| { | |
| "best_metric": 0.6666666666666666, | |
| "best_model_checkpoint": "/data/data2/azhar/mine/testing_chamber/bpn-mining-model/swin-transformer3/checkpoint-532", | |
| "epoch": 99.24812030075188, | |
| "eval_steps": 500, | |
| "global_step": 3300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 14.913878440856934, | |
| "learning_rate": 1.5151515151515152e-06, | |
| "loss": 2.3582, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "grad_norm": 15.318342208862305, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 2.1222, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9022556390977443, | |
| "grad_norm": 20.099170684814453, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.6659, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9924812030075187, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_f1": 0.624952380952381, | |
| "eval_loss": 1.0638588666915894, | |
| "eval_runtime": 6.7375, | |
| "eval_samples_per_second": 8.905, | |
| "eval_steps_per_second": 2.226, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2030075187969924, | |
| "grad_norm": 18.861299514770508, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 1.0907, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5037593984962405, | |
| "grad_norm": 14.466804504394531, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.8232, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8045112781954886, | |
| "grad_norm": 21.599777221679688, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.7561, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.9849624060150375, | |
| "eval_accuracy": 0.5166666666666667, | |
| "eval_f1": 0.352014652014652, | |
| "eval_loss": 0.7257525324821472, | |
| "eval_runtime": 6.3119, | |
| "eval_samples_per_second": 9.506, | |
| "eval_steps_per_second": 2.376, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 8.610815048217773, | |
| "learning_rate": 1.0606060606060607e-05, | |
| "loss": 0.7409, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.406015037593985, | |
| "grad_norm": 7.523438930511475, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 0.7021, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.706766917293233, | |
| "grad_norm": 17.187030792236328, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 0.7106, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.9774436090225564, | |
| "eval_accuracy": 0.5, | |
| "eval_f1": 0.3755129958960329, | |
| "eval_loss": 0.7334391474723816, | |
| "eval_runtime": 6.4801, | |
| "eval_samples_per_second": 9.259, | |
| "eval_steps_per_second": 2.315, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.007518796992481, | |
| "grad_norm": 20.541980743408203, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.6882, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.308270676691729, | |
| "grad_norm": 18.346364974975586, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.7986, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.6090225563909772, | |
| "grad_norm": 14.835421562194824, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.721, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.909774436090226, | |
| "grad_norm": 5.117762565612793, | |
| "learning_rate": 1.9696969696969697e-05, | |
| "loss": 0.6749, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_f1": 0.3661064425770308, | |
| "eval_loss": 0.7087975740432739, | |
| "eval_runtime": 6.5607, | |
| "eval_samples_per_second": 9.145, | |
| "eval_steps_per_second": 2.286, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 4.2105263157894735, | |
| "grad_norm": 5.199806213378906, | |
| "learning_rate": 2.1212121212121215e-05, | |
| "loss": 0.6836, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.511278195488722, | |
| "grad_norm": 5.881252288818359, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.7035, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.81203007518797, | |
| "grad_norm": 19.35033416748047, | |
| "learning_rate": 2.4242424242424244e-05, | |
| "loss": 0.751, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.992481203007519, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_f1": 0.3661064425770308, | |
| "eval_loss": 0.735622763633728, | |
| "eval_runtime": 6.9036, | |
| "eval_samples_per_second": 8.691, | |
| "eval_steps_per_second": 2.173, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 5.112781954887218, | |
| "grad_norm": 9.151863098144531, | |
| "learning_rate": 2.575757575757576e-05, | |
| "loss": 0.6634, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.413533834586466, | |
| "grad_norm": 23.333147048950195, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 0.7291, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 5.380008220672607, | |
| "learning_rate": 2.878787878787879e-05, | |
| "loss": 0.7146, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.984962406015038, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_f1": 0.3149812734082397, | |
| "eval_loss": 0.7836605310440063, | |
| "eval_runtime": 6.6834, | |
| "eval_samples_per_second": 8.977, | |
| "eval_steps_per_second": 2.244, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 6.015037593984962, | |
| "grad_norm": 5.286394119262695, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.7468, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.315789473684211, | |
| "grad_norm": 6.3437323570251465, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.6837, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.616541353383458, | |
| "grad_norm": 22.48058319091797, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7065, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 6.917293233082707, | |
| "grad_norm": 10.246678352355957, | |
| "learning_rate": 3.484848484848485e-05, | |
| "loss": 0.6699, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.977443609022556, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_f1": 0.34242424242424246, | |
| "eval_loss": 0.75690758228302, | |
| "eval_runtime": 6.5095, | |
| "eval_samples_per_second": 9.217, | |
| "eval_steps_per_second": 2.304, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 7.2180451127819545, | |
| "grad_norm": 6.964570045471191, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.6882, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 7.518796992481203, | |
| "grad_norm": 11.94023609161377, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.6776, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.819548872180452, | |
| "grad_norm": 10.98417854309082, | |
| "learning_rate": 3.939393939393939e-05, | |
| "loss": 0.6521, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.4674368848951647, | |
| "eval_loss": 0.7255270481109619, | |
| "eval_runtime": 6.3154, | |
| "eval_samples_per_second": 9.501, | |
| "eval_steps_per_second": 2.375, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 8.1203007518797, | |
| "grad_norm": 22.907865524291992, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 0.7176, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.421052631578947, | |
| "grad_norm": 10.256561279296875, | |
| "learning_rate": 4.242424242424243e-05, | |
| "loss": 0.5968, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.721804511278195, | |
| "grad_norm": 18.539447784423828, | |
| "learning_rate": 4.3939393939393944e-05, | |
| "loss": 0.6885, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 8.992481203007518, | |
| "eval_accuracy": 0.5166666666666667, | |
| "eval_f1": 0.4070028011204482, | |
| "eval_loss": 0.7252522706985474, | |
| "eval_runtime": 6.719, | |
| "eval_samples_per_second": 8.93, | |
| "eval_steps_per_second": 2.232, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 9.022556390977444, | |
| "grad_norm": 4.7263336181640625, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.7568, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.323308270676693, | |
| "grad_norm": 11.226090431213379, | |
| "learning_rate": 4.696969696969697e-05, | |
| "loss": 0.6667, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.62406015037594, | |
| "grad_norm": 20.75147819519043, | |
| "learning_rate": 4.848484848484849e-05, | |
| "loss": 0.6658, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 9.924812030075188, | |
| "grad_norm": 23.47601318359375, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6407, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 9.984962406015038, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5908571428571429, | |
| "eval_loss": 0.6506010890007019, | |
| "eval_runtime": 6.6092, | |
| "eval_samples_per_second": 9.078, | |
| "eval_steps_per_second": 2.27, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 10.225563909774436, | |
| "grad_norm": 14.811893463134766, | |
| "learning_rate": 4.983164983164983e-05, | |
| "loss": 0.654, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.526315789473685, | |
| "grad_norm": 10.347320556640625, | |
| "learning_rate": 4.966329966329967e-05, | |
| "loss": 0.6607, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 10.827067669172932, | |
| "grad_norm": 10.15239143371582, | |
| "learning_rate": 4.94949494949495e-05, | |
| "loss": 0.6436, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 10.977443609022556, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.44420062695924767, | |
| "eval_loss": 0.6720244288444519, | |
| "eval_runtime": 6.5965, | |
| "eval_samples_per_second": 9.096, | |
| "eval_steps_per_second": 2.274, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 11.12781954887218, | |
| "grad_norm": 10.023416519165039, | |
| "learning_rate": 4.932659932659932e-05, | |
| "loss": 0.7135, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 13.441643714904785, | |
| "learning_rate": 4.915824915824916e-05, | |
| "loss": 0.6766, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 11.729323308270677, | |
| "grad_norm": 12.908476829528809, | |
| "learning_rate": 4.898989898989899e-05, | |
| "loss": 0.7865, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.47922500814067076, | |
| "eval_loss": 0.6605614423751831, | |
| "eval_runtime": 6.4866, | |
| "eval_samples_per_second": 9.25, | |
| "eval_steps_per_second": 2.312, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 12.030075187969924, | |
| "grad_norm": 8.809733390808105, | |
| "learning_rate": 4.882154882154882e-05, | |
| "loss": 0.7082, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.330827067669173, | |
| "grad_norm": 8.784128189086914, | |
| "learning_rate": 4.865319865319866e-05, | |
| "loss": 0.656, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 12.631578947368421, | |
| "grad_norm": 5.786237716674805, | |
| "learning_rate": 4.848484848484849e-05, | |
| "loss": 0.6632, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 12.93233082706767, | |
| "grad_norm": 35.784297943115234, | |
| "learning_rate": 4.831649831649832e-05, | |
| "loss": 0.7191, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 12.992481203007518, | |
| "eval_accuracy": 0.65, | |
| "eval_f1": 0.6465502675302731, | |
| "eval_loss": 0.6406596899032593, | |
| "eval_runtime": 6.6562, | |
| "eval_samples_per_second": 9.014, | |
| "eval_steps_per_second": 2.254, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 13.233082706766917, | |
| "grad_norm": 16.550561904907227, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.6126, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 13.533834586466165, | |
| "grad_norm": 6.941432476043701, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 0.6654, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 13.834586466165414, | |
| "grad_norm": 16.613155364990234, | |
| "learning_rate": 4.7811447811447815e-05, | |
| "loss": 0.5889, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 13.984962406015038, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_f1": 0.3618599791013584, | |
| "eval_loss": 0.8008177876472473, | |
| "eval_runtime": 6.5666, | |
| "eval_samples_per_second": 9.137, | |
| "eval_steps_per_second": 2.284, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 14.135338345864662, | |
| "grad_norm": 5.850649833679199, | |
| "learning_rate": 4.7643097643097646e-05, | |
| "loss": 0.7016, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 14.436090225563909, | |
| "grad_norm": 3.8176016807556152, | |
| "learning_rate": 4.7474747474747476e-05, | |
| "loss": 0.6036, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 14.736842105263158, | |
| "grad_norm": 14.288350105285645, | |
| "learning_rate": 4.730639730639731e-05, | |
| "loss": 0.5489, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 14.977443609022556, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.4674368848951647, | |
| "eval_loss": 0.729806661605835, | |
| "eval_runtime": 8.5173, | |
| "eval_samples_per_second": 7.044, | |
| "eval_steps_per_second": 1.761, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 15.037593984962406, | |
| "grad_norm": 17.23583221435547, | |
| "learning_rate": 4.713804713804714e-05, | |
| "loss": 0.6795, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.338345864661655, | |
| "grad_norm": 3.6928858757019043, | |
| "learning_rate": 4.696969696969697e-05, | |
| "loss": 0.6264, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 15.639097744360903, | |
| "grad_norm": 22.685209274291992, | |
| "learning_rate": 4.68013468013468e-05, | |
| "loss": 0.593, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 15.93984962406015, | |
| "grad_norm": 7.016318321228027, | |
| "learning_rate": 4.6632996632996634e-05, | |
| "loss": 0.596, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_f1": 0.6591251885369532, | |
| "eval_loss": 0.746545135974884, | |
| "eval_runtime": 6.6407, | |
| "eval_samples_per_second": 9.035, | |
| "eval_steps_per_second": 2.259, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 16.2406015037594, | |
| "grad_norm": 13.344483375549316, | |
| "learning_rate": 4.6464646464646464e-05, | |
| "loss": 0.6249, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 16.541353383458645, | |
| "grad_norm": 10.184150695800781, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5373, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 16.842105263157894, | |
| "grad_norm": 16.70218849182129, | |
| "learning_rate": 4.612794612794613e-05, | |
| "loss": 0.6136, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 16.992481203007518, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.4691666666666666, | |
| "eval_loss": 0.9117582440376282, | |
| "eval_runtime": 6.56, | |
| "eval_samples_per_second": 9.146, | |
| "eval_steps_per_second": 2.287, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 31.319522857666016, | |
| "learning_rate": 4.595959595959596e-05, | |
| "loss": 0.6073, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 17.44360902255639, | |
| "grad_norm": 18.976797103881836, | |
| "learning_rate": 4.57912457912458e-05, | |
| "loss": 0.5716, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 17.74436090225564, | |
| "grad_norm": 18.692249298095703, | |
| "learning_rate": 4.562289562289562e-05, | |
| "loss": 0.5961, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 17.984962406015036, | |
| "eval_accuracy": 0.65, | |
| "eval_f1": 0.6297777777777778, | |
| "eval_loss": 0.690215528011322, | |
| "eval_runtime": 7.0118, | |
| "eval_samples_per_second": 8.557, | |
| "eval_steps_per_second": 2.139, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 18.045112781954888, | |
| "grad_norm": 56.27545928955078, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.5696, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 18.345864661654137, | |
| "grad_norm": 19.565650939941406, | |
| "learning_rate": 4.528619528619529e-05, | |
| "loss": 0.6346, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 18.646616541353385, | |
| "grad_norm": 12.217280387878418, | |
| "learning_rate": 4.511784511784512e-05, | |
| "loss": 0.4669, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 18.94736842105263, | |
| "grad_norm": 33.36597442626953, | |
| "learning_rate": 4.494949494949495e-05, | |
| "loss": 0.6327, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 18.977443609022558, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.519047619047619, | |
| "eval_loss": 0.8260101079940796, | |
| "eval_runtime": 6.5494, | |
| "eval_samples_per_second": 9.161, | |
| "eval_steps_per_second": 2.29, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 19.24812030075188, | |
| "grad_norm": 25.23843002319336, | |
| "learning_rate": 4.4781144781144786e-05, | |
| "loss": 0.5808, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 19.548872180451127, | |
| "grad_norm": 14.927197456359863, | |
| "learning_rate": 4.4612794612794616e-05, | |
| "loss": 0.5018, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 19.849624060150376, | |
| "grad_norm": 16.2906436920166, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.6518, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5714764779151096, | |
| "eval_loss": 0.6918700933456421, | |
| "eval_runtime": 6.4139, | |
| "eval_samples_per_second": 9.355, | |
| "eval_steps_per_second": 2.339, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 20.150375939849624, | |
| "grad_norm": 11.751864433288574, | |
| "learning_rate": 4.427609427609428e-05, | |
| "loss": 0.499, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 20.451127819548873, | |
| "grad_norm": 24.952850341796875, | |
| "learning_rate": 4.410774410774411e-05, | |
| "loss": 0.5204, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 20.75187969924812, | |
| "grad_norm": 7.636977195739746, | |
| "learning_rate": 4.3939393939393944e-05, | |
| "loss": 0.5551, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 20.992481203007518, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.516, | |
| "eval_loss": 1.1780269145965576, | |
| "eval_runtime": 6.7584, | |
| "eval_samples_per_second": 8.878, | |
| "eval_steps_per_second": 2.219, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 21.05263157894737, | |
| "grad_norm": 28.386489868164062, | |
| "learning_rate": 4.3771043771043774e-05, | |
| "loss": 0.6306, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 21.353383458646615, | |
| "grad_norm": 9.98483657836914, | |
| "learning_rate": 4.3602693602693604e-05, | |
| "loss": 0.443, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 21.654135338345863, | |
| "grad_norm": 15.316218376159668, | |
| "learning_rate": 4.343434343434344e-05, | |
| "loss": 0.5148, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 21.954887218045112, | |
| "grad_norm": 17.753332138061523, | |
| "learning_rate": 4.3265993265993265e-05, | |
| "loss": 0.511, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 21.984962406015036, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.6, | |
| "eval_loss": 0.7414445281028748, | |
| "eval_runtime": 6.8006, | |
| "eval_samples_per_second": 8.823, | |
| "eval_steps_per_second": 2.206, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 22.25563909774436, | |
| "grad_norm": 44.12444305419922, | |
| "learning_rate": 4.3097643097643095e-05, | |
| "loss": 0.5268, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 22.55639097744361, | |
| "grad_norm": 25.069778442382812, | |
| "learning_rate": 4.292929292929293e-05, | |
| "loss": 0.5273, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 9.567957878112793, | |
| "learning_rate": 4.276094276094276e-05, | |
| "loss": 0.4749, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 22.977443609022558, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.612888388247442, | |
| "eval_loss": 0.7978177666664124, | |
| "eval_runtime": 6.5763, | |
| "eval_samples_per_second": 9.124, | |
| "eval_steps_per_second": 2.281, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 23.157894736842106, | |
| "grad_norm": 32.95903396606445, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.5124, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 23.458646616541355, | |
| "grad_norm": 13.2031831741333, | |
| "learning_rate": 4.242424242424243e-05, | |
| "loss": 0.577, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 23.7593984962406, | |
| "grad_norm": 28.219993591308594, | |
| "learning_rate": 4.225589225589226e-05, | |
| "loss": 0.4607, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5420163334272036, | |
| "eval_loss": 0.8087051510810852, | |
| "eval_runtime": 6.5355, | |
| "eval_samples_per_second": 9.181, | |
| "eval_steps_per_second": 2.295, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 24.06015037593985, | |
| "grad_norm": 7.048239707946777, | |
| "learning_rate": 4.208754208754209e-05, | |
| "loss": 0.4982, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 24.360902255639097, | |
| "grad_norm": 8.705081939697266, | |
| "learning_rate": 4.191919191919192e-05, | |
| "loss": 0.4764, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 24.661654135338345, | |
| "grad_norm": 14.514195442199707, | |
| "learning_rate": 4.175084175084175e-05, | |
| "loss": 0.4705, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 24.962406015037594, | |
| "grad_norm": 15.823882102966309, | |
| "learning_rate": 4.158249158249159e-05, | |
| "loss": 0.5837, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 24.992481203007518, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5456018518518518, | |
| "eval_loss": 0.827062726020813, | |
| "eval_runtime": 6.6423, | |
| "eval_samples_per_second": 9.033, | |
| "eval_steps_per_second": 2.258, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 25.263157894736842, | |
| "grad_norm": 40.25634765625, | |
| "learning_rate": 4.141414141414142e-05, | |
| "loss": 0.5328, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 25.56390977443609, | |
| "grad_norm": 35.79170227050781, | |
| "learning_rate": 4.124579124579125e-05, | |
| "loss": 0.5592, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 25.86466165413534, | |
| "grad_norm": 30.948213577270508, | |
| "learning_rate": 4.1077441077441085e-05, | |
| "loss": 0.4608, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 25.984962406015036, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5862857142857142, | |
| "eval_loss": 0.853912353515625, | |
| "eval_runtime": 7.1127, | |
| "eval_samples_per_second": 8.436, | |
| "eval_steps_per_second": 2.109, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 26.165413533834588, | |
| "grad_norm": 16.665449142456055, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 0.4597, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 26.466165413533833, | |
| "grad_norm": 15.06215763092041, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.3808, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 26.76691729323308, | |
| "grad_norm": 16.880653381347656, | |
| "learning_rate": 4.0572390572390575e-05, | |
| "loss": 0.536, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 26.977443609022558, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.5026243634939287, | |
| "eval_loss": 0.9802255034446716, | |
| "eval_runtime": 6.3964, | |
| "eval_samples_per_second": 9.38, | |
| "eval_steps_per_second": 2.345, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 27.06766917293233, | |
| "grad_norm": 22.354326248168945, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.5231, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 27.36842105263158, | |
| "grad_norm": 21.1690731048584, | |
| "learning_rate": 4.0235690235690236e-05, | |
| "loss": 0.4904, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 27.669172932330827, | |
| "grad_norm": 45.88932800292969, | |
| "learning_rate": 4.006734006734007e-05, | |
| "loss": 0.4966, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 27.969924812030076, | |
| "grad_norm": 16.252901077270508, | |
| "learning_rate": 3.98989898989899e-05, | |
| "loss": 0.4225, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5909502262443439, | |
| "eval_loss": 0.9274828433990479, | |
| "eval_runtime": 6.4885, | |
| "eval_samples_per_second": 9.247, | |
| "eval_steps_per_second": 2.312, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 28.270676691729324, | |
| "grad_norm": 24.86367416381836, | |
| "learning_rate": 3.973063973063973e-05, | |
| "loss": 0.4523, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 59.121612548828125, | |
| "learning_rate": 3.956228956228956e-05, | |
| "loss": 0.4359, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 28.872180451127818, | |
| "grad_norm": 23.139965057373047, | |
| "learning_rate": 3.939393939393939e-05, | |
| "loss": 0.4325, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 28.992481203007518, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.6098657655120623, | |
| "eval_loss": 0.8834265470504761, | |
| "eval_runtime": 6.8775, | |
| "eval_samples_per_second": 8.724, | |
| "eval_steps_per_second": 2.181, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 29.172932330827066, | |
| "grad_norm": 28.827287673950195, | |
| "learning_rate": 3.9225589225589224e-05, | |
| "loss": 0.4721, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 29.473684210526315, | |
| "grad_norm": 16.462913513183594, | |
| "learning_rate": 3.905723905723906e-05, | |
| "loss": 0.4941, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 29.774436090225564, | |
| "grad_norm": 21.16120719909668, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.4874, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 29.984962406015036, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.616773177734556, | |
| "eval_loss": 0.8720671534538269, | |
| "eval_runtime": 6.6224, | |
| "eval_samples_per_second": 9.06, | |
| "eval_steps_per_second": 2.265, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 30.075187969924812, | |
| "grad_norm": 14.207987785339355, | |
| "learning_rate": 3.872053872053872e-05, | |
| "loss": 0.5007, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 30.37593984962406, | |
| "grad_norm": 6.5519537925720215, | |
| "learning_rate": 3.855218855218856e-05, | |
| "loss": 0.4059, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 30.67669172932331, | |
| "grad_norm": 8.17160415649414, | |
| "learning_rate": 3.838383838383838e-05, | |
| "loss": 0.3861, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 30.977443609022558, | |
| "grad_norm": 19.54429817199707, | |
| "learning_rate": 3.821548821548822e-05, | |
| "loss": 0.4165, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 30.977443609022558, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.616347133462999, | |
| "eval_loss": 1.0359536409378052, | |
| "eval_runtime": 6.5574, | |
| "eval_samples_per_second": 9.15, | |
| "eval_steps_per_second": 2.287, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 31.278195488721803, | |
| "grad_norm": 23.49751091003418, | |
| "learning_rate": 3.804713804713805e-05, | |
| "loss": 0.4572, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 31.57894736842105, | |
| "grad_norm": 9.040291786193848, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.3131, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 31.8796992481203, | |
| "grad_norm": 7.378245830535889, | |
| "learning_rate": 3.7710437710437716e-05, | |
| "loss": 0.4773, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.575941049469633, | |
| "eval_loss": 1.2209875583648682, | |
| "eval_runtime": 6.5797, | |
| "eval_samples_per_second": 9.119, | |
| "eval_steps_per_second": 2.28, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 32.18045112781955, | |
| "grad_norm": 15.682769775390625, | |
| "learning_rate": 3.7542087542087546e-05, | |
| "loss": 0.3388, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 32.4812030075188, | |
| "grad_norm": 19.28175163269043, | |
| "learning_rate": 3.7373737373737376e-05, | |
| "loss": 0.3307, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 32.78195488721804, | |
| "grad_norm": 14.588042259216309, | |
| "learning_rate": 3.720538720538721e-05, | |
| "loss": 0.3756, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 32.99248120300752, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5829860146336946, | |
| "eval_loss": 1.1291446685791016, | |
| "eval_runtime": 6.8244, | |
| "eval_samples_per_second": 8.792, | |
| "eval_steps_per_second": 2.198, | |
| "step": 1097 | |
| }, | |
| { | |
| "epoch": 33.08270676691729, | |
| "grad_norm": 13.086041450500488, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4182, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 33.38345864661654, | |
| "grad_norm": 5.811966419219971, | |
| "learning_rate": 3.686868686868687e-05, | |
| "loss": 0.3508, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 33.68421052631579, | |
| "grad_norm": 81.32879638671875, | |
| "learning_rate": 3.6700336700336704e-05, | |
| "loss": 0.3672, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 33.984962406015036, | |
| "grad_norm": 5.003579616546631, | |
| "learning_rate": 3.6531986531986534e-05, | |
| "loss": 0.636, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 33.984962406015036, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5829860146336946, | |
| "eval_loss": 1.0177818536758423, | |
| "eval_runtime": 6.5487, | |
| "eval_samples_per_second": 9.162, | |
| "eval_steps_per_second": 2.291, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 8.781743049621582, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.3774, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 34.58646616541353, | |
| "grad_norm": 57.26716232299805, | |
| "learning_rate": 3.61952861952862e-05, | |
| "loss": 0.4032, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 34.88721804511278, | |
| "grad_norm": 21.142290115356445, | |
| "learning_rate": 3.602693602693603e-05, | |
| "loss": 0.5474, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 34.97744360902256, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5608305274971942, | |
| "eval_loss": 0.9478945136070251, | |
| "eval_runtime": 6.7769, | |
| "eval_samples_per_second": 8.854, | |
| "eval_steps_per_second": 2.213, | |
| "step": 1163 | |
| }, | |
| { | |
| "epoch": 35.18796992481203, | |
| "grad_norm": 27.60926055908203, | |
| "learning_rate": 3.5858585858585855e-05, | |
| "loss": 0.3429, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 35.48872180451128, | |
| "grad_norm": 12.224372863769531, | |
| "learning_rate": 3.569023569023569e-05, | |
| "loss": 0.4284, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 35.78947368421053, | |
| "grad_norm": 13.833395004272461, | |
| "learning_rate": 3.552188552188552e-05, | |
| "loss": 0.3462, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.6163464216095794, | |
| "eval_loss": 0.9584738612174988, | |
| "eval_runtime": 6.5533, | |
| "eval_samples_per_second": 9.156, | |
| "eval_steps_per_second": 2.289, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 36.090225563909776, | |
| "grad_norm": 10.387247085571289, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.2622, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 36.390977443609025, | |
| "grad_norm": 16.11662483215332, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.3035, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 36.69172932330827, | |
| "grad_norm": 60.57283401489258, | |
| "learning_rate": 3.501683501683502e-05, | |
| "loss": 0.4646, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 36.99248120300752, | |
| "grad_norm": 11.045464515686035, | |
| "learning_rate": 3.484848484848485e-05, | |
| "loss": 0.3057, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 36.99248120300752, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.6163464216095794, | |
| "eval_loss": 1.2013615369796753, | |
| "eval_runtime": 7.009, | |
| "eval_samples_per_second": 8.56, | |
| "eval_steps_per_second": 2.14, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 37.29323308270677, | |
| "grad_norm": 20.90575408935547, | |
| "learning_rate": 3.468013468013468e-05, | |
| "loss": 0.3392, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 37.59398496240601, | |
| "grad_norm": 5.260161399841309, | |
| "learning_rate": 3.451178451178451e-05, | |
| "loss": 0.2822, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 37.89473684210526, | |
| "grad_norm": 10.245043754577637, | |
| "learning_rate": 3.434343434343435e-05, | |
| "loss": 0.2304, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 37.984962406015036, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_f1": 0.6333333333333333, | |
| "eval_loss": 1.1975445747375488, | |
| "eval_runtime": 6.8757, | |
| "eval_samples_per_second": 8.726, | |
| "eval_steps_per_second": 2.182, | |
| "step": 1263 | |
| }, | |
| { | |
| "epoch": 38.19548872180451, | |
| "grad_norm": 5.8279242515563965, | |
| "learning_rate": 3.417508417508418e-05, | |
| "loss": 0.3548, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 38.49624060150376, | |
| "grad_norm": 30.216154098510742, | |
| "learning_rate": 3.400673400673401e-05, | |
| "loss": 0.246, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 38.796992481203006, | |
| "grad_norm": 18.291364669799805, | |
| "learning_rate": 3.3838383838383844e-05, | |
| "loss": 0.2628, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 38.97744360902256, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5792540792540792, | |
| "eval_loss": 1.5224032402038574, | |
| "eval_runtime": 6.6333, | |
| "eval_samples_per_second": 9.045, | |
| "eval_steps_per_second": 2.261, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 39.097744360902254, | |
| "grad_norm": 29.24486541748047, | |
| "learning_rate": 3.3670033670033675e-05, | |
| "loss": 0.2907, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 39.3984962406015, | |
| "grad_norm": 10.511560440063477, | |
| "learning_rate": 3.35016835016835e-05, | |
| "loss": 0.3166, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 39.69924812030075, | |
| "grad_norm": 9.040928840637207, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2413, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 10.92233657836914, | |
| "learning_rate": 3.3164983164983165e-05, | |
| "loss": 0.3774, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5516203703703704, | |
| "eval_loss": 1.2903040647506714, | |
| "eval_runtime": 6.6687, | |
| "eval_samples_per_second": 8.997, | |
| "eval_steps_per_second": 2.249, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 40.30075187969925, | |
| "grad_norm": 14.264669418334961, | |
| "learning_rate": 3.2996632996632995e-05, | |
| "loss": 0.3152, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 40.6015037593985, | |
| "grad_norm": 21.567790985107422, | |
| "learning_rate": 3.282828282828283e-05, | |
| "loss": 0.3674, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 40.902255639097746, | |
| "grad_norm": 42.34912109375, | |
| "learning_rate": 3.265993265993266e-05, | |
| "loss": 0.2604, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 40.99248120300752, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5608305274971942, | |
| "eval_loss": 1.408166527748108, | |
| "eval_runtime": 6.9727, | |
| "eval_samples_per_second": 8.605, | |
| "eval_steps_per_second": 2.151, | |
| "step": 1363 | |
| }, | |
| { | |
| "epoch": 41.203007518796994, | |
| "grad_norm": 10.318882942199707, | |
| "learning_rate": 3.249158249158249e-05, | |
| "loss": 0.2682, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 41.50375939849624, | |
| "grad_norm": 12.875001907348633, | |
| "learning_rate": 3.232323232323233e-05, | |
| "loss": 0.2848, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 41.80451127819549, | |
| "grad_norm": 50.29880905151367, | |
| "learning_rate": 3.215488215488215e-05, | |
| "loss": 0.2522, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 41.984962406015036, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.616347133462999, | |
| "eval_loss": 1.178326964378357, | |
| "eval_runtime": 6.8032, | |
| "eval_samples_per_second": 8.819, | |
| "eval_steps_per_second": 2.205, | |
| "step": 1396 | |
| }, | |
| { | |
| "epoch": 42.10526315789474, | |
| "grad_norm": 47.25193405151367, | |
| "learning_rate": 3.198653198653199e-05, | |
| "loss": 0.4457, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 42.40601503759399, | |
| "grad_norm": 12.840446472167969, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.2781, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 42.70676691729323, | |
| "grad_norm": 12.884856224060059, | |
| "learning_rate": 3.164983164983165e-05, | |
| "loss": 0.1925, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 42.97744360902256, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.616347133462999, | |
| "eval_loss": 1.3612515926361084, | |
| "eval_runtime": 6.6918, | |
| "eval_samples_per_second": 8.966, | |
| "eval_steps_per_second": 2.242, | |
| "step": 1429 | |
| }, | |
| { | |
| "epoch": 43.00751879699248, | |
| "grad_norm": 24.348125457763672, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.2576, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 43.30827067669173, | |
| "grad_norm": 15.819385528564453, | |
| "learning_rate": 3.131313131313132e-05, | |
| "loss": 0.2574, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 43.609022556390975, | |
| "grad_norm": 7.910970211029053, | |
| "learning_rate": 3.114478114478115e-05, | |
| "loss": 0.2357, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 43.909774436090224, | |
| "grad_norm": 20.98566436767578, | |
| "learning_rate": 3.097643097643098e-05, | |
| "loss": 0.3436, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.5173333333333333, | |
| "eval_loss": 1.6382521390914917, | |
| "eval_runtime": 6.4628, | |
| "eval_samples_per_second": 9.284, | |
| "eval_steps_per_second": 2.321, | |
| "step": 1463 | |
| }, | |
| { | |
| "epoch": 44.21052631578947, | |
| "grad_norm": 15.531021118164062, | |
| "learning_rate": 3.080808080808081e-05, | |
| "loss": 0.2849, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 44.51127819548872, | |
| "grad_norm": 20.71696662902832, | |
| "learning_rate": 3.063973063973064e-05, | |
| "loss": 0.274, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 44.81203007518797, | |
| "grad_norm": 20.764507293701172, | |
| "learning_rate": 3.0471380471380472e-05, | |
| "loss": 0.1955, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 44.99248120300752, | |
| "eval_accuracy": 0.5, | |
| "eval_f1": 0.4828571428571428, | |
| "eval_loss": 1.8947157859802246, | |
| "eval_runtime": 6.9171, | |
| "eval_samples_per_second": 8.674, | |
| "eval_steps_per_second": 2.169, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 45.11278195488722, | |
| "grad_norm": 22.713884353637695, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.2448, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 45.41353383458647, | |
| "grad_norm": 10.142008781433105, | |
| "learning_rate": 3.013468013468014e-05, | |
| "loss": 0.1694, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "grad_norm": 24.03466796875, | |
| "learning_rate": 2.996632996632997e-05, | |
| "loss": 0.2206, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 45.984962406015036, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.6, | |
| "eval_loss": 1.4390347003936768, | |
| "eval_runtime": 6.8263, | |
| "eval_samples_per_second": 8.79, | |
| "eval_steps_per_second": 2.197, | |
| "step": 1529 | |
| }, | |
| { | |
| "epoch": 46.015037593984964, | |
| "grad_norm": 13.955698013305664, | |
| "learning_rate": 2.9797979797979796e-05, | |
| "loss": 0.2549, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 46.31578947368421, | |
| "grad_norm": 11.930123329162598, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.2461, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 46.61654135338346, | |
| "grad_norm": 12.452401161193848, | |
| "learning_rate": 2.946127946127946e-05, | |
| "loss": 0.1838, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 46.91729323308271, | |
| "grad_norm": 6.408818244934082, | |
| "learning_rate": 2.9292929292929294e-05, | |
| "loss": 0.1912, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 46.97744360902256, | |
| "eval_accuracy": 0.65, | |
| "eval_f1": 0.6400402414486922, | |
| "eval_loss": 1.5288487672805786, | |
| "eval_runtime": 6.7766, | |
| "eval_samples_per_second": 8.854, | |
| "eval_steps_per_second": 2.213, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 47.21804511278196, | |
| "grad_norm": 1.8607676029205322, | |
| "learning_rate": 2.9124579124579127e-05, | |
| "loss": 0.2388, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 47.5187969924812, | |
| "grad_norm": 47.768798828125, | |
| "learning_rate": 2.8956228956228958e-05, | |
| "loss": 0.2501, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 47.81954887218045, | |
| "grad_norm": 48.893470764160156, | |
| "learning_rate": 2.878787878787879e-05, | |
| "loss": 0.2794, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5420163334272036, | |
| "eval_loss": 1.7392734289169312, | |
| "eval_runtime": 6.7034, | |
| "eval_samples_per_second": 8.951, | |
| "eval_steps_per_second": 2.238, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 48.1203007518797, | |
| "grad_norm": 3.5548160076141357, | |
| "learning_rate": 2.8619528619528618e-05, | |
| "loss": 0.2652, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 48.421052631578945, | |
| "grad_norm": 19.021543502807617, | |
| "learning_rate": 2.845117845117845e-05, | |
| "loss": 0.0985, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 48.721804511278194, | |
| "grad_norm": 33.23078918457031, | |
| "learning_rate": 2.8282828282828282e-05, | |
| "loss": 0.3166, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 48.99248120300752, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5608305274971942, | |
| "eval_loss": 2.041395664215088, | |
| "eval_runtime": 6.6771, | |
| "eval_samples_per_second": 8.986, | |
| "eval_steps_per_second": 2.246, | |
| "step": 1629 | |
| }, | |
| { | |
| "epoch": 49.02255639097744, | |
| "grad_norm": 24.95660972595215, | |
| "learning_rate": 2.8114478114478115e-05, | |
| "loss": 0.2412, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 49.32330827067669, | |
| "grad_norm": 19.062162399291992, | |
| "learning_rate": 2.794612794612795e-05, | |
| "loss": 0.2181, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 49.62406015037594, | |
| "grad_norm": 5.83784294128418, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2117, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 49.92481203007519, | |
| "grad_norm": 22.206602096557617, | |
| "learning_rate": 2.7609427609427613e-05, | |
| "loss": 0.173, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 49.984962406015036, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5991071428571428, | |
| "eval_loss": 1.6376549005508423, | |
| "eval_runtime": 6.909, | |
| "eval_samples_per_second": 8.684, | |
| "eval_steps_per_second": 2.171, | |
| "step": 1662 | |
| }, | |
| { | |
| "epoch": 50.225563909774436, | |
| "grad_norm": 12.871647834777832, | |
| "learning_rate": 2.7441077441077446e-05, | |
| "loss": 0.194, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 50.526315789473685, | |
| "grad_norm": 27.346282958984375, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 0.1649, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 50.82706766917293, | |
| "grad_norm": 9.746476173400879, | |
| "learning_rate": 2.7104377104377103e-05, | |
| "loss": 0.1375, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 50.97744360902256, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.6, | |
| "eval_loss": 1.622830867767334, | |
| "eval_runtime": 6.6844, | |
| "eval_samples_per_second": 8.976, | |
| "eval_steps_per_second": 2.244, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 51.12781954887218, | |
| "grad_norm": 12.960921287536621, | |
| "learning_rate": 2.6936026936026937e-05, | |
| "loss": 0.2868, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 51.42857142857143, | |
| "grad_norm": 10.291200637817383, | |
| "learning_rate": 2.676767676767677e-05, | |
| "loss": 0.1947, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 51.72932330827068, | |
| "grad_norm": 39.014408111572266, | |
| "learning_rate": 2.65993265993266e-05, | |
| "loss": 0.2659, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_f1": 0.6333333333333333, | |
| "eval_loss": 1.6452404260635376, | |
| "eval_runtime": 6.7167, | |
| "eval_samples_per_second": 8.933, | |
| "eval_steps_per_second": 2.233, | |
| "step": 1729 | |
| }, | |
| { | |
| "epoch": 52.03007518796993, | |
| "grad_norm": 25.84610366821289, | |
| "learning_rate": 2.6430976430976434e-05, | |
| "loss": 0.1805, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 52.330827067669176, | |
| "grad_norm": 20.498271942138672, | |
| "learning_rate": 2.6262626262626268e-05, | |
| "loss": 0.2289, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 52.63157894736842, | |
| "grad_norm": 13.4515962600708, | |
| "learning_rate": 2.6094276094276095e-05, | |
| "loss": 0.0952, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 52.932330827067666, | |
| "grad_norm": 27.01753044128418, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.2045, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 52.99248120300752, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5608305274971942, | |
| "eval_loss": 1.970557451248169, | |
| "eval_runtime": 6.8136, | |
| "eval_samples_per_second": 8.806, | |
| "eval_steps_per_second": 2.201, | |
| "step": 1762 | |
| }, | |
| { | |
| "epoch": 53.233082706766915, | |
| "grad_norm": 53.2229118347168, | |
| "learning_rate": 2.575757575757576e-05, | |
| "loss": 0.2113, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 53.53383458646616, | |
| "grad_norm": 1.9475269317626953, | |
| "learning_rate": 2.5589225589225592e-05, | |
| "loss": 0.159, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 53.83458646616541, | |
| "grad_norm": 50.679840087890625, | |
| "learning_rate": 2.5420875420875422e-05, | |
| "loss": 0.1081, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 53.984962406015036, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.6009102232442273, | |
| "eval_loss": 1.954608678817749, | |
| "eval_runtime": 6.9274, | |
| "eval_samples_per_second": 8.661, | |
| "eval_steps_per_second": 2.165, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 54.13533834586466, | |
| "grad_norm": 42.00580596923828, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.2169, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 54.43609022556391, | |
| "grad_norm": 34.89802169799805, | |
| "learning_rate": 2.5084175084175086e-05, | |
| "loss": 0.1815, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 54.73684210526316, | |
| "grad_norm": 43.92179489135742, | |
| "learning_rate": 2.4915824915824916e-05, | |
| "loss": 0.1782, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 54.97744360902256, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5608305274971942, | |
| "eval_loss": 2.1268014907836914, | |
| "eval_runtime": 6.6378, | |
| "eval_samples_per_second": 9.039, | |
| "eval_steps_per_second": 2.26, | |
| "step": 1828 | |
| }, | |
| { | |
| "epoch": 55.037593984962406, | |
| "grad_norm": 23.048227310180664, | |
| "learning_rate": 2.474747474747475e-05, | |
| "loss": 0.2837, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 55.338345864661655, | |
| "grad_norm": 31.097103118896484, | |
| "learning_rate": 2.457912457912458e-05, | |
| "loss": 0.1967, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 55.6390977443609, | |
| "grad_norm": 31.70062255859375, | |
| "learning_rate": 2.441077441077441e-05, | |
| "loss": 0.1528, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 55.93984962406015, | |
| "grad_norm": 25.655332565307617, | |
| "learning_rate": 2.4242424242424244e-05, | |
| "loss": 0.244, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.6098039215686274, | |
| "eval_loss": 1.8301317691802979, | |
| "eval_runtime": 6.6758, | |
| "eval_samples_per_second": 8.988, | |
| "eval_steps_per_second": 2.247, | |
| "step": 1862 | |
| }, | |
| { | |
| "epoch": 56.2406015037594, | |
| "grad_norm": 9.54874038696289, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.1363, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 56.54135338345865, | |
| "grad_norm": 32.316490173339844, | |
| "learning_rate": 2.3905723905723908e-05, | |
| "loss": 0.2024, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 56.8421052631579, | |
| "grad_norm": 8.345525741577148, | |
| "learning_rate": 2.3737373737373738e-05, | |
| "loss": 0.1783, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 56.99248120300752, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5070833333333334, | |
| "eval_loss": 2.5808091163635254, | |
| "eval_runtime": 6.6634, | |
| "eval_samples_per_second": 9.004, | |
| "eval_steps_per_second": 2.251, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "grad_norm": 16.978073120117188, | |
| "learning_rate": 2.356902356902357e-05, | |
| "loss": 0.246, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 57.443609022556394, | |
| "grad_norm": 23.652156829833984, | |
| "learning_rate": 2.34006734006734e-05, | |
| "loss": 0.1651, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 57.744360902255636, | |
| "grad_norm": 67.35960388183594, | |
| "learning_rate": 2.3232323232323232e-05, | |
| "loss": 0.2429, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 57.984962406015036, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.6058823529411764, | |
| "eval_loss": 2.1214308738708496, | |
| "eval_runtime": 6.6413, | |
| "eval_samples_per_second": 9.034, | |
| "eval_steps_per_second": 2.259, | |
| "step": 1928 | |
| }, | |
| { | |
| "epoch": 58.045112781954884, | |
| "grad_norm": 21.2883243560791, | |
| "learning_rate": 2.3063973063973065e-05, | |
| "loss": 0.1294, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 58.34586466165413, | |
| "grad_norm": 33.893524169921875, | |
| "learning_rate": 2.28956228956229e-05, | |
| "loss": 0.1717, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 58.64661654135338, | |
| "grad_norm": 7.831489086151123, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.1625, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 58.94736842105263, | |
| "grad_norm": 36.57512283325195, | |
| "learning_rate": 2.255892255892256e-05, | |
| "loss": 0.2, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 58.97744360902256, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5657026325546904, | |
| "eval_loss": 2.2281510829925537, | |
| "eval_runtime": 6.9221, | |
| "eval_samples_per_second": 8.668, | |
| "eval_steps_per_second": 2.167, | |
| "step": 1961 | |
| }, | |
| { | |
| "epoch": 59.24812030075188, | |
| "grad_norm": 41.826107025146484, | |
| "learning_rate": 2.2390572390572393e-05, | |
| "loss": 0.1346, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 59.54887218045113, | |
| "grad_norm": 44.347206115722656, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.2132, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 59.849624060150376, | |
| "grad_norm": 36.68692398071289, | |
| "learning_rate": 2.2053872053872053e-05, | |
| "loss": 0.1646, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5662067643958992, | |
| "eval_loss": 2.327244281768799, | |
| "eval_runtime": 6.9668, | |
| "eval_samples_per_second": 8.612, | |
| "eval_steps_per_second": 2.153, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 60.150375939849624, | |
| "grad_norm": 32.38457107543945, | |
| "learning_rate": 2.1885521885521887e-05, | |
| "loss": 0.1555, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 60.45112781954887, | |
| "grad_norm": 40.30613708496094, | |
| "learning_rate": 2.171717171717172e-05, | |
| "loss": 0.1694, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 60.75187969924812, | |
| "grad_norm": 32.216827392578125, | |
| "learning_rate": 2.1548821548821547e-05, | |
| "loss": 0.1663, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 60.99248120300752, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.5322916666666667, | |
| "eval_loss": 2.472301959991455, | |
| "eval_runtime": 6.5598, | |
| "eval_samples_per_second": 9.147, | |
| "eval_steps_per_second": 2.287, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 61.05263157894737, | |
| "grad_norm": 14.56987190246582, | |
| "learning_rate": 2.138047138047138e-05, | |
| "loss": 0.142, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 61.35338345864662, | |
| "grad_norm": 83.00841522216797, | |
| "learning_rate": 2.1212121212121215e-05, | |
| "loss": 0.1869, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 61.65413533834587, | |
| "grad_norm": 16.63633918762207, | |
| "learning_rate": 2.1043771043771045e-05, | |
| "loss": 0.0878, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 61.954887218045116, | |
| "grad_norm": 21.885534286499023, | |
| "learning_rate": 2.0875420875420875e-05, | |
| "loss": 0.1935, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 61.984962406015036, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5973214285714284, | |
| "eval_loss": 2.338430166244507, | |
| "eval_runtime": 6.6897, | |
| "eval_samples_per_second": 8.969, | |
| "eval_steps_per_second": 2.242, | |
| "step": 2061 | |
| }, | |
| { | |
| "epoch": 62.255639097744364, | |
| "grad_norm": 2.885319471359253, | |
| "learning_rate": 2.070707070707071e-05, | |
| "loss": 0.1802, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 62.556390977443606, | |
| "grad_norm": 13.658590316772461, | |
| "learning_rate": 2.0538720538720542e-05, | |
| "loss": 0.1909, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 62.857142857142854, | |
| "grad_norm": 12.268779754638672, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.2079, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 62.97744360902256, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5829860146336946, | |
| "eval_loss": 1.9270540475845337, | |
| "eval_runtime": 6.7469, | |
| "eval_samples_per_second": 8.893, | |
| "eval_steps_per_second": 2.223, | |
| "step": 2094 | |
| }, | |
| { | |
| "epoch": 63.1578947368421, | |
| "grad_norm": 27.859628677368164, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.1491, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 63.45864661654135, | |
| "grad_norm": 22.086532592773438, | |
| "learning_rate": 2.0033670033670036e-05, | |
| "loss": 0.1178, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 63.7593984962406, | |
| "grad_norm": 12.724394798278809, | |
| "learning_rate": 1.9865319865319866e-05, | |
| "loss": 0.1797, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.6150582750582749, | |
| "eval_loss": 1.870719313621521, | |
| "eval_runtime": 6.5187, | |
| "eval_samples_per_second": 9.204, | |
| "eval_steps_per_second": 2.301, | |
| "step": 2128 | |
| }, | |
| { | |
| "epoch": 64.06015037593986, | |
| "grad_norm": 2.5529205799102783, | |
| "learning_rate": 1.9696969696969697e-05, | |
| "loss": 0.2255, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 64.3609022556391, | |
| "grad_norm": 46.02068328857422, | |
| "learning_rate": 1.952861952861953e-05, | |
| "loss": 0.1442, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 64.66165413533835, | |
| "grad_norm": 15.257735252380371, | |
| "learning_rate": 1.936026936026936e-05, | |
| "loss": 0.1668, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 64.9624060150376, | |
| "grad_norm": 10.21757698059082, | |
| "learning_rate": 1.919191919191919e-05, | |
| "loss": 0.173, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 64.99248120300751, | |
| "eval_accuracy": 0.5166666666666667, | |
| "eval_f1": 0.5030690537084399, | |
| "eval_loss": 2.629154682159424, | |
| "eval_runtime": 6.56, | |
| "eval_samples_per_second": 9.146, | |
| "eval_steps_per_second": 2.287, | |
| "step": 2161 | |
| }, | |
| { | |
| "epoch": 65.26315789473684, | |
| "grad_norm": 9.854087829589844, | |
| "learning_rate": 1.9023569023569024e-05, | |
| "loss": 0.1248, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 65.56390977443608, | |
| "grad_norm": 4.802936553955078, | |
| "learning_rate": 1.8855218855218858e-05, | |
| "loss": 0.1242, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 65.86466165413533, | |
| "grad_norm": 38.107017517089844, | |
| "learning_rate": 1.8686868686868688e-05, | |
| "loss": 0.1815, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 65.98496240601504, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5973214285714284, | |
| "eval_loss": 2.6566758155822754, | |
| "eval_runtime": 6.7429, | |
| "eval_samples_per_second": 8.898, | |
| "eval_steps_per_second": 2.225, | |
| "step": 2194 | |
| }, | |
| { | |
| "epoch": 66.16541353383458, | |
| "grad_norm": 7.107358455657959, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1251, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 66.46616541353383, | |
| "grad_norm": 71.81128692626953, | |
| "learning_rate": 1.8350168350168352e-05, | |
| "loss": 0.3104, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 66.76691729323308, | |
| "grad_norm": 0.22506819665431976, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.0665, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 66.97744360902256, | |
| "eval_accuracy": 0.5166666666666667, | |
| "eval_f1": 0.5030690537084399, | |
| "eval_loss": 3.2103826999664307, | |
| "eval_runtime": 7.0616, | |
| "eval_samples_per_second": 8.497, | |
| "eval_steps_per_second": 2.124, | |
| "step": 2227 | |
| }, | |
| { | |
| "epoch": 67.06766917293233, | |
| "grad_norm": 7.794451713562012, | |
| "learning_rate": 1.8013468013468016e-05, | |
| "loss": 0.1232, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 67.36842105263158, | |
| "grad_norm": 0.3173252046108246, | |
| "learning_rate": 1.7845117845117846e-05, | |
| "loss": 0.0533, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 67.66917293233082, | |
| "grad_norm": 14.248137474060059, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.1336, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 67.96992481203007, | |
| "grad_norm": 28.17351531982422, | |
| "learning_rate": 1.750841750841751e-05, | |
| "loss": 0.1084, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.5227752639517346, | |
| "eval_loss": 3.669238567352295, | |
| "eval_runtime": 6.5484, | |
| "eval_samples_per_second": 9.163, | |
| "eval_steps_per_second": 2.291, | |
| "step": 2261 | |
| }, | |
| { | |
| "epoch": 68.27067669172932, | |
| "grad_norm": 20.75010871887207, | |
| "learning_rate": 1.734006734006734e-05, | |
| "loss": 0.1947, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 68.57142857142857, | |
| "grad_norm": 0.9663441777229309, | |
| "learning_rate": 1.7171717171717173e-05, | |
| "loss": 0.1185, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 68.87218045112782, | |
| "grad_norm": 21.510988235473633, | |
| "learning_rate": 1.7003367003367004e-05, | |
| "loss": 0.1298, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 68.99248120300751, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5373401534526855, | |
| "eval_loss": 3.4104325771331787, | |
| "eval_runtime": 6.6129, | |
| "eval_samples_per_second": 9.073, | |
| "eval_steps_per_second": 2.268, | |
| "step": 2294 | |
| }, | |
| { | |
| "epoch": 69.17293233082707, | |
| "grad_norm": 52.829627990722656, | |
| "learning_rate": 1.6835016835016837e-05, | |
| "loss": 0.1408, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 69.47368421052632, | |
| "grad_norm": 14.396146774291992, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0992, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 69.77443609022556, | |
| "grad_norm": 19.629337310791016, | |
| "learning_rate": 1.6498316498316498e-05, | |
| "loss": 0.1338, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 69.98496240601504, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5973063973063972, | |
| "eval_loss": 2.82153058052063, | |
| "eval_runtime": 6.722, | |
| "eval_samples_per_second": 8.926, | |
| "eval_steps_per_second": 2.231, | |
| "step": 2327 | |
| }, | |
| { | |
| "epoch": 70.07518796992481, | |
| "grad_norm": 18.8348445892334, | |
| "learning_rate": 1.632996632996633e-05, | |
| "loss": 0.1428, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 70.37593984962406, | |
| "grad_norm": 30.958715438842773, | |
| "learning_rate": 1.6161616161616165e-05, | |
| "loss": 0.1255, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 70.67669172932331, | |
| "grad_norm": 16.776973724365234, | |
| "learning_rate": 1.5993265993265995e-05, | |
| "loss": 0.1582, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 70.97744360902256, | |
| "grad_norm": 8.8987398147583, | |
| "learning_rate": 1.5824915824915825e-05, | |
| "loss": 0.0795, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 70.97744360902256, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5829852408799777, | |
| "eval_loss": 2.920820713043213, | |
| "eval_runtime": 6.6561, | |
| "eval_samples_per_second": 9.014, | |
| "eval_steps_per_second": 2.254, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 71.2781954887218, | |
| "grad_norm": 18.05194664001465, | |
| "learning_rate": 1.565656565656566e-05, | |
| "loss": 0.1047, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 71.57894736842105, | |
| "grad_norm": 20.946168899536133, | |
| "learning_rate": 1.548821548821549e-05, | |
| "loss": 0.1055, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 71.8796992481203, | |
| "grad_norm": 25.874860763549805, | |
| "learning_rate": 1.531986531986532e-05, | |
| "loss": 0.1138, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.5302083333333333, | |
| "eval_loss": 3.427683115005493, | |
| "eval_runtime": 6.9445, | |
| "eval_samples_per_second": 8.64, | |
| "eval_steps_per_second": 2.16, | |
| "step": 2394 | |
| }, | |
| { | |
| "epoch": 72.18045112781955, | |
| "grad_norm": 18.978233337402344, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.155, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 72.4812030075188, | |
| "grad_norm": 100.18550109863281, | |
| "learning_rate": 1.4983164983164985e-05, | |
| "loss": 0.1628, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 72.78195488721805, | |
| "grad_norm": 65.66423797607422, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1644, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 72.99248120300751, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5829852408799777, | |
| "eval_loss": 2.8140501976013184, | |
| "eval_runtime": 6.6318, | |
| "eval_samples_per_second": 9.047, | |
| "eval_steps_per_second": 2.262, | |
| "step": 2427 | |
| }, | |
| { | |
| "epoch": 73.0827067669173, | |
| "grad_norm": 2.0067760944366455, | |
| "learning_rate": 1.4646464646464647e-05, | |
| "loss": 0.1517, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 73.38345864661655, | |
| "grad_norm": 0.03711702302098274, | |
| "learning_rate": 1.4478114478114479e-05, | |
| "loss": 0.1144, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 73.6842105263158, | |
| "grad_norm": 4.453554153442383, | |
| "learning_rate": 1.4309764309764309e-05, | |
| "loss": 0.0904, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 73.98496240601504, | |
| "grad_norm": 39.73163604736328, | |
| "learning_rate": 1.4141414141414141e-05, | |
| "loss": 0.1659, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 73.98496240601504, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.6, | |
| "eval_loss": 2.872349500656128, | |
| "eval_runtime": 6.965, | |
| "eval_samples_per_second": 8.614, | |
| "eval_steps_per_second": 2.154, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 74.28571428571429, | |
| "grad_norm": 3.167804479598999, | |
| "learning_rate": 1.3973063973063974e-05, | |
| "loss": 0.0658, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 74.58646616541354, | |
| "grad_norm": 6.628215789794922, | |
| "learning_rate": 1.3804713804713806e-05, | |
| "loss": 0.1165, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 74.88721804511279, | |
| "grad_norm": 36.84265899658203, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 0.0453, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 74.97744360902256, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_f1": 0.6308641975308641, | |
| "eval_loss": 2.876894950866699, | |
| "eval_runtime": 6.9372, | |
| "eval_samples_per_second": 8.649, | |
| "eval_steps_per_second": 2.162, | |
| "step": 2493 | |
| }, | |
| { | |
| "epoch": 75.18796992481202, | |
| "grad_norm": 40.516727447509766, | |
| "learning_rate": 1.3468013468013468e-05, | |
| "loss": 0.095, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 75.48872180451127, | |
| "grad_norm": 10.00910758972168, | |
| "learning_rate": 1.32996632996633e-05, | |
| "loss": 0.078, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 75.78947368421052, | |
| "grad_norm": 28.663267135620117, | |
| "learning_rate": 1.3131313131313134e-05, | |
| "loss": 0.0956, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_f1": 0.6098039215686274, | |
| "eval_loss": 3.29703426361084, | |
| "eval_runtime": 6.6814, | |
| "eval_samples_per_second": 8.98, | |
| "eval_steps_per_second": 2.245, | |
| "step": 2527 | |
| }, | |
| { | |
| "epoch": 76.09022556390977, | |
| "grad_norm": 0.029593205079436302, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.1537, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 76.39097744360902, | |
| "grad_norm": 117.96146392822266, | |
| "learning_rate": 1.2794612794612796e-05, | |
| "loss": 0.1007, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 76.69172932330827, | |
| "grad_norm": 3.2077600955963135, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.0296, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 76.99248120300751, | |
| "grad_norm": 17.509721755981445, | |
| "learning_rate": 1.2457912457912458e-05, | |
| "loss": 0.1581, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 76.99248120300751, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5815850815850816, | |
| "eval_loss": 3.6671502590179443, | |
| "eval_runtime": 6.7787, | |
| "eval_samples_per_second": 8.851, | |
| "eval_steps_per_second": 2.213, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 77.29323308270676, | |
| "grad_norm": 17.232837677001953, | |
| "learning_rate": 1.228956228956229e-05, | |
| "loss": 0.0953, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 77.59398496240601, | |
| "grad_norm": 4.897756099700928, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 0.1592, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 77.89473684210526, | |
| "grad_norm": 7.417236328125, | |
| "learning_rate": 1.1952861952861954e-05, | |
| "loss": 0.157, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 77.98496240601504, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.55012503473187, | |
| "eval_loss": 3.531651258468628, | |
| "eval_runtime": 6.7182, | |
| "eval_samples_per_second": 8.931, | |
| "eval_steps_per_second": 2.233, | |
| "step": 2593 | |
| }, | |
| { | |
| "epoch": 78.19548872180451, | |
| "grad_norm": 2.9548983573913574, | |
| "learning_rate": 1.1784511784511786e-05, | |
| "loss": 0.1002, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 78.49624060150376, | |
| "grad_norm": 0.129615917801857, | |
| "learning_rate": 1.1616161616161616e-05, | |
| "loss": 0.2083, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 78.796992481203, | |
| "grad_norm": 13.61913013458252, | |
| "learning_rate": 1.144781144781145e-05, | |
| "loss": 0.0662, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 78.97744360902256, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5455944055944055, | |
| "eval_loss": 3.9002785682678223, | |
| "eval_runtime": 6.7274, | |
| "eval_samples_per_second": 8.919, | |
| "eval_steps_per_second": 2.23, | |
| "step": 2626 | |
| }, | |
| { | |
| "epoch": 79.09774436090225, | |
| "grad_norm": 39.20783233642578, | |
| "learning_rate": 1.127946127946128e-05, | |
| "loss": 0.0954, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 79.3984962406015, | |
| "grad_norm": 5.543479919433594, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0968, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 79.69924812030075, | |
| "grad_norm": 1.9669289588928223, | |
| "learning_rate": 1.0942760942760944e-05, | |
| "loss": 0.061, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 0.08515916019678116, | |
| "learning_rate": 1.0774410774410774e-05, | |
| "loss": 0.1954, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5834491062332129, | |
| "eval_loss": 3.2999682426452637, | |
| "eval_runtime": 6.8436, | |
| "eval_samples_per_second": 8.767, | |
| "eval_steps_per_second": 2.192, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 80.30075187969925, | |
| "grad_norm": 129.70567321777344, | |
| "learning_rate": 1.0606060606060607e-05, | |
| "loss": 0.0925, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 80.6015037593985, | |
| "grad_norm": 31.757814407348633, | |
| "learning_rate": 1.0437710437710438e-05, | |
| "loss": 0.0628, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 80.90225563909775, | |
| "grad_norm": 24.929340362548828, | |
| "learning_rate": 1.0269360269360271e-05, | |
| "loss": 0.0527, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 80.99248120300751, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.563764880952381, | |
| "eval_loss": 3.9595704078674316, | |
| "eval_runtime": 6.6214, | |
| "eval_samples_per_second": 9.061, | |
| "eval_steps_per_second": 2.265, | |
| "step": 2693 | |
| }, | |
| { | |
| "epoch": 81.203007518797, | |
| "grad_norm": 29.07752799987793, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.2314, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 81.50375939849624, | |
| "grad_norm": 3.3806166648864746, | |
| "learning_rate": 9.932659932659933e-06, | |
| "loss": 0.1772, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 81.80451127819549, | |
| "grad_norm": 44.8973388671875, | |
| "learning_rate": 9.764309764309765e-06, | |
| "loss": 0.1578, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 81.98496240601504, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5481203007518796, | |
| "eval_loss": 3.67238712310791, | |
| "eval_runtime": 6.7367, | |
| "eval_samples_per_second": 8.906, | |
| "eval_steps_per_second": 2.227, | |
| "step": 2726 | |
| }, | |
| { | |
| "epoch": 82.10526315789474, | |
| "grad_norm": 35.64302062988281, | |
| "learning_rate": 9.595959595959595e-06, | |
| "loss": 0.1126, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 82.40601503759399, | |
| "grad_norm": 1.958249568939209, | |
| "learning_rate": 9.427609427609429e-06, | |
| "loss": 0.0772, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 82.70676691729324, | |
| "grad_norm": 15.566617965698242, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0737, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 82.97744360902256, | |
| "eval_accuracy": 0.5166666666666667, | |
| "eval_f1": 0.5119347319347319, | |
| "eval_loss": 4.022154331207275, | |
| "eval_runtime": 6.7543, | |
| "eval_samples_per_second": 8.883, | |
| "eval_steps_per_second": 2.221, | |
| "step": 2759 | |
| }, | |
| { | |
| "epoch": 83.00751879699249, | |
| "grad_norm": 29.270156860351562, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.1313, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 83.30827067669173, | |
| "grad_norm": 28.969818115234375, | |
| "learning_rate": 8.922558922558923e-06, | |
| "loss": 0.0702, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 83.60902255639098, | |
| "grad_norm": 129.39942932128906, | |
| "learning_rate": 8.754208754208755e-06, | |
| "loss": 0.1426, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 83.90977443609023, | |
| "grad_norm": 38.763427734375, | |
| "learning_rate": 8.585858585858587e-06, | |
| "loss": 0.0617, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5834491062332129, | |
| "eval_loss": 3.551039934158325, | |
| "eval_runtime": 6.5857, | |
| "eval_samples_per_second": 9.111, | |
| "eval_steps_per_second": 2.278, | |
| "step": 2793 | |
| }, | |
| { | |
| "epoch": 84.21052631578948, | |
| "grad_norm": 4.888305187225342, | |
| "learning_rate": 8.417508417508419e-06, | |
| "loss": 0.0564, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 84.51127819548873, | |
| "grad_norm": 58.47932434082031, | |
| "learning_rate": 8.249158249158249e-06, | |
| "loss": 0.0997, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 84.81203007518798, | |
| "grad_norm": 2.1397640705108643, | |
| "learning_rate": 8.080808080808082e-06, | |
| "loss": 0.0531, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 84.99248120300751, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.6, | |
| "eval_loss": 3.510986328125, | |
| "eval_runtime": 6.6781, | |
| "eval_samples_per_second": 8.985, | |
| "eval_steps_per_second": 2.246, | |
| "step": 2826 | |
| }, | |
| { | |
| "epoch": 85.11278195488721, | |
| "grad_norm": 9.81313705444336, | |
| "learning_rate": 7.912457912457913e-06, | |
| "loss": 0.2663, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 85.41353383458646, | |
| "grad_norm": 89.6509017944336, | |
| "learning_rate": 7.744107744107745e-06, | |
| "loss": 0.1666, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 85.71428571428571, | |
| "grad_norm": 1.1382590532302856, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.0993, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 85.98496240601504, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5481203007518796, | |
| "eval_loss": 4.06988000869751, | |
| "eval_runtime": 6.9333, | |
| "eval_samples_per_second": 8.654, | |
| "eval_steps_per_second": 2.163, | |
| "step": 2859 | |
| }, | |
| { | |
| "epoch": 86.01503759398496, | |
| "grad_norm": 1.276601791381836, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0773, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 86.3157894736842, | |
| "grad_norm": 2.0897693634033203, | |
| "learning_rate": 7.239057239057239e-06, | |
| "loss": 0.0431, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 86.61654135338345, | |
| "grad_norm": 25.9661922454834, | |
| "learning_rate": 7.0707070707070704e-06, | |
| "loss": 0.1435, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 86.9172932330827, | |
| "grad_norm": 49.344520568847656, | |
| "learning_rate": 6.902356902356903e-06, | |
| "loss": 0.1545, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 86.97744360902256, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5666666666666667, | |
| "eval_loss": 3.6860132217407227, | |
| "eval_runtime": 7.1718, | |
| "eval_samples_per_second": 8.366, | |
| "eval_steps_per_second": 2.092, | |
| "step": 2892 | |
| }, | |
| { | |
| "epoch": 87.21804511278195, | |
| "grad_norm": 20.44532585144043, | |
| "learning_rate": 6.734006734006734e-06, | |
| "loss": 0.0467, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 87.5187969924812, | |
| "grad_norm": 0.8258923292160034, | |
| "learning_rate": 6.565656565656567e-06, | |
| "loss": 0.1309, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 87.81954887218045, | |
| "grad_norm": 0.22264444828033447, | |
| "learning_rate": 6.397306397306398e-06, | |
| "loss": 0.0554, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.6, | |
| "eval_loss": 3.440887212753296, | |
| "eval_runtime": 6.7259, | |
| "eval_samples_per_second": 8.921, | |
| "eval_steps_per_second": 2.23, | |
| "step": 2926 | |
| }, | |
| { | |
| "epoch": 88.1203007518797, | |
| "grad_norm": 26.937969207763672, | |
| "learning_rate": 6.228956228956229e-06, | |
| "loss": 0.1753, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 88.42105263157895, | |
| "grad_norm": 5.258349418640137, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 0.0585, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 88.7218045112782, | |
| "grad_norm": 0.008519310504198074, | |
| "learning_rate": 5.892255892255893e-06, | |
| "loss": 0.0641, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 88.99248120300751, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5496248958043901, | |
| "eval_loss": 3.8303909301757812, | |
| "eval_runtime": 6.6141, | |
| "eval_samples_per_second": 9.072, | |
| "eval_steps_per_second": 2.268, | |
| "step": 2959 | |
| }, | |
| { | |
| "epoch": 89.02255639097744, | |
| "grad_norm": 0.1844397634267807, | |
| "learning_rate": 5.723905723905725e-06, | |
| "loss": 0.0186, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 89.32330827067669, | |
| "grad_norm": 15.114968299865723, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0863, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 89.62406015037594, | |
| "grad_norm": 2.7161004543304443, | |
| "learning_rate": 5.387205387205387e-06, | |
| "loss": 0.0546, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 89.92481203007519, | |
| "grad_norm": 24.26571273803711, | |
| "learning_rate": 5.218855218855219e-06, | |
| "loss": 0.0633, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 89.98496240601504, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5455944055944055, | |
| "eval_loss": 4.089901924133301, | |
| "eval_runtime": 6.6774, | |
| "eval_samples_per_second": 8.986, | |
| "eval_steps_per_second": 2.246, | |
| "step": 2992 | |
| }, | |
| { | |
| "epoch": 90.22556390977444, | |
| "grad_norm": 1.2879589796066284, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.0261, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 90.52631578947368, | |
| "grad_norm": 60.2087287902832, | |
| "learning_rate": 4.8821548821548826e-06, | |
| "loss": 0.0305, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 90.82706766917293, | |
| "grad_norm": 0.27982065081596375, | |
| "learning_rate": 4.7138047138047145e-06, | |
| "loss": 0.0991, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 90.97744360902256, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.6, | |
| "eval_loss": 3.734445095062256, | |
| "eval_runtime": 6.8383, | |
| "eval_samples_per_second": 8.774, | |
| "eval_steps_per_second": 2.194, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 91.12781954887218, | |
| "grad_norm": 21.401033401489258, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 0.099, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 91.42857142857143, | |
| "grad_norm": 83.67088317871094, | |
| "learning_rate": 4.377104377104377e-06, | |
| "loss": 0.2015, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 91.72932330827068, | |
| "grad_norm": 4.662288188934326, | |
| "learning_rate": 4.208754208754209e-06, | |
| "loss": 0.0772, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5991101223581758, | |
| "eval_loss": 3.8447837829589844, | |
| "eval_runtime": 6.7081, | |
| "eval_samples_per_second": 8.944, | |
| "eval_steps_per_second": 2.236, | |
| "step": 3059 | |
| }, | |
| { | |
| "epoch": 92.03007518796993, | |
| "grad_norm": 8.341154098510742, | |
| "learning_rate": 4.040404040404041e-06, | |
| "loss": 0.1092, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 92.33082706766918, | |
| "grad_norm": 0.6782325506210327, | |
| "learning_rate": 3.872053872053872e-06, | |
| "loss": 0.1804, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 92.63157894736842, | |
| "grad_norm": 0.04346880316734314, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.1252, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 92.93233082706767, | |
| "grad_norm": 8.484058380126953, | |
| "learning_rate": 3.5353535353535352e-06, | |
| "loss": 0.0646, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 92.99248120300751, | |
| "eval_accuracy": 0.6, | |
| "eval_f1": 0.5991101223581758, | |
| "eval_loss": 3.779362440109253, | |
| "eval_runtime": 6.7205, | |
| "eval_samples_per_second": 8.928, | |
| "eval_steps_per_second": 2.232, | |
| "step": 3092 | |
| }, | |
| { | |
| "epoch": 93.23308270676692, | |
| "grad_norm": 27.746423721313477, | |
| "learning_rate": 3.367003367003367e-06, | |
| "loss": 0.1189, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 93.53383458646617, | |
| "grad_norm": 73.70268249511719, | |
| "learning_rate": 3.198653198653199e-06, | |
| "loss": 0.0597, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 93.83458646616542, | |
| "grad_norm": 1.809439778327942, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 0.0562, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 93.98496240601504, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_f1": 0.5829860146336946, | |
| "eval_loss": 3.934034824371338, | |
| "eval_runtime": 6.724, | |
| "eval_samples_per_second": 8.923, | |
| "eval_steps_per_second": 2.231, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 94.13533834586467, | |
| "grad_norm": 28.367788314819336, | |
| "learning_rate": 2.8619528619528624e-06, | |
| "loss": 0.12, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 94.43609022556392, | |
| "grad_norm": 18.267364501953125, | |
| "learning_rate": 2.6936026936026934e-06, | |
| "loss": 0.0473, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 94.73684210526316, | |
| "grad_norm": 3.8993523120880127, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.0475, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 94.97744360902256, | |
| "eval_accuracy": 0.55, | |
| "eval_f1": 0.5481203007518796, | |
| "eval_loss": 4.238762378692627, | |
| "eval_runtime": 6.722, | |
| "eval_samples_per_second": 8.926, | |
| "eval_steps_per_second": 2.231, | |
| "step": 3158 | |
| }, | |
| { | |
| "epoch": 95.0375939849624, | |
| "grad_norm": 1.1250429153442383, | |
| "learning_rate": 2.3569023569023572e-06, | |
| "loss": 0.1145, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 95.33834586466165, | |
| "grad_norm": 0.013231492601335049, | |
| "learning_rate": 2.1885521885521887e-06, | |
| "loss": 0.0648, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 95.6390977443609, | |
| "grad_norm": 0.1679408848285675, | |
| "learning_rate": 2.0202020202020206e-06, | |
| "loss": 0.0993, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 95.93984962406014, | |
| "grad_norm": 45.490089416503906, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0715, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_f1": 0.5302083333333333, | |
| "eval_loss": 4.273224830627441, | |
| "eval_runtime": 6.8339, | |
| "eval_samples_per_second": 8.78, | |
| "eval_steps_per_second": 2.195, | |
| "step": 3192 | |
| }, | |
| { | |
| "epoch": 96.2406015037594, | |
| "grad_norm": 6.96300745010376, | |
| "learning_rate": 1.6835016835016836e-06, | |
| "loss": 0.048, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 96.54135338345864, | |
| "grad_norm": 2.091585397720337, | |
| "learning_rate": 1.5151515151515152e-06, | |
| "loss": 0.0434, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 96.84210526315789, | |
| "grad_norm": 73.60545349121094, | |
| "learning_rate": 1.3468013468013467e-06, | |
| "loss": 0.0875, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 96.99248120300751, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5657026325546904, | |
| "eval_loss": 4.152093410491943, | |
| "eval_runtime": 6.4099, | |
| "eval_samples_per_second": 9.36, | |
| "eval_steps_per_second": 2.34, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 97.14285714285714, | |
| "grad_norm": 0.0025759534910321236, | |
| "learning_rate": 1.1784511784511786e-06, | |
| "loss": 0.0766, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 97.44360902255639, | |
| "grad_norm": 0.3083040416240692, | |
| "learning_rate": 1.0101010101010103e-06, | |
| "loss": 0.1051, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 97.74436090225564, | |
| "grad_norm": 49.4640998840332, | |
| "learning_rate": 8.417508417508418e-07, | |
| "loss": 0.0253, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 97.98496240601504, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5666666666666667, | |
| "eval_loss": 4.0813493728637695, | |
| "eval_runtime": 6.8426, | |
| "eval_samples_per_second": 8.769, | |
| "eval_steps_per_second": 2.192, | |
| "step": 3258 | |
| }, | |
| { | |
| "epoch": 98.04511278195488, | |
| "grad_norm": 26.789464950561523, | |
| "learning_rate": 6.734006734006734e-07, | |
| "loss": 0.2367, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 98.34586466165413, | |
| "grad_norm": 2.038747549057007, | |
| "learning_rate": 5.050505050505052e-07, | |
| "loss": 0.1146, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 98.64661654135338, | |
| "grad_norm": 0.2587548494338989, | |
| "learning_rate": 3.367003367003367e-07, | |
| "loss": 0.0966, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 98.94736842105263, | |
| "grad_norm": 43.22801971435547, | |
| "learning_rate": 1.6835016835016834e-07, | |
| "loss": 0.1037, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 98.97744360902256, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5666666666666667, | |
| "eval_loss": 4.107425212860107, | |
| "eval_runtime": 6.6385, | |
| "eval_samples_per_second": 9.038, | |
| "eval_steps_per_second": 2.26, | |
| "step": 3291 | |
| }, | |
| { | |
| "epoch": 99.24812030075188, | |
| "grad_norm": 1.0782755613327026, | |
| "learning_rate": 0.0, | |
| "loss": 0.1094, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 99.24812030075188, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_f1": 0.5666666666666667, | |
| "eval_loss": 4.108070373535156, | |
| "eval_runtime": 8.9284, | |
| "eval_samples_per_second": 6.72, | |
| "eval_steps_per_second": 1.68, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 99.24812030075188, | |
| "step": 3300, | |
| "total_flos": 2.7357484620290458e+19, | |
| "train_loss": 0.32434610511768946, | |
| "train_runtime": 9596.5736, | |
| "train_samples_per_second": 5.544, | |
| "train_steps_per_second": 0.344 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "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": 2.7357484620290458e+19, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |