| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9999845578447693, | |
| "global_step": 40473, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 9.7353, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4e-05, | |
| "loss": 8.2306, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6e-05, | |
| "loss": 7.5102, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8e-05, | |
| "loss": 7.2441, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9668, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00012, | |
| "loss": 6.6706, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00014, | |
| "loss": 6.4207, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00016, | |
| "loss": 6.2927, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018, | |
| "loss": 6.1555, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 5.9469, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.14350219833903274, | |
| "eval_loss": 6.5843048095703125, | |
| "eval_runtime": 149.8081, | |
| "eval_samples_per_second": 6.675, | |
| "eval_steps_per_second": 3.338, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019999683286053426, | |
| "loss": 5.8516, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001999873316427525, | |
| "loss": 5.6928, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019997149694848834, | |
| "loss": 5.5905, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019994932978075548, | |
| "loss": 5.4808, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019992083154368414, | |
| "loss": 5.3261, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019988600404243222, | |
| "loss": 5.2571, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001998448494830707, | |
| "loss": 5.1842, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019979737047244424, | |
| "loss": 5.1502, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019974357001800575, | |
| "loss": 5.0854, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019968345152762614, | |
| "loss": 4.9953, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.1911294577430386, | |
| "eval_loss": 5.77092170715332, | |
| "eval_runtime": 149.2322, | |
| "eval_samples_per_second": 6.701, | |
| "eval_steps_per_second": 3.35, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019961701880937823, | |
| "loss": 4.9123, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001995442760712957, | |
| "loss": 4.8373, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019946522792110648, | |
| "loss": 4.7841, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019937987936594095, | |
| "loss": 4.731, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019928823581201455, | |
| "loss": 4.6354, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001991903030642857, | |
| "loss": 4.6333, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001990860873260878, | |
| "loss": 4.5291, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019897559519873635, | |
| "loss": 4.4949, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019885883368111093, | |
| "loss": 4.4967, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019873581016921173, | |
| "loss": 4.3754, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.23306155349291646, | |
| "eval_loss": 5.262444019317627, | |
| "eval_runtime": 151.6242, | |
| "eval_samples_per_second": 6.595, | |
| "eval_steps_per_second": 3.298, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001986065324556912, | |
| "loss": 4.3805, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019847100872936023, | |
| "loss": 4.2668, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019832924757466974, | |
| "loss": 4.289, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001981812579711666, | |
| "loss": 4.2334, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019802704929292514, | |
| "loss": 4.2227, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019786663130795317, | |
| "loss": 4.1494, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019770001417757332, | |
| "loss": 4.1242, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019752720845577938, | |
| "loss": 4.0128, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019734822508856773, | |
| "loss": 3.9907, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019716307541324418, | |
| "loss": 3.9795, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.27312457254518807, | |
| "eval_loss": 4.875171184539795, | |
| "eval_runtime": 149.3435, | |
| "eval_samples_per_second": 6.696, | |
| "eval_steps_per_second": 3.348, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019697177115770548, | |
| "loss": 3.9426, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001967743244396969, | |
| "loss": 3.8986, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019657074776604426, | |
| "loss": 3.8835, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001963610540318619, | |
| "loss": 3.9364, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019614525651973582, | |
| "loss": 3.7685, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019592336889888244, | |
| "loss": 3.7921, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001956954052242825, | |
| "loss": 3.7474, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019546137993579107, | |
| "loss": 3.7227, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019522130785722266, | |
| "loss": 3.7087, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019497520419541235, | |
| "loss": 3.7099, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.30389936492427944, | |
| "eval_loss": 4.592658996582031, | |
| "eval_runtime": 149.1172, | |
| "eval_samples_per_second": 6.706, | |
| "eval_steps_per_second": 3.353, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019472308453925258, | |
| "loss": 3.649, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001944649648587056, | |
| "loss": 3.6001, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019420086150379192, | |
| "loss": 3.6509, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019393079120355475, | |
| "loss": 3.598, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001936547710650002, | |
| "loss": 3.5339, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019337281857201378, | |
| "loss": 3.573, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001930849515842528, | |
| "loss": 3.5411, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019279118833601523, | |
| "loss": 3.5458, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019249154743508463, | |
| "loss": 3.5076, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019218604786155148, | |
| "loss": 3.4747, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.32299853444064486, | |
| "eval_loss": 4.394214630126953, | |
| "eval_runtime": 164.2578, | |
| "eval_samples_per_second": 6.088, | |
| "eval_steps_per_second": 3.044, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019187470896661084, | |
| "loss": 3.5194, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019155755047133678, | |
| "loss": 3.4677, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019123459246543303, | |
| "loss": 3.4157, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019090585540596053, | |
| "loss": 3.4342, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019057136011604156, | |
| "loss": 3.436, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019023112778354082, | |
| "loss": 3.394, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018988517995972325, | |
| "loss": 3.4081, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018953353855788896, | |
| "loss": 3.3736, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001891762258519852, | |
| "loss": 3.3793, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001888132644751954, | |
| "loss": 3.343, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.334904738641915, | |
| "eval_loss": 4.287891387939453, | |
| "eval_runtime": 142.0586, | |
| "eval_samples_per_second": 7.039, | |
| "eval_steps_per_second": 3.52, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001884446774185056, | |
| "loss": 3.3829, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018807048802924804, | |
| "loss": 3.3683, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001876907200096224, | |
| "loss": 3.299, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018730539741519436, | |
| "loss": 3.3129, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0001869145446533718, | |
| "loss": 3.3329, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018651818648185886, | |
| "loss": 3.3036, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018611634800708767, | |
| "loss": 3.2714, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018570905468262816, | |
| "loss": 3.2606, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018529633230757547, | |
| "loss": 3.2601, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018487820702491615, | |
| "loss": 3.2767, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.3458881289692233, | |
| "eval_loss": 4.169787883758545, | |
| "eval_runtime": 147.5408, | |
| "eval_samples_per_second": 6.778, | |
| "eval_steps_per_second": 3.389, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018445470531987178, | |
| "loss": 3.2766, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018402585401822172, | |
| "loss": 3.2475, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001835916802846036, | |
| "loss": 3.2341, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001831522116207927, | |
| "loss": 3.2234, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00018270747586396008, | |
| "loss": 3.2216, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00018225750118490904, | |
| "loss": 3.2029, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001818023160862909, | |
| "loss": 3.1778, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00018134194940079942, | |
| "loss": 3.1699, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001808764302893446, | |
| "loss": 3.1801, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00018040578823920545, | |
| "loss": 3.1852, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.3533742061553493, | |
| "eval_loss": 4.092532634735107, | |
| "eval_runtime": 149.3684, | |
| "eval_samples_per_second": 6.695, | |
| "eval_steps_per_second": 3.347, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00017993005306216216, | |
| "loss": 3.1856, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017944925489260784, | |
| "loss": 3.1604, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017896342418563963, | |
| "loss": 3.1725, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017847259171512963, | |
| "loss": 3.1451, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017797678857177566, | |
| "loss": 3.142, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00017747604616113175, | |
| "loss": 3.1825, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00017697039620161894, | |
| "loss": 3.1747, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000176459870722516, | |
| "loss": 3.0989, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00017594450206193088, | |
| "loss": 3.1139, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.000175424322864752, | |
| "loss": 3.0871, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.360838299951148, | |
| "eval_loss": 4.023919105529785, | |
| "eval_runtime": 149.3116, | |
| "eval_samples_per_second": 6.697, | |
| "eval_steps_per_second": 3.349, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00017489936608058073, | |
| "loss": 3.1034, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00017436966496164397, | |
| "loss": 3.0933, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00017383525306068816, | |
| "loss": 3.1107, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00017329616422885372, | |
| "loss": 3.0945, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00017275243261353094, | |
| "loss": 3.0885, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00017220409265619697, | |
| "loss": 3.0761, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00017165117909023425, | |
| "loss": 3.0988, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00017109372693873022, | |
| "loss": 3.0941, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00017053177151225913, | |
| "loss": 3.1068, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00016996534840664514, | |
| "loss": 3.0746, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.36640889106008795, | |
| "eval_loss": 3.9645512104034424, | |
| "eval_runtime": 151.7078, | |
| "eval_samples_per_second": 6.592, | |
| "eval_steps_per_second": 3.296, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00016939449350070768, | |
| "loss": 3.0761, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00016881924295398883, | |
| "loss": 3.0362, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00016823963320446273, | |
| "loss": 3.0012, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00016765570096622761, | |
| "loss": 3.0244, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00016706748322718027, | |
| "loss": 3.0108, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000166475017246673, | |
| "loss": 3.0364, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00016587834055315358, | |
| "loss": 3.0235, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00016527749094178806, | |
| "loss": 3.0356, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00016467250647206685, | |
| "loss": 3.0178, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001640634254653937, | |
| "loss": 2.9473, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.37060478749389353, | |
| "eval_loss": 3.9244790077209473, | |
| "eval_runtime": 149.2451, | |
| "eval_samples_per_second": 6.7, | |
| "eval_steps_per_second": 3.35, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00016345028650265853, | |
| "loss": 3.0204, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00016283312842179344, | |
| "loss": 2.976, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00016221199031531277, | |
| "loss": 3.0472, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00016158691152783666, | |
| "loss": 2.9778, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001609579316535991, | |
| "loss": 2.9958, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00016032509053393978, | |
| "loss": 2.9772, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00015968842825478033, | |
| "loss": 3.0037, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00015904798514408545, | |
| "loss": 2.9888, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00015840380176930808, | |
| "loss": 2.9614, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001577559189348201, | |
| "loss": 2.9737, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.375352711284807, | |
| "eval_loss": 3.8742177486419678, | |
| "eval_runtime": 149.4881, | |
| "eval_samples_per_second": 6.689, | |
| "eval_steps_per_second": 3.345, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001571043776793273, | |
| "loss": 2.9724, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00015644921927327024, | |
| "loss": 2.9695, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00015579048521620977, | |
| "loss": 3.0015, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001551282172341985, | |
| "loss": 2.9804, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00015446245727713758, | |
| "loss": 2.9711, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00015379324751611985, | |
| "loss": 2.9746, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00015312063034075816, | |
| "loss": 2.9414, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00015244464835650052, | |
| "loss": 2.9365, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001517653443819313, | |
| "loss": 2.9674, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00015108276144605912, | |
| "loss": 2.9193, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.37964826575476307, | |
| "eval_loss": 3.8284761905670166, | |
| "eval_runtime": 149.3853, | |
| "eval_samples_per_second": 6.694, | |
| "eval_steps_per_second": 3.347, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001503969427855911, | |
| "loss": 2.9236, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00014970793184219402, | |
| "loss": 2.8793, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.000149015772259743, | |
| "loss": 2.9347, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014832050788155668, | |
| "loss": 2.908, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014762218274762, | |
| "loss": 2.9523, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014692084109179483, | |
| "loss": 2.9633, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001462165273390179, | |
| "loss": 2.8945, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00014550928610248688, | |
| "loss": 2.9083, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001447991621808344, | |
| "loss": 2.881, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00014408620055529045, | |
| "loss": 2.8833, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.3837151929653151, | |
| "eval_loss": 3.7952051162719727, | |
| "eval_runtime": 142.0749, | |
| "eval_samples_per_second": 7.039, | |
| "eval_steps_per_second": 3.519, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00014337044638683297, | |
| "loss": 2.8999, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00014265194501332756, | |
| "loss": 2.8795, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001419307419466553, | |
| "loss": 2.8995, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00014120688286983012, | |
| "loss": 2.9001, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00014048041363410498, | |
| "loss": 2.9089, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00013975138025606765, | |
| "loss": 2.9049, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001390198289147258, | |
| "loss": 2.8915, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001382858059485819, | |
| "loss": 2.8382, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00013754935785269802, | |
| "loss": 2.8535, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00013681053127575078, | |
| "loss": 2.8533, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.3872970200293112, | |
| "eval_loss": 3.761565923690796, | |
| "eval_runtime": 141.7939, | |
| "eval_samples_per_second": 7.052, | |
| "eval_steps_per_second": 3.526, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001360693730170764, | |
| "loss": 2.8792, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001353259300237063, | |
| "loss": 2.8601, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00013458024938739328, | |
| "loss": 2.8794, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013383237834162893, | |
| "loss": 2.8738, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013308236425865123, | |
| "loss": 2.8475, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013233025464644426, | |
| "loss": 2.8692, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013157609714572877, | |
| "loss": 2.8282, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00013081993952694434, | |
| "loss": 2.8956, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00013006182968722382, | |
| "loss": 2.8338, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012930181564735897, | |
| "loss": 2.8654, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.39067855398143625, | |
| "eval_loss": 3.72955322265625, | |
| "eval_runtime": 141.9976, | |
| "eval_samples_per_second": 7.042, | |
| "eval_steps_per_second": 3.521, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012853994554875902, | |
| "loss": 2.8337, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012777626765040116, | |
| "loss": 2.811, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00012701083032577354, | |
| "loss": 2.827, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00012624368205981136, | |
| "loss": 2.8085, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00012547487144582564, | |
| "loss": 2.8328, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001247044471824251, | |
| "loss": 2.8269, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00012393245807043154, | |
| "loss": 2.8141, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00012315895300978863, | |
| "loss": 2.8054, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001223839809964645, | |
| "loss": 2.8176, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001216075911193481, | |
| "loss": 2.8196, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.3935666829506595, | |
| "eval_loss": 3.7048707008361816, | |
| "eval_runtime": 141.7514, | |
| "eval_samples_per_second": 7.055, | |
| "eval_steps_per_second": 3.527, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001208298325571398, | |
| "loss": 2.8031, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00012005075457523635, | |
| "loss": 2.8213, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00011927040652261028, | |
| "loss": 2.823, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00011848883782868381, | |
| "loss": 2.8006, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001177060980001981, | |
| "loss": 2.7874, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011692223661807716, | |
| "loss": 2.7917, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011613730333428738, | |
| "loss": 2.7983, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011535134786869242, | |
| "loss": 2.8175, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011456442000590371, | |
| "loss": 2.7732, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011377656959212703, | |
| "loss": 2.7883, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.3966370297997069, | |
| "eval_loss": 3.678572177886963, | |
| "eval_runtime": 141.8348, | |
| "eval_samples_per_second": 7.05, | |
| "eval_steps_per_second": 3.525, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011298784653200525, | |
| "loss": 2.779, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001121983007854569, | |
| "loss": 2.7928, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001114079823645119, | |
| "loss": 2.7889, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00011061694133014351, | |
| "loss": 2.7992, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00010982522778909725, | |
| "loss": 2.8229, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00010903289189071721, | |
| "loss": 2.7589, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00010823998382376919, | |
| "loss": 2.7828, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00010744655381326188, | |
| "loss": 2.7468, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00010665265211726528, | |
| "loss": 2.7686, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00010585832902372721, | |
| "loss": 2.747, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.3989570102589155, | |
| "eval_loss": 3.6488404273986816, | |
| "eval_runtime": 141.8989, | |
| "eval_samples_per_second": 7.047, | |
| "eval_steps_per_second": 3.524, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010506363484728803, | |
| "loss": 2.7899, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010426861992609356, | |
| "loss": 2.7468, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010347333461860647, | |
| "loss": 2.7607, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001026778293004164, | |
| "loss": 2.7659, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00010188215436104913, | |
| "loss": 2.7515, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00010108636020077471, | |
| "loss": 2.786, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.000100290497227415, | |
| "loss": 2.7153, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.94946158531506e-05, | |
| "loss": 2.7299, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.869876649132773e-05, | |
| "loss": 2.7673, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.790299955326484e-05, | |
| "loss": 2.7355, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.4021494870542257, | |
| "eval_loss": 3.6243462562561035, | |
| "eval_runtime": 142.1627, | |
| "eval_samples_per_second": 7.034, | |
| "eval_steps_per_second": 3.517, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.710736544505947e-05, | |
| "loss": 2.7641, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.631191456439525e-05, | |
| "loss": 2.7809, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.551669729734978e-05, | |
| "loss": 2.7434, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.472176401520279e-05, | |
| "loss": 2.7287, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.392716507124576e-05, | |
| "loss": 2.7536, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.313295079759219e-05, | |
| "loss": 2.7539, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.233917150198943e-05, | |
| "loss": 2.7753, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.154587746463225e-05, | |
| "loss": 2.7551, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.07531189349776e-05, | |
| "loss": 2.706, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 8.996094612856212e-05, | |
| "loss": 2.7355, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.40534440644846115, | |
| "eval_loss": 3.5981943607330322, | |
| "eval_runtime": 141.9963, | |
| "eval_samples_per_second": 7.042, | |
| "eval_steps_per_second": 3.521, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.916940922382091e-05, | |
| "loss": 2.7117, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.837855835890943e-05, | |
| "loss": 2.717, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.758844362852732e-05, | |
| "loss": 2.733, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.679911508074552e-05, | |
| "loss": 2.7257, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.601062271383592e-05, | |
| "loss": 2.6842, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.522301647310445e-05, | |
| "loss": 2.7144, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.443634624772719e-05, | |
| "loss": 2.7521, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.365066186759055e-05, | |
| "loss": 2.7484, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.286601310013463e-05, | |
| "loss": 2.7177, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.208244964720108e-05, | |
| "loss": 2.6999, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.4074880312652662, | |
| "eval_loss": 3.5765340328216553, | |
| "eval_runtime": 142.0816, | |
| "eval_samples_per_second": 7.038, | |
| "eval_steps_per_second": 3.519, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.130002114188453e-05, | |
| "loss": 2.6884, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.0518777145389e-05, | |
| "loss": 2.6783, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.97387671438883e-05, | |
| "loss": 2.6857, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.896004054539173e-05, | |
| "loss": 2.6957, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.818264667661405e-05, | |
| "loss": 2.7092, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.740663477985133e-05, | |
| "loss": 2.6602, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.663205400986167e-05, | |
| "loss": 2.7544, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.585895343075162e-05, | |
| "loss": 2.6894, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.508738201286819e-05, | |
| "loss": 2.6764, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.431738862969718e-05, | |
| "loss": 2.7243, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.41014020517830974, | |
| "eval_loss": 3.5558369159698486, | |
| "eval_runtime": 141.9008, | |
| "eval_samples_per_second": 7.047, | |
| "eval_steps_per_second": 3.524, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.354902205476732e-05, | |
| "loss": 2.7029, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.278233095856057e-05, | |
| "loss": 2.6547, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.201736390542958e-05, | |
| "loss": 2.6755, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.125416935052119e-05, | |
| "loss": 2.6666, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.049279563670732e-05, | |
| "loss": 2.6753, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.973329099152268e-05, | |
| "loss": 2.6411, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.897570352411003e-05, | |
| "loss": 2.6519, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.822008122217267e-05, | |
| "loss": 2.6922, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.746647194893494e-05, | |
| "loss": 2.6432, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.671492344011017e-05, | |
| "loss": 2.6526, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.41251294577430386, | |
| "eval_loss": 3.537142753601074, | |
| "eval_runtime": 149.0732, | |
| "eval_samples_per_second": 6.708, | |
| "eval_steps_per_second": 3.354, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.596548330087729e-05, | |
| "loss": 2.6583, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.521819900286509e-05, | |
| "loss": 2.7001, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.447311788114547e-05, | |
| "loss": 2.6591, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.373028713123489e-05, | |
| "loss": 2.6622, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.298975380610508e-05, | |
| "loss": 2.7062, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.22515648132024e-05, | |
| "loss": 2.679, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.151576691147676e-05, | |
| "loss": 2.6539, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.0782406708419535e-05, | |
| "loss": 2.6741, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.005153065711164e-05, | |
| "loss": 2.6285, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.932318505328076e-05, | |
| "loss": 2.641, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.4146458231558378, | |
| "eval_loss": 3.5149853229522705, | |
| "eval_runtime": 181.5716, | |
| "eval_samples_per_second": 5.507, | |
| "eval_steps_per_second": 2.754, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.859741603236909e-05, | |
| "loss": 2.6834, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.787426956661071e-05, | |
| "loss": 2.6712, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.715379146211998e-05, | |
| "loss": 2.6772, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.6436027355989517e-05, | |
| "loss": 2.6672, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.5721022713399965e-05, | |
| "loss": 2.6001, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.500882282473983e-05, | |
| "loss": 2.6681, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.429947280273646e-05, | |
| "loss": 2.6229, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.359301757959896e-05, | |
| "loss": 2.6637, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.2889501904171633e-05, | |
| "loss": 2.617, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.2188970339099716e-05, | |
| "loss": 2.6602, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.4168324377137274, | |
| "eval_loss": 3.497141122817993, | |
| "eval_runtime": 143.8542, | |
| "eval_samples_per_second": 6.951, | |
| "eval_steps_per_second": 3.476, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.149146725800653e-05, | |
| "loss": 2.6309, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.0797036842682796e-05, | |
| "loss": 2.6206, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.0105723080287956e-05, | |
| "loss": 2.6232, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.941756976056414e-05, | |
| "loss": 2.6094, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.873262047306193e-05, | |
| "loss": 2.6533, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.805091860437985e-05, | |
| "loss": 2.611, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.7372507335415716e-05, | |
| "loss": 2.6003, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.6697429638631594e-05, | |
| "loss": 2.6118, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.6025728275331805e-05, | |
| "loss": 2.5899, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.53574457929543e-05, | |
| "loss": 2.644, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.4192027357107963, | |
| "eval_loss": 3.4811973571777344, | |
| "eval_runtime": 151.4293, | |
| "eval_samples_per_second": 6.604, | |
| "eval_steps_per_second": 3.302, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.469262452237552e-05, | |
| "loss": 2.6313, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.403130657522924e-05, | |
| "loss": 2.5829, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.337353384123871e-05, | |
| "loss": 2.6009, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.2719347985563754e-05, | |
| "loss": 2.6282, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.2068790446161166e-05, | |
| "loss": 2.6724, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.1421902431160095e-05, | |
| "loss": 2.6432, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.07787249162518e-05, | |
| "loss": 2.6422, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.013929864209407e-05, | |
| "loss": 2.6249, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.950366411173067e-05, | |
| "loss": 2.6187, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.887186158802581e-05, | |
| "loss": 2.6558, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.42146458231558376, | |
| "eval_loss": 3.462165594100952, | |
| "eval_runtime": 159.3822, | |
| "eval_samples_per_second": 6.274, | |
| "eval_steps_per_second": 3.137, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.8243931091113525e-05, | |
| "loss": 2.6114, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.7619912395863045e-05, | |
| "loss": 2.6093, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.699984502935918e-05, | |
| "loss": 2.641, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.6383768268398356e-05, | |
| "loss": 2.618, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.5771721137001134e-05, | |
| "loss": 2.5961, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.516374240393999e-05, | |
| "loss": 2.5759, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.455987058028372e-05, | |
| "loss": 2.5699, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.3960143916957995e-05, | |
| "loss": 2.6057, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.336460040232252e-05, | |
| "loss": 2.6013, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.2773277759764644e-05, | |
| "loss": 2.5664, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.42288812896922323, | |
| "eval_loss": 3.4503753185272217, | |
| "eval_runtime": 152.9493, | |
| "eval_samples_per_second": 6.538, | |
| "eval_steps_per_second": 3.269, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.218621344531002e-05, | |
| "loss": 2.601, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.16034446452497e-05, | |
| "loss": 2.5845, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.102500827378511e-05, | |
| "loss": 2.5578, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.0450940970689413e-05, | |
| "loss": 2.6059, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.988127909898686e-05, | |
| "loss": 2.5967, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.9316058742649354e-05, | |
| "loss": 2.5889, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.875531570431086e-05, | |
| "loss": 2.5626, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.819908550299947e-05, | |
| "loss": 2.6232, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.7647403371887736e-05, | |
| "loss": 2.5861, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.7100304256060526e-05, | |
| "loss": 2.5669, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.424466536394724, | |
| "eval_loss": 3.4375574588775635, | |
| "eval_runtime": 144.0616, | |
| "eval_samples_per_second": 6.941, | |
| "eval_steps_per_second": 3.471, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.655782281030198e-05, | |
| "loss": 2.5697, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.6019993396899977e-05, | |
| "loss": 2.613, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.548685008346974e-05, | |
| "loss": 2.5858, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.495842664079584e-05, | |
| "loss": 2.534, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.4434756540693082e-05, | |
| "loss": 2.5843, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.3915872953886265e-05, | |
| "loss": 2.5988, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.340180874790916e-05, | |
| "loss": 2.5684, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.2892596485022423e-05, | |
| "loss": 2.5921, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.2388268420151127e-05, | |
| "loss": 2.5761, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.1888856498841704e-05, | |
| "loss": 2.5498, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.42633659013190034, | |
| "eval_loss": 3.4263486862182617, | |
| "eval_runtime": 144.2437, | |
| "eval_samples_per_second": 6.933, | |
| "eval_steps_per_second": 3.466, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.1394392355238145e-05, | |
| "loss": 2.5563, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.0904907310078626e-05, | |
| "loss": 2.574, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.0420432368711195e-05, | |
| "loss": 2.5599, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.9940998219130004e-05, | |
| "loss": 2.5991, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.946663523003136e-05, | |
| "loss": 2.5622, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.8997373448890154e-05, | |
| "loss": 2.5672, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.853324260005649e-05, | |
| "loss": 2.5733, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.8074272082873023e-05, | |
| "loss": 2.5602, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.762049096981243e-05, | |
| "loss": 2.6033, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.7171928004636205e-05, | |
| "loss": 2.5874, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.42740302882266734, | |
| "eval_loss": 3.416874885559082, | |
| "eval_runtime": 166.1443, | |
| "eval_samples_per_second": 6.019, | |
| "eval_steps_per_second": 3.009, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.672861160057373e-05, | |
| "loss": 2.5585, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.6290569838522605e-05, | |
| "loss": 2.6195, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.585783046526984e-05, | |
| "loss": 2.5723, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.5430420891734422e-05, | |
| "loss": 2.5354, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.500836819123086e-05, | |
| "loss": 2.5736, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4591699097754541e-05, | |
| "loss": 2.5509, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4180440004287954e-05, | |
| "loss": 2.5864, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.3774616961129284e-05, | |
| "loss": 2.5337, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.3374255674242031e-05, | |
| "loss": 2.5268, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.2979381503626842e-05, | |
| "loss": 2.5555, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.42858915486077187, | |
| "eval_loss": 3.4067070484161377, | |
| "eval_runtime": 152.5339, | |
| "eval_samples_per_second": 6.556, | |
| "eval_steps_per_second": 3.278, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.2590019461715118e-05, | |
| "loss": 2.5291, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.2206194211784615e-05, | |
| "loss": 2.5592, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.182793006639732e-05, | |
| "loss": 2.535, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1455250985859277e-05, | |
| "loss": 2.5476, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1088180576702967e-05, | |
| "loss": 2.5339, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.0726742090191965e-05, | |
| "loss": 2.5451, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.037095842084822e-05, | |
| "loss": 2.5518, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.0020852105001677e-05, | |
| "loss": 2.5064, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.676445319362993e-06, | |
| "loss": 2.5714, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.337759879618601e-06, | |
| "loss": 2.5502, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.42984025403028825, | |
| "eval_loss": 3.3996939659118652, | |
| "eval_runtime": 152.8547, | |
| "eval_samples_per_second": 6.542, | |
| "eval_steps_per_second": 3.271, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.004817239048968e-06, | |
| "loss": 2.5244, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.677638487169614e-06, | |
| "loss": 2.5521, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.356244348395304e-06, | |
| "loss": 2.5726, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.04065518072723e-06, | |
| "loss": 2.538, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.730890974463601e-06, | |
| "loss": 2.5026, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.42697135093321e-06, | |
| "loss": 2.5445, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.1289155612527805e-06, | |
| "loss": 2.5331, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.836742485107383e-06, | |
| "loss": 2.5293, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.55047062955465e-06, | |
| "loss": 2.4755, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.270118127852376e-06, | |
| "loss": 2.5232, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.4302408402540303, | |
| "eval_loss": 3.3945846557617188, | |
| "eval_runtime": 153.7116, | |
| "eval_samples_per_second": 6.506, | |
| "eval_steps_per_second": 3.253, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.995702738310038e-06, | |
| "loss": 2.5161, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.727241843163822e-06, | |
| "loss": 2.5739, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.464752447475685e-06, | |
| "loss": 2.5553, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.208251178056056e-06, | |
| "loss": 2.5469, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.9577542824108535e-06, | |
| "loss": 2.5504, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.713277627712143e-06, | |
| "loss": 2.57, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.474836699793139e-06, | |
| "loss": 2.5595, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.242446602167361e-06, | |
| "loss": 2.5876, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.016122055071725e-06, | |
| "loss": 2.5513, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.795877394534386e-06, | |
| "loss": 2.5369, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.4308510014655594, | |
| "eval_loss": 3.3898189067840576, | |
| "eval_runtime": 153.5134, | |
| "eval_samples_per_second": 6.514, | |
| "eval_steps_per_second": 3.257, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.5817265714664592e-06, | |
| "loss": 2.5822, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.373683150778406e-06, | |
| "loss": 2.5611, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.171760310520788e-06, | |
| "loss": 2.5626, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.975970841049569e-06, | |
| "loss": 2.5263, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.786327144215817e-06, | |
| "loss": 2.5412, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.6028412325802887e-06, | |
| "loss": 2.5721, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.4255247286524286e-06, | |
| "loss": 2.5137, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.254388864154189e-06, | |
| "loss": 2.5477, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.0894444793085664e-06, | |
| "loss": 2.5345, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.930702022152975e-06, | |
| "loss": 2.5335, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.43129213483146067, | |
| "eval_loss": 3.386915445327759, | |
| "eval_runtime": 152.6319, | |
| "eval_samples_per_second": 6.552, | |
| "eval_steps_per_second": 3.276, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.7781715478774497e-06, | |
| "loss": 2.5494, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.6318627181876933e-06, | |
| "loss": 2.5837, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.4917848006930413e-06, | |
| "loss": 2.5224, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.357946668319554e-06, | |
| "loss": 2.5507, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.2303567987478336e-06, | |
| "loss": 2.5112, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.1090232738760975e-06, | |
| "loss": 2.5139, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.939537793082654e-07, | |
| "loss": 2.5593, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 8.851556038670828e-07, | |
| "loss": 2.5327, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.826356391324341e-07, | |
| "loss": 2.5504, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6.864003790048923e-07, | |
| "loss": 2.6032, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.431466536394724, | |
| "eval_loss": 3.38529109954834, | |
| "eval_runtime": 155.9485, | |
| "eval_samples_per_second": 6.412, | |
| "eval_steps_per_second": 3.206, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.964559192942142e-07, | |
| "loss": 2.5262, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.128079573333943e-07, | |
| "loss": 2.5585, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.3546179161765287e-07, | |
| "loss": 2.4912, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.6442232146886024e-07, | |
| "loss": 2.5106, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.996940467252185e-07, | |
| "loss": 2.5446, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.412810674562005e-07, | |
| "loss": 2.5244, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.8918708370283532e-07, | |
| "loss": 2.5743, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.4341539524337366e-07, | |
| "loss": 2.5332, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.0396890138422155e-07, | |
| "loss": 2.5329, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.08501007763207e-08, | |
| "loss": 2.5244, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.43141182217879825, | |
| "eval_loss": 3.3849878311157227, | |
| "eval_runtime": 153.9769, | |
| "eval_samples_per_second": 6.494, | |
| "eval_steps_per_second": 3.247, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.406109125690838e-08, | |
| "loss": 2.5568, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.3603569716545982e-08, | |
| "loss": 2.5507, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.478831991716064e-09, | |
| "loss": 2.5186, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.687772782721364e-09, | |
| "loss": 2.5194, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 40473, | |
| "total_flos": 3.382987152257188e+17, | |
| "train_loss": 3.073313300175377, | |
| "train_runtime": 120576.6781, | |
| "train_samples_per_second": 2.685, | |
| "train_steps_per_second": 0.336 | |
| } | |
| ], | |
| "max_steps": 40473, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.382987152257188e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |