| { | |
| "best_metric": 2.304363250732422, | |
| "best_model_checkpoint": "bert_12_layer_model_v2_complete_training_new_wt_init_120/checkpoint-110000", | |
| "epoch": 0.9012190925625523, | |
| "global_step": 110001, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 2.5197, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 2.5105, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.5e-06, | |
| "loss": 2.5092, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.5039, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.5e-06, | |
| "loss": 2.501, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3e-06, | |
| "loss": 2.5054, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.5e-06, | |
| "loss": 2.5019, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.505, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.5e-06, | |
| "loss": 2.5021, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5e-06, | |
| "loss": 2.5071, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 2.4992, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6e-06, | |
| "loss": 2.5033, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 2.5079, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 7e-06, | |
| "loss": 2.4988, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 2.5016, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.5056, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.5e-06, | |
| "loss": 2.5008, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9e-06, | |
| "loss": 2.5012, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.5e-06, | |
| "loss": 2.5019, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-05, | |
| "loss": 2.5079, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.5539112656076758, | |
| "eval_loss": 2.4010965824127197, | |
| "eval_runtime": 1770.3493, | |
| "eval_samples_per_second": 174.178, | |
| "eval_steps_per_second": 3.629, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.991670692498626e-06, | |
| "loss": 2.5045, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.983341384997253e-06, | |
| "loss": 2.5155, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.975012077495878e-06, | |
| "loss": 2.5076, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.966682769994504e-06, | |
| "loss": 2.5068, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.95835346249313e-06, | |
| "loss": 2.5025, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.950024154991756e-06, | |
| "loss": 2.5003, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.941694847490381e-06, | |
| "loss": 2.5053, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.933365539989006e-06, | |
| "loss": 2.5063, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.925036232487631e-06, | |
| "loss": 2.4954, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.916706924986258e-06, | |
| "loss": 2.5019, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.908377617484883e-06, | |
| "loss": 2.498, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.90004830998351e-06, | |
| "loss": 2.5007, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.891719002482134e-06, | |
| "loss": 2.5027, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.883389694980761e-06, | |
| "loss": 2.498, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.875060387479386e-06, | |
| "loss": 2.5001, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.866731079978011e-06, | |
| "loss": 2.502, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.858401772476636e-06, | |
| "loss": 2.5032, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.850072464975263e-06, | |
| "loss": 2.4982, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.84174315747389e-06, | |
| "loss": 2.496, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.833413849972514e-06, | |
| "loss": 2.4953, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.5552527754737907, | |
| "eval_loss": 2.3920583724975586, | |
| "eval_runtime": 1770.5599, | |
| "eval_samples_per_second": 174.157, | |
| "eval_steps_per_second": 3.629, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.82508454247114e-06, | |
| "loss": 2.4916, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.816755234969766e-06, | |
| "loss": 2.4969, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.808425927468391e-06, | |
| "loss": 2.4927, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.800096619967016e-06, | |
| "loss": 2.494, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.791767312465643e-06, | |
| "loss": 2.4855, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.783438004964268e-06, | |
| "loss": 2.4856, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.775108697462895e-06, | |
| "loss": 2.4926, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.76677938996152e-06, | |
| "loss": 2.4878, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.758450082460145e-06, | |
| "loss": 2.488, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.750120774958771e-06, | |
| "loss": 2.4831, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.741791467457396e-06, | |
| "loss": 2.4863, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.733462159956021e-06, | |
| "loss": 2.4874, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.725132852454648e-06, | |
| "loss": 2.4904, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.716803544953275e-06, | |
| "loss": 2.4878, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.7084742374519e-06, | |
| "loss": 2.4858, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.700144929950525e-06, | |
| "loss": 2.4833, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.69181562244915e-06, | |
| "loss": 2.486, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.683486314947776e-06, | |
| "loss": 2.4852, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.675157007446401e-06, | |
| "loss": 2.4864, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.666827699945028e-06, | |
| "loss": 2.484, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.5568474390906643, | |
| "eval_loss": 2.382256031036377, | |
| "eval_runtime": 1771.5828, | |
| "eval_samples_per_second": 174.057, | |
| "eval_steps_per_second": 3.627, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.658498392443653e-06, | |
| "loss": 2.4784, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.65016908494228e-06, | |
| "loss": 2.4836, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.641839777440905e-06, | |
| "loss": 2.4833, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.63351046993953e-06, | |
| "loss": 2.4841, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.625181162438155e-06, | |
| "loss": 2.4801, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.616851854936781e-06, | |
| "loss": 2.4854, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.608522547435406e-06, | |
| "loss": 2.482, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.600193239934033e-06, | |
| "loss": 2.4798, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.591863932432658e-06, | |
| "loss": 2.4788, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.583534624931285e-06, | |
| "loss": 2.4784, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.57520531742991e-06, | |
| "loss": 2.4857, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.566876009928535e-06, | |
| "loss": 2.4783, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.55854670242716e-06, | |
| "loss": 2.4814, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.550217394925787e-06, | |
| "loss": 2.4755, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.541888087424413e-06, | |
| "loss": 2.4746, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.533558779923038e-06, | |
| "loss": 2.4735, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.525229472421663e-06, | |
| "loss": 2.4661, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.51690016492029e-06, | |
| "loss": 2.4705, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.508570857418915e-06, | |
| "loss": 2.4715, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.50024154991754e-06, | |
| "loss": 2.4828, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.5582355883182831, | |
| "eval_loss": 2.3711230754852295, | |
| "eval_runtime": 1770.1265, | |
| "eval_samples_per_second": 174.2, | |
| "eval_steps_per_second": 3.63, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.491912242416167e-06, | |
| "loss": 2.472, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.483582934914792e-06, | |
| "loss": 2.4715, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.475253627413418e-06, | |
| "loss": 2.4702, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.466924319912043e-06, | |
| "loss": 2.4767, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.458595012410668e-06, | |
| "loss": 2.4682, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.450265704909295e-06, | |
| "loss": 2.4678, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.44193639740792e-06, | |
| "loss": 2.4617, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.433607089906545e-06, | |
| "loss": 2.4681, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.425277782405172e-06, | |
| "loss": 2.4667, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.416948474903798e-06, | |
| "loss": 2.4681, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.408619167402423e-06, | |
| "loss": 2.4709, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.400289859901048e-06, | |
| "loss": 2.4591, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.391960552399673e-06, | |
| "loss": 2.4605, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.3836312448983e-06, | |
| "loss": 2.462, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.375301937396925e-06, | |
| "loss": 2.4623, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.366972629895552e-06, | |
| "loss": 2.4631, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.358643322394177e-06, | |
| "loss": 2.4649, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.350314014892804e-06, | |
| "loss": 2.4599, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.341984707391429e-06, | |
| "loss": 2.4601, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.333655399890054e-06, | |
| "loss": 2.4639, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.5597901132529427, | |
| "eval_loss": 2.3586926460266113, | |
| "eval_runtime": 1771.8546, | |
| "eval_samples_per_second": 174.03, | |
| "eval_steps_per_second": 3.626, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.325326092388679e-06, | |
| "loss": 2.4581, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.316996784887305e-06, | |
| "loss": 2.4622, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.30866747738593e-06, | |
| "loss": 2.4624, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.300338169884557e-06, | |
| "loss": 2.4619, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.292008862383182e-06, | |
| "loss": 2.4593, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.283679554881809e-06, | |
| "loss": 2.4568, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.275350247380434e-06, | |
| "loss": 2.4577, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.267020939879059e-06, | |
| "loss": 2.4519, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.258691632377685e-06, | |
| "loss": 2.4553, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.25036232487631e-06, | |
| "loss": 2.4553, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.242033017374937e-06, | |
| "loss": 2.4552, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.233703709873562e-06, | |
| "loss": 2.4503, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.225374402372189e-06, | |
| "loss": 2.453, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.217045094870814e-06, | |
| "loss": 2.4457, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.208715787369439e-06, | |
| "loss": 2.4549, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.200386479868064e-06, | |
| "loss": 2.4498, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.19205717236669e-06, | |
| "loss": 2.4477, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.183727864865315e-06, | |
| "loss": 2.4548, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.175398557363942e-06, | |
| "loss": 2.4566, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.167069249862567e-06, | |
| "loss": 2.4572, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.5610056263323915, | |
| "eval_loss": 2.3520750999450684, | |
| "eval_runtime": 1770.7421, | |
| "eval_samples_per_second": 174.139, | |
| "eval_steps_per_second": 3.628, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.158739942361194e-06, | |
| "loss": 2.4501, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.150410634859819e-06, | |
| "loss": 2.445, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.142081327358444e-06, | |
| "loss": 2.4523, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.133752019857069e-06, | |
| "loss": 2.442, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.125422712355696e-06, | |
| "loss": 2.4491, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.11709340485432e-06, | |
| "loss": 2.4508, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.108764097352947e-06, | |
| "loss": 2.4387, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.100434789851572e-06, | |
| "loss": 2.4422, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.092105482350199e-06, | |
| "loss": 2.4438, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.083776174848824e-06, | |
| "loss": 2.4414, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.075446867347449e-06, | |
| "loss": 2.4507, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.067117559846076e-06, | |
| "loss": 2.4457, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.0587882523447e-06, | |
| "loss": 2.4418, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.050458944843327e-06, | |
| "loss": 2.4345, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.042129637341952e-06, | |
| "loss": 2.4417, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.033800329840577e-06, | |
| "loss": 2.4421, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.025471022339204e-06, | |
| "loss": 2.4477, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.017141714837829e-06, | |
| "loss": 2.4408, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.008812407336454e-06, | |
| "loss": 2.4447, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.00048309983508e-06, | |
| "loss": 2.4385, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.5626236561796967, | |
| "eval_loss": 2.3429956436157227, | |
| "eval_runtime": 1772.0368, | |
| "eval_samples_per_second": 174.012, | |
| "eval_steps_per_second": 3.626, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.992153792333706e-06, | |
| "loss": 2.4347, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.983824484832332e-06, | |
| "loss": 2.4359, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.975495177330957e-06, | |
| "loss": 2.4404, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.967165869829582e-06, | |
| "loss": 2.4345, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.958836562328209e-06, | |
| "loss": 2.4385, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.950507254826834e-06, | |
| "loss": 2.4314, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.942177947325459e-06, | |
| "loss": 2.4371, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.933848639824086e-06, | |
| "loss": 2.4356, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.925519332322713e-06, | |
| "loss": 2.4349, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.917190024821338e-06, | |
| "loss": 2.4381, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.908860717319963e-06, | |
| "loss": 2.4328, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.900531409818588e-06, | |
| "loss": 2.4295, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.892202102317214e-06, | |
| "loss": 2.43, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.88387279481584e-06, | |
| "loss": 2.4278, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.875543487314466e-06, | |
| "loss": 2.4285, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.867214179813091e-06, | |
| "loss": 2.4248, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.858884872311718e-06, | |
| "loss": 2.4308, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.850555564810343e-06, | |
| "loss": 2.4227, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.842226257308968e-06, | |
| "loss": 2.4351, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.833896949807593e-06, | |
| "loss": 2.4307, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.5632668976063443, | |
| "eval_loss": 2.333714485168457, | |
| "eval_runtime": 1773.4984, | |
| "eval_samples_per_second": 173.869, | |
| "eval_steps_per_second": 3.623, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.82556764230622e-06, | |
| "loss": 2.4265, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.817238334804844e-06, | |
| "loss": 2.4305, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.808909027303471e-06, | |
| "loss": 2.4254, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.800579719802096e-06, | |
| "loss": 2.4233, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 8.792250412300723e-06, | |
| "loss": 2.4158, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 8.783921104799348e-06, | |
| "loss": 2.4272, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 8.775591797297973e-06, | |
| "loss": 2.4248, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.767262489796598e-06, | |
| "loss": 2.4233, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.758933182295224e-06, | |
| "loss": 2.4191, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.750603874793851e-06, | |
| "loss": 2.4211, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.742274567292476e-06, | |
| "loss": 2.4238, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.733945259791101e-06, | |
| "loss": 2.4175, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.725615952289728e-06, | |
| "loss": 2.4216, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.717286644788353e-06, | |
| "loss": 2.4243, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.708957337286978e-06, | |
| "loss": 2.418, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.700628029785605e-06, | |
| "loss": 2.4151, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.69229872228423e-06, | |
| "loss": 2.4209, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.683969414782856e-06, | |
| "loss": 2.4172, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.675640107281481e-06, | |
| "loss": 2.4139, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.667310799780106e-06, | |
| "loss": 2.4162, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.5646881097400172, | |
| "eval_loss": 2.3208436965942383, | |
| "eval_runtime": 1775.7054, | |
| "eval_samples_per_second": 173.653, | |
| "eval_steps_per_second": 3.618, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.658981492278733e-06, | |
| "loss": 2.4125, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.650652184777358e-06, | |
| "loss": 2.413, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.642322877275983e-06, | |
| "loss": 2.4174, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.63399356977461e-06, | |
| "loss": 2.4206, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.625664262273236e-06, | |
| "loss": 2.4147, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.617334954771861e-06, | |
| "loss": 2.4175, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.609005647270486e-06, | |
| "loss": 2.4102, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.600676339769111e-06, | |
| "loss": 2.409, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.592347032267738e-06, | |
| "loss": 2.4131, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.584017724766363e-06, | |
| "loss": 2.4128, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.57568841726499e-06, | |
| "loss": 2.4133, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.567359109763615e-06, | |
| "loss": 2.4125, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.559029802262241e-06, | |
| "loss": 2.4088, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.550700494760866e-06, | |
| "loss": 2.412, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.542371187259491e-06, | |
| "loss": 2.4127, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.534041879758118e-06, | |
| "loss": 2.4116, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.525712572256743e-06, | |
| "loss": 2.4155, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.517383264755368e-06, | |
| "loss": 2.4109, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.509053957253995e-06, | |
| "loss": 2.406, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.500724649752622e-06, | |
| "loss": 2.4088, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.5662760459904025, | |
| "eval_loss": 2.313347816467285, | |
| "eval_runtime": 1774.927, | |
| "eval_samples_per_second": 173.729, | |
| "eval_steps_per_second": 3.62, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.492395342251247e-06, | |
| "loss": 2.4252, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.484066034749872e-06, | |
| "loss": 2.4152, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.475736727248497e-06, | |
| "loss": 2.4255, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.467407419747123e-06, | |
| "loss": 2.4186, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.459078112245748e-06, | |
| "loss": 2.4184, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.450748804744375e-06, | |
| "loss": 2.4239, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.442419497243e-06, | |
| "loss": 2.4185, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.434090189741627e-06, | |
| "loss": 2.4155, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.425760882240252e-06, | |
| "loss": 2.4269, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.417431574738877e-06, | |
| "loss": 2.4187, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.409102267237502e-06, | |
| "loss": 2.4235, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.400772959736128e-06, | |
| "loss": 2.4182, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.392443652234753e-06, | |
| "loss": 2.4188, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.38411434473338e-06, | |
| "loss": 2.4098, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.375785037232005e-06, | |
| "loss": 2.4092, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.367455729730632e-06, | |
| "loss": 2.4184, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.359126422229257e-06, | |
| "loss": 2.4139, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.350797114727882e-06, | |
| "loss": 2.411, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.342467807226507e-06, | |
| "loss": 2.4128, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.334138499725133e-06, | |
| "loss": 2.4139, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.5674646571968632, | |
| "eval_loss": 2.304363250732422, | |
| "eval_runtime": 1774.2846, | |
| "eval_samples_per_second": 173.792, | |
| "eval_steps_per_second": 3.621, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "step": 110001, | |
| "total_flos": 1.545850768759718e+18, | |
| "train_loss": 2.4566562785945028, | |
| "train_runtime": 109009.4688, | |
| "train_samples_per_second": 268.727, | |
| "train_steps_per_second": 5.599 | |
| } | |
| ], | |
| "max_steps": 610290, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.545850768759718e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |