| { | |
| "best_metric": 2.6206448078155518, | |
| "best_model_checkpoint": "./model_tweets_2020_Q3_50/checkpoint-1696000", | |
| "epoch": 10.143273741600101, | |
| "eval_steps": 8000, | |
| "global_step": 2400000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.9380319118499756, | |
| "eval_runtime": 413.1894, | |
| "eval_samples_per_second": 482.224, | |
| "eval_steps_per_second": 30.141, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.0726666666666665e-07, | |
| "loss": 3.1308, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.85927152633667, | |
| "eval_runtime": 411.8608, | |
| "eval_samples_per_second": 483.78, | |
| "eval_steps_per_second": 30.238, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 2.806320905685425, | |
| "eval_runtime": 412.6446, | |
| "eval_samples_per_second": 482.861, | |
| "eval_steps_per_second": 30.181, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.0453333333333336e-07, | |
| "loss": 2.9519, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 2.7831950187683105, | |
| "eval_runtime": 413.8798, | |
| "eval_samples_per_second": 481.42, | |
| "eval_steps_per_second": 30.091, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 2.75207257270813, | |
| "eval_runtime": 415.2779, | |
| "eval_samples_per_second": 479.799, | |
| "eval_steps_per_second": 29.99, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.018e-07, | |
| "loss": 2.889, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.732224225997925, | |
| "eval_runtime": 412.3868, | |
| "eval_samples_per_second": 483.163, | |
| "eval_steps_per_second": 30.2, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 2.7259225845336914, | |
| "eval_runtime": 413.3395, | |
| "eval_samples_per_second": 482.049, | |
| "eval_steps_per_second": 30.13, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.9906666666666667e-07, | |
| "loss": 2.8592, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.7218177318573, | |
| "eval_runtime": 416.6569, | |
| "eval_samples_per_second": 478.211, | |
| "eval_steps_per_second": 29.89, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 2.7105536460876465, | |
| "eval_runtime": 416.4392, | |
| "eval_samples_per_second": 478.461, | |
| "eval_steps_per_second": 29.906, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.963333333333333e-07, | |
| "loss": 2.8345, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 2.7070746421813965, | |
| "eval_runtime": 412.3646, | |
| "eval_samples_per_second": 483.189, | |
| "eval_steps_per_second": 30.201, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 2.690347671508789, | |
| "eval_runtime": 411.5327, | |
| "eval_samples_per_second": 484.166, | |
| "eval_steps_per_second": 30.262, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.936e-07, | |
| "loss": 2.8303, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 2.700122356414795, | |
| "eval_runtime": 415.2403, | |
| "eval_samples_per_second": 479.843, | |
| "eval_steps_per_second": 29.992, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.692945957183838, | |
| "eval_runtime": 418.3575, | |
| "eval_samples_per_second": 476.267, | |
| "eval_steps_per_second": 29.769, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3.908666666666667e-07, | |
| "loss": 2.824, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 2.690654993057251, | |
| "eval_runtime": 418.1816, | |
| "eval_samples_per_second": 476.468, | |
| "eval_steps_per_second": 29.781, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.685214042663574, | |
| "eval_runtime": 414.1853, | |
| "eval_samples_per_second": 481.065, | |
| "eval_steps_per_second": 30.069, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.8813333333333334e-07, | |
| "loss": 2.8223, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 2.6804039478302, | |
| "eval_runtime": 415.7725, | |
| "eval_samples_per_second": 479.228, | |
| "eval_steps_per_second": 29.954, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 2.672717332839966, | |
| "eval_runtime": 413.8751, | |
| "eval_samples_per_second": 481.425, | |
| "eval_steps_per_second": 30.091, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.854e-07, | |
| "loss": 2.8141, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 2.678410291671753, | |
| "eval_runtime": 416.4592, | |
| "eval_samples_per_second": 478.438, | |
| "eval_steps_per_second": 29.904, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 2.6774685382843018, | |
| "eval_runtime": 415.2116, | |
| "eval_samples_per_second": 479.876, | |
| "eval_steps_per_second": 29.994, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.8266666666666665e-07, | |
| "loss": 2.8124, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 2.6723482608795166, | |
| "eval_runtime": 414.2419, | |
| "eval_samples_per_second": 480.999, | |
| "eval_steps_per_second": 30.065, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 2.668304681777954, | |
| "eval_runtime": 416.7765, | |
| "eval_samples_per_second": 478.074, | |
| "eval_steps_per_second": 29.882, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.799333333333333e-07, | |
| "loss": 2.8042, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 2.671178102493286, | |
| "eval_runtime": 416.7365, | |
| "eval_samples_per_second": 478.12, | |
| "eval_steps_per_second": 29.885, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 2.6660544872283936, | |
| "eval_runtime": 416.2186, | |
| "eval_samples_per_second": 478.715, | |
| "eval_steps_per_second": 29.922, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.772e-07, | |
| "loss": 2.8051, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 2.67832612991333, | |
| "eval_runtime": 414.4038, | |
| "eval_samples_per_second": 480.811, | |
| "eval_steps_per_second": 30.053, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 2.6682960987091064, | |
| "eval_runtime": 415.8345, | |
| "eval_samples_per_second": 479.157, | |
| "eval_steps_per_second": 29.949, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.7446666666666667e-07, | |
| "loss": 2.798, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 2.6656229496002197, | |
| "eval_runtime": 416.0143, | |
| "eval_samples_per_second": 478.95, | |
| "eval_steps_per_second": 29.936, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 2.6659064292907715, | |
| "eval_runtime": 415.0891, | |
| "eval_samples_per_second": 480.017, | |
| "eval_steps_per_second": 30.003, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.7173333333333333e-07, | |
| "loss": 2.8043, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 2.6699647903442383, | |
| "eval_runtime": 414.3393, | |
| "eval_samples_per_second": 480.886, | |
| "eval_steps_per_second": 30.057, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 2.667956829071045, | |
| "eval_runtime": 415.3586, | |
| "eval_samples_per_second": 479.706, | |
| "eval_steps_per_second": 29.984, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.69e-07, | |
| "loss": 2.8055, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 2.659658432006836, | |
| "eval_runtime": 417.4574, | |
| "eval_samples_per_second": 477.294, | |
| "eval_steps_per_second": 29.833, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 2.659682512283325, | |
| "eval_runtime": 415.1848, | |
| "eval_samples_per_second": 479.907, | |
| "eval_steps_per_second": 29.996, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.6626666666666664e-07, | |
| "loss": 2.8048, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 2.656872272491455, | |
| "eval_runtime": 413.9085, | |
| "eval_samples_per_second": 481.387, | |
| "eval_steps_per_second": 30.089, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 2.6502044200897217, | |
| "eval_runtime": 415.1132, | |
| "eval_samples_per_second": 479.99, | |
| "eval_steps_per_second": 30.001, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.6353333333333335e-07, | |
| "loss": 2.806, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.659311532974243, | |
| "eval_runtime": 416.7743, | |
| "eval_samples_per_second": 478.076, | |
| "eval_steps_per_second": 29.882, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 2.659724473953247, | |
| "eval_runtime": 416.7046, | |
| "eval_samples_per_second": 478.157, | |
| "eval_steps_per_second": 29.887, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.608e-07, | |
| "loss": 2.8012, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 2.6603612899780273, | |
| "eval_runtime": 415.9031, | |
| "eval_samples_per_second": 479.078, | |
| "eval_steps_per_second": 29.944, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 2.6545276641845703, | |
| "eval_runtime": 414.5962, | |
| "eval_samples_per_second": 480.588, | |
| "eval_steps_per_second": 30.039, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.5806666666666666e-07, | |
| "loss": 2.8029, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 2.6571340560913086, | |
| "eval_runtime": 416.6303, | |
| "eval_samples_per_second": 478.242, | |
| "eval_steps_per_second": 29.892, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 2.6534266471862793, | |
| "eval_runtime": 416.4252, | |
| "eval_samples_per_second": 478.477, | |
| "eval_steps_per_second": 29.907, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.553333333333333e-07, | |
| "loss": 2.7991, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 2.665046215057373, | |
| "eval_runtime": 414.7989, | |
| "eval_samples_per_second": 480.353, | |
| "eval_steps_per_second": 30.024, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 2.6680290699005127, | |
| "eval_runtime": 413.9236, | |
| "eval_samples_per_second": 481.369, | |
| "eval_steps_per_second": 30.088, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 3.5259999999999997e-07, | |
| "loss": 2.7949, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 2.6544442176818848, | |
| "eval_runtime": 415.4503, | |
| "eval_samples_per_second": 479.6, | |
| "eval_steps_per_second": 29.977, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 2.645993709564209, | |
| "eval_runtime": 414.7891, | |
| "eval_samples_per_second": 480.365, | |
| "eval_steps_per_second": 30.025, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 3.498666666666667e-07, | |
| "loss": 2.7972, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 2.655319929122925, | |
| "eval_runtime": 413.6708, | |
| "eval_samples_per_second": 481.663, | |
| "eval_steps_per_second": 30.106, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 2.6427876949310303, | |
| "eval_runtime": 415.818, | |
| "eval_samples_per_second": 479.176, | |
| "eval_steps_per_second": 29.951, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.4713333333333333e-07, | |
| "loss": 2.7924, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 2.6535725593566895, | |
| "eval_runtime": 415.5951, | |
| "eval_samples_per_second": 479.433, | |
| "eval_steps_per_second": 29.967, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 2.6550498008728027, | |
| "eval_runtime": 416.627, | |
| "eval_samples_per_second": 478.246, | |
| "eval_steps_per_second": 29.892, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.444e-07, | |
| "loss": 2.805, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 2.6524453163146973, | |
| "eval_runtime": 417.0486, | |
| "eval_samples_per_second": 477.762, | |
| "eval_steps_per_second": 29.862, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 2.652374744415283, | |
| "eval_runtime": 416.3041, | |
| "eval_samples_per_second": 478.616, | |
| "eval_steps_per_second": 29.916, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.416666666666667e-07, | |
| "loss": 2.7972, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 2.657935619354248, | |
| "eval_runtime": 415.2722, | |
| "eval_samples_per_second": 479.806, | |
| "eval_steps_per_second": 29.99, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 2.649958372116089, | |
| "eval_runtime": 416.9007, | |
| "eval_samples_per_second": 477.932, | |
| "eval_steps_per_second": 29.873, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.3893333333333335e-07, | |
| "loss": 2.8003, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 2.652555227279663, | |
| "eval_runtime": 416.2811, | |
| "eval_samples_per_second": 478.643, | |
| "eval_steps_per_second": 29.917, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 2.6443850994110107, | |
| "eval_runtime": 416.0471, | |
| "eval_samples_per_second": 478.912, | |
| "eval_steps_per_second": 29.934, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.3619999999999995e-07, | |
| "loss": 2.8005, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 2.6462562084198, | |
| "eval_runtime": 413.6662, | |
| "eval_samples_per_second": 481.669, | |
| "eval_steps_per_second": 30.106, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 2.6549031734466553, | |
| "eval_runtime": 414.0878, | |
| "eval_samples_per_second": 481.178, | |
| "eval_steps_per_second": 30.076, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.3346666666666666e-07, | |
| "loss": 2.7957, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 2.6530463695526123, | |
| "eval_runtime": 415.4694, | |
| "eval_samples_per_second": 479.578, | |
| "eval_steps_per_second": 29.976, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 2.6503868103027344, | |
| "eval_runtime": 415.0439, | |
| "eval_samples_per_second": 480.07, | |
| "eval_steps_per_second": 30.006, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3.307333333333333e-07, | |
| "loss": 2.7949, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 2.6479649543762207, | |
| "eval_runtime": 415.3875, | |
| "eval_samples_per_second": 479.673, | |
| "eval_steps_per_second": 29.982, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 2.64969539642334, | |
| "eval_runtime": 415.7352, | |
| "eval_samples_per_second": 479.271, | |
| "eval_steps_per_second": 29.957, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.28e-07, | |
| "loss": 2.7978, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 2.6489925384521484, | |
| "eval_runtime": 416.7057, | |
| "eval_samples_per_second": 478.155, | |
| "eval_steps_per_second": 29.887, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 2.6505074501037598, | |
| "eval_runtime": 415.397, | |
| "eval_samples_per_second": 479.662, | |
| "eval_steps_per_second": 29.981, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.252666666666667e-07, | |
| "loss": 2.8041, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 2.6387767791748047, | |
| "eval_runtime": 414.3947, | |
| "eval_samples_per_second": 480.822, | |
| "eval_steps_per_second": 30.053, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 2.645991325378418, | |
| "eval_runtime": 415.4791, | |
| "eval_samples_per_second": 479.567, | |
| "eval_steps_per_second": 29.975, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.2253333333333334e-07, | |
| "loss": 2.7935, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 2.6518516540527344, | |
| "eval_runtime": 415.3071, | |
| "eval_samples_per_second": 479.765, | |
| "eval_steps_per_second": 29.987, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 2.6494412422180176, | |
| "eval_runtime": 416.2526, | |
| "eval_samples_per_second": 478.676, | |
| "eval_steps_per_second": 29.919, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.198e-07, | |
| "loss": 2.7982, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 2.654994249343872, | |
| "eval_runtime": 415.1386, | |
| "eval_samples_per_second": 479.96, | |
| "eval_steps_per_second": 30.0, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 2.6460273265838623, | |
| "eval_runtime": 415.2099, | |
| "eval_samples_per_second": 479.878, | |
| "eval_steps_per_second": 29.994, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 3.1706666666666665e-07, | |
| "loss": 2.7949, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 2.649731397628784, | |
| "eval_runtime": 416.6025, | |
| "eval_samples_per_second": 478.274, | |
| "eval_steps_per_second": 29.894, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 2.6478219032287598, | |
| "eval_runtime": 416.4871, | |
| "eval_samples_per_second": 478.406, | |
| "eval_steps_per_second": 29.902, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 3.1433333333333336e-07, | |
| "loss": 2.7953, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 2.6487133502960205, | |
| "eval_runtime": 414.3193, | |
| "eval_samples_per_second": 480.909, | |
| "eval_steps_per_second": 30.059, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 2.640001058578491, | |
| "eval_runtime": 414.4485, | |
| "eval_samples_per_second": 480.759, | |
| "eval_steps_per_second": 30.05, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.116e-07, | |
| "loss": 2.7942, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 2.6439836025238037, | |
| "eval_runtime": 415.349, | |
| "eval_samples_per_second": 479.717, | |
| "eval_steps_per_second": 29.984, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": NaN, | |
| "eval_runtime": 415.6748, | |
| "eval_samples_per_second": 479.341, | |
| "eval_steps_per_second": 29.961, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.0886666666666667e-07, | |
| "loss": 2.803, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 2.6454689502716064, | |
| "eval_runtime": 416.6019, | |
| "eval_samples_per_second": 478.274, | |
| "eval_steps_per_second": 29.894, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 2.64009165763855, | |
| "eval_runtime": 414.1362, | |
| "eval_samples_per_second": 481.122, | |
| "eval_steps_per_second": 30.072, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 3.061333333333333e-07, | |
| "loss": 2.7961, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 2.6510584354400635, | |
| "eval_runtime": 414.5176, | |
| "eval_samples_per_second": 480.679, | |
| "eval_steps_per_second": 30.045, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 2.6400928497314453, | |
| "eval_runtime": 414.9292, | |
| "eval_samples_per_second": 480.202, | |
| "eval_steps_per_second": 30.015, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.034e-07, | |
| "loss": 2.7975, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 2.6436855792999268, | |
| "eval_runtime": 414.0912, | |
| "eval_samples_per_second": 481.174, | |
| "eval_steps_per_second": 30.075, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 2.6431784629821777, | |
| "eval_runtime": 414.8023, | |
| "eval_samples_per_second": 480.349, | |
| "eval_steps_per_second": 30.024, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.0066666666666663e-07, | |
| "loss": 2.7946, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 2.6461291313171387, | |
| "eval_runtime": 415.6685, | |
| "eval_samples_per_second": 479.348, | |
| "eval_steps_per_second": 29.961, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 2.6491315364837646, | |
| "eval_runtime": 417.1915, | |
| "eval_samples_per_second": 477.598, | |
| "eval_steps_per_second": 29.852, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.9793333333333334e-07, | |
| "loss": 2.7963, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 2.6441593170166016, | |
| "eval_runtime": 417.5373, | |
| "eval_samples_per_second": 477.203, | |
| "eval_steps_per_second": 29.827, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 2.641571283340454, | |
| "eval_runtime": 414.7923, | |
| "eval_samples_per_second": 480.361, | |
| "eval_steps_per_second": 30.025, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.952e-07, | |
| "loss": 2.7924, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 2.6403403282165527, | |
| "eval_runtime": 413.6349, | |
| "eval_samples_per_second": 481.705, | |
| "eval_steps_per_second": 30.109, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 2.6465871334075928, | |
| "eval_runtime": 416.286, | |
| "eval_samples_per_second": 478.637, | |
| "eval_steps_per_second": 29.917, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.9246666666666665e-07, | |
| "loss": 2.8004, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 2.6435861587524414, | |
| "eval_runtime": 414.7095, | |
| "eval_samples_per_second": 480.457, | |
| "eval_steps_per_second": 30.031, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 2.6446969509124756, | |
| "eval_runtime": 415.0332, | |
| "eval_samples_per_second": 480.082, | |
| "eval_steps_per_second": 30.007, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.897333333333333e-07, | |
| "loss": 2.8039, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 2.641172409057617, | |
| "eval_runtime": 414.5379, | |
| "eval_samples_per_second": 480.656, | |
| "eval_steps_per_second": 30.043, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_loss": 2.639988422393799, | |
| "eval_runtime": 414.2916, | |
| "eval_samples_per_second": 480.941, | |
| "eval_steps_per_second": 30.061, | |
| "step": 712000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2.8699999999999996e-07, | |
| "loss": 2.7958, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 2.6418933868408203, | |
| "eval_runtime": 415.0166, | |
| "eval_samples_per_second": 480.101, | |
| "eval_steps_per_second": 30.008, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 2.6413352489471436, | |
| "eval_runtime": 413.087, | |
| "eval_samples_per_second": 482.344, | |
| "eval_steps_per_second": 30.149, | |
| "step": 728000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.8426666666666667e-07, | |
| "loss": 2.7967, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": NaN, | |
| "eval_runtime": 413.1334, | |
| "eval_samples_per_second": 482.29, | |
| "eval_steps_per_second": 30.145, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_loss": 2.639918327331543, | |
| "eval_runtime": 422.7228, | |
| "eval_samples_per_second": 471.349, | |
| "eval_steps_per_second": 29.461, | |
| "step": 744000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 2.815333333333333e-07, | |
| "loss": 2.7934, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 2.640524387359619, | |
| "eval_runtime": 422.6777, | |
| "eval_samples_per_second": 471.399, | |
| "eval_steps_per_second": 29.465, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_loss": 2.6387245655059814, | |
| "eval_runtime": 420.9074, | |
| "eval_samples_per_second": 473.382, | |
| "eval_steps_per_second": 29.588, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 2.7880000000000003e-07, | |
| "loss": 2.7988, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_loss": 2.64625883102417, | |
| "eval_runtime": 419.8681, | |
| "eval_samples_per_second": 474.554, | |
| "eval_steps_per_second": 29.662, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 2.6307883262634277, | |
| "eval_runtime": 413.6046, | |
| "eval_samples_per_second": 481.74, | |
| "eval_steps_per_second": 30.111, | |
| "step": 776000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 2.7606666666666664e-07, | |
| "loss": 2.793, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "eval_loss": 2.6342904567718506, | |
| "eval_runtime": 414.4973, | |
| "eval_samples_per_second": 480.703, | |
| "eval_steps_per_second": 30.046, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_loss": 2.6358492374420166, | |
| "eval_runtime": 414.875, | |
| "eval_samples_per_second": 480.265, | |
| "eval_steps_per_second": 30.019, | |
| "step": 792000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 2.733333333333333e-07, | |
| "loss": 2.797, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 2.639730930328369, | |
| "eval_runtime": 414.0225, | |
| "eval_samples_per_second": 481.254, | |
| "eval_steps_per_second": 30.08, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 2.6340529918670654, | |
| "eval_runtime": 415.9272, | |
| "eval_samples_per_second": 479.05, | |
| "eval_steps_per_second": 29.943, | |
| "step": 808000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.706e-07, | |
| "loss": 2.7832, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 2.6393821239471436, | |
| "eval_runtime": 419.307, | |
| "eval_samples_per_second": 475.189, | |
| "eval_steps_per_second": 29.701, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 2.6341216564178467, | |
| "eval_runtime": 415.9801, | |
| "eval_samples_per_second": 478.989, | |
| "eval_steps_per_second": 29.939, | |
| "step": 824000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 2.6786666666666666e-07, | |
| "loss": 2.792, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 2.642409086227417, | |
| "eval_runtime": 416.1328, | |
| "eval_samples_per_second": 478.814, | |
| "eval_steps_per_second": 29.928, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 2.638009786605835, | |
| "eval_runtime": 412.7545, | |
| "eval_samples_per_second": 482.733, | |
| "eval_steps_per_second": 30.173, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 2.651333333333333e-07, | |
| "loss": 2.7945, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "eval_loss": 2.6373209953308105, | |
| "eval_runtime": 415.2424, | |
| "eval_samples_per_second": 479.84, | |
| "eval_steps_per_second": 29.992, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "eval_loss": 2.636631965637207, | |
| "eval_runtime": 415.4773, | |
| "eval_samples_per_second": 479.569, | |
| "eval_steps_per_second": 29.975, | |
| "step": 856000 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 2.624e-07, | |
| "loss": 2.7876, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_loss": 2.6409096717834473, | |
| "eval_runtime": 413.1752, | |
| "eval_samples_per_second": 482.241, | |
| "eval_steps_per_second": 30.142, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_loss": 2.638249635696411, | |
| "eval_runtime": 412.6062, | |
| "eval_samples_per_second": 482.906, | |
| "eval_steps_per_second": 30.184, | |
| "step": 872000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 2.596666666666667e-07, | |
| "loss": 2.7975, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_loss": 2.62591290473938, | |
| "eval_runtime": 413.5939, | |
| "eval_samples_per_second": 481.753, | |
| "eval_steps_per_second": 30.112, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 2.6443488597869873, | |
| "eval_runtime": 415.3476, | |
| "eval_samples_per_second": 479.719, | |
| "eval_steps_per_second": 29.985, | |
| "step": 888000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 2.5693333333333333e-07, | |
| "loss": 2.7965, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_loss": 2.624751567840576, | |
| "eval_runtime": 415.4056, | |
| "eval_samples_per_second": 479.652, | |
| "eval_steps_per_second": 29.98, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "eval_loss": 2.639540433883667, | |
| "eval_runtime": 414.6525, | |
| "eval_samples_per_second": 480.523, | |
| "eval_steps_per_second": 30.035, | |
| "step": 904000 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 2.542e-07, | |
| "loss": 2.7991, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "eval_loss": 2.632520914077759, | |
| "eval_runtime": 414.5399, | |
| "eval_samples_per_second": 480.653, | |
| "eval_steps_per_second": 30.043, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_loss": 2.635369300842285, | |
| "eval_runtime": 415.2855, | |
| "eval_samples_per_second": 479.79, | |
| "eval_steps_per_second": 29.989, | |
| "step": 920000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 2.5146666666666664e-07, | |
| "loss": 2.7947, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 2.6342415809631348, | |
| "eval_runtime": 414.7268, | |
| "eval_samples_per_second": 480.437, | |
| "eval_steps_per_second": 30.029, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "eval_loss": 2.6290154457092285, | |
| "eval_runtime": 414.3923, | |
| "eval_samples_per_second": 480.825, | |
| "eval_steps_per_second": 30.054, | |
| "step": 936000 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 2.4873333333333335e-07, | |
| "loss": 2.7977, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 2.631457567214966, | |
| "eval_runtime": 414.9085, | |
| "eval_samples_per_second": 480.226, | |
| "eval_steps_per_second": 30.016, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_loss": 2.634674310684204, | |
| "eval_runtime": 415.5412, | |
| "eval_samples_per_second": 479.495, | |
| "eval_steps_per_second": 29.971, | |
| "step": 952000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.46e-07, | |
| "loss": 2.8, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_loss": 2.631823778152466, | |
| "eval_runtime": 415.1034, | |
| "eval_samples_per_second": 480.001, | |
| "eval_steps_per_second": 30.002, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 2.6328303813934326, | |
| "eval_runtime": 415.6276, | |
| "eval_samples_per_second": 479.395, | |
| "eval_steps_per_second": 29.964, | |
| "step": 968000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 2.4326666666666666e-07, | |
| "loss": 2.7945, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 2.6315038204193115, | |
| "eval_runtime": 414.41, | |
| "eval_samples_per_second": 480.804, | |
| "eval_steps_per_second": 30.052, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "eval_loss": 2.6296520233154297, | |
| "eval_runtime": 415.5411, | |
| "eval_samples_per_second": 479.495, | |
| "eval_steps_per_second": 29.971, | |
| "step": 984000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 2.405333333333333e-07, | |
| "loss": 2.7946, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_loss": 2.6377837657928467, | |
| "eval_runtime": 415.4925, | |
| "eval_samples_per_second": 479.551, | |
| "eval_steps_per_second": 29.974, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "eval_loss": 2.632783889770508, | |
| "eval_runtime": 415.0903, | |
| "eval_samples_per_second": 480.016, | |
| "eval_steps_per_second": 30.003, | |
| "step": 1000000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 2.3779999999999997e-07, | |
| "loss": 2.7962, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_loss": 2.6295533180236816, | |
| "eval_runtime": 413.2357, | |
| "eval_samples_per_second": 482.17, | |
| "eval_steps_per_second": 30.138, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_loss": 2.6346757411956787, | |
| "eval_runtime": 416.3926, | |
| "eval_samples_per_second": 478.515, | |
| "eval_steps_per_second": 29.909, | |
| "step": 1016000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 2.3506666666666668e-07, | |
| "loss": 2.7932, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 2.6355090141296387, | |
| "eval_runtime": 417.2451, | |
| "eval_samples_per_second": 477.537, | |
| "eval_steps_per_second": 29.848, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "eval_loss": 2.6363675594329834, | |
| "eval_runtime": 416.1756, | |
| "eval_samples_per_second": 478.764, | |
| "eval_steps_per_second": 29.925, | |
| "step": 1032000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 2.3233333333333334e-07, | |
| "loss": 2.7992, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_loss": 2.632688522338867, | |
| "eval_runtime": 414.8733, | |
| "eval_samples_per_second": 480.267, | |
| "eval_steps_per_second": 30.019, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 2.6272976398468018, | |
| "eval_runtime": 416.0306, | |
| "eval_samples_per_second": 478.931, | |
| "eval_steps_per_second": 29.935, | |
| "step": 1048000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2.2960000000000002e-07, | |
| "loss": 2.7922, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "eval_loss": 2.6301381587982178, | |
| "eval_runtime": 418.1292, | |
| "eval_samples_per_second": 476.527, | |
| "eval_steps_per_second": 29.785, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_loss": 2.634971857070923, | |
| "eval_runtime": 415.4628, | |
| "eval_samples_per_second": 479.586, | |
| "eval_steps_per_second": 29.976, | |
| "step": 1064000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 2.2686666666666667e-07, | |
| "loss": 2.7939, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_loss": 2.63580584526062, | |
| "eval_runtime": 414.2262, | |
| "eval_samples_per_second": 481.017, | |
| "eval_steps_per_second": 30.066, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "eval_loss": NaN, | |
| "eval_runtime": 415.858, | |
| "eval_samples_per_second": 479.13, | |
| "eval_steps_per_second": 29.948, | |
| "step": 1080000 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 2.2413333333333333e-07, | |
| "loss": 2.789, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 2.628849983215332, | |
| "eval_runtime": 416.3917, | |
| "eval_samples_per_second": 478.516, | |
| "eval_steps_per_second": 29.909, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 2.626696825027466, | |
| "eval_runtime": 415.8123, | |
| "eval_samples_per_second": 479.183, | |
| "eval_steps_per_second": 29.951, | |
| "step": 1096000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.214e-07, | |
| "loss": 2.7965, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_loss": 2.6229259967803955, | |
| "eval_runtime": 415.4378, | |
| "eval_samples_per_second": 479.615, | |
| "eval_steps_per_second": 29.978, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "eval_loss": 2.6331067085266113, | |
| "eval_runtime": 415.4213, | |
| "eval_samples_per_second": 479.634, | |
| "eval_steps_per_second": 29.979, | |
| "step": 1112000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.1866666666666667e-07, | |
| "loss": 2.7963, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "eval_loss": 2.6367764472961426, | |
| "eval_runtime": 416.9274, | |
| "eval_samples_per_second": 477.901, | |
| "eval_steps_per_second": 29.871, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "eval_loss": 2.6436047554016113, | |
| "eval_runtime": 414.3896, | |
| "eval_samples_per_second": 480.828, | |
| "eval_steps_per_second": 30.054, | |
| "step": 1128000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.1593333333333332e-07, | |
| "loss": 2.7993, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 2.6363236904144287, | |
| "eval_runtime": 414.4703, | |
| "eval_samples_per_second": 480.734, | |
| "eval_steps_per_second": 30.048, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 2.628790855407715, | |
| "eval_runtime": 413.6012, | |
| "eval_samples_per_second": 481.744, | |
| "eval_steps_per_second": 30.111, | |
| "step": 1144000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 2.132e-07, | |
| "loss": 2.7952, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_loss": 2.6294453144073486, | |
| "eval_runtime": 414.7494, | |
| "eval_samples_per_second": 480.411, | |
| "eval_steps_per_second": 30.028, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_loss": 2.6337034702301025, | |
| "eval_runtime": 416.1788, | |
| "eval_samples_per_second": 478.761, | |
| "eval_steps_per_second": 29.925, | |
| "step": 1160000 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.1046666666666666e-07, | |
| "loss": 2.7972, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 2.623483657836914, | |
| "eval_runtime": 414.4419, | |
| "eval_samples_per_second": 480.767, | |
| "eval_steps_per_second": 30.05, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_loss": 2.640516996383667, | |
| "eval_runtime": 414.5607, | |
| "eval_samples_per_second": 480.629, | |
| "eval_steps_per_second": 30.041, | |
| "step": 1176000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.0773333333333334e-07, | |
| "loss": 2.7988, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.626560926437378, | |
| "eval_runtime": 415.66, | |
| "eval_samples_per_second": 479.358, | |
| "eval_steps_per_second": 29.962, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "eval_loss": 2.632770299911499, | |
| "eval_runtime": 422.5737, | |
| "eval_samples_per_second": 471.515, | |
| "eval_steps_per_second": 29.472, | |
| "step": 1192000 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 2.05e-07, | |
| "loss": 2.7901, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "eval_loss": 2.6335248947143555, | |
| "eval_runtime": 419.9786, | |
| "eval_samples_per_second": 474.429, | |
| "eval_steps_per_second": 29.654, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_loss": 2.6405279636383057, | |
| "eval_runtime": 419.4258, | |
| "eval_samples_per_second": 475.054, | |
| "eval_steps_per_second": 29.693, | |
| "step": 1208000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 2.0226666666666668e-07, | |
| "loss": 2.7975, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "eval_loss": 2.624608278274536, | |
| "eval_runtime": 421.319, | |
| "eval_samples_per_second": 472.92, | |
| "eval_steps_per_second": 29.56, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_loss": 2.6314573287963867, | |
| "eval_runtime": 417.198, | |
| "eval_samples_per_second": 477.591, | |
| "eval_steps_per_second": 29.852, | |
| "step": 1224000 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 1.9953333333333333e-07, | |
| "loss": 2.7974, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "eval_loss": 2.639028549194336, | |
| "eval_runtime": 414.299, | |
| "eval_samples_per_second": 480.933, | |
| "eval_steps_per_second": 30.06, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "eval_loss": 2.631808280944824, | |
| "eval_runtime": 413.617, | |
| "eval_samples_per_second": 481.726, | |
| "eval_steps_per_second": 30.11, | |
| "step": 1240000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 1.968e-07, | |
| "loss": 2.7909, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_loss": 2.6236965656280518, | |
| "eval_runtime": 414.1647, | |
| "eval_samples_per_second": 481.089, | |
| "eval_steps_per_second": 30.07, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "eval_loss": 2.6343328952789307, | |
| "eval_runtime": 416.7312, | |
| "eval_samples_per_second": 478.126, | |
| "eval_steps_per_second": 29.885, | |
| "step": 1256000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 1.9406666666666667e-07, | |
| "loss": 2.7899, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "eval_loss": 2.628756284713745, | |
| "eval_runtime": 415.9879, | |
| "eval_samples_per_second": 478.98, | |
| "eval_steps_per_second": 29.938, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "eval_loss": 2.629678964614868, | |
| "eval_runtime": 415.5157, | |
| "eval_samples_per_second": 479.525, | |
| "eval_steps_per_second": 29.972, | |
| "step": 1272000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 1.9133333333333333e-07, | |
| "loss": 2.7937, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 2.63431715965271, | |
| "eval_runtime": 416.1785, | |
| "eval_samples_per_second": 478.761, | |
| "eval_steps_per_second": 29.925, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "eval_loss": 2.6306326389312744, | |
| "eval_runtime": 421.3392, | |
| "eval_samples_per_second": 472.897, | |
| "eval_steps_per_second": 29.558, | |
| "step": 1288000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 1.886e-07, | |
| "loss": 2.7916, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "eval_loss": 2.6267640590667725, | |
| "eval_runtime": 419.4553, | |
| "eval_samples_per_second": 475.021, | |
| "eval_steps_per_second": 29.691, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "eval_loss": 2.63167667388916, | |
| "eval_runtime": 419.3882, | |
| "eval_samples_per_second": 475.097, | |
| "eval_steps_per_second": 29.696, | |
| "step": 1304000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 1.8586666666666666e-07, | |
| "loss": 2.7874, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "eval_loss": 2.6380093097686768, | |
| "eval_runtime": 418.5148, | |
| "eval_samples_per_second": 476.088, | |
| "eval_steps_per_second": 29.758, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "eval_loss": 2.6281051635742188, | |
| "eval_runtime": 415.0221, | |
| "eval_samples_per_second": 480.095, | |
| "eval_steps_per_second": 30.008, | |
| "step": 1320000 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 1.8313333333333332e-07, | |
| "loss": 2.7967, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "eval_loss": 2.633375406265259, | |
| "eval_runtime": 414.3238, | |
| "eval_samples_per_second": 480.904, | |
| "eval_steps_per_second": 30.059, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "eval_loss": 2.6272847652435303, | |
| "eval_runtime": 413.511, | |
| "eval_samples_per_second": 481.849, | |
| "eval_steps_per_second": 30.118, | |
| "step": 1336000 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 1.804e-07, | |
| "loss": 2.791, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "eval_loss": 2.6339497566223145, | |
| "eval_runtime": 414.4191, | |
| "eval_samples_per_second": 480.794, | |
| "eval_steps_per_second": 30.052, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_loss": 2.6276426315307617, | |
| "eval_runtime": 415.1118, | |
| "eval_samples_per_second": 479.991, | |
| "eval_steps_per_second": 30.002, | |
| "step": 1352000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 1.7766666666666666e-07, | |
| "loss": 2.791, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "eval_loss": 2.6246891021728516, | |
| "eval_runtime": 414.8524, | |
| "eval_samples_per_second": 480.291, | |
| "eval_steps_per_second": 30.02, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "eval_loss": 2.630341053009033, | |
| "eval_runtime": 413.0138, | |
| "eval_samples_per_second": 482.429, | |
| "eval_steps_per_second": 30.154, | |
| "step": 1368000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 1.7493333333333334e-07, | |
| "loss": 2.7909, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "eval_loss": 2.635547637939453, | |
| "eval_runtime": 414.6547, | |
| "eval_samples_per_second": 480.52, | |
| "eval_steps_per_second": 30.035, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "eval_loss": 2.6352195739746094, | |
| "eval_runtime": 415.8747, | |
| "eval_samples_per_second": 479.111, | |
| "eval_steps_per_second": 29.947, | |
| "step": 1384000 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 1.722e-07, | |
| "loss": 2.7833, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "eval_loss": 2.6320648193359375, | |
| "eval_runtime": 415.8557, | |
| "eval_samples_per_second": 479.133, | |
| "eval_steps_per_second": 29.948, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "eval_loss": 2.6335620880126953, | |
| "eval_runtime": 415.5817, | |
| "eval_samples_per_second": 479.448, | |
| "eval_steps_per_second": 29.968, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 1.6946666666666668e-07, | |
| "loss": 2.7944, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "eval_loss": 2.631206750869751, | |
| "eval_runtime": 414.1531, | |
| "eval_samples_per_second": 481.102, | |
| "eval_steps_per_second": 30.071, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_loss": 2.6222622394561768, | |
| "eval_runtime": 414.6922, | |
| "eval_samples_per_second": 480.477, | |
| "eval_steps_per_second": 30.032, | |
| "step": 1416000 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 1.6673333333333333e-07, | |
| "loss": 2.8001, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_loss": 2.6369099617004395, | |
| "eval_runtime": 415.0521, | |
| "eval_samples_per_second": 480.06, | |
| "eval_steps_per_second": 30.006, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "eval_loss": 2.629903793334961, | |
| "eval_runtime": 414.081, | |
| "eval_samples_per_second": 481.186, | |
| "eval_steps_per_second": 30.076, | |
| "step": 1432000 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 1.64e-07, | |
| "loss": 2.7954, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_loss": 2.637263536453247, | |
| "eval_runtime": 414.6606, | |
| "eval_samples_per_second": 480.513, | |
| "eval_steps_per_second": 30.034, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "eval_loss": 2.622265100479126, | |
| "eval_runtime": 416.7434, | |
| "eval_samples_per_second": 478.112, | |
| "eval_steps_per_second": 29.884, | |
| "step": 1448000 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 1.6126666666666667e-07, | |
| "loss": 2.7914, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "eval_loss": 2.622511863708496, | |
| "eval_runtime": 417.3412, | |
| "eval_samples_per_second": 477.427, | |
| "eval_steps_per_second": 29.841, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "eval_loss": 2.627666473388672, | |
| "eval_runtime": 416.5994, | |
| "eval_samples_per_second": 478.277, | |
| "eval_steps_per_second": 29.894, | |
| "step": 1464000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 1.5853333333333332e-07, | |
| "loss": 2.7896, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_loss": 2.633397102355957, | |
| "eval_runtime": 415.8503, | |
| "eval_samples_per_second": 479.139, | |
| "eval_steps_per_second": 29.948, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "eval_loss": 2.625962495803833, | |
| "eval_runtime": 414.2001, | |
| "eval_samples_per_second": 481.048, | |
| "eval_steps_per_second": 30.068, | |
| "step": 1480000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 1.558e-07, | |
| "loss": 2.7925, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "eval_loss": 2.6312003135681152, | |
| "eval_runtime": 415.5727, | |
| "eval_samples_per_second": 479.459, | |
| "eval_steps_per_second": 29.968, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "eval_loss": 2.633601427078247, | |
| "eval_runtime": 416.5001, | |
| "eval_samples_per_second": 478.391, | |
| "eval_steps_per_second": 29.902, | |
| "step": 1496000 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 1.5306666666666666e-07, | |
| "loss": 2.7976, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "eval_loss": 2.626960277557373, | |
| "eval_runtime": 413.9057, | |
| "eval_samples_per_second": 481.39, | |
| "eval_steps_per_second": 30.089, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_loss": 2.6285572052001953, | |
| "eval_runtime": 415.4246, | |
| "eval_samples_per_second": 479.63, | |
| "eval_steps_per_second": 29.979, | |
| "step": 1512000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 1.5033333333333332e-07, | |
| "loss": 2.8025, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "eval_loss": 2.632030487060547, | |
| "eval_runtime": 415.8213, | |
| "eval_samples_per_second": 479.172, | |
| "eval_steps_per_second": 29.95, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "eval_loss": 2.6252386569976807, | |
| "eval_runtime": 415.748, | |
| "eval_samples_per_second": 479.257, | |
| "eval_steps_per_second": 29.956, | |
| "step": 1528000 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 1.476e-07, | |
| "loss": 2.7953, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "eval_loss": 2.631873607635498, | |
| "eval_runtime": 413.9705, | |
| "eval_samples_per_second": 481.314, | |
| "eval_steps_per_second": 30.084, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_loss": 2.622326135635376, | |
| "eval_runtime": 417.8553, | |
| "eval_samples_per_second": 476.84, | |
| "eval_steps_per_second": 29.805, | |
| "step": 1544000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 1.4486666666666665e-07, | |
| "loss": 2.7994, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 2.6357638835906982, | |
| "eval_runtime": 417.2592, | |
| "eval_samples_per_second": 477.521, | |
| "eval_steps_per_second": 29.847, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "eval_loss": 2.629568576812744, | |
| "eval_runtime": 416.6599, | |
| "eval_samples_per_second": 478.208, | |
| "eval_steps_per_second": 29.89, | |
| "step": 1560000 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 1.4213333333333334e-07, | |
| "loss": 2.7966, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "eval_loss": 2.636014938354492, | |
| "eval_runtime": 416.2491, | |
| "eval_samples_per_second": 478.68, | |
| "eval_steps_per_second": 29.92, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "eval_loss": 2.6326565742492676, | |
| "eval_runtime": 414.8509, | |
| "eval_samples_per_second": 480.293, | |
| "eval_steps_per_second": 30.02, | |
| "step": 1576000 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 1.3940000000000002e-07, | |
| "loss": 2.7883, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "eval_loss": 2.6365151405334473, | |
| "eval_runtime": 416.5987, | |
| "eval_samples_per_second": 478.278, | |
| "eval_steps_per_second": 29.894, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "eval_loss": 2.6257715225219727, | |
| "eval_runtime": 417.307, | |
| "eval_samples_per_second": 477.466, | |
| "eval_steps_per_second": 29.844, | |
| "step": 1592000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1.3666666666666665e-07, | |
| "loss": 2.7963, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "eval_loss": 2.6400821208953857, | |
| "eval_runtime": 416.6899, | |
| "eval_samples_per_second": 478.173, | |
| "eval_steps_per_second": 29.888, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_loss": 2.6317903995513916, | |
| "eval_runtime": 424.5231, | |
| "eval_samples_per_second": 469.35, | |
| "eval_steps_per_second": 29.336, | |
| "step": 1608000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 1.3393333333333333e-07, | |
| "loss": 2.7923, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "eval_loss": 2.633047103881836, | |
| "eval_runtime": 425.6323, | |
| "eval_samples_per_second": 468.127, | |
| "eval_steps_per_second": 29.26, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_loss": 2.637237071990967, | |
| "eval_runtime": 424.7976, | |
| "eval_samples_per_second": 469.047, | |
| "eval_steps_per_second": 29.317, | |
| "step": 1624000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 1.312e-07, | |
| "loss": 2.789, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_loss": 2.636323928833008, | |
| "eval_runtime": 425.1309, | |
| "eval_samples_per_second": 468.679, | |
| "eval_steps_per_second": 29.295, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "eval_loss": 2.6345624923706055, | |
| "eval_runtime": 421.3336, | |
| "eval_samples_per_second": 472.903, | |
| "eval_steps_per_second": 29.559, | |
| "step": 1640000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 1.2846666666666667e-07, | |
| "loss": 2.7883, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_loss": 2.629164934158325, | |
| "eval_runtime": 419.6709, | |
| "eval_samples_per_second": 474.777, | |
| "eval_steps_per_second": 29.676, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.6284499168395996, | |
| "eval_runtime": 421.1638, | |
| "eval_samples_per_second": 473.094, | |
| "eval_steps_per_second": 29.57, | |
| "step": 1656000 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 1.2573333333333332e-07, | |
| "loss": 2.7965, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "eval_loss": 2.6407673358917236, | |
| "eval_runtime": 421.0368, | |
| "eval_samples_per_second": 473.237, | |
| "eval_steps_per_second": 29.579, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 2.629608154296875, | |
| "eval_runtime": 418.0892, | |
| "eval_samples_per_second": 476.573, | |
| "eval_steps_per_second": 29.788, | |
| "step": 1672000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.23e-07, | |
| "loss": 2.7963, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_loss": 2.633134603500366, | |
| "eval_runtime": 417.1134, | |
| "eval_samples_per_second": 477.688, | |
| "eval_steps_per_second": 29.858, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "eval_loss": 2.633925437927246, | |
| "eval_runtime": 416.8801, | |
| "eval_samples_per_second": 477.955, | |
| "eval_steps_per_second": 29.874, | |
| "step": 1688000 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 1.2026666666666666e-07, | |
| "loss": 2.7911, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "eval_loss": 2.6206448078155518, | |
| "eval_runtime": 416.5239, | |
| "eval_samples_per_second": 478.364, | |
| "eval_steps_per_second": 29.9, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "eval_loss": 2.626826047897339, | |
| "eval_runtime": 423.5563, | |
| "eval_samples_per_second": 470.422, | |
| "eval_steps_per_second": 29.403, | |
| "step": 1704000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 1.1753333333333334e-07, | |
| "loss": 2.794, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "eval_loss": 2.6277658939361572, | |
| "eval_runtime": 424.0426, | |
| "eval_samples_per_second": 469.882, | |
| "eval_steps_per_second": 29.37, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "eval_loss": 2.624177932739258, | |
| "eval_runtime": 424.5606, | |
| "eval_samples_per_second": 469.309, | |
| "eval_steps_per_second": 29.334, | |
| "step": 1720000 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1.1480000000000001e-07, | |
| "loss": 2.7893, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "eval_loss": 2.6329119205474854, | |
| "eval_runtime": 423.4044, | |
| "eval_samples_per_second": 470.59, | |
| "eval_steps_per_second": 29.414, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 2.634227991104126, | |
| "eval_runtime": 416.548, | |
| "eval_samples_per_second": 478.336, | |
| "eval_steps_per_second": 29.898, | |
| "step": 1736000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 1.1206666666666666e-07, | |
| "loss": 2.7935, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "eval_loss": 2.632899284362793, | |
| "eval_runtime": 416.0609, | |
| "eval_samples_per_second": 478.896, | |
| "eval_steps_per_second": 29.933, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "eval_loss": 2.6293511390686035, | |
| "eval_runtime": 417.5782, | |
| "eval_samples_per_second": 477.156, | |
| "eval_steps_per_second": 29.824, | |
| "step": 1752000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.0933333333333333e-07, | |
| "loss": 2.7936, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "eval_loss": 2.6300759315490723, | |
| "eval_runtime": 417.5993, | |
| "eval_samples_per_second": 477.132, | |
| "eval_steps_per_second": 29.823, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "eval_loss": 2.629504442214966, | |
| "eval_runtime": 417.0022, | |
| "eval_samples_per_second": 477.815, | |
| "eval_steps_per_second": 29.866, | |
| "step": 1768000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 1.066e-07, | |
| "loss": 2.7922, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_loss": 2.6260571479797363, | |
| "eval_runtime": 415.7532, | |
| "eval_samples_per_second": 479.251, | |
| "eval_steps_per_second": 29.955, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "eval_loss": 2.6370482444763184, | |
| "eval_runtime": 417.3737, | |
| "eval_samples_per_second": 477.39, | |
| "eval_steps_per_second": 29.839, | |
| "step": 1784000 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1.0386666666666667e-07, | |
| "loss": 2.7911, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "eval_loss": 2.636384963989258, | |
| "eval_runtime": 417.7415, | |
| "eval_samples_per_second": 476.97, | |
| "eval_steps_per_second": 29.813, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_loss": 2.623237371444702, | |
| "eval_runtime": 418.4252, | |
| "eval_samples_per_second": 476.19, | |
| "eval_steps_per_second": 29.764, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 1.0113333333333334e-07, | |
| "loss": 2.795, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "eval_loss": 2.6200833320617676, | |
| "eval_runtime": 419.0681, | |
| "eval_samples_per_second": 475.46, | |
| "eval_steps_per_second": 29.718, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "eval_loss": 2.6329450607299805, | |
| "eval_runtime": 420.2799, | |
| "eval_samples_per_second": 474.089, | |
| "eval_steps_per_second": 29.633, | |
| "step": 1816000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 9.84e-08, | |
| "loss": 2.7898, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_loss": 2.6248958110809326, | |
| "eval_runtime": 419.6056, | |
| "eval_samples_per_second": 474.851, | |
| "eval_steps_per_second": 29.68, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "eval_loss": 2.6249101161956787, | |
| "eval_runtime": 420.4509, | |
| "eval_samples_per_second": 473.896, | |
| "eval_steps_per_second": 29.621, | |
| "step": 1832000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 9.566666666666666e-08, | |
| "loss": 2.7931, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_loss": 2.636091947555542, | |
| "eval_runtime": 419.4224, | |
| "eval_samples_per_second": 475.058, | |
| "eval_steps_per_second": 29.693, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_loss": NaN, | |
| "eval_runtime": 419.9847, | |
| "eval_samples_per_second": 474.422, | |
| "eval_steps_per_second": 29.653, | |
| "step": 1848000 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 9.293333333333333e-08, | |
| "loss": 2.7919, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "eval_loss": 2.627026319503784, | |
| "eval_runtime": 421.2325, | |
| "eval_samples_per_second": 473.017, | |
| "eval_steps_per_second": 29.566, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "eval_loss": 2.636218309402466, | |
| "eval_runtime": 416.4114, | |
| "eval_samples_per_second": 478.493, | |
| "eval_steps_per_second": 29.908, | |
| "step": 1864000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 9.02e-08, | |
| "loss": 2.7833, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "eval_loss": 2.6277663707733154, | |
| "eval_runtime": 417.346, | |
| "eval_samples_per_second": 477.422, | |
| "eval_steps_per_second": 29.841, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_loss": 2.623185634613037, | |
| "eval_runtime": 417.1182, | |
| "eval_samples_per_second": 477.682, | |
| "eval_steps_per_second": 29.857, | |
| "step": 1880000 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 8.746666666666667e-08, | |
| "loss": 2.8067, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "eval_loss": 2.626035451889038, | |
| "eval_runtime": 417.7897, | |
| "eval_samples_per_second": 476.915, | |
| "eval_steps_per_second": 29.809, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "eval_loss": 2.626246929168701, | |
| "eval_runtime": 419.7511, | |
| "eval_samples_per_second": 474.686, | |
| "eval_steps_per_second": 29.67, | |
| "step": 1896000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 8.473333333333334e-08, | |
| "loss": 2.7953, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_loss": 2.6271278858184814, | |
| "eval_runtime": 416.9341, | |
| "eval_samples_per_second": 477.893, | |
| "eval_steps_per_second": 29.87, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "eval_loss": 2.6269619464874268, | |
| "eval_runtime": 417.5655, | |
| "eval_samples_per_second": 477.171, | |
| "eval_steps_per_second": 29.825, | |
| "step": 1912000 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 8.2e-08, | |
| "loss": 2.7953, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "eval_loss": 2.6304750442504883, | |
| "eval_runtime": 418.9519, | |
| "eval_samples_per_second": 475.592, | |
| "eval_steps_per_second": 29.727, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "eval_loss": 2.62542724609375, | |
| "eval_runtime": 417.0471, | |
| "eval_samples_per_second": 477.764, | |
| "eval_steps_per_second": 29.862, | |
| "step": 1928000 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 7.926666666666666e-08, | |
| "loss": 2.7881, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "eval_loss": 2.6296772956848145, | |
| "eval_runtime": 416.8665, | |
| "eval_samples_per_second": 477.971, | |
| "eval_steps_per_second": 29.875, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_loss": 2.6271204948425293, | |
| "eval_runtime": 416.2392, | |
| "eval_samples_per_second": 478.691, | |
| "eval_steps_per_second": 29.92, | |
| "step": 1944000 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 7.653333333333333e-08, | |
| "loss": 2.7928, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "eval_loss": 2.6253867149353027, | |
| "eval_runtime": 417.7441, | |
| "eval_samples_per_second": 476.967, | |
| "eval_steps_per_second": 29.813, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "eval_loss": 2.6286251544952393, | |
| "eval_runtime": 418.17, | |
| "eval_samples_per_second": 476.481, | |
| "eval_steps_per_second": 29.782, | |
| "step": 1960000 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 7.38e-08, | |
| "loss": 2.8003, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_loss": 2.632986307144165, | |
| "eval_runtime": 416.6612, | |
| "eval_samples_per_second": 478.206, | |
| "eval_steps_per_second": 29.89, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "eval_loss": 2.6285812854766846, | |
| "eval_runtime": 416.6788, | |
| "eval_samples_per_second": 478.186, | |
| "eval_steps_per_second": 29.889, | |
| "step": 1976000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 7.106666666666667e-08, | |
| "loss": 2.7935, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "eval_loss": 2.640784502029419, | |
| "eval_runtime": 417.7728, | |
| "eval_samples_per_second": 476.934, | |
| "eval_steps_per_second": 29.81, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "eval_loss": 2.627523422241211, | |
| "eval_runtime": 419.2453, | |
| "eval_samples_per_second": 475.259, | |
| "eval_steps_per_second": 29.706, | |
| "step": 1992000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 6.833333333333332e-08, | |
| "loss": 2.7925, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "eval_loss": 2.625904083251953, | |
| "eval_runtime": 418.4291, | |
| "eval_samples_per_second": 476.186, | |
| "eval_steps_per_second": 29.764, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "eval_loss": 2.6302177906036377, | |
| "eval_runtime": 418.3648, | |
| "eval_samples_per_second": 476.259, | |
| "eval_steps_per_second": 29.768, | |
| "step": 2008000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 6.56e-08, | |
| "loss": 2.7924, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "eval_loss": 2.6320409774780273, | |
| "eval_runtime": 420.0509, | |
| "eval_samples_per_second": 474.347, | |
| "eval_steps_per_second": 29.649, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "eval_loss": 2.629477024078369, | |
| "eval_runtime": 418.2782, | |
| "eval_samples_per_second": 476.358, | |
| "eval_steps_per_second": 29.774, | |
| "step": 2024000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 6.286666666666666e-08, | |
| "loss": 2.799, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "eval_loss": 2.6258628368377686, | |
| "eval_runtime": 417.2044, | |
| "eval_samples_per_second": 477.584, | |
| "eval_steps_per_second": 29.851, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "eval_loss": 2.6245615482330322, | |
| "eval_runtime": 418.8359, | |
| "eval_samples_per_second": 475.723, | |
| "eval_steps_per_second": 29.735, | |
| "step": 2040000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 6.013333333333333e-08, | |
| "loss": 2.7983, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "eval_loss": 2.629530429840088, | |
| "eval_runtime": 418.9926, | |
| "eval_samples_per_second": 475.545, | |
| "eval_steps_per_second": 29.724, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_loss": 2.619439125061035, | |
| "eval_runtime": 421.9976, | |
| "eval_samples_per_second": 472.159, | |
| "eval_steps_per_second": 29.512, | |
| "step": 2056000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 5.7400000000000004e-08, | |
| "loss": 2.7901, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "eval_loss": 2.6258339881896973, | |
| "eval_runtime": 420.472, | |
| "eval_samples_per_second": 473.872, | |
| "eval_steps_per_second": 29.619, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_loss": 2.633378267288208, | |
| "eval_runtime": 421.3576, | |
| "eval_samples_per_second": 472.876, | |
| "eval_steps_per_second": 29.557, | |
| "step": 2072000 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 5.4666666666666666e-08, | |
| "loss": 2.7956, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "eval_loss": 2.6361238956451416, | |
| "eval_runtime": 421.9485, | |
| "eval_samples_per_second": 472.214, | |
| "eval_steps_per_second": 29.515, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "eval_loss": 2.617746591567993, | |
| "eval_runtime": 418.7323, | |
| "eval_samples_per_second": 475.841, | |
| "eval_steps_per_second": 29.742, | |
| "step": 2088000 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 5.1933333333333335e-08, | |
| "loss": 2.8008, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_loss": 2.632232189178467, | |
| "eval_runtime": 418.7251, | |
| "eval_samples_per_second": 475.849, | |
| "eval_steps_per_second": 29.743, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_loss": 2.6280999183654785, | |
| "eval_runtime": 417.4346, | |
| "eval_samples_per_second": 477.32, | |
| "eval_steps_per_second": 29.835, | |
| "step": 2104000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 4.92e-08, | |
| "loss": 2.791, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "eval_loss": 2.624938726425171, | |
| "eval_runtime": 418.5637, | |
| "eval_samples_per_second": 476.033, | |
| "eval_steps_per_second": 29.754, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_loss": 2.628361225128174, | |
| "eval_runtime": 419.8496, | |
| "eval_samples_per_second": 474.575, | |
| "eval_steps_per_second": 29.663, | |
| "step": 2120000 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 4.6466666666666666e-08, | |
| "loss": 2.7933, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_loss": 2.6270060539245605, | |
| "eval_runtime": 419.4985, | |
| "eval_samples_per_second": 474.972, | |
| "eval_steps_per_second": 29.688, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 2.624077081680298, | |
| "eval_runtime": 422.5644, | |
| "eval_samples_per_second": 471.526, | |
| "eval_steps_per_second": 29.472, | |
| "step": 2136000 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 4.3733333333333335e-08, | |
| "loss": 2.7825, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "eval_loss": 2.6254072189331055, | |
| "eval_runtime": 421.1669, | |
| "eval_samples_per_second": 473.09, | |
| "eval_steps_per_second": 29.57, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_loss": 2.6282851696014404, | |
| "eval_runtime": 427.7816, | |
| "eval_samples_per_second": 465.775, | |
| "eval_steps_per_second": 29.113, | |
| "step": 2152000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 4.1e-08, | |
| "loss": 2.7854, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "eval_loss": 2.634307622909546, | |
| "eval_runtime": 424.5298, | |
| "eval_samples_per_second": 469.343, | |
| "eval_steps_per_second": 29.336, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "eval_loss": 2.6208443641662598, | |
| "eval_runtime": 422.4964, | |
| "eval_samples_per_second": 471.602, | |
| "eval_steps_per_second": 29.477, | |
| "step": 2168000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 3.8266666666666665e-08, | |
| "loss": 2.7949, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_loss": 2.62925386428833, | |
| "eval_runtime": 420.757, | |
| "eval_samples_per_second": 473.551, | |
| "eval_steps_per_second": 29.599, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "eval_loss": 2.6265780925750732, | |
| "eval_runtime": 420.6962, | |
| "eval_samples_per_second": 473.62, | |
| "eval_steps_per_second": 29.603, | |
| "step": 2184000 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 3.5533333333333334e-08, | |
| "loss": 2.7938, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "eval_loss": 2.6270058155059814, | |
| "eval_runtime": 420.3162, | |
| "eval_samples_per_second": 474.048, | |
| "eval_steps_per_second": 29.63, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_loss": 2.6237611770629883, | |
| "eval_runtime": 418.1737, | |
| "eval_samples_per_second": 476.477, | |
| "eval_steps_per_second": 29.782, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 3.28e-08, | |
| "loss": 2.7905, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "eval_loss": 2.628171920776367, | |
| "eval_runtime": 420.3324, | |
| "eval_samples_per_second": 474.03, | |
| "eval_steps_per_second": 29.629, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "eval_loss": 2.6245853900909424, | |
| "eval_runtime": 421.5905, | |
| "eval_samples_per_second": 472.615, | |
| "eval_steps_per_second": 29.541, | |
| "step": 2216000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.0066666666666665e-08, | |
| "loss": 2.8004, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "eval_loss": 2.6274161338806152, | |
| "eval_runtime": 419.7336, | |
| "eval_samples_per_second": 474.706, | |
| "eval_steps_per_second": 29.671, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "eval_loss": 2.6251978874206543, | |
| "eval_runtime": 418.2128, | |
| "eval_samples_per_second": 476.432, | |
| "eval_steps_per_second": 29.779, | |
| "step": 2232000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.7333333333333333e-08, | |
| "loss": 2.7921, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "eval_loss": 2.6343250274658203, | |
| "eval_runtime": 419.0507, | |
| "eval_samples_per_second": 475.479, | |
| "eval_steps_per_second": 29.72, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "eval_loss": 2.632768154144287, | |
| "eval_runtime": 424.1088, | |
| "eval_samples_per_second": 469.809, | |
| "eval_steps_per_second": 29.365, | |
| "step": 2248000 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 2.46e-08, | |
| "loss": 2.7964, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_loss": 2.6206092834472656, | |
| "eval_runtime": 423.0049, | |
| "eval_samples_per_second": 471.035, | |
| "eval_steps_per_second": 29.442, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 2.6235222816467285, | |
| "eval_runtime": 421.2675, | |
| "eval_samples_per_second": 472.977, | |
| "eval_steps_per_second": 29.563, | |
| "step": 2264000 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 2.1866666666666667e-08, | |
| "loss": 2.7954, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_loss": 2.6287684440612793, | |
| "eval_runtime": 421.0647, | |
| "eval_samples_per_second": 473.205, | |
| "eval_steps_per_second": 29.577, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "eval_loss": 2.6203510761260986, | |
| "eval_runtime": 420.6158, | |
| "eval_samples_per_second": 473.71, | |
| "eval_steps_per_second": 29.609, | |
| "step": 2280000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 1.9133333333333333e-08, | |
| "loss": 2.7902, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 2.6231720447540283, | |
| "eval_runtime": 419.7124, | |
| "eval_samples_per_second": 474.73, | |
| "eval_steps_per_second": 29.673, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "eval_loss": 2.6238837242126465, | |
| "eval_runtime": 419.2797, | |
| "eval_samples_per_second": 475.22, | |
| "eval_steps_per_second": 29.703, | |
| "step": 2296000 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 1.64e-08, | |
| "loss": 2.8046, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "eval_loss": 2.6240670680999756, | |
| "eval_runtime": 419.389, | |
| "eval_samples_per_second": 475.096, | |
| "eval_steps_per_second": 29.696, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "eval_loss": 2.6258645057678223, | |
| "eval_runtime": 420.6507, | |
| "eval_samples_per_second": 473.671, | |
| "eval_steps_per_second": 29.607, | |
| "step": 2312000 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 1.3666666666666667e-08, | |
| "loss": 2.793, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "eval_loss": 2.6274592876434326, | |
| "eval_runtime": 419.5581, | |
| "eval_samples_per_second": 474.904, | |
| "eval_steps_per_second": 29.684, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_loss": 2.6264114379882812, | |
| "eval_runtime": 418.2082, | |
| "eval_samples_per_second": 476.437, | |
| "eval_steps_per_second": 29.779, | |
| "step": 2328000 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 1.0933333333333334e-08, | |
| "loss": 2.7893, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "eval_loss": 2.633244037628174, | |
| "eval_runtime": 419.1985, | |
| "eval_samples_per_second": 475.312, | |
| "eval_steps_per_second": 29.709, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_loss": 2.621447801589966, | |
| "eval_runtime": 423.5885, | |
| "eval_samples_per_second": 470.386, | |
| "eval_steps_per_second": 29.401, | |
| "step": 2344000 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 8.2e-09, | |
| "loss": 2.7898, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_loss": 2.631804943084717, | |
| "eval_runtime": 424.5578, | |
| "eval_samples_per_second": 469.312, | |
| "eval_steps_per_second": 29.334, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_loss": 2.623945474624634, | |
| "eval_runtime": 421.6182, | |
| "eval_samples_per_second": 472.584, | |
| "eval_steps_per_second": 29.539, | |
| "step": 2360000 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 5.466666666666667e-09, | |
| "loss": 2.7906, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "eval_loss": 2.6214942932128906, | |
| "eval_runtime": 421.2919, | |
| "eval_samples_per_second": 472.95, | |
| "eval_steps_per_second": 29.561, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "eval_loss": 2.633603096008301, | |
| "eval_runtime": 422.9875, | |
| "eval_samples_per_second": 471.054, | |
| "eval_steps_per_second": 29.443, | |
| "step": 2376000 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 2.7333333333333334e-09, | |
| "loss": 2.7942, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "eval_loss": 2.6217610836029053, | |
| "eval_runtime": 422.4965, | |
| "eval_samples_per_second": 471.602, | |
| "eval_steps_per_second": 29.477, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "eval_loss": 2.6299171447753906, | |
| "eval_runtime": 419.6936, | |
| "eval_samples_per_second": 474.751, | |
| "eval_steps_per_second": 29.674, | |
| "step": 2392000 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 0.0, | |
| "loss": 2.7997, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "eval_loss": 2.6303224563598633, | |
| "eval_runtime": 419.2829, | |
| "eval_samples_per_second": 475.216, | |
| "eval_steps_per_second": 29.703, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "step": 2400000, | |
| "total_flos": 7.667884600087345e+17, | |
| "train_loss": 2.8006172998046877, | |
| "train_runtime": 396247.3581, | |
| "train_samples_per_second": 96.909, | |
| "train_steps_per_second": 6.057 | |
| } | |
| ], | |
| "logging_steps": 16000, | |
| "max_steps": 2400000, | |
| "num_train_epochs": 11, | |
| "save_steps": 32000, | |
| "total_flos": 7.667884600087345e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |