| { | |
| "best_metric": 0.3740881383419037, | |
| "best_model_checkpoint": "/output/bert-base-dutch-cased-mlm-zgt-radpat/checkpoint-215000", | |
| "epoch": 2.9999692760411154, | |
| "global_step": 219696, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.98862063942903e-05, | |
| "loss": 2.2457, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9772412788580583e-05, | |
| "loss": 1.5618, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.965861918287088e-05, | |
| "loss": 1.3494, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.954482557716117e-05, | |
| "loss": 1.2085, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.943103197145146e-05, | |
| "loss": 1.1219, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.931723836574175e-05, | |
| "loss": 1.0672, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.920344476003205e-05, | |
| "loss": 1.019, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.908965115432234e-05, | |
| "loss": 0.9802, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.897585754861263e-05, | |
| "loss": 0.9458, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.886206394290293e-05, | |
| "loss": 0.9108, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.8237946784561654, | |
| "eval_loss": 0.8260091543197632, | |
| "eval_runtime": 2158.7476, | |
| "eval_samples_per_second": 67.939, | |
| "eval_steps_per_second": 16.985, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.874827033719321e-05, | |
| "loss": 0.8877, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.863447673148351e-05, | |
| "loss": 0.8687, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.85206831257738e-05, | |
| "loss": 0.8495, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.840688952006409e-05, | |
| "loss": 0.8388, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.829309591435438e-05, | |
| "loss": 0.8158, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.817930230864468e-05, | |
| "loss": 0.8081, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.806550870293497e-05, | |
| "loss": 0.7942, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.795171509722526e-05, | |
| "loss": 0.7903, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7837921491515556e-05, | |
| "loss": 0.7759, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.772412788580584e-05, | |
| "loss": 0.7611, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.8465949226392128, | |
| "eval_loss": 0.6964662671089172, | |
| "eval_runtime": 2158.1384, | |
| "eval_samples_per_second": 67.958, | |
| "eval_steps_per_second": 16.99, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.761033428009614e-05, | |
| "loss": 0.7551, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.749654067438643e-05, | |
| "loss": 0.7481, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.738274706867672e-05, | |
| "loss": 0.7398, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7268953462967015e-05, | |
| "loss": 0.7328, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.7155159857257306e-05, | |
| "loss": 0.7163, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.7041366251547596e-05, | |
| "loss": 0.712, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.692757264583789e-05, | |
| "loss": 0.7099, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.681377904012818e-05, | |
| "loss": 0.7059, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.669998543441847e-05, | |
| "loss": 0.6952, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6586191828708765e-05, | |
| "loss": 0.6909, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.8575000699065417, | |
| "eval_loss": 0.6342362761497498, | |
| "eval_runtime": 2158.6043, | |
| "eval_samples_per_second": 67.943, | |
| "eval_steps_per_second": 16.986, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6472398222999056e-05, | |
| "loss": 0.6902, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6358604617289346e-05, | |
| "loss": 0.6837, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.624481101157964e-05, | |
| "loss": 0.674, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6131017405869934e-05, | |
| "loss": 0.6747, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.6017223800160224e-05, | |
| "loss": 0.6669, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.5903430194450515e-05, | |
| "loss": 0.6659, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.5789636588740805e-05, | |
| "loss": 0.6612, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.5675842983031096e-05, | |
| "loss": 0.6607, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.556204937732139e-05, | |
| "loss": 0.6516, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.5448255771611684e-05, | |
| "loss": 0.6476, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.8644562505743907, | |
| "eval_loss": 0.5950246453285217, | |
| "eval_runtime": 2156.4823, | |
| "eval_samples_per_second": 68.01, | |
| "eval_steps_per_second": 17.003, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5334462165901974e-05, | |
| "loss": 0.6397, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.522066856019227e-05, | |
| "loss": 0.65, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.510687495448256e-05, | |
| "loss": 0.6432, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.499308134877285e-05, | |
| "loss": 0.6377, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.487928774306314e-05, | |
| "loss": 0.6321, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4765494137353433e-05, | |
| "loss": 0.63, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4651700531643724e-05, | |
| "loss": 0.6247, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.453790692593402e-05, | |
| "loss": 0.6309, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.442411332022431e-05, | |
| "loss": 0.6249, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.43103197145146e-05, | |
| "loss": 0.6201, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.8697080298884816, | |
| "eval_loss": 0.568393349647522, | |
| "eval_runtime": 2156.1617, | |
| "eval_samples_per_second": 68.02, | |
| "eval_steps_per_second": 17.005, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.41965261088049e-05, | |
| "loss": 0.6113, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.408273250309518e-05, | |
| "loss": 0.6106, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.396893889738548e-05, | |
| "loss": 0.6125, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.385514529167577e-05, | |
| "loss": 0.6086, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.374135168596606e-05, | |
| "loss": 0.6058, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.362755808025636e-05, | |
| "loss": 0.5997, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.351376447454665e-05, | |
| "loss": 0.5993, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.339997086883694e-05, | |
| "loss": 0.5941, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.328617726312723e-05, | |
| "loss": 0.5986, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.317238365741753e-05, | |
| "loss": 0.599, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.8734989669528743, | |
| "eval_loss": 0.5458448529243469, | |
| "eval_runtime": 2154.762, | |
| "eval_samples_per_second": 68.065, | |
| "eval_steps_per_second": 17.016, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.305859005170781e-05, | |
| "loss": 0.5963, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.294479644599811e-05, | |
| "loss": 0.5888, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.28310028402884e-05, | |
| "loss": 0.5874, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.271720923457869e-05, | |
| "loss": 0.5874, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.260341562886899e-05, | |
| "loss": 0.5826, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.248962202315928e-05, | |
| "loss": 0.5841, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.237582841744957e-05, | |
| "loss": 0.5787, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.226203481173986e-05, | |
| "loss": 0.586, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2148241206030156e-05, | |
| "loss": 0.575, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.203444760032044e-05, | |
| "loss": 0.5736, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.8767297871240187, | |
| "eval_loss": 0.5289933681488037, | |
| "eval_runtime": 2154.7351, | |
| "eval_samples_per_second": 68.065, | |
| "eval_steps_per_second": 17.016, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.192065399461074e-05, | |
| "loss": 0.5777, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.1806860388901034e-05, | |
| "loss": 0.5731, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.169306678319132e-05, | |
| "loss": 0.5643, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.1579273177481615e-05, | |
| "loss": 0.5686, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.1465479571771906e-05, | |
| "loss": 0.5703, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1351685966062196e-05, | |
| "loss": 0.5681, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.1237892360352487e-05, | |
| "loss": 0.5633, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.1124098754642784e-05, | |
| "loss": 0.5637, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.1010305148933074e-05, | |
| "loss": 0.5595, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.0896511543223365e-05, | |
| "loss": 0.562, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.8793699356208747, | |
| "eval_loss": 0.5154067873954773, | |
| "eval_runtime": 2155.4611, | |
| "eval_samples_per_second": 68.043, | |
| "eval_steps_per_second": 17.011, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.078271793751366e-05, | |
| "loss": 0.5635, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.0668924331803946e-05, | |
| "loss": 0.5593, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.055513072609424e-05, | |
| "loss": 0.5502, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.0441337120384534e-05, | |
| "loss": 0.5559, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.0327543514674824e-05, | |
| "loss": 0.5548, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.0213749908965115e-05, | |
| "loss": 0.5526, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.009995630325541e-05, | |
| "loss": 0.5511, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.99861626975457e-05, | |
| "loss": 0.5479, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.987236909183599e-05, | |
| "loss": 0.5484, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.975857548612629e-05, | |
| "loss": 0.5448, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.8815636591304047, | |
| "eval_loss": 0.5042124390602112, | |
| "eval_runtime": 2154.4288, | |
| "eval_samples_per_second": 68.075, | |
| "eval_steps_per_second": 17.019, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9644781880416574e-05, | |
| "loss": 0.5464, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.953098827470687e-05, | |
| "loss": 0.5426, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.941719466899716e-05, | |
| "loss": 0.5408, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.930340106328745e-05, | |
| "loss": 0.5421, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.918960745757775e-05, | |
| "loss": 0.5421, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.907581385186804e-05, | |
| "loss": 0.5427, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.896202024615833e-05, | |
| "loss": 0.5434, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.884822664044862e-05, | |
| "loss": 0.5364, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.873443303473892e-05, | |
| "loss": 0.5382, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.86206394290292e-05, | |
| "loss": 0.5354, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.8837189220054034, | |
| "eval_loss": 0.4926992356777191, | |
| "eval_runtime": 2154.3764, | |
| "eval_samples_per_second": 68.077, | |
| "eval_steps_per_second": 17.019, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.85068458233195e-05, | |
| "loss": 0.5354, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.839305221760979e-05, | |
| "loss": 0.5347, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.827925861190008e-05, | |
| "loss": 0.5345, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.816546500619038e-05, | |
| "loss": 0.5321, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.805167140048067e-05, | |
| "loss": 0.5346, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.793787779477096e-05, | |
| "loss": 0.5316, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.782408418906125e-05, | |
| "loss": 0.5249, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.771029058335154e-05, | |
| "loss": 0.5293, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.759649697764183e-05, | |
| "loss": 0.5262, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.748270337193213e-05, | |
| "loss": 0.5231, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.88523342323253, | |
| "eval_loss": 0.48392435908317566, | |
| "eval_runtime": 2153.8585, | |
| "eval_samples_per_second": 68.093, | |
| "eval_steps_per_second": 17.023, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.736890976622242e-05, | |
| "loss": 0.5265, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.725511616051271e-05, | |
| "loss": 0.5316, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.7141322554803006e-05, | |
| "loss": 0.5224, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.7027528949093296e-05, | |
| "loss": 0.5221, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.691373534338359e-05, | |
| "loss": 0.5216, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.679994173767388e-05, | |
| "loss": 0.5193, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.668614813196417e-05, | |
| "loss": 0.5201, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.657235452625446e-05, | |
| "loss": 0.5174, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.6458560920544756e-05, | |
| "loss": 0.5158, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.6344767314835046e-05, | |
| "loss": 0.5145, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.8870722746070282, | |
| "eval_loss": 0.47552376985549927, | |
| "eval_runtime": 2156.2198, | |
| "eval_samples_per_second": 68.019, | |
| "eval_steps_per_second": 17.005, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6230973709125337e-05, | |
| "loss": 0.5135, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6117180103415634e-05, | |
| "loss": 0.5207, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.600338649770592e-05, | |
| "loss": 0.5184, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.5889592891996215e-05, | |
| "loss": 0.5129, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.5775799286286505e-05, | |
| "loss": 0.51, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.5662005680576796e-05, | |
| "loss": 0.5112, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.554821207486709e-05, | |
| "loss": 0.5109, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.5434418469157384e-05, | |
| "loss": 0.5081, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.5320624863447674e-05, | |
| "loss": 0.5121, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5206831257737965e-05, | |
| "loss": 0.5054, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.8885442859495518, | |
| "eval_loss": 0.4669877886772156, | |
| "eval_runtime": 2155.7499, | |
| "eval_samples_per_second": 68.033, | |
| "eval_steps_per_second": 17.008, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.509303765202826e-05, | |
| "loss": 0.5039, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.4979244046318546e-05, | |
| "loss": 0.5039, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.486545044060884e-05, | |
| "loss": 0.5036, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.4751656834899134e-05, | |
| "loss": 0.5061, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.4637863229189424e-05, | |
| "loss": 0.5016, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.452406962347972e-05, | |
| "loss": 0.5072, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.441027601777001e-05, | |
| "loss": 0.4996, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.42964824120603e-05, | |
| "loss": 0.5044, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.418268880635059e-05, | |
| "loss": 0.5011, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.406889520064089e-05, | |
| "loss": 0.5025, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.8897554085084038, | |
| "eval_loss": 0.46060749888420105, | |
| "eval_runtime": 2156.7123, | |
| "eval_samples_per_second": 68.003, | |
| "eval_steps_per_second": 17.001, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.3955101594931174e-05, | |
| "loss": 0.5004, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.384130798922147e-05, | |
| "loss": 0.5013, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.372751438351177e-05, | |
| "loss": 0.504, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.361372077780205e-05, | |
| "loss": 0.501, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.349992717209235e-05, | |
| "loss": 0.4924, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.338613356638264e-05, | |
| "loss": 0.4979, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.327233996067293e-05, | |
| "loss": 0.493, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.315854635496322e-05, | |
| "loss": 0.4954, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.304475274925352e-05, | |
| "loss": 0.4975, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.293095914354381e-05, | |
| "loss": 0.4931, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.8908734163811548, | |
| "eval_loss": 0.45606353878974915, | |
| "eval_runtime": 2158.0121, | |
| "eval_samples_per_second": 67.962, | |
| "eval_steps_per_second": 16.991, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.28171655378341e-05, | |
| "loss": 0.4948, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.2703371932124397e-05, | |
| "loss": 0.4896, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.258957832641468e-05, | |
| "loss": 0.4972, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.247578472070498e-05, | |
| "loss": 0.4929, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.236199111499527e-05, | |
| "loss": 0.4916, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.224819750928556e-05, | |
| "loss": 0.4898, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.213440390357585e-05, | |
| "loss": 0.4823, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.2020610297866146e-05, | |
| "loss": 0.4862, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.190681669215644e-05, | |
| "loss": 0.4874, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.179302308644673e-05, | |
| "loss": 0.4843, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_accuracy": 0.892281354181696, | |
| "eval_loss": 0.44839057326316833, | |
| "eval_runtime": 2158.2709, | |
| "eval_samples_per_second": 67.954, | |
| "eval_steps_per_second": 16.989, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1679229480737025e-05, | |
| "loss": 0.4846, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.156543587502731e-05, | |
| "loss": 0.4882, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.1451642269317606e-05, | |
| "loss": 0.4808, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.1337848663607896e-05, | |
| "loss": 0.4862, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.122405505789819e-05, | |
| "loss": 0.483, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.1110261452188484e-05, | |
| "loss": 0.4828, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.0996467846478774e-05, | |
| "loss": 0.4804, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.0882674240769065e-05, | |
| "loss": 0.4807, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.0768880635059355e-05, | |
| "loss": 0.4808, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.065508702934965e-05, | |
| "loss": 0.4801, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_accuracy": 0.8932934230811805, | |
| "eval_loss": 0.44512268900871277, | |
| "eval_runtime": 2157.4288, | |
| "eval_samples_per_second": 67.98, | |
| "eval_steps_per_second": 16.995, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.0541293423639936e-05, | |
| "loss": 0.4768, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.0427499817930234e-05, | |
| "loss": 0.4794, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.031370621222052e-05, | |
| "loss": 0.4828, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0199912606510815e-05, | |
| "loss": 0.4783, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0086119000801112e-05, | |
| "loss": 0.4776, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.99723253950914e-05, | |
| "loss": 0.4738, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9858531789381693e-05, | |
| "loss": 0.4741, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9744738183671984e-05, | |
| "loss": 0.4753, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9630944577962277e-05, | |
| "loss": 0.4744, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9517150972252568e-05, | |
| "loss": 0.4781, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_accuracy": 0.894076440048766, | |
| "eval_loss": 0.4388616979122162, | |
| "eval_runtime": 2159.5744, | |
| "eval_samples_per_second": 67.913, | |
| "eval_steps_per_second": 16.978, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9403357366542862e-05, | |
| "loss": 0.4716, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9289563760833156e-05, | |
| "loss": 0.4752, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9175770155123443e-05, | |
| "loss": 0.4676, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.906197654941374e-05, | |
| "loss": 0.4706, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.8948182943704027e-05, | |
| "loss": 0.4695, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.883438933799432e-05, | |
| "loss": 0.4735, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.872059573228461e-05, | |
| "loss": 0.4699, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8606802126574906e-05, | |
| "loss": 0.4702, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.8493008520865193e-05, | |
| "loss": 0.4719, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.837921491515549e-05, | |
| "loss": 0.4721, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_accuracy": 0.8949646114588999, | |
| "eval_loss": 0.4361897110939026, | |
| "eval_runtime": 2158.3457, | |
| "eval_samples_per_second": 67.952, | |
| "eval_steps_per_second": 16.988, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.8265421309445784e-05, | |
| "loss": 0.4673, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.815162770373607e-05, | |
| "loss": 0.4686, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.8037834098026365e-05, | |
| "loss": 0.468, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7924040492316655e-05, | |
| "loss": 0.4638, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.781024688660695e-05, | |
| "loss": 0.4644, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.769645328089724e-05, | |
| "loss": 0.4688, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7582659675187534e-05, | |
| "loss": 0.4661, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7468866069477828e-05, | |
| "loss": 0.4649, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7355072463768118e-05, | |
| "loss": 0.4723, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7241278858058412e-05, | |
| "loss": 0.4676, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_accuracy": 0.8959113381567293, | |
| "eval_loss": 0.43063369393348694, | |
| "eval_runtime": 2155.3448, | |
| "eval_samples_per_second": 68.046, | |
| "eval_steps_per_second": 17.012, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.71274852523487e-05, | |
| "loss": 0.4612, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.7013691646638993e-05, | |
| "loss": 0.466, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6899898040929283e-05, | |
| "loss": 0.4618, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6786104435219577e-05, | |
| "loss": 0.4627, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6672310829509868e-05, | |
| "loss": 0.4658, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6558517223800162e-05, | |
| "loss": 0.4598, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6444723618090456e-05, | |
| "loss": 0.4641, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6330930012380746e-05, | |
| "loss": 0.4544, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.621713640667104e-05, | |
| "loss": 0.4587, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6103342800961327e-05, | |
| "loss": 0.4569, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.8969798763719528, | |
| "eval_loss": 0.4255083203315735, | |
| "eval_runtime": 2157.7053, | |
| "eval_samples_per_second": 67.972, | |
| "eval_steps_per_second": 16.993, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.598954919525162e-05, | |
| "loss": 0.4601, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.587575558954191e-05, | |
| "loss": 0.4572, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.5761961983832205e-05, | |
| "loss": 0.4527, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.56481683781225e-05, | |
| "loss": 0.4595, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.553437477241279e-05, | |
| "loss": 0.4621, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5420581166703084e-05, | |
| "loss": 0.458, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.530678756099337e-05, | |
| "loss": 0.4606, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5192993955283668e-05, | |
| "loss": 0.4573, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5079200349573955e-05, | |
| "loss": 0.4601, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.496540674386425e-05, | |
| "loss": 0.4562, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.897719716014404, | |
| "eval_loss": 0.4225170314311981, | |
| "eval_runtime": 2157.2636, | |
| "eval_samples_per_second": 67.986, | |
| "eval_steps_per_second": 16.997, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4851613138154543e-05, | |
| "loss": 0.4552, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4737819532444834e-05, | |
| "loss": 0.4577, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4624025926735124e-05, | |
| "loss": 0.4526, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4510232321025418e-05, | |
| "loss": 0.4533, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4396438715315712e-05, | |
| "loss": 0.456, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4282645109606002e-05, | |
| "loss": 0.4536, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4168851503896296e-05, | |
| "loss": 0.4612, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.4055057898186587e-05, | |
| "loss": 0.4527, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.3941264292476877e-05, | |
| "loss": 0.4528, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.382747068676717e-05, | |
| "loss": 0.4532, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_accuracy": 0.8983772130502822, | |
| "eval_loss": 0.4186096489429474, | |
| "eval_runtime": 2156.0493, | |
| "eval_samples_per_second": 68.024, | |
| "eval_steps_per_second": 17.006, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3713677081057462e-05, | |
| "loss": 0.4508, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3599883475347752e-05, | |
| "loss": 0.4521, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3486089869638046e-05, | |
| "loss": 0.4492, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.337229626392834e-05, | |
| "loss": 0.4485, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.325850265821863e-05, | |
| "loss": 0.4499, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.3144709052508924e-05, | |
| "loss": 0.4495, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.3030915446799215e-05, | |
| "loss": 0.4499, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.2917121841089505e-05, | |
| "loss": 0.4508, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.28033282353798e-05, | |
| "loss": 0.4474, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.268953462967009e-05, | |
| "loss": 0.4481, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_accuracy": 0.8989962769112119, | |
| "eval_loss": 0.4165661036968231, | |
| "eval_runtime": 2156.6641, | |
| "eval_samples_per_second": 68.005, | |
| "eval_steps_per_second": 17.001, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.2575741023960384e-05, | |
| "loss": 0.4489, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.2461947418250674e-05, | |
| "loss": 0.4509, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.2348153812540968e-05, | |
| "loss": 0.4495, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.223436020683126e-05, | |
| "loss": 0.4475, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.212056660112155e-05, | |
| "loss": 0.4502, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.2006772995411843e-05, | |
| "loss": 0.4448, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.1892979389702134e-05, | |
| "loss": 0.4511, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.1779185783992424e-05, | |
| "loss": 0.4436, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.166539217828272e-05, | |
| "loss": 0.4401, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.1551598572573012e-05, | |
| "loss": 0.4474, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_accuracy": 0.8998707125729046, | |
| "eval_loss": 0.41221463680267334, | |
| "eval_runtime": 2156.9802, | |
| "eval_samples_per_second": 67.995, | |
| "eval_steps_per_second": 16.999, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.1437804966863302e-05, | |
| "loss": 0.4452, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.1324011361153596e-05, | |
| "loss": 0.4375, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.1210217755443887e-05, | |
| "loss": 0.4429, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.1096424149734177e-05, | |
| "loss": 0.4426, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.098263054402447e-05, | |
| "loss": 0.4427, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.086883693831476e-05, | |
| "loss": 0.4434, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.0755043332605056e-05, | |
| "loss": 0.442, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.064124972689535e-05, | |
| "loss": 0.4409, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.052745612118564e-05, | |
| "loss": 0.4422, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.041366251547593e-05, | |
| "loss": 0.4417, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_accuracy": 0.9003224313444536, | |
| "eval_loss": 0.40945446491241455, | |
| "eval_runtime": 2157.4017, | |
| "eval_samples_per_second": 67.981, | |
| "eval_steps_per_second": 16.995, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.0299868909766224e-05, | |
| "loss": 0.4395, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.0186075304056515e-05, | |
| "loss": 0.4428, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.0072281698346805e-05, | |
| "loss": 0.4437, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.99584880926371e-05, | |
| "loss": 0.438, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.9844694486927393e-05, | |
| "loss": 0.4379, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.9730900881217684e-05, | |
| "loss": 0.4381, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.9617107275507978e-05, | |
| "loss": 0.4442, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.9503313669798268e-05, | |
| "loss": 0.4404, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.938952006408856e-05, | |
| "loss": 0.4386, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.9275726458378852e-05, | |
| "loss": 0.4329, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_accuracy": 0.9011228326204502, | |
| "eval_loss": 0.4052372872829437, | |
| "eval_runtime": 2157.9151, | |
| "eval_samples_per_second": 67.965, | |
| "eval_steps_per_second": 16.991, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.9161932852669143e-05, | |
| "loss": 0.4336, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.9048139246959433e-05, | |
| "loss": 0.4388, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.8934345641249727e-05, | |
| "loss": 0.4335, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.882055203554002e-05, | |
| "loss": 0.4346, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.8706758429830312e-05, | |
| "loss": 0.4335, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.8592964824120602e-05, | |
| "loss": 0.4351, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.8479171218410896e-05, | |
| "loss": 0.4318, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.8365377612701187e-05, | |
| "loss": 0.4337, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.825158400699148e-05, | |
| "loss": 0.4377, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.8137790401281774e-05, | |
| "loss": 0.436, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_accuracy": 0.9015046107759694, | |
| "eval_loss": 0.40359699726104736, | |
| "eval_runtime": 2159.0025, | |
| "eval_samples_per_second": 67.931, | |
| "eval_steps_per_second": 16.983, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.8023996795572065e-05, | |
| "loss": 0.4322, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7910203189862355e-05, | |
| "loss": 0.4367, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.779640958415265e-05, | |
| "loss": 0.4289, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.768261597844294e-05, | |
| "loss": 0.4357, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.756882237273323e-05, | |
| "loss": 0.4316, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.7455028767023524e-05, | |
| "loss": 0.4334, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.7341235161313815e-05, | |
| "loss": 0.4298, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.722744155560411e-05, | |
| "loss": 0.4344, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.7113647949894403e-05, | |
| "loss": 0.4309, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.6999854344184693e-05, | |
| "loss": 0.4289, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.9022181156532487, | |
| "eval_loss": 0.4002615809440613, | |
| "eval_runtime": 2157.6915, | |
| "eval_samples_per_second": 67.972, | |
| "eval_steps_per_second": 16.993, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.6886060738474984e-05, | |
| "loss": 0.4271, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.6772267132765277e-05, | |
| "loss": 0.4264, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6658473527055568e-05, | |
| "loss": 0.43, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.654467992134586e-05, | |
| "loss": 0.4292, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.6430886315636152e-05, | |
| "loss": 0.429, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6317092709926446e-05, | |
| "loss": 0.4265, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.6203299104216737e-05, | |
| "loss": 0.4283, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.608950549850703e-05, | |
| "loss": 0.4279, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.597571189279732e-05, | |
| "loss": 0.4272, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.586191828708761e-05, | |
| "loss": 0.4326, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_accuracy": 0.902766321286562, | |
| "eval_loss": 0.3976551294326782, | |
| "eval_runtime": 2157.9395, | |
| "eval_samples_per_second": 67.964, | |
| "eval_steps_per_second": 16.991, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.5748124681377906e-05, | |
| "loss": 0.4257, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.5634331075668196e-05, | |
| "loss": 0.4223, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.5520537469958487e-05, | |
| "loss": 0.4228, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.540674386424878e-05, | |
| "loss": 0.4276, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.5292950258539074e-05, | |
| "loss": 0.4244, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.5179156652829365e-05, | |
| "loss": 0.4261, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.5065363047119657e-05, | |
| "loss": 0.4226, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.495156944140995e-05, | |
| "loss": 0.4265, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.483777583570024e-05, | |
| "loss": 0.4262, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.4723982229990532e-05, | |
| "loss": 0.4231, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.9031951195206896, | |
| "eval_loss": 0.3947906792163849, | |
| "eval_runtime": 2160.1666, | |
| "eval_samples_per_second": 67.894, | |
| "eval_steps_per_second": 16.974, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.4610188624280824e-05, | |
| "loss": 0.4195, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.4496395018571118e-05, | |
| "loss": 0.4216, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.438260141286141e-05, | |
| "loss": 0.4152, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.4268807807151702e-05, | |
| "loss": 0.4194, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.4155014201441993e-05, | |
| "loss": 0.4193, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.4041220595732285e-05, | |
| "loss": 0.4223, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.3927426990022577e-05, | |
| "loss": 0.4259, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3813633384312868e-05, | |
| "loss": 0.4215, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.369983977860316e-05, | |
| "loss": 0.4195, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.3586046172893454e-05, | |
| "loss": 0.4233, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_accuracy": 0.9036811615656513, | |
| "eval_loss": 0.3929060399532318, | |
| "eval_runtime": 2157.8805, | |
| "eval_samples_per_second": 67.966, | |
| "eval_steps_per_second": 16.992, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.3472252567183746e-05, | |
| "loss": 0.4216, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.3358458961474038e-05, | |
| "loss": 0.4192, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.3244665355764329e-05, | |
| "loss": 0.4202, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.3130871750054621e-05, | |
| "loss": 0.4239, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.3017078144344913e-05, | |
| "loss": 0.4254, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.2903284538635205e-05, | |
| "loss": 0.4154, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.2789490932925496e-05, | |
| "loss": 0.4232, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.2675697327215792e-05, | |
| "loss": 0.422, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.2561903721506082e-05, | |
| "loss": 0.4177, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.2448110115796374e-05, | |
| "loss": 0.4179, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.9042119348171125, | |
| "eval_loss": 0.3903782367706299, | |
| "eval_runtime": 2158.6911, | |
| "eval_samples_per_second": 67.941, | |
| "eval_steps_per_second": 16.985, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.2334316510086666e-05, | |
| "loss": 0.4215, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.2220522904376957e-05, | |
| "loss": 0.4206, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.210672929866725e-05, | |
| "loss": 0.4186, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.1992935692957543e-05, | |
| "loss": 0.4205, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.1879142087247834e-05, | |
| "loss": 0.4163, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.1765348481538126e-05, | |
| "loss": 0.4178, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.1651554875828418e-05, | |
| "loss": 0.4163, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.153776127011871e-05, | |
| "loss": 0.4176, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1423967664409002e-05, | |
| "loss": 0.4179, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1310174058699295e-05, | |
| "loss": 0.4141, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_accuracy": 0.9047012480604113, | |
| "eval_loss": 0.38813966512680054, | |
| "eval_runtime": 2158.6653, | |
| "eval_samples_per_second": 67.942, | |
| "eval_steps_per_second": 16.985, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1196380452989585e-05, | |
| "loss": 0.4174, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.1082586847279879e-05, | |
| "loss": 0.4172, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.096879324157017e-05, | |
| "loss": 0.4194, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0854999635860462e-05, | |
| "loss": 0.4147, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.0741206030150754e-05, | |
| "loss": 0.4104, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.0627412424441046e-05, | |
| "loss": 0.4128, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0513618818731338e-05, | |
| "loss": 0.4111, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.039982521302163e-05, | |
| "loss": 0.4159, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0286031607311923e-05, | |
| "loss": 0.4163, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0172238001602215e-05, | |
| "loss": 0.4138, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_accuracy": 0.9050543084721216, | |
| "eval_loss": 0.3864535987377167, | |
| "eval_runtime": 2159.9244, | |
| "eval_samples_per_second": 67.902, | |
| "eval_steps_per_second": 16.976, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.0058444395892507e-05, | |
| "loss": 0.4141, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.944650790182798e-06, | |
| "loss": 0.4129, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.830857184473091e-06, | |
| "loss": 0.4119, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.717063578763384e-06, | |
| "loss": 0.4067, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.603269973053674e-06, | |
| "loss": 0.4148, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.489476367343966e-06, | |
| "loss": 0.4115, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.375682761634259e-06, | |
| "loss": 0.4183, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.26188915592455e-06, | |
| "loss": 0.4162, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.148095550214843e-06, | |
| "loss": 0.411, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.034301944505135e-06, | |
| "loss": 0.4122, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_accuracy": 0.90535241823386, | |
| "eval_loss": 0.38498830795288086, | |
| "eval_runtime": 2156.8626, | |
| "eval_samples_per_second": 67.998, | |
| "eval_steps_per_second": 17.0, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.920508338795427e-06, | |
| "loss": 0.4101, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.80671473308572e-06, | |
| "loss": 0.4126, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.69292112737601e-06, | |
| "loss": 0.4106, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.579127521666302e-06, | |
| "loss": 0.4138, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.465333915956596e-06, | |
| "loss": 0.413, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.351540310246887e-06, | |
| "loss": 0.4105, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.237746704537179e-06, | |
| "loss": 0.4149, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.123953098827471e-06, | |
| "loss": 0.4149, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.010159493117763e-06, | |
| "loss": 0.41, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.896365887408056e-06, | |
| "loss": 0.4065, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_accuracy": 0.9059730589750316, | |
| "eval_loss": 0.3823322355747223, | |
| "eval_runtime": 2156.2214, | |
| "eval_samples_per_second": 68.019, | |
| "eval_steps_per_second": 17.005, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.782572281698348e-06, | |
| "loss": 0.4057, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.668778675988638e-06, | |
| "loss": 0.4132, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.554985070278932e-06, | |
| "loss": 0.4108, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.4411914645692235e-06, | |
| "loss": 0.4088, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.327397858859515e-06, | |
| "loss": 0.4101, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.213604253149807e-06, | |
| "loss": 0.413, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.0998106474401e-06, | |
| "loss": 0.4097, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 6.986017041730391e-06, | |
| "loss": 0.4049, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.872223436020684e-06, | |
| "loss": 0.4086, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.758429830310975e-06, | |
| "loss": 0.4056, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_accuracy": 0.906182177835412, | |
| "eval_loss": 0.38130033016204834, | |
| "eval_runtime": 2156.4695, | |
| "eval_samples_per_second": 68.011, | |
| "eval_steps_per_second": 17.003, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 6.644636224601268e-06, | |
| "loss": 0.4059, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.530842618891559e-06, | |
| "loss": 0.4041, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.4170490131818516e-06, | |
| "loss": 0.4107, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.303255407472143e-06, | |
| "loss": 0.4053, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.189461801762435e-06, | |
| "loss": 0.4107, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.075668196052728e-06, | |
| "loss": 0.4038, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.9618745903430195e-06, | |
| "loss": 0.41, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 5.848080984633312e-06, | |
| "loss": 0.4074, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.734287378923604e-06, | |
| "loss": 0.4081, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.620493773213896e-06, | |
| "loss": 0.4074, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_accuracy": 0.9065305015342497, | |
| "eval_loss": 0.3795691132545471, | |
| "eval_runtime": 2156.844, | |
| "eval_samples_per_second": 67.999, | |
| "eval_steps_per_second": 17.0, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.5067001675041875e-06, | |
| "loss": 0.4122, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.39290656179448e-06, | |
| "loss": 0.4066, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.279112956084772e-06, | |
| "loss": 0.4071, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.165319350375064e-06, | |
| "loss": 0.4049, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.0515257446653554e-06, | |
| "loss": 0.4028, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.9377321389556485e-06, | |
| "loss": 0.4064, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.82393853324594e-06, | |
| "loss": 0.4057, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.710144927536232e-06, | |
| "loss": 0.4029, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.596351321826524e-06, | |
| "loss": 0.4068, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.4825577161168164e-06, | |
| "loss": 0.4046, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_accuracy": 0.9069610695948094, | |
| "eval_loss": 0.3776489198207855, | |
| "eval_runtime": 2156.5964, | |
| "eval_samples_per_second": 68.007, | |
| "eval_steps_per_second": 17.002, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.368764110407108e-06, | |
| "loss": 0.4016, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.2549705046974e-06, | |
| "loss": 0.404, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.141176898987692e-06, | |
| "loss": 0.4043, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.027383293277984e-06, | |
| "loss": 0.4043, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.913589687568276e-06, | |
| "loss": 0.4008, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.7997960818585684e-06, | |
| "loss": 0.4055, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.68600247614886e-06, | |
| "loss": 0.403, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.5722088704391523e-06, | |
| "loss": 0.4005, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.458415264729444e-06, | |
| "loss": 0.4009, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.3446216590197367e-06, | |
| "loss": 0.4061, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_accuracy": 0.9072532294618356, | |
| "eval_loss": 0.3758757412433624, | |
| "eval_runtime": 2157.4549, | |
| "eval_samples_per_second": 67.98, | |
| "eval_steps_per_second": 16.995, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.230828053310028e-06, | |
| "loss": 0.4059, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.1170344476003207e-06, | |
| "loss": 0.4046, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.0032408418906125e-06, | |
| "loss": 0.4037, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.8894472361809047e-06, | |
| "loss": 0.4011, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.775653630471197e-06, | |
| "loss": 0.4027, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.6618600247614887e-06, | |
| "loss": 0.4054, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.548066419051781e-06, | |
| "loss": 0.3995, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.4342728133420727e-06, | |
| "loss": 0.4019, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.320479207632365e-06, | |
| "loss": 0.3978, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.206685601922657e-06, | |
| "loss": 0.4036, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_accuracy": 0.9072046194275737, | |
| "eval_loss": 0.3758549690246582, | |
| "eval_runtime": 2155.2543, | |
| "eval_samples_per_second": 68.049, | |
| "eval_steps_per_second": 17.012, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.092891996212949e-06, | |
| "loss": 0.3992, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.979098390503241e-06, | |
| "loss": 0.3968, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.865304784793533e-06, | |
| "loss": 0.4051, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.751511179083825e-06, | |
| "loss": 0.4044, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.637717573374117e-06, | |
| "loss": 0.4017, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.523923967664409e-06, | |
| "loss": 0.4009, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.410130361954701e-06, | |
| "loss": 0.4043, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.2963367562449932e-06, | |
| "loss": 0.4054, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.1825431505352852e-06, | |
| "loss": 0.4044, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.0687495448255772e-06, | |
| "loss": 0.4003, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_accuracy": 0.9076027976570412, | |
| "eval_loss": 0.3740881383419037, | |
| "eval_runtime": 2155.6745, | |
| "eval_samples_per_second": 68.036, | |
| "eval_steps_per_second": 17.009, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 9.549559391158691e-07, | |
| "loss": 0.4014, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.411623334061612e-07, | |
| "loss": 0.4, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.273687276964533e-07, | |
| "loss": 0.4007, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.135751219867453e-07, | |
| "loss": 0.4017, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.997815162770374e-07, | |
| "loss": 0.4036, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.859879105673294e-07, | |
| "loss": 0.4, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.7219430485762144e-07, | |
| "loss": 0.3958, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.584006991479135e-07, | |
| "loss": 0.4019, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.4607093438205524e-08, | |
| "loss": 0.405, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 219696, | |
| "total_flos": 9.251953379141652e+17, | |
| "train_loss": 0.5021202932867165, | |
| "train_runtime": 238578.5378, | |
| "train_samples_per_second": 14.734, | |
| "train_steps_per_second": 0.921 | |
| } | |
| ], | |
| "max_steps": 219696, | |
| "num_train_epochs": 3, | |
| "total_flos": 9.251953379141652e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |