| { | |
| "best_metric": 1.8842545747756958, | |
| "best_model_checkpoint": "./model_tweets_2020_Q1_90/checkpoint-1440000", | |
| "epoch": 49.171259398881354, | |
| "eval_steps": 8000, | |
| "global_step": 2400000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 2.2375540733337402, | |
| "eval_runtime": 45.4292, | |
| "eval_samples_per_second": 904.749, | |
| "eval_steps_per_second": 56.55, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.0726666666666665e-07, | |
| "loss": 2.4394, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 2.155681610107422, | |
| "eval_runtime": 44.9417, | |
| "eval_samples_per_second": 914.562, | |
| "eval_steps_per_second": 57.163, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 2.0965232849121094, | |
| "eval_runtime": 45.1589, | |
| "eval_samples_per_second": 910.165, | |
| "eval_steps_per_second": 56.888, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.0453333333333336e-07, | |
| "loss": 2.2403, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.063685894012451, | |
| "eval_runtime": 45.4617, | |
| "eval_samples_per_second": 904.101, | |
| "eval_steps_per_second": 56.509, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 2.062025308609009, | |
| "eval_runtime": 46.1664, | |
| "eval_samples_per_second": 890.301, | |
| "eval_steps_per_second": 55.647, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.018e-07, | |
| "loss": 2.1859, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 2.0426833629608154, | |
| "eval_runtime": 44.881, | |
| "eval_samples_per_second": 915.8, | |
| "eval_steps_per_second": 57.24, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.044032335281372, | |
| "eval_runtime": 45.0876, | |
| "eval_samples_per_second": 911.602, | |
| "eval_steps_per_second": 56.978, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.9906666666666667e-07, | |
| "loss": 2.1472, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 2.017690420150757, | |
| "eval_runtime": 45.0, | |
| "eval_samples_per_second": 913.377, | |
| "eval_steps_per_second": 57.089, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.9980425834655762, | |
| "eval_runtime": 44.953, | |
| "eval_samples_per_second": 914.333, | |
| "eval_steps_per_second": 57.149, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3.963333333333333e-07, | |
| "loss": 2.1334, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 2.0021114349365234, | |
| "eval_runtime": 45.3203, | |
| "eval_samples_per_second": 906.923, | |
| "eval_steps_per_second": 56.685, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 1.9963111877441406, | |
| "eval_runtime": 44.8632, | |
| "eval_samples_per_second": 916.163, | |
| "eval_steps_per_second": 57.263, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.936e-07, | |
| "loss": 2.1271, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 1.9917570352554321, | |
| "eval_runtime": 45.4669, | |
| "eval_samples_per_second": 903.999, | |
| "eval_steps_per_second": 56.503, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.988930344581604, | |
| "eval_runtime": 45.0716, | |
| "eval_samples_per_second": 911.927, | |
| "eval_steps_per_second": 56.998, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.908666666666667e-07, | |
| "loss": 2.1065, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 1.9688993692398071, | |
| "eval_runtime": 44.5304, | |
| "eval_samples_per_second": 923.009, | |
| "eval_steps_per_second": 57.691, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 1.991935133934021, | |
| "eval_runtime": 45.9679, | |
| "eval_samples_per_second": 894.146, | |
| "eval_steps_per_second": 55.887, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.8813333333333334e-07, | |
| "loss": 2.105, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 1.9705941677093506, | |
| "eval_runtime": 45.4865, | |
| "eval_samples_per_second": 903.609, | |
| "eval_steps_per_second": 56.478, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.9724736213684082, | |
| "eval_runtime": 44.9361, | |
| "eval_samples_per_second": 914.676, | |
| "eval_steps_per_second": 57.17, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.854e-07, | |
| "loss": 2.1033, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 2.000924825668335, | |
| "eval_runtime": 45.1849, | |
| "eval_samples_per_second": 909.641, | |
| "eval_steps_per_second": 56.855, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 1.9660991430282593, | |
| "eval_runtime": 45.122, | |
| "eval_samples_per_second": 910.909, | |
| "eval_steps_per_second": 56.935, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.8266666666666665e-07, | |
| "loss": 2.0934, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 1.964065432548523, | |
| "eval_runtime": 45.5781, | |
| "eval_samples_per_second": 901.792, | |
| "eval_steps_per_second": 56.365, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 1.973306655883789, | |
| "eval_runtime": 45.0146, | |
| "eval_samples_per_second": 913.081, | |
| "eval_steps_per_second": 57.07, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.799333333333333e-07, | |
| "loss": 2.0899, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 1.9746649265289307, | |
| "eval_runtime": 45.1942, | |
| "eval_samples_per_second": 909.454, | |
| "eval_steps_per_second": 56.844, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 1.9442167282104492, | |
| "eval_runtime": 44.9807, | |
| "eval_samples_per_second": 913.769, | |
| "eval_steps_per_second": 57.113, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.772e-07, | |
| "loss": 2.0903, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_loss": 1.9585589170455933, | |
| "eval_runtime": 45.3512, | |
| "eval_samples_per_second": 906.304, | |
| "eval_steps_per_second": 56.647, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "eval_loss": 1.9585614204406738, | |
| "eval_runtime": 44.9754, | |
| "eval_samples_per_second": 913.877, | |
| "eval_steps_per_second": 57.12, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 3.7446666666666667e-07, | |
| "loss": 2.0842, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_loss": 1.9401671886444092, | |
| "eval_runtime": 45.4042, | |
| "eval_samples_per_second": 905.247, | |
| "eval_steps_per_second": 56.581, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 1.9483397006988525, | |
| "eval_runtime": 45.1835, | |
| "eval_samples_per_second": 909.668, | |
| "eval_steps_per_second": 56.857, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 3.7173333333333333e-07, | |
| "loss": 2.0761, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "eval_loss": 1.9532350301742554, | |
| "eval_runtime": 45.6838, | |
| "eval_samples_per_second": 899.706, | |
| "eval_steps_per_second": 56.234, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 1.945618748664856, | |
| "eval_runtime": 44.9815, | |
| "eval_samples_per_second": 913.754, | |
| "eval_steps_per_second": 57.112, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.69e-07, | |
| "loss": 2.0799, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 1.9322354793548584, | |
| "eval_runtime": 45.7219, | |
| "eval_samples_per_second": 898.957, | |
| "eval_steps_per_second": 56.188, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "eval_loss": 1.9460111856460571, | |
| "eval_runtime": 44.9207, | |
| "eval_samples_per_second": 914.991, | |
| "eval_steps_per_second": 57.19, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 3.6626666666666664e-07, | |
| "loss": 2.0704, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "eval_loss": 1.9477649927139282, | |
| "eval_runtime": 45.4934, | |
| "eval_samples_per_second": 903.472, | |
| "eval_steps_per_second": 56.47, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 1.943530559539795, | |
| "eval_runtime": 45.5332, | |
| "eval_samples_per_second": 902.683, | |
| "eval_steps_per_second": 56.42, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 3.6353333333333335e-07, | |
| "loss": 2.0727, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_loss": 1.9356465339660645, | |
| "eval_runtime": 45.2443, | |
| "eval_samples_per_second": 908.445, | |
| "eval_steps_per_second": 56.781, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "eval_loss": 1.9543371200561523, | |
| "eval_runtime": 44.9666, | |
| "eval_samples_per_second": 914.056, | |
| "eval_steps_per_second": 57.131, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 3.608e-07, | |
| "loss": 2.073, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "eval_loss": 1.9541795253753662, | |
| "eval_runtime": 45.5545, | |
| "eval_samples_per_second": 902.26, | |
| "eval_steps_per_second": 56.394, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 1.9503259658813477, | |
| "eval_runtime": 45.0063, | |
| "eval_samples_per_second": 913.25, | |
| "eval_steps_per_second": 57.081, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 3.5806666666666666e-07, | |
| "loss": 2.0647, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "eval_loss": 1.9437284469604492, | |
| "eval_runtime": 45.0801, | |
| "eval_samples_per_second": 911.755, | |
| "eval_steps_per_second": 56.987, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_loss": 1.9450260400772095, | |
| "eval_runtime": 45.0125, | |
| "eval_samples_per_second": 913.125, | |
| "eval_steps_per_second": 57.073, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 3.553333333333333e-07, | |
| "loss": 2.0668, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 1.9220808744430542, | |
| "eval_runtime": 45.7281, | |
| "eval_samples_per_second": 898.834, | |
| "eval_steps_per_second": 56.18, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "eval_loss": 1.927699089050293, | |
| "eval_runtime": 45.3402, | |
| "eval_samples_per_second": 906.525, | |
| "eval_steps_per_second": 56.661, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 3.5259999999999997e-07, | |
| "loss": 2.0695, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "eval_loss": 1.935697317123413, | |
| "eval_runtime": 45.1353, | |
| "eval_samples_per_second": 910.64, | |
| "eval_steps_per_second": 56.918, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "eval_loss": 1.924439549446106, | |
| "eval_runtime": 45.0671, | |
| "eval_samples_per_second": 912.017, | |
| "eval_steps_per_second": 57.004, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 3.498666666666667e-07, | |
| "loss": 2.0652, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_loss": 1.938655138015747, | |
| "eval_runtime": 45.305, | |
| "eval_samples_per_second": 907.228, | |
| "eval_steps_per_second": 56.704, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "eval_loss": 1.9354636669158936, | |
| "eval_runtime": 45.6689, | |
| "eval_samples_per_second": 900.0, | |
| "eval_steps_per_second": 56.253, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 3.4713333333333333e-07, | |
| "loss": 2.0607, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "eval_loss": 1.9389930963516235, | |
| "eval_runtime": 45.2501, | |
| "eval_samples_per_second": 908.33, | |
| "eval_steps_per_second": 56.773, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "eval_loss": 1.9358594417572021, | |
| "eval_runtime": 45.5644, | |
| "eval_samples_per_second": 902.064, | |
| "eval_steps_per_second": 56.382, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 3.444e-07, | |
| "loss": 2.0707, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "eval_loss": 1.9393250942230225, | |
| "eval_runtime": 45.0739, | |
| "eval_samples_per_second": 911.881, | |
| "eval_steps_per_second": 56.995, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "eval_loss": 1.9217476844787598, | |
| "eval_runtime": 45.0711, | |
| "eval_samples_per_second": 911.938, | |
| "eval_steps_per_second": 56.999, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 3.416666666666667e-07, | |
| "loss": 2.0621, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "eval_loss": 1.9284311532974243, | |
| "eval_runtime": 45.6293, | |
| "eval_samples_per_second": 900.781, | |
| "eval_steps_per_second": 56.302, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "eval_loss": 1.9383472204208374, | |
| "eval_runtime": 46.4801, | |
| "eval_samples_per_second": 884.292, | |
| "eval_steps_per_second": 55.271, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 3.3893333333333335e-07, | |
| "loss": 2.0643, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "eval_loss": 1.922420859336853, | |
| "eval_runtime": 45.4784, | |
| "eval_samples_per_second": 903.77, | |
| "eval_steps_per_second": 56.488, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_loss": 1.928429365158081, | |
| "eval_runtime": 45.9472, | |
| "eval_samples_per_second": 894.549, | |
| "eval_steps_per_second": 55.912, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 3.3619999999999995e-07, | |
| "loss": 2.0498, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "eval_loss": 1.9399133920669556, | |
| "eval_runtime": 46.3003, | |
| "eval_samples_per_second": 887.726, | |
| "eval_steps_per_second": 55.486, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "eval_loss": 1.9427006244659424, | |
| "eval_runtime": 46.6439, | |
| "eval_samples_per_second": 881.187, | |
| "eval_steps_per_second": 55.077, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 3.3346666666666666e-07, | |
| "loss": 2.0689, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "eval_loss": 1.9351186752319336, | |
| "eval_runtime": 45.2002, | |
| "eval_samples_per_second": 909.333, | |
| "eval_steps_per_second": 56.836, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "eval_loss": 1.9312766790390015, | |
| "eval_runtime": 47.0788, | |
| "eval_samples_per_second": 873.047, | |
| "eval_steps_per_second": 54.568, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 3.307333333333333e-07, | |
| "loss": 2.0511, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "eval_loss": 1.9392344951629639, | |
| "eval_runtime": 47.5719, | |
| "eval_samples_per_second": 863.997, | |
| "eval_steps_per_second": 54.002, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 1.9278026819229126, | |
| "eval_runtime": 48.6246, | |
| "eval_samples_per_second": 845.292, | |
| "eval_steps_per_second": 52.833, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 3.28e-07, | |
| "loss": 2.0664, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "eval_loss": 1.9384809732437134, | |
| "eval_runtime": 48.0322, | |
| "eval_samples_per_second": 855.717, | |
| "eval_steps_per_second": 53.485, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.9471704959869385, | |
| "eval_runtime": 46.9, | |
| "eval_samples_per_second": 876.375, | |
| "eval_steps_per_second": 54.776, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 3.252666666666667e-07, | |
| "loss": 2.0565, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "eval_loss": 1.937743902206421, | |
| "eval_runtime": 48.1967, | |
| "eval_samples_per_second": 852.796, | |
| "eval_steps_per_second": 53.302, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "eval_loss": 1.9480650424957275, | |
| "eval_runtime": 47.3213, | |
| "eval_samples_per_second": 868.572, | |
| "eval_steps_per_second": 54.288, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 3.2253333333333334e-07, | |
| "loss": 2.0566, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "eval_loss": 1.9453697204589844, | |
| "eval_runtime": 47.4611, | |
| "eval_samples_per_second": 866.014, | |
| "eval_steps_per_second": 54.128, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "eval_loss": 1.9244284629821777, | |
| "eval_runtime": 48.2751, | |
| "eval_samples_per_second": 851.412, | |
| "eval_steps_per_second": 53.216, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 3.198e-07, | |
| "loss": 2.0523, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "eval_loss": 1.935764193534851, | |
| "eval_runtime": 47.3047, | |
| "eval_samples_per_second": 868.877, | |
| "eval_steps_per_second": 54.307, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_loss": 1.9176356792449951, | |
| "eval_runtime": 46.998, | |
| "eval_samples_per_second": 874.549, | |
| "eval_steps_per_second": 54.662, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 3.1706666666666665e-07, | |
| "loss": 2.0554, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "eval_loss": 1.9284305572509766, | |
| "eval_runtime": 47.0847, | |
| "eval_samples_per_second": 872.937, | |
| "eval_steps_per_second": 54.561, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "eval_loss": 1.9287078380584717, | |
| "eval_runtime": 47.0031, | |
| "eval_samples_per_second": 874.453, | |
| "eval_steps_per_second": 54.656, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 3.1433333333333336e-07, | |
| "loss": 2.0485, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "eval_loss": 1.923736810684204, | |
| "eval_runtime": 45.756, | |
| "eval_samples_per_second": 898.286, | |
| "eval_steps_per_second": 56.146, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "eval_loss": 1.920929193496704, | |
| "eval_runtime": 48.761, | |
| "eval_samples_per_second": 842.927, | |
| "eval_steps_per_second": 52.686, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 3.116e-07, | |
| "loss": 2.0485, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "eval_loss": 1.9261997938156128, | |
| "eval_runtime": 47.8227, | |
| "eval_samples_per_second": 859.467, | |
| "eval_steps_per_second": 53.719, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "eval_loss": 1.9207805395126343, | |
| "eval_runtime": 47.2192, | |
| "eval_samples_per_second": 870.452, | |
| "eval_steps_per_second": 54.406, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 3.0886666666666667e-07, | |
| "loss": 2.0542, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "eval_loss": 1.9320107698440552, | |
| "eval_runtime": 47.8604, | |
| "eval_samples_per_second": 858.789, | |
| "eval_steps_per_second": 53.677, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "eval_loss": 1.9076824188232422, | |
| "eval_runtime": 48.2616, | |
| "eval_samples_per_second": 851.651, | |
| "eval_steps_per_second": 53.231, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 3.061333333333333e-07, | |
| "loss": 2.0527, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "eval_loss": 1.9248530864715576, | |
| "eval_runtime": 46.9547, | |
| "eval_samples_per_second": 875.353, | |
| "eval_steps_per_second": 54.712, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "eval_loss": 1.919195532798767, | |
| "eval_runtime": 47.8559, | |
| "eval_samples_per_second": 858.87, | |
| "eval_steps_per_second": 53.682, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 3.034e-07, | |
| "loss": 2.0606, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "eval_loss": 1.9151537418365479, | |
| "eval_runtime": 47.7757, | |
| "eval_samples_per_second": 860.311, | |
| "eval_steps_per_second": 53.772, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "eval_loss": 1.9194060564041138, | |
| "eval_runtime": 46.9693, | |
| "eval_samples_per_second": 875.082, | |
| "eval_steps_per_second": 54.695, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 3.0066666666666663e-07, | |
| "loss": 2.0542, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "eval_loss": 1.919755458831787, | |
| "eval_runtime": 48.4882, | |
| "eval_samples_per_second": 847.671, | |
| "eval_steps_per_second": 52.982, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "eval_loss": 1.9134645462036133, | |
| "eval_runtime": 49.7276, | |
| "eval_samples_per_second": 826.544, | |
| "eval_steps_per_second": 51.662, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 2.9793333333333334e-07, | |
| "loss": 2.0593, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "eval_loss": 1.919248342514038, | |
| "eval_runtime": 46.444, | |
| "eval_samples_per_second": 884.98, | |
| "eval_steps_per_second": 55.314, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_loss": 1.9256792068481445, | |
| "eval_runtime": 46.3375, | |
| "eval_samples_per_second": 887.013, | |
| "eval_steps_per_second": 55.441, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 2.952e-07, | |
| "loss": 2.0467, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "eval_loss": 1.9134962558746338, | |
| "eval_runtime": 48.3494, | |
| "eval_samples_per_second": 850.104, | |
| "eval_steps_per_second": 53.134, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "eval_loss": 1.8994532823562622, | |
| "eval_runtime": 46.5628, | |
| "eval_samples_per_second": 882.721, | |
| "eval_steps_per_second": 55.173, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 2.9246666666666665e-07, | |
| "loss": 2.0535, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "eval_loss": 1.9305521249771118, | |
| "eval_runtime": 46.8843, | |
| "eval_samples_per_second": 876.669, | |
| "eval_steps_per_second": 54.795, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "eval_loss": 1.927839994430542, | |
| "eval_runtime": 48.051, | |
| "eval_samples_per_second": 855.384, | |
| "eval_steps_per_second": 53.464, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 2.897333333333333e-07, | |
| "loss": 2.0559, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "eval_loss": 1.9136629104614258, | |
| "eval_runtime": 47.4852, | |
| "eval_samples_per_second": 865.574, | |
| "eval_steps_per_second": 54.101, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "eval_loss": 1.9164540767669678, | |
| "eval_runtime": 46.9282, | |
| "eval_samples_per_second": 875.849, | |
| "eval_steps_per_second": 54.743, | |
| "step": 712000 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 2.8699999999999996e-07, | |
| "loss": 2.0544, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "eval_loss": 1.921919345855713, | |
| "eval_runtime": 50.0641, | |
| "eval_samples_per_second": 820.987, | |
| "eval_steps_per_second": 51.314, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_loss": 1.9200448989868164, | |
| "eval_runtime": 50.8477, | |
| "eval_samples_per_second": 808.336, | |
| "eval_steps_per_second": 50.523, | |
| "step": 728000 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 2.8426666666666667e-07, | |
| "loss": 2.0493, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "eval_loss": 1.924161434173584, | |
| "eval_runtime": 46.3633, | |
| "eval_samples_per_second": 886.519, | |
| "eval_steps_per_second": 55.41, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "eval_loss": 1.9263921976089478, | |
| "eval_runtime": 48.7265, | |
| "eval_samples_per_second": 843.525, | |
| "eval_steps_per_second": 52.723, | |
| "step": 744000 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 2.815333333333333e-07, | |
| "loss": 2.0538, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "eval_loss": 1.9333122968673706, | |
| "eval_runtime": 48.0632, | |
| "eval_samples_per_second": 855.165, | |
| "eval_steps_per_second": 53.45, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "eval_loss": 1.912643551826477, | |
| "eval_runtime": 46.2548, | |
| "eval_samples_per_second": 888.599, | |
| "eval_steps_per_second": 55.54, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 2.7880000000000003e-07, | |
| "loss": 2.0457, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "eval_loss": 1.9022926092147827, | |
| "eval_runtime": 48.0637, | |
| "eval_samples_per_second": 855.157, | |
| "eval_steps_per_second": 53.45, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "eval_loss": 1.9153952598571777, | |
| "eval_runtime": 47.4167, | |
| "eval_samples_per_second": 866.825, | |
| "eval_steps_per_second": 54.179, | |
| "step": 776000 | |
| }, | |
| { | |
| "epoch": 16.06, | |
| "learning_rate": 2.7606666666666664e-07, | |
| "loss": 2.0436, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 16.06, | |
| "eval_loss": 1.894668698310852, | |
| "eval_runtime": 47.3621, | |
| "eval_samples_per_second": 867.824, | |
| "eval_steps_per_second": 54.242, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "eval_loss": 1.9197973012924194, | |
| "eval_runtime": 48.7318, | |
| "eval_samples_per_second": 843.432, | |
| "eval_steps_per_second": 52.717, | |
| "step": 792000 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 2.733333333333333e-07, | |
| "loss": 2.0527, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "eval_loss": 1.912539005279541, | |
| "eval_runtime": 47.1232, | |
| "eval_samples_per_second": 872.224, | |
| "eval_steps_per_second": 54.517, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 1.9129201173782349, | |
| "eval_runtime": 46.5511, | |
| "eval_samples_per_second": 882.944, | |
| "eval_steps_per_second": 55.187, | |
| "step": 808000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 2.706e-07, | |
| "loss": 2.0484, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "eval_loss": 1.930238127708435, | |
| "eval_runtime": 48.6118, | |
| "eval_samples_per_second": 845.514, | |
| "eval_steps_per_second": 52.847, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 16.88, | |
| "eval_loss": 1.915164589881897, | |
| "eval_runtime": 47.3129, | |
| "eval_samples_per_second": 868.727, | |
| "eval_steps_per_second": 54.298, | |
| "step": 824000 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 2.6786666666666666e-07, | |
| "loss": 2.0535, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "eval_loss": 1.9222667217254639, | |
| "eval_runtime": 48.8011, | |
| "eval_samples_per_second": 842.235, | |
| "eval_steps_per_second": 52.642, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "eval_loss": 1.9195363521575928, | |
| "eval_runtime": 47.9497, | |
| "eval_samples_per_second": 857.19, | |
| "eval_steps_per_second": 53.577, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 2.651333333333333e-07, | |
| "loss": 2.0516, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "eval_loss": 1.9071532487869263, | |
| "eval_runtime": 46.9027, | |
| "eval_samples_per_second": 876.325, | |
| "eval_steps_per_second": 54.773, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "eval_loss": 1.9210063219070435, | |
| "eval_runtime": 48.1848, | |
| "eval_samples_per_second": 853.007, | |
| "eval_steps_per_second": 53.316, | |
| "step": 856000 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 2.624e-07, | |
| "loss": 2.0546, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "eval_loss": 1.9014463424682617, | |
| "eval_runtime": 49.087, | |
| "eval_samples_per_second": 837.329, | |
| "eval_steps_per_second": 52.336, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "eval_loss": 1.9129884243011475, | |
| "eval_runtime": 46.451, | |
| "eval_samples_per_second": 884.847, | |
| "eval_steps_per_second": 55.306, | |
| "step": 872000 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 2.596666666666667e-07, | |
| "loss": 2.0439, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "eval_loss": 1.9064290523529053, | |
| "eval_runtime": 48.2272, | |
| "eval_samples_per_second": 852.258, | |
| "eval_steps_per_second": 53.269, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "eval_loss": 1.9166321754455566, | |
| "eval_runtime": 48.6696, | |
| "eval_samples_per_second": 844.511, | |
| "eval_steps_per_second": 52.785, | |
| "step": 888000 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 2.5693333333333333e-07, | |
| "loss": 2.0391, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "eval_loss": 1.930993676185608, | |
| "eval_runtime": 47.1469, | |
| "eval_samples_per_second": 871.786, | |
| "eval_steps_per_second": 54.489, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "eval_loss": 1.9064345359802246, | |
| "eval_runtime": 45.9523, | |
| "eval_samples_per_second": 894.45, | |
| "eval_steps_per_second": 55.906, | |
| "step": 904000 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 2.542e-07, | |
| "loss": 2.0568, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "eval_loss": 1.9106640815734863, | |
| "eval_runtime": 47.4421, | |
| "eval_samples_per_second": 866.361, | |
| "eval_steps_per_second": 54.15, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "eval_loss": 1.931686520576477, | |
| "eval_runtime": 47.8842, | |
| "eval_samples_per_second": 858.363, | |
| "eval_steps_per_second": 53.65, | |
| "step": 920000 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 2.5146666666666664e-07, | |
| "loss": 2.047, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "eval_loss": 1.9234881401062012, | |
| "eval_runtime": 47.1905, | |
| "eval_samples_per_second": 870.981, | |
| "eval_steps_per_second": 54.439, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 19.18, | |
| "eval_loss": 1.917264699935913, | |
| "eval_runtime": 48.2222, | |
| "eval_samples_per_second": 852.346, | |
| "eval_steps_per_second": 53.274, | |
| "step": 936000 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 2.4873333333333335e-07, | |
| "loss": 2.0431, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "eval_loss": 1.8946489095687866, | |
| "eval_runtime": 48.6788, | |
| "eval_samples_per_second": 844.352, | |
| "eval_steps_per_second": 52.775, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "eval_loss": 1.9247366189956665, | |
| "eval_runtime": 47.3908, | |
| "eval_samples_per_second": 867.3, | |
| "eval_steps_per_second": 54.209, | |
| "step": 952000 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "learning_rate": 2.46e-07, | |
| "loss": 2.0444, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "eval_loss": 1.9105546474456787, | |
| "eval_runtime": 47.3389, | |
| "eval_samples_per_second": 868.249, | |
| "eval_steps_per_second": 54.268, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 19.83, | |
| "eval_loss": 1.9022789001464844, | |
| "eval_runtime": 48.8131, | |
| "eval_samples_per_second": 842.027, | |
| "eval_steps_per_second": 52.629, | |
| "step": 968000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.4326666666666666e-07, | |
| "loss": 2.0465, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.9196343421936035, | |
| "eval_runtime": 47.9588, | |
| "eval_samples_per_second": 857.027, | |
| "eval_steps_per_second": 53.567, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "eval_loss": 1.9111627340316772, | |
| "eval_runtime": 48.5638, | |
| "eval_samples_per_second": 846.35, | |
| "eval_steps_per_second": 52.899, | |
| "step": 984000 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 2.405333333333333e-07, | |
| "loss": 2.0454, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "eval_loss": 1.9045841693878174, | |
| "eval_runtime": 47.3858, | |
| "eval_samples_per_second": 867.39, | |
| "eval_steps_per_second": 54.215, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 20.49, | |
| "eval_loss": 1.9031916856765747, | |
| "eval_runtime": 47.9829, | |
| "eval_samples_per_second": 856.596, | |
| "eval_steps_per_second": 53.54, | |
| "step": 1000000 | |
| }, | |
| { | |
| "epoch": 20.65, | |
| "learning_rate": 2.3779999999999997e-07, | |
| "loss": 2.04, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 20.65, | |
| "eval_loss": 1.9129735231399536, | |
| "eval_runtime": 48.8696, | |
| "eval_samples_per_second": 841.055, | |
| "eval_steps_per_second": 52.568, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 20.82, | |
| "eval_loss": 1.922319769859314, | |
| "eval_runtime": 48.2743, | |
| "eval_samples_per_second": 851.427, | |
| "eval_steps_per_second": 53.217, | |
| "step": 1016000 | |
| }, | |
| { | |
| "epoch": 20.98, | |
| "learning_rate": 2.3506666666666668e-07, | |
| "loss": 2.0406, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 20.98, | |
| "eval_loss": 1.9261207580566406, | |
| "eval_runtime": 48.256, | |
| "eval_samples_per_second": 851.749, | |
| "eval_steps_per_second": 53.237, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 21.14, | |
| "eval_loss": 1.9014304876327515, | |
| "eval_runtime": 47.3123, | |
| "eval_samples_per_second": 868.737, | |
| "eval_steps_per_second": 54.299, | |
| "step": 1032000 | |
| }, | |
| { | |
| "epoch": 21.31, | |
| "learning_rate": 2.3233333333333334e-07, | |
| "loss": 2.0401, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 21.31, | |
| "eval_loss": 1.905246615409851, | |
| "eval_runtime": 47.017, | |
| "eval_samples_per_second": 874.195, | |
| "eval_steps_per_second": 54.64, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "eval_loss": 1.9004502296447754, | |
| "eval_runtime": 47.6152, | |
| "eval_samples_per_second": 863.213, | |
| "eval_steps_per_second": 53.953, | |
| "step": 1048000 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 2.2960000000000002e-07, | |
| "loss": 2.044, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "eval_loss": 1.9044198989868164, | |
| "eval_runtime": 48.1051, | |
| "eval_samples_per_second": 854.421, | |
| "eval_steps_per_second": 53.404, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "eval_loss": 1.9169893264770508, | |
| "eval_runtime": 49.4919, | |
| "eval_samples_per_second": 830.479, | |
| "eval_steps_per_second": 51.907, | |
| "step": 1064000 | |
| }, | |
| { | |
| "epoch": 21.96, | |
| "learning_rate": 2.2686666666666667e-07, | |
| "loss": 2.0401, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 21.96, | |
| "eval_loss": 1.9103343486785889, | |
| "eval_runtime": 47.4547, | |
| "eval_samples_per_second": 866.132, | |
| "eval_steps_per_second": 54.136, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "eval_loss": 1.8970900774002075, | |
| "eval_runtime": 46.9831, | |
| "eval_samples_per_second": 874.825, | |
| "eval_steps_per_second": 54.679, | |
| "step": 1080000 | |
| }, | |
| { | |
| "epoch": 22.29, | |
| "learning_rate": 2.2413333333333333e-07, | |
| "loss": 2.0458, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 22.29, | |
| "eval_loss": 1.9256750345230103, | |
| "eval_runtime": 49.8527, | |
| "eval_samples_per_second": 824.47, | |
| "eval_steps_per_second": 51.532, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 22.45, | |
| "eval_loss": 1.9029202461242676, | |
| "eval_runtime": 48.7208, | |
| "eval_samples_per_second": 843.623, | |
| "eval_steps_per_second": 52.729, | |
| "step": 1096000 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 2.214e-07, | |
| "loss": 2.0414, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "eval_loss": 1.915024995803833, | |
| "eval_runtime": 47.4381, | |
| "eval_samples_per_second": 866.434, | |
| "eval_steps_per_second": 54.155, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "eval_loss": 1.9123761653900146, | |
| "eval_runtime": 48.794, | |
| "eval_samples_per_second": 842.358, | |
| "eval_steps_per_second": 52.65, | |
| "step": 1112000 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 2.1866666666666667e-07, | |
| "loss": 2.0419, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "eval_loss": 1.9029767513275146, | |
| "eval_runtime": 46.4756, | |
| "eval_samples_per_second": 884.378, | |
| "eval_steps_per_second": 55.276, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "eval_loss": 1.9144717454910278, | |
| "eval_runtime": 47.2249, | |
| "eval_samples_per_second": 870.345, | |
| "eval_steps_per_second": 54.399, | |
| "step": 1128000 | |
| }, | |
| { | |
| "epoch": 23.27, | |
| "learning_rate": 2.1593333333333332e-07, | |
| "loss": 2.0415, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 23.27, | |
| "eval_loss": 1.9132155179977417, | |
| "eval_runtime": 49.2316, | |
| "eval_samples_per_second": 834.869, | |
| "eval_steps_per_second": 52.182, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "eval_loss": 1.9053661823272705, | |
| "eval_runtime": 47.1942, | |
| "eval_samples_per_second": 870.913, | |
| "eval_steps_per_second": 54.435, | |
| "step": 1144000 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 2.132e-07, | |
| "loss": 2.0394, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "eval_loss": 1.915486216545105, | |
| "eval_runtime": 47.1108, | |
| "eval_samples_per_second": 872.454, | |
| "eval_steps_per_second": 54.531, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 23.77, | |
| "eval_loss": 1.9147080183029175, | |
| "eval_runtime": 48.0401, | |
| "eval_samples_per_second": 855.578, | |
| "eval_steps_per_second": 53.476, | |
| "step": 1160000 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "learning_rate": 2.1046666666666666e-07, | |
| "loss": 2.0414, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "eval_loss": 1.9130446910858154, | |
| "eval_runtime": 47.5065, | |
| "eval_samples_per_second": 865.187, | |
| "eval_steps_per_second": 54.077, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 24.09, | |
| "eval_loss": 1.9002370834350586, | |
| "eval_runtime": 46.3893, | |
| "eval_samples_per_second": 886.023, | |
| "eval_steps_per_second": 55.379, | |
| "step": 1176000 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 2.0773333333333334e-07, | |
| "loss": 2.036, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "eval_loss": 1.899147391319275, | |
| "eval_runtime": 49.4488, | |
| "eval_samples_per_second": 831.204, | |
| "eval_steps_per_second": 51.953, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "eval_loss": 1.9202589988708496, | |
| "eval_runtime": 47.2347, | |
| "eval_samples_per_second": 870.165, | |
| "eval_steps_per_second": 54.388, | |
| "step": 1192000 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "learning_rate": 2.05e-07, | |
| "loss": 2.0393, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "eval_loss": 1.9327338933944702, | |
| "eval_runtime": 47.2461, | |
| "eval_samples_per_second": 869.956, | |
| "eval_steps_per_second": 54.375, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "eval_loss": 1.9098608493804932, | |
| "eval_runtime": 49.039, | |
| "eval_samples_per_second": 838.15, | |
| "eval_steps_per_second": 52.387, | |
| "step": 1208000 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 2.0226666666666668e-07, | |
| "loss": 2.0375, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "eval_loss": 1.9097236394882202, | |
| "eval_runtime": 46.2815, | |
| "eval_samples_per_second": 888.088, | |
| "eval_steps_per_second": 55.508, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 25.08, | |
| "eval_loss": 1.900553584098816, | |
| "eval_runtime": 47.0809, | |
| "eval_samples_per_second": 873.008, | |
| "eval_steps_per_second": 54.566, | |
| "step": 1224000 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "learning_rate": 1.9953333333333333e-07, | |
| "loss": 2.0384, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "eval_loss": 1.9062752723693848, | |
| "eval_runtime": 48.6722, | |
| "eval_samples_per_second": 844.466, | |
| "eval_steps_per_second": 52.782, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 25.41, | |
| "eval_loss": 1.9056702852249146, | |
| "eval_runtime": 46.3936, | |
| "eval_samples_per_second": 885.941, | |
| "eval_steps_per_second": 55.374, | |
| "step": 1240000 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 1.968e-07, | |
| "loss": 2.0392, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "eval_loss": 1.9037301540374756, | |
| "eval_runtime": 47.9627, | |
| "eval_samples_per_second": 856.958, | |
| "eval_steps_per_second": 53.563, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 25.73, | |
| "eval_loss": 1.9013148546218872, | |
| "eval_runtime": 47.5129, | |
| "eval_samples_per_second": 865.07, | |
| "eval_steps_per_second": 54.07, | |
| "step": 1256000 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "learning_rate": 1.9406666666666667e-07, | |
| "loss": 2.0503, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "eval_loss": 1.903662085533142, | |
| "eval_runtime": 47.6911, | |
| "eval_samples_per_second": 861.838, | |
| "eval_steps_per_second": 53.867, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 26.06, | |
| "eval_loss": 1.904166579246521, | |
| "eval_runtime": 51.6224, | |
| "eval_samples_per_second": 796.204, | |
| "eval_steps_per_second": 49.765, | |
| "step": 1272000 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 1.9133333333333333e-07, | |
| "loss": 2.0418, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "eval_loss": 1.896562933921814, | |
| "eval_runtime": 47.6826, | |
| "eval_samples_per_second": 861.992, | |
| "eval_steps_per_second": 53.877, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "eval_loss": 1.9186903238296509, | |
| "eval_runtime": 49.1139, | |
| "eval_samples_per_second": 836.872, | |
| "eval_steps_per_second": 52.307, | |
| "step": 1288000 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 1.886e-07, | |
| "loss": 2.0416, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "eval_loss": 1.9097530841827393, | |
| "eval_runtime": 48.6689, | |
| "eval_samples_per_second": 844.523, | |
| "eval_steps_per_second": 52.785, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "eval_loss": 1.9153447151184082, | |
| "eval_runtime": 49.0115, | |
| "eval_samples_per_second": 838.62, | |
| "eval_steps_per_second": 52.416, | |
| "step": 1304000 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.8586666666666666e-07, | |
| "loss": 2.0396, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "eval_loss": 1.9163771867752075, | |
| "eval_runtime": 48.0083, | |
| "eval_samples_per_second": 856.144, | |
| "eval_steps_per_second": 53.512, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "eval_loss": 1.886674404144287, | |
| "eval_runtime": 48.4626, | |
| "eval_samples_per_second": 848.117, | |
| "eval_steps_per_second": 53.01, | |
| "step": 1320000 | |
| }, | |
| { | |
| "epoch": 27.21, | |
| "learning_rate": 1.8313333333333332e-07, | |
| "loss": 2.0397, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 27.21, | |
| "eval_loss": 1.8968819379806519, | |
| "eval_runtime": 48.9216, | |
| "eval_samples_per_second": 840.161, | |
| "eval_steps_per_second": 52.513, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 27.37, | |
| "eval_loss": 1.915518879890442, | |
| "eval_runtime": 46.9702, | |
| "eval_samples_per_second": 875.066, | |
| "eval_steps_per_second": 54.694, | |
| "step": 1336000 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 1.804e-07, | |
| "loss": 2.0442, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "eval_loss": 1.9004348516464233, | |
| "eval_runtime": 47.3437, | |
| "eval_samples_per_second": 868.163, | |
| "eval_steps_per_second": 54.263, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 27.7, | |
| "eval_loss": 1.9026644229888916, | |
| "eval_runtime": 47.3596, | |
| "eval_samples_per_second": 867.87, | |
| "eval_steps_per_second": 54.245, | |
| "step": 1352000 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "learning_rate": 1.7766666666666666e-07, | |
| "loss": 2.0332, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "eval_loss": 1.9095487594604492, | |
| "eval_runtime": 48.6586, | |
| "eval_samples_per_second": 844.702, | |
| "eval_steps_per_second": 52.796, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "eval_loss": 1.9133695363998413, | |
| "eval_runtime": 46.4591, | |
| "eval_samples_per_second": 884.693, | |
| "eval_steps_per_second": 55.296, | |
| "step": 1368000 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 1.7493333333333334e-07, | |
| "loss": 2.0398, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "eval_loss": 1.9082748889923096, | |
| "eval_runtime": 48.6075, | |
| "eval_samples_per_second": 845.589, | |
| "eval_steps_per_second": 52.852, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "eval_loss": 1.9041306972503662, | |
| "eval_runtime": 47.5314, | |
| "eval_samples_per_second": 864.733, | |
| "eval_steps_per_second": 54.048, | |
| "step": 1384000 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 1.722e-07, | |
| "loss": 2.0387, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "eval_loss": 1.8979713916778564, | |
| "eval_runtime": 47.145, | |
| "eval_samples_per_second": 871.821, | |
| "eval_steps_per_second": 54.491, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 28.68, | |
| "eval_loss": 1.9209250211715698, | |
| "eval_runtime": 48.0076, | |
| "eval_samples_per_second": 856.156, | |
| "eval_steps_per_second": 53.512, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 1.6946666666666668e-07, | |
| "loss": 2.0378, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "eval_loss": 1.896246314048767, | |
| "eval_runtime": 47.2348, | |
| "eval_samples_per_second": 870.163, | |
| "eval_steps_per_second": 54.388, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "eval_loss": 1.8981308937072754, | |
| "eval_runtime": 46.2446, | |
| "eval_samples_per_second": 888.796, | |
| "eval_steps_per_second": 55.552, | |
| "step": 1416000 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "learning_rate": 1.6673333333333333e-07, | |
| "loss": 2.0359, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "eval_loss": 1.9077860116958618, | |
| "eval_runtime": 47.7404, | |
| "eval_samples_per_second": 860.949, | |
| "eval_steps_per_second": 53.812, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "eval_loss": 1.8961683511734009, | |
| "eval_runtime": 48.4809, | |
| "eval_samples_per_second": 847.798, | |
| "eval_steps_per_second": 52.99, | |
| "step": 1432000 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "learning_rate": 1.64e-07, | |
| "loss": 2.0357, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "eval_loss": 1.8842545747756958, | |
| "eval_runtime": 46.6243, | |
| "eval_samples_per_second": 881.558, | |
| "eval_steps_per_second": 55.1, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "eval_loss": 1.9157154560089111, | |
| "eval_runtime": 47.0518, | |
| "eval_samples_per_second": 873.548, | |
| "eval_steps_per_second": 54.599, | |
| "step": 1448000 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "learning_rate": 1.6126666666666667e-07, | |
| "loss": 2.0367, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "eval_loss": 1.9277722835540771, | |
| "eval_runtime": 48.4635, | |
| "eval_samples_per_second": 848.102, | |
| "eval_steps_per_second": 53.009, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 29.99, | |
| "eval_loss": 1.900920033454895, | |
| "eval_runtime": 48.4837, | |
| "eval_samples_per_second": 847.75, | |
| "eval_steps_per_second": 52.987, | |
| "step": 1464000 | |
| }, | |
| { | |
| "epoch": 30.16, | |
| "learning_rate": 1.5853333333333332e-07, | |
| "loss": 2.0442, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 30.16, | |
| "eval_loss": 1.8968621492385864, | |
| "eval_runtime": 47.5534, | |
| "eval_samples_per_second": 864.334, | |
| "eval_steps_per_second": 54.024, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "eval_loss": 1.908553123474121, | |
| "eval_runtime": 49.61, | |
| "eval_samples_per_second": 828.502, | |
| "eval_steps_per_second": 51.784, | |
| "step": 1480000 | |
| }, | |
| { | |
| "epoch": 30.49, | |
| "learning_rate": 1.558e-07, | |
| "loss": 2.0401, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 30.49, | |
| "eval_loss": 1.9059042930603027, | |
| "eval_runtime": 47.0678, | |
| "eval_samples_per_second": 873.252, | |
| "eval_steps_per_second": 54.581, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 30.65, | |
| "eval_loss": 1.8996624946594238, | |
| "eval_runtime": 46.6534, | |
| "eval_samples_per_second": 881.007, | |
| "eval_steps_per_second": 55.066, | |
| "step": 1496000 | |
| }, | |
| { | |
| "epoch": 30.81, | |
| "learning_rate": 1.5306666666666666e-07, | |
| "loss": 2.0293, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 30.81, | |
| "eval_loss": 1.9013988971710205, | |
| "eval_runtime": 48.769, | |
| "eval_samples_per_second": 842.79, | |
| "eval_steps_per_second": 52.677, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 30.98, | |
| "eval_loss": 1.8971112966537476, | |
| "eval_runtime": 46.4191, | |
| "eval_samples_per_second": 885.455, | |
| "eval_steps_per_second": 55.344, | |
| "step": 1512000 | |
| }, | |
| { | |
| "epoch": 31.14, | |
| "learning_rate": 1.5033333333333332e-07, | |
| "loss": 2.035, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 31.14, | |
| "eval_loss": 1.911407470703125, | |
| "eval_runtime": 48.2406, | |
| "eval_samples_per_second": 852.021, | |
| "eval_steps_per_second": 53.254, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 31.31, | |
| "eval_loss": 1.9107669591903687, | |
| "eval_runtime": 48.5327, | |
| "eval_samples_per_second": 846.893, | |
| "eval_steps_per_second": 52.933, | |
| "step": 1528000 | |
| }, | |
| { | |
| "epoch": 31.47, | |
| "learning_rate": 1.476e-07, | |
| "loss": 2.0389, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 31.47, | |
| "eval_loss": 1.897054672241211, | |
| "eval_runtime": 47.3694, | |
| "eval_samples_per_second": 867.69, | |
| "eval_steps_per_second": 54.233, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 31.63, | |
| "eval_loss": 1.9081885814666748, | |
| "eval_runtime": 47.7941, | |
| "eval_samples_per_second": 859.98, | |
| "eval_steps_per_second": 53.751, | |
| "step": 1544000 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 1.4486666666666665e-07, | |
| "loss": 2.0346, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "eval_loss": 1.9208694696426392, | |
| "eval_runtime": 47.5276, | |
| "eval_samples_per_second": 864.802, | |
| "eval_steps_per_second": 54.053, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 31.96, | |
| "eval_loss": 1.9018235206604004, | |
| "eval_runtime": 48.2326, | |
| "eval_samples_per_second": 852.162, | |
| "eval_steps_per_second": 53.263, | |
| "step": 1560000 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 1.4213333333333334e-07, | |
| "loss": 2.0428, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "eval_loss": 1.8987597227096558, | |
| "eval_runtime": 48.8575, | |
| "eval_samples_per_second": 841.263, | |
| "eval_steps_per_second": 52.581, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 32.29, | |
| "eval_loss": 1.9089306592941284, | |
| "eval_runtime": 48.142, | |
| "eval_samples_per_second": 853.766, | |
| "eval_steps_per_second": 53.363, | |
| "step": 1576000 | |
| }, | |
| { | |
| "epoch": 32.45, | |
| "learning_rate": 1.3940000000000002e-07, | |
| "loss": 2.0286, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 32.45, | |
| "eval_loss": 1.8982652425765991, | |
| "eval_runtime": 47.0839, | |
| "eval_samples_per_second": 872.953, | |
| "eval_steps_per_second": 54.562, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 32.62, | |
| "eval_loss": 1.9029755592346191, | |
| "eval_runtime": 47.4849, | |
| "eval_samples_per_second": 865.581, | |
| "eval_steps_per_second": 54.101, | |
| "step": 1592000 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 1.3666666666666665e-07, | |
| "loss": 2.037, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "eval_loss": 1.9041838645935059, | |
| "eval_runtime": 47.6583, | |
| "eval_samples_per_second": 862.431, | |
| "eval_steps_per_second": 53.905, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 32.94, | |
| "eval_loss": 1.9021574258804321, | |
| "eval_runtime": 47.636, | |
| "eval_samples_per_second": 862.836, | |
| "eval_steps_per_second": 53.93, | |
| "step": 1608000 | |
| }, | |
| { | |
| "epoch": 33.11, | |
| "learning_rate": 1.3393333333333333e-07, | |
| "loss": 2.0348, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 33.11, | |
| "eval_loss": 1.8987573385238647, | |
| "eval_runtime": 48.3458, | |
| "eval_samples_per_second": 850.167, | |
| "eval_steps_per_second": 53.138, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 33.27, | |
| "eval_loss": 1.9159427881240845, | |
| "eval_runtime": 48.9467, | |
| "eval_samples_per_second": 839.73, | |
| "eval_steps_per_second": 52.486, | |
| "step": 1624000 | |
| }, | |
| { | |
| "epoch": 33.44, | |
| "learning_rate": 1.312e-07, | |
| "loss": 2.042, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 33.44, | |
| "eval_loss": 1.8933523893356323, | |
| "eval_runtime": 48.1661, | |
| "eval_samples_per_second": 853.339, | |
| "eval_steps_per_second": 53.336, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "eval_loss": 1.890829086303711, | |
| "eval_runtime": 47.8234, | |
| "eval_samples_per_second": 859.454, | |
| "eval_steps_per_second": 53.719, | |
| "step": 1640000 | |
| }, | |
| { | |
| "epoch": 33.76, | |
| "learning_rate": 1.2846666666666667e-07, | |
| "loss": 2.0426, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 33.76, | |
| "eval_loss": 1.88780677318573, | |
| "eval_runtime": 48.4427, | |
| "eval_samples_per_second": 848.466, | |
| "eval_steps_per_second": 53.032, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "eval_loss": 1.8881806135177612, | |
| "eval_runtime": 48.0347, | |
| "eval_samples_per_second": 855.674, | |
| "eval_steps_per_second": 53.482, | |
| "step": 1656000 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "learning_rate": 1.2573333333333332e-07, | |
| "loss": 2.0293, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "eval_loss": 1.9031046628952026, | |
| "eval_runtime": 48.0682, | |
| "eval_samples_per_second": 855.077, | |
| "eval_steps_per_second": 53.445, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 34.26, | |
| "eval_loss": 1.9005811214447021, | |
| "eval_runtime": 48.7309, | |
| "eval_samples_per_second": 843.448, | |
| "eval_steps_per_second": 52.718, | |
| "step": 1672000 | |
| }, | |
| { | |
| "epoch": 34.42, | |
| "learning_rate": 1.23e-07, | |
| "loss": 2.0401, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 34.42, | |
| "eval_loss": 1.9066253900527954, | |
| "eval_runtime": 52.1229, | |
| "eval_samples_per_second": 788.56, | |
| "eval_steps_per_second": 49.287, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 34.58, | |
| "eval_loss": 1.8970048427581787, | |
| "eval_runtime": 48.6499, | |
| "eval_samples_per_second": 844.853, | |
| "eval_steps_per_second": 52.806, | |
| "step": 1688000 | |
| }, | |
| { | |
| "epoch": 34.75, | |
| "learning_rate": 1.2026666666666666e-07, | |
| "loss": 2.0315, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 34.75, | |
| "eval_loss": 1.895332932472229, | |
| "eval_runtime": 47.3522, | |
| "eval_samples_per_second": 868.006, | |
| "eval_steps_per_second": 54.253, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 34.91, | |
| "eval_loss": 1.9029524326324463, | |
| "eval_runtime": 48.1027, | |
| "eval_samples_per_second": 854.464, | |
| "eval_steps_per_second": 53.407, | |
| "step": 1704000 | |
| }, | |
| { | |
| "epoch": 35.08, | |
| "learning_rate": 1.1753333333333334e-07, | |
| "loss": 2.0393, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 35.08, | |
| "eval_loss": 1.908921480178833, | |
| "eval_runtime": 49.5777, | |
| "eval_samples_per_second": 829.043, | |
| "eval_steps_per_second": 51.818, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 35.24, | |
| "eval_loss": 1.9037113189697266, | |
| "eval_runtime": 46.6983, | |
| "eval_samples_per_second": 880.16, | |
| "eval_steps_per_second": 55.013, | |
| "step": 1720000 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "learning_rate": 1.1480000000000001e-07, | |
| "loss": 2.0422, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "eval_loss": 1.8991347551345825, | |
| "eval_runtime": 50.2373, | |
| "eval_samples_per_second": 818.157, | |
| "eval_steps_per_second": 51.137, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "eval_loss": 1.8825979232788086, | |
| "eval_runtime": 48.4051, | |
| "eval_samples_per_second": 849.125, | |
| "eval_steps_per_second": 53.073, | |
| "step": 1736000 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "learning_rate": 1.1206666666666666e-07, | |
| "loss": 2.0307, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "eval_loss": 1.9027307033538818, | |
| "eval_runtime": 48.1077, | |
| "eval_samples_per_second": 854.375, | |
| "eval_steps_per_second": 53.401, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "eval_loss": 1.9172565937042236, | |
| "eval_runtime": 52.2685, | |
| "eval_samples_per_second": 786.363, | |
| "eval_steps_per_second": 49.15, | |
| "step": 1752000 | |
| }, | |
| { | |
| "epoch": 36.06, | |
| "learning_rate": 1.0933333333333333e-07, | |
| "loss": 2.0414, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 36.06, | |
| "eval_loss": 1.9065029621124268, | |
| "eval_runtime": 46.9419, | |
| "eval_samples_per_second": 875.593, | |
| "eval_steps_per_second": 54.727, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 36.22, | |
| "eval_loss": 1.8984663486480713, | |
| "eval_runtime": 46.6191, | |
| "eval_samples_per_second": 881.656, | |
| "eval_steps_per_second": 55.106, | |
| "step": 1768000 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "learning_rate": 1.066e-07, | |
| "loss": 2.0393, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "eval_loss": 1.884873628616333, | |
| "eval_runtime": 48.406, | |
| "eval_samples_per_second": 849.11, | |
| "eval_steps_per_second": 53.072, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "eval_loss": 1.8944772481918335, | |
| "eval_runtime": 47.82, | |
| "eval_samples_per_second": 859.514, | |
| "eval_steps_per_second": 53.722, | |
| "step": 1784000 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "learning_rate": 1.0386666666666667e-07, | |
| "loss": 2.0302, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "eval_loss": 1.8962441682815552, | |
| "eval_runtime": 47.8175, | |
| "eval_samples_per_second": 859.56, | |
| "eval_steps_per_second": 53.725, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 36.88, | |
| "eval_loss": 1.901509165763855, | |
| "eval_runtime": 48.8399, | |
| "eval_samples_per_second": 841.566, | |
| "eval_steps_per_second": 52.6, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 37.04, | |
| "learning_rate": 1.0113333333333334e-07, | |
| "loss": 2.0344, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 37.04, | |
| "eval_loss": 1.8923826217651367, | |
| "eval_runtime": 48.2438, | |
| "eval_samples_per_second": 851.964, | |
| "eval_steps_per_second": 53.25, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 37.21, | |
| "eval_loss": 1.8804473876953125, | |
| "eval_runtime": 46.9418, | |
| "eval_samples_per_second": 875.595, | |
| "eval_steps_per_second": 54.727, | |
| "step": 1816000 | |
| }, | |
| { | |
| "epoch": 37.37, | |
| "learning_rate": 9.84e-08, | |
| "loss": 2.0303, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 37.37, | |
| "eval_loss": 1.894727349281311, | |
| "eval_runtime": 49.8927, | |
| "eval_samples_per_second": 823.808, | |
| "eval_steps_per_second": 51.491, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 37.53, | |
| "eval_loss": 1.891680121421814, | |
| "eval_runtime": 47.928, | |
| "eval_samples_per_second": 857.579, | |
| "eval_steps_per_second": 53.601, | |
| "step": 1832000 | |
| }, | |
| { | |
| "epoch": 37.7, | |
| "learning_rate": 9.566666666666666e-08, | |
| "loss": 2.0318, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 37.7, | |
| "eval_loss": 1.8992102146148682, | |
| "eval_runtime": 46.9913, | |
| "eval_samples_per_second": 874.673, | |
| "eval_steps_per_second": 54.67, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 37.86, | |
| "eval_loss": 1.901772379875183, | |
| "eval_runtime": 48.5091, | |
| "eval_samples_per_second": 847.306, | |
| "eval_steps_per_second": 52.959, | |
| "step": 1848000 | |
| }, | |
| { | |
| "epoch": 38.03, | |
| "learning_rate": 9.293333333333333e-08, | |
| "loss": 2.039, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 38.03, | |
| "eval_loss": 1.8903098106384277, | |
| "eval_runtime": 49.839, | |
| "eval_samples_per_second": 824.695, | |
| "eval_steps_per_second": 51.546, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "eval_loss": 1.9088859558105469, | |
| "eval_runtime": 49.3732, | |
| "eval_samples_per_second": 832.477, | |
| "eval_steps_per_second": 52.032, | |
| "step": 1864000 | |
| }, | |
| { | |
| "epoch": 38.35, | |
| "learning_rate": 9.02e-08, | |
| "loss": 2.0319, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 38.35, | |
| "eval_loss": 1.9092743396759033, | |
| "eval_runtime": 47.4891, | |
| "eval_samples_per_second": 865.505, | |
| "eval_steps_per_second": 54.097, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 38.52, | |
| "eval_loss": 1.895071268081665, | |
| "eval_runtime": 50.6752, | |
| "eval_samples_per_second": 811.087, | |
| "eval_steps_per_second": 50.695, | |
| "step": 1880000 | |
| }, | |
| { | |
| "epoch": 38.68, | |
| "learning_rate": 8.746666666666667e-08, | |
| "loss": 2.0359, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 38.68, | |
| "eval_loss": 1.8970472812652588, | |
| "eval_runtime": 47.92, | |
| "eval_samples_per_second": 857.721, | |
| "eval_steps_per_second": 53.61, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 38.85, | |
| "eval_loss": 1.89948308467865, | |
| "eval_runtime": 49.1024, | |
| "eval_samples_per_second": 837.067, | |
| "eval_steps_per_second": 52.319, | |
| "step": 1896000 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 8.473333333333334e-08, | |
| "loss": 2.0353, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "eval_loss": 1.8887970447540283, | |
| "eval_runtime": 49.8221, | |
| "eval_samples_per_second": 824.975, | |
| "eval_steps_per_second": 51.563, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 39.17, | |
| "eval_loss": 1.914867877960205, | |
| "eval_runtime": 47.1415, | |
| "eval_samples_per_second": 871.885, | |
| "eval_steps_per_second": 54.495, | |
| "step": 1912000 | |
| }, | |
| { | |
| "epoch": 39.34, | |
| "learning_rate": 8.2e-08, | |
| "loss": 2.0343, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 39.34, | |
| "eval_loss": 1.8881230354309082, | |
| "eval_runtime": 48.2273, | |
| "eval_samples_per_second": 852.256, | |
| "eval_steps_per_second": 53.269, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 39.5, | |
| "eval_loss": 1.8935189247131348, | |
| "eval_runtime": 49.8823, | |
| "eval_samples_per_second": 823.979, | |
| "eval_steps_per_second": 51.501, | |
| "step": 1928000 | |
| }, | |
| { | |
| "epoch": 39.66, | |
| "learning_rate": 7.926666666666666e-08, | |
| "loss": 2.0395, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 39.66, | |
| "eval_loss": 1.8938074111938477, | |
| "eval_runtime": 49.2266, | |
| "eval_samples_per_second": 834.956, | |
| "eval_steps_per_second": 52.187, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 39.83, | |
| "eval_loss": 1.8929249048233032, | |
| "eval_runtime": 47.6917, | |
| "eval_samples_per_second": 861.827, | |
| "eval_steps_per_second": 53.867, | |
| "step": 1944000 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "learning_rate": 7.653333333333333e-08, | |
| "loss": 2.0316, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "eval_loss": 1.9186030626296997, | |
| "eval_runtime": 49.8739, | |
| "eval_samples_per_second": 824.118, | |
| "eval_steps_per_second": 51.51, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 40.16, | |
| "eval_loss": 1.9189401865005493, | |
| "eval_runtime": 50.0489, | |
| "eval_samples_per_second": 821.238, | |
| "eval_steps_per_second": 51.33, | |
| "step": 1960000 | |
| }, | |
| { | |
| "epoch": 40.32, | |
| "learning_rate": 7.38e-08, | |
| "loss": 2.0302, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 40.32, | |
| "eval_loss": 1.9124609231948853, | |
| "eval_runtime": 52.3286, | |
| "eval_samples_per_second": 785.459, | |
| "eval_steps_per_second": 49.094, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 40.48, | |
| "eval_loss": 1.9077569246292114, | |
| "eval_runtime": 48.6653, | |
| "eval_samples_per_second": 844.585, | |
| "eval_steps_per_second": 52.789, | |
| "step": 1976000 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "learning_rate": 7.106666666666667e-08, | |
| "loss": 2.0355, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "eval_loss": 1.8975083827972412, | |
| "eval_runtime": 48.5464, | |
| "eval_samples_per_second": 846.654, | |
| "eval_steps_per_second": 52.918, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 40.81, | |
| "eval_loss": 1.892892837524414, | |
| "eval_runtime": 49.649, | |
| "eval_samples_per_second": 827.852, | |
| "eval_steps_per_second": 51.743, | |
| "step": 1992000 | |
| }, | |
| { | |
| "epoch": 40.98, | |
| "learning_rate": 6.833333333333332e-08, | |
| "loss": 2.0332, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 40.98, | |
| "eval_loss": 1.8898950815200806, | |
| "eval_runtime": 48.8626, | |
| "eval_samples_per_second": 841.175, | |
| "eval_steps_per_second": 52.576, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 41.14, | |
| "eval_loss": 1.9043201208114624, | |
| "eval_runtime": 49.3883, | |
| "eval_samples_per_second": 832.221, | |
| "eval_steps_per_second": 52.016, | |
| "step": 2008000 | |
| }, | |
| { | |
| "epoch": 41.3, | |
| "learning_rate": 6.56e-08, | |
| "loss": 2.0327, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 41.3, | |
| "eval_loss": 1.9086461067199707, | |
| "eval_runtime": 48.958, | |
| "eval_samples_per_second": 839.535, | |
| "eval_steps_per_second": 52.474, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 41.47, | |
| "eval_loss": 1.894409418106079, | |
| "eval_runtime": 50.95, | |
| "eval_samples_per_second": 806.713, | |
| "eval_steps_per_second": 50.422, | |
| "step": 2024000 | |
| }, | |
| { | |
| "epoch": 41.63, | |
| "learning_rate": 6.286666666666666e-08, | |
| "loss": 2.0414, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 41.63, | |
| "eval_loss": 1.9029189348220825, | |
| "eval_runtime": 48.6407, | |
| "eval_samples_per_second": 845.013, | |
| "eval_steps_per_second": 52.816, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "eval_loss": 1.8990041017532349, | |
| "eval_runtime": 48.9601, | |
| "eval_samples_per_second": 839.5, | |
| "eval_steps_per_second": 52.471, | |
| "step": 2040000 | |
| }, | |
| { | |
| "epoch": 41.96, | |
| "learning_rate": 6.013333333333333e-08, | |
| "loss": 2.0327, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 41.96, | |
| "eval_loss": 1.9174869060516357, | |
| "eval_runtime": 47.4446, | |
| "eval_samples_per_second": 866.315, | |
| "eval_steps_per_second": 54.147, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 42.12, | |
| "eval_loss": 1.88877534866333, | |
| "eval_runtime": 48.6939, | |
| "eval_samples_per_second": 844.09, | |
| "eval_steps_per_second": 52.758, | |
| "step": 2056000 | |
| }, | |
| { | |
| "epoch": 42.29, | |
| "learning_rate": 5.7400000000000004e-08, | |
| "loss": 2.0428, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 42.29, | |
| "eval_loss": 1.8971478939056396, | |
| "eval_runtime": 47.9266, | |
| "eval_samples_per_second": 857.603, | |
| "eval_steps_per_second": 53.603, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "eval_loss": 1.90713369846344, | |
| "eval_runtime": 49.0676, | |
| "eval_samples_per_second": 837.661, | |
| "eval_steps_per_second": 52.356, | |
| "step": 2072000 | |
| }, | |
| { | |
| "epoch": 42.62, | |
| "learning_rate": 5.4666666666666666e-08, | |
| "loss": 2.0337, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 42.62, | |
| "eval_loss": 1.8967806100845337, | |
| "eval_runtime": 50.5362, | |
| "eval_samples_per_second": 813.318, | |
| "eval_steps_per_second": 50.835, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 42.78, | |
| "eval_loss": 1.9059593677520752, | |
| "eval_runtime": 48.8076, | |
| "eval_samples_per_second": 842.122, | |
| "eval_steps_per_second": 52.635, | |
| "step": 2088000 | |
| }, | |
| { | |
| "epoch": 42.94, | |
| "learning_rate": 5.1933333333333335e-08, | |
| "loss": 2.0394, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 42.94, | |
| "eval_loss": 1.902763843536377, | |
| "eval_runtime": 48.599, | |
| "eval_samples_per_second": 845.737, | |
| "eval_steps_per_second": 52.861, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 43.11, | |
| "eval_loss": 1.8916599750518799, | |
| "eval_runtime": 50.6067, | |
| "eval_samples_per_second": 812.185, | |
| "eval_steps_per_second": 50.764, | |
| "step": 2104000 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 4.92e-08, | |
| "loss": 2.0314, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "eval_loss": 1.8868290185928345, | |
| "eval_runtime": 50.3637, | |
| "eval_samples_per_second": 816.103, | |
| "eval_steps_per_second": 51.009, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 43.43, | |
| "eval_loss": 1.9086658954620361, | |
| "eval_runtime": 47.3253, | |
| "eval_samples_per_second": 868.499, | |
| "eval_steps_per_second": 54.284, | |
| "step": 2120000 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "learning_rate": 4.6466666666666666e-08, | |
| "loss": 2.0368, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "eval_loss": 1.8951292037963867, | |
| "eval_runtime": 48.361, | |
| "eval_samples_per_second": 849.9, | |
| "eval_steps_per_second": 53.121, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 43.76, | |
| "eval_loss": 1.893837809562683, | |
| "eval_runtime": 47.3135, | |
| "eval_samples_per_second": 868.717, | |
| "eval_steps_per_second": 54.297, | |
| "step": 2136000 | |
| }, | |
| { | |
| "epoch": 43.93, | |
| "learning_rate": 4.3733333333333335e-08, | |
| "loss": 2.0298, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 43.93, | |
| "eval_loss": 1.8874099254608154, | |
| "eval_runtime": 47.3514, | |
| "eval_samples_per_second": 868.022, | |
| "eval_steps_per_second": 54.254, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 44.09, | |
| "eval_loss": 1.90646493434906, | |
| "eval_runtime": 49.5581, | |
| "eval_samples_per_second": 829.37, | |
| "eval_steps_per_second": 51.838, | |
| "step": 2152000 | |
| }, | |
| { | |
| "epoch": 44.25, | |
| "learning_rate": 4.1e-08, | |
| "loss": 2.0353, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 44.25, | |
| "eval_loss": 1.9097111225128174, | |
| "eval_runtime": 46.9959, | |
| "eval_samples_per_second": 874.587, | |
| "eval_steps_per_second": 54.664, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 44.42, | |
| "eval_loss": 1.8985484838485718, | |
| "eval_runtime": 48.6536, | |
| "eval_samples_per_second": 844.788, | |
| "eval_steps_per_second": 52.802, | |
| "step": 2168000 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "learning_rate": 3.8266666666666665e-08, | |
| "loss": 2.0324, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "eval_loss": 1.9160007238388062, | |
| "eval_runtime": 49.8464, | |
| "eval_samples_per_second": 824.574, | |
| "eval_steps_per_second": 51.538, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 44.75, | |
| "eval_loss": 1.9059538841247559, | |
| "eval_runtime": 49.9186, | |
| "eval_samples_per_second": 823.38, | |
| "eval_steps_per_second": 51.464, | |
| "step": 2184000 | |
| }, | |
| { | |
| "epoch": 44.91, | |
| "learning_rate": 3.5533333333333334e-08, | |
| "loss": 2.0316, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 44.91, | |
| "eval_loss": 1.8911948204040527, | |
| "eval_runtime": 47.2346, | |
| "eval_samples_per_second": 870.167, | |
| "eval_steps_per_second": 54.388, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 45.07, | |
| "eval_loss": 1.9013826847076416, | |
| "eval_runtime": 47.9929, | |
| "eval_samples_per_second": 856.419, | |
| "eval_steps_per_second": 53.529, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 45.24, | |
| "learning_rate": 3.28e-08, | |
| "loss": 2.0322, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 45.24, | |
| "eval_loss": 1.903083324432373, | |
| "eval_runtime": 47.6274, | |
| "eval_samples_per_second": 862.991, | |
| "eval_steps_per_second": 53.94, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 45.4, | |
| "eval_loss": 1.9086343050003052, | |
| "eval_runtime": 47.838, | |
| "eval_samples_per_second": 859.191, | |
| "eval_steps_per_second": 53.702, | |
| "step": 2216000 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "learning_rate": 3.0066666666666665e-08, | |
| "loss": 2.035, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "eval_loss": 1.9147051572799683, | |
| "eval_runtime": 47.9056, | |
| "eval_samples_per_second": 857.978, | |
| "eval_steps_per_second": 53.626, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 45.73, | |
| "eval_loss": 1.900397777557373, | |
| "eval_runtime": 48.7638, | |
| "eval_samples_per_second": 842.879, | |
| "eval_steps_per_second": 52.682, | |
| "step": 2232000 | |
| }, | |
| { | |
| "epoch": 45.89, | |
| "learning_rate": 2.7333333333333333e-08, | |
| "loss": 2.0431, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 45.89, | |
| "eval_loss": 1.9027053117752075, | |
| "eval_runtime": 47.5248, | |
| "eval_samples_per_second": 864.854, | |
| "eval_steps_per_second": 54.056, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 46.06, | |
| "eval_loss": 1.891597032546997, | |
| "eval_runtime": 48.2801, | |
| "eval_samples_per_second": 851.323, | |
| "eval_steps_per_second": 53.21, | |
| "step": 2248000 | |
| }, | |
| { | |
| "epoch": 46.22, | |
| "learning_rate": 2.46e-08, | |
| "loss": 2.0347, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 46.22, | |
| "eval_loss": 1.9048635959625244, | |
| "eval_runtime": 48.7746, | |
| "eval_samples_per_second": 842.693, | |
| "eval_steps_per_second": 52.671, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "eval_loss": 1.8972582817077637, | |
| "eval_runtime": 48.3007, | |
| "eval_samples_per_second": 850.96, | |
| "eval_steps_per_second": 53.188, | |
| "step": 2264000 | |
| }, | |
| { | |
| "epoch": 46.55, | |
| "learning_rate": 2.1866666666666667e-08, | |
| "loss": 2.0353, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 46.55, | |
| "eval_loss": 1.8931912183761597, | |
| "eval_runtime": 49.2437, | |
| "eval_samples_per_second": 834.665, | |
| "eval_steps_per_second": 52.169, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 46.71, | |
| "eval_loss": 1.912061333656311, | |
| "eval_runtime": 48.3695, | |
| "eval_samples_per_second": 849.75, | |
| "eval_steps_per_second": 53.112, | |
| "step": 2280000 | |
| }, | |
| { | |
| "epoch": 46.88, | |
| "learning_rate": 1.9133333333333333e-08, | |
| "loss": 2.0309, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 46.88, | |
| "eval_loss": 1.8972575664520264, | |
| "eval_runtime": 48.673, | |
| "eval_samples_per_second": 844.452, | |
| "eval_steps_per_second": 52.781, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 47.04, | |
| "eval_loss": 1.8985596895217896, | |
| "eval_runtime": 50.0454, | |
| "eval_samples_per_second": 821.294, | |
| "eval_steps_per_second": 51.333, | |
| "step": 2296000 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "learning_rate": 1.64e-08, | |
| "loss": 2.0359, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "eval_loss": 1.9202120304107666, | |
| "eval_runtime": 49.0939, | |
| "eval_samples_per_second": 837.212, | |
| "eval_steps_per_second": 52.328, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 47.37, | |
| "eval_loss": 1.8778069019317627, | |
| "eval_runtime": 48.2597, | |
| "eval_samples_per_second": 851.683, | |
| "eval_steps_per_second": 53.233, | |
| "step": 2312000 | |
| }, | |
| { | |
| "epoch": 47.53, | |
| "learning_rate": 1.3666666666666667e-08, | |
| "loss": 2.037, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 47.53, | |
| "eval_loss": 1.9136707782745361, | |
| "eval_runtime": 48.2191, | |
| "eval_samples_per_second": 852.401, | |
| "eval_steps_per_second": 53.278, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 47.7, | |
| "eval_loss": 1.9095231294631958, | |
| "eval_runtime": 49.9332, | |
| "eval_samples_per_second": 823.14, | |
| "eval_steps_per_second": 51.449, | |
| "step": 2328000 | |
| }, | |
| { | |
| "epoch": 47.86, | |
| "learning_rate": 1.0933333333333334e-08, | |
| "loss": 2.0306, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 47.86, | |
| "eval_loss": 1.903990626335144, | |
| "eval_runtime": 47.1892, | |
| "eval_samples_per_second": 871.005, | |
| "eval_steps_per_second": 54.44, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_loss": 1.8931529521942139, | |
| "eval_runtime": 47.2904, | |
| "eval_samples_per_second": 869.141, | |
| "eval_steps_per_second": 54.324, | |
| "step": 2344000 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 8.2e-09, | |
| "loss": 2.0342, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "eval_loss": 1.9151569604873657, | |
| "eval_runtime": 50.819, | |
| "eval_samples_per_second": 808.791, | |
| "eval_steps_per_second": 50.552, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 48.35, | |
| "eval_loss": 1.9058945178985596, | |
| "eval_runtime": 47.9047, | |
| "eval_samples_per_second": 857.995, | |
| "eval_steps_per_second": 53.627, | |
| "step": 2360000 | |
| }, | |
| { | |
| "epoch": 48.52, | |
| "learning_rate": 5.466666666666667e-09, | |
| "loss": 2.0457, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 48.52, | |
| "eval_loss": 1.8844729661941528, | |
| "eval_runtime": 47.9335, | |
| "eval_samples_per_second": 857.479, | |
| "eval_steps_per_second": 53.595, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 48.68, | |
| "eval_loss": 1.903971791267395, | |
| "eval_runtime": 49.7448, | |
| "eval_samples_per_second": 826.257, | |
| "eval_steps_per_second": 51.644, | |
| "step": 2376000 | |
| }, | |
| { | |
| "epoch": 48.84, | |
| "learning_rate": 2.7333333333333334e-09, | |
| "loss": 2.0349, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 48.84, | |
| "eval_loss": 1.9000164270401, | |
| "eval_runtime": 48.2699, | |
| "eval_samples_per_second": 851.504, | |
| "eval_steps_per_second": 53.222, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "eval_loss": 1.905893087387085, | |
| "eval_runtime": 48.9997, | |
| "eval_samples_per_second": 838.822, | |
| "eval_steps_per_second": 52.429, | |
| "step": 2392000 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "learning_rate": 0.0, | |
| "loss": 2.0322, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "eval_loss": 1.8925877809524536, | |
| "eval_runtime": 49.4417, | |
| "eval_samples_per_second": 831.323, | |
| "eval_steps_per_second": 51.96, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "step": 2400000, | |
| "total_flos": 7.48474678802484e+17, | |
| "train_loss": 2.0531104736328123, | |
| "train_runtime": 167230.1572, | |
| "train_samples_per_second": 229.624, | |
| "train_steps_per_second": 14.351 | |
| } | |
| ], | |
| "logging_steps": 16000, | |
| "max_steps": 2400000, | |
| "num_train_epochs": 50, | |
| "save_steps": 32000, | |
| "total_flos": 7.48474678802484e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |