| { | |
| "best_metric": 0.8897058823529411, | |
| "best_model_checkpoint": "convnext-tiny-224-finetuned-papsmear/checkpoint-399", | |
| "epoch": 46.15384615384615, | |
| "eval_steps": 500, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9230769230769231, | |
| "eval_accuracy": 0.16911764705882354, | |
| "eval_loss": 1.780842900276184, | |
| "eval_runtime": 28.9972, | |
| "eval_samples_per_second": 4.69, | |
| "eval_steps_per_second": 0.172, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 2.4460816383361816, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.8057, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.9487179487179487, | |
| "eval_accuracy": 0.33088235294117646, | |
| "eval_loss": 1.680767297744751, | |
| "eval_runtime": 28.8937, | |
| "eval_samples_per_second": 4.707, | |
| "eval_steps_per_second": 0.173, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 2.7383179664611816, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.7394, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.9743589743589745, | |
| "eval_accuracy": 0.3382352941176471, | |
| "eval_loss": 1.5824888944625854, | |
| "eval_runtime": 29.5183, | |
| "eval_samples_per_second": 4.607, | |
| "eval_steps_per_second": 0.169, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 2.6751656532287598, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.6408, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.375, | |
| "eval_loss": 1.4575930833816528, | |
| "eval_runtime": 29.917, | |
| "eval_samples_per_second": 4.546, | |
| "eval_steps_per_second": 0.167, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "grad_norm": 2.3050172328948975, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.5428, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "eval_accuracy": 0.5220588235294118, | |
| "eval_loss": 1.328136682510376, | |
| "eval_runtime": 29.7396, | |
| "eval_samples_per_second": 4.573, | |
| "eval_steps_per_second": 0.168, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "grad_norm": 3.6692676544189453, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 1.3931, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.948717948717949, | |
| "eval_accuracy": 0.5588235294117647, | |
| "eval_loss": 1.2043910026550293, | |
| "eval_runtime": 29.8682, | |
| "eval_samples_per_second": 4.553, | |
| "eval_steps_per_second": 0.167, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 5.583779811859131, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.2669, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.9743589743589745, | |
| "eval_accuracy": 0.6102941176470589, | |
| "eval_loss": 1.0755624771118164, | |
| "eval_runtime": 29.2586, | |
| "eval_samples_per_second": 4.648, | |
| "eval_steps_per_second": 0.171, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 7.17948717948718, | |
| "grad_norm": 4.539360046386719, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 1.1355, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6323529411764706, | |
| "eval_loss": 0.9844695925712585, | |
| "eval_runtime": 29.1373, | |
| "eval_samples_per_second": 4.668, | |
| "eval_steps_per_second": 0.172, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 8.205128205128204, | |
| "grad_norm": 4.369154453277588, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 1.0379, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.923076923076923, | |
| "eval_accuracy": 0.6617647058823529, | |
| "eval_loss": 0.9259934425354004, | |
| "eval_runtime": 28.1315, | |
| "eval_samples_per_second": 4.834, | |
| "eval_steps_per_second": 0.178, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 9.379680633544922, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9571, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 9.948717948717949, | |
| "eval_accuracy": 0.6617647058823529, | |
| "eval_loss": 0.8539159893989563, | |
| "eval_runtime": 28.427, | |
| "eval_samples_per_second": 4.784, | |
| "eval_steps_per_second": 0.176, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 10.256410256410255, | |
| "grad_norm": 5.348514080047607, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.8376, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 10.974358974358974, | |
| "eval_accuracy": 0.7279411764705882, | |
| "eval_loss": 0.7998486757278442, | |
| "eval_runtime": 27.68, | |
| "eval_samples_per_second": 4.913, | |
| "eval_steps_per_second": 0.181, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 11.282051282051283, | |
| "grad_norm": 5.533881664276123, | |
| "learning_rate": 4.197530864197531e-05, | |
| "loss": 0.7942, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.757344663143158, | |
| "eval_runtime": 28.6943, | |
| "eval_samples_per_second": 4.74, | |
| "eval_steps_per_second": 0.174, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 8.20283031463623, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.7095, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 12.923076923076923, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.7004891633987427, | |
| "eval_runtime": 27.9492, | |
| "eval_samples_per_second": 4.866, | |
| "eval_steps_per_second": 0.179, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 7.526528358459473, | |
| "learning_rate": 3.950617283950617e-05, | |
| "loss": 0.7022, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 13.948717948717949, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.6833786964416504, | |
| "eval_runtime": 28.5203, | |
| "eval_samples_per_second": 4.769, | |
| "eval_steps_per_second": 0.175, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 14.35897435897436, | |
| "grad_norm": 8.826446533203125, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.6504, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 14.974358974358974, | |
| "eval_accuracy": 0.7720588235294118, | |
| "eval_loss": 0.6552230715751648, | |
| "eval_runtime": 28.1583, | |
| "eval_samples_per_second": 4.83, | |
| "eval_steps_per_second": 0.178, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 11.680583953857422, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.589, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8014705882352942, | |
| "eval_loss": 0.6191554665565491, | |
| "eval_runtime": 28.3476, | |
| "eval_samples_per_second": 4.798, | |
| "eval_steps_per_second": 0.176, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 16.41025641025641, | |
| "grad_norm": 7.944546699523926, | |
| "learning_rate": 3.580246913580247e-05, | |
| "loss": 0.5679, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "eval_accuracy": 0.8088235294117647, | |
| "eval_loss": 0.5738231539726257, | |
| "eval_runtime": 28.4094, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 0.176, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 17.435897435897434, | |
| "grad_norm": 13.33797550201416, | |
| "learning_rate": 3.45679012345679e-05, | |
| "loss": 0.5236, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 17.94871794871795, | |
| "eval_accuracy": 0.8014705882352942, | |
| "eval_loss": 0.5617075562477112, | |
| "eval_runtime": 27.45, | |
| "eval_samples_per_second": 4.954, | |
| "eval_steps_per_second": 0.182, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "grad_norm": 9.086050987243652, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5244, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 18.974358974358974, | |
| "eval_accuracy": 0.8235294117647058, | |
| "eval_loss": 0.5072647333145142, | |
| "eval_runtime": 27.8398, | |
| "eval_samples_per_second": 4.885, | |
| "eval_steps_per_second": 0.18, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 19.487179487179485, | |
| "grad_norm": 17.615938186645508, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 0.4781, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8161764705882353, | |
| "eval_loss": 0.5111706256866455, | |
| "eval_runtime": 28.0372, | |
| "eval_samples_per_second": 4.851, | |
| "eval_steps_per_second": 0.178, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 20.51282051282051, | |
| "grad_norm": 8.245569229125977, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.453, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 20.923076923076923, | |
| "eval_accuracy": 0.8235294117647058, | |
| "eval_loss": 0.46496695280075073, | |
| "eval_runtime": 27.566, | |
| "eval_samples_per_second": 4.934, | |
| "eval_steps_per_second": 0.181, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 21.53846153846154, | |
| "grad_norm": 29.225616455078125, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.4544, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 21.94871794871795, | |
| "eval_accuracy": 0.8455882352941176, | |
| "eval_loss": 0.45913681387901306, | |
| "eval_runtime": 28.694, | |
| "eval_samples_per_second": 4.74, | |
| "eval_steps_per_second": 0.174, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 22.564102564102566, | |
| "grad_norm": 11.300565719604492, | |
| "learning_rate": 2.839506172839506e-05, | |
| "loss": 0.419, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 22.974358974358974, | |
| "eval_accuracy": 0.8308823529411765, | |
| "eval_loss": 0.4402587115764618, | |
| "eval_runtime": 27.5811, | |
| "eval_samples_per_second": 4.931, | |
| "eval_steps_per_second": 0.181, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 23.58974358974359, | |
| "grad_norm": 24.8338680267334, | |
| "learning_rate": 2.7160493827160493e-05, | |
| "loss": 0.4146, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.4292435348033905, | |
| "eval_runtime": 28.0224, | |
| "eval_samples_per_second": 4.853, | |
| "eval_steps_per_second": 0.178, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 24.615384615384617, | |
| "grad_norm": 33.230125427246094, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.398, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 24.923076923076923, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.4315250515937805, | |
| "eval_runtime": 27.9117, | |
| "eval_samples_per_second": 4.873, | |
| "eval_steps_per_second": 0.179, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "grad_norm": 11.8997802734375, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.3918, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 25.94871794871795, | |
| "eval_accuracy": 0.8676470588235294, | |
| "eval_loss": 0.39800333976745605, | |
| "eval_runtime": 27.1303, | |
| "eval_samples_per_second": 5.013, | |
| "eval_steps_per_second": 0.184, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 16.35055923461914, | |
| "learning_rate": 2.345679012345679e-05, | |
| "loss": 0.361, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 26.974358974358974, | |
| "eval_accuracy": 0.8602941176470589, | |
| "eval_loss": 0.37583470344543457, | |
| "eval_runtime": 27.9321, | |
| "eval_samples_per_second": 4.869, | |
| "eval_steps_per_second": 0.179, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 27.692307692307693, | |
| "grad_norm": 7.5509724617004395, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.3355, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8602941176470589, | |
| "eval_loss": 0.36569300293922424, | |
| "eval_runtime": 27.4222, | |
| "eval_samples_per_second": 4.959, | |
| "eval_steps_per_second": 0.182, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 28.71794871794872, | |
| "grad_norm": 16.6190128326416, | |
| "learning_rate": 2.0987654320987655e-05, | |
| "loss": 0.3483, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 28.923076923076923, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.366921603679657, | |
| "eval_runtime": 27.8307, | |
| "eval_samples_per_second": 4.887, | |
| "eval_steps_per_second": 0.18, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 29.743589743589745, | |
| "grad_norm": 14.241522789001465, | |
| "learning_rate": 1.9753086419753087e-05, | |
| "loss": 0.3171, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 29.94871794871795, | |
| "eval_accuracy": 0.8602941176470589, | |
| "eval_loss": 0.3492419719696045, | |
| "eval_runtime": 27.0548, | |
| "eval_samples_per_second": 5.027, | |
| "eval_steps_per_second": 0.185, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 30.76923076923077, | |
| "grad_norm": 13.727191925048828, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3249, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 30.974358974358974, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.3399755358695984, | |
| "eval_runtime": 27.5478, | |
| "eval_samples_per_second": 4.937, | |
| "eval_steps_per_second": 0.182, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 31.794871794871796, | |
| "grad_norm": 16.1718692779541, | |
| "learning_rate": 1.728395061728395e-05, | |
| "loss": 0.3087, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.3251068592071533, | |
| "eval_runtime": 28.8731, | |
| "eval_samples_per_second": 4.71, | |
| "eval_steps_per_second": 0.173, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 32.82051282051282, | |
| "grad_norm": 14.378969192504883, | |
| "learning_rate": 1.604938271604938e-05, | |
| "loss": 0.3029, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 32.92307692307692, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.31666299700737, | |
| "eval_runtime": 27.475, | |
| "eval_samples_per_second": 4.95, | |
| "eval_steps_per_second": 0.182, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 33.84615384615385, | |
| "grad_norm": 12.18956470489502, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.3018, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 33.94871794871795, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.3191751539707184, | |
| "eval_runtime": 27.7647, | |
| "eval_samples_per_second": 4.898, | |
| "eval_steps_per_second": 0.18, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 34.87179487179487, | |
| "grad_norm": 12.676053047180176, | |
| "learning_rate": 1.3580246913580247e-05, | |
| "loss": 0.2823, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 34.97435897435897, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.3066389560699463, | |
| "eval_runtime": 27.6676, | |
| "eval_samples_per_second": 4.916, | |
| "eval_steps_per_second": 0.181, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 35.8974358974359, | |
| "grad_norm": 10.490346908569336, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.2744, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.300258070230484, | |
| "eval_runtime": 29.0445, | |
| "eval_samples_per_second": 4.682, | |
| "eval_steps_per_second": 0.172, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "grad_norm": 17.77071189880371, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.258, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.2963866591453552, | |
| "eval_runtime": 27.8633, | |
| "eval_samples_per_second": 4.881, | |
| "eval_steps_per_second": 0.179, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "grad_norm": 14.726465225219727, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 0.2714, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.3039358854293823, | |
| "eval_runtime": 27.3906, | |
| "eval_samples_per_second": 4.965, | |
| "eval_steps_per_second": 0.183, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "grad_norm": 5.834155082702637, | |
| "learning_rate": 8.641975308641975e-06, | |
| "loss": 0.2486, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.29370391368865967, | |
| "eval_runtime": 27.4875, | |
| "eval_samples_per_second": 4.948, | |
| "eval_steps_per_second": 0.182, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 48.52106857299805, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.2511, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.27393513917922974, | |
| "eval_runtime": 27.5378, | |
| "eval_samples_per_second": 4.939, | |
| "eval_steps_per_second": 0.182, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 40.92307692307692, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.28356170654296875, | |
| "eval_runtime": 27.6475, | |
| "eval_samples_per_second": 4.919, | |
| "eval_steps_per_second": 0.181, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 41.02564102564103, | |
| "grad_norm": 12.991565704345703, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.2659, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 41.94871794871795, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.2804461717605591, | |
| "eval_runtime": 28.1041, | |
| "eval_samples_per_second": 4.839, | |
| "eval_steps_per_second": 0.178, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 42.05128205128205, | |
| "grad_norm": 10.837814331054688, | |
| "learning_rate": 4.938271604938272e-06, | |
| "loss": 0.2379, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 42.97435897435897, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.2746768891811371, | |
| "eval_runtime": 27.287, | |
| "eval_samples_per_second": 4.984, | |
| "eval_steps_per_second": 0.183, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 43.07692307692308, | |
| "grad_norm": 21.34435272216797, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.2279, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.27258822321891785, | |
| "eval_runtime": 27.4605, | |
| "eval_samples_per_second": 4.953, | |
| "eval_steps_per_second": 0.182, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 44.1025641025641, | |
| "grad_norm": 15.666738510131836, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 0.2153, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 44.92307692307692, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.27316194772720337, | |
| "eval_runtime": 28.0117, | |
| "eval_samples_per_second": 4.855, | |
| "eval_steps_per_second": 0.178, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 45.12820512820513, | |
| "grad_norm": 9.311797142028809, | |
| "learning_rate": 1.234567901234568e-06, | |
| "loss": 0.2461, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 45.94871794871795, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.27384060621261597, | |
| "eval_runtime": 28.0924, | |
| "eval_samples_per_second": 4.841, | |
| "eval_steps_per_second": 0.178, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "grad_norm": 23.28314971923828, | |
| "learning_rate": 0.0, | |
| "loss": 0.2482, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_loss": 0.2737831771373749, | |
| "eval_runtime": 28.0709, | |
| "eval_samples_per_second": 4.845, | |
| "eval_steps_per_second": 0.178, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "step": 450, | |
| "total_flos": 1.4197680152537334e+18, | |
| "train_loss": 0.6011993959214952, | |
| "train_runtime": 12614.4578, | |
| "train_samples_per_second": 4.852, | |
| "train_steps_per_second": 0.036 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4197680152537334e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |