0.288379967212677, | |
| "learning_rate": 2.4521072796934867e-05, | |
| "loss": 0.0079, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 23.448275862068964, | |
| "grad_norm": 0.34467244148254395, | |
| "learning_rate": 2.426564495530013e-05, | |
| "loss": 0.0058, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 23.517241379310345, | |
| "grad_norm": 2.5069077014923096, | |
| "learning_rate": 2.401021711366539e-05, | |
| "loss": 0.0169, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 23.586206896551722, | |
| "grad_norm": 0.22579370439052582, | |
| "learning_rate": 2.3754789272030653e-05, | |
| "loss": 0.0077, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 23.655172413793103, | |
| "grad_norm": 0.15394940972328186, | |
| "learning_rate": 2.3499361430395913e-05, | |
| "loss": 0.0648, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 23.724137931034484, | |
| "grad_norm": 0.045006781816482544, | |
| "learning_rate": 2.3243933588761177e-05, | |
| "loss": 0.087, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 23.79310344827586, | |
| "grad_norm": 0.6705069541931152, | |
| "learning_rate": 2.2988505747126437e-05, | |
| "loss": 0.0168, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 23.862068965517242, | |
| "grad_norm": 0.20562146604061127, | |
| "learning_rate": 2.27330779054917e-05, | |
| "loss": 0.0059, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 23.93103448275862, | |
| "grad_norm": 0.12316538393497467, | |
| "learning_rate": 2.247765006385696e-05, | |
| "loss": 0.005, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 3.606569528579712, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0275, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6212121212121212, | |
| "eval_f1_macro": 0.5293264604717091, | |
| "eval_f1_micro": 0.6212121212121212, | |
| "eval_f1_weighted": 0.6006327806228502, | |
| "eval_loss": 1.6261619329452515, | |
| "eval_precision_macro": 0.527442388438629, | |
| "eval_precision_micro": 0.6212121212121212, | |
| "eval_precision_weighted": 0.591250595497007, | |
| "eval_recall_macro": 0.5421541950113379, | |
| "eval_recall_micro": 0.6212121212121212, | |
| "eval_recall_weighted": 0.6212121212121212, | |
| "eval_runtime": 2.315, | |
| "eval_samples_per_second": 57.021, | |
| "eval_steps_per_second": 7.344, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 24.06896551724138, | |
| "grad_norm": 0.13560178875923157, | |
| "learning_rate": 2.1966794380587487e-05, | |
| "loss": 0.0063, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 24.137931034482758, | |
| "grad_norm": 0.858462929725647, | |
| "learning_rate": 2.1711366538952747e-05, | |
| "loss": 0.0073, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 24.20689655172414, | |
| "grad_norm": 2.4385788440704346, | |
| "learning_rate": 2.145593869731801e-05, | |
| "loss": 0.0149, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 24.275862068965516, | |
| "grad_norm": 0.1377100646495819, | |
| "learning_rate": 2.120051085568327e-05, | |
| "loss": 0.0034, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 24.344827586206897, | |
| "grad_norm": 1.9415969848632812, | |
| "learning_rate": 2.0945083014048533e-05, | |
| "loss": 0.0675, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 24.413793103448278, | |
| "grad_norm": 0.028621500357985497, | |
| "learning_rate": 2.0689655172413793e-05, | |
| "loss": 0.0062, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 24.482758620689655, | |
| "grad_norm": 0.3451801538467407, | |
| "learning_rate": 2.0434227330779057e-05, | |
| "loss": 0.004, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 24.551724137931036, | |
| "grad_norm": 0.7758638262748718, | |
| "learning_rate": 2.0178799489144317e-05, | |
| "loss": 0.0182, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 24.620689655172413, | |
| "grad_norm": 9.42198371887207, | |
| "learning_rate": 1.992337164750958e-05, | |
| "loss": 0.0647, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 24.689655172413794, | |
| "grad_norm": 0.6298714280128479, | |
| "learning_rate": 1.9667943805874843e-05, | |
| "loss": 0.0108, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 24.75862068965517, | |
| "grad_norm": 0.5104489326477051, | |
| "learning_rate": 1.9412515964240103e-05, | |
| "loss": 0.009, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 24.82758620689655, | |
| "grad_norm": 0.20583294332027435, | |
| "learning_rate": 1.9157088122605367e-05, | |
| "loss": 0.0044, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 24.896551724137932, | |
| "grad_norm": 0.09636816382408142, | |
| "learning_rate": 1.8901660280970627e-05, | |
| "loss": 0.0073, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 24.96551724137931, | |
| "grad_norm": 0.13066060841083527, | |
| "learning_rate": 1.864623243933589e-05, | |
| "loss": 0.0034, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6590909090909091, | |
| "eval_f1_macro": 0.5680281748326861, | |
| "eval_f1_micro": 0.6590909090909091, | |
| "eval_f1_weighted": 0.6409447423921109, | |
| "eval_loss": 1.7278190851211548, | |
| "eval_precision_macro": 0.5673925245094548, | |
| "eval_precision_micro": 0.6590909090909091, | |
| "eval_precision_weighted": 0.6333160386699408, | |
| "eval_recall_macro": 0.5785563114134543, | |
| "eval_recall_micro": 0.6590909090909091, | |
| "eval_recall_weighted": 0.6590909090909091, | |
| "eval_runtime": 2.3069, | |
| "eval_samples_per_second": 57.219, | |
| "eval_steps_per_second": 7.369, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 25.03448275862069, | |
| "grad_norm": 0.1809925138950348, | |
| "learning_rate": 1.839080459770115e-05, | |
| "loss": 0.0291, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 25.103448275862068, | |
| "grad_norm": 0.24622710049152374, | |
| "learning_rate": 1.8135376756066413e-05, | |
| "loss": 0.0196, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 25.17241379310345, | |
| "grad_norm": 0.8039155006408691, | |
| "learning_rate": 1.7879948914431673e-05, | |
| "loss": 0.0187, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 25.24137931034483, | |
| "grad_norm": 0.09927386790513992, | |
| "learning_rate": 1.7624521072796933e-05, | |
| "loss": 0.0444, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 25.310344827586206, | |
| "grad_norm": 0.25122836232185364, | |
| "learning_rate": 1.7369093231162197e-05, | |
| "loss": 0.0032, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 25.379310344827587, | |
| "grad_norm": 0.5785457491874695, | |
| "learning_rate": 1.711366538952746e-05, | |
| "loss": 0.0054, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 25.448275862068964, | |
| "grad_norm": 0.3383479714393616, | |
| "learning_rate": 1.6858237547892723e-05, | |
| "loss": 0.0079, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 25.517241379310345, | |
| "grad_norm": 0.07435264438390732, | |
| "learning_rate": 1.6602809706257983e-05, | |
| "loss": 0.0021, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 25.586206896551722, | |
| "grad_norm": 0.10871023684740067, | |
| "learning_rate": 1.6347381864623247e-05, | |
| "loss": 0.0027, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 25.655172413793103, | |
| "grad_norm": 0.22888857126235962, | |
| "learning_rate": 1.6091954022988507e-05, | |
| "loss": 0.0031, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 25.724137931034484, | |
| "grad_norm": 4.243800640106201, | |
| "learning_rate": 1.583652618135377e-05, | |
| "loss": 0.0211, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 25.79310344827586, | |
| "grad_norm": 0.25736576318740845, | |
| "learning_rate": 1.558109833971903e-05, | |
| "loss": 0.0033, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 25.862068965517242, | |
| "grad_norm": 0.03959902003407478, | |
| "learning_rate": 1.532567049808429e-05, | |
| "loss": 0.0133, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 25.93103448275862, | |
| "grad_norm": 0.07808686792850494, | |
| "learning_rate": 1.5070242656449553e-05, | |
| "loss": 0.0022, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "grad_norm": 0.05853148549795151, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0021, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6439393939393939, | |
| "eval_f1_macro": 0.554181839979619, | |
| "eval_f1_micro": 0.6439393939393939, | |
| "eval_f1_weighted": 0.6249546588712281, | |
| "eval_loss": 1.7111490964889526, | |
| "eval_precision_macro": 0.5506334900131893, | |
| "eval_precision_micro": 0.6439393939393939, | |
| "eval_precision_weighted": 0.6148272110443164, | |
| "eval_recall_macro": 0.5656991685563114, | |
| "eval_recall_micro": 0.6439393939393939, | |
| "eval_recall_weighted": 0.6439393939393939, | |
| "eval_runtime": 2.3159, | |
| "eval_samples_per_second": 56.997, | |
| "eval_steps_per_second": 7.341, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 26.06896551724138, | |
| "grad_norm": 1.2636756896972656, | |
| "learning_rate": 1.4559386973180078e-05, | |
| "loss": 0.008, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 26.137931034482758, | |
| "grad_norm": 0.132855623960495, | |
| "learning_rate": 1.4303959131545338e-05, | |
| "loss": 0.0042, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 26.20689655172414, | |
| "grad_norm": 0.33450737595558167, | |
| "learning_rate": 1.4048531289910602e-05, | |
| "loss": 0.0072, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 26.275862068965516, | |
| "grad_norm": 0.05951528623700142, | |
| "learning_rate": 1.3793103448275863e-05, | |
| "loss": 0.0014, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 26.344827586206897, | |
| "grad_norm": 0.046173300594091415, | |
| "learning_rate": 1.3537675606641127e-05, | |
| "loss": 0.0046, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 26.413793103448278, | |
| "grad_norm": 0.030656151473522186, | |
| "learning_rate": 1.3282247765006387e-05, | |
| "loss": 0.0019, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 26.482758620689655, | |
| "grad_norm": 8.779583930969238, | |
| "learning_rate": 1.3026819923371647e-05, | |
| "loss": 0.0493, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 26.551724137931036, | |
| "grad_norm": 0.07112403959035873, | |
| "learning_rate": 1.277139208173691e-05, | |
| "loss": 0.0019, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 26.620689655172413, | |
| "grad_norm": 0.10120349377393723, | |
| "learning_rate": 1.2515964240102172e-05, | |
| "loss": 0.0039, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 26.689655172413794, | |
| "grad_norm": 0.1142292320728302, | |
| "learning_rate": 1.2260536398467433e-05, | |
| "loss": 0.0036, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 26.75862068965517, | |
| "grad_norm": 0.6233051419258118, | |
| "learning_rate": 1.2005108556832695e-05, | |
| "loss": 0.0043, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 26.82758620689655, | |
| "grad_norm": 0.03758774697780609, | |
| "learning_rate": 1.1749680715197957e-05, | |
| "loss": 0.0106, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 26.896551724137932, | |
| "grad_norm": 1.8201748132705688, | |
| "learning_rate": 1.1494252873563218e-05, | |
| "loss": 0.0569, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 26.96551724137931, | |
| "grad_norm": 0.15079987049102783, | |
| "learning_rate": 1.123882503192848e-05, | |
| "loss": 0.0021, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6439393939393939, | |
| "eval_f1_macro": 0.555558065475334, | |
| "eval_f1_micro": 0.6439393939393939, | |
| "eval_f1_weighted": 0.6256767300352377, | |
| "eval_loss": 1.7411731481552124, | |
| "eval_precision_macro": 0.5507048374905518, | |
| "eval_precision_micro": 0.6439393939393939, | |
| "eval_precision_weighted": 0.616289381914382, | |
| "eval_recall_macro": 0.5684202569916855, | |
| "eval_recall_micro": 0.6439393939393939, | |
| "eval_recall_weighted": 0.6439393939393939, | |
| "eval_runtime": 2.4493, | |
| "eval_samples_per_second": 53.894, | |
| "eval_steps_per_second": 6.941, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 27.03448275862069, | |
| "grad_norm": 0.30042076110839844, | |
| "learning_rate": 1.0983397190293743e-05, | |
| "loss": 0.023, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 27.103448275862068, | |
| "grad_norm": 0.06235335394740105, | |
| "learning_rate": 1.0727969348659005e-05, | |
| "loss": 0.0051, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 27.17241379310345, | |
| "grad_norm": 1.5789542198181152, | |
| "learning_rate": 1.0472541507024267e-05, | |
| "loss": 0.0104, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 27.24137931034483, | |
| "grad_norm": 0.17915375530719757, | |
| "learning_rate": 1.0217113665389528e-05, | |
| "loss": 0.002, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 27.310344827586206, | |
| "grad_norm": 0.71551513671875, | |
| "learning_rate": 9.96168582375479e-06, | |
| "loss": 0.0114, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 27.379310344827587, | |
| "grad_norm": 0.043835002928972244, | |
| "learning_rate": 9.706257982120052e-06, | |
| "loss": 0.0029, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 27.448275862068964, | |
| "grad_norm": 1.4578912258148193, | |
| "learning_rate": 9.450830140485313e-06, | |
| "loss": 0.0388, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 27.517241379310345, | |
| "grad_norm": 0.7825492024421692, | |
| "learning_rate": 9.195402298850575e-06, | |
| "loss": 0.0168, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 27.586206896551722, | |
| "grad_norm": 0.5712390542030334, | |
| "learning_rate": 8.939974457215837e-06, | |
| "loss": 0.0036, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 27.655172413793103, | |
| "grad_norm": 0.05121476203203201, | |
| "learning_rate": 8.684546615581098e-06, | |
| "loss": 0.0019, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 27.724137931034484, | |
| "grad_norm": 0.02635987475514412, | |
| "learning_rate": 8.429118773946362e-06, | |
| "loss": 0.0015, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 27.79310344827586, | |
| "grad_norm": 0.09528487920761108, | |
| "learning_rate": 8.173690932311623e-06, | |
| "loss": 0.0021, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 27.862068965517242, | |
| "grad_norm": 12.712857246398926, | |
| "learning_rate": 7.918263090676885e-06, | |
| "loss": 0.0664, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 27.93103448275862, | |
| "grad_norm": 0.25220927596092224, | |
| "learning_rate": 7.662835249042145e-06, | |
| "loss": 0.0093, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "grad_norm": 0.45354342460632324, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0079, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_f1_macro": 0.5506189724046867, | |
| "eval_f1_micro": 0.6363636363636364, | |
| "eval_f1_weighted": 0.6175532948828404, | |
| "eval_loss": 1.8650879859924316, | |
| "eval_precision_macro": 0.5427141891239254, | |
| "eval_precision_micro": 0.6363636363636364, | |
| "eval_precision_weighted": 0.6077663040137685, | |
| "eval_recall_macro": 0.5670219198790628, | |
| "eval_recall_micro": 0.6363636363636364, | |
| "eval_recall_weighted": 0.6363636363636364, | |
| "eval_runtime": 2.3148, | |
| "eval_samples_per_second": 57.023, | |
| "eval_steps_per_second": 7.344, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 28.06896551724138, | |
| "grad_norm": 1.3216640949249268, | |
| "learning_rate": 7.151979565772669e-06, | |
| "loss": 0.0333, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 28.137931034482758, | |
| "grad_norm": 9.799240112304688, | |
| "learning_rate": 6.896551724137932e-06, | |
| "loss": 0.1634, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 28.20689655172414, | |
| "grad_norm": 0.052395276725292206, | |
| "learning_rate": 6.641123882503193e-06, | |
| "loss": 0.0016, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 28.275862068965516, | |
| "grad_norm": 4.465813159942627, | |
| "learning_rate": 6.385696040868455e-06, | |
| "loss": 0.0404, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 28.344827586206897, | |
| "grad_norm": 2.288407564163208, | |
| "learning_rate": 6.130268199233717e-06, | |
| "loss": 0.0091, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 28.413793103448278, | |
| "grad_norm": 0.025375355035066605, | |
| "learning_rate": 5.874840357598978e-06, | |
| "loss": 0.0011, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 28.482758620689655, | |
| "grad_norm": 0.16025374829769135, | |
| "learning_rate": 5.61941251596424e-06, | |
| "loss": 0.003, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 28.551724137931036, | |
| "grad_norm": 0.03463875502347946, | |
| "learning_rate": 5.3639846743295025e-06, | |
| "loss": 0.0093, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 28.620689655172413, | |
| "grad_norm": 0.12321082502603531, | |
| "learning_rate": 5.108556832694764e-06, | |
| "loss": 0.0103, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 28.689655172413794, | |
| "grad_norm": 0.22069355845451355, | |
| "learning_rate": 4.853128991060026e-06, | |
| "loss": 0.0025, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 28.75862068965517, | |
| "grad_norm": 0.04350389167666435, | |
| "learning_rate": 4.5977011494252875e-06, | |
| "loss": 0.0024, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 28.82758620689655, | |
| "grad_norm": 0.0725034549832344, | |
| "learning_rate": 4.342273307790549e-06, | |
| "loss": 0.0025, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 28.896551724137932, | |
| "grad_norm": 0.0820830762386322, | |
| "learning_rate": 4.086845466155812e-06, | |
| "loss": 0.0044, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 28.96551724137931, | |
| "grad_norm": 0.12842264771461487, | |
| "learning_rate": 3.8314176245210725e-06, | |
| "loss": 0.0018, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_f1_macro": 0.550809139380568, | |
| "eval_f1_micro": 0.6363636363636364, | |
| "eval_f1_weighted": 0.6183867102048921, | |
| "eval_loss": 1.8015811443328857, | |
| "eval_precision_macro": 0.5424965742265075, | |
| "eval_precision_micro": 0.6363636363636364, | |
| "eval_precision_weighted": 0.6074053566447076, | |
| "eval_recall_macro": 0.5654346182917611, | |
| "eval_recall_micro": 0.6363636363636364, | |
| "eval_recall_weighted": 0.6363636363636364, | |
| "eval_runtime": 2.3209, | |
| "eval_samples_per_second": 56.875, | |
| "eval_steps_per_second": 7.325, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 29.03448275862069, | |
| "grad_norm": 0.04786275699734688, | |
| "learning_rate": 3.5759897828863346e-06, | |
| "loss": 0.0016, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 29.103448275862068, | |
| "grad_norm": 0.12234374135732651, | |
| "learning_rate": 3.3205619412515967e-06, | |
| "loss": 0.0024, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 29.17241379310345, | |
| "grad_norm": 1.1938027143478394, | |
| "learning_rate": 3.0651340996168583e-06, | |
| "loss": 0.0247, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 29.24137931034483, | |
| "grad_norm": 0.06169275566935539, | |
| "learning_rate": 2.80970625798212e-06, | |
| "loss": 0.0019, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 29.310344827586206, | |
| "grad_norm": 0.05622587725520134, | |
| "learning_rate": 2.554278416347382e-06, | |
| "loss": 0.0048, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 29.379310344827587, | |
| "grad_norm": 1.4125478267669678, | |
| "learning_rate": 2.2988505747126437e-06, | |
| "loss": 0.0341, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 29.448275862068964, | |
| "grad_norm": 0.7389807105064392, | |
| "learning_rate": 2.043422733077906e-06, | |
| "loss": 0.0063, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 29.517241379310345, | |
| "grad_norm": 0.1219203844666481, | |
| "learning_rate": 1.7879948914431673e-06, | |
| "loss": 0.0024, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 29.586206896551722, | |
| "grad_norm": 0.02140001207590103, | |
| "learning_rate": 1.5325670498084292e-06, | |
| "loss": 0.001, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 29.655172413793103, | |
| "grad_norm": 0.16312941908836365, | |
| "learning_rate": 1.277139208173691e-06, | |
| "loss": 0.0051, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 29.724137931034484, | |
| "grad_norm": 0.09436585009098053, | |
| "learning_rate": 1.021711366538953e-06, | |
| "loss": 0.0027, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 29.79310344827586, | |
| "grad_norm": 0.05503632500767708, | |
| "learning_rate": 7.662835249042146e-07, | |
| "loss": 0.0013, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 29.862068965517242, | |
| "grad_norm": 0.17716890573501587, | |
| "learning_rate": 5.108556832694765e-07, | |
| "loss": 0.0038, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 29.93103448275862, | |
| "grad_norm": 0.061406251043081284, | |
| "learning_rate": 2.5542784163473823e-07, | |
| "loss": 0.0235, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.027203461155295372, | |
| "learning_rate": 0.0, | |
| "loss": 0.0068, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_f1_macro": 0.5510361100016273, | |
| "eval_f1_micro": 0.6363636363636364, | |
| "eval_f1_weighted": 0.6182163433025503, | |
| "eval_loss": 1.793615460395813, | |
| "eval_precision_macro": 0.5435933453841307, | |
| "eval_precision_micro": 0.6363636363636364, | |
| "eval_precision_weighted": 0.6073074998024288, | |
| "eval_recall_macro": 0.5650113378684807, | |
| "eval_recall_micro": 0.6363636363636364, | |
| "eval_recall_weighted": 0.6363636363636364, | |
| "eval_runtime": 2.3235, | |
| "eval_samples_per_second": 56.811, | |
| "eval_steps_per_second": 7.317, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 870, | |
| "total_flos": 1.0740871074163507e+18, | |
| "train_loss": 0.5336226776871167, | |
| "train_runtime": 850.3912, | |
| "train_samples_per_second": 16.298, | |
| "train_steps_per_second": 1.023 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 870, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "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": 1.0740871074163507e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |