| { | |
| "best_metric": 0.6745562130177515, | |
| "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/MY DATA/ViViT_WLASL_100_SR_4_ep200_p20/checkpoint-4686", | |
| "epoch": 45.00499305555556, | |
| "eval_steps": 500, | |
| "global_step": 8291, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002777777777777778, | |
| "grad_norm": 46.614158630371094, | |
| "learning_rate": 1.3472222222222222e-06, | |
| "loss": 18.9788, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "eval_accuracy": 0.026627218934911243, | |
| "eval_f1": 0.008186647196111367, | |
| "eval_loss": 4.690920829772949, | |
| "eval_precision": 0.005517409748672709, | |
| "eval_recall": 0.026627218934911243, | |
| "eval_runtime": 19.4352, | |
| "eval_samples_per_second": 17.391, | |
| "eval_steps_per_second": 8.696, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.000548611111111, | |
| "grad_norm": 44.873966217041016, | |
| "learning_rate": 2.7361111111111114e-06, | |
| "loss": 18.8244, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0033263888888888, | |
| "grad_norm": 43.23536682128906, | |
| "learning_rate": 4.125e-06, | |
| "loss": 18.6803, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0049930555555555, | |
| "eval_accuracy": 0.026627218934911243, | |
| "eval_f1": 0.0057761083277597, | |
| "eval_loss": 4.617973327636719, | |
| "eval_precision": 0.003442859602301134, | |
| "eval_recall": 0.026627218934911243, | |
| "eval_runtime": 18.7273, | |
| "eval_samples_per_second": 18.049, | |
| "eval_steps_per_second": 9.024, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.001097222222222, | |
| "grad_norm": 43.87873458862305, | |
| "learning_rate": 5.513888888888889e-06, | |
| "loss": 18.3151, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.003875, | |
| "grad_norm": 45.60523986816406, | |
| "learning_rate": 6.902777777777777e-06, | |
| "loss": 18.0341, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.004986111111111, | |
| "eval_accuracy": 0.047337278106508875, | |
| "eval_f1": 0.023768276430998322, | |
| "eval_loss": 4.518121242523193, | |
| "eval_precision": 0.020485887948289476, | |
| "eval_recall": 0.047337278106508875, | |
| "eval_runtime": 19.5951, | |
| "eval_samples_per_second": 17.249, | |
| "eval_steps_per_second": 8.625, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.0016458333333333, | |
| "grad_norm": 49.1752815246582, | |
| "learning_rate": 8.291666666666667e-06, | |
| "loss": 17.4359, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.004423611111111, | |
| "grad_norm": 51.076786041259766, | |
| "learning_rate": 9.680555555555556e-06, | |
| "loss": 17.0617, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.0050069444444443, | |
| "eval_accuracy": 0.07396449704142012, | |
| "eval_f1": 0.047821065111354005, | |
| "eval_loss": 4.337636470794678, | |
| "eval_precision": 0.054133340554329064, | |
| "eval_recall": 0.07396449704142012, | |
| "eval_runtime": 18.9343, | |
| "eval_samples_per_second": 17.851, | |
| "eval_steps_per_second": 8.926, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 4.002194444444444, | |
| "grad_norm": 46.15924835205078, | |
| "learning_rate": 1.1069444444444445e-05, | |
| "loss": 16.0988, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.004972222222222, | |
| "grad_norm": 51.79167938232422, | |
| "learning_rate": 1.2458333333333334e-05, | |
| "loss": 15.6302, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.005, | |
| "eval_accuracy": 0.11834319526627218, | |
| "eval_f1": 0.081513142682628, | |
| "eval_loss": 4.070884704589844, | |
| "eval_precision": 0.07720141700404858, | |
| "eval_recall": 0.11834319526627218, | |
| "eval_runtime": 20.1431, | |
| "eval_samples_per_second": 16.78, | |
| "eval_steps_per_second": 8.39, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 5.002743055555555, | |
| "grad_norm": 55.07365798950195, | |
| "learning_rate": 1.3847222222222223e-05, | |
| "loss": 14.0851, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0049930555555555, | |
| "eval_accuracy": 0.1863905325443787, | |
| "eval_f1": 0.14494279207764105, | |
| "eval_loss": 3.755218029022217, | |
| "eval_precision": 0.1535636372174834, | |
| "eval_recall": 0.1863905325443787, | |
| "eval_runtime": 19.7392, | |
| "eval_samples_per_second": 17.123, | |
| "eval_steps_per_second": 8.562, | |
| "step": 1081 | |
| }, | |
| { | |
| "epoch": 6.0005138888888885, | |
| "grad_norm": 49.54998779296875, | |
| "learning_rate": 1.5236111111111112e-05, | |
| "loss": 13.3452, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.003291666666667, | |
| "grad_norm": 54.62944793701172, | |
| "learning_rate": 1.6625e-05, | |
| "loss": 11.953, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.004986111111111, | |
| "eval_accuracy": 0.26627218934911245, | |
| "eval_f1": 0.2220989336141275, | |
| "eval_loss": 3.406508684158325, | |
| "eval_precision": 0.26431351743742965, | |
| "eval_recall": 0.26627218934911245, | |
| "eval_runtime": 19.5936, | |
| "eval_samples_per_second": 17.251, | |
| "eval_steps_per_second": 8.625, | |
| "step": 1261 | |
| }, | |
| { | |
| "epoch": 7.0010625, | |
| "grad_norm": 56.319576263427734, | |
| "learning_rate": 1.8013888888888888e-05, | |
| "loss": 11.0917, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.003840277777778, | |
| "grad_norm": 54.84210205078125, | |
| "learning_rate": 1.940277777777778e-05, | |
| "loss": 9.8223, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.005006944444444, | |
| "eval_accuracy": 0.33727810650887574, | |
| "eval_f1": 0.29438573252416295, | |
| "eval_loss": 3.103813886642456, | |
| "eval_precision": 0.3283793047846302, | |
| "eval_recall": 0.33727810650887574, | |
| "eval_runtime": 20.1573, | |
| "eval_samples_per_second": 16.768, | |
| "eval_steps_per_second": 8.384, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 8.001611111111112, | |
| "grad_norm": 51.06685256958008, | |
| "learning_rate": 2.0791666666666666e-05, | |
| "loss": 8.6714, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.004388888888888, | |
| "grad_norm": 50.67875289916992, | |
| "learning_rate": 2.2180555555555557e-05, | |
| "loss": 7.8126, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.005, | |
| "eval_accuracy": 0.41420118343195267, | |
| "eval_f1": 0.3676157668761219, | |
| "eval_loss": 2.7834277153015137, | |
| "eval_precision": 0.42014839107599283, | |
| "eval_recall": 0.41420118343195267, | |
| "eval_runtime": 19.7317, | |
| "eval_samples_per_second": 17.13, | |
| "eval_steps_per_second": 8.565, | |
| "step": 1622 | |
| }, | |
| { | |
| "epoch": 9.002159722222222, | |
| "grad_norm": 49.01296615600586, | |
| "learning_rate": 2.3569444444444447e-05, | |
| "loss": 6.4863, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.0049375, | |
| "grad_norm": 47.182640075683594, | |
| "learning_rate": 2.4958333333333335e-05, | |
| "loss": 6.0952, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.004993055555556, | |
| "eval_accuracy": 0.47633136094674555, | |
| "eval_f1": 0.4368087369566659, | |
| "eval_loss": 2.512887477874756, | |
| "eval_precision": 0.4949564324564325, | |
| "eval_recall": 0.47633136094674555, | |
| "eval_runtime": 20.1068, | |
| "eval_samples_per_second": 16.81, | |
| "eval_steps_per_second": 8.405, | |
| "step": 1802 | |
| }, | |
| { | |
| "epoch": 10.002708333333333, | |
| "grad_norm": 49.08199691772461, | |
| "learning_rate": 2.6347222222222222e-05, | |
| "loss": 4.3155, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 10.00498611111111, | |
| "eval_accuracy": 0.5059171597633136, | |
| "eval_f1": 0.48941789637055916, | |
| "eval_loss": 2.2756905555725098, | |
| "eval_precision": 0.5593944517021441, | |
| "eval_recall": 0.5059171597633136, | |
| "eval_runtime": 18.9167, | |
| "eval_samples_per_second": 17.868, | |
| "eval_steps_per_second": 8.934, | |
| "step": 1982 | |
| }, | |
| { | |
| "epoch": 11.000479166666667, | |
| "grad_norm": 37.75128936767578, | |
| "learning_rate": 2.7736111111111113e-05, | |
| "loss": 4.3448, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.003256944444445, | |
| "grad_norm": 36.987205505371094, | |
| "learning_rate": 2.9111111111111112e-05, | |
| "loss": 3.0214, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 11.005006944444444, | |
| "eval_accuracy": 0.5473372781065089, | |
| "eval_f1": 0.5177564874310436, | |
| "eval_loss": 2.0459656715393066, | |
| "eval_precision": 0.563966482235713, | |
| "eval_recall": 0.5473372781065089, | |
| "eval_runtime": 19.7866, | |
| "eval_samples_per_second": 17.082, | |
| "eval_steps_per_second": 8.541, | |
| "step": 2163 | |
| }, | |
| { | |
| "epoch": 12.001027777777777, | |
| "grad_norm": 30.315874099731445, | |
| "learning_rate": 3.05e-05, | |
| "loss": 2.7849, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 12.003805555555555, | |
| "grad_norm": 27.424291610717773, | |
| "learning_rate": 3.188888888888889e-05, | |
| "loss": 2.0687, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 12.005, | |
| "eval_accuracy": 0.591715976331361, | |
| "eval_f1": 0.5730650184792196, | |
| "eval_loss": 1.8803057670593262, | |
| "eval_precision": 0.6183537616229923, | |
| "eval_recall": 0.591715976331361, | |
| "eval_runtime": 19.466, | |
| "eval_samples_per_second": 17.364, | |
| "eval_steps_per_second": 8.682, | |
| "step": 2343 | |
| }, | |
| { | |
| "epoch": 13.00157638888889, | |
| "grad_norm": 19.18665313720703, | |
| "learning_rate": 3.327777777777778e-05, | |
| "loss": 1.5252, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 13.004354166666667, | |
| "grad_norm": 31.665971755981445, | |
| "learning_rate": 3.466666666666667e-05, | |
| "loss": 1.3523, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 13.004993055555556, | |
| "eval_accuracy": 0.591715976331361, | |
| "eval_f1": 0.5601332592456852, | |
| "eval_loss": 1.7261461019515991, | |
| "eval_precision": 0.6065053536207382, | |
| "eval_recall": 0.591715976331361, | |
| "eval_runtime": 19.273, | |
| "eval_samples_per_second": 17.537, | |
| "eval_steps_per_second": 8.769, | |
| "step": 2523 | |
| }, | |
| { | |
| "epoch": 14.002125, | |
| "grad_norm": 10.98436450958252, | |
| "learning_rate": 3.605555555555556e-05, | |
| "loss": 0.9208, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 14.004902777777778, | |
| "grad_norm": 45.65860366821289, | |
| "learning_rate": 3.7444444444444446e-05, | |
| "loss": 0.7828, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 14.00498611111111, | |
| "eval_accuracy": 0.6035502958579881, | |
| "eval_f1": 0.5923542762300159, | |
| "eval_loss": 1.6275168657302856, | |
| "eval_precision": 0.6644219028834413, | |
| "eval_recall": 0.6035502958579881, | |
| "eval_runtime": 19.479, | |
| "eval_samples_per_second": 17.352, | |
| "eval_steps_per_second": 8.676, | |
| "step": 2703 | |
| }, | |
| { | |
| "epoch": 15.002673611111112, | |
| "grad_norm": 24.026081085205078, | |
| "learning_rate": 3.883333333333333e-05, | |
| "loss": 0.4222, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 15.005006944444444, | |
| "eval_accuracy": 0.6420118343195266, | |
| "eval_f1": 0.6244853437161129, | |
| "eval_loss": 1.5283950567245483, | |
| "eval_precision": 0.67558435154589, | |
| "eval_recall": 0.6420118343195266, | |
| "eval_runtime": 19.8172, | |
| "eval_samples_per_second": 17.056, | |
| "eval_steps_per_second": 8.528, | |
| "step": 2884 | |
| }, | |
| { | |
| "epoch": 16.000444444444444, | |
| "grad_norm": 11.13332748413086, | |
| "learning_rate": 4.022222222222222e-05, | |
| "loss": 0.4752, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 16.003222222222224, | |
| "grad_norm": 8.170760154724121, | |
| "learning_rate": 4.1611111111111114e-05, | |
| "loss": 0.3113, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 16.005, | |
| "eval_accuracy": 0.6272189349112426, | |
| "eval_f1": 0.6092443552502724, | |
| "eval_loss": 1.5459295511245728, | |
| "eval_precision": 0.6664412510566357, | |
| "eval_recall": 0.6272189349112426, | |
| "eval_runtime": 19.569, | |
| "eval_samples_per_second": 17.272, | |
| "eval_steps_per_second": 8.636, | |
| "step": 3064 | |
| }, | |
| { | |
| "epoch": 17.000993055555554, | |
| "grad_norm": 1.5062611103057861, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.2905, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 17.003770833333334, | |
| "grad_norm": 1.255529761314392, | |
| "learning_rate": 4.438888888888889e-05, | |
| "loss": 0.2021, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 17.004993055555556, | |
| "eval_accuracy": 0.665680473372781, | |
| "eval_f1": 0.6484432398633582, | |
| "eval_loss": 1.4440850019454956, | |
| "eval_precision": 0.6991018596787828, | |
| "eval_recall": 0.665680473372781, | |
| "eval_runtime": 20.6892, | |
| "eval_samples_per_second": 16.337, | |
| "eval_steps_per_second": 8.168, | |
| "step": 3244 | |
| }, | |
| { | |
| "epoch": 18.001541666666668, | |
| "grad_norm": 2.2327980995178223, | |
| "learning_rate": 4.577777777777778e-05, | |
| "loss": 0.1544, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 18.004319444444445, | |
| "grad_norm": 1.6391757726669312, | |
| "learning_rate": 4.716666666666667e-05, | |
| "loss": 0.1698, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 18.004986111111112, | |
| "eval_accuracy": 0.6124260355029586, | |
| "eval_f1": 0.5942196856398039, | |
| "eval_loss": 1.5340176820755005, | |
| "eval_precision": 0.6510575962499039, | |
| "eval_recall": 0.6124260355029586, | |
| "eval_runtime": 19.0949, | |
| "eval_samples_per_second": 17.701, | |
| "eval_steps_per_second": 8.851, | |
| "step": 3424 | |
| }, | |
| { | |
| "epoch": 19.00209027777778, | |
| "grad_norm": 7.581464767456055, | |
| "learning_rate": 4.855555555555556e-05, | |
| "loss": 0.0791, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 19.004868055555555, | |
| "grad_norm": 0.5042413473129272, | |
| "learning_rate": 4.994444444444445e-05, | |
| "loss": 0.1199, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 19.005006944444446, | |
| "eval_accuracy": 0.650887573964497, | |
| "eval_f1": 0.6288250211327134, | |
| "eval_loss": 1.3934611082077026, | |
| "eval_precision": 0.6745703014933784, | |
| "eval_recall": 0.650887573964497, | |
| "eval_runtime": 18.5254, | |
| "eval_samples_per_second": 18.245, | |
| "eval_steps_per_second": 9.123, | |
| "step": 3605 | |
| }, | |
| { | |
| "epoch": 20.00263888888889, | |
| "grad_norm": 0.40117892622947693, | |
| "learning_rate": 4.9851851851851855e-05, | |
| "loss": 0.0244, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 20.005, | |
| "eval_accuracy": 0.6686390532544378, | |
| "eval_f1": 0.6573669919823766, | |
| "eval_loss": 1.478171706199646, | |
| "eval_precision": 0.7130459284305437, | |
| "eval_recall": 0.6686390532544378, | |
| "eval_runtime": 19.5864, | |
| "eval_samples_per_second": 17.257, | |
| "eval_steps_per_second": 8.628, | |
| "step": 3785 | |
| }, | |
| { | |
| "epoch": 21.000409722222223, | |
| "grad_norm": 0.6385509967803955, | |
| "learning_rate": 4.969753086419753e-05, | |
| "loss": 0.1644, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 21.0031875, | |
| "grad_norm": 0.36917442083358765, | |
| "learning_rate": 4.954320987654321e-05, | |
| "loss": 0.0407, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 21.004993055555556, | |
| "eval_accuracy": 0.6686390532544378, | |
| "eval_f1": 0.6557107422492038, | |
| "eval_loss": 1.388999581336975, | |
| "eval_precision": 0.7149478726401803, | |
| "eval_recall": 0.6686390532544378, | |
| "eval_runtime": 19.0631, | |
| "eval_samples_per_second": 17.731, | |
| "eval_steps_per_second": 8.865, | |
| "step": 3965 | |
| }, | |
| { | |
| "epoch": 22.000958333333333, | |
| "grad_norm": 0.5856227874755859, | |
| "learning_rate": 4.938888888888889e-05, | |
| "loss": 0.1314, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 22.00373611111111, | |
| "grad_norm": 0.7390286326408386, | |
| "learning_rate": 4.923611111111112e-05, | |
| "loss": 0.0719, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 22.004986111111112, | |
| "eval_accuracy": 0.6597633136094675, | |
| "eval_f1": 0.6477249246480016, | |
| "eval_loss": 1.4896520376205444, | |
| "eval_precision": 0.7189349112426036, | |
| "eval_recall": 0.6597633136094675, | |
| "eval_runtime": 19.4131, | |
| "eval_samples_per_second": 17.411, | |
| "eval_steps_per_second": 8.705, | |
| "step": 4145 | |
| }, | |
| { | |
| "epoch": 23.001506944444444, | |
| "grad_norm": 0.09171107411384583, | |
| "learning_rate": 4.9081790123456794e-05, | |
| "loss": 0.1134, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 23.004284722222224, | |
| "grad_norm": 27.191944122314453, | |
| "learning_rate": 4.892746913580247e-05, | |
| "loss": 0.1163, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 23.005006944444446, | |
| "eval_accuracy": 0.6715976331360947, | |
| "eval_f1": 0.6638741600280061, | |
| "eval_loss": 1.3919016122817993, | |
| "eval_precision": 0.7218300929839392, | |
| "eval_recall": 0.6715976331360947, | |
| "eval_runtime": 18.0114, | |
| "eval_samples_per_second": 18.766, | |
| "eval_steps_per_second": 9.383, | |
| "step": 4326 | |
| }, | |
| { | |
| "epoch": 24.002055555555554, | |
| "grad_norm": 0.14431528747081757, | |
| "learning_rate": 4.877314814814815e-05, | |
| "loss": 0.061, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 24.004833333333334, | |
| "grad_norm": 33.57377624511719, | |
| "learning_rate": 4.861882716049383e-05, | |
| "loss": 0.1167, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 24.005, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_f1": 0.6379572761229566, | |
| "eval_loss": 1.569033145904541, | |
| "eval_precision": 0.7189384333615103, | |
| "eval_recall": 0.6538461538461539, | |
| "eval_runtime": 18.5212, | |
| "eval_samples_per_second": 18.249, | |
| "eval_steps_per_second": 9.125, | |
| "step": 4506 | |
| }, | |
| { | |
| "epoch": 25.002604166666668, | |
| "grad_norm": 0.03929486870765686, | |
| "learning_rate": 4.8464506172839505e-05, | |
| "loss": 0.0366, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 25.004993055555556, | |
| "eval_accuracy": 0.6745562130177515, | |
| "eval_f1": 0.6541387606476363, | |
| "eval_loss": 1.5032190084457397, | |
| "eval_precision": 0.6978867286559595, | |
| "eval_recall": 0.6745562130177515, | |
| "eval_runtime": 18.3411, | |
| "eval_samples_per_second": 18.429, | |
| "eval_steps_per_second": 9.214, | |
| "step": 4686 | |
| }, | |
| { | |
| "epoch": 26.000375, | |
| "grad_norm": 0.10611555725336075, | |
| "learning_rate": 4.831018518518518e-05, | |
| "loss": 0.1361, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 26.00315277777778, | |
| "grad_norm": 1.335172176361084, | |
| "learning_rate": 4.815586419753087e-05, | |
| "loss": 0.1065, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 26.004986111111112, | |
| "eval_accuracy": 0.6390532544378699, | |
| "eval_f1": 0.6134555615324846, | |
| "eval_loss": 1.4892995357513428, | |
| "eval_precision": 0.6475309946463793, | |
| "eval_recall": 0.6390532544378699, | |
| "eval_runtime": 19.1889, | |
| "eval_samples_per_second": 17.614, | |
| "eval_steps_per_second": 8.807, | |
| "step": 4866 | |
| }, | |
| { | |
| "epoch": 27.000923611111112, | |
| "grad_norm": 0.25120797753334045, | |
| "learning_rate": 4.8001543209876545e-05, | |
| "loss": 0.1148, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 27.00370138888889, | |
| "grad_norm": 0.08281093835830688, | |
| "learning_rate": 4.784722222222223e-05, | |
| "loss": 0.0454, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 27.005006944444446, | |
| "eval_accuracy": 0.6242603550295858, | |
| "eval_f1": 0.6022126952600326, | |
| "eval_loss": 1.5013433694839478, | |
| "eval_precision": 0.6600591715976332, | |
| "eval_recall": 0.6242603550295858, | |
| "eval_runtime": 20.5193, | |
| "eval_samples_per_second": 16.472, | |
| "eval_steps_per_second": 8.236, | |
| "step": 5047 | |
| }, | |
| { | |
| "epoch": 28.001472222222223, | |
| "grad_norm": 0.05560300499200821, | |
| "learning_rate": 4.769290123456791e-05, | |
| "loss": 0.0973, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 28.00425, | |
| "grad_norm": 1.4039995670318604, | |
| "learning_rate": 4.7538580246913585e-05, | |
| "loss": 0.0844, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 28.005, | |
| "eval_accuracy": 0.6597633136094675, | |
| "eval_f1": 0.6388020099558561, | |
| "eval_loss": 1.5608867406845093, | |
| "eval_precision": 0.6974077204846435, | |
| "eval_recall": 0.6597633136094675, | |
| "eval_runtime": 20.1446, | |
| "eval_samples_per_second": 16.779, | |
| "eval_steps_per_second": 8.389, | |
| "step": 5227 | |
| }, | |
| { | |
| "epoch": 29.002020833333333, | |
| "grad_norm": 0.056026242673397064, | |
| "learning_rate": 4.738425925925926e-05, | |
| "loss": 0.0921, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 29.00479861111111, | |
| "grad_norm": 0.39889276027679443, | |
| "learning_rate": 4.722993827160494e-05, | |
| "loss": 0.109, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 29.004993055555556, | |
| "eval_accuracy": 0.665680473372781, | |
| "eval_f1": 0.6506595311329039, | |
| "eval_loss": 1.4839813709259033, | |
| "eval_precision": 0.7151002843310535, | |
| "eval_recall": 0.665680473372781, | |
| "eval_runtime": 18.7473, | |
| "eval_samples_per_second": 18.029, | |
| "eval_steps_per_second": 9.015, | |
| "step": 5407 | |
| }, | |
| { | |
| "epoch": 30.002569444444443, | |
| "grad_norm": 0.05277135968208313, | |
| "learning_rate": 4.707561728395062e-05, | |
| "loss": 0.1508, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 30.004986111111112, | |
| "eval_accuracy": 0.6035502958579881, | |
| "eval_f1": 0.590259690999336, | |
| "eval_loss": 1.801746129989624, | |
| "eval_precision": 0.6784164553395322, | |
| "eval_recall": 0.6035502958579881, | |
| "eval_runtime": 17.6073, | |
| "eval_samples_per_second": 19.197, | |
| "eval_steps_per_second": 9.598, | |
| "step": 5587 | |
| }, | |
| { | |
| "epoch": 31.000340277777777, | |
| "grad_norm": 0.6189529895782471, | |
| "learning_rate": 4.6921296296296296e-05, | |
| "loss": 0.0796, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 31.003118055555557, | |
| "grad_norm": 0.06006496772170067, | |
| "learning_rate": 4.676697530864197e-05, | |
| "loss": 0.1114, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 31.005006944444446, | |
| "eval_accuracy": 0.6390532544378699, | |
| "eval_f1": 0.613423755731448, | |
| "eval_loss": 1.6675891876220703, | |
| "eval_precision": 0.6721329952099183, | |
| "eval_recall": 0.6390532544378699, | |
| "eval_runtime": 17.8113, | |
| "eval_samples_per_second": 18.977, | |
| "eval_steps_per_second": 9.488, | |
| "step": 5768 | |
| }, | |
| { | |
| "epoch": 32.00088888888889, | |
| "grad_norm": 0.04244798794388771, | |
| "learning_rate": 4.661265432098766e-05, | |
| "loss": 0.1236, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 32.00366666666667, | |
| "grad_norm": 0.24667857587337494, | |
| "learning_rate": 4.6458333333333335e-05, | |
| "loss": 0.0931, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 32.005, | |
| "eval_accuracy": 0.6745562130177515, | |
| "eval_f1": 0.6520330097253173, | |
| "eval_loss": 1.534504771232605, | |
| "eval_precision": 0.7082065370526909, | |
| "eval_recall": 0.6745562130177515, | |
| "eval_runtime": 16.9203, | |
| "eval_samples_per_second": 19.976, | |
| "eval_steps_per_second": 9.988, | |
| "step": 5948 | |
| }, | |
| { | |
| "epoch": 33.0014375, | |
| "grad_norm": 0.04040142521262169, | |
| "learning_rate": 4.630401234567901e-05, | |
| "loss": 0.0767, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 33.004215277777774, | |
| "grad_norm": 0.18193276226520538, | |
| "learning_rate": 4.614969135802469e-05, | |
| "loss": 0.0619, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 33.00499305555556, | |
| "eval_accuracy": 0.6301775147928994, | |
| "eval_f1": 0.6008137161983316, | |
| "eval_loss": 1.746155858039856, | |
| "eval_precision": 0.6424168779938011, | |
| "eval_recall": 0.6301775147928994, | |
| "eval_runtime": 18.9428, | |
| "eval_samples_per_second": 17.843, | |
| "eval_steps_per_second": 8.922, | |
| "step": 6128 | |
| }, | |
| { | |
| "epoch": 34.00198611111111, | |
| "grad_norm": 0.009634270332753658, | |
| "learning_rate": 4.599691358024691e-05, | |
| "loss": 0.1314, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 34.00476388888889, | |
| "grad_norm": 0.21367499232292175, | |
| "learning_rate": 4.584259259259259e-05, | |
| "loss": 0.2698, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 34.00498611111111, | |
| "eval_accuracy": 0.6331360946745562, | |
| "eval_f1": 0.6126230606999838, | |
| "eval_loss": 1.7031519412994385, | |
| "eval_precision": 0.6710693153000845, | |
| "eval_recall": 0.6331360946745562, | |
| "eval_runtime": 19.9792, | |
| "eval_samples_per_second": 16.918, | |
| "eval_steps_per_second": 8.459, | |
| "step": 6308 | |
| }, | |
| { | |
| "epoch": 35.00253472222222, | |
| "grad_norm": 0.03326309099793434, | |
| "learning_rate": 4.5688271604938275e-05, | |
| "loss": 0.1108, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 35.005006944444446, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_f1": 0.62648739111679, | |
| "eval_loss": 1.7694625854492188, | |
| "eval_precision": 0.6784205193228862, | |
| "eval_recall": 0.6538461538461539, | |
| "eval_runtime": 18.3538, | |
| "eval_samples_per_second": 18.416, | |
| "eval_steps_per_second": 9.208, | |
| "step": 6489 | |
| }, | |
| { | |
| "epoch": 36.000305555555556, | |
| "grad_norm": 104.1079330444336, | |
| "learning_rate": 4.553395061728395e-05, | |
| "loss": 0.1261, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 36.003083333333336, | |
| "grad_norm": 0.1133200004696846, | |
| "learning_rate": 4.537962962962963e-05, | |
| "loss": 0.1006, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 36.005, | |
| "eval_accuracy": 0.5828402366863905, | |
| "eval_f1": 0.5661115757104835, | |
| "eval_loss": 2.018780469894409, | |
| "eval_precision": 0.6289293300387975, | |
| "eval_recall": 0.5828402366863905, | |
| "eval_runtime": 17.6731, | |
| "eval_samples_per_second": 19.125, | |
| "eval_steps_per_second": 9.563, | |
| "step": 6669 | |
| }, | |
| { | |
| "epoch": 37.00085416666667, | |
| "grad_norm": 0.024959033355116844, | |
| "learning_rate": 4.5225308641975314e-05, | |
| "loss": 0.1183, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 37.00363194444444, | |
| "grad_norm": 0.09667906910181046, | |
| "learning_rate": 4.507098765432099e-05, | |
| "loss": 0.0823, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 37.00499305555556, | |
| "eval_accuracy": 0.6568047337278107, | |
| "eval_f1": 0.6425439452066671, | |
| "eval_loss": 1.6487033367156982, | |
| "eval_precision": 0.6874260355029587, | |
| "eval_recall": 0.6568047337278107, | |
| "eval_runtime": 20.3974, | |
| "eval_samples_per_second": 16.571, | |
| "eval_steps_per_second": 8.285, | |
| "step": 6849 | |
| }, | |
| { | |
| "epoch": 38.00140277777778, | |
| "grad_norm": 0.025008585304021835, | |
| "learning_rate": 4.491666666666667e-05, | |
| "loss": 0.1114, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 38.00418055555556, | |
| "grad_norm": 3.3624982833862305, | |
| "learning_rate": 4.476234567901235e-05, | |
| "loss": 0.0632, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 38.00498611111111, | |
| "eval_accuracy": 0.636094674556213, | |
| "eval_f1": 0.6253254280582216, | |
| "eval_loss": 1.8013869524002075, | |
| "eval_precision": 0.691735347985348, | |
| "eval_recall": 0.636094674556213, | |
| "eval_runtime": 18.4919, | |
| "eval_samples_per_second": 18.278, | |
| "eval_steps_per_second": 9.139, | |
| "step": 7029 | |
| }, | |
| { | |
| "epoch": 39.00195138888889, | |
| "grad_norm": 0.028111210092902184, | |
| "learning_rate": 4.4608024691358025e-05, | |
| "loss": 0.0691, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 39.004729166666664, | |
| "grad_norm": 0.022145342081785202, | |
| "learning_rate": 4.445370370370371e-05, | |
| "loss": 0.1162, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 39.005006944444446, | |
| "eval_accuracy": 0.6449704142011834, | |
| "eval_f1": 0.6195841797912803, | |
| "eval_loss": 1.67414128780365, | |
| "eval_precision": 0.6671691556306941, | |
| "eval_recall": 0.6449704142011834, | |
| "eval_runtime": 19.1991, | |
| "eval_samples_per_second": 17.605, | |
| "eval_steps_per_second": 8.802, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 40.0025, | |
| "grad_norm": 0.012291846796870232, | |
| "learning_rate": 4.429938271604939e-05, | |
| "loss": 0.0846, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 40.005, | |
| "eval_accuracy": 0.636094674556213, | |
| "eval_f1": 0.6205015070399685, | |
| "eval_loss": 1.8031796216964722, | |
| "eval_precision": 0.6948467692900892, | |
| "eval_recall": 0.636094674556213, | |
| "eval_runtime": 19.3607, | |
| "eval_samples_per_second": 17.458, | |
| "eval_steps_per_second": 8.729, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 41.00027083333333, | |
| "grad_norm": 0.45003169775009155, | |
| "learning_rate": 4.4145061728395065e-05, | |
| "loss": 0.146, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 41.00304861111111, | |
| "grad_norm": 4.705352306365967, | |
| "learning_rate": 4.399074074074074e-05, | |
| "loss": 0.1528, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 41.00499305555556, | |
| "eval_accuracy": 0.6331360946745562, | |
| "eval_f1": 0.6101778563317025, | |
| "eval_loss": 1.8375493288040161, | |
| "eval_precision": 0.673196675119752, | |
| "eval_recall": 0.6331360946745562, | |
| "eval_runtime": 17.7659, | |
| "eval_samples_per_second": 19.025, | |
| "eval_steps_per_second": 9.513, | |
| "step": 7570 | |
| }, | |
| { | |
| "epoch": 42.000819444444446, | |
| "grad_norm": 94.2012939453125, | |
| "learning_rate": 4.383641975308642e-05, | |
| "loss": 0.1548, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 42.003597222222226, | |
| "grad_norm": 0.008578118868172169, | |
| "learning_rate": 4.36820987654321e-05, | |
| "loss": 0.0695, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 42.00498611111111, | |
| "eval_accuracy": 0.6568047337278107, | |
| "eval_f1": 0.6417349744272821, | |
| "eval_loss": 1.672219157218933, | |
| "eval_precision": 0.7030008453085377, | |
| "eval_recall": 0.6568047337278107, | |
| "eval_runtime": 18.0993, | |
| "eval_samples_per_second": 18.675, | |
| "eval_steps_per_second": 9.337, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 43.00136805555555, | |
| "grad_norm": 0.005858391989022493, | |
| "learning_rate": 4.3527777777777776e-05, | |
| "loss": 0.0513, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 43.00414583333333, | |
| "grad_norm": 0.24502906203269958, | |
| "learning_rate": 4.3375000000000004e-05, | |
| "loss": 0.1516, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 43.005006944444446, | |
| "eval_accuracy": 0.6715976331360947, | |
| "eval_f1": 0.6494567398413551, | |
| "eval_loss": 1.7810900211334229, | |
| "eval_precision": 0.7009087066779375, | |
| "eval_recall": 0.6715976331360947, | |
| "eval_runtime": 18.6526, | |
| "eval_samples_per_second": 18.121, | |
| "eval_steps_per_second": 9.06, | |
| "step": 7931 | |
| }, | |
| { | |
| "epoch": 44.001916666666666, | |
| "grad_norm": 0.023847075179219246, | |
| "learning_rate": 4.322067901234568e-05, | |
| "loss": 0.1172, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 44.004694444444446, | |
| "grad_norm": 0.1472051441669464, | |
| "learning_rate": 4.306635802469136e-05, | |
| "loss": 0.1565, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 44.005, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_f1": 0.6346678469459534, | |
| "eval_loss": 1.8077248334884644, | |
| "eval_precision": 0.6883840518455903, | |
| "eval_recall": 0.6538461538461539, | |
| "eval_runtime": 18.0276, | |
| "eval_samples_per_second": 18.749, | |
| "eval_steps_per_second": 9.375, | |
| "step": 8111 | |
| }, | |
| { | |
| "epoch": 45.00246527777778, | |
| "grad_norm": 0.013580802828073502, | |
| "learning_rate": 4.291203703703704e-05, | |
| "loss": 0.0728, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 45.00499305555556, | |
| "eval_accuracy": 0.6272189349112426, | |
| "eval_f1": 0.604730419153496, | |
| "eval_loss": 1.7950366735458374, | |
| "eval_precision": 0.6755196480048551, | |
| "eval_recall": 0.6272189349112426, | |
| "eval_runtime": 18.0454, | |
| "eval_samples_per_second": 18.731, | |
| "eval_steps_per_second": 9.365, | |
| "step": 8291 | |
| }, | |
| { | |
| "epoch": 45.00499305555556, | |
| "step": 8291, | |
| "total_flos": 1.700902027656954e+20, | |
| "train_loss": 3.3378389804185824, | |
| "train_runtime": 8591.5525, | |
| "train_samples_per_second": 33.521, | |
| "train_steps_per_second": 4.19 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 36000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 20, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 20 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.700902027656954e+20, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |