| { | |
| "best_metric": 1.8842545747756958, | |
| "best_model_checkpoint": "./model_tweets_2020_Q1_90_2/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": 44.4512, | |
| "eval_samples_per_second": 924.655, | |
| "eval_steps_per_second": 57.794, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.0726666666666665e-07, | |
| "loss": 2.4394, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 2.155681610107422, | |
| "eval_runtime": 44.6165, | |
| "eval_samples_per_second": 921.229, | |
| "eval_steps_per_second": 57.58, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 2.0965232849121094, | |
| "eval_runtime": 44.4096, | |
| "eval_samples_per_second": 925.521, | |
| "eval_steps_per_second": 57.848, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.0453333333333336e-07, | |
| "loss": 2.2403, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.063685894012451, | |
| "eval_runtime": 44.7424, | |
| "eval_samples_per_second": 918.637, | |
| "eval_steps_per_second": 57.418, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 2.062025308609009, | |
| "eval_runtime": 45.5911, | |
| "eval_samples_per_second": 901.535, | |
| "eval_steps_per_second": 56.349, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.018e-07, | |
| "loss": 2.1859, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 2.0426833629608154, | |
| "eval_runtime": 44.8823, | |
| "eval_samples_per_second": 915.773, | |
| "eval_steps_per_second": 57.239, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.044032335281372, | |
| "eval_runtime": 45.1969, | |
| "eval_samples_per_second": 909.398, | |
| "eval_steps_per_second": 56.84, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.9906666666666667e-07, | |
| "loss": 2.1472, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 2.017690420150757, | |
| "eval_runtime": 44.7902, | |
| "eval_samples_per_second": 917.655, | |
| "eval_steps_per_second": 57.356, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.9980425834655762, | |
| "eval_runtime": 45.9383, | |
| "eval_samples_per_second": 894.721, | |
| "eval_steps_per_second": 55.923, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3.963333333333333e-07, | |
| "loss": 2.1334, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 2.0021114349365234, | |
| "eval_runtime": 45.2262, | |
| "eval_samples_per_second": 908.81, | |
| "eval_steps_per_second": 56.803, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 1.9963111877441406, | |
| "eval_runtime": 45.3678, | |
| "eval_samples_per_second": 905.973, | |
| "eval_steps_per_second": 56.626, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.936e-07, | |
| "loss": 2.1271, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 1.9917570352554321, | |
| "eval_runtime": 45.3467, | |
| "eval_samples_per_second": 906.395, | |
| "eval_steps_per_second": 56.652, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.988930344581604, | |
| "eval_runtime": 44.5535, | |
| "eval_samples_per_second": 922.532, | |
| "eval_steps_per_second": 57.661, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.908666666666667e-07, | |
| "loss": 2.1065, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 1.9688993692398071, | |
| "eval_runtime": 44.9183, | |
| "eval_samples_per_second": 915.039, | |
| "eval_steps_per_second": 57.193, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 1.991935133934021, | |
| "eval_runtime": 44.922, | |
| "eval_samples_per_second": 914.964, | |
| "eval_steps_per_second": 57.188, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.8813333333333334e-07, | |
| "loss": 2.105, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 1.9705941677093506, | |
| "eval_runtime": 45.3654, | |
| "eval_samples_per_second": 906.021, | |
| "eval_steps_per_second": 56.629, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.9724736213684082, | |
| "eval_runtime": 44.6248, | |
| "eval_samples_per_second": 921.057, | |
| "eval_steps_per_second": 57.569, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.854e-07, | |
| "loss": 2.1033, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 2.000924825668335, | |
| "eval_runtime": 44.6809, | |
| "eval_samples_per_second": 919.901, | |
| "eval_steps_per_second": 57.497, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 1.9660991430282593, | |
| "eval_runtime": 45.3271, | |
| "eval_samples_per_second": 906.786, | |
| "eval_steps_per_second": 56.677, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.8266666666666665e-07, | |
| "loss": 2.0934, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 1.964065432548523, | |
| "eval_runtime": 45.3105, | |
| "eval_samples_per_second": 907.118, | |
| "eval_steps_per_second": 56.698, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 1.973306655883789, | |
| "eval_runtime": 45.0686, | |
| "eval_samples_per_second": 911.988, | |
| "eval_steps_per_second": 57.002, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.799333333333333e-07, | |
| "loss": 2.0899, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 1.9746649265289307, | |
| "eval_runtime": 45.3568, | |
| "eval_samples_per_second": 906.193, | |
| "eval_steps_per_second": 56.64, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 1.9442167282104492, | |
| "eval_runtime": 44.7788, | |
| "eval_samples_per_second": 917.889, | |
| "eval_steps_per_second": 57.371, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.772e-07, | |
| "loss": 2.0903, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_loss": 1.9585589170455933, | |
| "eval_runtime": 44.7775, | |
| "eval_samples_per_second": 917.915, | |
| "eval_steps_per_second": 57.373, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "eval_loss": 1.9585614204406738, | |
| "eval_runtime": 44.6141, | |
| "eval_samples_per_second": 921.278, | |
| "eval_steps_per_second": 57.583, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 3.7446666666666667e-07, | |
| "loss": 2.0842, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_loss": 1.9401671886444092, | |
| "eval_runtime": 45.384, | |
| "eval_samples_per_second": 905.65, | |
| "eval_steps_per_second": 56.606, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 1.9483397006988525, | |
| "eval_runtime": 44.7805, | |
| "eval_samples_per_second": 917.855, | |
| "eval_steps_per_second": 57.369, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 3.7173333333333333e-07, | |
| "loss": 2.0761, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "eval_loss": 1.9532350301742554, | |
| "eval_runtime": 44.8654, | |
| "eval_samples_per_second": 916.117, | |
| "eval_steps_per_second": 57.26, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 1.945618748664856, | |
| "eval_runtime": 46.2969, | |
| "eval_samples_per_second": 887.792, | |
| "eval_steps_per_second": 55.49, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.69e-07, | |
| "loss": 2.0799, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 1.9322354793548584, | |
| "eval_runtime": 44.8701, | |
| "eval_samples_per_second": 916.023, | |
| "eval_steps_per_second": 57.254, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "eval_loss": 1.9460111856460571, | |
| "eval_runtime": 46.0976, | |
| "eval_samples_per_second": 891.629, | |
| "eval_steps_per_second": 55.73, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 3.6626666666666664e-07, | |
| "loss": 2.0704, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "eval_loss": 1.9477649927139282, | |
| "eval_runtime": 46.6633, | |
| "eval_samples_per_second": 880.821, | |
| "eval_steps_per_second": 55.054, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 1.943530559539795, | |
| "eval_runtime": 44.6432, | |
| "eval_samples_per_second": 920.678, | |
| "eval_steps_per_second": 57.545, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 3.6353333333333335e-07, | |
| "loss": 2.0727, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_loss": 1.9356465339660645, | |
| "eval_runtime": 46.1985, | |
| "eval_samples_per_second": 889.682, | |
| "eval_steps_per_second": 55.608, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "eval_loss": 1.9543371200561523, | |
| "eval_runtime": 45.3342, | |
| "eval_samples_per_second": 906.645, | |
| "eval_steps_per_second": 56.668, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 3.608e-07, | |
| "loss": 2.073, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "eval_loss": 1.9541795253753662, | |
| "eval_runtime": 45.0744, | |
| "eval_samples_per_second": 911.871, | |
| "eval_steps_per_second": 56.995, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 1.9503259658813477, | |
| "eval_runtime": 45.4487, | |
| "eval_samples_per_second": 904.359, | |
| "eval_steps_per_second": 56.525, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 3.5806666666666666e-07, | |
| "loss": 2.0647, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "eval_loss": 1.9437284469604492, | |
| "eval_runtime": 45.8852, | |
| "eval_samples_per_second": 895.757, | |
| "eval_steps_per_second": 55.988, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_loss": 1.9450260400772095, | |
| "eval_runtime": 45.357, | |
| "eval_samples_per_second": 906.188, | |
| "eval_steps_per_second": 56.64, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 3.553333333333333e-07, | |
| "loss": 2.0668, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 1.9220808744430542, | |
| "eval_runtime": 45.2729, | |
| "eval_samples_per_second": 907.873, | |
| "eval_steps_per_second": 56.745, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "eval_loss": 1.927699089050293, | |
| "eval_runtime": 45.6224, | |
| "eval_samples_per_second": 900.917, | |
| "eval_steps_per_second": 56.31, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 3.5259999999999997e-07, | |
| "loss": 2.0695, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "eval_loss": 1.935697317123413, | |
| "eval_runtime": 45.5283, | |
| "eval_samples_per_second": 902.779, | |
| "eval_steps_per_second": 56.426, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "eval_loss": 1.924439549446106, | |
| "eval_runtime": 44.8085, | |
| "eval_samples_per_second": 917.282, | |
| "eval_steps_per_second": 57.333, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 3.498666666666667e-07, | |
| "loss": 2.0652, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_loss": 1.938655138015747, | |
| "eval_runtime": 45.4835, | |
| "eval_samples_per_second": 903.669, | |
| "eval_steps_per_second": 56.482, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "eval_loss": 1.9354636669158936, | |
| "eval_runtime": 44.716, | |
| "eval_samples_per_second": 919.178, | |
| "eval_steps_per_second": 57.451, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 3.4713333333333333e-07, | |
| "loss": 2.0607, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "eval_loss": 1.9389930963516235, | |
| "eval_runtime": 44.6813, | |
| "eval_samples_per_second": 919.893, | |
| "eval_steps_per_second": 57.496, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "eval_loss": 1.9358594417572021, | |
| "eval_runtime": 45.4077, | |
| "eval_samples_per_second": 905.177, | |
| "eval_steps_per_second": 56.576, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 3.444e-07, | |
| "loss": 2.0707, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "eval_loss": 1.9393250942230225, | |
| "eval_runtime": 45.4398, | |
| "eval_samples_per_second": 904.537, | |
| "eval_steps_per_second": 56.536, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "eval_loss": 1.9217476844787598, | |
| "eval_runtime": 46.1561, | |
| "eval_samples_per_second": 890.5, | |
| "eval_steps_per_second": 55.659, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 3.416666666666667e-07, | |
| "loss": 2.0621, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "eval_loss": 1.9284311532974243, | |
| "eval_runtime": 46.4848, | |
| "eval_samples_per_second": 884.203, | |
| "eval_steps_per_second": 55.265, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "eval_loss": 1.9383472204208374, | |
| "eval_runtime": 46.1371, | |
| "eval_samples_per_second": 890.867, | |
| "eval_steps_per_second": 55.682, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 3.3893333333333335e-07, | |
| "loss": 2.0643, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "eval_loss": 1.922420859336853, | |
| "eval_runtime": 45.1714, | |
| "eval_samples_per_second": 909.911, | |
| "eval_steps_per_second": 56.872, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_loss": 1.928429365158081, | |
| "eval_runtime": 45.6103, | |
| "eval_samples_per_second": 901.157, | |
| "eval_steps_per_second": 56.325, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 3.3619999999999995e-07, | |
| "loss": 2.0498, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "eval_loss": 1.9399133920669556, | |
| "eval_runtime": 45.3159, | |
| "eval_samples_per_second": 907.01, | |
| "eval_steps_per_second": 56.691, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "eval_loss": 1.9427006244659424, | |
| "eval_runtime": 45.0449, | |
| "eval_samples_per_second": 912.468, | |
| "eval_steps_per_second": 57.032, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 3.3346666666666666e-07, | |
| "loss": 2.0689, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "eval_loss": 1.9351186752319336, | |
| "eval_runtime": 46.3442, | |
| "eval_samples_per_second": 886.886, | |
| "eval_steps_per_second": 55.433, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "eval_loss": 1.9312766790390015, | |
| "eval_runtime": 45.0453, | |
| "eval_samples_per_second": 912.46, | |
| "eval_steps_per_second": 57.032, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 3.307333333333333e-07, | |
| "loss": 2.0511, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "eval_loss": 1.9392344951629639, | |
| "eval_runtime": 45.0174, | |
| "eval_samples_per_second": 913.025, | |
| "eval_steps_per_second": 57.067, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 1.9278026819229126, | |
| "eval_runtime": 44.8506, | |
| "eval_samples_per_second": 916.42, | |
| "eval_steps_per_second": 57.279, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 3.28e-07, | |
| "loss": 2.0664, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "eval_loss": 1.9384809732437134, | |
| "eval_runtime": 45.34, | |
| "eval_samples_per_second": 906.529, | |
| "eval_steps_per_second": 56.661, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.9471704959869385, | |
| "eval_runtime": 44.7273, | |
| "eval_samples_per_second": 918.947, | |
| "eval_steps_per_second": 57.437, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 3.252666666666667e-07, | |
| "loss": 2.0565, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "eval_loss": 1.937743902206421, | |
| "eval_runtime": 45.3104, | |
| "eval_samples_per_second": 907.121, | |
| "eval_steps_per_second": 56.698, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "eval_loss": 1.9480650424957275, | |
| "eval_runtime": 45.4075, | |
| "eval_samples_per_second": 905.182, | |
| "eval_steps_per_second": 56.577, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 3.2253333333333334e-07, | |
| "loss": 2.0566, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "eval_loss": 1.9453697204589844, | |
| "eval_runtime": 44.898, | |
| "eval_samples_per_second": 915.452, | |
| "eval_steps_per_second": 57.219, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "eval_loss": 1.9244284629821777, | |
| "eval_runtime": 45.3186, | |
| "eval_samples_per_second": 906.957, | |
| "eval_steps_per_second": 56.688, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 3.198e-07, | |
| "loss": 2.0523, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "eval_loss": 1.935764193534851, | |
| "eval_runtime": 44.869, | |
| "eval_samples_per_second": 916.045, | |
| "eval_steps_per_second": 57.256, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_loss": 1.9176356792449951, | |
| "eval_runtime": 45.328, | |
| "eval_samples_per_second": 906.768, | |
| "eval_steps_per_second": 56.676, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 3.1706666666666665e-07, | |
| "loss": 2.0554, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "eval_loss": 1.9284305572509766, | |
| "eval_runtime": 45.5519, | |
| "eval_samples_per_second": 902.311, | |
| "eval_steps_per_second": 56.397, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "eval_loss": 1.9287078380584717, | |
| "eval_runtime": 44.7567, | |
| "eval_samples_per_second": 918.343, | |
| "eval_steps_per_second": 57.399, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 3.1433333333333336e-07, | |
| "loss": 2.0485, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "eval_loss": 1.923736810684204, | |
| "eval_runtime": 44.866, | |
| "eval_samples_per_second": 916.107, | |
| "eval_steps_per_second": 57.259, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "eval_loss": 1.920929193496704, | |
| "eval_runtime": 44.798, | |
| "eval_samples_per_second": 917.497, | |
| "eval_steps_per_second": 57.346, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 3.116e-07, | |
| "loss": 2.0485, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "eval_loss": 1.9261997938156128, | |
| "eval_runtime": 44.83, | |
| "eval_samples_per_second": 916.842, | |
| "eval_steps_per_second": 57.305, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "eval_loss": 1.9207805395126343, | |
| "eval_runtime": 44.7975, | |
| "eval_samples_per_second": 917.507, | |
| "eval_steps_per_second": 57.347, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 3.0886666666666667e-07, | |
| "loss": 2.0542, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "eval_loss": 1.9320107698440552, | |
| "eval_runtime": 44.9881, | |
| "eval_samples_per_second": 913.619, | |
| "eval_steps_per_second": 57.104, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "eval_loss": 1.9076824188232422, | |
| "eval_runtime": 44.823, | |
| "eval_samples_per_second": 916.985, | |
| "eval_steps_per_second": 57.314, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 3.061333333333333e-07, | |
| "loss": 2.0527, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "eval_loss": 1.9248530864715576, | |
| "eval_runtime": 45.2012, | |
| "eval_samples_per_second": 909.312, | |
| "eval_steps_per_second": 56.835, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "eval_loss": 1.919195532798767, | |
| "eval_runtime": 44.95, | |
| "eval_samples_per_second": 914.393, | |
| "eval_steps_per_second": 57.152, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 3.034e-07, | |
| "loss": 2.0606, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "eval_loss": 1.9151537418365479, | |
| "eval_runtime": 44.9136, | |
| "eval_samples_per_second": 915.135, | |
| "eval_steps_per_second": 57.199, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "eval_loss": 1.9194060564041138, | |
| "eval_runtime": 45.7535, | |
| "eval_samples_per_second": 898.337, | |
| "eval_steps_per_second": 56.149, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 3.0066666666666663e-07, | |
| "loss": 2.0542, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "eval_loss": 1.919755458831787, | |
| "eval_runtime": 45.4065, | |
| "eval_samples_per_second": 905.201, | |
| "eval_steps_per_second": 56.578, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "eval_loss": 1.9134645462036133, | |
| "eval_runtime": 45.523, | |
| "eval_samples_per_second": 902.884, | |
| "eval_steps_per_second": 56.433, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 2.9793333333333334e-07, | |
| "loss": 2.0593, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "eval_loss": 1.919248342514038, | |
| "eval_runtime": 45.5047, | |
| "eval_samples_per_second": 903.248, | |
| "eval_steps_per_second": 56.456, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_loss": 1.9256792068481445, | |
| "eval_runtime": 45.5171, | |
| "eval_samples_per_second": 903.002, | |
| "eval_steps_per_second": 56.44, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 2.952e-07, | |
| "loss": 2.0467, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "eval_loss": 1.9134962558746338, | |
| "eval_runtime": 44.9903, | |
| "eval_samples_per_second": 913.574, | |
| "eval_steps_per_second": 57.101, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "eval_loss": 1.8994532823562622, | |
| "eval_runtime": 45.5632, | |
| "eval_samples_per_second": 902.087, | |
| "eval_steps_per_second": 56.383, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 2.9246666666666665e-07, | |
| "loss": 2.0535, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "eval_loss": 1.9305521249771118, | |
| "eval_runtime": 45.4839, | |
| "eval_samples_per_second": 903.66, | |
| "eval_steps_per_second": 56.481, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "eval_loss": 1.927839994430542, | |
| "eval_runtime": 44.9073, | |
| "eval_samples_per_second": 915.264, | |
| "eval_steps_per_second": 57.207, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 2.897333333333333e-07, | |
| "loss": 2.0559, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "eval_loss": 1.9136629104614258, | |
| "eval_runtime": 45.1604, | |
| "eval_samples_per_second": 910.133, | |
| "eval_steps_per_second": 56.886, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "eval_loss": 1.9164540767669678, | |
| "eval_runtime": 44.9974, | |
| "eval_samples_per_second": 913.431, | |
| "eval_steps_per_second": 57.092, | |
| "step": 712000 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 2.8699999999999996e-07, | |
| "loss": 2.0544, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "eval_loss": 1.921919345855713, | |
| "eval_runtime": 45.8685, | |
| "eval_samples_per_second": 896.084, | |
| "eval_steps_per_second": 56.008, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_loss": 1.9200448989868164, | |
| "eval_runtime": 45.5436, | |
| "eval_samples_per_second": 902.476, | |
| "eval_steps_per_second": 56.407, | |
| "step": 728000 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 2.8426666666666667e-07, | |
| "loss": 2.0493, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "eval_loss": 1.924161434173584, | |
| "eval_runtime": 44.985, | |
| "eval_samples_per_second": 913.683, | |
| "eval_steps_per_second": 57.108, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "eval_loss": 1.9263921976089478, | |
| "eval_runtime": 44.8608, | |
| "eval_samples_per_second": 916.211, | |
| "eval_steps_per_second": 57.266, | |
| "step": 744000 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 2.815333333333333e-07, | |
| "loss": 2.0538, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "eval_loss": 1.9333122968673706, | |
| "eval_runtime": 44.8991, | |
| "eval_samples_per_second": 915.431, | |
| "eval_steps_per_second": 57.217, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "eval_loss": 1.912643551826477, | |
| "eval_runtime": 46.091, | |
| "eval_samples_per_second": 891.758, | |
| "eval_steps_per_second": 55.738, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 2.7880000000000003e-07, | |
| "loss": 2.0457, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "eval_loss": 1.9022926092147827, | |
| "eval_runtime": 45.2957, | |
| "eval_samples_per_second": 907.416, | |
| "eval_steps_per_second": 56.716, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "eval_loss": 1.9153952598571777, | |
| "eval_runtime": 44.9942, | |
| "eval_samples_per_second": 913.495, | |
| "eval_steps_per_second": 57.096, | |
| "step": 776000 | |
| }, | |
| { | |
| "epoch": 16.06, | |
| "learning_rate": 2.7606666666666664e-07, | |
| "loss": 2.0436, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 16.06, | |
| "eval_loss": 1.894668698310852, | |
| "eval_runtime": 45.1573, | |
| "eval_samples_per_second": 910.196, | |
| "eval_steps_per_second": 56.89, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "eval_loss": 1.9197973012924194, | |
| "eval_runtime": 45.5499, | |
| "eval_samples_per_second": 902.351, | |
| "eval_steps_per_second": 56.4, | |
| "step": 792000 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 2.733333333333333e-07, | |
| "loss": 2.0527, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "eval_loss": 1.912539005279541, | |
| "eval_runtime": 45.0868, | |
| "eval_samples_per_second": 911.619, | |
| "eval_steps_per_second": 56.979, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 1.9129201173782349, | |
| "eval_runtime": 45.0169, | |
| "eval_samples_per_second": 913.036, | |
| "eval_steps_per_second": 57.068, | |
| "step": 808000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 2.706e-07, | |
| "loss": 2.0484, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "eval_loss": 1.930238127708435, | |
| "eval_runtime": 45.0627, | |
| "eval_samples_per_second": 912.107, | |
| "eval_steps_per_second": 57.009, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 16.88, | |
| "eval_loss": 1.915164589881897, | |
| "eval_runtime": 44.8156, | |
| "eval_samples_per_second": 917.137, | |
| "eval_steps_per_second": 57.324, | |
| "step": 824000 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 2.6786666666666666e-07, | |
| "loss": 2.0535, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "eval_loss": 1.9222667217254639, | |
| "eval_runtime": 45.4436, | |
| "eval_samples_per_second": 904.463, | |
| "eval_steps_per_second": 56.532, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "eval_loss": 1.9195363521575928, | |
| "eval_runtime": 45.1269, | |
| "eval_samples_per_second": 910.809, | |
| "eval_steps_per_second": 56.928, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 2.651333333333333e-07, | |
| "loss": 2.0516, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "eval_loss": 1.9071532487869263, | |
| "eval_runtime": 45.5538, | |
| "eval_samples_per_second": 902.274, | |
| "eval_steps_per_second": 56.395, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "eval_loss": 1.9210063219070435, | |
| "eval_runtime": 45.0127, | |
| "eval_samples_per_second": 913.12, | |
| "eval_steps_per_second": 57.073, | |
| "step": 856000 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 2.624e-07, | |
| "loss": 2.0546, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "eval_loss": 1.9014463424682617, | |
| "eval_runtime": 45.0217, | |
| "eval_samples_per_second": 912.937, | |
| "eval_steps_per_second": 57.061, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "eval_loss": 1.9129884243011475, | |
| "eval_runtime": 45.0333, | |
| "eval_samples_per_second": 912.702, | |
| "eval_steps_per_second": 57.047, | |
| "step": 872000 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 2.596666666666667e-07, | |
| "loss": 2.0439, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "eval_loss": 1.9064290523529053, | |
| "eval_runtime": 45.5491, | |
| "eval_samples_per_second": 902.367, | |
| "eval_steps_per_second": 56.401, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "eval_loss": 1.9166321754455566, | |
| "eval_runtime": 45.3148, | |
| "eval_samples_per_second": 907.032, | |
| "eval_steps_per_second": 56.692, | |
| "step": 888000 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 2.5693333333333333e-07, | |
| "loss": 2.0391, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "eval_loss": 1.930993676185608, | |
| "eval_runtime": 45.1221, | |
| "eval_samples_per_second": 910.905, | |
| "eval_steps_per_second": 56.934, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "eval_loss": 1.9064345359802246, | |
| "eval_runtime": 44.9731, | |
| "eval_samples_per_second": 913.923, | |
| "eval_steps_per_second": 57.123, | |
| "step": 904000 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 2.542e-07, | |
| "loss": 2.0568, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "eval_loss": 1.9106640815734863, | |
| "eval_runtime": 45.255, | |
| "eval_samples_per_second": 908.23, | |
| "eval_steps_per_second": 56.767, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "eval_loss": 1.931686520576477, | |
| "eval_runtime": 44.9728, | |
| "eval_samples_per_second": 913.931, | |
| "eval_steps_per_second": 57.123, | |
| "step": 920000 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 2.5146666666666664e-07, | |
| "loss": 2.047, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "eval_loss": 1.9234881401062012, | |
| "eval_runtime": 46.2033, | |
| "eval_samples_per_second": 889.591, | |
| "eval_steps_per_second": 55.602, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 19.18, | |
| "eval_loss": 1.917264699935913, | |
| "eval_runtime": 45.8963, | |
| "eval_samples_per_second": 895.541, | |
| "eval_steps_per_second": 55.974, | |
| "step": 936000 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 2.4873333333333335e-07, | |
| "loss": 2.0431, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "eval_loss": 1.8946489095687866, | |
| "eval_runtime": 45.1842, | |
| "eval_samples_per_second": 909.654, | |
| "eval_steps_per_second": 56.856, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "eval_loss": 1.9247366189956665, | |
| "eval_runtime": 45.5385, | |
| "eval_samples_per_second": 902.578, | |
| "eval_steps_per_second": 56.414, | |
| "step": 952000 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "learning_rate": 2.46e-07, | |
| "loss": 2.0444, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "eval_loss": 1.9105546474456787, | |
| "eval_runtime": 45.0193, | |
| "eval_samples_per_second": 912.987, | |
| "eval_steps_per_second": 57.064, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 19.83, | |
| "eval_loss": 1.9022789001464844, | |
| "eval_runtime": 45.0679, | |
| "eval_samples_per_second": 912.002, | |
| "eval_steps_per_second": 57.003, | |
| "step": 968000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.4326666666666666e-07, | |
| "loss": 2.0465, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.9196343421936035, | |
| "eval_runtime": 44.9372, | |
| "eval_samples_per_second": 914.655, | |
| "eval_steps_per_second": 57.169, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "eval_loss": 1.9111627340316772, | |
| "eval_runtime": 45.8537, | |
| "eval_samples_per_second": 896.372, | |
| "eval_steps_per_second": 56.026, | |
| "step": 984000 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 2.405333333333333e-07, | |
| "loss": 2.0454, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "eval_loss": 1.9045841693878174, | |
| "eval_runtime": 45.0217, | |
| "eval_samples_per_second": 912.937, | |
| "eval_steps_per_second": 57.061, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 20.49, | |
| "eval_loss": 1.9031916856765747, | |
| "eval_runtime": 44.8617, | |
| "eval_samples_per_second": 916.194, | |
| "eval_steps_per_second": 57.265, | |
| "step": 1000000 | |
| }, | |
| { | |
| "epoch": 20.65, | |
| "learning_rate": 2.3779999999999997e-07, | |
| "loss": 2.04, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 20.65, | |
| "eval_loss": 1.9129735231399536, | |
| "eval_runtime": 45.7328, | |
| "eval_samples_per_second": 898.742, | |
| "eval_steps_per_second": 56.174, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 20.82, | |
| "eval_loss": 1.922319769859314, | |
| "eval_runtime": 45.7137, | |
| "eval_samples_per_second": 899.117, | |
| "eval_steps_per_second": 56.198, | |
| "step": 1016000 | |
| }, | |
| { | |
| "epoch": 20.98, | |
| "learning_rate": 2.3506666666666668e-07, | |
| "loss": 2.0406, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 20.98, | |
| "eval_loss": 1.9261207580566406, | |
| "eval_runtime": 45.2159, | |
| "eval_samples_per_second": 909.017, | |
| "eval_steps_per_second": 56.816, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 21.14, | |
| "eval_loss": 1.9014304876327515, | |
| "eval_runtime": 45.6968, | |
| "eval_samples_per_second": 899.451, | |
| "eval_steps_per_second": 56.218, | |
| "step": 1032000 | |
| }, | |
| { | |
| "epoch": 21.31, | |
| "learning_rate": 2.3233333333333334e-07, | |
| "loss": 2.0401, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 21.31, | |
| "eval_loss": 1.905246615409851, | |
| "eval_runtime": 45.6693, | |
| "eval_samples_per_second": 899.993, | |
| "eval_steps_per_second": 56.252, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "eval_loss": 1.9004502296447754, | |
| "eval_runtime": 45.6183, | |
| "eval_samples_per_second": 900.998, | |
| "eval_steps_per_second": 56.315, | |
| "step": 1048000 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 2.2960000000000002e-07, | |
| "loss": 2.044, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "eval_loss": 1.9044198989868164, | |
| "eval_runtime": 45.8662, | |
| "eval_samples_per_second": 896.128, | |
| "eval_steps_per_second": 56.011, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "eval_loss": 1.9169893264770508, | |
| "eval_runtime": 45.213, | |
| "eval_samples_per_second": 909.076, | |
| "eval_steps_per_second": 56.82, | |
| "step": 1064000 | |
| }, | |
| { | |
| "epoch": 21.96, | |
| "learning_rate": 2.2686666666666667e-07, | |
| "loss": 2.0401, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 21.96, | |
| "eval_loss": 1.9103343486785889, | |
| "eval_runtime": 45.7608, | |
| "eval_samples_per_second": 898.192, | |
| "eval_steps_per_second": 56.14, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "eval_loss": 1.8970900774002075, | |
| "eval_runtime": 45.1522, | |
| "eval_samples_per_second": 910.298, | |
| "eval_steps_per_second": 56.896, | |
| "step": 1080000 | |
| }, | |
| { | |
| "epoch": 22.29, | |
| "learning_rate": 2.2413333333333333e-07, | |
| "loss": 2.0458, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 22.29, | |
| "eval_loss": 1.9256750345230103, | |
| "eval_runtime": 45.4505, | |
| "eval_samples_per_second": 904.324, | |
| "eval_steps_per_second": 56.523, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 22.45, | |
| "eval_loss": 1.9029202461242676, | |
| "eval_runtime": 45.9975, | |
| "eval_samples_per_second": 893.57, | |
| "eval_steps_per_second": 55.851, | |
| "step": 1096000 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 2.214e-07, | |
| "loss": 2.0414, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "eval_loss": 1.915024995803833, | |
| "eval_runtime": 45.2783, | |
| "eval_samples_per_second": 907.764, | |
| "eval_steps_per_second": 56.738, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "eval_loss": 1.9123761653900146, | |
| "eval_runtime": 45.0133, | |
| "eval_samples_per_second": 913.107, | |
| "eval_steps_per_second": 57.072, | |
| "step": 1112000 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 2.1866666666666667e-07, | |
| "loss": 2.0419, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "eval_loss": 1.9029767513275146, | |
| "eval_runtime": 45.0706, | |
| "eval_samples_per_second": 911.947, | |
| "eval_steps_per_second": 56.999, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "eval_loss": 1.9144717454910278, | |
| "eval_runtime": 45.5951, | |
| "eval_samples_per_second": 901.457, | |
| "eval_steps_per_second": 56.344, | |
| "step": 1128000 | |
| }, | |
| { | |
| "epoch": 23.27, | |
| "learning_rate": 2.1593333333333332e-07, | |
| "loss": 2.0415, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 23.27, | |
| "eval_loss": 1.9132155179977417, | |
| "eval_runtime": 44.6846, | |
| "eval_samples_per_second": 919.824, | |
| "eval_steps_per_second": 57.492, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "eval_loss": 1.9053661823272705, | |
| "eval_runtime": 45.6412, | |
| "eval_samples_per_second": 900.547, | |
| "eval_steps_per_second": 56.287, | |
| "step": 1144000 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 2.132e-07, | |
| "loss": 2.0394, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "eval_loss": 1.915486216545105, | |
| "eval_runtime": 46.1174, | |
| "eval_samples_per_second": 891.246, | |
| "eval_steps_per_second": 55.706, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 23.77, | |
| "eval_loss": 1.9147080183029175, | |
| "eval_runtime": 44.9401, | |
| "eval_samples_per_second": 914.595, | |
| "eval_steps_per_second": 57.165, | |
| "step": 1160000 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "learning_rate": 2.1046666666666666e-07, | |
| "loss": 2.0414, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "eval_loss": 1.9130446910858154, | |
| "eval_runtime": 44.5878, | |
| "eval_samples_per_second": 921.822, | |
| "eval_steps_per_second": 57.617, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 24.09, | |
| "eval_loss": 1.9002370834350586, | |
| "eval_runtime": 45.5775, | |
| "eval_samples_per_second": 901.805, | |
| "eval_steps_per_second": 56.366, | |
| "step": 1176000 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 2.0773333333333334e-07, | |
| "loss": 2.036, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "eval_loss": 1.899147391319275, | |
| "eval_runtime": 45.1106, | |
| "eval_samples_per_second": 911.138, | |
| "eval_steps_per_second": 56.949, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "eval_loss": 1.9202589988708496, | |
| "eval_runtime": 44.9471, | |
| "eval_samples_per_second": 914.452, | |
| "eval_steps_per_second": 57.156, | |
| "step": 1192000 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "learning_rate": 2.05e-07, | |
| "loss": 2.0393, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "eval_loss": 1.9327338933944702, | |
| "eval_runtime": 45.225, | |
| "eval_samples_per_second": 908.834, | |
| "eval_steps_per_second": 56.805, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "eval_loss": 1.9098608493804932, | |
| "eval_runtime": 44.9604, | |
| "eval_samples_per_second": 914.182, | |
| "eval_steps_per_second": 57.139, | |
| "step": 1208000 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 2.0226666666666668e-07, | |
| "loss": 2.0375, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "eval_loss": 1.9097236394882202, | |
| "eval_runtime": 45.2358, | |
| "eval_samples_per_second": 908.617, | |
| "eval_steps_per_second": 56.791, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 25.08, | |
| "eval_loss": 1.900553584098816, | |
| "eval_runtime": 45.0389, | |
| "eval_samples_per_second": 912.589, | |
| "eval_steps_per_second": 57.04, | |
| "step": 1224000 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "learning_rate": 1.9953333333333333e-07, | |
| "loss": 2.0384, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "eval_loss": 1.9062752723693848, | |
| "eval_runtime": 45.0968, | |
| "eval_samples_per_second": 911.418, | |
| "eval_steps_per_second": 56.966, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 25.41, | |
| "eval_loss": 1.9056702852249146, | |
| "eval_runtime": 44.7493, | |
| "eval_samples_per_second": 918.496, | |
| "eval_steps_per_second": 57.409, | |
| "step": 1240000 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 1.968e-07, | |
| "loss": 2.0392, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "eval_loss": 1.9037301540374756, | |
| "eval_runtime": 45.476, | |
| "eval_samples_per_second": 903.817, | |
| "eval_steps_per_second": 56.491, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 25.73, | |
| "eval_loss": 1.9013148546218872, | |
| "eval_runtime": 45.2771, | |
| "eval_samples_per_second": 907.789, | |
| "eval_steps_per_second": 56.74, | |
| "step": 1256000 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "learning_rate": 1.9406666666666667e-07, | |
| "loss": 2.0503, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "eval_loss": 1.903662085533142, | |
| "eval_runtime": 45.1825, | |
| "eval_samples_per_second": 909.689, | |
| "eval_steps_per_second": 56.858, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 26.06, | |
| "eval_loss": 1.904166579246521, | |
| "eval_runtime": 44.9558, | |
| "eval_samples_per_second": 914.275, | |
| "eval_steps_per_second": 57.145, | |
| "step": 1272000 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 1.9133333333333333e-07, | |
| "loss": 2.0418, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "eval_loss": 1.896562933921814, | |
| "eval_runtime": 44.9261, | |
| "eval_samples_per_second": 914.881, | |
| "eval_steps_per_second": 57.183, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "eval_loss": 1.9186903238296509, | |
| "eval_runtime": 45.6851, | |
| "eval_samples_per_second": 899.681, | |
| "eval_steps_per_second": 56.233, | |
| "step": 1288000 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 1.886e-07, | |
| "loss": 2.0416, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "eval_loss": 1.9097530841827393, | |
| "eval_runtime": 45.1674, | |
| "eval_samples_per_second": 909.992, | |
| "eval_steps_per_second": 56.877, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "eval_loss": 1.9153447151184082, | |
| "eval_runtime": 45.0006, | |
| "eval_samples_per_second": 913.366, | |
| "eval_steps_per_second": 57.088, | |
| "step": 1304000 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.8586666666666666e-07, | |
| "loss": 2.0396, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "eval_loss": 1.9163771867752075, | |
| "eval_runtime": 45.1212, | |
| "eval_samples_per_second": 910.924, | |
| "eval_steps_per_second": 56.936, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "eval_loss": 1.886674404144287, | |
| "eval_runtime": 45.5153, | |
| "eval_samples_per_second": 903.038, | |
| "eval_steps_per_second": 56.443, | |
| "step": 1320000 | |
| }, | |
| { | |
| "epoch": 27.21, | |
| "learning_rate": 1.8313333333333332e-07, | |
| "loss": 2.0397, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 27.21, | |
| "eval_loss": 1.8968819379806519, | |
| "eval_runtime": 45.2936, | |
| "eval_samples_per_second": 907.458, | |
| "eval_steps_per_second": 56.719, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 27.37, | |
| "eval_loss": 1.915518879890442, | |
| "eval_runtime": 45.0557, | |
| "eval_samples_per_second": 912.249, | |
| "eval_steps_per_second": 57.018, | |
| "step": 1336000 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 1.804e-07, | |
| "loss": 2.0442, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "eval_loss": 1.9004348516464233, | |
| "eval_runtime": 45.9864, | |
| "eval_samples_per_second": 893.785, | |
| "eval_steps_per_second": 55.864, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 27.7, | |
| "eval_loss": 1.9026644229888916, | |
| "eval_runtime": 45.0271, | |
| "eval_samples_per_second": 912.829, | |
| "eval_steps_per_second": 57.055, | |
| "step": 1352000 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "learning_rate": 1.7766666666666666e-07, | |
| "loss": 2.0332, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "eval_loss": 1.9095487594604492, | |
| "eval_runtime": 45.6627, | |
| "eval_samples_per_second": 900.123, | |
| "eval_steps_per_second": 56.26, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "eval_loss": 1.9133695363998413, | |
| "eval_runtime": 45.1776, | |
| "eval_samples_per_second": 909.786, | |
| "eval_steps_per_second": 56.864, | |
| "step": 1368000 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 1.7493333333333334e-07, | |
| "loss": 2.0398, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "eval_loss": 1.9082748889923096, | |
| "eval_runtime": 45.8093, | |
| "eval_samples_per_second": 897.242, | |
| "eval_steps_per_second": 56.08, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "eval_loss": 1.9041306972503662, | |
| "eval_runtime": 45.2392, | |
| "eval_samples_per_second": 908.549, | |
| "eval_steps_per_second": 56.787, | |
| "step": 1384000 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 1.722e-07, | |
| "loss": 2.0387, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "eval_loss": 1.8979713916778564, | |
| "eval_runtime": 44.9884, | |
| "eval_samples_per_second": 913.613, | |
| "eval_steps_per_second": 57.104, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 28.68, | |
| "eval_loss": 1.9209250211715698, | |
| "eval_runtime": 44.9769, | |
| "eval_samples_per_second": 913.847, | |
| "eval_steps_per_second": 57.118, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 1.6946666666666668e-07, | |
| "loss": 2.0378, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "eval_loss": 1.896246314048767, | |
| "eval_runtime": 45.6981, | |
| "eval_samples_per_second": 899.425, | |
| "eval_steps_per_second": 56.217, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "eval_loss": 1.8981308937072754, | |
| "eval_runtime": 45.1348, | |
| "eval_samples_per_second": 910.65, | |
| "eval_steps_per_second": 56.918, | |
| "step": 1416000 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "learning_rate": 1.6673333333333333e-07, | |
| "loss": 2.0359, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "eval_loss": 1.9077860116958618, | |
| "eval_runtime": 45.2141, | |
| "eval_samples_per_second": 909.054, | |
| "eval_steps_per_second": 56.819, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "eval_loss": 1.8961683511734009, | |
| "eval_runtime": 45.0582, | |
| "eval_samples_per_second": 912.197, | |
| "eval_steps_per_second": 57.015, | |
| "step": 1432000 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "learning_rate": 1.64e-07, | |
| "loss": 2.0357, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "eval_loss": 1.8842545747756958, | |
| "eval_runtime": 45.1031, | |
| "eval_samples_per_second": 911.291, | |
| "eval_steps_per_second": 56.958, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "eval_loss": 1.9157154560089111, | |
| "eval_runtime": 46.1984, | |
| "eval_samples_per_second": 889.685, | |
| "eval_steps_per_second": 55.608, | |
| "step": 1448000 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "learning_rate": 1.6126666666666667e-07, | |
| "loss": 2.0367, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "eval_loss": 1.9277722835540771, | |
| "eval_runtime": 44.9891, | |
| "eval_samples_per_second": 913.6, | |
| "eval_steps_per_second": 57.103, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 29.99, | |
| "eval_loss": 1.900920033454895, | |
| "eval_runtime": 45.4927, | |
| "eval_samples_per_second": 903.485, | |
| "eval_steps_per_second": 56.471, | |
| "step": 1464000 | |
| }, | |
| { | |
| "epoch": 30.16, | |
| "learning_rate": 1.5853333333333332e-07, | |
| "loss": 2.0442, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 30.16, | |
| "eval_loss": 1.8968621492385864, | |
| "eval_runtime": 45.254, | |
| "eval_samples_per_second": 908.251, | |
| "eval_steps_per_second": 56.768, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "eval_loss": 1.908553123474121, | |
| "eval_runtime": 45.9278, | |
| "eval_samples_per_second": 894.927, | |
| "eval_steps_per_second": 55.936, | |
| "step": 1480000 | |
| }, | |
| { | |
| "epoch": 30.49, | |
| "learning_rate": 1.558e-07, | |
| "loss": 2.0401, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 30.49, | |
| "eval_loss": 1.9059042930603027, | |
| "eval_runtime": 45.2972, | |
| "eval_samples_per_second": 907.384, | |
| "eval_steps_per_second": 56.714, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 30.65, | |
| "eval_loss": 1.8996624946594238, | |
| "eval_runtime": 45.1056, | |
| "eval_samples_per_second": 911.24, | |
| "eval_steps_per_second": 56.955, | |
| "step": 1496000 | |
| }, | |
| { | |
| "epoch": 30.81, | |
| "learning_rate": 1.5306666666666666e-07, | |
| "loss": 2.0293, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 30.81, | |
| "eval_loss": 1.9013988971710205, | |
| "eval_runtime": 45.2081, | |
| "eval_samples_per_second": 909.174, | |
| "eval_steps_per_second": 56.826, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 30.98, | |
| "eval_loss": 1.8971112966537476, | |
| "eval_runtime": 45.1495, | |
| "eval_samples_per_second": 910.354, | |
| "eval_steps_per_second": 56.9, | |
| "step": 1512000 | |
| }, | |
| { | |
| "epoch": 31.14, | |
| "learning_rate": 1.5033333333333332e-07, | |
| "loss": 2.035, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 31.14, | |
| "eval_loss": 1.911407470703125, | |
| "eval_runtime": 45.2705, | |
| "eval_samples_per_second": 907.92, | |
| "eval_steps_per_second": 56.748, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 31.31, | |
| "eval_loss": 1.9107669591903687, | |
| "eval_runtime": 45.8007, | |
| "eval_samples_per_second": 897.409, | |
| "eval_steps_per_second": 56.091, | |
| "step": 1528000 | |
| }, | |
| { | |
| "epoch": 31.47, | |
| "learning_rate": 1.476e-07, | |
| "loss": 2.0389, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 31.47, | |
| "eval_loss": 1.897054672241211, | |
| "eval_runtime": 45.5487, | |
| "eval_samples_per_second": 902.375, | |
| "eval_steps_per_second": 56.401, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 31.63, | |
| "eval_loss": 1.9081885814666748, | |
| "eval_runtime": 45.7595, | |
| "eval_samples_per_second": 898.218, | |
| "eval_steps_per_second": 56.141, | |
| "step": 1544000 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 1.4486666666666665e-07, | |
| "loss": 2.0346, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "eval_loss": 1.9208694696426392, | |
| "eval_runtime": 45.3969, | |
| "eval_samples_per_second": 905.391, | |
| "eval_steps_per_second": 56.59, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 31.96, | |
| "eval_loss": 1.9018235206604004, | |
| "eval_runtime": 45.7851, | |
| "eval_samples_per_second": 897.717, | |
| "eval_steps_per_second": 56.11, | |
| "step": 1560000 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 1.4213333333333334e-07, | |
| "loss": 2.0428, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "eval_loss": 1.8987597227096558, | |
| "eval_runtime": 45.4714, | |
| "eval_samples_per_second": 903.908, | |
| "eval_steps_per_second": 56.497, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 32.29, | |
| "eval_loss": 1.9089306592941284, | |
| "eval_runtime": 46.3208, | |
| "eval_samples_per_second": 887.333, | |
| "eval_steps_per_second": 55.461, | |
| "step": 1576000 | |
| }, | |
| { | |
| "epoch": 32.45, | |
| "learning_rate": 1.3940000000000002e-07, | |
| "loss": 2.0286, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 32.45, | |
| "eval_loss": 1.8982652425765991, | |
| "eval_runtime": 45.8114, | |
| "eval_samples_per_second": 897.2, | |
| "eval_steps_per_second": 56.078, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 32.62, | |
| "eval_loss": 1.9029755592346191, | |
| "eval_runtime": 46.5806, | |
| "eval_samples_per_second": 882.385, | |
| "eval_steps_per_second": 55.152, | |
| "step": 1592000 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 1.3666666666666665e-07, | |
| "loss": 2.037, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "eval_loss": 1.9041838645935059, | |
| "eval_runtime": 46.254, | |
| "eval_samples_per_second": 888.615, | |
| "eval_steps_per_second": 55.541, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 32.94, | |
| "eval_loss": 1.9021574258804321, | |
| "eval_runtime": 46.3868, | |
| "eval_samples_per_second": 886.07, | |
| "eval_steps_per_second": 55.382, | |
| "step": 1608000 | |
| }, | |
| { | |
| "epoch": 33.11, | |
| "learning_rate": 1.3393333333333333e-07, | |
| "loss": 2.0348, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 33.11, | |
| "eval_loss": 1.8987573385238647, | |
| "eval_runtime": 46.3647, | |
| "eval_samples_per_second": 886.494, | |
| "eval_steps_per_second": 55.409, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 33.27, | |
| "eval_loss": 1.9159427881240845, | |
| "eval_runtime": 47.3206, | |
| "eval_samples_per_second": 868.587, | |
| "eval_steps_per_second": 54.289, | |
| "step": 1624000 | |
| }, | |
| { | |
| "epoch": 33.44, | |
| "learning_rate": 1.312e-07, | |
| "loss": 2.042, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 33.44, | |
| "eval_loss": 1.8933523893356323, | |
| "eval_runtime": 46.2105, | |
| "eval_samples_per_second": 889.452, | |
| "eval_steps_per_second": 55.593, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "eval_loss": 1.890829086303711, | |
| "eval_runtime": 45.7149, | |
| "eval_samples_per_second": 899.094, | |
| "eval_steps_per_second": 56.196, | |
| "step": 1640000 | |
| }, | |
| { | |
| "epoch": 33.76, | |
| "learning_rate": 1.2846666666666667e-07, | |
| "loss": 2.0426, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 33.76, | |
| "eval_loss": 1.88780677318573, | |
| "eval_runtime": 46.0333, | |
| "eval_samples_per_second": 892.876, | |
| "eval_steps_per_second": 55.807, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "eval_loss": 1.8881806135177612, | |
| "eval_runtime": 46.0263, | |
| "eval_samples_per_second": 893.012, | |
| "eval_steps_per_second": 55.816, | |
| "step": 1656000 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "learning_rate": 1.2573333333333332e-07, | |
| "loss": 2.0293, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "eval_loss": 1.9031046628952026, | |
| "eval_runtime": 45.8901, | |
| "eval_samples_per_second": 895.662, | |
| "eval_steps_per_second": 55.982, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 34.26, | |
| "eval_loss": 1.9005811214447021, | |
| "eval_runtime": 45.915, | |
| "eval_samples_per_second": 895.177, | |
| "eval_steps_per_second": 55.951, | |
| "step": 1672000 | |
| }, | |
| { | |
| "epoch": 34.42, | |
| "learning_rate": 1.23e-07, | |
| "loss": 2.0401, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 34.42, | |
| "eval_loss": 1.9066253900527954, | |
| "eval_runtime": 46.1755, | |
| "eval_samples_per_second": 890.126, | |
| "eval_steps_per_second": 55.636, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 34.58, | |
| "eval_loss": 1.8970048427581787, | |
| "eval_runtime": 45.9657, | |
| "eval_samples_per_second": 894.188, | |
| "eval_steps_per_second": 55.889, | |
| "step": 1688000 | |
| }, | |
| { | |
| "epoch": 34.75, | |
| "learning_rate": 1.2026666666666666e-07, | |
| "loss": 2.0315, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 34.75, | |
| "eval_loss": 1.895332932472229, | |
| "eval_runtime": 45.6192, | |
| "eval_samples_per_second": 900.98, | |
| "eval_steps_per_second": 56.314, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 34.91, | |
| "eval_loss": 1.9029524326324463, | |
| "eval_runtime": 45.1831, | |
| "eval_samples_per_second": 909.676, | |
| "eval_steps_per_second": 56.857, | |
| "step": 1704000 | |
| }, | |
| { | |
| "epoch": 35.08, | |
| "learning_rate": 1.1753333333333334e-07, | |
| "loss": 2.0393, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 35.08, | |
| "eval_loss": 1.908921480178833, | |
| "eval_runtime": 45.6994, | |
| "eval_samples_per_second": 899.399, | |
| "eval_steps_per_second": 56.215, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 35.24, | |
| "eval_loss": 1.9037113189697266, | |
| "eval_runtime": 45.2722, | |
| "eval_samples_per_second": 907.887, | |
| "eval_steps_per_second": 56.746, | |
| "step": 1720000 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "learning_rate": 1.1480000000000001e-07, | |
| "loss": 2.0422, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "eval_loss": 1.8991347551345825, | |
| "eval_runtime": 46.062, | |
| "eval_samples_per_second": 892.319, | |
| "eval_steps_per_second": 55.773, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "eval_loss": 1.8825979232788086, | |
| "eval_runtime": 45.3033, | |
| "eval_samples_per_second": 907.262, | |
| "eval_steps_per_second": 56.707, | |
| "step": 1736000 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "learning_rate": 1.1206666666666666e-07, | |
| "loss": 2.0307, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "eval_loss": 1.9027307033538818, | |
| "eval_runtime": 45.5838, | |
| "eval_samples_per_second": 901.681, | |
| "eval_steps_per_second": 56.358, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "eval_loss": 1.9172565937042236, | |
| "eval_runtime": 45.2197, | |
| "eval_samples_per_second": 908.94, | |
| "eval_steps_per_second": 56.811, | |
| "step": 1752000 | |
| }, | |
| { | |
| "epoch": 36.06, | |
| "learning_rate": 1.0933333333333333e-07, | |
| "loss": 2.0414, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 36.06, | |
| "eval_loss": 1.9065029621124268, | |
| "eval_runtime": 45.5684, | |
| "eval_samples_per_second": 901.985, | |
| "eval_steps_per_second": 56.377, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 36.22, | |
| "eval_loss": 1.8984663486480713, | |
| "eval_runtime": 45.1302, | |
| "eval_samples_per_second": 910.743, | |
| "eval_steps_per_second": 56.924, | |
| "step": 1768000 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "learning_rate": 1.066e-07, | |
| "loss": 2.0393, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "eval_loss": 1.884873628616333, | |
| "eval_runtime": 45.3848, | |
| "eval_samples_per_second": 905.634, | |
| "eval_steps_per_second": 56.605, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "eval_loss": 1.8944772481918335, | |
| "eval_runtime": 45.1483, | |
| "eval_samples_per_second": 910.378, | |
| "eval_steps_per_second": 56.901, | |
| "step": 1784000 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "learning_rate": 1.0386666666666667e-07, | |
| "loss": 2.0302, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "eval_loss": 1.8962441682815552, | |
| "eval_runtime": 46.8165, | |
| "eval_samples_per_second": 877.938, | |
| "eval_steps_per_second": 54.874, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 36.88, | |
| "eval_loss": 1.901509165763855, | |
| "eval_runtime": 46.5098, | |
| "eval_samples_per_second": 883.727, | |
| "eval_steps_per_second": 55.236, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 37.04, | |
| "learning_rate": 1.0113333333333334e-07, | |
| "loss": 2.0344, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 37.04, | |
| "eval_loss": 1.8923826217651367, | |
| "eval_runtime": 47.0536, | |
| "eval_samples_per_second": 873.514, | |
| "eval_steps_per_second": 54.597, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 37.21, | |
| "eval_loss": 1.8804473876953125, | |
| "eval_runtime": 45.649, | |
| "eval_samples_per_second": 900.393, | |
| "eval_steps_per_second": 56.277, | |
| "step": 1816000 | |
| }, | |
| { | |
| "epoch": 37.37, | |
| "learning_rate": 9.84e-08, | |
| "loss": 2.0303, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 37.37, | |
| "eval_loss": 1.894727349281311, | |
| "eval_runtime": 45.669, | |
| "eval_samples_per_second": 899.998, | |
| "eval_steps_per_second": 56.253, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 37.53, | |
| "eval_loss": 1.891680121421814, | |
| "eval_runtime": 45.9688, | |
| "eval_samples_per_second": 894.128, | |
| "eval_steps_per_second": 55.886, | |
| "step": 1832000 | |
| }, | |
| { | |
| "epoch": 37.7, | |
| "learning_rate": 9.566666666666666e-08, | |
| "loss": 2.0318, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 37.7, | |
| "eval_loss": 1.8992102146148682, | |
| "eval_runtime": 46.1777, | |
| "eval_samples_per_second": 890.083, | |
| "eval_steps_per_second": 55.633, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 37.86, | |
| "eval_loss": 1.901772379875183, | |
| "eval_runtime": 46.2844, | |
| "eval_samples_per_second": 888.031, | |
| "eval_steps_per_second": 55.505, | |
| "step": 1848000 | |
| }, | |
| { | |
| "epoch": 38.03, | |
| "learning_rate": 9.293333333333333e-08, | |
| "loss": 2.039, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 38.03, | |
| "eval_loss": 1.8903098106384277, | |
| "eval_runtime": 47.0109, | |
| "eval_samples_per_second": 874.308, | |
| "eval_steps_per_second": 54.647, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "eval_loss": 1.9088859558105469, | |
| "eval_runtime": 45.4014, | |
| "eval_samples_per_second": 905.303, | |
| "eval_steps_per_second": 56.584, | |
| "step": 1864000 | |
| }, | |
| { | |
| "epoch": 38.35, | |
| "learning_rate": 9.02e-08, | |
| "loss": 2.0319, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 38.35, | |
| "eval_loss": 1.9092743396759033, | |
| "eval_runtime": 45.713, | |
| "eval_samples_per_second": 899.132, | |
| "eval_steps_per_second": 56.198, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 38.52, | |
| "eval_loss": 1.895071268081665, | |
| "eval_runtime": 46.0527, | |
| "eval_samples_per_second": 892.499, | |
| "eval_steps_per_second": 55.784, | |
| "step": 1880000 | |
| }, | |
| { | |
| "epoch": 38.68, | |
| "learning_rate": 8.746666666666667e-08, | |
| "loss": 2.0359, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 38.68, | |
| "eval_loss": 1.8970472812652588, | |
| "eval_runtime": 45.2938, | |
| "eval_samples_per_second": 907.454, | |
| "eval_steps_per_second": 56.719, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 38.85, | |
| "eval_loss": 1.89948308467865, | |
| "eval_runtime": 46.012, | |
| "eval_samples_per_second": 893.288, | |
| "eval_steps_per_second": 55.833, | |
| "step": 1896000 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 8.473333333333334e-08, | |
| "loss": 2.0353, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "eval_loss": 1.8887970447540283, | |
| "eval_runtime": 45.8877, | |
| "eval_samples_per_second": 895.709, | |
| "eval_steps_per_second": 55.985, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 39.17, | |
| "eval_loss": 1.914867877960205, | |
| "eval_runtime": 45.5355, | |
| "eval_samples_per_second": 902.636, | |
| "eval_steps_per_second": 56.418, | |
| "step": 1912000 | |
| }, | |
| { | |
| "epoch": 39.34, | |
| "learning_rate": 8.2e-08, | |
| "loss": 2.0343, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 39.34, | |
| "eval_loss": 1.8881230354309082, | |
| "eval_runtime": 46.2793, | |
| "eval_samples_per_second": 888.13, | |
| "eval_steps_per_second": 55.511, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 39.5, | |
| "eval_loss": 1.8935189247131348, | |
| "eval_runtime": 46.1086, | |
| "eval_samples_per_second": 891.417, | |
| "eval_steps_per_second": 55.716, | |
| "step": 1928000 | |
| }, | |
| { | |
| "epoch": 39.66, | |
| "learning_rate": 7.926666666666666e-08, | |
| "loss": 2.0395, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 39.66, | |
| "eval_loss": 1.8938074111938477, | |
| "eval_runtime": 45.8793, | |
| "eval_samples_per_second": 895.872, | |
| "eval_steps_per_second": 55.995, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 39.83, | |
| "eval_loss": 1.8929249048233032, | |
| "eval_runtime": 46.149, | |
| "eval_samples_per_second": 890.637, | |
| "eval_steps_per_second": 55.668, | |
| "step": 1944000 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "learning_rate": 7.653333333333333e-08, | |
| "loss": 2.0316, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "eval_loss": 1.9186030626296997, | |
| "eval_runtime": 45.3993, | |
| "eval_samples_per_second": 905.345, | |
| "eval_steps_per_second": 56.587, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 40.16, | |
| "eval_loss": 1.9189401865005493, | |
| "eval_runtime": 46.9208, | |
| "eval_samples_per_second": 875.987, | |
| "eval_steps_per_second": 54.752, | |
| "step": 1960000 | |
| }, | |
| { | |
| "epoch": 40.32, | |
| "learning_rate": 7.38e-08, | |
| "loss": 2.0302, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 40.32, | |
| "eval_loss": 1.9124609231948853, | |
| "eval_runtime": 46.2172, | |
| "eval_samples_per_second": 889.322, | |
| "eval_steps_per_second": 55.585, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 40.48, | |
| "eval_loss": 1.9077569246292114, | |
| "eval_runtime": 46.4482, | |
| "eval_samples_per_second": 884.901, | |
| "eval_steps_per_second": 55.309, | |
| "step": 1976000 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "learning_rate": 7.106666666666667e-08, | |
| "loss": 2.0355, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "eval_loss": 1.8975083827972412, | |
| "eval_runtime": 45.4061, | |
| "eval_samples_per_second": 905.208, | |
| "eval_steps_per_second": 56.578, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 40.81, | |
| "eval_loss": 1.892892837524414, | |
| "eval_runtime": 45.6207, | |
| "eval_samples_per_second": 900.951, | |
| "eval_steps_per_second": 56.312, | |
| "step": 1992000 | |
| }, | |
| { | |
| "epoch": 40.98, | |
| "learning_rate": 6.833333333333332e-08, | |
| "loss": 2.0332, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 40.98, | |
| "eval_loss": 1.8898950815200806, | |
| "eval_runtime": 45.4778, | |
| "eval_samples_per_second": 903.782, | |
| "eval_steps_per_second": 56.489, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 41.14, | |
| "eval_loss": 1.9043201208114624, | |
| "eval_runtime": 45.2865, | |
| "eval_samples_per_second": 907.599, | |
| "eval_steps_per_second": 56.728, | |
| "step": 2008000 | |
| }, | |
| { | |
| "epoch": 41.3, | |
| "learning_rate": 6.56e-08, | |
| "loss": 2.0327, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 41.3, | |
| "eval_loss": 1.9086461067199707, | |
| "eval_runtime": 45.7752, | |
| "eval_samples_per_second": 897.91, | |
| "eval_steps_per_second": 56.122, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 41.47, | |
| "eval_loss": 1.894409418106079, | |
| "eval_runtime": 45.9308, | |
| "eval_samples_per_second": 894.867, | |
| "eval_steps_per_second": 55.932, | |
| "step": 2024000 | |
| }, | |
| { | |
| "epoch": 41.63, | |
| "learning_rate": 6.286666666666666e-08, | |
| "loss": 2.0414, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 41.63, | |
| "eval_loss": 1.9029189348220825, | |
| "eval_runtime": 45.9761, | |
| "eval_samples_per_second": 893.986, | |
| "eval_steps_per_second": 55.877, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "eval_loss": 1.8990041017532349, | |
| "eval_runtime": 46.0838, | |
| "eval_samples_per_second": 891.897, | |
| "eval_steps_per_second": 55.746, | |
| "step": 2040000 | |
| }, | |
| { | |
| "epoch": 41.96, | |
| "learning_rate": 6.013333333333333e-08, | |
| "loss": 2.0327, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 41.96, | |
| "eval_loss": 1.9174869060516357, | |
| "eval_runtime": 46.0447, | |
| "eval_samples_per_second": 892.655, | |
| "eval_steps_per_second": 55.794, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 42.12, | |
| "eval_loss": 1.88877534866333, | |
| "eval_runtime": 45.3492, | |
| "eval_samples_per_second": 906.344, | |
| "eval_steps_per_second": 56.649, | |
| "step": 2056000 | |
| }, | |
| { | |
| "epoch": 42.29, | |
| "learning_rate": 5.7400000000000004e-08, | |
| "loss": 2.0428, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 42.29, | |
| "eval_loss": 1.8971478939056396, | |
| "eval_runtime": 46.1829, | |
| "eval_samples_per_second": 889.983, | |
| "eval_steps_per_second": 55.627, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "eval_loss": 1.90713369846344, | |
| "eval_runtime": 46.2493, | |
| "eval_samples_per_second": 888.706, | |
| "eval_steps_per_second": 55.547, | |
| "step": 2072000 | |
| }, | |
| { | |
| "epoch": 42.62, | |
| "learning_rate": 5.4666666666666666e-08, | |
| "loss": 2.0337, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 42.62, | |
| "eval_loss": 1.8967806100845337, | |
| "eval_runtime": 45.4829, | |
| "eval_samples_per_second": 903.679, | |
| "eval_steps_per_second": 56.483, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 42.78, | |
| "eval_loss": 1.9059593677520752, | |
| "eval_runtime": 45.3661, | |
| "eval_samples_per_second": 906.008, | |
| "eval_steps_per_second": 56.628, | |
| "step": 2088000 | |
| }, | |
| { | |
| "epoch": 42.94, | |
| "learning_rate": 5.1933333333333335e-08, | |
| "loss": 2.0394, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 42.94, | |
| "eval_loss": 1.902763843536377, | |
| "eval_runtime": 46.1023, | |
| "eval_samples_per_second": 891.539, | |
| "eval_steps_per_second": 55.724, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 43.11, | |
| "eval_loss": 1.8916599750518799, | |
| "eval_runtime": 46.167, | |
| "eval_samples_per_second": 890.289, | |
| "eval_steps_per_second": 55.646, | |
| "step": 2104000 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 4.92e-08, | |
| "loss": 2.0314, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "eval_loss": 1.8868290185928345, | |
| "eval_runtime": 45.7209, | |
| "eval_samples_per_second": 898.977, | |
| "eval_steps_per_second": 56.189, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 43.43, | |
| "eval_loss": 1.9086658954620361, | |
| "eval_runtime": 46.6687, | |
| "eval_samples_per_second": 880.719, | |
| "eval_steps_per_second": 55.048, | |
| "step": 2120000 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "learning_rate": 4.6466666666666666e-08, | |
| "loss": 2.0368, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "eval_loss": 1.8951292037963867, | |
| "eval_runtime": 45.5475, | |
| "eval_samples_per_second": 902.399, | |
| "eval_steps_per_second": 56.403, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 43.76, | |
| "eval_loss": 1.893837809562683, | |
| "eval_runtime": 46.7129, | |
| "eval_samples_per_second": 879.885, | |
| "eval_steps_per_second": 54.996, | |
| "step": 2136000 | |
| }, | |
| { | |
| "epoch": 43.93, | |
| "learning_rate": 4.3733333333333335e-08, | |
| "loss": 2.0298, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 43.93, | |
| "eval_loss": 1.8874099254608154, | |
| "eval_runtime": 46.1171, | |
| "eval_samples_per_second": 891.254, | |
| "eval_steps_per_second": 55.706, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 44.09, | |
| "eval_loss": 1.90646493434906, | |
| "eval_runtime": 45.5199, | |
| "eval_samples_per_second": 902.945, | |
| "eval_steps_per_second": 56.437, | |
| "step": 2152000 | |
| }, | |
| { | |
| "epoch": 44.25, | |
| "learning_rate": 4.1e-08, | |
| "loss": 2.0353, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 44.25, | |
| "eval_loss": 1.9097111225128174, | |
| "eval_runtime": 46.2608, | |
| "eval_samples_per_second": 888.484, | |
| "eval_steps_per_second": 55.533, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 44.42, | |
| "eval_loss": 1.8985484838485718, | |
| "eval_runtime": 46.7775, | |
| "eval_samples_per_second": 878.67, | |
| "eval_steps_per_second": 54.92, | |
| "step": 2168000 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "learning_rate": 3.8266666666666665e-08, | |
| "loss": 2.0324, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "eval_loss": 1.9160007238388062, | |
| "eval_runtime": 45.5635, | |
| "eval_samples_per_second": 902.082, | |
| "eval_steps_per_second": 56.383, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 44.75, | |
| "eval_loss": 1.9059538841247559, | |
| "eval_runtime": 46.2267, | |
| "eval_samples_per_second": 889.139, | |
| "eval_steps_per_second": 55.574, | |
| "step": 2184000 | |
| }, | |
| { | |
| "epoch": 44.91, | |
| "learning_rate": 3.5533333333333334e-08, | |
| "loss": 2.0316, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 44.91, | |
| "eval_loss": 1.8911948204040527, | |
| "eval_runtime": 46.1128, | |
| "eval_samples_per_second": 891.335, | |
| "eval_steps_per_second": 55.711, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 45.07, | |
| "eval_loss": 1.9013826847076416, | |
| "eval_runtime": 46.2728, | |
| "eval_samples_per_second": 888.253, | |
| "eval_steps_per_second": 55.519, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 45.24, | |
| "learning_rate": 3.28e-08, | |
| "loss": 2.0322, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 45.24, | |
| "eval_loss": 1.903083324432373, | |
| "eval_runtime": 45.9933, | |
| "eval_samples_per_second": 893.652, | |
| "eval_steps_per_second": 55.856, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 45.4, | |
| "eval_loss": 1.9086343050003052, | |
| "eval_runtime": 46.1275, | |
| "eval_samples_per_second": 891.053, | |
| "eval_steps_per_second": 55.694, | |
| "step": 2216000 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "learning_rate": 3.0066666666666665e-08, | |
| "loss": 2.035, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "eval_loss": 1.9147051572799683, | |
| "eval_runtime": 46.1882, | |
| "eval_samples_per_second": 889.88, | |
| "eval_steps_per_second": 55.62, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 45.73, | |
| "eval_loss": 1.900397777557373, | |
| "eval_runtime": 46.2313, | |
| "eval_samples_per_second": 889.052, | |
| "eval_steps_per_second": 55.568, | |
| "step": 2232000 | |
| }, | |
| { | |
| "epoch": 45.89, | |
| "learning_rate": 2.7333333333333333e-08, | |
| "loss": 2.0431, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 45.89, | |
| "eval_loss": 1.9027053117752075, | |
| "eval_runtime": 45.9169, | |
| "eval_samples_per_second": 895.139, | |
| "eval_steps_per_second": 55.949, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 46.06, | |
| "eval_loss": 1.891597032546997, | |
| "eval_runtime": 45.8109, | |
| "eval_samples_per_second": 897.211, | |
| "eval_steps_per_second": 56.078, | |
| "step": 2248000 | |
| }, | |
| { | |
| "epoch": 46.22, | |
| "learning_rate": 2.46e-08, | |
| "loss": 2.0347, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 46.22, | |
| "eval_loss": 1.9048635959625244, | |
| "eval_runtime": 46.62, | |
| "eval_samples_per_second": 881.64, | |
| "eval_steps_per_second": 55.105, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "eval_loss": 1.8972582817077637, | |
| "eval_runtime": 45.4329, | |
| "eval_samples_per_second": 904.675, | |
| "eval_steps_per_second": 56.545, | |
| "step": 2264000 | |
| }, | |
| { | |
| "epoch": 46.55, | |
| "learning_rate": 2.1866666666666667e-08, | |
| "loss": 2.0353, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 46.55, | |
| "eval_loss": 1.8931912183761597, | |
| "eval_runtime": 45.83, | |
| "eval_samples_per_second": 896.836, | |
| "eval_steps_per_second": 56.055, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 46.71, | |
| "eval_loss": 1.912061333656311, | |
| "eval_runtime": 45.6862, | |
| "eval_samples_per_second": 899.659, | |
| "eval_steps_per_second": 56.231, | |
| "step": 2280000 | |
| }, | |
| { | |
| "epoch": 46.88, | |
| "learning_rate": 1.9133333333333333e-08, | |
| "loss": 2.0309, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 46.88, | |
| "eval_loss": 1.8972575664520264, | |
| "eval_runtime": 45.7208, | |
| "eval_samples_per_second": 898.978, | |
| "eval_steps_per_second": 56.189, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 47.04, | |
| "eval_loss": 1.8985596895217896, | |
| "eval_runtime": 45.62, | |
| "eval_samples_per_second": 900.965, | |
| "eval_steps_per_second": 56.313, | |
| "step": 2296000 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "learning_rate": 1.64e-08, | |
| "loss": 2.0359, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "eval_loss": 1.9202120304107666, | |
| "eval_runtime": 46.1708, | |
| "eval_samples_per_second": 890.216, | |
| "eval_steps_per_second": 55.641, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 47.37, | |
| "eval_loss": 1.8778069019317627, | |
| "eval_runtime": 45.0738, | |
| "eval_samples_per_second": 911.882, | |
| "eval_steps_per_second": 56.995, | |
| "step": 2312000 | |
| }, | |
| { | |
| "epoch": 47.53, | |
| "learning_rate": 1.3666666666666667e-08, | |
| "loss": 2.037, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 47.53, | |
| "eval_loss": 1.9136707782745361, | |
| "eval_runtime": 45.7351, | |
| "eval_samples_per_second": 898.698, | |
| "eval_steps_per_second": 56.171, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 47.7, | |
| "eval_loss": 1.9095231294631958, | |
| "eval_runtime": 46.2067, | |
| "eval_samples_per_second": 889.525, | |
| "eval_steps_per_second": 55.598, | |
| "step": 2328000 | |
| }, | |
| { | |
| "epoch": 47.86, | |
| "learning_rate": 1.0933333333333334e-08, | |
| "loss": 2.0306, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 47.86, | |
| "eval_loss": 1.903990626335144, | |
| "eval_runtime": 45.7769, | |
| "eval_samples_per_second": 897.877, | |
| "eval_steps_per_second": 56.12, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_loss": 1.8931529521942139, | |
| "eval_runtime": 46.2564, | |
| "eval_samples_per_second": 888.57, | |
| "eval_steps_per_second": 55.538, | |
| "step": 2344000 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 8.2e-09, | |
| "loss": 2.0342, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "eval_loss": 1.9151569604873657, | |
| "eval_runtime": 45.6412, | |
| "eval_samples_per_second": 900.547, | |
| "eval_steps_per_second": 56.287, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 48.35, | |
| "eval_loss": 1.9058945178985596, | |
| "eval_runtime": 46.1965, | |
| "eval_samples_per_second": 889.72, | |
| "eval_steps_per_second": 55.61, | |
| "step": 2360000 | |
| }, | |
| { | |
| "epoch": 48.52, | |
| "learning_rate": 5.466666666666667e-09, | |
| "loss": 2.0457, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 48.52, | |
| "eval_loss": 1.8844729661941528, | |
| "eval_runtime": 46.2206, | |
| "eval_samples_per_second": 889.257, | |
| "eval_steps_per_second": 55.581, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 48.68, | |
| "eval_loss": 1.903971791267395, | |
| "eval_runtime": 45.6349, | |
| "eval_samples_per_second": 900.67, | |
| "eval_steps_per_second": 56.295, | |
| "step": 2376000 | |
| }, | |
| { | |
| "epoch": 48.84, | |
| "learning_rate": 2.7333333333333334e-09, | |
| "loss": 2.0349, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 48.84, | |
| "eval_loss": 1.9000164270401, | |
| "eval_runtime": 45.9273, | |
| "eval_samples_per_second": 894.936, | |
| "eval_steps_per_second": 55.936, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "eval_loss": 1.905893087387085, | |
| "eval_runtime": 46.548, | |
| "eval_samples_per_second": 883.003, | |
| "eval_steps_per_second": 55.19, | |
| "step": 2392000 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "learning_rate": 0.0, | |
| "loss": 2.0322, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "eval_loss": 1.8925877809524536, | |
| "eval_runtime": 45.4613, | |
| "eval_samples_per_second": 904.11, | |
| "eval_steps_per_second": 56.51, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "step": 2400000, | |
| "total_flos": 7.48474678802484e+17, | |
| "train_loss": 2.0531104736328123, | |
| "train_runtime": 163423.6248, | |
| "train_samples_per_second": 234.972, | |
| "train_steps_per_second": 14.686 | |
| } | |
| ], | |
| "logging_steps": 16000, | |
| "max_steps": 2400000, | |
| "num_train_epochs": 50, | |
| "save_steps": 32000, | |
| "total_flos": 7.48474678802484e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |