| { | |
| "best_metric": 2.2240703105926514, | |
| "best_model_checkpoint": "./model_tweets_2020_Q2_75/checkpoint-2368000", | |
| "epoch": 6.7372770733268394, | |
| "eval_steps": 8000, | |
| "global_step": 2400000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.486480474472046, | |
| "eval_runtime": 326.396, | |
| "eval_samples_per_second": 919.068, | |
| "eval_steps_per_second": 57.442, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.0726666666666665e-07, | |
| "loss": 2.6592, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.459786891937256, | |
| "eval_runtime": 328.9344, | |
| "eval_samples_per_second": 911.975, | |
| "eval_steps_per_second": 56.999, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.447173595428467, | |
| "eval_runtime": 326.9299, | |
| "eval_samples_per_second": 917.567, | |
| "eval_steps_per_second": 57.349, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.0453333333333336e-07, | |
| "loss": 2.6211, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4340574741363525, | |
| "eval_runtime": 331.0965, | |
| "eval_samples_per_second": 906.02, | |
| "eval_steps_per_second": 56.627, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 2.4222826957702637, | |
| "eval_runtime": 330.5401, | |
| "eval_samples_per_second": 907.545, | |
| "eval_steps_per_second": 56.722, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.018e-07, | |
| "loss": 2.6048, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 2.4217443466186523, | |
| "eval_runtime": 328.8317, | |
| "eval_samples_per_second": 912.26, | |
| "eval_steps_per_second": 57.017, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 2.418403387069702, | |
| "eval_runtime": 328.052, | |
| "eval_samples_per_second": 914.428, | |
| "eval_steps_per_second": 57.153, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.9906666666666667e-07, | |
| "loss": 2.5861, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 2.4061949253082275, | |
| "eval_runtime": 330.9569, | |
| "eval_samples_per_second": 906.402, | |
| "eval_steps_per_second": 56.651, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.3918895721435547, | |
| "eval_runtime": 327.7147, | |
| "eval_samples_per_second": 915.369, | |
| "eval_steps_per_second": 57.211, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.963333333333333e-07, | |
| "loss": 2.5736, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.3896288871765137, | |
| "eval_runtime": 329.9795, | |
| "eval_samples_per_second": 909.087, | |
| "eval_steps_per_second": 56.819, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 2.3951096534729004, | |
| "eval_runtime": 328.5879, | |
| "eval_samples_per_second": 912.937, | |
| "eval_steps_per_second": 57.059, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.936e-07, | |
| "loss": 2.5559, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.3903470039367676, | |
| "eval_runtime": 328.446, | |
| "eval_samples_per_second": 913.331, | |
| "eval_steps_per_second": 57.084, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.3835983276367188, | |
| "eval_runtime": 330.3118, | |
| "eval_samples_per_second": 908.172, | |
| "eval_steps_per_second": 56.762, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.908666666666667e-07, | |
| "loss": 2.5551, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 2.374908685684204, | |
| "eval_runtime": 328.8458, | |
| "eval_samples_per_second": 912.221, | |
| "eval_steps_per_second": 57.015, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 2.3793506622314453, | |
| "eval_runtime": 329.1311, | |
| "eval_samples_per_second": 911.43, | |
| "eval_steps_per_second": 56.965, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.8813333333333334e-07, | |
| "loss": 2.5371, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.3733017444610596, | |
| "eval_runtime": 328.0343, | |
| "eval_samples_per_second": 914.477, | |
| "eval_steps_per_second": 57.156, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 2.3703365325927734, | |
| "eval_runtime": 328.4858, | |
| "eval_samples_per_second": 913.221, | |
| "eval_steps_per_second": 57.077, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.854e-07, | |
| "loss": 2.5417, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 2.366170883178711, | |
| "eval_runtime": 328.5536, | |
| "eval_samples_per_second": 913.032, | |
| "eval_steps_per_second": 57.065, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 2.372772216796875, | |
| "eval_runtime": 330.4279, | |
| "eval_samples_per_second": 907.853, | |
| "eval_steps_per_second": 56.742, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.8266666666666665e-07, | |
| "loss": 2.5316, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 2.364302158355713, | |
| "eval_runtime": 328.3485, | |
| "eval_samples_per_second": 913.603, | |
| "eval_steps_per_second": 57.101, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 2.3567655086517334, | |
| "eval_runtime": 329.7531, | |
| "eval_samples_per_second": 909.711, | |
| "eval_steps_per_second": 56.858, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 3.799333333333333e-07, | |
| "loss": 2.5296, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 2.3554866313934326, | |
| "eval_runtime": 329.7554, | |
| "eval_samples_per_second": 909.705, | |
| "eval_steps_per_second": 56.857, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 2.3506195545196533, | |
| "eval_runtime": 331.0345, | |
| "eval_samples_per_second": 906.19, | |
| "eval_steps_per_second": 56.638, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.772e-07, | |
| "loss": 2.5215, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 2.348207473754883, | |
| "eval_runtime": 329.4713, | |
| "eval_samples_per_second": 910.489, | |
| "eval_steps_per_second": 56.906, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 2.351372480392456, | |
| "eval_runtime": 329.1084, | |
| "eval_samples_per_second": 911.493, | |
| "eval_steps_per_second": 56.969, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.7446666666666667e-07, | |
| "loss": 2.5274, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.3531200885772705, | |
| "eval_runtime": 330.4502, | |
| "eval_samples_per_second": 907.792, | |
| "eval_steps_per_second": 56.738, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 2.3463432788848877, | |
| "eval_runtime": 331.5879, | |
| "eval_samples_per_second": 904.677, | |
| "eval_steps_per_second": 56.543, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7173333333333333e-07, | |
| "loss": 2.5215, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 2.346996784210205, | |
| "eval_runtime": 330.4016, | |
| "eval_samples_per_second": 907.925, | |
| "eval_steps_per_second": 56.746, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 2.3407442569732666, | |
| "eval_runtime": 331.6282, | |
| "eval_samples_per_second": 904.567, | |
| "eval_steps_per_second": 56.536, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.69e-07, | |
| "loss": 2.5096, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 2.340013265609741, | |
| "eval_runtime": 330.2111, | |
| "eval_samples_per_second": 908.449, | |
| "eval_steps_per_second": 56.779, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 2.340172290802002, | |
| "eval_runtime": 330.4785, | |
| "eval_samples_per_second": 907.714, | |
| "eval_steps_per_second": 56.733, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.6626666666666664e-07, | |
| "loss": 2.5176, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 2.330843210220337, | |
| "eval_runtime": 329.4037, | |
| "eval_samples_per_second": 910.676, | |
| "eval_steps_per_second": 56.918, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 2.3342106342315674, | |
| "eval_runtime": 329.9573, | |
| "eval_samples_per_second": 909.148, | |
| "eval_steps_per_second": 56.823, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.6353333333333335e-07, | |
| "loss": 2.5048, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 2.333300828933716, | |
| "eval_runtime": 330.8736, | |
| "eval_samples_per_second": 906.63, | |
| "eval_steps_per_second": 56.665, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 2.3288071155548096, | |
| "eval_runtime": 329.6491, | |
| "eval_samples_per_second": 909.998, | |
| "eval_steps_per_second": 56.876, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.608e-07, | |
| "loss": 2.4979, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 2.329832077026367, | |
| "eval_runtime": 329.6289, | |
| "eval_samples_per_second": 910.054, | |
| "eval_steps_per_second": 56.879, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 2.323723554611206, | |
| "eval_runtime": 330.3451, | |
| "eval_samples_per_second": 908.081, | |
| "eval_steps_per_second": 56.756, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.5806666666666666e-07, | |
| "loss": 2.4963, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 2.326643943786621, | |
| "eval_runtime": 331.0075, | |
| "eval_samples_per_second": 906.263, | |
| "eval_steps_per_second": 56.642, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 2.3196959495544434, | |
| "eval_runtime": 329.7349, | |
| "eval_samples_per_second": 909.761, | |
| "eval_steps_per_second": 56.861, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.553333333333333e-07, | |
| "loss": 2.4972, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 2.327077627182007, | |
| "eval_runtime": 329.8959, | |
| "eval_samples_per_second": 909.317, | |
| "eval_steps_per_second": 56.833, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 2.327465534210205, | |
| "eval_runtime": 329.8835, | |
| "eval_samples_per_second": 909.351, | |
| "eval_steps_per_second": 56.835, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.5259999999999997e-07, | |
| "loss": 2.4969, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 2.3209738731384277, | |
| "eval_runtime": 330.0001, | |
| "eval_samples_per_second": 909.03, | |
| "eval_steps_per_second": 56.815, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 2.3222391605377197, | |
| "eval_runtime": 331.2832, | |
| "eval_samples_per_second": 905.509, | |
| "eval_steps_per_second": 56.595, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.498666666666667e-07, | |
| "loss": 2.4961, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 2.324232339859009, | |
| "eval_runtime": 329.8848, | |
| "eval_samples_per_second": 909.348, | |
| "eval_steps_per_second": 56.835, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 2.3154807090759277, | |
| "eval_runtime": 330.051, | |
| "eval_samples_per_second": 908.89, | |
| "eval_steps_per_second": 56.806, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.4713333333333333e-07, | |
| "loss": 2.49, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 2.3175013065338135, | |
| "eval_runtime": 331.4361, | |
| "eval_samples_per_second": 905.092, | |
| "eval_steps_per_second": 56.569, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 2.307647228240967, | |
| "eval_runtime": 332.1323, | |
| "eval_samples_per_second": 903.194, | |
| "eval_steps_per_second": 56.45, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.444e-07, | |
| "loss": 2.4847, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 2.313831090927124, | |
| "eval_runtime": 330.4544, | |
| "eval_samples_per_second": 907.78, | |
| "eval_steps_per_second": 56.737, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 2.3183014392852783, | |
| "eval_runtime": 331.0864, | |
| "eval_samples_per_second": 906.047, | |
| "eval_steps_per_second": 56.629, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.416666666666667e-07, | |
| "loss": 2.4767, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 2.3118338584899902, | |
| "eval_runtime": 330.5298, | |
| "eval_samples_per_second": 907.573, | |
| "eval_steps_per_second": 56.724, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.3151934146881104, | |
| "eval_runtime": 334.1069, | |
| "eval_samples_per_second": 897.856, | |
| "eval_steps_per_second": 56.117, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.3893333333333335e-07, | |
| "loss": 2.4788, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 2.3089170455932617, | |
| "eval_runtime": 330.2914, | |
| "eval_samples_per_second": 908.228, | |
| "eval_steps_per_second": 56.765, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 2.3051483631134033, | |
| "eval_runtime": 330.8266, | |
| "eval_samples_per_second": 906.759, | |
| "eval_steps_per_second": 56.673, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.3619999999999995e-07, | |
| "loss": 2.4738, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 2.310180425643921, | |
| "eval_runtime": 329.7325, | |
| "eval_samples_per_second": 909.768, | |
| "eval_steps_per_second": 56.861, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 2.3069398403167725, | |
| "eval_runtime": 330.3228, | |
| "eval_samples_per_second": 908.142, | |
| "eval_steps_per_second": 56.76, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3346666666666666e-07, | |
| "loss": 2.4635, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 2.3003976345062256, | |
| "eval_runtime": 331.7126, | |
| "eval_samples_per_second": 904.337, | |
| "eval_steps_per_second": 56.522, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 2.3066189289093018, | |
| "eval_runtime": 331.273, | |
| "eval_samples_per_second": 905.537, | |
| "eval_steps_per_second": 56.597, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.307333333333333e-07, | |
| "loss": 2.4828, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 2.307849168777466, | |
| "eval_runtime": 333.5774, | |
| "eval_samples_per_second": 899.282, | |
| "eval_steps_per_second": 56.206, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 2.3072116374969482, | |
| "eval_runtime": 330.1882, | |
| "eval_samples_per_second": 908.512, | |
| "eval_steps_per_second": 56.783, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.28e-07, | |
| "loss": 2.4675, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 2.3072662353515625, | |
| "eval_runtime": 330.6229, | |
| "eval_samples_per_second": 907.318, | |
| "eval_steps_per_second": 56.708, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 2.3013877868652344, | |
| "eval_runtime": 332.2733, | |
| "eval_samples_per_second": 902.811, | |
| "eval_steps_per_second": 56.426, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 3.252666666666667e-07, | |
| "loss": 2.4676, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 2.298736095428467, | |
| "eval_runtime": 330.3572, | |
| "eval_samples_per_second": 908.047, | |
| "eval_steps_per_second": 56.754, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 2.2987987995147705, | |
| "eval_runtime": 330.8652, | |
| "eval_samples_per_second": 906.653, | |
| "eval_steps_per_second": 56.667, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3.2253333333333334e-07, | |
| "loss": 2.4678, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 2.2971158027648926, | |
| "eval_runtime": 333.0983, | |
| "eval_samples_per_second": 900.575, | |
| "eval_steps_per_second": 56.287, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 2.2968783378601074, | |
| "eval_runtime": 331.5018, | |
| "eval_samples_per_second": 904.912, | |
| "eval_steps_per_second": 56.558, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.198e-07, | |
| "loss": 2.4634, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 2.2989814281463623, | |
| "eval_runtime": 333.5333, | |
| "eval_samples_per_second": 899.4, | |
| "eval_steps_per_second": 56.213, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 2.2869136333465576, | |
| "eval_runtime": 332.2841, | |
| "eval_samples_per_second": 902.782, | |
| "eval_steps_per_second": 56.425, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 3.1706666666666665e-07, | |
| "loss": 2.4657, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 2.293611526489258, | |
| "eval_runtime": 331.5364, | |
| "eval_samples_per_second": 904.818, | |
| "eval_steps_per_second": 56.552, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 2.291510581970215, | |
| "eval_runtime": 331.7602, | |
| "eval_samples_per_second": 904.207, | |
| "eval_steps_per_second": 56.514, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 3.1433333333333336e-07, | |
| "loss": 2.4607, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 2.290339469909668, | |
| "eval_runtime": 331.9545, | |
| "eval_samples_per_second": 903.678, | |
| "eval_steps_per_second": 56.481, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 2.2934372425079346, | |
| "eval_runtime": 334.4873, | |
| "eval_samples_per_second": 896.835, | |
| "eval_steps_per_second": 56.053, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.116e-07, | |
| "loss": 2.4558, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 2.284529447555542, | |
| "eval_runtime": 334.3226, | |
| "eval_samples_per_second": 897.277, | |
| "eval_steps_per_second": 56.081, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 2.289668083190918, | |
| "eval_runtime": 335.2625, | |
| "eval_samples_per_second": 894.761, | |
| "eval_steps_per_second": 55.923, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.0886666666666667e-07, | |
| "loss": 2.4662, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 2.2928452491760254, | |
| "eval_runtime": 330.9741, | |
| "eval_samples_per_second": 906.355, | |
| "eval_steps_per_second": 56.648, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 2.286137580871582, | |
| "eval_runtime": 332.2239, | |
| "eval_samples_per_second": 902.945, | |
| "eval_steps_per_second": 56.435, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.061333333333333e-07, | |
| "loss": 2.4658, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 2.2883219718933105, | |
| "eval_runtime": 334.2582, | |
| "eval_samples_per_second": 897.45, | |
| "eval_steps_per_second": 56.091, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 2.287848472595215, | |
| "eval_runtime": 332.6298, | |
| "eval_samples_per_second": 901.843, | |
| "eval_steps_per_second": 56.366, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.034e-07, | |
| "loss": 2.4533, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 2.2891786098480225, | |
| "eval_runtime": 333.5921, | |
| "eval_samples_per_second": 899.242, | |
| "eval_steps_per_second": 56.203, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 2.2885706424713135, | |
| "eval_runtime": 332.9432, | |
| "eval_samples_per_second": 900.995, | |
| "eval_steps_per_second": 56.313, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.0066666666666663e-07, | |
| "loss": 2.4575, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 2.2894177436828613, | |
| "eval_runtime": 334.1499, | |
| "eval_samples_per_second": 897.741, | |
| "eval_steps_per_second": 56.11, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 2.2870869636535645, | |
| "eval_runtime": 332.2509, | |
| "eval_samples_per_second": 902.872, | |
| "eval_steps_per_second": 56.43, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.9793333333333334e-07, | |
| "loss": 2.4565, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 2.2797837257385254, | |
| "eval_runtime": 332.3564, | |
| "eval_samples_per_second": 902.585, | |
| "eval_steps_per_second": 56.412, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 2.2877373695373535, | |
| "eval_runtime": 332.7462, | |
| "eval_samples_per_second": 901.528, | |
| "eval_steps_per_second": 56.346, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.952e-07, | |
| "loss": 2.4548, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 2.2859256267547607, | |
| "eval_runtime": 333.4649, | |
| "eval_samples_per_second": 899.585, | |
| "eval_steps_per_second": 56.225, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 2.2786755561828613, | |
| "eval_runtime": 331.6465, | |
| "eval_samples_per_second": 904.517, | |
| "eval_steps_per_second": 56.533, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.9246666666666665e-07, | |
| "loss": 2.4507, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 2.277973175048828, | |
| "eval_runtime": 332.624, | |
| "eval_samples_per_second": 901.859, | |
| "eval_steps_per_second": 56.367, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 2.2825992107391357, | |
| "eval_runtime": 332.2329, | |
| "eval_samples_per_second": 902.921, | |
| "eval_steps_per_second": 56.433, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.897333333333333e-07, | |
| "loss": 2.4455, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 2.283816337585449, | |
| "eval_runtime": 332.7513, | |
| "eval_samples_per_second": 901.514, | |
| "eval_steps_per_second": 56.345, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.2763917446136475, | |
| "eval_runtime": 331.7671, | |
| "eval_samples_per_second": 904.188, | |
| "eval_steps_per_second": 56.513, | |
| "step": 712000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.8699999999999996e-07, | |
| "loss": 2.4516, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 2.281355381011963, | |
| "eval_runtime": 331.7857, | |
| "eval_samples_per_second": 904.138, | |
| "eval_steps_per_second": 56.509, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 2.2807059288024902, | |
| "eval_runtime": 332.6438, | |
| "eval_samples_per_second": 901.805, | |
| "eval_steps_per_second": 56.364, | |
| "step": 728000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.8426666666666667e-07, | |
| "loss": 2.445, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 2.2740111351013184, | |
| "eval_runtime": 332.4045, | |
| "eval_samples_per_second": 902.455, | |
| "eval_steps_per_second": 56.404, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 2.277953624725342, | |
| "eval_runtime": 331.8291, | |
| "eval_samples_per_second": 904.02, | |
| "eval_steps_per_second": 56.502, | |
| "step": 744000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.815333333333333e-07, | |
| "loss": 2.4466, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 2.2774717807769775, | |
| "eval_runtime": 331.8071, | |
| "eval_samples_per_second": 904.079, | |
| "eval_steps_per_second": 56.506, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 2.2783188819885254, | |
| "eval_runtime": 333.2568, | |
| "eval_samples_per_second": 900.147, | |
| "eval_steps_per_second": 56.26, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.7880000000000003e-07, | |
| "loss": 2.4476, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 2.2762770652770996, | |
| "eval_runtime": 331.8887, | |
| "eval_samples_per_second": 903.857, | |
| "eval_steps_per_second": 56.492, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 2.2737369537353516, | |
| "eval_runtime": 331.8743, | |
| "eval_samples_per_second": 903.896, | |
| "eval_steps_per_second": 56.494, | |
| "step": 776000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.7606666666666664e-07, | |
| "loss": 2.4449, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 2.2752888202667236, | |
| "eval_runtime": 334.1528, | |
| "eval_samples_per_second": 897.733, | |
| "eval_steps_per_second": 56.109, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 2.276200532913208, | |
| "eval_runtime": 332.3689, | |
| "eval_samples_per_second": 902.551, | |
| "eval_steps_per_second": 56.41, | |
| "step": 792000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.733333333333333e-07, | |
| "loss": 2.4424, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 2.276653528213501, | |
| "eval_runtime": 332.4217, | |
| "eval_samples_per_second": 902.408, | |
| "eval_steps_per_second": 56.401, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 2.2701988220214844, | |
| "eval_runtime": 332.7419, | |
| "eval_samples_per_second": 901.54, | |
| "eval_steps_per_second": 56.347, | |
| "step": 808000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 2.706e-07, | |
| "loss": 2.4528, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 2.26547908782959, | |
| "eval_runtime": 332.284, | |
| "eval_samples_per_second": 902.782, | |
| "eval_steps_per_second": 56.425, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 2.272664785385132, | |
| "eval_runtime": 332.94, | |
| "eval_samples_per_second": 901.003, | |
| "eval_steps_per_second": 56.313, | |
| "step": 824000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.6786666666666666e-07, | |
| "loss": 2.4523, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 2.2732608318328857, | |
| "eval_runtime": 332.6487, | |
| "eval_samples_per_second": 901.792, | |
| "eval_steps_per_second": 56.363, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 2.2654263973236084, | |
| "eval_runtime": 332.7531, | |
| "eval_samples_per_second": 901.509, | |
| "eval_steps_per_second": 56.345, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.651333333333333e-07, | |
| "loss": 2.4395, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 2.2673776149749756, | |
| "eval_runtime": 332.3327, | |
| "eval_samples_per_second": 902.65, | |
| "eval_steps_per_second": 56.416, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 2.275400161743164, | |
| "eval_runtime": 333.0968, | |
| "eval_samples_per_second": 900.579, | |
| "eval_steps_per_second": 56.287, | |
| "step": 856000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.624e-07, | |
| "loss": 2.434, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 2.2722461223602295, | |
| "eval_runtime": 333.3836, | |
| "eval_samples_per_second": 899.804, | |
| "eval_steps_per_second": 56.239, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 2.266554117202759, | |
| "eval_runtime": 332.9633, | |
| "eval_samples_per_second": 900.94, | |
| "eval_steps_per_second": 56.31, | |
| "step": 872000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.596666666666667e-07, | |
| "loss": 2.4407, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 2.265575647354126, | |
| "eval_runtime": 334.6536, | |
| "eval_samples_per_second": 896.39, | |
| "eval_steps_per_second": 56.025, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 2.265437602996826, | |
| "eval_runtime": 333.1051, | |
| "eval_samples_per_second": 900.556, | |
| "eval_steps_per_second": 56.286, | |
| "step": 888000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.5693333333333333e-07, | |
| "loss": 2.4352, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 2.263028383255005, | |
| "eval_runtime": 333.7641, | |
| "eval_samples_per_second": 898.778, | |
| "eval_steps_per_second": 56.174, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 2.2662160396575928, | |
| "eval_runtime": 333.089, | |
| "eval_samples_per_second": 900.6, | |
| "eval_steps_per_second": 56.288, | |
| "step": 904000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.542e-07, | |
| "loss": 2.4393, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 2.2692363262176514, | |
| "eval_runtime": 333.5532, | |
| "eval_samples_per_second": 899.347, | |
| "eval_steps_per_second": 56.21, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 2.2558484077453613, | |
| "eval_runtime": 335.5892, | |
| "eval_samples_per_second": 893.891, | |
| "eval_steps_per_second": 55.869, | |
| "step": 920000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.5146666666666664e-07, | |
| "loss": 2.4378, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 2.2619380950927734, | |
| "eval_runtime": 333.9818, | |
| "eval_samples_per_second": 898.193, | |
| "eval_steps_per_second": 56.138, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 2.261375665664673, | |
| "eval_runtime": 333.299, | |
| "eval_samples_per_second": 900.033, | |
| "eval_steps_per_second": 56.253, | |
| "step": 936000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.4873333333333335e-07, | |
| "loss": 2.4392, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 2.2577741146087646, | |
| "eval_runtime": 332.5892, | |
| "eval_samples_per_second": 901.954, | |
| "eval_steps_per_second": 56.373, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 2.267181873321533, | |
| "eval_runtime": 333.717, | |
| "eval_samples_per_second": 898.905, | |
| "eval_steps_per_second": 56.182, | |
| "step": 952000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.46e-07, | |
| "loss": 2.437, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 2.2597758769989014, | |
| "eval_runtime": 334.1825, | |
| "eval_samples_per_second": 897.653, | |
| "eval_steps_per_second": 56.104, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 2.263289451599121, | |
| "eval_runtime": 333.6576, | |
| "eval_samples_per_second": 899.065, | |
| "eval_steps_per_second": 56.192, | |
| "step": 968000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.4326666666666666e-07, | |
| "loss": 2.4388, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 2.256582260131836, | |
| "eval_runtime": 335.1086, | |
| "eval_samples_per_second": 895.172, | |
| "eval_steps_per_second": 55.949, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.255068778991699, | |
| "eval_runtime": 334.1259, | |
| "eval_samples_per_second": 897.805, | |
| "eval_steps_per_second": 56.114, | |
| "step": 984000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.405333333333333e-07, | |
| "loss": 2.4386, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 2.2605791091918945, | |
| "eval_runtime": 334.7883, | |
| "eval_samples_per_second": 896.029, | |
| "eval_steps_per_second": 56.003, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 2.263402223587036, | |
| "eval_runtime": 334.1108, | |
| "eval_samples_per_second": 897.846, | |
| "eval_steps_per_second": 56.116, | |
| "step": 1000000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.3779999999999997e-07, | |
| "loss": 2.4402, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 2.264103889465332, | |
| "eval_runtime": 334.5974, | |
| "eval_samples_per_second": 896.54, | |
| "eval_steps_per_second": 56.035, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 2.2618744373321533, | |
| "eval_runtime": 335.396, | |
| "eval_samples_per_second": 894.405, | |
| "eval_steps_per_second": 55.901, | |
| "step": 1016000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.3506666666666668e-07, | |
| "loss": 2.4442, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 2.258431911468506, | |
| "eval_runtime": 334.1391, | |
| "eval_samples_per_second": 897.77, | |
| "eval_steps_per_second": 56.111, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 2.257888078689575, | |
| "eval_runtime": 337.4777, | |
| "eval_samples_per_second": 888.888, | |
| "eval_steps_per_second": 55.556, | |
| "step": 1032000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.3233333333333334e-07, | |
| "loss": 2.4327, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 2.252260684967041, | |
| "eval_runtime": 335.916, | |
| "eval_samples_per_second": 893.021, | |
| "eval_steps_per_second": 55.815, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 2.2561793327331543, | |
| "eval_runtime": 335.381, | |
| "eval_samples_per_second": 894.446, | |
| "eval_steps_per_second": 55.904, | |
| "step": 1048000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.2960000000000002e-07, | |
| "loss": 2.4289, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 2.259270191192627, | |
| "eval_runtime": 338.94, | |
| "eval_samples_per_second": 885.053, | |
| "eval_steps_per_second": 55.317, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 2.256190776824951, | |
| "eval_runtime": 337.0761, | |
| "eval_samples_per_second": 889.947, | |
| "eval_steps_per_second": 55.622, | |
| "step": 1064000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.2686666666666667e-07, | |
| "loss": 2.4319, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_loss": 2.253577709197998, | |
| "eval_runtime": 337.3724, | |
| "eval_samples_per_second": 889.166, | |
| "eval_steps_per_second": 55.574, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 2.260322332382202, | |
| "eval_runtime": 335.9181, | |
| "eval_samples_per_second": 893.015, | |
| "eval_steps_per_second": 55.814, | |
| "step": 1080000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.2413333333333333e-07, | |
| "loss": 2.4174, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 2.2548863887786865, | |
| "eval_runtime": 336.1593, | |
| "eval_samples_per_second": 892.374, | |
| "eval_steps_per_second": 55.774, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 2.2595221996307373, | |
| "eval_runtime": 338.2665, | |
| "eval_samples_per_second": 886.816, | |
| "eval_steps_per_second": 55.427, | |
| "step": 1096000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.214e-07, | |
| "loss": 2.4155, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 2.255467176437378, | |
| "eval_runtime": 335.0383, | |
| "eval_samples_per_second": 895.36, | |
| "eval_steps_per_second": 55.961, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 2.250143527984619, | |
| "eval_runtime": 337.3147, | |
| "eval_samples_per_second": 889.318, | |
| "eval_steps_per_second": 55.583, | |
| "step": 1112000 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 2.1866666666666667e-07, | |
| "loss": 2.427, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_loss": 2.2528042793273926, | |
| "eval_runtime": 335.8317, | |
| "eval_samples_per_second": 893.245, | |
| "eval_steps_per_second": 55.829, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 2.252933979034424, | |
| "eval_runtime": 335.79, | |
| "eval_samples_per_second": 893.356, | |
| "eval_steps_per_second": 55.835, | |
| "step": 1128000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 2.1593333333333332e-07, | |
| "loss": 2.4222, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 2.253556251525879, | |
| "eval_runtime": 336.7473, | |
| "eval_samples_per_second": 890.816, | |
| "eval_steps_per_second": 55.677, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_loss": 2.258152723312378, | |
| "eval_runtime": 337.5276, | |
| "eval_samples_per_second": 888.757, | |
| "eval_steps_per_second": 55.548, | |
| "step": 1144000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2.132e-07, | |
| "loss": 2.4232, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 2.2522146701812744, | |
| "eval_runtime": 335.4197, | |
| "eval_samples_per_second": 894.342, | |
| "eval_steps_per_second": 55.897, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_loss": 2.2524819374084473, | |
| "eval_runtime": 337.4419, | |
| "eval_samples_per_second": 888.983, | |
| "eval_steps_per_second": 55.562, | |
| "step": 1160000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 2.1046666666666666e-07, | |
| "loss": 2.4252, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 2.2537834644317627, | |
| "eval_runtime": 336.2053, | |
| "eval_samples_per_second": 892.252, | |
| "eval_steps_per_second": 55.767, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_loss": 2.2512009143829346, | |
| "eval_runtime": 335.734, | |
| "eval_samples_per_second": 893.505, | |
| "eval_steps_per_second": 55.845, | |
| "step": 1176000 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 2.0773333333333334e-07, | |
| "loss": 2.4209, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_loss": 2.255702018737793, | |
| "eval_runtime": 337.398, | |
| "eval_samples_per_second": 889.098, | |
| "eval_steps_per_second": 55.569, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_loss": 2.2445454597473145, | |
| "eval_runtime": 338.3834, | |
| "eval_samples_per_second": 886.509, | |
| "eval_steps_per_second": 55.408, | |
| "step": 1192000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 2.05e-07, | |
| "loss": 2.4243, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_loss": 2.257007122039795, | |
| "eval_runtime": 336.8153, | |
| "eval_samples_per_second": 890.636, | |
| "eval_steps_per_second": 55.666, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_loss": 2.25388240814209, | |
| "eval_runtime": 339.0365, | |
| "eval_samples_per_second": 884.801, | |
| "eval_steps_per_second": 55.301, | |
| "step": 1208000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.0226666666666668e-07, | |
| "loss": 2.4278, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 2.2514150142669678, | |
| "eval_runtime": 340.5571, | |
| "eval_samples_per_second": 880.851, | |
| "eval_steps_per_second": 55.054, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 2.2454025745391846, | |
| "eval_runtime": 337.7515, | |
| "eval_samples_per_second": 888.168, | |
| "eval_steps_per_second": 55.511, | |
| "step": 1224000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.9953333333333333e-07, | |
| "loss": 2.4286, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_loss": 2.246293306350708, | |
| "eval_runtime": 339.7018, | |
| "eval_samples_per_second": 883.069, | |
| "eval_steps_per_second": 55.193, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 2.25063157081604, | |
| "eval_runtime": 336.5454, | |
| "eval_samples_per_second": 891.351, | |
| "eval_steps_per_second": 55.71, | |
| "step": 1240000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 1.968e-07, | |
| "loss": 2.4274, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_loss": 2.2426698207855225, | |
| "eval_runtime": 339.3399, | |
| "eval_samples_per_second": 884.01, | |
| "eval_steps_per_second": 55.251, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "eval_loss": 2.2535440921783447, | |
| "eval_runtime": 339.1007, | |
| "eval_samples_per_second": 884.634, | |
| "eval_steps_per_second": 55.29, | |
| "step": 1256000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.9406666666666667e-07, | |
| "loss": 2.4201, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 2.2516891956329346, | |
| "eval_runtime": 337.2905, | |
| "eval_samples_per_second": 889.382, | |
| "eval_steps_per_second": 55.587, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 2.2436001300811768, | |
| "eval_runtime": 340.5027, | |
| "eval_samples_per_second": 880.992, | |
| "eval_steps_per_second": 55.063, | |
| "step": 1272000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 1.9133333333333333e-07, | |
| "loss": 2.4233, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_loss": 2.242955446243286, | |
| "eval_runtime": 338.961, | |
| "eval_samples_per_second": 884.999, | |
| "eval_steps_per_second": 55.313, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "eval_loss": 2.247040271759033, | |
| "eval_runtime": 336.8862, | |
| "eval_samples_per_second": 890.449, | |
| "eval_steps_per_second": 55.654, | |
| "step": 1288000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.886e-07, | |
| "loss": 2.4183, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 2.244565963745117, | |
| "eval_runtime": 337.986, | |
| "eval_samples_per_second": 887.552, | |
| "eval_steps_per_second": 55.473, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "eval_loss": 2.2539021968841553, | |
| "eval_runtime": 340.0782, | |
| "eval_samples_per_second": 882.091, | |
| "eval_steps_per_second": 55.131, | |
| "step": 1304000 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.8586666666666666e-07, | |
| "loss": 2.428, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "eval_loss": 2.249154806137085, | |
| "eval_runtime": 337.5652, | |
| "eval_samples_per_second": 888.658, | |
| "eval_steps_per_second": 55.542, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "eval_loss": 2.2543509006500244, | |
| "eval_runtime": 337.3598, | |
| "eval_samples_per_second": 889.199, | |
| "eval_steps_per_second": 55.576, | |
| "step": 1320000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.8313333333333332e-07, | |
| "loss": 2.4206, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "eval_loss": 2.2478220462799072, | |
| "eval_runtime": 339.2392, | |
| "eval_samples_per_second": 884.273, | |
| "eval_steps_per_second": 55.268, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 2.2420246601104736, | |
| "eval_runtime": 337.9033, | |
| "eval_samples_per_second": 887.769, | |
| "eval_steps_per_second": 55.486, | |
| "step": 1336000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.804e-07, | |
| "loss": 2.4287, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 2.244210958480835, | |
| "eval_runtime": 337.3268, | |
| "eval_samples_per_second": 889.286, | |
| "eval_steps_per_second": 55.581, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_loss": 2.2426180839538574, | |
| "eval_runtime": 339.5586, | |
| "eval_samples_per_second": 883.441, | |
| "eval_steps_per_second": 55.216, | |
| "step": 1352000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.7766666666666666e-07, | |
| "loss": 2.4297, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "eval_loss": 2.242596387863159, | |
| "eval_runtime": 337.7343, | |
| "eval_samples_per_second": 888.213, | |
| "eval_steps_per_second": 55.514, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_loss": 2.2480640411376953, | |
| "eval_runtime": 337.5382, | |
| "eval_samples_per_second": 888.729, | |
| "eval_steps_per_second": 55.546, | |
| "step": 1368000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1.7493333333333334e-07, | |
| "loss": 2.4185, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_loss": 2.2448768615722656, | |
| "eval_runtime": 339.0271, | |
| "eval_samples_per_second": 884.826, | |
| "eval_steps_per_second": 55.302, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_loss": 2.246758222579956, | |
| "eval_runtime": 338.8022, | |
| "eval_samples_per_second": 885.413, | |
| "eval_steps_per_second": 55.339, | |
| "step": 1384000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.722e-07, | |
| "loss": 2.4217, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_loss": 2.2466745376586914, | |
| "eval_runtime": 341.1017, | |
| "eval_samples_per_second": 879.444, | |
| "eval_steps_per_second": 54.966, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_loss": 2.2463412284851074, | |
| "eval_runtime": 340.0034, | |
| "eval_samples_per_second": 882.285, | |
| "eval_steps_per_second": 55.144, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.6946666666666668e-07, | |
| "loss": 2.4144, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_loss": 2.2481906414031982, | |
| "eval_runtime": 338.7844, | |
| "eval_samples_per_second": 885.46, | |
| "eval_steps_per_second": 55.342, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 2.242440938949585, | |
| "eval_runtime": 339.569, | |
| "eval_samples_per_second": 883.414, | |
| "eval_steps_per_second": 55.214, | |
| "step": 1416000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.6673333333333333e-07, | |
| "loss": 2.4175, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.2414705753326416, | |
| "eval_runtime": 339.2204, | |
| "eval_samples_per_second": 884.322, | |
| "eval_steps_per_second": 55.271, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_loss": 2.2450637817382812, | |
| "eval_runtime": 338.8494, | |
| "eval_samples_per_second": 885.29, | |
| "eval_steps_per_second": 55.331, | |
| "step": 1432000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1.64e-07, | |
| "loss": 2.4169, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 2.244276285171509, | |
| "eval_runtime": 338.3144, | |
| "eval_samples_per_second": 886.69, | |
| "eval_steps_per_second": 55.419, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_loss": 2.2389209270477295, | |
| "eval_runtime": 343.9025, | |
| "eval_samples_per_second": 872.282, | |
| "eval_steps_per_second": 54.518, | |
| "step": 1448000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.6126666666666667e-07, | |
| "loss": 2.4142, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 2.2376506328582764, | |
| "eval_runtime": 338.9552, | |
| "eval_samples_per_second": 885.014, | |
| "eval_steps_per_second": 55.314, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 2.239941358566284, | |
| "eval_runtime": 342.029, | |
| "eval_samples_per_second": 877.06, | |
| "eval_steps_per_second": 54.817, | |
| "step": 1464000 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1.5853333333333332e-07, | |
| "loss": 2.4122, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_loss": 2.24470853805542, | |
| "eval_runtime": 338.988, | |
| "eval_samples_per_second": 884.928, | |
| "eval_steps_per_second": 55.309, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_loss": 2.24562931060791, | |
| "eval_runtime": 341.3425, | |
| "eval_samples_per_second": 878.824, | |
| "eval_steps_per_second": 54.927, | |
| "step": 1480000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 1.558e-07, | |
| "loss": 2.4166, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_loss": 2.245072364807129, | |
| "eval_runtime": 339.7578, | |
| "eval_samples_per_second": 882.923, | |
| "eval_steps_per_second": 55.183, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_loss": 2.2368929386138916, | |
| "eval_runtime": 340.9662, | |
| "eval_samples_per_second": 879.794, | |
| "eval_steps_per_second": 54.988, | |
| "step": 1496000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 1.5306666666666666e-07, | |
| "loss": 2.4165, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "eval_loss": 2.2426319122314453, | |
| "eval_runtime": 339.1777, | |
| "eval_samples_per_second": 884.433, | |
| "eval_steps_per_second": 55.278, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 2.238410472869873, | |
| "eval_runtime": 340.071, | |
| "eval_samples_per_second": 882.11, | |
| "eval_steps_per_second": 55.133, | |
| "step": 1512000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 1.5033333333333332e-07, | |
| "loss": 2.4204, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "eval_loss": 2.245389461517334, | |
| "eval_runtime": 339.4968, | |
| "eval_samples_per_second": 883.602, | |
| "eval_steps_per_second": 55.226, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_loss": 2.242230176925659, | |
| "eval_runtime": 341.1938, | |
| "eval_samples_per_second": 879.207, | |
| "eval_steps_per_second": 54.951, | |
| "step": 1528000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 1.476e-07, | |
| "loss": 2.4192, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_loss": 2.2423222064971924, | |
| "eval_runtime": 341.7051, | |
| "eval_samples_per_second": 877.892, | |
| "eval_steps_per_second": 54.869, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 2.2434957027435303, | |
| "eval_runtime": 344.5773, | |
| "eval_samples_per_second": 870.574, | |
| "eval_steps_per_second": 54.412, | |
| "step": 1544000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 1.4486666666666665e-07, | |
| "loss": 2.4167, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "eval_loss": 2.2450661659240723, | |
| "eval_runtime": 342.2307, | |
| "eval_samples_per_second": 876.543, | |
| "eval_steps_per_second": 54.785, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_loss": 2.2442915439605713, | |
| "eval_runtime": 339.3897, | |
| "eval_samples_per_second": 883.881, | |
| "eval_steps_per_second": 55.243, | |
| "step": 1560000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 1.4213333333333334e-07, | |
| "loss": 2.4124, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_loss": 2.243011713027954, | |
| "eval_runtime": 339.9044, | |
| "eval_samples_per_second": 882.542, | |
| "eval_steps_per_second": 55.16, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "eval_loss": 2.2422168254852295, | |
| "eval_runtime": 340.0517, | |
| "eval_samples_per_second": 882.16, | |
| "eval_steps_per_second": 55.136, | |
| "step": 1576000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 1.3940000000000002e-07, | |
| "loss": 2.406, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "eval_loss": 2.2356574535369873, | |
| "eval_runtime": 339.8299, | |
| "eval_samples_per_second": 882.736, | |
| "eval_steps_per_second": 55.172, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_loss": 2.2395410537719727, | |
| "eval_runtime": 340.769, | |
| "eval_samples_per_second": 880.303, | |
| "eval_steps_per_second": 55.02, | |
| "step": 1592000 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 1.3666666666666665e-07, | |
| "loss": 2.4166, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "eval_loss": 2.2377548217773438, | |
| "eval_runtime": 341.8287, | |
| "eval_samples_per_second": 877.574, | |
| "eval_steps_per_second": 54.849, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 2.2419931888580322, | |
| "eval_runtime": 341.3154, | |
| "eval_samples_per_second": 878.894, | |
| "eval_steps_per_second": 54.932, | |
| "step": 1608000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 1.3393333333333333e-07, | |
| "loss": 2.4144, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_loss": 2.2401504516601562, | |
| "eval_runtime": 341.1783, | |
| "eval_samples_per_second": 879.247, | |
| "eval_steps_per_second": 54.954, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "eval_loss": 2.238373041152954, | |
| "eval_runtime": 340.7212, | |
| "eval_samples_per_second": 880.427, | |
| "eval_steps_per_second": 55.027, | |
| "step": 1624000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.312e-07, | |
| "loss": 2.4219, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_loss": 2.2437572479248047, | |
| "eval_runtime": 342.9314, | |
| "eval_samples_per_second": 874.752, | |
| "eval_steps_per_second": 54.673, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 2.2455334663391113, | |
| "eval_runtime": 340.3903, | |
| "eval_samples_per_second": 881.282, | |
| "eval_steps_per_second": 55.081, | |
| "step": 1640000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 1.2846666666666667e-07, | |
| "loss": 2.4061, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 2.2396554946899414, | |
| "eval_runtime": 342.4586, | |
| "eval_samples_per_second": 875.96, | |
| "eval_steps_per_second": 54.748, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_loss": 2.23541522026062, | |
| "eval_runtime": 341.3616, | |
| "eval_samples_per_second": 878.775, | |
| "eval_steps_per_second": 54.924, | |
| "step": 1656000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 1.2573333333333332e-07, | |
| "loss": 2.411, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_loss": 2.2392566204071045, | |
| "eval_runtime": 340.724, | |
| "eval_samples_per_second": 880.419, | |
| "eval_steps_per_second": 55.027, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 2.238832473754883, | |
| "eval_runtime": 342.3701, | |
| "eval_samples_per_second": 876.186, | |
| "eval_steps_per_second": 54.762, | |
| "step": 1672000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 1.23e-07, | |
| "loss": 2.4125, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "eval_loss": 2.2406108379364014, | |
| "eval_runtime": 343.1331, | |
| "eval_samples_per_second": 874.238, | |
| "eval_steps_per_second": 54.641, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_loss": 2.2330496311187744, | |
| "eval_runtime": 341.3886, | |
| "eval_samples_per_second": 878.705, | |
| "eval_steps_per_second": 54.92, | |
| "step": 1688000 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 1.2026666666666666e-07, | |
| "loss": 2.4092, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "eval_loss": 2.2335941791534424, | |
| "eval_runtime": 341.2812, | |
| "eval_samples_per_second": 878.982, | |
| "eval_steps_per_second": 54.937, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "eval_loss": 2.239811658859253, | |
| "eval_runtime": 341.3993, | |
| "eval_samples_per_second": 878.678, | |
| "eval_steps_per_second": 54.918, | |
| "step": 1704000 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 1.1753333333333334e-07, | |
| "loss": 2.4078, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "eval_loss": 2.2368171215057373, | |
| "eval_runtime": 342.0299, | |
| "eval_samples_per_second": 877.058, | |
| "eval_steps_per_second": 54.817, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 2.236109495162964, | |
| "eval_runtime": 341.4467, | |
| "eval_samples_per_second": 878.556, | |
| "eval_steps_per_second": 54.91, | |
| "step": 1720000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 1.1480000000000001e-07, | |
| "loss": 2.4185, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 2.2378110885620117, | |
| "eval_runtime": 342.0137, | |
| "eval_samples_per_second": 877.099, | |
| "eval_steps_per_second": 54.819, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_loss": 2.2338638305664062, | |
| "eval_runtime": 341.8702, | |
| "eval_samples_per_second": 877.467, | |
| "eval_steps_per_second": 54.842, | |
| "step": 1736000 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.1206666666666666e-07, | |
| "loss": 2.4088, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_loss": 2.2365610599517822, | |
| "eval_runtime": 343.0203, | |
| "eval_samples_per_second": 874.526, | |
| "eval_steps_per_second": 54.659, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 2.238463878631592, | |
| "eval_runtime": 342.0664, | |
| "eval_samples_per_second": 876.964, | |
| "eval_steps_per_second": 54.811, | |
| "step": 1752000 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 1.0933333333333333e-07, | |
| "loss": 2.4095, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 2.2336812019348145, | |
| "eval_runtime": 343.3628, | |
| "eval_samples_per_second": 873.653, | |
| "eval_steps_per_second": 54.604, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_loss": 2.2413289546966553, | |
| "eval_runtime": 342.3332, | |
| "eval_samples_per_second": 876.281, | |
| "eval_steps_per_second": 54.768, | |
| "step": 1768000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 1.066e-07, | |
| "loss": 2.4078, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 2.237656593322754, | |
| "eval_runtime": 342.7683, | |
| "eval_samples_per_second": 875.168, | |
| "eval_steps_per_second": 54.699, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "eval_loss": 2.2302229404449463, | |
| "eval_runtime": 342.0809, | |
| "eval_samples_per_second": 876.927, | |
| "eval_steps_per_second": 54.809, | |
| "step": 1784000 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.0386666666666667e-07, | |
| "loss": 2.4073, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 2.2356677055358887, | |
| "eval_runtime": 342.5577, | |
| "eval_samples_per_second": 875.707, | |
| "eval_steps_per_second": 54.732, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 2.2384088039398193, | |
| "eval_runtime": 342.428, | |
| "eval_samples_per_second": 876.038, | |
| "eval_steps_per_second": 54.753, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 1.0113333333333334e-07, | |
| "loss": 2.4073, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "eval_loss": 2.2321836948394775, | |
| "eval_runtime": 342.2614, | |
| "eval_samples_per_second": 876.465, | |
| "eval_steps_per_second": 54.78, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_loss": 2.234363317489624, | |
| "eval_runtime": 344.4478, | |
| "eval_samples_per_second": 870.901, | |
| "eval_steps_per_second": 54.432, | |
| "step": 1816000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 9.84e-08, | |
| "loss": 2.4043, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_loss": 2.232731819152832, | |
| "eval_runtime": 342.8187, | |
| "eval_samples_per_second": 875.04, | |
| "eval_steps_per_second": 54.691, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "eval_loss": 2.234955072402954, | |
| "eval_runtime": 343.4884, | |
| "eval_samples_per_second": 873.334, | |
| "eval_steps_per_second": 54.584, | |
| "step": 1832000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 9.566666666666666e-08, | |
| "loss": 2.4082, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_loss": 2.2375595569610596, | |
| "eval_runtime": 343.7508, | |
| "eval_samples_per_second": 872.667, | |
| "eval_steps_per_second": 54.542, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "eval_loss": 2.2363414764404297, | |
| "eval_runtime": 343.8693, | |
| "eval_samples_per_second": 872.366, | |
| "eval_steps_per_second": 54.524, | |
| "step": 1848000 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 9.293333333333333e-08, | |
| "loss": 2.4073, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "eval_loss": 2.23234224319458, | |
| "eval_runtime": 342.8958, | |
| "eval_samples_per_second": 874.843, | |
| "eval_steps_per_second": 54.678, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "eval_loss": 2.2419273853302, | |
| "eval_runtime": 343.3653, | |
| "eval_samples_per_second": 873.647, | |
| "eval_steps_per_second": 54.604, | |
| "step": 1864000 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 9.02e-08, | |
| "loss": 2.4148, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "eval_loss": 2.2292640209198, | |
| "eval_runtime": 344.1756, | |
| "eval_samples_per_second": 871.59, | |
| "eval_steps_per_second": 54.475, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "eval_loss": 2.2345802783966064, | |
| "eval_runtime": 346.0562, | |
| "eval_samples_per_second": 866.854, | |
| "eval_steps_per_second": 54.179, | |
| "step": 1880000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 8.746666666666667e-08, | |
| "loss": 2.4098, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "eval_loss": 2.237226963043213, | |
| "eval_runtime": 345.4208, | |
| "eval_samples_per_second": 868.448, | |
| "eval_steps_per_second": 54.279, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_loss": 2.237149953842163, | |
| "eval_runtime": 343.8922, | |
| "eval_samples_per_second": 872.308, | |
| "eval_steps_per_second": 54.52, | |
| "step": 1896000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 8.473333333333334e-08, | |
| "loss": 2.407, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "eval_loss": 2.2396621704101562, | |
| "eval_runtime": 346.177, | |
| "eval_samples_per_second": 866.551, | |
| "eval_steps_per_second": 54.16, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "eval_loss": 2.2300214767456055, | |
| "eval_runtime": 345.6113, | |
| "eval_samples_per_second": 867.969, | |
| "eval_steps_per_second": 54.249, | |
| "step": 1912000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 8.2e-08, | |
| "loss": 2.4108, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "eval_loss": 2.2317283153533936, | |
| "eval_runtime": 344.6229, | |
| "eval_samples_per_second": 870.459, | |
| "eval_steps_per_second": 54.404, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 2.2349703311920166, | |
| "eval_runtime": 344.7164, | |
| "eval_samples_per_second": 870.223, | |
| "eval_steps_per_second": 54.39, | |
| "step": 1928000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 7.926666666666666e-08, | |
| "loss": 2.4168, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "eval_loss": 2.2343006134033203, | |
| "eval_runtime": 344.4965, | |
| "eval_samples_per_second": 870.778, | |
| "eval_steps_per_second": 54.424, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "eval_loss": 2.232745885848999, | |
| "eval_runtime": 343.8717, | |
| "eval_samples_per_second": 872.36, | |
| "eval_steps_per_second": 54.523, | |
| "step": 1944000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 7.653333333333333e-08, | |
| "loss": 2.4113, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "eval_loss": 2.2363381385803223, | |
| "eval_runtime": 343.8179, | |
| "eval_samples_per_second": 872.497, | |
| "eval_steps_per_second": 54.532, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "eval_loss": 2.231372833251953, | |
| "eval_runtime": 345.6256, | |
| "eval_samples_per_second": 867.933, | |
| "eval_steps_per_second": 54.247, | |
| "step": 1960000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 7.38e-08, | |
| "loss": 2.4131, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_loss": 2.23030686378479, | |
| "eval_runtime": 344.554, | |
| "eval_samples_per_second": 870.633, | |
| "eval_steps_per_second": 54.415, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "eval_loss": 2.2353336811065674, | |
| "eval_runtime": 345.2222, | |
| "eval_samples_per_second": 868.948, | |
| "eval_steps_per_second": 54.31, | |
| "step": 1976000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 7.106666666666667e-08, | |
| "loss": 2.4129, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_loss": 2.235344886779785, | |
| "eval_runtime": 344.2446, | |
| "eval_samples_per_second": 871.415, | |
| "eval_steps_per_second": 54.464, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_loss": 2.2295796871185303, | |
| "eval_runtime": 344.0878, | |
| "eval_samples_per_second": 871.812, | |
| "eval_steps_per_second": 54.489, | |
| "step": 1992000 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 6.833333333333332e-08, | |
| "loss": 2.4129, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "eval_loss": 2.2313883304595947, | |
| "eval_runtime": 344.0986, | |
| "eval_samples_per_second": 871.785, | |
| "eval_steps_per_second": 54.487, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "eval_loss": 2.2287940979003906, | |
| "eval_runtime": 343.9635, | |
| "eval_samples_per_second": 872.127, | |
| "eval_steps_per_second": 54.509, | |
| "step": 2008000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 6.56e-08, | |
| "loss": 2.4045, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "eval_loss": 2.2346994876861572, | |
| "eval_runtime": 344.4276, | |
| "eval_samples_per_second": 870.952, | |
| "eval_steps_per_second": 54.435, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "eval_loss": 2.2348926067352295, | |
| "eval_runtime": 344.0715, | |
| "eval_samples_per_second": 871.854, | |
| "eval_steps_per_second": 54.492, | |
| "step": 2024000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 6.286666666666666e-08, | |
| "loss": 2.4089, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "eval_loss": 2.231017589569092, | |
| "eval_runtime": 344.7006, | |
| "eval_samples_per_second": 870.262, | |
| "eval_steps_per_second": 54.392, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 2.2342352867126465, | |
| "eval_runtime": 344.3635, | |
| "eval_samples_per_second": 871.114, | |
| "eval_steps_per_second": 54.445, | |
| "step": 2040000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 6.013333333333333e-08, | |
| "loss": 2.4091, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "eval_loss": 2.2319512367248535, | |
| "eval_runtime": 345.0718, | |
| "eval_samples_per_second": 869.326, | |
| "eval_steps_per_second": 54.334, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_loss": 2.231105327606201, | |
| "eval_runtime": 345.8677, | |
| "eval_samples_per_second": 867.326, | |
| "eval_steps_per_second": 54.209, | |
| "step": 2056000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 5.7400000000000004e-08, | |
| "loss": 2.4137, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 2.2278153896331787, | |
| "eval_runtime": 345.3364, | |
| "eval_samples_per_second": 868.66, | |
| "eval_steps_per_second": 54.292, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "eval_loss": 2.2343814373016357, | |
| "eval_runtime": 344.9277, | |
| "eval_samples_per_second": 869.69, | |
| "eval_steps_per_second": 54.356, | |
| "step": 2072000 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 5.4666666666666666e-08, | |
| "loss": 2.4063, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "eval_loss": 2.233853340148926, | |
| "eval_runtime": 346.3645, | |
| "eval_samples_per_second": 866.082, | |
| "eval_steps_per_second": 54.131, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_loss": 2.22705078125, | |
| "eval_runtime": 344.9123, | |
| "eval_samples_per_second": 869.728, | |
| "eval_steps_per_second": 54.359, | |
| "step": 2088000 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 5.1933333333333335e-08, | |
| "loss": 2.4046, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "eval_loss": 2.22632098197937, | |
| "eval_runtime": 346.6997, | |
| "eval_samples_per_second": 865.244, | |
| "eval_steps_per_second": 54.078, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_loss": 2.236851453781128, | |
| "eval_runtime": 346.071, | |
| "eval_samples_per_second": 866.816, | |
| "eval_steps_per_second": 54.177, | |
| "step": 2104000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 4.92e-08, | |
| "loss": 2.4105, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 2.2329680919647217, | |
| "eval_runtime": 347.6747, | |
| "eval_samples_per_second": 862.818, | |
| "eval_steps_per_second": 53.927, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "eval_loss": 2.236093521118164, | |
| "eval_runtime": 346.0239, | |
| "eval_samples_per_second": 866.934, | |
| "eval_steps_per_second": 54.184, | |
| "step": 2120000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 4.6466666666666666e-08, | |
| "loss": 2.4045, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "eval_loss": 2.231955051422119, | |
| "eval_runtime": 345.4242, | |
| "eval_samples_per_second": 868.439, | |
| "eval_steps_per_second": 54.278, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.2282557487487793, | |
| "eval_runtime": 345.9755, | |
| "eval_samples_per_second": 867.056, | |
| "eval_steps_per_second": 54.192, | |
| "step": 2136000 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 4.3733333333333335e-08, | |
| "loss": 2.4093, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_loss": 2.22622013092041, | |
| "eval_runtime": 347.3733, | |
| "eval_samples_per_second": 863.567, | |
| "eval_steps_per_second": 53.974, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "eval_loss": 2.229443311691284, | |
| "eval_runtime": 346.1833, | |
| "eval_samples_per_second": 866.535, | |
| "eval_steps_per_second": 54.159, | |
| "step": 2152000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 4.1e-08, | |
| "loss": 2.4109, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 2.233405351638794, | |
| "eval_runtime": 346.0615, | |
| "eval_samples_per_second": 866.84, | |
| "eval_steps_per_second": 54.178, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_loss": 2.236346483230591, | |
| "eval_runtime": 345.3461, | |
| "eval_samples_per_second": 868.636, | |
| "eval_steps_per_second": 54.29, | |
| "step": 2168000 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 3.8266666666666665e-08, | |
| "loss": 2.4061, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "eval_loss": 2.2308871746063232, | |
| "eval_runtime": 347.2972, | |
| "eval_samples_per_second": 863.756, | |
| "eval_steps_per_second": 53.985, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 2.2269339561462402, | |
| "eval_runtime": 347.1506, | |
| "eval_samples_per_second": 864.121, | |
| "eval_steps_per_second": 54.008, | |
| "step": 2184000 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 3.5533333333333334e-08, | |
| "loss": 2.4007, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "eval_loss": 2.236927032470703, | |
| "eval_runtime": 347.4425, | |
| "eval_samples_per_second": 863.395, | |
| "eval_steps_per_second": 53.963, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "eval_loss": 2.229724168777466, | |
| "eval_runtime": 345.6431, | |
| "eval_samples_per_second": 867.889, | |
| "eval_steps_per_second": 54.244, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 3.28e-08, | |
| "loss": 2.4034, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "eval_loss": 2.2266740798950195, | |
| "eval_runtime": 346.5718, | |
| "eval_samples_per_second": 865.564, | |
| "eval_steps_per_second": 54.098, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_loss": 2.2310221195220947, | |
| "eval_runtime": 346.6214, | |
| "eval_samples_per_second": 865.44, | |
| "eval_steps_per_second": 54.091, | |
| "step": 2216000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 3.0066666666666665e-08, | |
| "loss": 2.4049, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "eval_loss": 2.236175060272217, | |
| "eval_runtime": 348.3819, | |
| "eval_samples_per_second": 861.067, | |
| "eval_steps_per_second": 53.817, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "eval_loss": 2.231903076171875, | |
| "eval_runtime": 347.5521, | |
| "eval_samples_per_second": 863.122, | |
| "eval_steps_per_second": 53.946, | |
| "step": 2232000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 2.7333333333333333e-08, | |
| "loss": 2.4052, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "eval_loss": 2.2307627201080322, | |
| "eval_runtime": 347.1934, | |
| "eval_samples_per_second": 864.014, | |
| "eval_steps_per_second": 54.002, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "eval_loss": 2.2225306034088135, | |
| "eval_runtime": 347.1345, | |
| "eval_samples_per_second": 864.161, | |
| "eval_steps_per_second": 54.011, | |
| "step": 2248000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 2.46e-08, | |
| "loss": 2.4102, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "eval_loss": 2.2365851402282715, | |
| "eval_runtime": 347.8217, | |
| "eval_samples_per_second": 862.453, | |
| "eval_steps_per_second": 53.904, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "eval_loss": 2.232743740081787, | |
| "eval_runtime": 347.6812, | |
| "eval_samples_per_second": 862.802, | |
| "eval_steps_per_second": 53.926, | |
| "step": 2264000 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 2.1866666666666667e-08, | |
| "loss": 2.4046, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "eval_loss": 2.2304911613464355, | |
| "eval_runtime": 348.0072, | |
| "eval_samples_per_second": 861.994, | |
| "eval_steps_per_second": 53.875, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_loss": 2.230863094329834, | |
| "eval_runtime": 347.1957, | |
| "eval_samples_per_second": 864.008, | |
| "eval_steps_per_second": 54.001, | |
| "step": 2280000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 1.9133333333333333e-08, | |
| "loss": 2.4066, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "eval_loss": 2.2291176319122314, | |
| "eval_runtime": 347.3697, | |
| "eval_samples_per_second": 863.576, | |
| "eval_steps_per_second": 53.974, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "eval_loss": 2.2300875186920166, | |
| "eval_runtime": 348.7468, | |
| "eval_samples_per_second": 860.165, | |
| "eval_steps_per_second": 53.761, | |
| "step": 2296000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1.64e-08, | |
| "loss": 2.4041, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 2.237844467163086, | |
| "eval_runtime": 347.5443, | |
| "eval_samples_per_second": 863.142, | |
| "eval_steps_per_second": 53.947, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "eval_loss": 2.2317147254943848, | |
| "eval_runtime": 348.3274, | |
| "eval_samples_per_second": 861.201, | |
| "eval_steps_per_second": 53.826, | |
| "step": 2312000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1.3666666666666667e-08, | |
| "loss": 2.4081, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "eval_loss": 2.232565402984619, | |
| "eval_runtime": 349.1958, | |
| "eval_samples_per_second": 859.059, | |
| "eval_steps_per_second": 53.692, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_loss": 2.2412142753601074, | |
| "eval_runtime": 347.7133, | |
| "eval_samples_per_second": 862.722, | |
| "eval_steps_per_second": 53.921, | |
| "step": 2328000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 1.0933333333333334e-08, | |
| "loss": 2.4147, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 2.2348580360412598, | |
| "eval_runtime": 348.9265, | |
| "eval_samples_per_second": 859.722, | |
| "eval_steps_per_second": 53.733, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "eval_loss": 2.229579210281372, | |
| "eval_runtime": 348.1888, | |
| "eval_samples_per_second": 861.544, | |
| "eval_steps_per_second": 53.847, | |
| "step": 2344000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 8.2e-09, | |
| "loss": 2.4105, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_loss": 2.231281280517578, | |
| "eval_runtime": 348.2564, | |
| "eval_samples_per_second": 861.377, | |
| "eval_steps_per_second": 53.837, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "eval_loss": 2.229707717895508, | |
| "eval_runtime": 349.2314, | |
| "eval_samples_per_second": 858.972, | |
| "eval_steps_per_second": 53.686, | |
| "step": 2360000 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 5.466666666666667e-09, | |
| "loss": 2.4096, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "eval_loss": 2.2240703105926514, | |
| "eval_runtime": 348.1981, | |
| "eval_samples_per_second": 861.521, | |
| "eval_steps_per_second": 53.846, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_loss": 2.232208490371704, | |
| "eval_runtime": 349.4311, | |
| "eval_samples_per_second": 858.481, | |
| "eval_steps_per_second": 53.656, | |
| "step": 2376000 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 2.7333333333333334e-09, | |
| "loss": 2.4089, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "eval_loss": 2.234354019165039, | |
| "eval_runtime": 349.741, | |
| "eval_samples_per_second": 857.72, | |
| "eval_steps_per_second": 53.608, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "eval_loss": 2.229137659072876, | |
| "eval_runtime": 349.1189, | |
| "eval_samples_per_second": 859.249, | |
| "eval_steps_per_second": 53.704, | |
| "step": 2392000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.0, | |
| "loss": 2.4048, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "eval_loss": 2.227388858795166, | |
| "eval_runtime": 348.8655, | |
| "eval_samples_per_second": 859.873, | |
| "eval_steps_per_second": 53.743, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "step": 2400000, | |
| "total_flos": 7.587638746774346e+17, | |
| "train_loss": 2.443978935546875, | |
| "train_runtime": 257950.5102, | |
| "train_samples_per_second": 148.866, | |
| "train_steps_per_second": 9.304 | |
| } | |
| ], | |
| "logging_steps": 16000, | |
| "max_steps": 2400000, | |
| "num_train_epochs": 7, | |
| "save_steps": 32000, | |
| "total_flos": 7.587638746774346e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |