| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 36816, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9972837896566713e-05, | |
| "loss": 1.054, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.994567579313342e-05, | |
| "loss": 0.9516, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9918513689700133e-05, | |
| "loss": 0.9139, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9891351586266844e-05, | |
| "loss": 0.9051, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9864189482833552e-05, | |
| "loss": 0.8783, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.983702737940026e-05, | |
| "loss": 0.8573, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9809865275966972e-05, | |
| "loss": 0.8207, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.978270317253368e-05, | |
| "loss": 0.794, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9755541069100392e-05, | |
| "loss": 0.8113, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9728378965667103e-05, | |
| "loss": 0.8082, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.6484971981660723, | |
| "eval_loss": 0.7957563400268555, | |
| "eval_runtime": 17.0314, | |
| "eval_samples_per_second": 576.29, | |
| "eval_steps_per_second": 36.051, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9701216862233815e-05, | |
| "loss": 0.7763, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9674054758800523e-05, | |
| "loss": 0.7587, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9646892655367235e-05, | |
| "loss": 0.7735, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9619730551933943e-05, | |
| "loss": 0.755, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9592568448500654e-05, | |
| "loss": 0.7527, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9565406345067362e-05, | |
| "loss": 0.7235, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9538244241634074e-05, | |
| "loss": 0.7541, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9511082138200782e-05, | |
| "loss": 0.7464, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9483920034767494e-05, | |
| "loss": 0.729, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9456757931334205e-05, | |
| "loss": 0.7259, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.6894549159449822, | |
| "eval_loss": 0.7455270886421204, | |
| "eval_runtime": 16.9202, | |
| "eval_samples_per_second": 580.075, | |
| "eval_steps_per_second": 36.288, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9429595827900913e-05, | |
| "loss": 0.7029, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9402433724467625e-05, | |
| "loss": 0.7373, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9375271621034336e-05, | |
| "loss": 0.7395, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9348109517601044e-05, | |
| "loss": 0.7387, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9320947414167756e-05, | |
| "loss": 0.7048, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9293785310734464e-05, | |
| "loss": 0.7526, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9266623207301176e-05, | |
| "loss": 0.7174, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9239461103867884e-05, | |
| "loss": 0.7402, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9212299000434595e-05, | |
| "loss": 0.7091, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9185136897001307e-05, | |
| "loss": 0.7018, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.7117677024961793, | |
| "eval_loss": 0.697046160697937, | |
| "eval_runtime": 16.5846, | |
| "eval_samples_per_second": 591.813, | |
| "eval_steps_per_second": 37.022, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9157974793568015e-05, | |
| "loss": 0.7109, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9130812690134726e-05, | |
| "loss": 0.715, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9103650586701438e-05, | |
| "loss": 0.7342, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9076488483268146e-05, | |
| "loss": 0.6897, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9049326379834858e-05, | |
| "loss": 0.6904, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.9022164276401566e-05, | |
| "loss": 0.696, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.8995002172968274e-05, | |
| "loss": 0.7012, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.8967840069534985e-05, | |
| "loss": 0.6853, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.8940677966101697e-05, | |
| "loss": 0.6843, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.8913515862668405e-05, | |
| "loss": 0.7026, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.7126846663270504, | |
| "eval_loss": 0.6826978921890259, | |
| "eval_runtime": 16.6322, | |
| "eval_samples_per_second": 590.119, | |
| "eval_steps_per_second": 36.916, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.8886353759235117e-05, | |
| "loss": 0.6867, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.8859191655801828e-05, | |
| "loss": 0.7016, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8832029552368536e-05, | |
| "loss": 0.6852, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8804867448935248e-05, | |
| "loss": 0.6866, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8777705345501956e-05, | |
| "loss": 0.6875, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.8750543242068668e-05, | |
| "loss": 0.6745, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.8723381138635376e-05, | |
| "loss": 0.6835, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8696219035202087e-05, | |
| "loss": 0.7015, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.86690569317688e-05, | |
| "loss": 0.6591, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8641894828335507e-05, | |
| "loss": 0.6696, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.732348446255731, | |
| "eval_loss": 0.6500351428985596, | |
| "eval_runtime": 16.6184, | |
| "eval_samples_per_second": 590.61, | |
| "eval_steps_per_second": 36.947, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.861473272490222e-05, | |
| "loss": 0.6698, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.858757062146893e-05, | |
| "loss": 0.6786, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.8560408518035638e-05, | |
| "loss": 0.653, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.853324641460235e-05, | |
| "loss": 0.6565, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.8506084311169058e-05, | |
| "loss": 0.6336, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.847892220773577e-05, | |
| "loss": 0.6557, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.8451760104302477e-05, | |
| "loss": 0.6577, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.842459800086919e-05, | |
| "loss": 0.6704, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.8397435897435897e-05, | |
| "loss": 0.6687, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.837027379400261e-05, | |
| "loss": 0.6744, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.7379521141110545, | |
| "eval_loss": 0.6344741582870483, | |
| "eval_runtime": 16.7056, | |
| "eval_samples_per_second": 587.527, | |
| "eval_steps_per_second": 36.754, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.834311169056932e-05, | |
| "loss": 0.6719, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.8315949587136028e-05, | |
| "loss": 0.6715, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.828878748370274e-05, | |
| "loss": 0.6609, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.826162538026945e-05, | |
| "loss": 0.6616, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.823446327683616e-05, | |
| "loss": 0.6656, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.820730117340287e-05, | |
| "loss": 0.6704, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.818013906996958e-05, | |
| "loss": 0.6752, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.815297696653629e-05, | |
| "loss": 0.6648, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.8125814863103e-05, | |
| "loss": 0.672, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.809865275966971e-05, | |
| "loss": 0.6136, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.7401935812531839, | |
| "eval_loss": 0.6294288039207458, | |
| "eval_runtime": 16.6109, | |
| "eval_samples_per_second": 590.877, | |
| "eval_steps_per_second": 36.964, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.8071490656236422e-05, | |
| "loss": 0.6482, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.804432855280313e-05, | |
| "loss": 0.6243, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.801716644936984e-05, | |
| "loss": 0.6725, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.7990004345936553e-05, | |
| "loss": 0.608, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.796284224250326e-05, | |
| "loss": 0.7044, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.793568013906997e-05, | |
| "loss": 0.6414, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.790851803563668e-05, | |
| "loss": 0.606, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.788135593220339e-05, | |
| "loss": 0.651, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.78541938287701e-05, | |
| "loss": 0.645, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.7827031725336812e-05, | |
| "loss": 0.632, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.7472236372898624, | |
| "eval_loss": 0.6268670558929443, | |
| "eval_runtime": 16.6358, | |
| "eval_samples_per_second": 589.992, | |
| "eval_steps_per_second": 36.908, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.7799869621903524e-05, | |
| "loss": 0.6513, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.777270751847023e-05, | |
| "loss": 0.6287, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.7745545415036943e-05, | |
| "loss": 0.6541, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.771838331160365e-05, | |
| "loss": 0.6218, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.7691221208170363e-05, | |
| "loss": 0.6466, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.766405910473707e-05, | |
| "loss": 0.6607, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.7636897001303783e-05, | |
| "loss": 0.6593, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.760973489787049e-05, | |
| "loss": 0.6342, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.7582572794437202e-05, | |
| "loss": 0.6293, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.7555410691003914e-05, | |
| "loss": 0.6735, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.7488537952114112, | |
| "eval_loss": 0.6195499300956726, | |
| "eval_runtime": 16.6827, | |
| "eval_samples_per_second": 588.333, | |
| "eval_steps_per_second": 36.805, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.7528248587570622e-05, | |
| "loss": 0.6421, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.7501086484137333e-05, | |
| "loss": 0.6366, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.7473924380704045e-05, | |
| "loss": 0.6744, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.7446762277270753e-05, | |
| "loss": 0.6501, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.7419600173837465e-05, | |
| "loss": 0.6253, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.7392438070404173e-05, | |
| "loss": 0.622, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.7365275966970884e-05, | |
| "loss": 0.6402, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.7338113863537592e-05, | |
| "loss": 0.6292, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.7310951760104304e-05, | |
| "loss": 0.6268, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.7283789656671015e-05, | |
| "loss": 0.6202, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.7414161996943454, | |
| "eval_loss": 0.6335541009902954, | |
| "eval_runtime": 16.736, | |
| "eval_samples_per_second": 586.46, | |
| "eval_steps_per_second": 36.687, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.7256627553237724e-05, | |
| "loss": 0.611, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.7229465449804435e-05, | |
| "loss": 0.6101, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.7202303346371147e-05, | |
| "loss": 0.6348, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.7175141242937855e-05, | |
| "loss": 0.6076, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.7147979139504566e-05, | |
| "loss": 0.6617, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.7120817036071274e-05, | |
| "loss": 0.6127, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7093654932637983e-05, | |
| "loss": 0.6405, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7066492829204694e-05, | |
| "loss": 0.6036, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7039330725771406e-05, | |
| "loss": 0.6318, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.7012168622338114e-05, | |
| "loss": 0.6495, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.7517065715741212, | |
| "eval_loss": 0.6124893426895142, | |
| "eval_runtime": 17.3079, | |
| "eval_samples_per_second": 567.082, | |
| "eval_steps_per_second": 35.475, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.6985006518904825e-05, | |
| "loss": 0.629, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6957844415471537e-05, | |
| "loss": 0.6266, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6930682312038245e-05, | |
| "loss": 0.6063, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6903520208604957e-05, | |
| "loss": 0.6087, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.6876358105171665e-05, | |
| "loss": 0.6174, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.6849196001738376e-05, | |
| "loss": 0.6533, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6822033898305084e-05, | |
| "loss": 0.6389, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6794871794871796e-05, | |
| "loss": 0.6218, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6767709691438507e-05, | |
| "loss": 0.6181, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.6740547588005215e-05, | |
| "loss": 0.6235, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.7515028018339277, | |
| "eval_loss": 0.6097389459609985, | |
| "eval_runtime": 16.5568, | |
| "eval_samples_per_second": 592.808, | |
| "eval_steps_per_second": 37.084, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.6713385484571927e-05, | |
| "loss": 0.6581, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.668622338113864e-05, | |
| "loss": 0.6288, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.6659061277705347e-05, | |
| "loss": 0.639, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.6631899174272058e-05, | |
| "loss": 0.6057, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.6604737070838766e-05, | |
| "loss": 0.6332, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.6577574967405478e-05, | |
| "loss": 0.6089, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.6550412863972186e-05, | |
| "loss": 0.6442, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.6523250760538898e-05, | |
| "loss": 0.6089, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.6496088657105606e-05, | |
| "loss": 0.6056, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.6468926553672317e-05, | |
| "loss": 0.5852, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.758125318390219, | |
| "eval_loss": 0.6068304181098938, | |
| "eval_runtime": 16.5697, | |
| "eval_samples_per_second": 592.346, | |
| "eval_steps_per_second": 37.056, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.644176445023903e-05, | |
| "loss": 0.6521, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.6414602346805737e-05, | |
| "loss": 0.6018, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.638744024337245e-05, | |
| "loss": 0.6197, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.636027813993916e-05, | |
| "loss": 0.5924, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.6333116036505868e-05, | |
| "loss": 0.6155, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.630595393307258e-05, | |
| "loss": 0.6017, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.6278791829639288e-05, | |
| "loss": 0.6055, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.6251629726206e-05, | |
| "loss": 0.6155, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.6224467622772707e-05, | |
| "loss": 0.6481, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.619730551933942e-05, | |
| "loss": 0.6395, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.7492613346917982, | |
| "eval_loss": 0.6038582921028137, | |
| "eval_runtime": 16.6298, | |
| "eval_samples_per_second": 590.205, | |
| "eval_steps_per_second": 36.922, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.617014341590613e-05, | |
| "loss": 0.6394, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.614298131247284e-05, | |
| "loss": 0.5932, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.611581920903955e-05, | |
| "loss": 0.6, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.608865710560626e-05, | |
| "loss": 0.613, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.606149500217297e-05, | |
| "loss": 0.6144, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.6034332898739678e-05, | |
| "loss": 0.6415, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.600717079530639e-05, | |
| "loss": 0.5952, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.5980008691873098e-05, | |
| "loss": 0.624, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.595284658843981e-05, | |
| "loss": 0.6312, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.592568448500652e-05, | |
| "loss": 0.6009, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.7552725420275089, | |
| "eval_loss": 0.5877503752708435, | |
| "eval_runtime": 16.7748, | |
| "eval_samples_per_second": 585.104, | |
| "eval_steps_per_second": 36.603, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.589852238157323e-05, | |
| "loss": 0.5553, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.587136027813994e-05, | |
| "loss": 0.6063, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.5844198174706652e-05, | |
| "loss": 0.6206, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.5817036071273363e-05, | |
| "loss": 0.602, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.578987396784007e-05, | |
| "loss": 0.6027, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.576271186440678e-05, | |
| "loss": 0.5697, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.573554976097349e-05, | |
| "loss": 0.6199, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.57083876575402e-05, | |
| "loss": 0.6129, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.568122555410691e-05, | |
| "loss": 0.5687, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.5654063450673622e-05, | |
| "loss": 0.6059, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.7638308711156393, | |
| "eval_loss": 0.587600827217102, | |
| "eval_runtime": 16.6195, | |
| "eval_samples_per_second": 590.572, | |
| "eval_steps_per_second": 36.945, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.562690134724033e-05, | |
| "loss": 0.6294, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.5599739243807042e-05, | |
| "loss": 0.6165, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.5572577140373754e-05, | |
| "loss": 0.5893, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.5545415036940462e-05, | |
| "loss": 0.6011, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.5518252933507173e-05, | |
| "loss": 0.5966, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.549109083007388e-05, | |
| "loss": 0.5748, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.5463928726640593e-05, | |
| "loss": 0.5683, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.54367666232073e-05, | |
| "loss": 0.5961, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5409604519774013e-05, | |
| "loss": 0.639, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5382442416340724e-05, | |
| "loss": 0.6019, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.7650534895568009, | |
| "eval_loss": 0.5828633308410645, | |
| "eval_runtime": 16.5868, | |
| "eval_samples_per_second": 591.735, | |
| "eval_steps_per_second": 37.017, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5355280312907432e-05, | |
| "loss": 0.5775, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5328118209474144e-05, | |
| "loss": 0.6359, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5300956106040855e-05, | |
| "loss": 0.5983, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5273794002607563e-05, | |
| "loss": 0.5799, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5246631899174273e-05, | |
| "loss": 0.6028, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5219469795740985e-05, | |
| "loss": 0.591, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5192307692307693e-05, | |
| "loss": 0.6125, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.5165145588874404e-05, | |
| "loss": 0.5865, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.5137983485441114e-05, | |
| "loss": 0.5829, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.5110821382007822e-05, | |
| "loss": 0.5989, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.7611818644931228, | |
| "eval_loss": 0.5921522378921509, | |
| "eval_runtime": 16.6138, | |
| "eval_samples_per_second": 590.773, | |
| "eval_steps_per_second": 36.957, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5083659278574534e-05, | |
| "loss": 0.5825, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5056497175141245e-05, | |
| "loss": 0.6022, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5029335071707954e-05, | |
| "loss": 0.6153, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5002172968274663e-05, | |
| "loss": 0.6395, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.4975010864841375e-05, | |
| "loss": 0.5981, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.4947848761408083e-05, | |
| "loss": 0.6052, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.4920686657974795e-05, | |
| "loss": 0.5811, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4893524554541504e-05, | |
| "loss": 0.6188, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4866362451108216e-05, | |
| "loss": 0.5857, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4839200347674924e-05, | |
| "loss": 0.6195, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.7614875191034132, | |
| "eval_loss": 0.5868236422538757, | |
| "eval_runtime": 16.6677, | |
| "eval_samples_per_second": 588.863, | |
| "eval_steps_per_second": 36.838, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4812038244241636e-05, | |
| "loss": 0.5567, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4784876140808346e-05, | |
| "loss": 0.5745, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4757714037375055e-05, | |
| "loss": 0.564, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4730551933941765e-05, | |
| "loss": 0.5712, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4703389830508477e-05, | |
| "loss": 0.5771, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.4676227727075185e-05, | |
| "loss": 0.5914, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.4649065623641896e-05, | |
| "loss": 0.5496, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.4621903520208606e-05, | |
| "loss": 0.5674, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.4594741416775316e-05, | |
| "loss": 0.6229, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.4567579313342026e-05, | |
| "loss": 0.6028, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.7708609271523179, | |
| "eval_loss": 0.5723991990089417, | |
| "eval_runtime": 16.6902, | |
| "eval_samples_per_second": 588.068, | |
| "eval_steps_per_second": 36.788, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.4540417209908737e-05, | |
| "loss": 0.57, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.4513255106475446e-05, | |
| "loss": 0.5607, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4486093003042157e-05, | |
| "loss": 0.5943, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4458930899608867e-05, | |
| "loss": 0.6099, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.4431768796175577e-05, | |
| "loss": 0.6208, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.4404606692742287e-05, | |
| "loss": 0.5951, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.4377444589308998e-05, | |
| "loss": 0.6182, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.4350282485875708e-05, | |
| "loss": 0.577, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.4323120382442418e-05, | |
| "loss": 0.6062, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4295958279009128e-05, | |
| "loss": 0.5741, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.7716760061130922, | |
| "eval_loss": 0.5670150518417358, | |
| "eval_runtime": 17.275, | |
| "eval_samples_per_second": 568.162, | |
| "eval_steps_per_second": 35.543, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4268796175575839e-05, | |
| "loss": 0.5679, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4241634072142547e-05, | |
| "loss": 0.6072, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.4214471968709259e-05, | |
| "loss": 0.5923, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.4187309865275969e-05, | |
| "loss": 0.5478, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.4160147761842677e-05, | |
| "loss": 0.5796, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.4132985658409388e-05, | |
| "loss": 0.5723, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.41058235549761e-05, | |
| "loss": 0.5958, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.4078661451542808e-05, | |
| "loss": 0.5799, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.4051499348109518e-05, | |
| "loss": 0.5984, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.402433724467623e-05, | |
| "loss": 0.582, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.773204279164544, | |
| "eval_loss": 0.5701923370361328, | |
| "eval_runtime": 16.6758, | |
| "eval_samples_per_second": 588.579, | |
| "eval_steps_per_second": 36.82, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.3997175141242937e-05, | |
| "loss": 0.5914, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.3970013037809649e-05, | |
| "loss": 0.577, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.3942850934376359e-05, | |
| "loss": 0.6039, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.391568883094307e-05, | |
| "loss": 0.5756, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.3888526727509778e-05, | |
| "loss": 0.5661, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.386136462407649e-05, | |
| "loss": 0.5799, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.38342025206432e-05, | |
| "loss": 0.5825, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.380704041720991e-05, | |
| "loss": 0.5377, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.377987831377662e-05, | |
| "loss": 0.5592, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3752716210343331e-05, | |
| "loss": 0.5706, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.7755476311767703, | |
| "eval_loss": 0.5596539974212646, | |
| "eval_runtime": 16.5535, | |
| "eval_samples_per_second": 592.926, | |
| "eval_steps_per_second": 37.092, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.372555410691004e-05, | |
| "loss": 0.5668, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.369839200347675e-05, | |
| "loss": 0.6023, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.367122990004346e-05, | |
| "loss": 0.6018, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.364406779661017e-05, | |
| "loss": 0.6023, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.361690569317688e-05, | |
| "loss": 0.5844, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.3589743589743592e-05, | |
| "loss": 0.5498, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.35625814863103e-05, | |
| "loss": 0.6128, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3535419382877011e-05, | |
| "loss": 0.582, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3508257279443721e-05, | |
| "loss": 0.6105, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.3481095176010431e-05, | |
| "loss": 0.5676, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.7735099337748345, | |
| "eval_loss": 0.5655471682548523, | |
| "eval_runtime": 16.6523, | |
| "eval_samples_per_second": 589.407, | |
| "eval_steps_per_second": 36.872, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.3453933072577141e-05, | |
| "loss": 0.6, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.3426770969143852e-05, | |
| "loss": 0.5771, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.3399608865710562e-05, | |
| "loss": 0.5766, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.3372446762277272e-05, | |
| "loss": 0.5579, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3345284658843982e-05, | |
| "loss": 0.5777, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3318122555410693e-05, | |
| "loss": 0.5586, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.3290960451977402e-05, | |
| "loss": 0.5168, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.3263798348544113e-05, | |
| "loss": 0.481, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.3236636245110823e-05, | |
| "loss": 0.5111, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.3209474141677531e-05, | |
| "loss": 0.5235, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.7661742231278655, | |
| "eval_loss": 0.5849180817604065, | |
| "eval_runtime": 16.6987, | |
| "eval_samples_per_second": 587.77, | |
| "eval_steps_per_second": 36.769, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.3182312038244243e-05, | |
| "loss": 0.4823, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.3155149934810954e-05, | |
| "loss": 0.4994, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.3127987831377662e-05, | |
| "loss": 0.4964, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.3100825727944372e-05, | |
| "loss": 0.566, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.3073663624511084e-05, | |
| "loss": 0.5039, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.3046501521077792e-05, | |
| "loss": 0.5065, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.3019339417644503e-05, | |
| "loss": 0.5022, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.2992177314211213e-05, | |
| "loss": 0.4774, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.2965015210777925e-05, | |
| "loss": 0.5155, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.2937853107344633e-05, | |
| "loss": 0.521, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.7788079470198676, | |
| "eval_loss": 0.5645545125007629, | |
| "eval_runtime": 17.0994, | |
| "eval_samples_per_second": 573.997, | |
| "eval_steps_per_second": 35.908, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.2910691003911344e-05, | |
| "loss": 0.4994, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.2883528900478056e-05, | |
| "loss": 0.4956, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.2856366797044764e-05, | |
| "loss": 0.4972, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.2829204693611474e-05, | |
| "loss": 0.5194, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.2802042590178185e-05, | |
| "loss": 0.5387, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.2774880486744893e-05, | |
| "loss": 0.5384, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.2747718383311605e-05, | |
| "loss": 0.5104, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.2720556279878315e-05, | |
| "loss": 0.5093, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.2693394176445025e-05, | |
| "loss": 0.5115, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.2666232073011735e-05, | |
| "loss": 0.5122, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.7738155883851248, | |
| "eval_loss": 0.571690022945404, | |
| "eval_runtime": 16.5787, | |
| "eval_samples_per_second": 592.023, | |
| "eval_steps_per_second": 37.035, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.2639069969578446e-05, | |
| "loss": 0.5075, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.2611907866145154e-05, | |
| "loss": 0.5129, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.2584745762711866e-05, | |
| "loss": 0.4917, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.2557583659278576e-05, | |
| "loss": 0.5174, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.2530421555845285e-05, | |
| "loss": 0.5128, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.2503259452411995e-05, | |
| "loss": 0.5086, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.2476097348978707e-05, | |
| "loss": 0.5231, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.2448935245545417e-05, | |
| "loss": 0.5136, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.2421773142112126e-05, | |
| "loss": 0.5138, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.2394611038678836e-05, | |
| "loss": 0.5102, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_accuracy": 0.7764645950076413, | |
| "eval_loss": 0.5666928291320801, | |
| "eval_runtime": 16.6153, | |
| "eval_samples_per_second": 590.719, | |
| "eval_steps_per_second": 36.954, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.2367448935245548e-05, | |
| "loss": 0.5032, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.2340286831812256e-05, | |
| "loss": 0.5038, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.2313124728378967e-05, | |
| "loss": 0.5259, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.2285962624945677e-05, | |
| "loss": 0.5317, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.2258800521512385e-05, | |
| "loss": 0.4966, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.2231638418079097e-05, | |
| "loss": 0.4657, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.2204476314645808e-05, | |
| "loss": 0.5134, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.2177314211212517e-05, | |
| "loss": 0.5008, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.2150152107779226e-05, | |
| "loss": 0.4875, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.2122990004345938e-05, | |
| "loss": 0.5152, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.7779928680590932, | |
| "eval_loss": 0.5598427057266235, | |
| "eval_runtime": 16.6576, | |
| "eval_samples_per_second": 589.222, | |
| "eval_steps_per_second": 36.86, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.2095827900912646e-05, | |
| "loss": 0.505, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.2068665797479358e-05, | |
| "loss": 0.5347, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.204150369404607e-05, | |
| "loss": 0.5076, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2014341590612777e-05, | |
| "loss": 0.4958, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.1987179487179487e-05, | |
| "loss": 0.4894, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.1960017383746199e-05, | |
| "loss": 0.515, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.193285528031291e-05, | |
| "loss": 0.4977, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.1905693176879618e-05, | |
| "loss": 0.4875, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.1878531073446328e-05, | |
| "loss": 0.5038, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.185136897001304e-05, | |
| "loss": 0.4904, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_accuracy": 0.7746306673458991, | |
| "eval_loss": 0.5693045258522034, | |
| "eval_runtime": 16.677, | |
| "eval_samples_per_second": 588.536, | |
| "eval_steps_per_second": 36.817, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.1824206866579748e-05, | |
| "loss": 0.4827, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.179704476314646e-05, | |
| "loss": 0.5086, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.176988265971317e-05, | |
| "loss": 0.5306, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.1742720556279879e-05, | |
| "loss": 0.4733, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.1715558452846589e-05, | |
| "loss": 0.5022, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.16883963494133e-05, | |
| "loss": 0.4895, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.1661234245980009e-05, | |
| "loss": 0.5, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.163407214254672e-05, | |
| "loss": 0.5207, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.160691003911343e-05, | |
| "loss": 0.4875, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.157974793568014e-05, | |
| "loss": 0.507, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_accuracy": 0.7804381049414162, | |
| "eval_loss": 0.5583797097206116, | |
| "eval_runtime": 17.0661, | |
| "eval_samples_per_second": 575.117, | |
| "eval_steps_per_second": 35.978, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.155258583224685e-05, | |
| "loss": 0.4895, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.1525423728813561e-05, | |
| "loss": 0.4749, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.1498261625380271e-05, | |
| "loss": 0.4779, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.147109952194698e-05, | |
| "loss": 0.5026, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.144393741851369e-05, | |
| "loss": 0.486, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.1416775315080402e-05, | |
| "loss": 0.527, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.138961321164711e-05, | |
| "loss": 0.5671, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.1362451108213822e-05, | |
| "loss": 0.4655, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.1335289004780532e-05, | |
| "loss": 0.4796, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.130812690134724e-05, | |
| "loss": 0.5163, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_accuracy": 0.7787060621497708, | |
| "eval_loss": 0.5569875240325928, | |
| "eval_runtime": 16.5492, | |
| "eval_samples_per_second": 593.081, | |
| "eval_steps_per_second": 37.102, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.1280964797913951e-05, | |
| "loss": 0.4991, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.1253802694480663e-05, | |
| "loss": 0.4983, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.1226640591047371e-05, | |
| "loss": 0.5009, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.1199478487614082e-05, | |
| "loss": 0.4772, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.1172316384180792e-05, | |
| "loss": 0.453, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.11451542807475e-05, | |
| "loss": 0.4771, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.1117992177314212e-05, | |
| "loss": 0.5068, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.1090830073880923e-05, | |
| "loss": 0.4958, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.1063667970447632e-05, | |
| "loss": 0.5195, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.1036505867014341e-05, | |
| "loss": 0.4921, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_accuracy": 0.7798267957208355, | |
| "eval_loss": 0.5727071166038513, | |
| "eval_runtime": 16.5628, | |
| "eval_samples_per_second": 592.594, | |
| "eval_steps_per_second": 37.071, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.1009343763581053e-05, | |
| "loss": 0.4947, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.0982181660147765e-05, | |
| "loss": 0.4835, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.0955019556714473e-05, | |
| "loss": 0.4971, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.0927857453281182e-05, | |
| "loss": 0.5035, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.0900695349847894e-05, | |
| "loss": 0.499, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.0873533246414602e-05, | |
| "loss": 0.5214, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.0846371142981314e-05, | |
| "loss": 0.5168, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.0819209039548024e-05, | |
| "loss": 0.5138, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.0792046936114733e-05, | |
| "loss": 0.5218, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.0764884832681443e-05, | |
| "loss": 0.5249, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_accuracy": 0.7789098318899643, | |
| "eval_loss": 0.5653498768806458, | |
| "eval_runtime": 16.6944, | |
| "eval_samples_per_second": 587.923, | |
| "eval_steps_per_second": 36.779, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.0737722729248155e-05, | |
| "loss": 0.4932, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.0710560625814863e-05, | |
| "loss": 0.483, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0683398522381574e-05, | |
| "loss": 0.4782, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0656236418948284e-05, | |
| "loss": 0.506, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.0629074315514994e-05, | |
| "loss": 0.5083, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.0601912212081704e-05, | |
| "loss": 0.4828, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.0574750108648415e-05, | |
| "loss": 0.5181, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.0547588005215125e-05, | |
| "loss": 0.5061, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.0520425901781835e-05, | |
| "loss": 0.5177, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.0493263798348545e-05, | |
| "loss": 0.4994, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.7782985226693836, | |
| "eval_loss": 0.5726353526115417, | |
| "eval_runtime": 16.7415, | |
| "eval_samples_per_second": 586.269, | |
| "eval_steps_per_second": 36.675, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.0466101694915256e-05, | |
| "loss": 0.4989, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.0438939591481965e-05, | |
| "loss": 0.4856, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.0411777488048676e-05, | |
| "loss": 0.503, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.0384615384615386e-05, | |
| "loss": 0.4814, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.0357453281182096e-05, | |
| "loss": 0.5103, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.0330291177748806e-05, | |
| "loss": 0.5073, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.0303129074315517e-05, | |
| "loss": 0.4973, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.0275966970882225e-05, | |
| "loss": 0.4824, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.0248804867448937e-05, | |
| "loss": 0.4693, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.0221642764015647e-05, | |
| "loss": 0.5335, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_accuracy": 0.7848191543555781, | |
| "eval_loss": 0.5547093152999878, | |
| "eval_runtime": 17.1248, | |
| "eval_samples_per_second": 573.144, | |
| "eval_steps_per_second": 35.854, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.0194480660582355e-05, | |
| "loss": 0.5185, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.0167318557149066e-05, | |
| "loss": 0.4962, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.0140156453715778e-05, | |
| "loss": 0.504, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.0112994350282486e-05, | |
| "loss": 0.4818, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.0085832246849196e-05, | |
| "loss": 0.5191, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.0058670143415907e-05, | |
| "loss": 0.482, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.0031508039982619e-05, | |
| "loss": 0.4874, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.0004345936549327e-05, | |
| "loss": 0.4775, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.977183833116037e-06, | |
| "loss": 0.5012, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.950021729682747e-06, | |
| "loss": 0.543, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_accuracy": 0.7785022924095771, | |
| "eval_loss": 0.5540511012077332, | |
| "eval_runtime": 16.6332, | |
| "eval_samples_per_second": 590.083, | |
| "eval_steps_per_second": 36.914, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.922859626249458e-06, | |
| "loss": 0.4905, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.895697522816168e-06, | |
| "loss": 0.4881, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.868535419382878e-06, | |
| "loss": 0.4946, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.841373315949588e-06, | |
| "loss": 0.4785, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.814211212516298e-06, | |
| "loss": 0.4997, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.787049109083007e-06, | |
| "loss": 0.5178, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 9.759887005649719e-06, | |
| "loss": 0.4784, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 9.732724902216429e-06, | |
| "loss": 0.5092, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 9.705562798783139e-06, | |
| "loss": 0.4848, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.678400695349848e-06, | |
| "loss": 0.5138, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_accuracy": 0.7842078451349974, | |
| "eval_loss": 0.5569394826889038, | |
| "eval_runtime": 16.683, | |
| "eval_samples_per_second": 588.323, | |
| "eval_steps_per_second": 36.804, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.651238591916558e-06, | |
| "loss": 0.4596, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.62407648848327e-06, | |
| "loss": 0.4902, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.59691438504998e-06, | |
| "loss": 0.4894, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.56975228161669e-06, | |
| "loss": 0.4977, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.5425901781834e-06, | |
| "loss": 0.5189, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.515428074750109e-06, | |
| "loss": 0.5295, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.488265971316819e-06, | |
| "loss": 0.4909, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.46110386788353e-06, | |
| "loss": 0.5086, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.43394176445024e-06, | |
| "loss": 0.5054, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 9.40677966101695e-06, | |
| "loss": 0.4626, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_accuracy": 0.7860417727967397, | |
| "eval_loss": 0.5625388026237488, | |
| "eval_runtime": 16.6528, | |
| "eval_samples_per_second": 589.391, | |
| "eval_steps_per_second": 36.871, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 9.37961755758366e-06, | |
| "loss": 0.5023, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.35245545415037e-06, | |
| "loss": 0.504, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.325293350717081e-06, | |
| "loss": 0.5151, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.298131247283791e-06, | |
| "loss": 0.4941, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.2709691438505e-06, | |
| "loss": 0.5535, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.24380704041721e-06, | |
| "loss": 0.5053, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.21664493698392e-06, | |
| "loss": 0.4901, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.189482833550632e-06, | |
| "loss": 0.4864, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.162320730117342e-06, | |
| "loss": 0.4923, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.13515862668405e-06, | |
| "loss": 0.4828, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_accuracy": 0.785838003056546, | |
| "eval_loss": 0.543383777141571, | |
| "eval_runtime": 16.5892, | |
| "eval_samples_per_second": 591.65, | |
| "eval_steps_per_second": 37.012, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.107996523250762e-06, | |
| "loss": 0.4845, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.080834419817471e-06, | |
| "loss": 0.4763, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.053672316384181e-06, | |
| "loss": 0.51, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.026510212950891e-06, | |
| "loss": 0.5058, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.999348109517601e-06, | |
| "loss": 0.52, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.972186006084312e-06, | |
| "loss": 0.5008, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.945023902651022e-06, | |
| "loss": 0.4846, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.917861799217732e-06, | |
| "loss": 0.5186, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.890699695784442e-06, | |
| "loss": 0.4641, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.863537592351152e-06, | |
| "loss": 0.5121, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_accuracy": 0.7806418746816097, | |
| "eval_loss": 0.5494823455810547, | |
| "eval_runtime": 17.115, | |
| "eval_samples_per_second": 573.473, | |
| "eval_steps_per_second": 35.875, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.836375488917862e-06, | |
| "loss": 0.4905, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.809213385484573e-06, | |
| "loss": 0.5238, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.782051282051283e-06, | |
| "loss": 0.505, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.754889178617993e-06, | |
| "loss": 0.5239, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.727727075184703e-06, | |
| "loss": 0.4842, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.700564971751413e-06, | |
| "loss": 0.5169, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.673402868318124e-06, | |
| "loss": 0.5016, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.646240764884834e-06, | |
| "loss": 0.4756, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.619078661451544e-06, | |
| "loss": 0.518, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.591916558018254e-06, | |
| "loss": 0.5012, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_accuracy": 0.7900152827305145, | |
| "eval_loss": 0.5318433046340942, | |
| "eval_runtime": 17.1293, | |
| "eval_samples_per_second": 572.995, | |
| "eval_steps_per_second": 35.845, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.564754454584963e-06, | |
| "loss": 0.5283, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.537592351151673e-06, | |
| "loss": 0.4753, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.510430247718385e-06, | |
| "loss": 0.5125, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.483268144285095e-06, | |
| "loss": 0.5096, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.456106040851804e-06, | |
| "loss": 0.4746, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.428943937418514e-06, | |
| "loss": 0.4918, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.401781833985224e-06, | |
| "loss": 0.4991, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.374619730551936e-06, | |
| "loss": 0.5014, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.347457627118645e-06, | |
| "loss": 0.4807, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.320295523685355e-06, | |
| "loss": 0.4609, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.7877738155883851, | |
| "eval_loss": 0.5485233664512634, | |
| "eval_runtime": 16.5584, | |
| "eval_samples_per_second": 592.752, | |
| "eval_steps_per_second": 37.081, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.293133420252065e-06, | |
| "loss": 0.4985, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.265971316818775e-06, | |
| "loss": 0.4839, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.238809213385486e-06, | |
| "loss": 0.5051, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.211647109952196e-06, | |
| "loss": 0.4515, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.184485006518904e-06, | |
| "loss": 0.5255, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.157322903085616e-06, | |
| "loss": 0.5224, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.130160799652326e-06, | |
| "loss": 0.5068, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.102998696219036e-06, | |
| "loss": 0.4611, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 8.075836592785745e-06, | |
| "loss": 0.4998, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 8.048674489352455e-06, | |
| "loss": 0.4928, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_accuracy": 0.7867549668874172, | |
| "eval_loss": 0.546183705329895, | |
| "eval_runtime": 16.5167, | |
| "eval_samples_per_second": 594.247, | |
| "eval_steps_per_second": 37.175, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.021512385919165e-06, | |
| "loss": 0.5209, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.994350282485877e-06, | |
| "loss": 0.5098, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.967188179052586e-06, | |
| "loss": 0.4786, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.940026075619296e-06, | |
| "loss": 0.479, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.912863972186006e-06, | |
| "loss": 0.4733, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7.885701868752716e-06, | |
| "loss": 0.5133, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7.858539765319428e-06, | |
| "loss": 0.4548, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.831377661886137e-06, | |
| "loss": 0.4981, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.804215558452847e-06, | |
| "loss": 0.4931, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.777053455019557e-06, | |
| "loss": 0.4922, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.7919510952623535, | |
| "eval_loss": 0.5305083394050598, | |
| "eval_runtime": 16.5399, | |
| "eval_samples_per_second": 593.415, | |
| "eval_steps_per_second": 37.122, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.749891351586267e-06, | |
| "loss": 0.4534, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.722729248152978e-06, | |
| "loss": 0.4616, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.695567144719688e-06, | |
| "loss": 0.4823, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.668405041286398e-06, | |
| "loss": 0.505, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.641242937853108e-06, | |
| "loss": 0.4982, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.614080834419818e-06, | |
| "loss": 0.5249, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.5869187309865275e-06, | |
| "loss": 0.4711, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.559756627553238e-06, | |
| "loss": 0.4984, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.532594524119948e-06, | |
| "loss": 0.4881, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.505432420686659e-06, | |
| "loss": 0.4913, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.7890983188996434, | |
| "eval_loss": 0.539624035358429, | |
| "eval_runtime": 16.6144, | |
| "eval_samples_per_second": 590.753, | |
| "eval_steps_per_second": 36.956, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.4782703172533686e-06, | |
| "loss": 0.4851, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.451108213820078e-06, | |
| "loss": 0.5046, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 7.423946110386789e-06, | |
| "loss": 0.502, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 7.396784006953499e-06, | |
| "loss": 0.5172, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 7.369621903520209e-06, | |
| "loss": 0.5159, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.3424598000869194e-06, | |
| "loss": 0.5225, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.315297696653629e-06, | |
| "loss": 0.5184, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.288135593220339e-06, | |
| "loss": 0.5117, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.26097348978705e-06, | |
| "loss": 0.4801, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.23381138635376e-06, | |
| "loss": 0.4992, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_accuracy": 0.7952114111054508, | |
| "eval_loss": 0.5340686440467834, | |
| "eval_runtime": 17.0377, | |
| "eval_samples_per_second": 576.074, | |
| "eval_steps_per_second": 36.038, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 7.20664928292047e-06, | |
| "loss": 0.4961, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 7.17948717948718e-06, | |
| "loss": 0.4991, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 7.15232507605389e-06, | |
| "loss": 0.4806, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 7.125162972620601e-06, | |
| "loss": 0.5114, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.0980008691873105e-06, | |
| "loss": 0.5022, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.07083876575402e-06, | |
| "loss": 0.5116, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.043676662320731e-06, | |
| "loss": 0.4567, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.016514558887441e-06, | |
| "loss": 0.4891, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.9893524554541515e-06, | |
| "loss": 0.4748, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.962190352020861e-06, | |
| "loss": 0.4732, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_accuracy": 0.7952114111054508, | |
| "eval_loss": 0.5277342200279236, | |
| "eval_runtime": 16.5542, | |
| "eval_samples_per_second": 592.901, | |
| "eval_steps_per_second": 37.09, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.935028248587571e-06, | |
| "loss": 0.4943, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.907866145154282e-06, | |
| "loss": 0.4748, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.880704041720992e-06, | |
| "loss": 0.5075, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.8535419382877015e-06, | |
| "loss": 0.4767, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.826379834854412e-06, | |
| "loss": 0.515, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.799217731421122e-06, | |
| "loss": 0.5094, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.772055627987833e-06, | |
| "loss": 0.5114, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.7448935245545425e-06, | |
| "loss": 0.4693, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.7177314211212515e-06, | |
| "loss": 0.5004, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.690569317687963e-06, | |
| "loss": 0.4925, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7942944472745798, | |
| "eval_loss": 0.5339340567588806, | |
| "eval_runtime": 16.6058, | |
| "eval_samples_per_second": 591.059, | |
| "eval_steps_per_second": 36.975, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.663407214254672e-06, | |
| "loss": 0.4911, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.636245110821382e-06, | |
| "loss": 0.389, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 6.6090830073880925e-06, | |
| "loss": 0.3998, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 6.581920903954802e-06, | |
| "loss": 0.4128, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.554758800521513e-06, | |
| "loss": 0.413, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.527596697088223e-06, | |
| "loss": 0.4175, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.500434593654933e-06, | |
| "loss": 0.4156, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 6.473272490221643e-06, | |
| "loss": 0.4339, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 6.446110386788353e-06, | |
| "loss": 0.3902, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.418948283355063e-06, | |
| "loss": 0.4098, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_accuracy": 0.7911360163015793, | |
| "eval_loss": 0.5642890334129333, | |
| "eval_runtime": 16.6408, | |
| "eval_samples_per_second": 589.817, | |
| "eval_steps_per_second": 36.897, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.391786179921774e-06, | |
| "loss": 0.4147, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 6.364624076488484e-06, | |
| "loss": 0.4213, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 6.337461973055193e-06, | |
| "loss": 0.4161, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 6.310299869621904e-06, | |
| "loss": 0.4034, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 6.283137766188614e-06, | |
| "loss": 0.4032, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 6.255975662755325e-06, | |
| "loss": 0.3937, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.2288135593220344e-06, | |
| "loss": 0.4497, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.201651455888744e-06, | |
| "loss": 0.4043, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.174489352455455e-06, | |
| "loss": 0.3817, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.147327249022165e-06, | |
| "loss": 0.4168, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_accuracy": 0.7928680590932247, | |
| "eval_loss": 0.5534476637840271, | |
| "eval_runtime": 16.6553, | |
| "eval_samples_per_second": 589.303, | |
| "eval_steps_per_second": 36.865, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.120165145588875e-06, | |
| "loss": 0.4003, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.093003042155585e-06, | |
| "loss": 0.4051, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.065840938722295e-06, | |
| "loss": 0.3662, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.038678835289006e-06, | |
| "loss": 0.39, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.011516731855716e-06, | |
| "loss": 0.4026, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 5.9843546284224255e-06, | |
| "loss": 0.4228, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.957192524989136e-06, | |
| "loss": 0.3851, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.930030421555846e-06, | |
| "loss": 0.4015, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.902868318122556e-06, | |
| "loss": 0.3829, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 5.8757062146892665e-06, | |
| "loss": 0.4099, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.7924605196128375, | |
| "eval_loss": 0.5673933625221252, | |
| "eval_runtime": 17.0951, | |
| "eval_samples_per_second": 574.142, | |
| "eval_steps_per_second": 35.917, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 5.848544111255976e-06, | |
| "loss": 0.4165, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.821382007822687e-06, | |
| "loss": 0.4322, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.794219904389397e-06, | |
| "loss": 0.4324, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.767057800956106e-06, | |
| "loss": 0.4032, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 5.739895697522817e-06, | |
| "loss": 0.4215, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 5.712733594089526e-06, | |
| "loss": 0.3912, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 5.685571490656236e-06, | |
| "loss": 0.3968, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 5.658409387222948e-06, | |
| "loss": 0.3872, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.631247283789657e-06, | |
| "loss": 0.398, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.6040851803563665e-06, | |
| "loss": 0.4142, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_accuracy": 0.7918492103922568, | |
| "eval_loss": 0.5651636123657227, | |
| "eval_runtime": 16.5676, | |
| "eval_samples_per_second": 592.42, | |
| "eval_steps_per_second": 37.06, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.576923076923077e-06, | |
| "loss": 0.3709, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.549760973489787e-06, | |
| "loss": 0.398, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.522598870056498e-06, | |
| "loss": 0.3952, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.4954367666232076e-06, | |
| "loss": 0.4128, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.468274663189917e-06, | |
| "loss": 0.4361, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.441112559756628e-06, | |
| "loss": 0.4198, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.413950456323338e-06, | |
| "loss": 0.416, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.386788352890048e-06, | |
| "loss": 0.4384, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.359626249456758e-06, | |
| "loss": 0.3943, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.332464146023468e-06, | |
| "loss": 0.398, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.7899133978604177, | |
| "eval_loss": 0.5875393152236938, | |
| "eval_runtime": 16.5581, | |
| "eval_samples_per_second": 592.763, | |
| "eval_steps_per_second": 37.082, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.305302042590179e-06, | |
| "loss": 0.3961, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.278139939156889e-06, | |
| "loss": 0.4073, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.250977835723599e-06, | |
| "loss": 0.4225, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.223815732290309e-06, | |
| "loss": 0.3797, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.196653628857019e-06, | |
| "loss": 0.3943, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.169491525423729e-06, | |
| "loss": 0.4126, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.14232942199044e-06, | |
| "loss": 0.4163, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.1151673185571495e-06, | |
| "loss": 0.4084, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.08800521512386e-06, | |
| "loss": 0.389, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.06084311169057e-06, | |
| "loss": 0.3899, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.7974528782475803, | |
| "eval_loss": 0.5725763440132141, | |
| "eval_runtime": 16.5558, | |
| "eval_samples_per_second": 592.842, | |
| "eval_steps_per_second": 37.087, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.03368100825728e-06, | |
| "loss": 0.4425, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5.0065189048239905e-06, | |
| "loss": 0.4207, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 4.9793568013907e-06, | |
| "loss": 0.437, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.95219469795741e-06, | |
| "loss": 0.3897, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.92503259452412e-06, | |
| "loss": 0.4123, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.897870491090831e-06, | |
| "loss": 0.362, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.8707083876575405e-06, | |
| "loss": 0.4145, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.843546284224251e-06, | |
| "loss": 0.3992, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.816384180790961e-06, | |
| "loss": 0.4103, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.789222077357671e-06, | |
| "loss": 0.403, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.7968415690269995, | |
| "eval_loss": 0.5595614314079285, | |
| "eval_runtime": 16.6606, | |
| "eval_samples_per_second": 589.113, | |
| "eval_steps_per_second": 36.853, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.7620599739243815e-06, | |
| "loss": 0.3999, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.734897870491091e-06, | |
| "loss": 0.3976, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.707735767057801e-06, | |
| "loss": 0.4199, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.680573663624511e-06, | |
| "loss": 0.4393, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.653411560191222e-06, | |
| "loss": 0.3932, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.6262494567579315e-06, | |
| "loss": 0.4086, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.599087353324641e-06, | |
| "loss": 0.4247, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.571925249891352e-06, | |
| "loss": 0.4017, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.544763146458062e-06, | |
| "loss": 0.3994, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.5176010430247726e-06, | |
| "loss": 0.399, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_accuracy": 0.7884870096790627, | |
| "eval_loss": 0.5715699195861816, | |
| "eval_runtime": 17.2274, | |
| "eval_samples_per_second": 569.731, | |
| "eval_steps_per_second": 35.641, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 4.490438939591482e-06, | |
| "loss": 0.4276, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 4.463276836158192e-06, | |
| "loss": 0.4408, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 4.436114732724903e-06, | |
| "loss": 0.3554, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.408952629291613e-06, | |
| "loss": 0.4155, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.381790525858323e-06, | |
| "loss": 0.4254, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.354628422425033e-06, | |
| "loss": 0.4021, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.327466318991743e-06, | |
| "loss": 0.3796, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.300304215558454e-06, | |
| "loss": 0.4208, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.273142112125163e-06, | |
| "loss": 0.4203, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.2459800086918734e-06, | |
| "loss": 0.4176, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_accuracy": 0.7940906775343861, | |
| "eval_loss": 0.55697101354599, | |
| "eval_runtime": 17.0558, | |
| "eval_samples_per_second": 575.464, | |
| "eval_steps_per_second": 35.999, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 4.218817905258584e-06, | |
| "loss": 0.379, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 4.191655801825294e-06, | |
| "loss": 0.418, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.164493698392004e-06, | |
| "loss": 0.4222, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.137331594958714e-06, | |
| "loss": 0.4144, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.110169491525424e-06, | |
| "loss": 0.4191, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.083007388092134e-06, | |
| "loss": 0.4066, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.055845284658844e-06, | |
| "loss": 0.4006, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.028683181225555e-06, | |
| "loss": 0.4017, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.0015210777922645e-06, | |
| "loss": 0.4167, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 3.974358974358974e-06, | |
| "loss": 0.3871, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.7925624044829342, | |
| "eval_loss": 0.5689213871955872, | |
| "eval_runtime": 16.5185, | |
| "eval_samples_per_second": 594.183, | |
| "eval_steps_per_second": 37.17, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.947196870925685e-06, | |
| "loss": 0.3923, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.920034767492395e-06, | |
| "loss": 0.3924, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 3.8928726640591055e-06, | |
| "loss": 0.4157, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 3.865710560625815e-06, | |
| "loss": 0.4303, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 3.838548457192525e-06, | |
| "loss": 0.4128, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.8113863537592354e-06, | |
| "loss": 0.3768, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.7842242503259457e-06, | |
| "loss": 0.4072, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.7570621468926555e-06, | |
| "loss": 0.4336, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.7299000434593658e-06, | |
| "loss": 0.4139, | |
| "step": 29950 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.702737940026076e-06, | |
| "loss": 0.4156, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_accuracy": 0.7918492103922568, | |
| "eval_loss": 0.564761221408844, | |
| "eval_runtime": 16.5683, | |
| "eval_samples_per_second": 592.397, | |
| "eval_steps_per_second": 37.059, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.6755758365927863e-06, | |
| "loss": 0.414, | |
| "step": 30050 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.648413733159496e-06, | |
| "loss": 0.3981, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.6212516297262064e-06, | |
| "loss": 0.4313, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.5940895262929166e-06, | |
| "loss": 0.3945, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.566927422859627e-06, | |
| "loss": 0.4318, | |
| "step": 30250 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.5397653194263363e-06, | |
| "loss": 0.39, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.5126032159930466e-06, | |
| "loss": 0.4521, | |
| "step": 30350 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.4854411125597572e-06, | |
| "loss": 0.4081, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.4582790091264675e-06, | |
| "loss": 0.426, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.431116905693177e-06, | |
| "loss": 0.386, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_accuracy": 0.7930718288334182, | |
| "eval_loss": 0.5649917125701904, | |
| "eval_runtime": 16.6385, | |
| "eval_samples_per_second": 589.898, | |
| "eval_steps_per_second": 36.902, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.403954802259887e-06, | |
| "loss": 0.386, | |
| "step": 30550 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.3767926988265974e-06, | |
| "loss": 0.4156, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.3496305953933073e-06, | |
| "loss": 0.3839, | |
| "step": 30650 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.3224684919600175e-06, | |
| "loss": 0.3734, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.2953063885267278e-06, | |
| "loss": 0.3832, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.268144285093438e-06, | |
| "loss": 0.3926, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.240982181660148e-06, | |
| "loss": 0.4003, | |
| "step": 30850 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 3.213820078226858e-06, | |
| "loss": 0.411, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 3.1866579747935684e-06, | |
| "loss": 0.4139, | |
| "step": 30950 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.1594958713602786e-06, | |
| "loss": 0.4131, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_accuracy": 0.7948038716250637, | |
| "eval_loss": 0.5524526238441467, | |
| "eval_runtime": 16.7639, | |
| "eval_samples_per_second": 585.485, | |
| "eval_steps_per_second": 36.626, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.1323337679269885e-06, | |
| "loss": 0.4098, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.1051716644936987e-06, | |
| "loss": 0.4044, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.078009561060409e-06, | |
| "loss": 0.4334, | |
| "step": 31150 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.0508474576271192e-06, | |
| "loss": 0.4197, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.0236853541938286e-06, | |
| "loss": 0.4082, | |
| "step": 31250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.996523250760539e-06, | |
| "loss": 0.3904, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.969361147327249e-06, | |
| "loss": 0.4299, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.9421990438939594e-06, | |
| "loss": 0.4312, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.9150369404606692e-06, | |
| "loss": 0.3906, | |
| "step": 31450 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.8878748370273795e-06, | |
| "loss": 0.4202, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_accuracy": 0.7914416709118696, | |
| "eval_loss": 0.5584515929222107, | |
| "eval_runtime": 16.646, | |
| "eval_samples_per_second": 589.63, | |
| "eval_steps_per_second": 36.886, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.8607127335940898e-06, | |
| "loss": 0.4298, | |
| "step": 31550 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.8335506301608e-06, | |
| "loss": 0.4158, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.80638852672751e-06, | |
| "loss": 0.3487, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.77922642329422e-06, | |
| "loss": 0.402, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.7520643198609304e-06, | |
| "loss": 0.3861, | |
| "step": 31750 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.7249022164276406e-06, | |
| "loss": 0.4026, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.6977401129943505e-06, | |
| "loss": 0.406, | |
| "step": 31850 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.6705780095610607e-06, | |
| "loss": 0.4227, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.643415906127771e-06, | |
| "loss": 0.4084, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.6162538026944812e-06, | |
| "loss": 0.4129, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_accuracy": 0.7963321446765156, | |
| "eval_loss": 0.5494925379753113, | |
| "eval_runtime": 16.5344, | |
| "eval_samples_per_second": 593.61, | |
| "eval_steps_per_second": 37.135, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.589091699261191e-06, | |
| "loss": 0.377, | |
| "step": 32050 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.5619295958279013e-06, | |
| "loss": 0.3959, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.5347674923946116e-06, | |
| "loss": 0.4281, | |
| "step": 32150 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.507605388961321e-06, | |
| "loss": 0.3811, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.4804432855280312e-06, | |
| "loss": 0.4, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.4532811820947415e-06, | |
| "loss": 0.3864, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.4261190786614517e-06, | |
| "loss": 0.419, | |
| "step": 32350 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.398956975228162e-06, | |
| "loss": 0.4112, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.371794871794872e-06, | |
| "loss": 0.4252, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.344632768361582e-06, | |
| "loss": 0.4215, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_accuracy": 0.7977585328578706, | |
| "eval_loss": 0.5523735880851746, | |
| "eval_runtime": 16.641, | |
| "eval_samples_per_second": 589.807, | |
| "eval_steps_per_second": 36.897, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.3174706649282924e-06, | |
| "loss": 0.4246, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.2903085614950026e-06, | |
| "loss": 0.4073, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.2631464580617124e-06, | |
| "loss": 0.3856, | |
| "step": 32650 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.2359843546284227e-06, | |
| "loss": 0.4138, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.2088222511951325e-06, | |
| "loss": 0.4118, | |
| "step": 32750 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.1816601477618428e-06, | |
| "loss": 0.3948, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.154498044328553e-06, | |
| "loss": 0.3928, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.1273359408952633e-06, | |
| "loss": 0.4013, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.100173837461973e-06, | |
| "loss": 0.4276, | |
| "step": 32950 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.0730117340286834e-06, | |
| "loss": 0.413, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_accuracy": 0.7954151808456444, | |
| "eval_loss": 0.5578052997589111, | |
| "eval_runtime": 16.6318, | |
| "eval_samples_per_second": 590.136, | |
| "eval_steps_per_second": 36.917, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.0458496305953932e-06, | |
| "loss": 0.3866, | |
| "step": 33050 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.018687527162104e-06, | |
| "loss": 0.41, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.9915254237288137e-06, | |
| "loss": 0.4153, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.964363320295524e-06, | |
| "loss": 0.4118, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.937201216862234e-06, | |
| "loss": 0.4025, | |
| "step": 33250 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.910039113428944e-06, | |
| "loss": 0.4017, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.8828770099956541e-06, | |
| "loss": 0.3703, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.8557149065623644e-06, | |
| "loss": 0.3994, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.8285528031290744e-06, | |
| "loss": 0.4111, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.8013906996957845e-06, | |
| "loss": 0.4296, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_accuracy": 0.7966377992868059, | |
| "eval_loss": 0.5509371757507324, | |
| "eval_runtime": 16.7118, | |
| "eval_samples_per_second": 587.31, | |
| "eval_steps_per_second": 36.741, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.7742285962624947e-06, | |
| "loss": 0.3955, | |
| "step": 33550 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.7470664928292048e-06, | |
| "loss": 0.3788, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.719904389395915e-06, | |
| "loss": 0.3697, | |
| "step": 33650 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.6927422859626249e-06, | |
| "loss": 0.4051, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.6655801825293353e-06, | |
| "loss": 0.4483, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.6384180790960452e-06, | |
| "loss": 0.4394, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.6112559756627554e-06, | |
| "loss": 0.4124, | |
| "step": 33850 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.5840938722294655e-06, | |
| "loss": 0.3743, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.5569317687961757e-06, | |
| "loss": 0.3836, | |
| "step": 33950 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.5297696653628858e-06, | |
| "loss": 0.3602, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_accuracy": 0.7973509933774835, | |
| "eval_loss": 0.558102011680603, | |
| "eval_runtime": 17.0179, | |
| "eval_samples_per_second": 576.745, | |
| "eval_steps_per_second": 36.08, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.502607561929596e-06, | |
| "loss": 0.4199, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.475445458496306e-06, | |
| "loss": 0.4177, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.4482833550630163e-06, | |
| "loss": 0.4012, | |
| "step": 34150 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.4211212516297262e-06, | |
| "loss": 0.4107, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.3939591481964364e-06, | |
| "loss": 0.4082, | |
| "step": 34250 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.3667970447631465e-06, | |
| "loss": 0.3693, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.3396349413298567e-06, | |
| "loss": 0.4395, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.3124728378965668e-06, | |
| "loss": 0.3692, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.285310734463277e-06, | |
| "loss": 0.383, | |
| "step": 34450 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.258148631029987e-06, | |
| "loss": 0.3901, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_accuracy": 0.7984717269485482, | |
| "eval_loss": 0.5561137795448303, | |
| "eval_runtime": 16.5112, | |
| "eval_samples_per_second": 594.446, | |
| "eval_steps_per_second": 37.187, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.2309865275966971e-06, | |
| "loss": 0.411, | |
| "step": 34550 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.2038244241634074e-06, | |
| "loss": 0.398, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.1766623207301174e-06, | |
| "loss": 0.4058, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.1495002172968275e-06, | |
| "loss": 0.3626, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.1223381138635377e-06, | |
| "loss": 0.4277, | |
| "step": 34750 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.0951760104302478e-06, | |
| "loss": 0.3908, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.068013906996958e-06, | |
| "loss": 0.4084, | |
| "step": 34850 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.040851803563668e-06, | |
| "loss": 0.399, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.0136897001303781e-06, | |
| "loss": 0.4072, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 9.865275966970884e-07, | |
| "loss": 0.4163, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_accuracy": 0.7955170657157412, | |
| "eval_loss": 0.550171971321106, | |
| "eval_runtime": 16.6089, | |
| "eval_samples_per_second": 590.95, | |
| "eval_steps_per_second": 36.968, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 9.593654932637984e-07, | |
| "loss": 0.4183, | |
| "step": 35050 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 9.322033898305086e-07, | |
| "loss": 0.3863, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 9.050412863972187e-07, | |
| "loss": 0.4011, | |
| "step": 35150 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 8.778791829639289e-07, | |
| "loss": 0.3905, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 8.507170795306389e-07, | |
| "loss": 0.4197, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.235549760973491e-07, | |
| "loss": 0.424, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.963928726640592e-07, | |
| "loss": 0.3966, | |
| "step": 35350 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 0.3678, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.420686657974795e-07, | |
| "loss": 0.3938, | |
| "step": 35450 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.149065623641896e-07, | |
| "loss": 0.3787, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_accuracy": 0.795109526235354, | |
| "eval_loss": 0.557253360748291, | |
| "eval_runtime": 16.6651, | |
| "eval_samples_per_second": 588.954, | |
| "eval_steps_per_second": 36.843, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 6.877444589308997e-07, | |
| "loss": 0.3999, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 6.605823554976099e-07, | |
| "loss": 0.4299, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 6.3342025206432e-07, | |
| "loss": 0.446, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 6.0625814863103e-07, | |
| "loss": 0.4139, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.790960451977402e-07, | |
| "loss": 0.4093, | |
| "step": 35750 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.519339417644502e-07, | |
| "loss": 0.3684, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.247718383311604e-07, | |
| "loss": 0.4099, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.976097348978705e-07, | |
| "loss": 0.4303, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.704476314645807e-07, | |
| "loss": 0.3705, | |
| "step": 35950 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.432855280312908e-07, | |
| "loss": 0.4285, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_accuracy": 0.7958227203260316, | |
| "eval_loss": 0.5535317659378052, | |
| "eval_runtime": 16.7135, | |
| "eval_samples_per_second": 587.25, | |
| "eval_steps_per_second": 36.737, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 4.1612342459800084e-07, | |
| "loss": 0.4131, | |
| "step": 36050 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.88961321164711e-07, | |
| "loss": 0.4079, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.6179921773142114e-07, | |
| "loss": 0.3935, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.3463711429813124e-07, | |
| "loss": 0.3815, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.074750108648414e-07, | |
| "loss": 0.3795, | |
| "step": 36250 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.803129074315515e-07, | |
| "loss": 0.3865, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.5315080399826164e-07, | |
| "loss": 0.4245, | |
| "step": 36350 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.2598870056497177e-07, | |
| "loss": 0.3966, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.988265971316819e-07, | |
| "loss": 0.3952, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.7166449369839202e-07, | |
| "loss": 0.3578, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.7964340295466124, | |
| "eval_loss": 0.5563226938247681, | |
| "eval_runtime": 17.1718, | |
| "eval_samples_per_second": 571.576, | |
| "eval_steps_per_second": 35.756, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.4450239026510214e-07, | |
| "loss": 0.4001, | |
| "step": 36550 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.1734028683181226e-07, | |
| "loss": 0.4037, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.017818339852239e-08, | |
| "loss": 0.3991, | |
| "step": 36650 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 6.301607996523251e-08, | |
| "loss": 0.4447, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 3.585397653194264e-08, | |
| "loss": 0.3859, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.691873098652761e-09, | |
| "loss": 0.404, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 36816, | |
| "total_flos": 7.237394283638914e+16, | |
| "train_loss": 0.5151884243805375, | |
| "train_runtime": 9291.93, | |
| "train_samples_per_second": 126.788, | |
| "train_steps_per_second": 3.962 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 36816, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 7.237394283638914e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |