| { | |
| "best_metric": 0.7334500551223755, | |
| "best_model_checkpoint": "../../checkpoints/baseline/default-baseline-uncleaned/lm_model/finetune/mnli-mm/checkpoint-28000", | |
| "epoch": 7.389162561576355, | |
| "global_step": 30000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.3381603956222534, | |
| "eval_loss": 1.0937632322311401, | |
| "eval_runtime": 7.1539, | |
| "eval_samples_per_second": 878.405, | |
| "eval_steps_per_second": 109.87, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0056557655334473, | |
| "eval_runtime": 7.136, | |
| "eval_samples_per_second": 880.608, | |
| "eval_steps_per_second": 110.146, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.938423645320197e-05, | |
| "loss": 1.065, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.5747931003570557, | |
| "eval_loss": 0.9154016971588135, | |
| "eval_runtime": 7.1437, | |
| "eval_samples_per_second": 879.654, | |
| "eval_steps_per_second": 110.027, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.5988224148750305, | |
| "eval_loss": 0.8770188689231873, | |
| "eval_runtime": 7.1559, | |
| "eval_samples_per_second": 878.161, | |
| "eval_steps_per_second": 109.84, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.876847290640394e-05, | |
| "loss": 0.9452, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.6098026633262634, | |
| "eval_loss": 0.863080620765686, | |
| "eval_runtime": 7.1512, | |
| "eval_samples_per_second": 878.732, | |
| "eval_steps_per_second": 109.911, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.619191586971283, | |
| "eval_loss": 0.8449499011039734, | |
| "eval_runtime": 7.1301, | |
| "eval_samples_per_second": 881.33, | |
| "eval_steps_per_second": 110.236, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.630808413028717, | |
| "eval_loss": 0.8298859596252441, | |
| "eval_runtime": 7.1347, | |
| "eval_samples_per_second": 880.768, | |
| "eval_steps_per_second": 110.166, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.8152709359605915e-05, | |
| "loss": 0.9048, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.6325588822364807, | |
| "eval_loss": 0.8225136995315552, | |
| "eval_runtime": 7.1209, | |
| "eval_samples_per_second": 882.468, | |
| "eval_steps_per_second": 110.379, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.6378102898597717, | |
| "eval_loss": 0.8134775161743164, | |
| "eval_runtime": 7.1392, | |
| "eval_samples_per_second": 880.211, | |
| "eval_steps_per_second": 110.096, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.753694581280788e-05, | |
| "loss": 0.8715, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.6421069502830505, | |
| "eval_loss": 0.8081309795379639, | |
| "eval_runtime": 7.115, | |
| "eval_samples_per_second": 883.199, | |
| "eval_steps_per_second": 110.47, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.6468809843063354, | |
| "eval_loss": 0.7986512184143066, | |
| "eval_runtime": 7.1565, | |
| "eval_samples_per_second": 878.086, | |
| "eval_steps_per_second": 109.831, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.6494271159172058, | |
| "eval_loss": 0.7892561554908752, | |
| "eval_runtime": 7.1252, | |
| "eval_samples_per_second": 881.942, | |
| "eval_steps_per_second": 110.313, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.6921182266009855e-05, | |
| "loss": 0.8542, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.6537237167358398, | |
| "eval_loss": 0.7885516881942749, | |
| "eval_runtime": 7.1352, | |
| "eval_samples_per_second": 880.701, | |
| "eval_steps_per_second": 110.158, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.6580203771591187, | |
| "eval_loss": 0.7793189287185669, | |
| "eval_runtime": 7.1229, | |
| "eval_samples_per_second": 882.221, | |
| "eval_steps_per_second": 110.348, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.630541871921182e-05, | |
| "loss": 0.8344, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.660566508769989, | |
| "eval_loss": 0.7755009531974792, | |
| "eval_runtime": 7.1376, | |
| "eval_samples_per_second": 880.411, | |
| "eval_steps_per_second": 110.121, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.6670910120010376, | |
| "eval_loss": 0.769910454750061, | |
| "eval_runtime": 7.1523, | |
| "eval_samples_per_second": 878.594, | |
| "eval_steps_per_second": 109.894, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.6683641076087952, | |
| "eval_loss": 0.7647598385810852, | |
| "eval_runtime": 7.1504, | |
| "eval_samples_per_second": 878.833, | |
| "eval_steps_per_second": 109.924, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.5689655172413794e-05, | |
| "loss": 0.8204, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.6705919504165649, | |
| "eval_loss": 0.7597415447235107, | |
| "eval_runtime": 7.1426, | |
| "eval_samples_per_second": 879.79, | |
| "eval_steps_per_second": 110.044, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.6683641076087952, | |
| "eval_loss": 0.7540149688720703, | |
| "eval_runtime": 7.1581, | |
| "eval_samples_per_second": 877.882, | |
| "eval_steps_per_second": 109.805, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.507389162561577e-05, | |
| "loss": 0.8125, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.6728198528289795, | |
| "eval_loss": 0.7508071660995483, | |
| "eval_runtime": 7.1283, | |
| "eval_samples_per_second": 881.556, | |
| "eval_steps_per_second": 110.265, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_accuracy": 0.6731381416320801, | |
| "eval_loss": 0.7491191029548645, | |
| "eval_runtime": 7.1623, | |
| "eval_samples_per_second": 877.371, | |
| "eval_steps_per_second": 109.741, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_accuracy": 0.6718650460243225, | |
| "eval_loss": 0.7508663535118103, | |
| "eval_runtime": 7.1429, | |
| "eval_samples_per_second": 879.752, | |
| "eval_steps_per_second": 110.039, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.4458128078817734e-05, | |
| "loss": 0.786, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 0.6767982244491577, | |
| "eval_loss": 0.7442670464515686, | |
| "eval_runtime": 7.1445, | |
| "eval_samples_per_second": 879.556, | |
| "eval_steps_per_second": 110.015, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.6767982244491577, | |
| "eval_loss": 0.7406799793243408, | |
| "eval_runtime": 7.1302, | |
| "eval_samples_per_second": 881.316, | |
| "eval_steps_per_second": 110.235, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.384236453201971e-05, | |
| "loss": 0.78, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_accuracy": 0.6799809336662292, | |
| "eval_loss": 0.7390637993812561, | |
| "eval_runtime": 7.1525, | |
| "eval_samples_per_second": 878.57, | |
| "eval_steps_per_second": 109.891, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.681253969669342, | |
| "eval_loss": 0.7361044883728027, | |
| "eval_runtime": 7.1388, | |
| "eval_samples_per_second": 880.261, | |
| "eval_steps_per_second": 110.103, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_accuracy": 0.6806174516677856, | |
| "eval_loss": 0.732113242149353, | |
| "eval_runtime": 7.1437, | |
| "eval_samples_per_second": 879.653, | |
| "eval_steps_per_second": 110.027, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.3226600985221674e-05, | |
| "loss": 0.7614, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.6817314028739929, | |
| "eval_loss": 0.7297388315200806, | |
| "eval_runtime": 7.133, | |
| "eval_samples_per_second": 880.97, | |
| "eval_steps_per_second": 110.191, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.6847549080848694, | |
| "eval_loss": 0.730475902557373, | |
| "eval_runtime": 7.1451, | |
| "eval_samples_per_second": 879.487, | |
| "eval_steps_per_second": 110.006, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.261083743842365e-05, | |
| "loss": 0.7592, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.6876193284988403, | |
| "eval_loss": 0.7237519025802612, | |
| "eval_runtime": 7.1475, | |
| "eval_samples_per_second": 879.19, | |
| "eval_steps_per_second": 109.969, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_accuracy": 0.6947804093360901, | |
| "eval_loss": 0.7222017049789429, | |
| "eval_runtime": 7.1471, | |
| "eval_samples_per_second": 879.234, | |
| "eval_steps_per_second": 109.974, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_accuracy": 0.6931890249252319, | |
| "eval_loss": 0.7157117128372192, | |
| "eval_runtime": 7.1272, | |
| "eval_samples_per_second": 881.687, | |
| "eval_steps_per_second": 110.281, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.199507389162562e-05, | |
| "loss": 0.7596, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_accuracy": 0.6908020377159119, | |
| "eval_loss": 0.7141013741493225, | |
| "eval_runtime": 7.1497, | |
| "eval_samples_per_second": 878.921, | |
| "eval_steps_per_second": 109.935, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_accuracy": 0.6901655197143555, | |
| "eval_loss": 0.7196224331855774, | |
| "eval_runtime": 7.1397, | |
| "eval_samples_per_second": 880.145, | |
| "eval_steps_per_second": 110.088, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 0.7502, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_accuracy": 0.6928707957267761, | |
| "eval_loss": 0.7143052816390991, | |
| "eval_runtime": 7.1641, | |
| "eval_samples_per_second": 877.149, | |
| "eval_steps_per_second": 109.713, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.6971673965454102, | |
| "eval_loss": 0.7072923183441162, | |
| "eval_runtime": 7.1434, | |
| "eval_samples_per_second": 879.692, | |
| "eval_steps_per_second": 110.032, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_accuracy": 0.7013049125671387, | |
| "eval_loss": 0.7065105438232422, | |
| "eval_runtime": 7.1601, | |
| "eval_samples_per_second": 877.644, | |
| "eval_steps_per_second": 109.775, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 4.076354679802955e-05, | |
| "loss": 0.7496, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.6970082521438599, | |
| "eval_loss": 0.7033880949020386, | |
| "eval_runtime": 7.1435, | |
| "eval_samples_per_second": 879.677, | |
| "eval_steps_per_second": 110.03, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.7046467065811157, | |
| "eval_loss": 0.7007125020027161, | |
| "eval_runtime": 7.1609, | |
| "eval_samples_per_second": 877.54, | |
| "eval_steps_per_second": 109.762, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.014778325123153e-05, | |
| "loss": 0.746, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.7022597193717957, | |
| "eval_loss": 0.6992939710617065, | |
| "eval_runtime": 7.1492, | |
| "eval_samples_per_second": 878.974, | |
| "eval_steps_per_second": 109.942, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.6990770101547241, | |
| "eval_loss": 0.704833447933197, | |
| "eval_runtime": 7.1594, | |
| "eval_samples_per_second": 877.725, | |
| "eval_steps_per_second": 109.785, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.705760657787323, | |
| "eval_loss": 0.6999921202659607, | |
| "eval_runtime": 7.1391, | |
| "eval_samples_per_second": 880.219, | |
| "eval_steps_per_second": 110.097, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.95320197044335e-05, | |
| "loss": 0.7242, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.7013049125671387, | |
| "eval_loss": 0.700331449508667, | |
| "eval_runtime": 7.1723, | |
| "eval_samples_per_second": 876.149, | |
| "eval_steps_per_second": 109.588, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.7043284773826599, | |
| "eval_loss": 0.7018357515335083, | |
| "eval_runtime": 7.1315, | |
| "eval_samples_per_second": 881.159, | |
| "eval_steps_per_second": 110.215, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.891625615763547e-05, | |
| "loss": 0.7127, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_accuracy": 0.7008274793624878, | |
| "eval_loss": 0.7000855803489685, | |
| "eval_runtime": 7.1461, | |
| "eval_samples_per_second": 879.36, | |
| "eval_steps_per_second": 109.99, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.7009866237640381, | |
| "eval_loss": 0.6994293928146362, | |
| "eval_runtime": 7.1376, | |
| "eval_samples_per_second": 880.41, | |
| "eval_steps_per_second": 110.121, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_accuracy": 0.7036918997764587, | |
| "eval_loss": 0.6989775896072388, | |
| "eval_runtime": 7.1543, | |
| "eval_samples_per_second": 878.359, | |
| "eval_steps_per_second": 109.865, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.830049261083744e-05, | |
| "loss": 0.7142, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_accuracy": 0.7021005749702454, | |
| "eval_loss": 0.6990280151367188, | |
| "eval_runtime": 7.1395, | |
| "eval_samples_per_second": 880.172, | |
| "eval_steps_per_second": 110.092, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.711012065410614, | |
| "eval_loss": 0.6901064515113831, | |
| "eval_runtime": 7.1486, | |
| "eval_samples_per_second": 879.059, | |
| "eval_steps_per_second": 109.952, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.768472906403941e-05, | |
| "loss": 0.711, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_accuracy": 0.7097390294075012, | |
| "eval_loss": 0.6861850619316101, | |
| "eval_runtime": 7.1333, | |
| "eval_samples_per_second": 880.945, | |
| "eval_steps_per_second": 110.188, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_accuracy": 0.7105346918106079, | |
| "eval_loss": 0.6924527287483215, | |
| "eval_runtime": 7.1467, | |
| "eval_samples_per_second": 879.292, | |
| "eval_steps_per_second": 109.981, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.7073519825935364, | |
| "eval_loss": 0.6872392296791077, | |
| "eval_runtime": 7.1334, | |
| "eval_samples_per_second": 880.924, | |
| "eval_steps_per_second": 110.186, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.7068965517241385e-05, | |
| "loss": 0.7083, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_accuracy": 0.7133991122245789, | |
| "eval_loss": 0.6849201321601868, | |
| "eval_runtime": 7.1414, | |
| "eval_samples_per_second": 879.941, | |
| "eval_steps_per_second": 110.063, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_accuracy": 0.711966872215271, | |
| "eval_loss": 0.6847355365753174, | |
| "eval_runtime": 7.1397, | |
| "eval_samples_per_second": 880.145, | |
| "eval_steps_per_second": 110.088, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.645320197044335e-05, | |
| "loss": 0.6995, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_accuracy": 0.7130808234214783, | |
| "eval_loss": 0.6875377893447876, | |
| "eval_runtime": 7.146, | |
| "eval_samples_per_second": 879.379, | |
| "eval_steps_per_second": 109.992, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_accuracy": 0.7157860994338989, | |
| "eval_loss": 0.6812172532081604, | |
| "eval_runtime": 7.1597, | |
| "eval_samples_per_second": 877.692, | |
| "eval_steps_per_second": 109.781, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_accuracy": 0.7127625942230225, | |
| "eval_loss": 0.680852472782135, | |
| "eval_runtime": 7.1585, | |
| "eval_samples_per_second": 877.836, | |
| "eval_steps_per_second": 109.799, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.583743842364532e-05, | |
| "loss": 0.7014, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.7146722078323364, | |
| "eval_loss": 0.6794761419296265, | |
| "eval_runtime": 7.1353, | |
| "eval_samples_per_second": 880.696, | |
| "eval_steps_per_second": 110.157, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_accuracy": 0.7130808234214783, | |
| "eval_loss": 0.6790280938148499, | |
| "eval_runtime": 7.1362, | |
| "eval_samples_per_second": 880.579, | |
| "eval_steps_per_second": 110.142, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.522167487684729e-05, | |
| "loss": 0.6979, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.7159452438354492, | |
| "eval_loss": 0.6799929738044739, | |
| "eval_runtime": 7.1383, | |
| "eval_samples_per_second": 880.323, | |
| "eval_steps_per_second": 110.11, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7122851610183716, | |
| "eval_loss": 0.674569845199585, | |
| "eval_runtime": 7.1445, | |
| "eval_samples_per_second": 879.554, | |
| "eval_steps_per_second": 110.014, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_accuracy": 0.7169000506401062, | |
| "eval_loss": 0.6750736832618713, | |
| "eval_runtime": 7.1334, | |
| "eval_samples_per_second": 880.923, | |
| "eval_steps_per_second": 110.185, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.4605911330049265e-05, | |
| "loss": 0.6886, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_accuracy": 0.7151495814323425, | |
| "eval_loss": 0.675022542476654, | |
| "eval_runtime": 7.1463, | |
| "eval_samples_per_second": 879.333, | |
| "eval_steps_per_second": 109.987, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_accuracy": 0.7137174010276794, | |
| "eval_loss": 0.6786561012268066, | |
| "eval_runtime": 7.1561, | |
| "eval_samples_per_second": 878.138, | |
| "eval_steps_per_second": 109.837, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.399014778325123e-05, | |
| "loss": 0.6733, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_accuracy": 0.7189688086509705, | |
| "eval_loss": 0.6791766881942749, | |
| "eval_runtime": 7.1682, | |
| "eval_samples_per_second": 876.651, | |
| "eval_steps_per_second": 109.651, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.7149904370307922, | |
| "eval_loss": 0.680040717124939, | |
| "eval_runtime": 7.1467, | |
| "eval_samples_per_second": 879.292, | |
| "eval_steps_per_second": 109.981, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.7148312926292419, | |
| "eval_loss": 0.6780914664268494, | |
| "eval_runtime": 7.1572, | |
| "eval_samples_per_second": 878.0, | |
| "eval_steps_per_second": 109.82, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.3374384236453204e-05, | |
| "loss": 0.6685, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_accuracy": 0.7191279530525208, | |
| "eval_loss": 0.6794589161872864, | |
| "eval_runtime": 7.1322, | |
| "eval_samples_per_second": 881.071, | |
| "eval_steps_per_second": 110.204, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_accuracy": 0.7188096642494202, | |
| "eval_loss": 0.6752949953079224, | |
| "eval_runtime": 7.134, | |
| "eval_samples_per_second": 880.857, | |
| "eval_steps_per_second": 110.177, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.275862068965517e-05, | |
| "loss": 0.6682, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_accuracy": 0.7194462418556213, | |
| "eval_loss": 0.6764330863952637, | |
| "eval_runtime": 7.1203, | |
| "eval_samples_per_second": 882.545, | |
| "eval_steps_per_second": 110.388, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_accuracy": 0.7172183394432068, | |
| "eval_loss": 0.6686244010925293, | |
| "eval_runtime": 7.1712, | |
| "eval_samples_per_second": 876.284, | |
| "eval_steps_per_second": 109.605, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_accuracy": 0.7184914350509644, | |
| "eval_loss": 0.6764801144599915, | |
| "eval_runtime": 7.1495, | |
| "eval_samples_per_second": 878.938, | |
| "eval_steps_per_second": 109.937, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.6764, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.7191279530525208, | |
| "eval_loss": 0.6725979447364807, | |
| "eval_runtime": 7.1706, | |
| "eval_samples_per_second": 876.361, | |
| "eval_steps_per_second": 109.615, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_accuracy": 0.7191279530525208, | |
| "eval_loss": 0.6702936291694641, | |
| "eval_runtime": 7.1416, | |
| "eval_samples_per_second": 879.918, | |
| "eval_steps_per_second": 110.06, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 3.152709359605912e-05, | |
| "loss": 0.6693, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_accuracy": 0.7226288914680481, | |
| "eval_loss": 0.6674948930740356, | |
| "eval_runtime": 7.1555, | |
| "eval_samples_per_second": 878.209, | |
| "eval_steps_per_second": 109.846, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_accuracy": 0.7232654094696045, | |
| "eval_loss": 0.6659447550773621, | |
| "eval_runtime": 7.1241, | |
| "eval_samples_per_second": 882.079, | |
| "eval_steps_per_second": 110.33, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_accuracy": 0.7235836982727051, | |
| "eval_loss": 0.6667641997337341, | |
| "eval_runtime": 7.132, | |
| "eval_samples_per_second": 881.1, | |
| "eval_steps_per_second": 110.208, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 3.0911330049261084e-05, | |
| "loss": 0.6736, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_accuracy": 0.7205601334571838, | |
| "eval_loss": 0.6661719679832458, | |
| "eval_runtime": 7.1184, | |
| "eval_samples_per_second": 882.786, | |
| "eval_steps_per_second": 110.419, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_accuracy": 0.7205601334571838, | |
| "eval_loss": 0.6669681668281555, | |
| "eval_runtime": 7.1374, | |
| "eval_samples_per_second": 880.427, | |
| "eval_steps_per_second": 110.123, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3.0295566502463057e-05, | |
| "loss": 0.6718, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.7204009890556335, | |
| "eval_loss": 0.6656709313392639, | |
| "eval_runtime": 7.1161, | |
| "eval_samples_per_second": 883.063, | |
| "eval_steps_per_second": 110.453, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.7242202162742615, | |
| "eval_loss": 0.66374671459198, | |
| "eval_runtime": 7.1264, | |
| "eval_samples_per_second": 881.788, | |
| "eval_steps_per_second": 110.294, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_accuracy": 0.720241904258728, | |
| "eval_loss": 0.6692517995834351, | |
| "eval_runtime": 7.1197, | |
| "eval_samples_per_second": 882.62, | |
| "eval_steps_per_second": 110.398, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.9679802955665027e-05, | |
| "loss": 0.656, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_accuracy": 0.7210375666618347, | |
| "eval_loss": 0.6680518984794617, | |
| "eval_runtime": 7.1182, | |
| "eval_samples_per_second": 882.811, | |
| "eval_steps_per_second": 110.422, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_accuracy": 0.723106324672699, | |
| "eval_loss": 0.6737614274024963, | |
| "eval_runtime": 7.1146, | |
| "eval_samples_per_second": 883.25, | |
| "eval_steps_per_second": 110.477, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 2.9064039408866993e-05, | |
| "loss": 0.6429, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_accuracy": 0.7194462418556213, | |
| "eval_loss": 0.6714398860931396, | |
| "eval_runtime": 7.1257, | |
| "eval_samples_per_second": 881.881, | |
| "eval_steps_per_second": 110.305, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_accuracy": 0.7216740846633911, | |
| "eval_loss": 0.6679774522781372, | |
| "eval_runtime": 7.124, | |
| "eval_samples_per_second": 882.094, | |
| "eval_steps_per_second": 110.332, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_accuracy": 0.7210375666618347, | |
| "eval_loss": 0.6685846447944641, | |
| "eval_runtime": 7.1342, | |
| "eval_samples_per_second": 880.83, | |
| "eval_steps_per_second": 110.174, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 2.844827586206897e-05, | |
| "loss": 0.6464, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_accuracy": 0.7270846366882324, | |
| "eval_loss": 0.670677125453949, | |
| "eval_runtime": 7.1152, | |
| "eval_samples_per_second": 883.18, | |
| "eval_steps_per_second": 110.468, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_accuracy": 0.7251750230789185, | |
| "eval_loss": 0.6647821068763733, | |
| "eval_runtime": 7.1238, | |
| "eval_samples_per_second": 882.114, | |
| "eval_steps_per_second": 110.334, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.7832512315270936e-05, | |
| "loss": 0.6428, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_accuracy": 0.7246976494789124, | |
| "eval_loss": 0.6627594232559204, | |
| "eval_runtime": 7.13, | |
| "eval_samples_per_second": 881.351, | |
| "eval_steps_per_second": 110.239, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_accuracy": 0.7239019870758057, | |
| "eval_loss": 0.664979100227356, | |
| "eval_runtime": 7.1457, | |
| "eval_samples_per_second": 879.411, | |
| "eval_steps_per_second": 109.996, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_accuracy": 0.7256524562835693, | |
| "eval_loss": 0.6631101965904236, | |
| "eval_runtime": 7.128, | |
| "eval_samples_per_second": 881.597, | |
| "eval_steps_per_second": 110.27, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 2.7216748768472906e-05, | |
| "loss": 0.6404, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_accuracy": 0.7235836982727051, | |
| "eval_loss": 0.6692806482315063, | |
| "eval_runtime": 7.1275, | |
| "eval_samples_per_second": 881.66, | |
| "eval_steps_per_second": 110.278, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_accuracy": 0.72835773229599, | |
| "eval_loss": 0.6607570648193359, | |
| "eval_runtime": 7.1216, | |
| "eval_samples_per_second": 882.388, | |
| "eval_steps_per_second": 110.369, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.660098522167488e-05, | |
| "loss": 0.6395, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_accuracy": 0.7259707450866699, | |
| "eval_loss": 0.6591860055923462, | |
| "eval_runtime": 7.1318, | |
| "eval_samples_per_second": 881.119, | |
| "eval_steps_per_second": 110.21, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "eval_accuracy": 0.7277212142944336, | |
| "eval_loss": 0.657184898853302, | |
| "eval_runtime": 7.1172, | |
| "eval_samples_per_second": 882.928, | |
| "eval_steps_per_second": 110.436, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "eval_accuracy": 0.7291533946990967, | |
| "eval_loss": 0.6624195575714111, | |
| "eval_runtime": 7.1289, | |
| "eval_samples_per_second": 881.476, | |
| "eval_steps_per_second": 110.255, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.598522167487685e-05, | |
| "loss": 0.6374, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_accuracy": 0.729312539100647, | |
| "eval_loss": 0.6546571254730225, | |
| "eval_runtime": 7.1204, | |
| "eval_samples_per_second": 882.541, | |
| "eval_steps_per_second": 110.388, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "eval_accuracy": 0.7278803586959839, | |
| "eval_loss": 0.6573053598403931, | |
| "eval_runtime": 7.1365, | |
| "eval_samples_per_second": 880.549, | |
| "eval_steps_per_second": 110.139, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 2.5369458128078822e-05, | |
| "loss": 0.646, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "eval_accuracy": 0.7258116006851196, | |
| "eval_loss": 0.6613573431968689, | |
| "eval_runtime": 7.1306, | |
| "eval_samples_per_second": 881.266, | |
| "eval_steps_per_second": 110.228, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "eval_accuracy": 0.7281985878944397, | |
| "eval_loss": 0.6586018800735474, | |
| "eval_runtime": 7.1343, | |
| "eval_samples_per_second": 880.812, | |
| "eval_steps_per_second": 110.172, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_accuracy": 0.727402925491333, | |
| "eval_loss": 0.6686715483665466, | |
| "eval_runtime": 7.1093, | |
| "eval_samples_per_second": 883.91, | |
| "eval_steps_per_second": 110.559, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 2.475369458128079e-05, | |
| "loss": 0.629, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "eval_accuracy": 0.7250159382820129, | |
| "eval_loss": 0.66302090883255, | |
| "eval_runtime": 7.134, | |
| "eval_samples_per_second": 880.855, | |
| "eval_steps_per_second": 110.177, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_accuracy": 0.7280394434928894, | |
| "eval_loss": 0.667898416519165, | |
| "eval_runtime": 7.117, | |
| "eval_samples_per_second": 882.951, | |
| "eval_steps_per_second": 110.439, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 2.413793103448276e-05, | |
| "loss": 0.617, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_accuracy": 0.7280394434928894, | |
| "eval_loss": 0.6668043732643127, | |
| "eval_runtime": 7.1304, | |
| "eval_samples_per_second": 881.295, | |
| "eval_steps_per_second": 110.232, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_accuracy": 0.72835773229599, | |
| "eval_loss": 0.6602988839149475, | |
| "eval_runtime": 7.1165, | |
| "eval_samples_per_second": 883.014, | |
| "eval_steps_per_second": 110.447, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_accuracy": 0.731699526309967, | |
| "eval_loss": 0.6601841449737549, | |
| "eval_runtime": 7.1229, | |
| "eval_samples_per_second": 882.224, | |
| "eval_steps_per_second": 110.348, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.3522167487684728e-05, | |
| "loss": 0.6239, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_accuracy": 0.7299490571022034, | |
| "eval_loss": 0.6645928025245667, | |
| "eval_runtime": 7.1079, | |
| "eval_samples_per_second": 884.089, | |
| "eval_steps_per_second": 110.581, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "eval_accuracy": 0.7286760210990906, | |
| "eval_loss": 0.6626018285751343, | |
| "eval_runtime": 7.1349, | |
| "eval_samples_per_second": 880.737, | |
| "eval_steps_per_second": 110.162, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.29064039408867e-05, | |
| "loss": 0.6206, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "eval_accuracy": 0.7262889742851257, | |
| "eval_loss": 0.6620416045188904, | |
| "eval_runtime": 7.1083, | |
| "eval_samples_per_second": 884.033, | |
| "eval_steps_per_second": 110.574, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "eval_accuracy": 0.7259707450866699, | |
| "eval_loss": 0.6685923933982849, | |
| "eval_runtime": 7.1136, | |
| "eval_samples_per_second": 883.379, | |
| "eval_steps_per_second": 110.493, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_accuracy": 0.7312221527099609, | |
| "eval_loss": 0.6637505292892456, | |
| "eval_runtime": 7.0986, | |
| "eval_samples_per_second": 885.242, | |
| "eval_steps_per_second": 110.726, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 2.229064039408867e-05, | |
| "loss": 0.614, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_accuracy": 0.7297899723052979, | |
| "eval_loss": 0.6602672338485718, | |
| "eval_runtime": 7.1489, | |
| "eval_samples_per_second": 879.01, | |
| "eval_steps_per_second": 109.946, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_accuracy": 0.7278803586959839, | |
| "eval_loss": 0.662921667098999, | |
| "eval_runtime": 7.105, | |
| "eval_samples_per_second": 884.45, | |
| "eval_steps_per_second": 110.627, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 2.1674876847290644e-05, | |
| "loss": 0.6193, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "eval_accuracy": 0.7323361039161682, | |
| "eval_loss": 0.6599108576774597, | |
| "eval_runtime": 7.1371, | |
| "eval_samples_per_second": 880.464, | |
| "eval_steps_per_second": 110.128, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_accuracy": 0.7286760210990906, | |
| "eval_loss": 0.6652523279190063, | |
| "eval_runtime": 7.1062, | |
| "eval_samples_per_second": 884.296, | |
| "eval_steps_per_second": 110.607, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "eval_accuracy": 0.7288351655006409, | |
| "eval_loss": 0.6546856760978699, | |
| "eval_runtime": 7.1178, | |
| "eval_samples_per_second": 882.851, | |
| "eval_steps_per_second": 110.427, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.105911330049261e-05, | |
| "loss": 0.6226, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "eval_accuracy": 0.730267345905304, | |
| "eval_loss": 0.6600866913795471, | |
| "eval_runtime": 7.0969, | |
| "eval_samples_per_second": 885.457, | |
| "eval_steps_per_second": 110.753, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_accuracy": 0.72835773229599, | |
| "eval_loss": 0.6599671244621277, | |
| "eval_runtime": 7.1128, | |
| "eval_samples_per_second": 883.483, | |
| "eval_steps_per_second": 110.506, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 2.0443349753694584e-05, | |
| "loss": 0.6158, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_accuracy": 0.7304264903068542, | |
| "eval_loss": 0.6600461602210999, | |
| "eval_runtime": 7.1187, | |
| "eval_samples_per_second": 882.74, | |
| "eval_steps_per_second": 110.413, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_accuracy": 0.7256524562835693, | |
| "eval_loss": 0.6626370549201965, | |
| "eval_runtime": 7.1145, | |
| "eval_samples_per_second": 883.27, | |
| "eval_steps_per_second": 110.479, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "eval_accuracy": 0.7334500551223755, | |
| "eval_loss": 0.6616737842559814, | |
| "eval_runtime": 7.1091, | |
| "eval_samples_per_second": 883.933, | |
| "eval_steps_per_second": 110.562, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 1.9827586206896554e-05, | |
| "loss": 0.6115, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_accuracy": 0.7310630083084106, | |
| "eval_loss": 0.6600754261016846, | |
| "eval_runtime": 7.1175, | |
| "eval_samples_per_second": 882.895, | |
| "eval_steps_per_second": 110.432, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "eval_accuracy": 0.7340865731239319, | |
| "eval_loss": 0.6601821780204773, | |
| "eval_runtime": 7.1275, | |
| "eval_samples_per_second": 881.653, | |
| "eval_steps_per_second": 110.277, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1.921182266009852e-05, | |
| "loss": 0.6057, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "eval_accuracy": 0.7321769595146179, | |
| "eval_loss": 0.6605399250984192, | |
| "eval_runtime": 7.1294, | |
| "eval_samples_per_second": 881.424, | |
| "eval_steps_per_second": 110.248, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "eval_accuracy": 0.7288351655006409, | |
| "eval_loss": 0.6598327159881592, | |
| "eval_runtime": 7.119, | |
| "eval_samples_per_second": 882.705, | |
| "eval_steps_per_second": 110.408, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "eval_accuracy": 0.7297899723052979, | |
| "eval_loss": 0.6586458683013916, | |
| "eval_runtime": 7.1237, | |
| "eval_samples_per_second": 882.12, | |
| "eval_steps_per_second": 110.335, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 1.8596059113300493e-05, | |
| "loss": 0.5992, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "eval_accuracy": 0.7342457175254822, | |
| "eval_loss": 0.6593834161758423, | |
| "eval_runtime": 7.1555, | |
| "eval_samples_per_second": 878.205, | |
| "eval_steps_per_second": 109.846, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "eval_accuracy": 0.733609139919281, | |
| "eval_loss": 0.659511923789978, | |
| "eval_runtime": 7.1271, | |
| "eval_samples_per_second": 881.705, | |
| "eval_steps_per_second": 110.283, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.7980295566502463e-05, | |
| "loss": 0.6028, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_accuracy": 0.7299490571022034, | |
| "eval_loss": 0.6572112441062927, | |
| "eval_runtime": 7.1318, | |
| "eval_samples_per_second": 881.126, | |
| "eval_steps_per_second": 110.211, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "eval_accuracy": 0.7334500551223755, | |
| "eval_loss": 0.6614532470703125, | |
| "eval_runtime": 7.1291, | |
| "eval_samples_per_second": 881.454, | |
| "eval_steps_per_second": 110.252, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "eval_accuracy": 0.7304264903068542, | |
| "eval_loss": 0.6609640717506409, | |
| "eval_runtime": 7.1218, | |
| "eval_samples_per_second": 882.36, | |
| "eval_steps_per_second": 110.365, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.7364532019704436e-05, | |
| "loss": 0.6058, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "eval_accuracy": 0.7310630083084106, | |
| "eval_loss": 0.6593703031539917, | |
| "eval_runtime": 7.1821, | |
| "eval_samples_per_second": 874.951, | |
| "eval_steps_per_second": 109.438, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_accuracy": 0.7334500551223755, | |
| "eval_loss": 0.6582794785499573, | |
| "eval_runtime": 7.1156, | |
| "eval_samples_per_second": 883.128, | |
| "eval_steps_per_second": 110.461, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 1.6748768472906403e-05, | |
| "loss": 0.5985, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "eval_accuracy": 0.7304264903068542, | |
| "eval_loss": 0.6584789752960205, | |
| "eval_runtime": 7.1255, | |
| "eval_samples_per_second": 881.898, | |
| "eval_steps_per_second": 110.307, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_accuracy": 0.7323361039161682, | |
| "eval_loss": 0.6626281142234802, | |
| "eval_runtime": 7.1065, | |
| "eval_samples_per_second": 884.263, | |
| "eval_steps_per_second": 110.603, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "eval_accuracy": 0.727402925491333, | |
| "eval_loss": 0.6593265533447266, | |
| "eval_runtime": 7.1566, | |
| "eval_samples_per_second": 878.068, | |
| "eval_steps_per_second": 109.828, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 1.6133004926108376e-05, | |
| "loss": 0.6, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_accuracy": 0.7328134775161743, | |
| "eval_loss": 0.6583454012870789, | |
| "eval_runtime": 7.1076, | |
| "eval_samples_per_second": 884.119, | |
| "eval_steps_per_second": 110.585, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "eval_accuracy": 0.732654333114624, | |
| "eval_loss": 0.6581458449363708, | |
| "eval_runtime": 7.1149, | |
| "eval_samples_per_second": 883.214, | |
| "eval_steps_per_second": 110.472, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 1.5517241379310346e-05, | |
| "loss": 0.6009, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_accuracy": 0.7334500551223755, | |
| "eval_loss": 0.6602644324302673, | |
| "eval_runtime": 7.1115, | |
| "eval_samples_per_second": 883.644, | |
| "eval_steps_per_second": 110.526, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "eval_accuracy": 0.7315404415130615, | |
| "eval_loss": 0.6539360284805298, | |
| "eval_runtime": 7.1218, | |
| "eval_samples_per_second": 882.358, | |
| "eval_steps_per_second": 110.365, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.733609139919281, | |
| "eval_loss": 0.6602201461791992, | |
| "eval_runtime": 7.1034, | |
| "eval_samples_per_second": 884.646, | |
| "eval_steps_per_second": 110.651, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 1.4901477832512317e-05, | |
| "loss": 0.6013, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_accuracy": 0.732654333114624, | |
| "eval_loss": 0.6585041284561157, | |
| "eval_runtime": 7.1174, | |
| "eval_samples_per_second": 882.908, | |
| "eval_steps_per_second": 110.434, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "eval_accuracy": 0.7301082015037537, | |
| "eval_loss": 0.659524142742157, | |
| "eval_runtime": 7.0987, | |
| "eval_samples_per_second": 885.233, | |
| "eval_steps_per_second": 110.725, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.5937, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "eval_accuracy": 0.7318586707115173, | |
| "eval_loss": 0.6640517711639404, | |
| "eval_runtime": 7.1062, | |
| "eval_samples_per_second": 884.293, | |
| "eval_steps_per_second": 110.607, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "eval_accuracy": 0.7324952483177185, | |
| "eval_loss": 0.6623978018760681, | |
| "eval_runtime": 7.1076, | |
| "eval_samples_per_second": 884.119, | |
| "eval_steps_per_second": 110.585, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "eval_accuracy": 0.7321769595146179, | |
| "eval_loss": 0.6652867794036865, | |
| "eval_runtime": 7.1683, | |
| "eval_samples_per_second": 876.634, | |
| "eval_steps_per_second": 109.649, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 1.3669950738916257e-05, | |
| "loss": 0.5779, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "eval_accuracy": 0.7324952483177185, | |
| "eval_loss": 0.6649503111839294, | |
| "eval_runtime": 7.1045, | |
| "eval_samples_per_second": 884.505, | |
| "eval_steps_per_second": 110.634, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_accuracy": 0.7332909107208252, | |
| "eval_loss": 0.6616361141204834, | |
| "eval_runtime": 7.114, | |
| "eval_samples_per_second": 883.327, | |
| "eval_steps_per_second": 110.486, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.3054187192118228e-05, | |
| "loss": 0.5809, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "eval_accuracy": 0.7312221527099609, | |
| "eval_loss": 0.6653700470924377, | |
| "eval_runtime": 7.1061, | |
| "eval_samples_per_second": 884.315, | |
| "eval_steps_per_second": 110.61, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "step": 30000, | |
| "total_flos": 4.469740936607232e+16, | |
| "train_loss": 0.6925110097249348, | |
| "train_runtime": 5542.0479, | |
| "train_samples_per_second": 468.744, | |
| "train_steps_per_second": 7.326 | |
| } | |
| ], | |
| "max_steps": 40600, | |
| "num_train_epochs": 10, | |
| "total_flos": 4.469740936607232e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |