| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 8680, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.971198156682028e-05, | |
| "loss": 0.3578, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.9423963133640554e-05, | |
| "loss": 0.2849, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.913594470046083e-05, | |
| "loss": 0.2763, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.8847926267281106e-05, | |
| "loss": 0.2625, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.8559907834101385e-05, | |
| "loss": 0.2641, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.827188940092166e-05, | |
| "loss": 0.2656, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.7983870967741937e-05, | |
| "loss": 0.2574, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.7695852534562216e-05, | |
| "loss": 0.262, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.7407834101382495e-05, | |
| "loss": 0.2602, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.711981566820277e-05, | |
| "loss": 0.2536, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.9346613714140859, | |
| "eval_f1": 0.037628278221208664, | |
| "eval_loss": 0.24692244827747345, | |
| "eval_precision": 0.08139013452914798, | |
| "eval_recall": 0.024470810300660645, | |
| "eval_runtime": 11.142, | |
| "eval_samples_per_second": 359.002, | |
| "eval_steps_per_second": 44.875, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.6831797235023047e-05, | |
| "loss": 0.2516, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.654377880184332e-05, | |
| "loss": 0.251, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.62557603686636e-05, | |
| "loss": 0.2515, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.596774193548387e-05, | |
| "loss": 0.247, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.567972350230415e-05, | |
| "loss": 0.251, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.539170506912442e-05, | |
| "loss": 0.26, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.51036866359447e-05, | |
| "loss": 0.2465, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.4815668202764974e-05, | |
| "loss": 0.2415, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.452764976958525e-05, | |
| "loss": 0.238, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.423963133640553e-05, | |
| "loss": 0.2316, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_accuracy": 0.935907727407157, | |
| "eval_f1": 0.13649655692859164, | |
| "eval_loss": 0.23386752605438232, | |
| "eval_precision": 0.22722989949748743, | |
| "eval_recall": 0.09754617769987865, | |
| "eval_runtime": 11.2428, | |
| "eval_samples_per_second": 355.782, | |
| "eval_steps_per_second": 44.473, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.395161290322581e-05, | |
| "loss": 0.2301, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.366359447004609e-05, | |
| "loss": 0.226, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.337557603686636e-05, | |
| "loss": 0.2298, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.308755760368664e-05, | |
| "loss": 0.2252, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.2799539170506915e-05, | |
| "loss": 0.2249, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.2511520737327194e-05, | |
| "loss": 0.2285, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.2223502304147466e-05, | |
| "loss": 0.2189, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.1935483870967746e-05, | |
| "loss": 0.2256, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.164746543778802e-05, | |
| "loss": 0.2247, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.13594470046083e-05, | |
| "loss": 0.2175, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_accuracy": 0.9391926148126241, | |
| "eval_f1": 0.18226781461806188, | |
| "eval_loss": 0.21722067892551422, | |
| "eval_precision": 0.2842045129962868, | |
| "eval_recall": 0.13415127410004044, | |
| "eval_runtime": 11.2492, | |
| "eval_samples_per_second": 355.579, | |
| "eval_steps_per_second": 44.447, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.107142857142857e-05, | |
| "loss": 0.2143, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 4.078341013824885e-05, | |
| "loss": 0.2157, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.049539170506912e-05, | |
| "loss": 0.216, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 4.02073732718894e-05, | |
| "loss": 0.2156, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.991935483870968e-05, | |
| "loss": 0.2038, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.963133640552996e-05, | |
| "loss": 0.1842, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.934331797235023e-05, | |
| "loss": 0.1829, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.905529953917051e-05, | |
| "loss": 0.1812, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 3.876728110599078e-05, | |
| "loss": 0.1802, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 3.847926267281106e-05, | |
| "loss": 0.1757, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_accuracy": 0.9438294816004056, | |
| "eval_f1": 0.31225296442687744, | |
| "eval_loss": 0.19787320494651794, | |
| "eval_precision": 0.40110006346519994, | |
| "eval_recall": 0.25562896049615746, | |
| "eval_runtime": 11.3248, | |
| "eval_samples_per_second": 353.209, | |
| "eval_steps_per_second": 44.151, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 3.819124423963134e-05, | |
| "loss": 0.1801, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 3.7903225806451614e-05, | |
| "loss": 0.1779, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.761520737327189e-05, | |
| "loss": 0.1743, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.7327188940092166e-05, | |
| "loss": 0.1733, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.7039170506912445e-05, | |
| "loss": 0.1717, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.675115207373272e-05, | |
| "loss": 0.1721, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.6463133640552996e-05, | |
| "loss": 0.1713, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.6175115207373276e-05, | |
| "loss": 0.1699, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.5887096774193555e-05, | |
| "loss": 0.1656, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.559907834101383e-05, | |
| "loss": 0.1682, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.9502196966496261, | |
| "eval_f1": 0.3911483253588517, | |
| "eval_loss": 0.18166299164295197, | |
| "eval_precision": 0.4787234042553192, | |
| "eval_recall": 0.3306592962114062, | |
| "eval_runtime": 11.6137, | |
| "eval_samples_per_second": 344.421, | |
| "eval_steps_per_second": 43.053, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.5311059907834107e-05, | |
| "loss": 0.1664, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.502304147465438e-05, | |
| "loss": 0.1616, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.473502304147466e-05, | |
| "loss": 0.129, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.444700460829493e-05, | |
| "loss": 0.1245, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 3.415898617511521e-05, | |
| "loss": 0.1237, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.387096774193548e-05, | |
| "loss": 0.1235, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.358294930875576e-05, | |
| "loss": 0.1238, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.3294930875576034e-05, | |
| "loss": 0.1225, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.300691244239631e-05, | |
| "loss": 0.1268, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 3.271889400921659e-05, | |
| "loss": 0.121, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_accuracy": 0.9536841438168068, | |
| "eval_f1": 0.450363008114299, | |
| "eval_loss": 0.17527730762958527, | |
| "eval_precision": 0.5309896548567243, | |
| "eval_recall": 0.39099366320614803, | |
| "eval_runtime": 11.2537, | |
| "eval_samples_per_second": 355.44, | |
| "eval_steps_per_second": 44.43, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 3.2430875576036865e-05, | |
| "loss": 0.1235, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.1257, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 3.185483870967742e-05, | |
| "loss": 0.1187, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 3.15668202764977e-05, | |
| "loss": 0.1227, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 3.1278801843317975e-05, | |
| "loss": 0.1204, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 3.0990783410138254e-05, | |
| "loss": 0.1228, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 3.0702764976958526e-05, | |
| "loss": 0.1189, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 3.0414746543778806e-05, | |
| "loss": 0.1206, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 3.0126728110599078e-05, | |
| "loss": 0.1197, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.9838709677419357e-05, | |
| "loss": 0.0982, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_accuracy": 0.9555959271621107, | |
| "eval_f1": 0.4979952786000675, | |
| "eval_loss": 0.18066732585430145, | |
| "eval_precision": 0.5606175651733738, | |
| "eval_recall": 0.4479573951732506, | |
| "eval_runtime": 11.3416, | |
| "eval_samples_per_second": 352.685, | |
| "eval_steps_per_second": 44.086, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.955069124423963e-05, | |
| "loss": 0.0831, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 2.926267281105991e-05, | |
| "loss": 0.0855, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 2.8974654377880185e-05, | |
| "loss": 0.0819, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 2.8686635944700464e-05, | |
| "loss": 0.0864, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 2.8398617511520736e-05, | |
| "loss": 0.0846, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.8110599078341016e-05, | |
| "loss": 0.0854, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.7822580645161288e-05, | |
| "loss": 0.0852, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 2.7534562211981567e-05, | |
| "loss": 0.0828, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 2.7246543778801846e-05, | |
| "loss": 0.0855, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 2.6958525345622122e-05, | |
| "loss": 0.0858, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "eval_accuracy": 0.9576767079302041, | |
| "eval_f1": 0.5303679621693512, | |
| "eval_loss": 0.1731788069009781, | |
| "eval_precision": 0.5867255190452836, | |
| "eval_recall": 0.4838883645678846, | |
| "eval_runtime": 11.3506, | |
| "eval_samples_per_second": 352.406, | |
| "eval_steps_per_second": 44.051, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.66705069124424e-05, | |
| "loss": 0.0867, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 2.6382488479262674e-05, | |
| "loss": 0.0872, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 2.6094470046082953e-05, | |
| "loss": 0.0844, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 2.5806451612903226e-05, | |
| "loss": 0.0877, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2.5518433179723505e-05, | |
| "loss": 0.0837, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 2.523041474654378e-05, | |
| "loss": 0.0827, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 2.4942396313364056e-05, | |
| "loss": 0.054, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 2.4654377880184332e-05, | |
| "loss": 0.0576, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 2.436635944700461e-05, | |
| "loss": 0.0581, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 2.4078341013824887e-05, | |
| "loss": 0.0563, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "eval_accuracy": 0.9584794456884532, | |
| "eval_f1": 0.5548340286595319, | |
| "eval_loss": 0.1838800460100174, | |
| "eval_precision": 0.6006598067708743, | |
| "eval_recall": 0.5155049211271403, | |
| "eval_runtime": 11.156, | |
| "eval_samples_per_second": 358.552, | |
| "eval_steps_per_second": 44.819, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2.3790322580645163e-05, | |
| "loss": 0.0598, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.350230414746544e-05, | |
| "loss": 0.0585, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 2.3214285714285715e-05, | |
| "loss": 0.0564, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 2.2926267281105994e-05, | |
| "loss": 0.0571, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 2.263824884792627e-05, | |
| "loss": 0.0615, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 2.2350230414746546e-05, | |
| "loss": 0.0584, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 2.206221198156682e-05, | |
| "loss": 0.0589, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 2.1774193548387097e-05, | |
| "loss": 0.0591, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 2.1486175115207373e-05, | |
| "loss": 0.0609, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 2.1198156682027652e-05, | |
| "loss": 0.0586, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "eval_accuracy": 0.9605179771008492, | |
| "eval_f1": 0.569084249084249, | |
| "eval_loss": 0.18037766218185425, | |
| "eval_precision": 0.6231349270014439, | |
| "eval_recall": 0.5236618578940272, | |
| "eval_runtime": 11.0173, | |
| "eval_samples_per_second": 363.066, | |
| "eval_steps_per_second": 45.383, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 2.0910138248847928e-05, | |
| "loss": 0.0608, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 2.0622119815668204e-05, | |
| "loss": 0.0583, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.033410138248848e-05, | |
| "loss": 0.0597, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 2.0046082949308755e-05, | |
| "loss": 0.0591, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.975806451612903e-05, | |
| "loss": 0.0422, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 1.9470046082949307e-05, | |
| "loss": 0.037, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1.9182027649769586e-05, | |
| "loss": 0.0387, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 1.8894009216589862e-05, | |
| "loss": 0.0425, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 1.860599078341014e-05, | |
| "loss": 0.0407, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 1.8317972350230417e-05, | |
| "loss": 0.0404, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "eval_accuracy": 0.9598631120875407, | |
| "eval_f1": 0.5791728159533494, | |
| "eval_loss": 0.1948222666978836, | |
| "eval_precision": 0.6213794701475245, | |
| "eval_recall": 0.5423351759471484, | |
| "eval_runtime": 11.5255, | |
| "eval_samples_per_second": 347.055, | |
| "eval_steps_per_second": 43.382, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.8029953917050693e-05, | |
| "loss": 0.0421, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 1.774193548387097e-05, | |
| "loss": 0.04, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1.7453917050691245e-05, | |
| "loss": 0.0412, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.7165898617511524e-05, | |
| "loss": 0.0397, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.68778801843318e-05, | |
| "loss": 0.0435, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 1.6589861751152075e-05, | |
| "loss": 0.0396, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.630184331797235e-05, | |
| "loss": 0.0428, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1.6013824884792627e-05, | |
| "loss": 0.0383, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1.5725806451612903e-05, | |
| "loss": 0.0426, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 1.543778801843318e-05, | |
| "loss": 0.0397, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "eval_accuracy": 0.9610460940470658, | |
| "eval_f1": 0.5852459608920374, | |
| "eval_loss": 0.1994314044713974, | |
| "eval_precision": 0.6308735291825762, | |
| "eval_recall": 0.5457732236753404, | |
| "eval_runtime": 11.4564, | |
| "eval_samples_per_second": 349.151, | |
| "eval_steps_per_second": 43.644, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 1.5149769585253456e-05, | |
| "loss": 0.0386, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 1.4861751152073732e-05, | |
| "loss": 0.0339, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1.457373271889401e-05, | |
| "loss": 0.0269, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.028, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 1.3997695852534561e-05, | |
| "loss": 0.0257, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 1.3709677419354839e-05, | |
| "loss": 0.0281, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.3421658986175115e-05, | |
| "loss": 0.0269, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 1.313364055299539e-05, | |
| "loss": 0.0253, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 1.284562211981567e-05, | |
| "loss": 0.0274, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 1.2557603686635947e-05, | |
| "loss": 0.0281, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_accuracy": 0.9610460940470658, | |
| "eval_f1": 0.5931138477004273, | |
| "eval_loss": 0.21313945949077606, | |
| "eval_precision": 0.6344573315922882, | |
| "eval_recall": 0.556828906565997, | |
| "eval_runtime": 11.2791, | |
| "eval_samples_per_second": 354.637, | |
| "eval_steps_per_second": 44.33, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 1.2269585253456221e-05, | |
| "loss": 0.0263, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 1.1981566820276497e-05, | |
| "loss": 0.0255, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 1.1693548387096775e-05, | |
| "loss": 0.0279, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 1.1405529953917052e-05, | |
| "loss": 0.0286, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 1.1117511520737328e-05, | |
| "loss": 0.0281, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.0829493087557604e-05, | |
| "loss": 0.0273, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 1.0541474654377881e-05, | |
| "loss": 0.0271, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.0253456221198157e-05, | |
| "loss": 0.0294, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.965437788018433e-06, | |
| "loss": 0.0271, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.0182, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "eval_accuracy": 0.9625142591575478, | |
| "eval_f1": 0.6047417992854823, | |
| "eval_loss": 0.22494320571422577, | |
| "eval_precision": 0.6506950376640522, | |
| "eval_recall": 0.5648510179317784, | |
| "eval_runtime": 11.2013, | |
| "eval_samples_per_second": 357.1, | |
| "eval_steps_per_second": 44.638, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 9.389400921658986e-06, | |
| "loss": 0.0187, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 9.101382488479262e-06, | |
| "loss": 0.019, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 8.81336405529954e-06, | |
| "loss": 0.0193, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 8.525345622119817e-06, | |
| "loss": 0.0192, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 8.237327188940093e-06, | |
| "loss": 0.0189, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 7.949308755760369e-06, | |
| "loss": 0.0187, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 7.661290322580646e-06, | |
| "loss": 0.0184, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 7.373271889400922e-06, | |
| "loss": 0.0194, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 7.085253456221199e-06, | |
| "loss": 0.02, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 6.7972350230414745e-06, | |
| "loss": 0.0188, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "eval_accuracy": 0.9612467784866281, | |
| "eval_f1": 0.6081037966606403, | |
| "eval_loss": 0.23223160207271576, | |
| "eval_precision": 0.6412710280373832, | |
| "eval_recall": 0.5781987326412296, | |
| "eval_runtime": 11.0711, | |
| "eval_samples_per_second": 361.3, | |
| "eval_steps_per_second": 45.162, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 6.509216589861751e-06, | |
| "loss": 0.0192, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 6.221198156682028e-06, | |
| "loss": 0.019, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 5.9331797235023045e-06, | |
| "loss": 0.0171, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 5.64516129032258e-06, | |
| "loss": 0.0173, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 0.0161, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 5.0691244239631346e-06, | |
| "loss": 0.019, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.78110599078341e-06, | |
| "loss": 0.0153, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 4.493087557603687e-06, | |
| "loss": 0.0141, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 4.205069124423963e-06, | |
| "loss": 0.013, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 3.9170506912442395e-06, | |
| "loss": 0.0123, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "eval_accuracy": 0.9621762643119692, | |
| "eval_f1": 0.6119898596779377, | |
| "eval_loss": 0.24726828932762146, | |
| "eval_precision": 0.6505731420329461, | |
| "eval_recall": 0.5777268437373602, | |
| "eval_runtime": 11.3598, | |
| "eval_samples_per_second": 352.118, | |
| "eval_steps_per_second": 44.015, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 3.6290322580645166e-06, | |
| "loss": 0.0127, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 3.341013824884793e-06, | |
| "loss": 0.014, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 3.052995391705069e-06, | |
| "loss": 0.0135, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 2.7649769585253458e-06, | |
| "loss": 0.0141, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 2.4769585253456224e-06, | |
| "loss": 0.0135, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.1889400921658987e-06, | |
| "loss": 0.0127, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 1.9009216589861754e-06, | |
| "loss": 0.0129, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.6129032258064516e-06, | |
| "loss": 0.0132, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 1.3248847926267283e-06, | |
| "loss": 0.0129, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 1.0368663594470047e-06, | |
| "loss": 0.0123, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "eval_accuracy": 0.961405213570493, | |
| "eval_f1": 0.6081335464393536, | |
| "eval_loss": 0.24913595616817474, | |
| "eval_precision": 0.6426694692590647, | |
| "eval_recall": 0.5771201294323851, | |
| "eval_runtime": 11.5972, | |
| "eval_samples_per_second": 344.912, | |
| "eval_steps_per_second": 43.114, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 7.488479262672811e-07, | |
| "loss": 0.0145, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 4.6082949308755763e-07, | |
| "loss": 0.0129, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 1.728110599078341e-07, | |
| "loss": 0.0134, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 8680, | |
| "total_flos": 4.589148928762742e+16, | |
| "train_loss": 0.015828275546637547, | |
| "train_runtime": 947.6725, | |
| "train_samples_per_second": 586.046, | |
| "train_steps_per_second": 9.159 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 8680, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 4.589148928762742e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |