| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9999847145752639, | |
| "eval_steps": 500, | |
| "global_step": 40888, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9981412639405207e-05, | |
| "loss": 3.4921, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9956955585991002e-05, | |
| "loss": 2.95, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9932498532576798e-05, | |
| "loss": 2.8209, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9908041479162593e-05, | |
| "loss": 2.7532, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.988358442574839e-05, | |
| "loss": 2.7287, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9859127372334184e-05, | |
| "loss": 2.6975, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9834670318919976e-05, | |
| "loss": 2.7061, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.981021326550577e-05, | |
| "loss": 2.6844, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.978575621209157e-05, | |
| "loss": 2.6694, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9761299158677366e-05, | |
| "loss": 2.6722, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.4950875237178296, | |
| "eval_loss": 2.48111629486084, | |
| "eval_runtime": 33.1501, | |
| "eval_samples_per_second": 73.393, | |
| "eval_steps_per_second": 4.615, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9736842105263158e-05, | |
| "loss": 2.6674, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9712385051848954e-05, | |
| "loss": 2.6716, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.968792799843475e-05, | |
| "loss": 2.6449, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9663470945020548e-05, | |
| "loss": 2.6395, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.963901389160634e-05, | |
| "loss": 2.6398, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9615045979260422e-05, | |
| "loss": 2.6342, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9590588925846218e-05, | |
| "loss": 2.6433, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.956613187243201e-05, | |
| "loss": 2.619, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9541674819017805e-05, | |
| "loss": 2.6278, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9517706906671884e-05, | |
| "loss": 2.6243, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.49991353398275346, | |
| "eval_loss": 2.445934295654297, | |
| "eval_runtime": 32.8968, | |
| "eval_samples_per_second": 73.959, | |
| "eval_steps_per_second": 4.651, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.949324985325768e-05, | |
| "loss": 2.6264, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.946928194091176e-05, | |
| "loss": 2.6283, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.944531402856584e-05, | |
| "loss": 2.6186, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9420856975151636e-05, | |
| "loss": 2.6125, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.939639992173743e-05, | |
| "loss": 2.606, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9371942868323227e-05, | |
| "loss": 2.6225, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9347974955977306e-05, | |
| "loss": 2.6235, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9324007043631385e-05, | |
| "loss": 2.6114, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.929954999021718e-05, | |
| "loss": 2.6051, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9275092936802975e-05, | |
| "loss": 2.6051, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.5025316445514746, | |
| "eval_loss": 2.4294509887695312, | |
| "eval_runtime": 32.8294, | |
| "eval_samples_per_second": 74.11, | |
| "eval_steps_per_second": 4.66, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9251614165525338e-05, | |
| "loss": 2.5985, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9227157112111133e-05, | |
| "loss": 2.6018, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9202700058696932e-05, | |
| "loss": 2.6135, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9179221287419294e-05, | |
| "loss": 2.5797, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9154764234005086e-05, | |
| "loss": 2.592, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9130307180590885e-05, | |
| "loss": 2.5919, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9106339268244964e-05, | |
| "loss": 2.5968, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.908188221483076e-05, | |
| "loss": 2.6137, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.905938172568969e-05, | |
| "loss": 2.584, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9034924672275487e-05, | |
| "loss": 2.5901, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.5037453861331029, | |
| "eval_loss": 2.4193975925445557, | |
| "eval_runtime": 32.9991, | |
| "eval_samples_per_second": 73.729, | |
| "eval_steps_per_second": 4.636, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9010467618861282e-05, | |
| "loss": 2.601, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.8986010565447078e-05, | |
| "loss": 2.5843, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.8962042653101156e-05, | |
| "loss": 2.58, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.8938074740755235e-05, | |
| "loss": 2.5896, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.891361768734103e-05, | |
| "loss": 2.5862, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8889160633926826e-05, | |
| "loss": 2.5904, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8865192721580905e-05, | |
| "loss": 2.6002, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.88407356681667e-05, | |
| "loss": 2.5939, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8817746037957346e-05, | |
| "loss": 2.597, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8793288984543145e-05, | |
| "loss": 2.5852, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.5048827158855367, | |
| "eval_loss": 2.412391185760498, | |
| "eval_runtime": 32.6918, | |
| "eval_samples_per_second": 74.422, | |
| "eval_steps_per_second": 4.68, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8769810213265507e-05, | |
| "loss": 2.5863, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8746331441987872e-05, | |
| "loss": 2.5691, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8721874388573668e-05, | |
| "loss": 2.5908, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8697417335159463e-05, | |
| "loss": 2.5939, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8672960281745255e-05, | |
| "loss": 2.5759, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.864850322833105e-05, | |
| "loss": 2.5764, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.862453531598513e-05, | |
| "loss": 2.5856, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.860056740363921e-05, | |
| "loss": 2.5867, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8576110350225007e-05, | |
| "loss": 2.5822, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8552142437879086e-05, | |
| "loss": 2.5818, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.5054369027309588, | |
| "eval_loss": 2.407233476638794, | |
| "eval_runtime": 32.7819, | |
| "eval_samples_per_second": 74.218, | |
| "eval_steps_per_second": 4.667, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8528174525533165e-05, | |
| "loss": 2.5806, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8504206613187247e-05, | |
| "loss": 2.5786, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.847974955977304e-05, | |
| "loss": 2.5866, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8455292506358834e-05, | |
| "loss": 2.578, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.843083545294463e-05, | |
| "loss": 2.5848, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8406378399530425e-05, | |
| "loss": 2.5773, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8382410487184504e-05, | |
| "loss": 2.5732, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8357953433770303e-05, | |
| "loss": 2.572, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.83334963803561e-05, | |
| "loss": 2.5753, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.830903932694189e-05, | |
| "loss": 2.5801, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.5058640046394045, | |
| "eval_loss": 2.4024484157562256, | |
| "eval_runtime": 32.8872, | |
| "eval_samples_per_second": 73.98, | |
| "eval_steps_per_second": 4.652, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8285560555664256e-05, | |
| "loss": 2.5758, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8261592643318335e-05, | |
| "loss": 2.5774, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.823713558990413e-05, | |
| "loss": 2.5818, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8212678536489926e-05, | |
| "loss": 2.5772, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8189199765212288e-05, | |
| "loss": 2.5673, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8164742711798083e-05, | |
| "loss": 2.5721, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8140774799452162e-05, | |
| "loss": 2.5678, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.811680688710624e-05, | |
| "loss": 2.5684, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8092349833692036e-05, | |
| "loss": 2.5663, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8067892780277835e-05, | |
| "loss": 2.5626, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.5069546829592774, | |
| "eval_loss": 2.398844003677368, | |
| "eval_runtime": 32.7613, | |
| "eval_samples_per_second": 74.265, | |
| "eval_steps_per_second": 4.67, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.804343572686363e-05, | |
| "loss": 2.5592, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.801946781451771e-05, | |
| "loss": 2.5735, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7995499902171788e-05, | |
| "loss": 2.5712, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7971042848757584e-05, | |
| "loss": 2.5609, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.794658579534338e-05, | |
| "loss": 2.5638, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7922617882997458e-05, | |
| "loss": 2.5806, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.789913911171982e-05, | |
| "loss": 2.5638, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7874682058305615e-05, | |
| "loss": 2.5546, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7850714145959694e-05, | |
| "loss": 2.5689, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.782625709254549e-05, | |
| "loss": 2.5697, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.5073463941257803, | |
| "eval_loss": 2.395766258239746, | |
| "eval_runtime": 33.0876, | |
| "eval_samples_per_second": 73.532, | |
| "eval_steps_per_second": 4.624, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.780180003913129e-05, | |
| "loss": 2.5672, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7777342985717084e-05, | |
| "loss": 2.5697, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7752885932302876e-05, | |
| "loss": 2.5668, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7728428878888672e-05, | |
| "loss": 2.5706, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.770446096654275e-05, | |
| "loss": 2.5661, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7680493054196833e-05, | |
| "loss": 2.5561, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7656036000782628e-05, | |
| "loss": 2.556, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.763157894736842e-05, | |
| "loss": 2.5593, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7608100176090786e-05, | |
| "loss": 2.5714, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7584132263744868e-05, | |
| "loss": 2.5532, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.5078651902292596, | |
| "eval_loss": 2.3927862644195557, | |
| "eval_runtime": 32.7397, | |
| "eval_samples_per_second": 74.314, | |
| "eval_steps_per_second": 4.673, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.755967521033066e-05, | |
| "loss": 2.5543, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.7535218156916455e-05, | |
| "loss": 2.553, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.751076110350225e-05, | |
| "loss": 2.554, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7486304050088046e-05, | |
| "loss": 2.5722, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7461846996673842e-05, | |
| "loss": 2.5687, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.743787908432792e-05, | |
| "loss": 2.5644, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7413911171982e-05, | |
| "loss": 2.562, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7389454118567798e-05, | |
| "loss": 2.5497, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7364997065153594e-05, | |
| "loss": 2.5639, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7340540011739386e-05, | |
| "loss": 2.5505, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.5079761884653529, | |
| "eval_loss": 2.3904242515563965, | |
| "eval_runtime": 32.835, | |
| "eval_samples_per_second": 74.098, | |
| "eval_steps_per_second": 4.66, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7316572099393468e-05, | |
| "loss": 2.561, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.729309332811583e-05, | |
| "loss": 2.5537, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7268636274701626e-05, | |
| "loss": 2.5581, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.724417922128742e-05, | |
| "loss": 2.5636, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7219722167873217e-05, | |
| "loss": 2.549, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7196732537663862e-05, | |
| "loss": 2.5434, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7172764625317944e-05, | |
| "loss": 2.5545, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.714830757190374e-05, | |
| "loss": 2.5686, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.712385051848953e-05, | |
| "loss": 2.5578, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.709939346507533e-05, | |
| "loss": 2.5497, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.5085874830989099, | |
| "eval_loss": 2.387216806411743, | |
| "eval_runtime": 32.9586, | |
| "eval_samples_per_second": 73.82, | |
| "eval_steps_per_second": 4.642, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7074936411661126e-05, | |
| "loss": 2.5619, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.705047935824692e-05, | |
| "loss": 2.5541, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7027489728037567e-05, | |
| "loss": 2.5574, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7003032674623362e-05, | |
| "loss": 2.5557, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.6978575621209158e-05, | |
| "loss": 2.5529, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.6954118567794953e-05, | |
| "loss": 2.5527, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.692966151438075e-05, | |
| "loss": 2.5603, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.690618274310311e-05, | |
| "loss": 2.5397, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.688172568968891e-05, | |
| "loss": 2.5471, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6857268636274705e-05, | |
| "loss": 2.5636, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.5088537179985249, | |
| "eval_loss": 2.3856565952301025, | |
| "eval_runtime": 32.985, | |
| "eval_samples_per_second": 73.761, | |
| "eval_steps_per_second": 4.638, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6833300723928784e-05, | |
| "loss": 2.5447, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6809821952651146e-05, | |
| "loss": 2.552, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.678536489923694e-05, | |
| "loss": 2.5511, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6760907845822737e-05, | |
| "loss": 2.5507, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6736939933476816e-05, | |
| "loss": 2.5357, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.671248288006261e-05, | |
| "loss": 2.5449, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.668851496771669e-05, | |
| "loss": 2.5525, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.666405791430249e-05, | |
| "loss": 2.5403, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6640579143024848e-05, | |
| "loss": 2.5628, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.661661123067893e-05, | |
| "loss": 2.5483, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.5091706260059216, | |
| "eval_loss": 2.383516550064087, | |
| "eval_runtime": 32.7354, | |
| "eval_samples_per_second": 74.323, | |
| "eval_steps_per_second": 4.674, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6592154177264725e-05, | |
| "loss": 2.5551, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.656769712385052e-05, | |
| "loss": 2.5489, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6543240070436316e-05, | |
| "loss": 2.553, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6519761299158678e-05, | |
| "loss": 2.5399, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6496282527881044e-05, | |
| "loss": 2.5468, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.647182547446684e-05, | |
| "loss": 2.5422, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.644736842105263e-05, | |
| "loss": 2.5484, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6423400508706713e-05, | |
| "loss": 2.534, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6399432596360792e-05, | |
| "loss": 2.5363, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6374975542946588e-05, | |
| "loss": 2.5505, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.5096669007281646, | |
| "eval_loss": 2.3813159465789795, | |
| "eval_runtime": 33.3592, | |
| "eval_samples_per_second": 72.933, | |
| "eval_steps_per_second": 4.586, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6350518489532383e-05, | |
| "loss": 2.5522, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6326061436118175e-05, | |
| "loss": 2.5449, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6302093523772257e-05, | |
| "loss": 2.5383, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6277636470358053e-05, | |
| "loss": 2.5492, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.625366855801213e-05, | |
| "loss": 2.547, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.622970064566621e-05, | |
| "loss": 2.543, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6205243592252006e-05, | |
| "loss": 2.5517, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.61807865388378e-05, | |
| "loss": 2.5545, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.615681862649188e-05, | |
| "loss": 2.5452, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.613285071414596e-05, | |
| "loss": 2.5419, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.5095663588476452, | |
| "eval_loss": 2.3796439170837402, | |
| "eval_runtime": 31.6594, | |
| "eval_samples_per_second": 76.849, | |
| "eval_steps_per_second": 4.833, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.610888280180004e-05, | |
| "loss": 2.5429, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6084425748385837e-05, | |
| "loss": 2.542, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6060457836039915e-05, | |
| "loss": 2.5469, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.603697906476228e-05, | |
| "loss": 2.5533, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6012522011348076e-05, | |
| "loss": 2.5465, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.598806495793387e-05, | |
| "loss": 2.5359, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.5963607904519664e-05, | |
| "loss": 2.5437, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5939639992173743e-05, | |
| "loss": 2.5483, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5915182938759538e-05, | |
| "loss": 2.5304, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5890725885345334e-05, | |
| "loss": 2.5467, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.5099267009474262, | |
| "eval_loss": 2.3786227703094482, | |
| "eval_runtime": 33.2478, | |
| "eval_samples_per_second": 73.178, | |
| "eval_steps_per_second": 4.602, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5866268831931132e-05, | |
| "loss": 2.5326, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5841811778516925e-05, | |
| "loss": 2.5463, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5817843866171007e-05, | |
| "loss": 2.5317, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5793875953825085e-05, | |
| "loss": 2.5485, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5769908041479164e-05, | |
| "loss": 2.5401, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.574545098806496e-05, | |
| "loss": 2.5376, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5721972216787322e-05, | |
| "loss": 2.5477, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5697515163373117e-05, | |
| "loss": 2.5336, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5673547251027196e-05, | |
| "loss": 2.5269, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.564909019761299e-05, | |
| "loss": 2.5419, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.51021787023341, | |
| "eval_loss": 2.3769397735595703, | |
| "eval_runtime": 32.7948, | |
| "eval_samples_per_second": 74.189, | |
| "eval_steps_per_second": 4.665, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5624633144198787e-05, | |
| "loss": 2.5284, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5600176090784586e-05, | |
| "loss": 2.5469, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5575719037370378e-05, | |
| "loss": 2.5307, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5551261983956173e-05, | |
| "loss": 2.5331, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.552778321267854e-05, | |
| "loss": 2.5359, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5503326159264334e-05, | |
| "loss": 2.5388, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5479358246918413e-05, | |
| "loss": 2.5388, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.545490119350421e-05, | |
| "loss": 2.549, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5430933281158287e-05, | |
| "loss": 2.5469, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5406476227744083e-05, | |
| "loss": 2.5269, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.5104511273962147, | |
| "eval_loss": 2.3753819465637207, | |
| "eval_runtime": 32.6269, | |
| "eval_samples_per_second": 74.57, | |
| "eval_steps_per_second": 4.689, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5382508315398162e-05, | |
| "loss": 2.5363, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5358051261983957e-05, | |
| "loss": 2.5245, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5334083349638036e-05, | |
| "loss": 2.5369, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5310115437292118e-05, | |
| "loss": 2.5294, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5286147524946197e-05, | |
| "loss": 2.5394, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5261690471531992e-05, | |
| "loss": 2.5266, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5237233418117788e-05, | |
| "loss": 2.538, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5213265505771867e-05, | |
| "loss": 2.5272, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5188808452357662e-05, | |
| "loss": 2.5478, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5164351398943456e-05, | |
| "loss": 2.5315, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.5106103857349571, | |
| "eval_loss": 2.37398099899292, | |
| "eval_runtime": 33.5869, | |
| "eval_samples_per_second": 72.439, | |
| "eval_steps_per_second": 4.555, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5140383486597536e-05, | |
| "loss": 2.537, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.51169047153199e-05, | |
| "loss": 2.5316, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5092447661905696e-05, | |
| "loss": 2.5337, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.506799060849149e-05, | |
| "loss": 2.5375, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5043533555077285e-05, | |
| "loss": 2.5388, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5019076501663082e-05, | |
| "loss": 2.5292, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.4995108589317159e-05, | |
| "loss": 2.5219, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.4971140676971238e-05, | |
| "loss": 2.5335, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.4946683623557035e-05, | |
| "loss": 2.5389, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.4922715711211116e-05, | |
| "loss": 2.5442, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.5107744700839645, | |
| "eval_loss": 2.372843027114868, | |
| "eval_runtime": 32.6321, | |
| "eval_samples_per_second": 74.558, | |
| "eval_steps_per_second": 4.689, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.489825865779691e-05, | |
| "loss": 2.5302, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.487429074545099e-05, | |
| "loss": 2.5339, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.4850811974173354e-05, | |
| "loss": 2.5355, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.4826354920759147e-05, | |
| "loss": 2.5411, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.4801897867344943e-05, | |
| "loss": 2.5354, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.4777440813930738e-05, | |
| "loss": 2.5302, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4752983760516536e-05, | |
| "loss": 2.5341, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4729015848170614e-05, | |
| "loss": 2.5327, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4705047935824693e-05, | |
| "loss": 2.523, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4681569164547057e-05, | |
| "loss": 2.5318, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.5111710072607324, | |
| "eval_loss": 2.3712527751922607, | |
| "eval_runtime": 32.9046, | |
| "eval_samples_per_second": 73.941, | |
| "eval_steps_per_second": 4.65, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4657112111132852e-05, | |
| "loss": 2.5355, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4633144198786931e-05, | |
| "loss": 2.5284, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4608687145372727e-05, | |
| "loss": 2.5394, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4584230091958522e-05, | |
| "loss": 2.5381, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.45602621796126e-05, | |
| "loss": 2.5397, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4536783408334965e-05, | |
| "loss": 2.5412, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.451232635492076e-05, | |
| "loss": 2.5417, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4487869301506557e-05, | |
| "loss": 2.5314, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.446341224809235e-05, | |
| "loss": 2.5305, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4438955194678146e-05, | |
| "loss": 2.5242, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.5112618971207219, | |
| "eval_loss": 2.37015700340271, | |
| "eval_runtime": 32.8429, | |
| "eval_samples_per_second": 74.08, | |
| "eval_steps_per_second": 4.659, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4414987282332227e-05, | |
| "loss": 2.5308, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4391019369986306e-05, | |
| "loss": 2.5333, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4366562316572101e-05, | |
| "loss": 2.532, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4342105263157895e-05, | |
| "loss": 2.5302, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.431764820974369e-05, | |
| "loss": 2.526, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4293680297397771e-05, | |
| "loss": 2.537, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.426971238505185e-05, | |
| "loss": 2.5316, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4245744472705928e-05, | |
| "loss": 2.5305, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4221287419291726e-05, | |
| "loss": 2.517, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4196830365877521e-05, | |
| "loss": 2.5178, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.511163768245335, | |
| "eval_loss": 2.3697993755340576, | |
| "eval_runtime": 32.6726, | |
| "eval_samples_per_second": 74.466, | |
| "eval_steps_per_second": 4.683, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.41728624535316e-05, | |
| "loss": 2.5196, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4148894541185679e-05, | |
| "loss": 2.5385, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4124437487771474e-05, | |
| "loss": 2.537, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4100469575425555e-05, | |
| "loss": 2.5318, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4076012522011348e-05, | |
| "loss": 2.5331, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4051555468597144e-05, | |
| "loss": 2.53, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4027098415182941e-05, | |
| "loss": 2.5301, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4003130502837018e-05, | |
| "loss": 2.5358, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.3978673449422815e-05, | |
| "loss": 2.5182, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.3954705537076894e-05, | |
| "loss": 2.5345, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.5114412638355682, | |
| "eval_loss": 2.3686695098876953, | |
| "eval_runtime": 33.0698, | |
| "eval_samples_per_second": 73.572, | |
| "eval_steps_per_second": 4.627, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.393024848366269e-05, | |
| "loss": 2.5227, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.3905791430248485e-05, | |
| "loss": 2.5324, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.388133437683428e-05, | |
| "loss": 2.5163, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.3856877323420074e-05, | |
| "loss": 2.5227, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.3832909411074157e-05, | |
| "loss": 2.5351, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.3808452357659949e-05, | |
| "loss": 2.5269, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.3783995304245746e-05, | |
| "loss": 2.5377, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3761005674036395e-05, | |
| "loss": 2.5336, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3736548620622188e-05, | |
| "loss": 2.526, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3712091567207984e-05, | |
| "loss": 2.531, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.511461372211672, | |
| "eval_loss": 2.367508888244629, | |
| "eval_runtime": 32.6315, | |
| "eval_samples_per_second": 74.56, | |
| "eval_steps_per_second": 4.689, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.368763451379378e-05, | |
| "loss": 2.5183, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3664155742516143e-05, | |
| "loss": 2.5289, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3639698689101939e-05, | |
| "loss": 2.5191, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3615241635687732e-05, | |
| "loss": 2.5241, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3590784582273528e-05, | |
| "loss": 2.5237, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3566816669927607e-05, | |
| "loss": 2.5301, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3542848757581689e-05, | |
| "loss": 2.5191, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3519369986304053e-05, | |
| "loss": 2.5184, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3494912932889848e-05, | |
| "loss": 2.527, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3470945020543927e-05, | |
| "loss": 2.5304, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.511769432533583, | |
| "eval_loss": 2.3661422729492188, | |
| "eval_runtime": 32.5737, | |
| "eval_samples_per_second": 74.692, | |
| "eval_steps_per_second": 4.697, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3446487967129722e-05, | |
| "loss": 2.5411, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3422030913715516e-05, | |
| "loss": 2.5291, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.339855214243788e-05, | |
| "loss": 2.5233, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3374095089023675e-05, | |
| "loss": 2.5259, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.334963803560947e-05, | |
| "loss": 2.5218, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3326159264331835e-05, | |
| "loss": 2.5301, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.330170221091763e-05, | |
| "loss": 2.519, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3277245157503424e-05, | |
| "loss": 2.5291, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3253277245157506e-05, | |
| "loss": 2.5241, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.32288201917433e-05, | |
| "loss": 2.5264, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.5121217312829225, | |
| "eval_loss": 2.3653178215026855, | |
| "eval_runtime": 32.9474, | |
| "eval_samples_per_second": 73.845, | |
| "eval_steps_per_second": 4.644, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.320485227939738e-05, | |
| "loss": 2.5259, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3180884367051459e-05, | |
| "loss": 2.5211, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3156427313637254e-05, | |
| "loss": 2.5171, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.313197026022305e-05, | |
| "loss": 2.5365, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3108002347877129e-05, | |
| "loss": 2.5259, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3083545294462924e-05, | |
| "loss": 2.5333, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3059577382117003e-05, | |
| "loss": 2.5238, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3035609469771082e-05, | |
| "loss": 2.5238, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3011152416356879e-05, | |
| "loss": 2.5237, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.2987673645079241e-05, | |
| "loss": 2.5281, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.5123228150439609, | |
| "eval_loss": 2.3646602630615234, | |
| "eval_runtime": 32.7106, | |
| "eval_samples_per_second": 74.38, | |
| "eval_steps_per_second": 4.677, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.296370573273332e-05, | |
| "loss": 2.5268, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2939248679319117e-05, | |
| "loss": 2.5184, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2914791625904912e-05, | |
| "loss": 2.5281, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2890823713558991e-05, | |
| "loss": 2.5295, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2866366660144787e-05, | |
| "loss": 2.5167, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2841909606730582e-05, | |
| "loss": 2.5253, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.281745255331638e-05, | |
| "loss": 2.5242, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2793484640970456e-05, | |
| "loss": 2.5257, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.277000586969282e-05, | |
| "loss": 2.5361, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2745548816278617e-05, | |
| "loss": 2.5259, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.51232844538927, | |
| "eval_loss": 2.3635854721069336, | |
| "eval_runtime": 32.8056, | |
| "eval_samples_per_second": 74.164, | |
| "eval_steps_per_second": 4.664, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2721580903932696e-05, | |
| "loss": 2.5093, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2697123850518492e-05, | |
| "loss": 2.5149, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2672666797104285e-05, | |
| "loss": 2.5249, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2648698884758366e-05, | |
| "loss": 2.5316, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2624241831344161e-05, | |
| "loss": 2.5086, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.260027391899824e-05, | |
| "loss": 2.5219, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2575816865584036e-05, | |
| "loss": 2.5162, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2551848953238114e-05, | |
| "loss": 2.516, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2527391899823912e-05, | |
| "loss": 2.5206, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2502934846409707e-05, | |
| "loss": 2.5075, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.5121699913855717, | |
| "eval_loss": 2.362924337387085, | |
| "eval_runtime": 32.9662, | |
| "eval_samples_per_second": 73.803, | |
| "eval_steps_per_second": 4.641, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2478966934063786e-05, | |
| "loss": 2.5232, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2454999021717865e-05, | |
| "loss": 2.5285, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.243054196830366e-05, | |
| "loss": 2.5247, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2406574055957739e-05, | |
| "loss": 2.5207, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.238260614361182e-05, | |
| "loss": 2.518, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2358149090197613e-05, | |
| "loss": 2.5202, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2333692036783409e-05, | |
| "loss": 2.5151, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2310213265505772e-05, | |
| "loss": 2.5139, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2285756212091568e-05, | |
| "loss": 2.5141, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2261788299745647e-05, | |
| "loss": 2.5147, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.5127105045352431, | |
| "eval_loss": 2.36214280128479, | |
| "eval_runtime": 32.6511, | |
| "eval_samples_per_second": 74.515, | |
| "eval_steps_per_second": 4.686, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2237820387399729e-05, | |
| "loss": 2.5304, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2213363333985523e-05, | |
| "loss": 2.5098, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2188906280571318e-05, | |
| "loss": 2.5328, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2165427509293682e-05, | |
| "loss": 2.505, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.214145959694776e-05, | |
| "loss": 2.5194, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2117002543533556e-05, | |
| "loss": 2.5094, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2092545490119351e-05, | |
| "loss": 2.5258, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2068088436705147e-05, | |
| "loss": 2.5215, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.204363138329094e-05, | |
| "loss": 2.5172, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2019663470945023e-05, | |
| "loss": 2.5137, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.5127627863131131, | |
| "eval_loss": 2.361149787902832, | |
| "eval_runtime": 33.1496, | |
| "eval_samples_per_second": 73.395, | |
| "eval_steps_per_second": 4.615, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.1995206417530815e-05, | |
| "loss": 2.525, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.1971238505184897e-05, | |
| "loss": 2.5122, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.1947759733907261e-05, | |
| "loss": 2.5112, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.1923302680493056e-05, | |
| "loss": 2.5175, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.189884562707885e-05, | |
| "loss": 2.5067, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.1874388573664646e-05, | |
| "loss": 2.5203, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.1849931520250441e-05, | |
| "loss": 2.52, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.182596360790452e-05, | |
| "loss": 2.5236, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.1801995695558599e-05, | |
| "loss": 2.5242, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.177802778321268e-05, | |
| "loss": 2.5206, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.5128585021833675, | |
| "eval_loss": 2.3603355884552, | |
| "eval_runtime": 32.6199, | |
| "eval_samples_per_second": 74.586, | |
| "eval_steps_per_second": 4.69, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1753570729798476e-05, | |
| "loss": 2.5156, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.172911367638427e-05, | |
| "loss": 2.5109, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.170514576403835e-05, | |
| "loss": 2.519, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1680688710624144e-05, | |
| "loss": 2.537, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.165623165720994e-05, | |
| "loss": 2.5155, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1632752885932304e-05, | |
| "loss": 2.5149, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1608784973586382e-05, | |
| "loss": 2.5142, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1584327920172178e-05, | |
| "loss": 2.5056, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1559870866757973e-05, | |
| "loss": 2.524, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1536392095480337e-05, | |
| "loss": 2.5153, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.5128440241525727, | |
| "eval_loss": 2.359724998474121, | |
| "eval_runtime": 32.6238, | |
| "eval_samples_per_second": 74.577, | |
| "eval_steps_per_second": 4.69, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1511935042066134e-05, | |
| "loss": 2.5147, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1487477988651926e-05, | |
| "loss": 2.5183, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1463020935237724e-05, | |
| "loss": 2.5125, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1438563881823519e-05, | |
| "loss": 2.5165, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1414595969477598e-05, | |
| "loss": 2.525, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1390138916063393e-05, | |
| "loss": 2.5231, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1367149285854042e-05, | |
| "loss": 2.5239, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1343670514576404e-05, | |
| "loss": 2.5146, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.13192134611622e-05, | |
| "loss": 2.5353, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1294756407747995e-05, | |
| "loss": 2.5184, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.5130169561870658, | |
| "eval_loss": 2.358973264694214, | |
| "eval_runtime": 32.9217, | |
| "eval_samples_per_second": 73.903, | |
| "eval_steps_per_second": 4.647, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1270788495402074e-05, | |
| "loss": 2.5251, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.124633144198787e-05, | |
| "loss": 2.5143, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1221874388573667e-05, | |
| "loss": 2.502, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1197906476227745e-05, | |
| "loss": 2.5125, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1173938563881826e-05, | |
| "loss": 2.5081, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.114948151046762e-05, | |
| "loss": 2.5133, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1125024457053415e-05, | |
| "loss": 2.517, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.110056740363921e-05, | |
| "loss": 2.512, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1076110350225006e-05, | |
| "loss": 2.5067, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1053120720015653e-05, | |
| "loss": 2.5104, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.5131923012266913, | |
| "eval_loss": 2.35813307762146, | |
| "eval_runtime": 32.6499, | |
| "eval_samples_per_second": 74.518, | |
| "eval_steps_per_second": 4.686, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1028663666601449e-05, | |
| "loss": 2.5125, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1004695754255527e-05, | |
| "loss": 2.5192, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0980727841909608e-05, | |
| "loss": 2.5033, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0956270788495402e-05, | |
| "loss": 2.5033, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0932302876149484e-05, | |
| "loss": 2.5134, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0908334963803562e-05, | |
| "loss": 2.5148, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0884367051457641e-05, | |
| "loss": 2.5006, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0859909998043437e-05, | |
| "loss": 2.5072, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0835452944629232e-05, | |
| "loss": 2.5137, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0810995891215028e-05, | |
| "loss": 2.5085, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.5133596029158755, | |
| "eval_loss": 2.3577353954315186, | |
| "eval_runtime": 32.7631, | |
| "eval_samples_per_second": 74.26, | |
| "eval_steps_per_second": 4.67, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0786538837800822e-05, | |
| "loss": 2.5277, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0762081784386617e-05, | |
| "loss": 2.5148, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.073860301310898e-05, | |
| "loss": 2.5241, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0714145959694778e-05, | |
| "loss": 2.5142, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0690178047348857e-05, | |
| "loss": 2.5231, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0666210135002937e-05, | |
| "loss": 2.5105, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0641753081588731e-05, | |
| "loss": 2.5149, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0617785169242811e-05, | |
| "loss": 2.5092, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.059381725689689e-05, | |
| "loss": 2.5284, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0569360203482686e-05, | |
| "loss": 2.509, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.5135132309093088, | |
| "eval_loss": 2.357166290283203, | |
| "eval_runtime": 32.782, | |
| "eval_samples_per_second": 74.218, | |
| "eval_steps_per_second": 4.667, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.054490315006848e-05, | |
| "loss": 2.5078, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0520446096654275e-05, | |
| "loss": 2.5138, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.049598904324007e-05, | |
| "loss": 2.5065, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0472510271962434e-05, | |
| "loss": 2.5247, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0448053218548231e-05, | |
| "loss": 2.5161, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0423596165134025e-05, | |
| "loss": 2.5142, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0399628252788106e-05, | |
| "loss": 2.5067, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0375171199373901e-05, | |
| "loss": 2.5104, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.035120328702798e-05, | |
| "loss": 2.5177, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0326746233613775e-05, | |
| "loss": 2.5143, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.5135220785947945, | |
| "eval_loss": 2.356419563293457, | |
| "eval_runtime": 32.6508, | |
| "eval_samples_per_second": 74.516, | |
| "eval_steps_per_second": 4.686, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0302778321267854e-05, | |
| "loss": 2.5068, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.027832126785365e-05, | |
| "loss": 2.5129, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0254842496576013e-05, | |
| "loss": 2.521, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0231363725298377e-05, | |
| "loss": 2.5188, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0206906671884171e-05, | |
| "loss": 2.5141, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0182938759538253e-05, | |
| "loss": 2.5039, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.015897084719233e-05, | |
| "loss": 2.5123, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0135002934846409e-05, | |
| "loss": 2.5113, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0110545881432206e-05, | |
| "loss": 2.503, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0086088828018002e-05, | |
| "loss": 2.5124, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.5137456837370693, | |
| "eval_loss": 2.355473279953003, | |
| "eval_runtime": 32.7777, | |
| "eval_samples_per_second": 74.227, | |
| "eval_steps_per_second": 4.668, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0061631774603797e-05, | |
| "loss": 2.5079, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0037174721189591e-05, | |
| "loss": 2.5096, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0012717667775386e-05, | |
| "loss": 2.5166, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.988260614361182e-06, | |
| "loss": 2.5056, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.963803560946977e-06, | |
| "loss": 2.5089, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.939835648601058e-06, | |
| "loss": 2.5149, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.915867736255137e-06, | |
| "loss": 2.5188, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.891410682840932e-06, | |
| "loss": 2.5172, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.866953629426728e-06, | |
| "loss": 2.5132, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.842496576012523e-06, | |
| "loss": 2.5107, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.513869551333869, | |
| "eval_loss": 2.354633092880249, | |
| "eval_runtime": 31.6609, | |
| "eval_samples_per_second": 76.845, | |
| "eval_steps_per_second": 4.832, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.818528663666602e-06, | |
| "loss": 2.5121, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.795049892388966e-06, | |
| "loss": 2.4904, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.770592838974761e-06, | |
| "loss": 2.5034, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.747114067697125e-06, | |
| "loss": 2.4998, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.72265701428292e-06, | |
| "loss": 2.4988, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.698199960868716e-06, | |
| "loss": 2.5118, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.673742907454511e-06, | |
| "loss": 2.5137, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.649285854040305e-06, | |
| "loss": 2.5139, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.625807082762669e-06, | |
| "loss": 2.5133, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.601350029348466e-06, | |
| "loss": 2.5034, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.513999853611022, | |
| "eval_loss": 2.354314088821411, | |
| "eval_runtime": 32.5811, | |
| "eval_samples_per_second": 74.675, | |
| "eval_steps_per_second": 4.696, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.577382117002543e-06, | |
| "loss": 2.5222, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.553414204656623e-06, | |
| "loss": 2.5016, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.528957151242419e-06, | |
| "loss": 2.5188, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.504500097828214e-06, | |
| "loss": 2.5084, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.48004304441401e-06, | |
| "loss": 2.5053, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.455585990999805e-06, | |
| "loss": 2.506, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.431618078653884e-06, | |
| "loss": 2.5099, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.40716102523968e-06, | |
| "loss": 2.502, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.383193112893758e-06, | |
| "loss": 2.5054, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.358736059479556e-06, | |
| "loss": 2.4922, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.5139121810912092, | |
| "eval_loss": 2.353778839111328, | |
| "eval_runtime": 32.8198, | |
| "eval_samples_per_second": 74.132, | |
| "eval_steps_per_second": 4.662, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.33427900606535e-06, | |
| "loss": 2.5071, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.309821952651145e-06, | |
| "loss": 2.5125, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.285854040305224e-06, | |
| "loss": 2.5201, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.261886127959304e-06, | |
| "loss": 2.5112, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.237918215613385e-06, | |
| "loss": 2.5034, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.213461162199178e-06, | |
| "loss": 2.4971, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.189004108784974e-06, | |
| "loss": 2.5133, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.16454705537077e-06, | |
| "loss": 2.5301, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.14057914302485e-06, | |
| "loss": 2.5093, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.116611230678929e-06, | |
| "loss": 2.514, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.513995027600757, | |
| "eval_loss": 2.3532376289367676, | |
| "eval_runtime": 32.6183, | |
| "eval_samples_per_second": 74.59, | |
| "eval_steps_per_second": 4.691, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.092154177264724e-06, | |
| "loss": 2.51, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.06769712385052e-06, | |
| "loss": 2.4977, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.043240070436315e-06, | |
| "loss": 2.5125, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.019761299158679e-06, | |
| "loss": 2.5002, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.995793386812758e-06, | |
| "loss": 2.5025, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.971336333398553e-06, | |
| "loss": 2.5102, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.947368421052632e-06, | |
| "loss": 2.499, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.922911367638427e-06, | |
| "loss": 2.5112, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.898454314224223e-06, | |
| "loss": 2.5066, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.873997260810018e-06, | |
| "loss": 2.5199, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.5140706350949075, | |
| "eval_loss": 2.3526594638824463, | |
| "eval_runtime": 32.7339, | |
| "eval_samples_per_second": 74.327, | |
| "eval_steps_per_second": 4.674, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.849540207395814e-06, | |
| "loss": 2.5014, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.825572295049893e-06, | |
| "loss": 2.4882, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.801115241635688e-06, | |
| "loss": 2.4938, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.777147329289769e-06, | |
| "loss": 2.5049, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.752690275875562e-06, | |
| "loss": 2.4916, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.728233222461358e-06, | |
| "loss": 2.504, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.704265310115438e-06, | |
| "loss": 2.5074, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.680297397769517e-06, | |
| "loss": 2.5175, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.655840344355313e-06, | |
| "loss": 2.5207, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.631383290941108e-06, | |
| "loss": 2.4926, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.5141896766814423, | |
| "eval_loss": 2.3520689010620117, | |
| "eval_runtime": 32.717, | |
| "eval_samples_per_second": 74.365, | |
| "eval_steps_per_second": 4.676, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.606926237526904e-06, | |
| "loss": 2.5076, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.582469184112699e-06, | |
| "loss": 2.5023, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.558012130698495e-06, | |
| "loss": 2.4904, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.535022500489142e-06, | |
| "loss": 2.5013, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.510565447074937e-06, | |
| "loss": 2.5109, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.4870866757973e-06, | |
| "loss": 2.5075, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.462629622383096e-06, | |
| "loss": 2.5093, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.438172568968892e-06, | |
| "loss": 2.5033, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.413715515554687e-06, | |
| "loss": 2.4903, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.389747603208766e-06, | |
| "loss": 2.5104, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.5141647422950735, | |
| "eval_loss": 2.3516719341278076, | |
| "eval_runtime": 32.5398, | |
| "eval_samples_per_second": 74.77, | |
| "eval_steps_per_second": 4.702, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.365290549794561e-06, | |
| "loss": 2.5064, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.341322637448642e-06, | |
| "loss": 2.5011, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.317354725102719e-06, | |
| "loss": 2.5028, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.292897671688516e-06, | |
| "loss": 2.4954, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.26844061827431e-06, | |
| "loss": 2.514, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.24447270592839e-06, | |
| "loss": 2.4848, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.220015652514186e-06, | |
| "loss": 2.5135, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.196047740168265e-06, | |
| "loss": 2.5149, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.17159068675406e-06, | |
| "loss": 2.5076, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.147133633339856e-06, | |
| "loss": 2.5067, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.5143770867467302, | |
| "eval_loss": 2.3510823249816895, | |
| "eval_runtime": 32.9679, | |
| "eval_samples_per_second": 73.799, | |
| "eval_steps_per_second": 4.641, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.122676579925651e-06, | |
| "loss": 2.5042, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.098708667579732e-06, | |
| "loss": 2.4911, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.074251614165525e-06, | |
| "loss": 2.5085, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.049794560751321e-06, | |
| "loss": 2.5185, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.025337507337116e-06, | |
| "loss": 2.4945, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.001369594991197e-06, | |
| "loss": 2.5176, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.97789082371356e-06, | |
| "loss": 2.5036, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.953433770299354e-06, | |
| "loss": 2.5015, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.929954999021718e-06, | |
| "loss": 2.5086, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.905497945607514e-06, | |
| "loss": 2.5055, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.5142451757994889, | |
| "eval_loss": 2.3508098125457764, | |
| "eval_runtime": 32.5406, | |
| "eval_samples_per_second": 74.768, | |
| "eval_steps_per_second": 4.702, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.881040892193309e-06, | |
| "loss": 2.5044, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.856583838779105e-06, | |
| "loss": 2.5009, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.8321267853649e-06, | |
| "loss": 2.511, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.808648014087264e-06, | |
| "loss": 2.5019, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.78419096067306e-06, | |
| "loss": 2.503, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.759733907258855e-06, | |
| "loss": 2.5006, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.73527685384465e-06, | |
| "loss": 2.5043, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.711308941498729e-06, | |
| "loss": 2.4988, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.687341029152808e-06, | |
| "loss": 2.5079, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.662883975738603e-06, | |
| "loss": 2.5011, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.5145990832189167, | |
| "eval_loss": 2.3502306938171387, | |
| "eval_runtime": 32.5132, | |
| "eval_samples_per_second": 74.831, | |
| "eval_steps_per_second": 4.706, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.639405204460967e-06, | |
| "loss": 2.5172, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.615437292115047e-06, | |
| "loss": 2.502, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.590980238700842e-06, | |
| "loss": 2.5124, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.567012326354921e-06, | |
| "loss": 2.4933, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.542555272940717e-06, | |
| "loss": 2.5154, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.518098219526512e-06, | |
| "loss": 2.4982, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.4936411661123074e-06, | |
| "loss": 2.4936, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.470162394834671e-06, | |
| "loss": 2.5064, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.445705341420466e-06, | |
| "loss": 2.5003, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.421248288006262e-06, | |
| "loss": 2.4931, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.5147076684498775, | |
| "eval_loss": 2.349609375, | |
| "eval_runtime": 32.9366, | |
| "eval_samples_per_second": 73.869, | |
| "eval_steps_per_second": 4.645, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.396791234592057e-06, | |
| "loss": 2.5008, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.372334181177852e-06, | |
| "loss": 2.5034, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.348366268831931e-06, | |
| "loss": 2.5083, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.324398356486011e-06, | |
| "loss": 2.5028, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.299941303071807e-06, | |
| "loss": 2.5082, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.275973390725886e-06, | |
| "loss": 2.52, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.251516337311681e-06, | |
| "loss": 2.5099, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.228037566034045e-06, | |
| "loss": 2.5112, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.20358051261984e-06, | |
| "loss": 2.4946, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.179123459205636e-06, | |
| "loss": 2.4965, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.5147020381045684, | |
| "eval_loss": 2.34912109375, | |
| "eval_runtime": 32.715, | |
| "eval_samples_per_second": 74.37, | |
| "eval_steps_per_second": 4.677, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.154666405791431e-06, | |
| "loss": 2.5126, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.130209352377226e-06, | |
| "loss": 2.5, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.10673058109959e-06, | |
| "loss": 2.4946, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.082762668753669e-06, | |
| "loss": 2.5005, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.058305615339465e-06, | |
| "loss": 2.4972, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.03384856192526e-06, | |
| "loss": 2.4976, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.009391508511055e-06, | |
| "loss": 2.5075, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.985912737233419e-06, | |
| "loss": 2.508, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.961944824887498e-06, | |
| "loss": 2.5023, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.937487771473294e-06, | |
| "loss": 2.495, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.5146360826309477, | |
| "eval_loss": 2.348769426345825, | |
| "eval_runtime": 32.8878, | |
| "eval_samples_per_second": 73.979, | |
| "eval_steps_per_second": 4.652, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.9135198591273735e-06, | |
| "loss": 2.5072, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.889551946781452e-06, | |
| "loss": 2.509, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.865094893367248e-06, | |
| "loss": 2.4979, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.841126981021327e-06, | |
| "loss": 2.5134, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.816669927607122e-06, | |
| "loss": 2.4994, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.792212874192918e-06, | |
| "loss": 2.5072, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.768244961846997e-06, | |
| "loss": 2.5068, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.743787908432793e-06, | |
| "loss": 2.5097, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.719819996086871e-06, | |
| "loss": 2.4966, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.695362942672668e-06, | |
| "loss": 2.5051, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.5150479021735546, | |
| "eval_loss": 2.348109245300293, | |
| "eval_runtime": 32.717, | |
| "eval_samples_per_second": 74.365, | |
| "eval_steps_per_second": 4.676, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.670905889258462e-06, | |
| "loss": 2.5036, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.646937976912542e-06, | |
| "loss": 2.4975, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.6224809234983375e-06, | |
| "loss": 2.485, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.598513011152416e-06, | |
| "loss": 2.4965, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.574055957738213e-06, | |
| "loss": 2.4911, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.549598904324007e-06, | |
| "loss": 2.5005, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.525141850909803e-06, | |
| "loss": 2.496, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.501173938563883e-06, | |
| "loss": 2.4988, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.477206026217961e-06, | |
| "loss": 2.4977, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.4532381138720416e-06, | |
| "loss": 2.51, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.5149642513289626, | |
| "eval_loss": 2.3477537631988525, | |
| "eval_runtime": 32.5166, | |
| "eval_samples_per_second": 74.823, | |
| "eval_steps_per_second": 4.705, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.428781060457837e-06, | |
| "loss": 2.5063, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.404324007043632e-06, | |
| "loss": 2.4999, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.379866953629428e-06, | |
| "loss": 2.4941, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.355899041283507e-06, | |
| "loss": 2.5031, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.331441987869302e-06, | |
| "loss": 2.5015, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.307474075523381e-06, | |
| "loss": 2.5091, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.283506163177461e-06, | |
| "loss": 2.4905, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.259049109763257e-06, | |
| "loss": 2.5008, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.234592056349052e-06, | |
| "loss": 2.4837, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.210624144003131e-06, | |
| "loss": 2.4883, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_accuracy": 0.515170161100266, | |
| "eval_loss": 2.347412586212158, | |
| "eval_runtime": 32.8011, | |
| "eval_samples_per_second": 74.174, | |
| "eval_steps_per_second": 4.664, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.186167090588926e-06, | |
| "loss": 2.5017, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.1621991782430055e-06, | |
| "loss": 2.4983, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.137742124828802e-06, | |
| "loss": 2.5059, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.1132850714145965e-06, | |
| "loss": 2.5119, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.089317159068676e-06, | |
| "loss": 2.5034, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.065349246722755e-06, | |
| "loss": 2.5012, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.0413813343768345e-06, | |
| "loss": 2.5052, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.016924280962631e-06, | |
| "loss": 2.5008, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.992956368616709e-06, | |
| "loss": 2.4927, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.968499315202505e-06, | |
| "loss": 2.4973, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.515144422378853, | |
| "eval_loss": 2.3470253944396973, | |
| "eval_runtime": 32.569, | |
| "eval_samples_per_second": 74.703, | |
| "eval_steps_per_second": 4.698, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.9440422617883e-06, | |
| "loss": 2.4978, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.919585208374096e-06, | |
| "loss": 2.4971, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.895128154959891e-06, | |
| "loss": 2.497, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.87116024261397e-06, | |
| "loss": 2.4949, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.847681471336334e-06, | |
| "loss": 2.4992, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.823224417922129e-06, | |
| "loss": 2.5073, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.798767364507924e-06, | |
| "loss": 2.5131, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.7743103110937205e-06, | |
| "loss": 2.4901, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.749853257679515e-06, | |
| "loss": 2.4982, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.725396204265311e-06, | |
| "loss": 2.4939, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.5153318324441409, | |
| "eval_loss": 2.346403121948242, | |
| "eval_runtime": 32.5012, | |
| "eval_samples_per_second": 74.859, | |
| "eval_steps_per_second": 4.708, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.7019174329876736e-06, | |
| "loss": 2.4936, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.67746037957347e-06, | |
| "loss": 2.4974, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.6530033261592646e-06, | |
| "loss": 2.4885, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.629524554881628e-06, | |
| "loss": 2.5044, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.605556642535708e-06, | |
| "loss": 2.4987, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.5815887301897875e-06, | |
| "loss": 2.5019, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.557131676775582e-06, | |
| "loss": 2.5086, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.5326746233613785e-06, | |
| "loss": 2.5045, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.508217569947173e-06, | |
| "loss": 2.4995, | |
| "step": 29950 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.483760516532969e-06, | |
| "loss": 2.4952, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.5152570292850346, | |
| "eval_loss": 2.3460702896118164, | |
| "eval_runtime": 32.6916, | |
| "eval_samples_per_second": 74.423, | |
| "eval_steps_per_second": 4.68, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.459303463118763e-06, | |
| "loss": 2.5039, | |
| "step": 30050 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.435335550772844e-06, | |
| "loss": 2.5014, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.411367638426923e-06, | |
| "loss": 2.4918, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.386910585012718e-06, | |
| "loss": 2.4954, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.3624535315985135e-06, | |
| "loss": 2.4942, | |
| "step": 30250 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.338485619252592e-06, | |
| "loss": 2.4852, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.315006847974956e-06, | |
| "loss": 2.5039, | |
| "step": 30350 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.290549794560752e-06, | |
| "loss": 2.4945, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.266581882214831e-06, | |
| "loss": 2.5077, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.242613969868911e-06, | |
| "loss": 2.5028, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.5153961792476732, | |
| "eval_loss": 2.345855712890625, | |
| "eval_runtime": 32.4963, | |
| "eval_samples_per_second": 74.87, | |
| "eval_steps_per_second": 4.708, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.218156916454706e-06, | |
| "loss": 2.5017, | |
| "step": 30550 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.193699863040501e-06, | |
| "loss": 2.4878, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.169242809626297e-06, | |
| "loss": 2.4964, | |
| "step": 30650 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.144785756212092e-06, | |
| "loss": 2.494, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.1208178438661714e-06, | |
| "loss": 2.4985, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.096849931520251e-06, | |
| "loss": 2.491, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.07288201917433e-06, | |
| "loss": 2.4893, | |
| "step": 30850 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.048424965760126e-06, | |
| "loss": 2.4917, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.024457053414205e-06, | |
| "loss": 2.4879, | |
| "step": 30950 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.000978282136568e-06, | |
| "loss": 2.4979, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.5153632015108629, | |
| "eval_loss": 2.3453683853149414, | |
| "eval_runtime": 32.8384, | |
| "eval_samples_per_second": 74.09, | |
| "eval_steps_per_second": 4.659, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.976521228722364e-06, | |
| "loss": 2.5128, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.95206417530816e-06, | |
| "loss": 2.5052, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.927607121893955e-06, | |
| "loss": 2.5018, | |
| "step": 31150 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.90315006847975e-06, | |
| "loss": 2.5049, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.878693015065545e-06, | |
| "loss": 2.497, | |
| "step": 31250 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.854725102719625e-06, | |
| "loss": 2.4941, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.8302680493054195e-06, | |
| "loss": 2.5037, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.8063001369595e-06, | |
| "loss": 2.4963, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.782332224613579e-06, | |
| "loss": 2.4972, | |
| "step": 31450 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.757875171199374e-06, | |
| "loss": 2.4928, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.5154951124581042, | |
| "eval_loss": 2.345027208328247, | |
| "eval_runtime": 32.6929, | |
| "eval_samples_per_second": 74.42, | |
| "eval_steps_per_second": 4.68, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.73341811778517e-06, | |
| "loss": 2.5037, | |
| "step": 31550 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.708961064370965e-06, | |
| "loss": 2.505, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.684993152025045e-06, | |
| "loss": 2.5032, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.661514380747408e-06, | |
| "loss": 2.5132, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.637057327333203e-06, | |
| "loss": 2.5075, | |
| "step": 31750 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.612600273918999e-06, | |
| "loss": 2.4932, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.588143220504794e-06, | |
| "loss": 2.4801, | |
| "step": 31850 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.564664449227157e-06, | |
| "loss": 2.5061, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.5402073958129526e-06, | |
| "loss": 2.5008, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.515750342398748e-06, | |
| "loss": 2.501, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.5156221973950805, | |
| "eval_loss": 2.344646692276001, | |
| "eval_runtime": 32.688, | |
| "eval_samples_per_second": 74.431, | |
| "eval_steps_per_second": 4.681, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.492271571121112e-06, | |
| "loss": 2.4899, | |
| "step": 32050 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.468303658775191e-06, | |
| "loss": 2.4936, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.443846605360986e-06, | |
| "loss": 2.4883, | |
| "step": 32150 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.4193895519467815e-06, | |
| "loss": 2.493, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.394932498532577e-06, | |
| "loss": 2.4964, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.3704754451183725e-06, | |
| "loss": 2.5093, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.346018391704168e-06, | |
| "loss": 2.5009, | |
| "step": 32350 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.322050479358248e-06, | |
| "loss": 2.4905, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.298082567012326e-06, | |
| "loss": 2.4964, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.274114654666406e-06, | |
| "loss": 2.5, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.5156302407455221, | |
| "eval_loss": 2.344324827194214, | |
| "eval_runtime": 32.7043, | |
| "eval_samples_per_second": 74.394, | |
| "eval_steps_per_second": 4.678, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.2496576012522015e-06, | |
| "loss": 2.504, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.225200547837997e-06, | |
| "loss": 2.4964, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.2007434944237925e-06, | |
| "loss": 2.5011, | |
| "step": 32650 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.177264723146155e-06, | |
| "loss": 2.4929, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.152807669731951e-06, | |
| "loss": 2.4895, | |
| "step": 32750 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.1288397573860305e-06, | |
| "loss": 2.4839, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.10487184504011e-06, | |
| "loss": 2.4969, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.080414791625905e-06, | |
| "loss": 2.4876, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.0559577382117e-06, | |
| "loss": 2.4903, | |
| "step": 32950 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.03198982586578e-06, | |
| "loss": 2.4865, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.5156238060651689, | |
| "eval_loss": 2.343801259994507, | |
| "eval_runtime": 32.5872, | |
| "eval_samples_per_second": 74.661, | |
| "eval_steps_per_second": 4.695, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.007532772451575e-06, | |
| "loss": 2.5003, | |
| "step": 33050 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.983564860105655e-06, | |
| "loss": 2.4968, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.9591078066914504e-06, | |
| "loss": 2.4738, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.935139894345529e-06, | |
| "loss": 2.4972, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.911171981999609e-06, | |
| "loss": 2.4924, | |
| "step": 33250 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.886714928585404e-06, | |
| "loss": 2.4915, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.8622578751712e-06, | |
| "loss": 2.4946, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.837800821756995e-06, | |
| "loss": 2.4924, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.8133437683427904e-06, | |
| "loss": 2.4889, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.788886714928586e-06, | |
| "loss": 2.4898, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.5156752835079947, | |
| "eval_loss": 2.3433618545532227, | |
| "eval_runtime": 32.4889, | |
| "eval_samples_per_second": 74.887, | |
| "eval_steps_per_second": 4.709, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.764918802582665e-06, | |
| "loss": 2.4994, | |
| "step": 33550 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.7414400313050288e-06, | |
| "loss": 2.5027, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.716982977890824e-06, | |
| "loss": 2.4859, | |
| "step": 33650 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.6935042066131876e-06, | |
| "loss": 2.4952, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.669047153198983e-06, | |
| "loss": 2.4965, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6450792408530623e-06, | |
| "loss": 2.507, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6206221874388573e-06, | |
| "loss": 2.4879, | |
| "step": 33850 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.596165134024653e-06, | |
| "loss": 2.4995, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.5717080806104483e-06, | |
| "loss": 2.4978, | |
| "step": 33950 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.5472510271962434e-06, | |
| "loss": 2.4977, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.515959213778581, | |
| "eval_loss": 2.3429620265960693, | |
| "eval_runtime": 32.8572, | |
| "eval_samples_per_second": 74.048, | |
| "eval_steps_per_second": 4.657, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.522793973782039e-06, | |
| "loss": 2.4929, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.4988260614361185e-06, | |
| "loss": 2.4945, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.4748581490901977e-06, | |
| "loss": 2.4988, | |
| "step": 34150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.450401095675993e-06, | |
| "loss": 2.4937, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.4259440422617886e-06, | |
| "loss": 2.5015, | |
| "step": 34250 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.4019761299158683e-06, | |
| "loss": 2.499, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.3780082175699474e-06, | |
| "loss": 2.4989, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.353551164155743e-06, | |
| "loss": 2.5043, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.329583251809822e-06, | |
| "loss": 2.4918, | |
| "step": 34450 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.305126198395617e-06, | |
| "loss": 2.4904, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.5156961962191426, | |
| "eval_loss": 2.3426706790924072, | |
| "eval_runtime": 32.6066, | |
| "eval_samples_per_second": 74.617, | |
| "eval_steps_per_second": 4.692, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.2806691449814127e-06, | |
| "loss": 2.4934, | |
| "step": 34550 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.2562120915672086e-06, | |
| "loss": 2.4905, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.2317550381530037e-06, | |
| "loss": 2.4866, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.207297984738799e-06, | |
| "loss": 2.4916, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.1838192134611625e-06, | |
| "loss": 2.4913, | |
| "step": 34750 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.1603404421835258e-06, | |
| "loss": 2.4898, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.1358833887693213e-06, | |
| "loss": 2.4992, | |
| "step": 34850 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.1114263353551168e-06, | |
| "loss": 2.4833, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.086969281940912e-06, | |
| "loss": 2.5011, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.0625122285267073e-06, | |
| "loss": 2.4779, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.5159109536759318, | |
| "eval_loss": 2.342430353164673, | |
| "eval_runtime": 32.637, | |
| "eval_samples_per_second": 74.547, | |
| "eval_steps_per_second": 4.688, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.038544316180787e-06, | |
| "loss": 2.4945, | |
| "step": 35050 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.0140872627665824e-06, | |
| "loss": 2.4966, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.9901193504206616e-06, | |
| "loss": 2.4912, | |
| "step": 35150 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.965662297006457e-06, | |
| "loss": 2.5, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.9416943846605363e-06, | |
| "loss": 2.4955, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.9172373312463314e-06, | |
| "loss": 2.4884, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.892780277832127e-06, | |
| "loss": 2.4983, | |
| "step": 35350 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.8693015065544906e-06, | |
| "loss": 2.4981, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.84533359420857e-06, | |
| "loss": 2.496, | |
| "step": 35450 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.8208765407943657e-06, | |
| "loss": 2.4792, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.5158892366297396, | |
| "eval_loss": 2.3420228958129883, | |
| "eval_runtime": 32.5968, | |
| "eval_samples_per_second": 74.639, | |
| "eval_steps_per_second": 4.694, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.7964194873801608e-06, | |
| "loss": 2.4965, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.77245157503424e-06, | |
| "loss": 2.5008, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.748483662688319e-06, | |
| "loss": 2.4933, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.724515750342399e-06, | |
| "loss": 2.4984, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.7000586969281942e-06, | |
| "loss": 2.481, | |
| "step": 35750 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.6756016435139897e-06, | |
| "loss": 2.498, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.6511445900997852e-06, | |
| "loss": 2.4974, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.6266875366855803e-06, | |
| "loss": 2.4965, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.6022304832713758e-06, | |
| "loss": 2.4812, | |
| "step": 35950 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.577773429857171e-06, | |
| "loss": 2.4931, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.5160203432419368, | |
| "eval_loss": 2.3419036865234375, | |
| "eval_runtime": 32.1614, | |
| "eval_samples_per_second": 75.65, | |
| "eval_steps_per_second": 4.757, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.5533163764429663e-06, | |
| "loss": 2.4803, | |
| "step": 36050 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.52983760516533e-06, | |
| "loss": 2.5021, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.5053805517511256e-06, | |
| "loss": 2.4942, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.4814126394052048e-06, | |
| "loss": 2.4948, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.456955585991e-06, | |
| "loss": 2.488, | |
| "step": 36250 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.4329876736450794e-06, | |
| "loss": 2.4923, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.408530620230875e-06, | |
| "loss": 2.4896, | |
| "step": 36350 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.384562707884954e-06, | |
| "loss": 2.5058, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.3605947955390337e-06, | |
| "loss": 2.4995, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.336626883193113e-06, | |
| "loss": 2.4997, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.5160388429479523, | |
| "eval_loss": 2.3416337966918945, | |
| "eval_runtime": 32.6706, | |
| "eval_samples_per_second": 74.471, | |
| "eval_steps_per_second": 4.683, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.3121698297789084e-06, | |
| "loss": 2.4922, | |
| "step": 36550 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.2891801995695563e-06, | |
| "loss": 2.4925, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.2652122872236355e-06, | |
| "loss": 2.4839, | |
| "step": 36650 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.2407552338094305e-06, | |
| "loss": 2.4843, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.216298180395226e-06, | |
| "loss": 2.4843, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.1923302680493056e-06, | |
| "loss": 2.5024, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.1678732146351007e-06, | |
| "loss": 2.4881, | |
| "step": 36850 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.143416161220896e-06, | |
| "loss": 2.504, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.1189591078066917e-06, | |
| "loss": 2.4966, | |
| "step": 36950 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.0945020543924868e-06, | |
| "loss": 2.4986, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.5161289284728975, | |
| "eval_loss": 2.341364860534668, | |
| "eval_runtime": 32.1728, | |
| "eval_samples_per_second": 75.623, | |
| "eval_steps_per_second": 4.756, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.0705341420465664e-06, | |
| "loss": 2.4914, | |
| "step": 37050 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.046077088632362e-06, | |
| "loss": 2.4945, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.021620035218157e-06, | |
| "loss": 2.4977, | |
| "step": 37150 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.9981412639405207e-06, | |
| "loss": 2.4917, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.973684210526316e-06, | |
| "loss": 2.4918, | |
| "step": 37250 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.9497162981803953e-06, | |
| "loss": 2.4991, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.9257483858344745e-06, | |
| "loss": 2.5053, | |
| "step": 37350 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.9017804734885541e-06, | |
| "loss": 2.4826, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8773234200743496e-06, | |
| "loss": 2.4844, | |
| "step": 37450 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.852866366660145e-06, | |
| "loss": 2.4965, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.5162141879875779, | |
| "eval_loss": 2.341057538986206, | |
| "eval_runtime": 32.6333, | |
| "eval_samples_per_second": 74.556, | |
| "eval_steps_per_second": 4.688, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8284093132459402e-06, | |
| "loss": 2.4963, | |
| "step": 37550 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8039522598317355e-06, | |
| "loss": 2.4976, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.7804734885540992e-06, | |
| "loss": 2.4893, | |
| "step": 37650 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.7560164351398945e-06, | |
| "loss": 2.4976, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.732048522793974e-06, | |
| "loss": 2.4924, | |
| "step": 37750 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.7080806104480533e-06, | |
| "loss": 2.4884, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6836235570338488e-06, | |
| "loss": 2.4838, | |
| "step": 37850 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.659166503619644e-06, | |
| "loss": 2.4991, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6356877323420076e-06, | |
| "loss": 2.4943, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6112306789278029e-06, | |
| "loss": 2.4743, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.5161860362610324, | |
| "eval_loss": 2.3409061431884766, | |
| "eval_runtime": 33.3068, | |
| "eval_samples_per_second": 73.048, | |
| "eval_steps_per_second": 4.594, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5867736255135981e-06, | |
| "loss": 2.4938, | |
| "step": 38050 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5632948542359619e-06, | |
| "loss": 2.4884, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5388378008217572e-06, | |
| "loss": 2.4933, | |
| "step": 38150 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5143807474075524e-06, | |
| "loss": 2.5, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.490901976129916e-06, | |
| "loss": 2.4906, | |
| "step": 38250 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.4664449227157112e-06, | |
| "loss": 2.4821, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.4424770103697909e-06, | |
| "loss": 2.4861, | |
| "step": 38350 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.4180199569555861e-06, | |
| "loss": 2.4956, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3935629035413814e-06, | |
| "loss": 2.5016, | |
| "step": 38450 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3691058501271767e-06, | |
| "loss": 2.497, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.5163235775535828, | |
| "eval_loss": 2.3405728340148926, | |
| "eval_runtime": 32.196, | |
| "eval_samples_per_second": 75.568, | |
| "eval_steps_per_second": 4.752, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3456270788495404e-06, | |
| "loss": 2.4884, | |
| "step": 38550 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3211700254353357e-06, | |
| "loss": 2.4936, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.297202113089415e-06, | |
| "loss": 2.4894, | |
| "step": 38650 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.2737233418117786e-06, | |
| "loss": 2.4807, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.249266288397574e-06, | |
| "loss": 2.4942, | |
| "step": 38750 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.2248092349833692e-06, | |
| "loss": 2.4939, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.201330463705733e-06, | |
| "loss": 2.4968, | |
| "step": 38850 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.1768734102915282e-06, | |
| "loss": 2.4934, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.1524163568773235e-06, | |
| "loss": 2.5042, | |
| "step": 38950 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.1284484445314029e-06, | |
| "loss": 2.4942, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.5161972969516506, | |
| "eval_loss": 2.3403635025024414, | |
| "eval_runtime": 33.4158, | |
| "eval_samples_per_second": 72.81, | |
| "eval_steps_per_second": 4.579, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.1039913911171984e-06, | |
| "loss": 2.4909, | |
| "step": 39050 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.0800234787712776e-06, | |
| "loss": 2.4877, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.0565447074936413e-06, | |
| "loss": 2.4823, | |
| "step": 39150 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.0320876540794366e-06, | |
| "loss": 2.4907, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.007630600665232e-06, | |
| "loss": 2.4978, | |
| "step": 39250 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.831735472510274e-07, | |
| "loss": 2.4916, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.587164938368226e-07, | |
| "loss": 2.5033, | |
| "step": 39350 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.352377225591862e-07, | |
| "loss": 2.4962, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.107806691449815e-07, | |
| "loss": 2.4796, | |
| "step": 39450 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.868127567990608e-07, | |
| "loss": 2.4907, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.5162889911466841, | |
| "eval_loss": 2.3401567935943604, | |
| "eval_runtime": 33.2059, | |
| "eval_samples_per_second": 73.27, | |
| "eval_steps_per_second": 4.608, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.628448444531404e-07, | |
| "loss": 2.4889, | |
| "step": 39550 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.388769321072198e-07, | |
| "loss": 2.4849, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.144198786930152e-07, | |
| "loss": 2.486, | |
| "step": 39650 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.909411074153786e-07, | |
| "loss": 2.4921, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.66484054001174e-07, | |
| "loss": 2.4956, | |
| "step": 39750 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.420270005869694e-07, | |
| "loss": 2.4897, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.175699471727647e-07, | |
| "loss": 2.5071, | |
| "step": 39850 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.9311289375856e-07, | |
| "loss": 2.4944, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.686558403443554e-07, | |
| "loss": 2.4962, | |
| "step": 39950 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.446879279984349e-07, | |
| "loss": 2.4821, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.5163211645484503, | |
| "eval_loss": 2.3399698734283447, | |
| "eval_runtime": 32.4683, | |
| "eval_samples_per_second": 74.935, | |
| "eval_steps_per_second": 4.712, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.202308745842302e-07, | |
| "loss": 2.4895, | |
| "step": 40050 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.957738211700255e-07, | |
| "loss": 2.4924, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.713167677558208e-07, | |
| "loss": 2.5049, | |
| "step": 40150 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.473488554099002e-07, | |
| "loss": 2.4949, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.228918019956956e-07, | |
| "loss": 2.4972, | |
| "step": 40250 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.98923889649775e-07, | |
| "loss": 2.4936, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.7495597730385447e-07, | |
| "loss": 2.4867, | |
| "step": 40350 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.5098806495793387e-07, | |
| "loss": 2.4935, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.270201526120133e-07, | |
| "loss": 2.4938, | |
| "step": 40450 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.025630991978087e-07, | |
| "loss": 2.4857, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.5163364469142893, | |
| "eval_loss": 2.339829683303833, | |
| "eval_runtime": 33.521, | |
| "eval_samples_per_second": 72.581, | |
| "eval_steps_per_second": 4.564, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.7810604578360404e-07, | |
| "loss": 2.496, | |
| "step": 40550 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.536489923693993e-07, | |
| "loss": 2.4848, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.301702210917629e-07, | |
| "loss": 2.487, | |
| "step": 40650 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.062023087458423e-07, | |
| "loss": 2.4902, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.817452553316377e-07, | |
| "loss": 2.478, | |
| "step": 40750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.57288201917433e-07, | |
| "loss": 2.4857, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.3283114850322835e-07, | |
| "loss": 2.472, | |
| "step": 40850 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 40888, | |
| "total_flos": 1.7043212067476708e+20, | |
| "train_loss": 2.5243868586182523, | |
| "train_runtime": 155862.8364, | |
| "train_samples_per_second": 33.579, | |
| "train_steps_per_second": 0.262 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 40888, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4000, | |
| "total_flos": 1.7043212067476708e+20, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |