| { | |
| "best_metric": 0.4240340292453766, | |
| "best_model_checkpoint": "OutModelPolicy/checkpoint-50000", | |
| "epoch": 0.23626586525285173, | |
| "global_step": 50000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9952746826949432e-05, | |
| "loss": 0.4762, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_accuracy": 0.8208744710860366, | |
| "eval_loss": 0.4056582748889923, | |
| "eval_runtime": 129.4288, | |
| "eval_samples_per_second": 82.169, | |
| "eval_steps_per_second": 8.221, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9905493653898863e-05, | |
| "loss": 0.4222, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_accuracy": 0.8309355900329102, | |
| "eval_loss": 0.39738503098487854, | |
| "eval_runtime": 129.5771, | |
| "eval_samples_per_second": 82.075, | |
| "eval_steps_per_second": 8.211, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.985824048084829e-05, | |
| "loss": 0.4226, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.8228490832157969, | |
| "eval_loss": 0.4244444668292999, | |
| "eval_runtime": 129.6288, | |
| "eval_samples_per_second": 82.042, | |
| "eval_steps_per_second": 8.208, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.981098730779772e-05, | |
| "loss": 0.4262, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.7945463093559003, | |
| "eval_loss": 0.4486662447452545, | |
| "eval_runtime": 129.6271, | |
| "eval_samples_per_second": 82.043, | |
| "eval_steps_per_second": 8.208, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.976373413474715e-05, | |
| "loss": 0.3976, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.8334743770568876, | |
| "eval_loss": 0.38648247718811035, | |
| "eval_runtime": 129.6078, | |
| "eval_samples_per_second": 82.055, | |
| "eval_steps_per_second": 8.209, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.971648096169658e-05, | |
| "loss": 0.4094, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.8145745181006112, | |
| "eval_loss": 0.481615275144577, | |
| "eval_runtime": 129.5734, | |
| "eval_samples_per_second": 82.077, | |
| "eval_steps_per_second": 8.212, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.966922778864601e-05, | |
| "loss": 0.4122, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.8160789844851905, | |
| "eval_loss": 0.4006648659706116, | |
| "eval_runtime": 129.6541, | |
| "eval_samples_per_second": 82.026, | |
| "eval_steps_per_second": 8.206, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.962197461559544e-05, | |
| "loss": 0.4086, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.7988716502115656, | |
| "eval_loss": 0.44481590390205383, | |
| "eval_runtime": 129.6035, | |
| "eval_samples_per_second": 82.058, | |
| "eval_steps_per_second": 8.21, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9574721442544867e-05, | |
| "loss": 0.3977, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.8329102021626704, | |
| "eval_loss": 0.38500234484672546, | |
| "eval_runtime": 130.5943, | |
| "eval_samples_per_second": 81.435, | |
| "eval_steps_per_second": 8.147, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9527468269494298e-05, | |
| "loss": 0.4121, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.8235072872590503, | |
| "eval_loss": 0.3987399637699127, | |
| "eval_runtime": 129.9565, | |
| "eval_samples_per_second": 81.835, | |
| "eval_steps_per_second": 8.187, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.948021509644373e-05, | |
| "loss": 0.3913, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.8207804419370005, | |
| "eval_loss": 0.4078373908996582, | |
| "eval_runtime": 129.7026, | |
| "eval_samples_per_second": 81.995, | |
| "eval_steps_per_second": 8.203, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9432961923393156e-05, | |
| "loss": 0.4043, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.8400564174894217, | |
| "eval_loss": 0.40346187353134155, | |
| "eval_runtime": 129.7498, | |
| "eval_samples_per_second": 81.965, | |
| "eval_steps_per_second": 8.2, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9385708750342586e-05, | |
| "loss": 0.3943, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.8372355430183357, | |
| "eval_loss": 0.4044436514377594, | |
| "eval_runtime": 129.5695, | |
| "eval_samples_per_second": 82.079, | |
| "eval_steps_per_second": 8.212, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9338455577292017e-05, | |
| "loss": 0.3951, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.8361071932299012, | |
| "eval_loss": 0.3758731782436371, | |
| "eval_runtime": 129.7099, | |
| "eval_samples_per_second": 81.991, | |
| "eval_steps_per_second": 8.203, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9291202404241447e-05, | |
| "loss": 0.3962, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.8284908321579689, | |
| "eval_loss": 0.41320571303367615, | |
| "eval_runtime": 129.8631, | |
| "eval_samples_per_second": 81.894, | |
| "eval_steps_per_second": 8.193, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9243949231190878e-05, | |
| "loss": 0.3776, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.8282087447108604, | |
| "eval_loss": 0.4154951274394989, | |
| "eval_runtime": 129.934, | |
| "eval_samples_per_second": 81.849, | |
| "eval_steps_per_second": 8.189, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9196696058140305e-05, | |
| "loss": 0.4021, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.8206864127879643, | |
| "eval_loss": 0.4651769697666168, | |
| "eval_runtime": 129.6522, | |
| "eval_samples_per_second": 82.027, | |
| "eval_steps_per_second": 8.207, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9149442885089736e-05, | |
| "loss": 0.4031, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.8377056887635167, | |
| "eval_loss": 0.3797547519207001, | |
| "eval_runtime": 129.7227, | |
| "eval_samples_per_second": 81.983, | |
| "eval_steps_per_second": 8.202, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9102189712039167e-05, | |
| "loss": 0.3971, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.8417489421720733, | |
| "eval_loss": 0.37185046076774597, | |
| "eval_runtime": 129.784, | |
| "eval_samples_per_second": 81.944, | |
| "eval_steps_per_second": 8.198, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9054936538988594e-05, | |
| "loss": 0.4018, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.8419370004701457, | |
| "eval_loss": 0.3951157331466675, | |
| "eval_runtime": 129.8232, | |
| "eval_samples_per_second": 81.919, | |
| "eval_steps_per_second": 8.196, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9007683365938024e-05, | |
| "loss": 0.3894, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.8360131640808651, | |
| "eval_loss": 0.37815341353416443, | |
| "eval_runtime": 130.1142, | |
| "eval_samples_per_second": 81.736, | |
| "eval_steps_per_second": 8.177, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.8960430192887455e-05, | |
| "loss": 0.3947, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.8376116596144805, | |
| "eval_loss": 0.3747114837169647, | |
| "eval_runtime": 129.8229, | |
| "eval_samples_per_second": 81.919, | |
| "eval_steps_per_second": 8.196, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.8913177019836882e-05, | |
| "loss": 0.3968, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.8425952045133992, | |
| "eval_loss": 0.36044278740882874, | |
| "eval_runtime": 129.6945, | |
| "eval_samples_per_second": 82.0, | |
| "eval_steps_per_second": 8.204, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8865923846786313e-05, | |
| "loss": 0.3823, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.8388340385519512, | |
| "eval_loss": 0.39501070976257324, | |
| "eval_runtime": 129.9377, | |
| "eval_samples_per_second": 81.847, | |
| "eval_steps_per_second": 8.189, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8818670673735744e-05, | |
| "loss": 0.3865, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.8396803008932769, | |
| "eval_loss": 0.37278103828430176, | |
| "eval_runtime": 129.7336, | |
| "eval_samples_per_second": 81.976, | |
| "eval_steps_per_second": 8.201, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.877141750068517e-05, | |
| "loss": 0.3895, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.8393041842971322, | |
| "eval_loss": 0.3665693402290344, | |
| "eval_runtime": 129.2422, | |
| "eval_samples_per_second": 82.287, | |
| "eval_steps_per_second": 8.233, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.87241643276346e-05, | |
| "loss": 0.3838, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.7994358251057828, | |
| "eval_loss": 0.4633244574069977, | |
| "eval_runtime": 129.1362, | |
| "eval_samples_per_second": 82.355, | |
| "eval_steps_per_second": 8.239, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8676911154584032e-05, | |
| "loss": 0.3924, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.8404325340855665, | |
| "eval_loss": 0.37671658396720886, | |
| "eval_runtime": 129.0223, | |
| "eval_samples_per_second": 82.428, | |
| "eval_steps_per_second": 8.247, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8629657981533463e-05, | |
| "loss": 0.4017, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.8437235543018335, | |
| "eval_loss": 0.36841943860054016, | |
| "eval_runtime": 130.2328, | |
| "eval_samples_per_second": 81.661, | |
| "eval_steps_per_second": 8.17, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.858240480848289e-05, | |
| "loss": 0.4186, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.8300893276915844, | |
| "eval_loss": 0.39305663108825684, | |
| "eval_runtime": 130.4473, | |
| "eval_samples_per_second": 81.527, | |
| "eval_steps_per_second": 8.157, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.853515163543232e-05, | |
| "loss": 0.3766, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.8358251057827927, | |
| "eval_loss": 0.39709869027137756, | |
| "eval_runtime": 130.0978, | |
| "eval_samples_per_second": 81.746, | |
| "eval_steps_per_second": 8.178, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.848789846238175e-05, | |
| "loss": 0.376, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8409026798307475, | |
| "eval_loss": 0.3675770163536072, | |
| "eval_runtime": 130.1191, | |
| "eval_samples_per_second": 81.733, | |
| "eval_steps_per_second": 8.177, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8440645289331182e-05, | |
| "loss": 0.3981, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8461683121767748, | |
| "eval_loss": 0.36740317940711975, | |
| "eval_runtime": 130.531, | |
| "eval_samples_per_second": 81.475, | |
| "eval_steps_per_second": 8.151, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.839339211628061e-05, | |
| "loss": 0.3805, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8456981664315938, | |
| "eval_loss": 0.3746638894081116, | |
| "eval_runtime": 130.414, | |
| "eval_samples_per_second": 81.548, | |
| "eval_steps_per_second": 8.159, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.834613894323004e-05, | |
| "loss": 0.3878, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8417489421720733, | |
| "eval_loss": 0.38845792412757874, | |
| "eval_runtime": 130.1922, | |
| "eval_samples_per_second": 81.687, | |
| "eval_steps_per_second": 8.173, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.829888577017947e-05, | |
| "loss": 0.3694, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.8435354960037612, | |
| "eval_loss": 0.36394280195236206, | |
| "eval_runtime": 130.5033, | |
| "eval_samples_per_second": 81.492, | |
| "eval_steps_per_second": 8.153, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8251632597128898e-05, | |
| "loss": 0.3937, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.8424071462153268, | |
| "eval_loss": 0.36728155612945557, | |
| "eval_runtime": 130.4243, | |
| "eval_samples_per_second": 81.542, | |
| "eval_steps_per_second": 8.158, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8204379424078328e-05, | |
| "loss": 0.3839, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.847202632816173, | |
| "eval_loss": 0.3707529306411743, | |
| "eval_runtime": 130.4582, | |
| "eval_samples_per_second": 81.52, | |
| "eval_steps_per_second": 8.156, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.815712625102776e-05, | |
| "loss": 0.3912, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.8412787964268923, | |
| "eval_loss": 0.37555885314941406, | |
| "eval_runtime": 130.2205, | |
| "eval_samples_per_second": 81.669, | |
| "eval_steps_per_second": 8.171, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8109873077977186e-05, | |
| "loss": 0.3863, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.8243535496003761, | |
| "eval_loss": 0.41004541516304016, | |
| "eval_runtime": 129.6398, | |
| "eval_samples_per_second": 82.035, | |
| "eval_steps_per_second": 8.207, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8062619904926617e-05, | |
| "loss": 0.3961, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.8417489421720733, | |
| "eval_loss": 0.3776857852935791, | |
| "eval_runtime": 129.4387, | |
| "eval_samples_per_second": 82.162, | |
| "eval_steps_per_second": 8.22, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8015366731876047e-05, | |
| "loss": 0.3933, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.8368594264221909, | |
| "eval_loss": 0.3933545649051666, | |
| "eval_runtime": 129.8078, | |
| "eval_samples_per_second": 81.929, | |
| "eval_steps_per_second": 8.197, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7968113558825478e-05, | |
| "loss": 0.3902, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.8445698166431593, | |
| "eval_loss": 0.3732445240020752, | |
| "eval_runtime": 129.549, | |
| "eval_samples_per_second": 82.092, | |
| "eval_steps_per_second": 8.213, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7920860385774905e-05, | |
| "loss": 0.387, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.8418429713211095, | |
| "eval_loss": 0.3905291259288788, | |
| "eval_runtime": 129.5578, | |
| "eval_samples_per_second": 82.087, | |
| "eval_steps_per_second": 8.213, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7873607212724336e-05, | |
| "loss": 0.3938, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.8378937470615891, | |
| "eval_loss": 0.3706592619419098, | |
| "eval_runtime": 129.5532, | |
| "eval_samples_per_second": 82.09, | |
| "eval_steps_per_second": 8.213, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7826354039673766e-05, | |
| "loss": 0.3879, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.8348848142924307, | |
| "eval_loss": 0.4062308967113495, | |
| "eval_runtime": 129.4397, | |
| "eval_samples_per_second": 82.162, | |
| "eval_steps_per_second": 8.22, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7779100866623197e-05, | |
| "loss": 0.3958, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.8449459332393042, | |
| "eval_loss": 0.3733549416065216, | |
| "eval_runtime": 129.5035, | |
| "eval_samples_per_second": 82.121, | |
| "eval_steps_per_second": 8.216, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7731847693572624e-05, | |
| "loss": 0.4004, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.841560883874001, | |
| "eval_loss": 0.3702126145362854, | |
| "eval_runtime": 130.0684, | |
| "eval_samples_per_second": 81.765, | |
| "eval_steps_per_second": 8.18, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7684594520522055e-05, | |
| "loss": 0.3989, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.8387400094029149, | |
| "eval_loss": 0.3675605356693268, | |
| "eval_runtime": 129.789, | |
| "eval_samples_per_second": 81.941, | |
| "eval_steps_per_second": 8.198, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7637341347471485e-05, | |
| "loss": 0.3993, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.840620592383639, | |
| "eval_loss": 0.3818625509738922, | |
| "eval_runtime": 129.7415, | |
| "eval_samples_per_second": 81.971, | |
| "eval_steps_per_second": 8.201, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7590088174420913e-05, | |
| "loss": 0.4096, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.8440996708979783, | |
| "eval_loss": 0.3813258409500122, | |
| "eval_runtime": 129.9826, | |
| "eval_samples_per_second": 81.819, | |
| "eval_steps_per_second": 8.186, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7542835001370343e-05, | |
| "loss": 0.3963, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.8412787964268923, | |
| "eval_loss": 0.4066058099269867, | |
| "eval_runtime": 129.6744, | |
| "eval_samples_per_second": 82.013, | |
| "eval_steps_per_second": 8.205, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.749558182831977e-05, | |
| "loss": 0.3901, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.8412787964268923, | |
| "eval_loss": 0.3806789815425873, | |
| "eval_runtime": 129.8481, | |
| "eval_samples_per_second": 81.903, | |
| "eval_steps_per_second": 8.194, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.74483286552692e-05, | |
| "loss": 0.3953, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.8321579689703809, | |
| "eval_loss": 0.40024057030677795, | |
| "eval_runtime": 130.2566, | |
| "eval_samples_per_second": 81.647, | |
| "eval_steps_per_second": 8.168, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7401075482218632e-05, | |
| "loss": 0.3813, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.8381758345086977, | |
| "eval_loss": 0.41771912574768066, | |
| "eval_runtime": 130.3445, | |
| "eval_samples_per_second": 81.591, | |
| "eval_steps_per_second": 8.163, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7353822309168062e-05, | |
| "loss": 0.4054, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.8449459332393042, | |
| "eval_loss": 0.382539838552475, | |
| "eval_runtime": 131.7654, | |
| "eval_samples_per_second": 80.712, | |
| "eval_steps_per_second": 8.075, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7306569136117493e-05, | |
| "loss": 0.3923, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.8414668547249647, | |
| "eval_loss": 0.3951680660247803, | |
| "eval_runtime": 131.5566, | |
| "eval_samples_per_second": 80.84, | |
| "eval_steps_per_second": 8.088, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.725931596306692e-05, | |
| "loss": 0.3866, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.8458862247296662, | |
| "eval_loss": 0.37791889905929565, | |
| "eval_runtime": 131.2917, | |
| "eval_samples_per_second": 81.003, | |
| "eval_steps_per_second": 8.104, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.721206279001635e-05, | |
| "loss": 0.4034, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.841560883874001, | |
| "eval_loss": 0.3799465000629425, | |
| "eval_runtime": 131.3633, | |
| "eval_samples_per_second": 80.959, | |
| "eval_steps_per_second": 8.1, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.716480961696578e-05, | |
| "loss": 0.4031, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.8417489421720733, | |
| "eval_loss": 0.38024023175239563, | |
| "eval_runtime": 131.3154, | |
| "eval_samples_per_second": 80.988, | |
| "eval_steps_per_second": 8.103, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7117556443915212e-05, | |
| "loss": 0.3877, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.8460742830277386, | |
| "eval_loss": 0.4047398865222931, | |
| "eval_runtime": 131.4081, | |
| "eval_samples_per_second": 80.931, | |
| "eval_steps_per_second": 8.097, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.707030327086464e-05, | |
| "loss": 0.3992, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.8449459332393042, | |
| "eval_loss": 0.38162681460380554, | |
| "eval_runtime": 131.6095, | |
| "eval_samples_per_second": 80.807, | |
| "eval_steps_per_second": 8.085, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.702305009781407e-05, | |
| "loss": 0.3939, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.8371415138692995, | |
| "eval_loss": 0.3953230679035187, | |
| "eval_runtime": 131.4077, | |
| "eval_samples_per_second": 80.931, | |
| "eval_steps_per_second": 8.097, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.69757969247635e-05, | |
| "loss": 0.3932, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.8424071462153268, | |
| "eval_loss": 0.38043248653411865, | |
| "eval_runtime": 131.6206, | |
| "eval_samples_per_second": 80.8, | |
| "eval_steps_per_second": 8.084, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.6928543751712928e-05, | |
| "loss": 0.4007, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.8237893747061589, | |
| "eval_loss": 0.3933298885822296, | |
| "eval_runtime": 131.4411, | |
| "eval_samples_per_second": 80.911, | |
| "eval_steps_per_second": 8.095, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.688129057866236e-05, | |
| "loss": 0.3818, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8447578749412318, | |
| "eval_loss": 0.3810153007507324, | |
| "eval_runtime": 131.6712, | |
| "eval_samples_per_second": 80.769, | |
| "eval_steps_per_second": 8.081, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6834037405611786e-05, | |
| "loss": 0.3991, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.841560883874001, | |
| "eval_loss": 0.4047435522079468, | |
| "eval_runtime": 131.767, | |
| "eval_samples_per_second": 80.711, | |
| "eval_steps_per_second": 8.075, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6786784232561216e-05, | |
| "loss": 0.3846, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8440056417489422, | |
| "eval_loss": 0.4012466073036194, | |
| "eval_runtime": 131.9637, | |
| "eval_samples_per_second": 80.59, | |
| "eval_steps_per_second": 8.063, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6739531059510647e-05, | |
| "loss": 0.3996, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8458862247296662, | |
| "eval_loss": 0.37191182374954224, | |
| "eval_runtime": 131.5827, | |
| "eval_samples_per_second": 80.824, | |
| "eval_steps_per_second": 8.086, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6692277886460078e-05, | |
| "loss": 0.3843, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.8440996708979783, | |
| "eval_loss": 0.3639690577983856, | |
| "eval_runtime": 131.6893, | |
| "eval_samples_per_second": 80.758, | |
| "eval_steps_per_second": 8.08, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6645024713409508e-05, | |
| "loss": 0.3898, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.8440056417489422, | |
| "eval_loss": 0.3992905914783478, | |
| "eval_runtime": 131.8229, | |
| "eval_samples_per_second": 80.676, | |
| "eval_steps_per_second": 8.071, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6597771540358936e-05, | |
| "loss": 0.4085, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.8452280206864128, | |
| "eval_loss": 0.3788784146308899, | |
| "eval_runtime": 131.7208, | |
| "eval_samples_per_second": 80.739, | |
| "eval_steps_per_second": 8.078, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6550518367308366e-05, | |
| "loss": 0.3983, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.846262341325811, | |
| "eval_loss": 0.3754882216453552, | |
| "eval_runtime": 131.8254, | |
| "eval_samples_per_second": 80.675, | |
| "eval_steps_per_second": 8.071, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6503265194257797e-05, | |
| "loss": 0.3937, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.84579219558063, | |
| "eval_loss": 0.45100608468055725, | |
| "eval_runtime": 131.8006, | |
| "eval_samples_per_second": 80.69, | |
| "eval_steps_per_second": 8.073, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6456012021207227e-05, | |
| "loss": 0.3915, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.8451339915373766, | |
| "eval_loss": 0.38479360938072205, | |
| "eval_runtime": 131.7637, | |
| "eval_samples_per_second": 80.713, | |
| "eval_steps_per_second": 8.075, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6408758848156655e-05, | |
| "loss": 0.3839, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.847202632816173, | |
| "eval_loss": 0.3964824974536896, | |
| "eval_runtime": 132.0608, | |
| "eval_samples_per_second": 80.531, | |
| "eval_steps_per_second": 8.057, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6361505675106085e-05, | |
| "loss": 0.3827, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.841560883874001, | |
| "eval_loss": 0.38886380195617676, | |
| "eval_runtime": 131.6557, | |
| "eval_samples_per_second": 80.779, | |
| "eval_steps_per_second": 8.082, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6314252502055516e-05, | |
| "loss": 0.3978, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.8442877291960508, | |
| "eval_loss": 0.38106653094291687, | |
| "eval_runtime": 131.916, | |
| "eval_samples_per_second": 80.619, | |
| "eval_steps_per_second": 8.066, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6266999329004943e-05, | |
| "loss": 0.3952, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.844851904090268, | |
| "eval_loss": 0.37970393896102905, | |
| "eval_runtime": 131.7319, | |
| "eval_samples_per_second": 80.732, | |
| "eval_steps_per_second": 8.077, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6219746155954374e-05, | |
| "loss": 0.3808, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.8430653502585802, | |
| "eval_loss": 0.40946319699287415, | |
| "eval_runtime": 131.7637, | |
| "eval_samples_per_second": 80.713, | |
| "eval_steps_per_second": 8.075, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.61724929829038e-05, | |
| "loss": 0.4109, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.8444757874941232, | |
| "eval_loss": 0.4174724221229553, | |
| "eval_runtime": 131.8451, | |
| "eval_samples_per_second": 80.663, | |
| "eval_steps_per_second": 8.07, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.612523980985323e-05, | |
| "loss": 0.4044, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.8441937000470146, | |
| "eval_loss": 0.41217777132987976, | |
| "eval_runtime": 131.8589, | |
| "eval_samples_per_second": 80.654, | |
| "eval_steps_per_second": 8.069, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6077986636802662e-05, | |
| "loss": 0.3964, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.8419370004701457, | |
| "eval_loss": 0.42735016345977783, | |
| "eval_runtime": 132.1503, | |
| "eval_samples_per_second": 80.477, | |
| "eval_steps_per_second": 8.051, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6030733463752093e-05, | |
| "loss": 0.3893, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.8400564174894217, | |
| "eval_loss": 0.43243229389190674, | |
| "eval_runtime": 132.2918, | |
| "eval_samples_per_second": 80.39, | |
| "eval_steps_per_second": 8.043, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.5983480290701524e-05, | |
| "loss": 0.4066, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.8435354960037612, | |
| "eval_loss": 0.4005473852157593, | |
| "eval_runtime": 132.1435, | |
| "eval_samples_per_second": 80.481, | |
| "eval_steps_per_second": 8.052, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.593622711765095e-05, | |
| "loss": 0.3937, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.8441937000470146, | |
| "eval_loss": 0.40180185437202454, | |
| "eval_runtime": 132.509, | |
| "eval_samples_per_second": 80.259, | |
| "eval_steps_per_second": 8.03, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.588897394460038e-05, | |
| "loss": 0.3865, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.8450399623883403, | |
| "eval_loss": 0.37694165110588074, | |
| "eval_runtime": 132.3417, | |
| "eval_samples_per_second": 80.36, | |
| "eval_steps_per_second": 8.04, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5841720771549812e-05, | |
| "loss": 0.3845, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.8468265162200282, | |
| "eval_loss": 0.4909285604953766, | |
| "eval_runtime": 132.4872, | |
| "eval_samples_per_second": 80.272, | |
| "eval_steps_per_second": 8.031, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5794467598499243e-05, | |
| "loss": 0.4027, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.8445698166431593, | |
| "eval_loss": 0.38147443532943726, | |
| "eval_runtime": 132.3614, | |
| "eval_samples_per_second": 80.348, | |
| "eval_steps_per_second": 8.039, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.574721442544867e-05, | |
| "loss": 0.3842, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.8464503996238834, | |
| "eval_loss": 0.402163028717041, | |
| "eval_runtime": 132.5083, | |
| "eval_samples_per_second": 80.259, | |
| "eval_steps_per_second": 8.03, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.56999612523981e-05, | |
| "loss": 0.3986, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.8469205453690644, | |
| "eval_loss": 0.38845333456993103, | |
| "eval_runtime": 132.293, | |
| "eval_samples_per_second": 80.39, | |
| "eval_steps_per_second": 8.043, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.565270807934753e-05, | |
| "loss": 0.3945, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.847672778561354, | |
| "eval_loss": 0.3806135058403015, | |
| "eval_runtime": 132.4246, | |
| "eval_samples_per_second": 80.31, | |
| "eval_steps_per_second": 8.035, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.560545490629696e-05, | |
| "loss": 0.3903, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.847672778561354, | |
| "eval_loss": 0.39041149616241455, | |
| "eval_runtime": 132.5258, | |
| "eval_samples_per_second": 80.249, | |
| "eval_steps_per_second": 8.029, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.555820173324639e-05, | |
| "loss": 0.3925, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.8421250587682182, | |
| "eval_loss": 0.38474157452583313, | |
| "eval_runtime": 132.3687, | |
| "eval_samples_per_second": 80.344, | |
| "eval_steps_per_second": 8.038, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5510948560195816e-05, | |
| "loss": 0.3834, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.8451339915373766, | |
| "eval_loss": 0.40873274207115173, | |
| "eval_runtime": 132.4385, | |
| "eval_samples_per_second": 80.301, | |
| "eval_steps_per_second": 8.034, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5463695387145247e-05, | |
| "loss": 0.3874, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.8421250587682182, | |
| "eval_loss": 0.384562224149704, | |
| "eval_runtime": 132.5359, | |
| "eval_samples_per_second": 80.242, | |
| "eval_steps_per_second": 8.028, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5416442214094677e-05, | |
| "loss": 0.3961, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.8428772919605078, | |
| "eval_loss": 0.40740007162094116, | |
| "eval_runtime": 132.6949, | |
| "eval_samples_per_second": 80.146, | |
| "eval_steps_per_second": 8.018, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5369189041044108e-05, | |
| "loss": 0.3885, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.8398683591913493, | |
| "eval_loss": 0.44784700870513916, | |
| "eval_runtime": 132.6686, | |
| "eval_samples_per_second": 80.162, | |
| "eval_steps_per_second": 8.02, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5321935867993535e-05, | |
| "loss": 0.3945, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.8479548660084626, | |
| "eval_loss": 0.36920443177223206, | |
| "eval_runtime": 132.561, | |
| "eval_samples_per_second": 80.227, | |
| "eval_steps_per_second": 8.026, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5274682694942966e-05, | |
| "loss": 0.383, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.8475787494123178, | |
| "eval_loss": 0.4240340292453766, | |
| "eval_runtime": 130.2268, | |
| "eval_samples_per_second": 81.665, | |
| "eval_steps_per_second": 8.17, | |
| "step": 50000 | |
| } | |
| ], | |
| "max_steps": 211626, | |
| "num_train_epochs": 1, | |
| "total_flos": 6.078558166414656e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |