| { | |
| "best_metric": 1.9065207242965698, | |
| "best_model_checkpoint": "./model_tweets_2020_Q3_full/checkpoint-2176000", | |
| "epoch": 10.105220609597433, | |
| "eval_steps": 8000, | |
| "global_step": 2400000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.219714641571045, | |
| "eval_runtime": 441.2719, | |
| "eval_samples_per_second": 906.47, | |
| "eval_steps_per_second": 56.654, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.0726666666666665e-07, | |
| "loss": 2.3934, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.142895460128784, | |
| "eval_runtime": 441.97, | |
| "eval_samples_per_second": 905.039, | |
| "eval_steps_per_second": 56.565, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 2.1001179218292236, | |
| "eval_runtime": 441.5938, | |
| "eval_samples_per_second": 905.81, | |
| "eval_steps_per_second": 56.613, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.0453333333333336e-07, | |
| "loss": 2.2294, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 2.076151132583618, | |
| "eval_runtime": 441.8927, | |
| "eval_samples_per_second": 905.197, | |
| "eval_steps_per_second": 56.575, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 2.05153489112854, | |
| "eval_runtime": 442.4391, | |
| "eval_samples_per_second": 904.079, | |
| "eval_steps_per_second": 56.505, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.018e-07, | |
| "loss": 2.1835, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.043534755706787, | |
| "eval_runtime": 441.9647, | |
| "eval_samples_per_second": 905.05, | |
| "eval_steps_per_second": 56.566, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 2.0345780849456787, | |
| "eval_runtime": 442.2484, | |
| "eval_samples_per_second": 904.469, | |
| "eval_steps_per_second": 56.529, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.9906666666666667e-07, | |
| "loss": 2.1517, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.0254366397857666, | |
| "eval_runtime": 441.5788, | |
| "eval_samples_per_second": 905.841, | |
| "eval_steps_per_second": 56.615, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 2.017543315887451, | |
| "eval_runtime": 442.2237, | |
| "eval_samples_per_second": 904.52, | |
| "eval_steps_per_second": 56.532, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.963333333333333e-07, | |
| "loss": 2.1381, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 2.007652521133423, | |
| "eval_runtime": 442.7678, | |
| "eval_samples_per_second": 903.408, | |
| "eval_steps_per_second": 56.463, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 2.0028882026672363, | |
| "eval_runtime": 443.0453, | |
| "eval_samples_per_second": 902.842, | |
| "eval_steps_per_second": 56.428, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.936e-07, | |
| "loss": 2.1244, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 2.001089572906494, | |
| "eval_runtime": 442.6781, | |
| "eval_samples_per_second": 903.591, | |
| "eval_steps_per_second": 56.474, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.9979643821716309, | |
| "eval_runtime": 443.0079, | |
| "eval_samples_per_second": 902.919, | |
| "eval_steps_per_second": 56.432, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3.908666666666667e-07, | |
| "loss": 2.1116, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.9901278018951416, | |
| "eval_runtime": 443.7009, | |
| "eval_samples_per_second": 901.508, | |
| "eval_steps_per_second": 56.344, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.9839751720428467, | |
| "eval_runtime": 442.1533, | |
| "eval_samples_per_second": 904.664, | |
| "eval_steps_per_second": 56.541, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.8813333333333334e-07, | |
| "loss": 2.1104, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.9885350465774536, | |
| "eval_runtime": 442.9416, | |
| "eval_samples_per_second": 903.054, | |
| "eval_steps_per_second": 56.441, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.9854729175567627, | |
| "eval_runtime": 442.2549, | |
| "eval_samples_per_second": 904.456, | |
| "eval_steps_per_second": 56.528, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.854e-07, | |
| "loss": 2.1031, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.9829412698745728, | |
| "eval_runtime": 442.7275, | |
| "eval_samples_per_second": 903.49, | |
| "eval_steps_per_second": 56.468, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.9812543392181396, | |
| "eval_runtime": 441.8999, | |
| "eval_samples_per_second": 905.182, | |
| "eval_steps_per_second": 56.574, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.8266666666666665e-07, | |
| "loss": 2.0971, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.981191873550415, | |
| "eval_runtime": 443.7308, | |
| "eval_samples_per_second": 901.447, | |
| "eval_steps_per_second": 56.34, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.979522943496704, | |
| "eval_runtime": 445.7901, | |
| "eval_samples_per_second": 897.283, | |
| "eval_steps_per_second": 56.08, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.799333333333333e-07, | |
| "loss": 2.1044, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.9738078117370605, | |
| "eval_runtime": 448.3685, | |
| "eval_samples_per_second": 892.123, | |
| "eval_steps_per_second": 55.758, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.9768003225326538, | |
| "eval_runtime": 447.4392, | |
| "eval_samples_per_second": 893.976, | |
| "eval_steps_per_second": 55.874, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.772e-07, | |
| "loss": 2.0928, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.978550672531128, | |
| "eval_runtime": 444.0634, | |
| "eval_samples_per_second": 900.772, | |
| "eval_steps_per_second": 56.298, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.9699029922485352, | |
| "eval_runtime": 448.9877, | |
| "eval_samples_per_second": 890.893, | |
| "eval_steps_per_second": 55.681, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.7446666666666667e-07, | |
| "loss": 2.0949, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.9700462818145752, | |
| "eval_runtime": 447.582, | |
| "eval_samples_per_second": 893.691, | |
| "eval_steps_per_second": 55.856, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.965348720550537, | |
| "eval_runtime": 452.353, | |
| "eval_samples_per_second": 884.265, | |
| "eval_steps_per_second": 55.267, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.7173333333333333e-07, | |
| "loss": 2.0892, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.9680548906326294, | |
| "eval_runtime": 448.4016, | |
| "eval_samples_per_second": 892.057, | |
| "eval_steps_per_second": 55.754, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.9649720191955566, | |
| "eval_runtime": 445.7154, | |
| "eval_samples_per_second": 897.434, | |
| "eval_steps_per_second": 56.09, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.69e-07, | |
| "loss": 2.0841, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.9638316631317139, | |
| "eval_runtime": 447.9015, | |
| "eval_samples_per_second": 893.054, | |
| "eval_steps_per_second": 55.816, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 1.9682003259658813, | |
| "eval_runtime": 448.197, | |
| "eval_samples_per_second": 892.465, | |
| "eval_steps_per_second": 55.779, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.6626666666666664e-07, | |
| "loss": 2.0887, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.9604706764221191, | |
| "eval_runtime": 446.1801, | |
| "eval_samples_per_second": 896.499, | |
| "eval_steps_per_second": 56.031, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 1.961388111114502, | |
| "eval_runtime": 449.8519, | |
| "eval_samples_per_second": 889.182, | |
| "eval_steps_per_second": 55.574, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.6353333333333335e-07, | |
| "loss": 2.0842, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 1.962444543838501, | |
| "eval_runtime": 447.5177, | |
| "eval_samples_per_second": 893.819, | |
| "eval_steps_per_second": 55.864, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 1.9605332612991333, | |
| "eval_runtime": 449.5723, | |
| "eval_samples_per_second": 889.734, | |
| "eval_steps_per_second": 55.608, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.608e-07, | |
| "loss": 2.0773, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 1.9554321765899658, | |
| "eval_runtime": 444.9546, | |
| "eval_samples_per_second": 898.968, | |
| "eval_steps_per_second": 56.186, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 1.957843542098999, | |
| "eval_runtime": 445.0742, | |
| "eval_samples_per_second": 898.727, | |
| "eval_steps_per_second": 56.17, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.5806666666666666e-07, | |
| "loss": 2.0795, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 1.957188606262207, | |
| "eval_runtime": 445.8149, | |
| "eval_samples_per_second": 897.233, | |
| "eval_steps_per_second": 56.077, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 1.9521090984344482, | |
| "eval_runtime": 444.7945, | |
| "eval_samples_per_second": 899.292, | |
| "eval_steps_per_second": 56.206, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.553333333333333e-07, | |
| "loss": 2.0794, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 1.9550837278366089, | |
| "eval_runtime": 446.4097, | |
| "eval_samples_per_second": 896.038, | |
| "eval_steps_per_second": 56.002, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 1.9569264650344849, | |
| "eval_runtime": 443.7576, | |
| "eval_samples_per_second": 901.393, | |
| "eval_steps_per_second": 56.337, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.5259999999999997e-07, | |
| "loss": 2.0788, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 1.9571126699447632, | |
| "eval_runtime": 445.1557, | |
| "eval_samples_per_second": 898.562, | |
| "eval_steps_per_second": 56.16, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 1.9501842260360718, | |
| "eval_runtime": 445.7741, | |
| "eval_samples_per_second": 897.315, | |
| "eval_steps_per_second": 56.082, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.498666666666667e-07, | |
| "loss": 2.0778, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.9543704986572266, | |
| "eval_runtime": 445.8348, | |
| "eval_samples_per_second": 897.193, | |
| "eval_steps_per_second": 56.075, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.947017788887024, | |
| "eval_runtime": 447.0241, | |
| "eval_samples_per_second": 894.806, | |
| "eval_steps_per_second": 55.925, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.4713333333333333e-07, | |
| "loss": 2.0694, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 1.9545376300811768, | |
| "eval_runtime": 446.4613, | |
| "eval_samples_per_second": 895.934, | |
| "eval_steps_per_second": 55.996, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.9471752643585205, | |
| "eval_runtime": 446.0717, | |
| "eval_samples_per_second": 896.717, | |
| "eval_steps_per_second": 56.045, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.444e-07, | |
| "loss": 2.0718, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 1.947655200958252, | |
| "eval_runtime": 445.8656, | |
| "eval_samples_per_second": 897.131, | |
| "eval_steps_per_second": 56.071, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 1.949648380279541, | |
| "eval_runtime": 446.4025, | |
| "eval_samples_per_second": 896.052, | |
| "eval_steps_per_second": 56.003, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.416666666666667e-07, | |
| "loss": 2.0787, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 1.943971037864685, | |
| "eval_runtime": 448.3905, | |
| "eval_samples_per_second": 892.08, | |
| "eval_steps_per_second": 55.755, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 1.9483779668807983, | |
| "eval_runtime": 448.4782, | |
| "eval_samples_per_second": 891.905, | |
| "eval_steps_per_second": 55.744, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.3893333333333335e-07, | |
| "loss": 2.0764, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.9475030899047852, | |
| "eval_runtime": 447.8377, | |
| "eval_samples_per_second": 893.181, | |
| "eval_steps_per_second": 55.824, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 1.946897029876709, | |
| "eval_runtime": 446.5774, | |
| "eval_samples_per_second": 895.701, | |
| "eval_steps_per_second": 55.981, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.3619999999999995e-07, | |
| "loss": 2.0795, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 1.947367787361145, | |
| "eval_runtime": 446.4599, | |
| "eval_samples_per_second": 895.937, | |
| "eval_steps_per_second": 55.996, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 1.9491695165634155, | |
| "eval_runtime": 449.1184, | |
| "eval_samples_per_second": 890.634, | |
| "eval_steps_per_second": 55.665, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.3346666666666666e-07, | |
| "loss": 2.07, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 1.9479598999023438, | |
| "eval_runtime": 447.8049, | |
| "eval_samples_per_second": 893.246, | |
| "eval_steps_per_second": 55.828, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.9481781721115112, | |
| "eval_runtime": 445.8382, | |
| "eval_samples_per_second": 897.186, | |
| "eval_steps_per_second": 56.074, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.307333333333333e-07, | |
| "loss": 2.0712, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 1.9497871398925781, | |
| "eval_runtime": 446.4596, | |
| "eval_samples_per_second": 895.938, | |
| "eval_steps_per_second": 55.996, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.9429104328155518, | |
| "eval_runtime": 446.91, | |
| "eval_samples_per_second": 895.035, | |
| "eval_steps_per_second": 55.94, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.28e-07, | |
| "loss": 2.0739, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 1.945642352104187, | |
| "eval_runtime": 446.7665, | |
| "eval_samples_per_second": 895.322, | |
| "eval_steps_per_second": 55.958, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 1.9468969106674194, | |
| "eval_runtime": 446.5973, | |
| "eval_samples_per_second": 895.661, | |
| "eval_steps_per_second": 55.979, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.252666666666667e-07, | |
| "loss": 2.0688, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 1.9466804265975952, | |
| "eval_runtime": 445.9118, | |
| "eval_samples_per_second": 897.038, | |
| "eval_steps_per_second": 56.065, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 1.945359230041504, | |
| "eval_runtime": 446.3398, | |
| "eval_samples_per_second": 896.178, | |
| "eval_steps_per_second": 56.011, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.2253333333333334e-07, | |
| "loss": 2.0706, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 1.9440275430679321, | |
| "eval_runtime": 445.8082, | |
| "eval_samples_per_second": 897.247, | |
| "eval_steps_per_second": 56.078, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 1.9401416778564453, | |
| "eval_runtime": 446.0226, | |
| "eval_samples_per_second": 896.816, | |
| "eval_steps_per_second": 56.051, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.198e-07, | |
| "loss": 2.0694, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 1.9396692514419556, | |
| "eval_runtime": 447.4896, | |
| "eval_samples_per_second": 893.876, | |
| "eval_steps_per_second": 55.867, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 1.9429028034210205, | |
| "eval_runtime": 445.7305, | |
| "eval_samples_per_second": 897.403, | |
| "eval_steps_per_second": 56.088, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.1706666666666665e-07, | |
| "loss": 2.0698, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 1.9483931064605713, | |
| "eval_runtime": 445.796, | |
| "eval_samples_per_second": 897.271, | |
| "eval_steps_per_second": 56.079, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 1.9375388622283936, | |
| "eval_runtime": 445.5629, | |
| "eval_samples_per_second": 897.741, | |
| "eval_steps_per_second": 56.109, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 3.1433333333333336e-07, | |
| "loss": 2.0681, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 1.9411094188690186, | |
| "eval_runtime": 446.974, | |
| "eval_samples_per_second": 894.907, | |
| "eval_steps_per_second": 55.932, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 1.9418509006500244, | |
| "eval_runtime": 445.5586, | |
| "eval_samples_per_second": 897.75, | |
| "eval_steps_per_second": 56.109, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.116e-07, | |
| "loss": 2.0676, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 1.9373135566711426, | |
| "eval_runtime": 446.9581, | |
| "eval_samples_per_second": 894.939, | |
| "eval_steps_per_second": 55.934, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 1.936606526374817, | |
| "eval_runtime": 448.0456, | |
| "eval_samples_per_second": 892.766, | |
| "eval_steps_per_second": 55.798, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.0886666666666667e-07, | |
| "loss": 2.0641, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 1.9421836137771606, | |
| "eval_runtime": 446.2468, | |
| "eval_samples_per_second": 896.365, | |
| "eval_steps_per_second": 56.023, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.9364625215530396, | |
| "eval_runtime": 446.5279, | |
| "eval_samples_per_second": 895.801, | |
| "eval_steps_per_second": 55.988, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 3.061333333333333e-07, | |
| "loss": 2.0692, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 1.941666603088379, | |
| "eval_runtime": 446.7472, | |
| "eval_samples_per_second": 895.361, | |
| "eval_steps_per_second": 55.96, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 1.938507318496704, | |
| "eval_runtime": 449.4705, | |
| "eval_samples_per_second": 889.936, | |
| "eval_steps_per_second": 55.621, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.034e-07, | |
| "loss": 2.0676, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 1.9362366199493408, | |
| "eval_runtime": 449.8, | |
| "eval_samples_per_second": 889.284, | |
| "eval_steps_per_second": 55.58, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 1.9413690567016602, | |
| "eval_runtime": 447.228, | |
| "eval_samples_per_second": 894.398, | |
| "eval_steps_per_second": 55.9, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.0066666666666663e-07, | |
| "loss": 2.0657, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 1.9437037706375122, | |
| "eval_runtime": 446.7561, | |
| "eval_samples_per_second": 895.343, | |
| "eval_steps_per_second": 55.959, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 1.935581922531128, | |
| "eval_runtime": 448.4477, | |
| "eval_samples_per_second": 891.966, | |
| "eval_steps_per_second": 55.748, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.9793333333333334e-07, | |
| "loss": 2.0638, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 1.9353160858154297, | |
| "eval_runtime": 447.7021, | |
| "eval_samples_per_second": 893.451, | |
| "eval_steps_per_second": 55.841, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.9384965896606445, | |
| "eval_runtime": 446.8195, | |
| "eval_samples_per_second": 895.216, | |
| "eval_steps_per_second": 55.951, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.952e-07, | |
| "loss": 2.0673, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 1.935878872871399, | |
| "eval_runtime": 447.5698, | |
| "eval_samples_per_second": 893.715, | |
| "eval_steps_per_second": 55.857, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 1.9314086437225342, | |
| "eval_runtime": 447.0842, | |
| "eval_samples_per_second": 894.686, | |
| "eval_steps_per_second": 55.918, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.9246666666666665e-07, | |
| "loss": 2.0634, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 1.9294040203094482, | |
| "eval_runtime": 447.3121, | |
| "eval_samples_per_second": 894.23, | |
| "eval_steps_per_second": 55.889, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 1.9346296787261963, | |
| "eval_runtime": 447.8515, | |
| "eval_samples_per_second": 893.153, | |
| "eval_steps_per_second": 55.822, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.897333333333333e-07, | |
| "loss": 2.0643, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 1.933471918106079, | |
| "eval_runtime": 446.8821, | |
| "eval_samples_per_second": 895.091, | |
| "eval_steps_per_second": 55.943, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.9316155910491943, | |
| "eval_runtime": 447.2102, | |
| "eval_samples_per_second": 894.434, | |
| "eval_steps_per_second": 55.902, | |
| "step": 712000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 2.8699999999999996e-07, | |
| "loss": 2.0596, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 1.9356091022491455, | |
| "eval_runtime": 450.1829, | |
| "eval_samples_per_second": 888.528, | |
| "eval_steps_per_second": 55.533, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_loss": 1.9390416145324707, | |
| "eval_runtime": 447.8923, | |
| "eval_samples_per_second": 893.072, | |
| "eval_steps_per_second": 55.817, | |
| "step": 728000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.8426666666666667e-07, | |
| "loss": 2.0637, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 1.9396628141403198, | |
| "eval_runtime": 447.225, | |
| "eval_samples_per_second": 894.404, | |
| "eval_steps_per_second": 55.9, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_loss": 1.9374940395355225, | |
| "eval_runtime": 450.2246, | |
| "eval_samples_per_second": 888.445, | |
| "eval_steps_per_second": 55.528, | |
| "step": 744000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2.815333333333333e-07, | |
| "loss": 2.0637, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 1.9351787567138672, | |
| "eval_runtime": 449.793, | |
| "eval_samples_per_second": 889.298, | |
| "eval_steps_per_second": 55.581, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 1.9309793710708618, | |
| "eval_runtime": 451.6574, | |
| "eval_samples_per_second": 885.627, | |
| "eval_steps_per_second": 55.352, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2.7880000000000003e-07, | |
| "loss": 2.0681, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 1.9316256046295166, | |
| "eval_runtime": 450.9965, | |
| "eval_samples_per_second": 886.925, | |
| "eval_steps_per_second": 55.433, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 1.9269251823425293, | |
| "eval_runtime": 451.9701, | |
| "eval_samples_per_second": 885.014, | |
| "eval_steps_per_second": 55.313, | |
| "step": 776000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 2.7606666666666664e-07, | |
| "loss": 2.0663, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_loss": 1.930124044418335, | |
| "eval_runtime": 450.7438, | |
| "eval_samples_per_second": 887.422, | |
| "eval_steps_per_second": 55.464, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 1.9354177713394165, | |
| "eval_runtime": 452.0689, | |
| "eval_samples_per_second": 884.821, | |
| "eval_steps_per_second": 55.301, | |
| "step": 792000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 2.733333333333333e-07, | |
| "loss": 2.0653, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_loss": 1.9372798204421997, | |
| "eval_runtime": 449.7405, | |
| "eval_samples_per_second": 889.402, | |
| "eval_steps_per_second": 55.588, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 1.935416579246521, | |
| "eval_runtime": 448.8481, | |
| "eval_samples_per_second": 891.17, | |
| "eval_steps_per_second": 55.698, | |
| "step": 808000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.706e-07, | |
| "loss": 2.0606, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 1.9285781383514404, | |
| "eval_runtime": 449.1658, | |
| "eval_samples_per_second": 890.54, | |
| "eval_steps_per_second": 55.659, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 1.9317643642425537, | |
| "eval_runtime": 454.8294, | |
| "eval_samples_per_second": 879.451, | |
| "eval_steps_per_second": 54.966, | |
| "step": 824000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.6786666666666666e-07, | |
| "loss": 2.0601, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_loss": 1.92868971824646, | |
| "eval_runtime": 451.6998, | |
| "eval_samples_per_second": 885.544, | |
| "eval_steps_per_second": 55.346, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_loss": 1.9279505014419556, | |
| "eval_runtime": 453.4329, | |
| "eval_samples_per_second": 882.159, | |
| "eval_steps_per_second": 55.135, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2.651333333333333e-07, | |
| "loss": 2.0555, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 1.9279268980026245, | |
| "eval_runtime": 452.6535, | |
| "eval_samples_per_second": 883.678, | |
| "eval_steps_per_second": 55.23, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 1.9296597242355347, | |
| "eval_runtime": 453.8201, | |
| "eval_samples_per_second": 881.407, | |
| "eval_steps_per_second": 55.088, | |
| "step": 856000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 2.624e-07, | |
| "loss": 2.0561, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 1.929028868675232, | |
| "eval_runtime": 449.3895, | |
| "eval_samples_per_second": 890.096, | |
| "eval_steps_per_second": 55.631, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_loss": 1.9251536130905151, | |
| "eval_runtime": 449.4314, | |
| "eval_samples_per_second": 890.014, | |
| "eval_steps_per_second": 55.626, | |
| "step": 872000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 2.596666666666667e-07, | |
| "loss": 2.066, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "eval_loss": 1.9274221658706665, | |
| "eval_runtime": 449.6898, | |
| "eval_samples_per_second": 889.502, | |
| "eval_steps_per_second": 55.594, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_loss": 1.9256700277328491, | |
| "eval_runtime": 454.59, | |
| "eval_samples_per_second": 879.914, | |
| "eval_steps_per_second": 54.995, | |
| "step": 888000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 2.5693333333333333e-07, | |
| "loss": 2.0634, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 1.9289941787719727, | |
| "eval_runtime": 450.5402, | |
| "eval_samples_per_second": 887.823, | |
| "eval_steps_per_second": 55.489, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_loss": 1.9266842603683472, | |
| "eval_runtime": 450.2964, | |
| "eval_samples_per_second": 888.304, | |
| "eval_steps_per_second": 55.519, | |
| "step": 904000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 2.542e-07, | |
| "loss": 2.0613, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_loss": 1.9295446872711182, | |
| "eval_runtime": 450.1243, | |
| "eval_samples_per_second": 888.643, | |
| "eval_steps_per_second": 55.54, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_loss": 1.9299752712249756, | |
| "eval_runtime": 450.6009, | |
| "eval_samples_per_second": 887.704, | |
| "eval_steps_per_second": 55.481, | |
| "step": 920000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 2.5146666666666664e-07, | |
| "loss": 2.0599, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_loss": 1.932616114616394, | |
| "eval_runtime": 451.4436, | |
| "eval_samples_per_second": 886.047, | |
| "eval_steps_per_second": 55.378, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 1.931321144104004, | |
| "eval_runtime": 453.239, | |
| "eval_samples_per_second": 882.537, | |
| "eval_steps_per_second": 55.159, | |
| "step": 936000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 2.4873333333333335e-07, | |
| "loss": 2.0592, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 1.9236520528793335, | |
| "eval_runtime": 450.6099, | |
| "eval_samples_per_second": 887.686, | |
| "eval_steps_per_second": 55.48, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 1.9271957874298096, | |
| "eval_runtime": 453.5158, | |
| "eval_samples_per_second": 881.998, | |
| "eval_steps_per_second": 55.125, | |
| "step": 952000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 2.46e-07, | |
| "loss": 2.0602, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 1.9260518550872803, | |
| "eval_runtime": 452.3583, | |
| "eval_samples_per_second": 884.255, | |
| "eval_steps_per_second": 55.266, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_loss": 1.9283181428909302, | |
| "eval_runtime": 451.1311, | |
| "eval_samples_per_second": 886.66, | |
| "eval_steps_per_second": 55.416, | |
| "step": 968000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 2.4326666666666666e-07, | |
| "loss": 2.0575, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 1.929377555847168, | |
| "eval_runtime": 453.899, | |
| "eval_samples_per_second": 881.253, | |
| "eval_steps_per_second": 55.078, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_loss": 1.9283651113510132, | |
| "eval_runtime": 451.3036, | |
| "eval_samples_per_second": 886.321, | |
| "eval_steps_per_second": 55.395, | |
| "step": 984000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 2.405333333333333e-07, | |
| "loss": 2.0585, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_loss": 1.926291823387146, | |
| "eval_runtime": 451.1498, | |
| "eval_samples_per_second": 886.623, | |
| "eval_steps_per_second": 55.414, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "eval_loss": 1.9226716756820679, | |
| "eval_runtime": 452.7662, | |
| "eval_samples_per_second": 883.458, | |
| "eval_steps_per_second": 55.216, | |
| "step": 1000000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 2.3779999999999997e-07, | |
| "loss": 2.0535, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 1.9251185655593872, | |
| "eval_runtime": 454.2127, | |
| "eval_samples_per_second": 880.645, | |
| "eval_steps_per_second": 55.04, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "eval_loss": 1.9273473024368286, | |
| "eval_runtime": 452.8001, | |
| "eval_samples_per_second": 883.392, | |
| "eval_steps_per_second": 55.212, | |
| "step": 1016000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 2.3506666666666668e-07, | |
| "loss": 2.062, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_loss": 1.9241611957550049, | |
| "eval_runtime": 452.8827, | |
| "eval_samples_per_second": 883.231, | |
| "eval_steps_per_second": 55.202, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 1.9242278337478638, | |
| "eval_runtime": 453.7634, | |
| "eval_samples_per_second": 881.517, | |
| "eval_steps_per_second": 55.095, | |
| "step": 1032000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.3233333333333334e-07, | |
| "loss": 2.0606, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_loss": 1.925549030303955, | |
| "eval_runtime": 451.5199, | |
| "eval_samples_per_second": 885.897, | |
| "eval_steps_per_second": 55.369, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "eval_loss": 1.9233018159866333, | |
| "eval_runtime": 453.1285, | |
| "eval_samples_per_second": 882.752, | |
| "eval_steps_per_second": 55.172, | |
| "step": 1048000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 2.2960000000000002e-07, | |
| "loss": 2.0565, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "eval_loss": 1.9242709875106812, | |
| "eval_runtime": 451.6366, | |
| "eval_samples_per_second": 885.668, | |
| "eval_steps_per_second": 55.354, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 1.9271726608276367, | |
| "eval_runtime": 452.6063, | |
| "eval_samples_per_second": 883.77, | |
| "eval_steps_per_second": 55.236, | |
| "step": 1064000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 2.2686666666666667e-07, | |
| "loss": 2.0538, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 1.9308254718780518, | |
| "eval_runtime": 452.9886, | |
| "eval_samples_per_second": 883.025, | |
| "eval_steps_per_second": 55.189, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 1.923595905303955, | |
| "eval_runtime": 454.1743, | |
| "eval_samples_per_second": 880.719, | |
| "eval_steps_per_second": 55.045, | |
| "step": 1080000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.2413333333333333e-07, | |
| "loss": 2.0573, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_loss": 1.9245961904525757, | |
| "eval_runtime": 453.1057, | |
| "eval_samples_per_second": 882.796, | |
| "eval_steps_per_second": 55.175, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "eval_loss": 1.9237180948257446, | |
| "eval_runtime": 453.1297, | |
| "eval_samples_per_second": 882.75, | |
| "eval_steps_per_second": 55.172, | |
| "step": 1096000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 2.214e-07, | |
| "loss": 2.0562, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_loss": 1.9198731184005737, | |
| "eval_runtime": 453.0177, | |
| "eval_samples_per_second": 882.968, | |
| "eval_steps_per_second": 55.185, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_loss": 1.9235132932662964, | |
| "eval_runtime": 452.6084, | |
| "eval_samples_per_second": 883.766, | |
| "eval_steps_per_second": 55.235, | |
| "step": 1112000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 2.1866666666666667e-07, | |
| "loss": 2.0534, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "eval_loss": 1.9209364652633667, | |
| "eval_runtime": 454.4995, | |
| "eval_samples_per_second": 880.089, | |
| "eval_steps_per_second": 55.006, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 1.9215258359909058, | |
| "eval_runtime": 454.5969, | |
| "eval_samples_per_second": 879.9, | |
| "eval_steps_per_second": 54.994, | |
| "step": 1128000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 2.1593333333333332e-07, | |
| "loss": 2.0567, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "eval_loss": 1.9241678714752197, | |
| "eval_runtime": 452.6555, | |
| "eval_samples_per_second": 883.674, | |
| "eval_steps_per_second": 55.23, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "eval_loss": 1.9272419214248657, | |
| "eval_runtime": 453.105, | |
| "eval_samples_per_second": 882.797, | |
| "eval_steps_per_second": 55.175, | |
| "step": 1144000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 2.132e-07, | |
| "loss": 2.0592, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 1.9257162809371948, | |
| "eval_runtime": 456.0338, | |
| "eval_samples_per_second": 877.128, | |
| "eval_steps_per_second": 54.82, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "eval_loss": 1.9228087663650513, | |
| "eval_runtime": 456.442, | |
| "eval_samples_per_second": 876.344, | |
| "eval_steps_per_second": 54.771, | |
| "step": 1160000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 2.1046666666666666e-07, | |
| "loss": 2.0599, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 1.9205422401428223, | |
| "eval_runtime": 455.2368, | |
| "eval_samples_per_second": 878.664, | |
| "eval_steps_per_second": 54.916, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_loss": 1.9189964532852173, | |
| "eval_runtime": 456.8477, | |
| "eval_samples_per_second": 875.565, | |
| "eval_steps_per_second": 54.723, | |
| "step": 1176000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 2.0773333333333334e-07, | |
| "loss": 2.0504, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 1.9240779876708984, | |
| "eval_runtime": 456.0663, | |
| "eval_samples_per_second": 877.065, | |
| "eval_steps_per_second": 54.817, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_loss": 1.9213923215866089, | |
| "eval_runtime": 454.1845, | |
| "eval_samples_per_second": 880.699, | |
| "eval_steps_per_second": 55.044, | |
| "step": 1192000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 2.05e-07, | |
| "loss": 2.0541, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 1.9264706373214722, | |
| "eval_runtime": 454.4773, | |
| "eval_samples_per_second": 880.132, | |
| "eval_steps_per_second": 55.008, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "eval_loss": 1.9250409603118896, | |
| "eval_runtime": 455.215, | |
| "eval_samples_per_second": 878.706, | |
| "eval_steps_per_second": 54.919, | |
| "step": 1208000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.0226666666666668e-07, | |
| "loss": 2.0581, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_loss": 1.9173840284347534, | |
| "eval_runtime": 455.628, | |
| "eval_samples_per_second": 877.909, | |
| "eval_steps_per_second": 54.869, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "eval_loss": 1.923222303390503, | |
| "eval_runtime": 454.8929, | |
| "eval_samples_per_second": 879.328, | |
| "eval_steps_per_second": 54.958, | |
| "step": 1224000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 1.9953333333333333e-07, | |
| "loss": 2.057, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "eval_loss": 1.92417311668396, | |
| "eval_runtime": 453.9991, | |
| "eval_samples_per_second": 881.059, | |
| "eval_steps_per_second": 55.066, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_loss": 1.920148491859436, | |
| "eval_runtime": 454.6117, | |
| "eval_samples_per_second": 879.872, | |
| "eval_steps_per_second": 54.992, | |
| "step": 1240000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 1.968e-07, | |
| "loss": 2.0541, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "eval_loss": 1.918699026107788, | |
| "eval_runtime": 454.7578, | |
| "eval_samples_per_second": 879.589, | |
| "eval_steps_per_second": 54.974, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "eval_loss": 1.9204912185668945, | |
| "eval_runtime": 456.9789, | |
| "eval_samples_per_second": 875.314, | |
| "eval_steps_per_second": 54.707, | |
| "step": 1256000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 1.9406666666666667e-07, | |
| "loss": 2.0542, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_loss": 1.9177594184875488, | |
| "eval_runtime": 454.9485, | |
| "eval_samples_per_second": 879.22, | |
| "eval_steps_per_second": 54.951, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "eval_loss": 1.923877477645874, | |
| "eval_runtime": 455.3795, | |
| "eval_samples_per_second": 878.388, | |
| "eval_steps_per_second": 54.899, | |
| "step": 1272000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 1.9133333333333333e-07, | |
| "loss": 2.0526, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "eval_loss": 1.9184619188308716, | |
| "eval_runtime": 455.3342, | |
| "eval_samples_per_second": 878.476, | |
| "eval_steps_per_second": 54.905, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "eval_loss": 1.9227157831192017, | |
| "eval_runtime": 455.665, | |
| "eval_samples_per_second": 877.838, | |
| "eval_steps_per_second": 54.865, | |
| "step": 1288000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 1.886e-07, | |
| "loss": 2.0503, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "eval_loss": 1.9222984313964844, | |
| "eval_runtime": 455.1314, | |
| "eval_samples_per_second": 878.867, | |
| "eval_steps_per_second": 54.929, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "eval_loss": 1.9229977130889893, | |
| "eval_runtime": 456.6723, | |
| "eval_samples_per_second": 875.902, | |
| "eval_steps_per_second": 54.744, | |
| "step": 1304000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 1.8586666666666666e-07, | |
| "loss": 2.0579, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_loss": 1.9143402576446533, | |
| "eval_runtime": 459.6633, | |
| "eval_samples_per_second": 870.202, | |
| "eval_steps_per_second": 54.388, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "eval_loss": 1.9187949895858765, | |
| "eval_runtime": 455.7334, | |
| "eval_samples_per_second": 877.706, | |
| "eval_steps_per_second": 54.857, | |
| "step": 1320000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 1.8313333333333332e-07, | |
| "loss": 2.0523, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_loss": 1.916965126991272, | |
| "eval_runtime": 460.7856, | |
| "eval_samples_per_second": 868.083, | |
| "eval_steps_per_second": 54.255, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "eval_loss": 1.9252265691757202, | |
| "eval_runtime": 461.7538, | |
| "eval_samples_per_second": 866.263, | |
| "eval_steps_per_second": 54.141, | |
| "step": 1336000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 1.804e-07, | |
| "loss": 2.056, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "eval_loss": 1.9182839393615723, | |
| "eval_runtime": 459.9309, | |
| "eval_samples_per_second": 869.696, | |
| "eval_steps_per_second": 54.356, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "eval_loss": 1.9236822128295898, | |
| "eval_runtime": 460.9421, | |
| "eval_samples_per_second": 867.788, | |
| "eval_steps_per_second": 54.237, | |
| "step": 1352000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 1.7766666666666666e-07, | |
| "loss": 2.0545, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 1.919832468032837, | |
| "eval_runtime": 459.7063, | |
| "eval_samples_per_second": 870.121, | |
| "eval_steps_per_second": 54.383, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "eval_loss": 1.9224891662597656, | |
| "eval_runtime": 457.5552, | |
| "eval_samples_per_second": 874.212, | |
| "eval_steps_per_second": 54.638, | |
| "step": 1368000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 1.7493333333333334e-07, | |
| "loss": 2.0552, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 1.9172176122665405, | |
| "eval_runtime": 458.1875, | |
| "eval_samples_per_second": 873.005, | |
| "eval_steps_per_second": 54.563, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "eval_loss": 1.9179189205169678, | |
| "eval_runtime": 460.0476, | |
| "eval_samples_per_second": 869.475, | |
| "eval_steps_per_second": 54.342, | |
| "step": 1384000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 1.722e-07, | |
| "loss": 2.0571, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_loss": 1.9238101243972778, | |
| "eval_runtime": 457.847, | |
| "eval_samples_per_second": 873.654, | |
| "eval_steps_per_second": 54.603, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_loss": 1.9188734292984009, | |
| "eval_runtime": 461.2969, | |
| "eval_samples_per_second": 867.12, | |
| "eval_steps_per_second": 54.195, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 1.6946666666666668e-07, | |
| "loss": 2.0637, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 1.9217091798782349, | |
| "eval_runtime": 460.9073, | |
| "eval_samples_per_second": 867.854, | |
| "eval_steps_per_second": 54.241, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_loss": 1.918999195098877, | |
| "eval_runtime": 461.2775, | |
| "eval_samples_per_second": 867.157, | |
| "eval_steps_per_second": 54.197, | |
| "step": 1416000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.6673333333333333e-07, | |
| "loss": 2.0554, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.9259402751922607, | |
| "eval_runtime": 460.6263, | |
| "eval_samples_per_second": 868.383, | |
| "eval_steps_per_second": 54.274, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "eval_loss": 1.9184104204177856, | |
| "eval_runtime": 456.8649, | |
| "eval_samples_per_second": 875.532, | |
| "eval_steps_per_second": 54.721, | |
| "step": 1432000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 1.64e-07, | |
| "loss": 2.0545, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 1.924387812614441, | |
| "eval_runtime": 460.2444, | |
| "eval_samples_per_second": 869.103, | |
| "eval_steps_per_second": 54.319, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_loss": 1.920113444328308, | |
| "eval_runtime": 458.5556, | |
| "eval_samples_per_second": 872.304, | |
| "eval_steps_per_second": 54.519, | |
| "step": 1448000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1.6126666666666667e-07, | |
| "loss": 2.0538, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 1.9250693321228027, | |
| "eval_runtime": 458.1637, | |
| "eval_samples_per_second": 873.05, | |
| "eval_steps_per_second": 54.566, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "eval_loss": 1.9216325283050537, | |
| "eval_runtime": 458.8324, | |
| "eval_samples_per_second": 871.778, | |
| "eval_steps_per_second": 54.486, | |
| "step": 1464000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 1.5853333333333332e-07, | |
| "loss": 2.058, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "eval_loss": 1.9220870733261108, | |
| "eval_runtime": 457.9425, | |
| "eval_samples_per_second": 873.472, | |
| "eval_steps_per_second": 54.592, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "eval_loss": 1.924748182296753, | |
| "eval_runtime": 459.3633, | |
| "eval_samples_per_second": 870.77, | |
| "eval_steps_per_second": 54.423, | |
| "step": 1480000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 1.558e-07, | |
| "loss": 2.0482, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "eval_loss": 1.9209040403366089, | |
| "eval_runtime": 458.2832, | |
| "eval_samples_per_second": 872.823, | |
| "eval_steps_per_second": 54.551, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_loss": 1.9206820726394653, | |
| "eval_runtime": 458.0167, | |
| "eval_samples_per_second": 873.331, | |
| "eval_steps_per_second": 54.583, | |
| "step": 1496000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 1.5306666666666666e-07, | |
| "loss": 2.0528, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "eval_loss": 1.9176584482192993, | |
| "eval_runtime": 460.0682, | |
| "eval_samples_per_second": 869.436, | |
| "eval_steps_per_second": 54.34, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "eval_loss": 1.91410231590271, | |
| "eval_runtime": 460.3351, | |
| "eval_samples_per_second": 868.932, | |
| "eval_steps_per_second": 54.308, | |
| "step": 1512000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.5033333333333332e-07, | |
| "loss": 2.0529, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_loss": 1.921297550201416, | |
| "eval_runtime": 458.1751, | |
| "eval_samples_per_second": 873.029, | |
| "eval_steps_per_second": 54.564, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "eval_loss": 1.9170490503311157, | |
| "eval_runtime": 459.8968, | |
| "eval_samples_per_second": 869.76, | |
| "eval_steps_per_second": 54.36, | |
| "step": 1528000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1.476e-07, | |
| "loss": 2.059, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 1.916093111038208, | |
| "eval_runtime": 460.0388, | |
| "eval_samples_per_second": 869.492, | |
| "eval_steps_per_second": 54.343, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "eval_loss": 1.9164094924926758, | |
| "eval_runtime": 458.9188, | |
| "eval_samples_per_second": 871.614, | |
| "eval_steps_per_second": 54.476, | |
| "step": 1544000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.4486666666666665e-07, | |
| "loss": 2.056, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_loss": 1.9176851511001587, | |
| "eval_runtime": 458.5111, | |
| "eval_samples_per_second": 872.389, | |
| "eval_steps_per_second": 54.524, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "eval_loss": 1.9188567399978638, | |
| "eval_runtime": 459.5705, | |
| "eval_samples_per_second": 870.378, | |
| "eval_steps_per_second": 54.399, | |
| "step": 1560000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 1.4213333333333334e-07, | |
| "loss": 2.058, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_loss": 1.9181184768676758, | |
| "eval_runtime": 461.1752, | |
| "eval_samples_per_second": 867.349, | |
| "eval_steps_per_second": 54.209, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "eval_loss": 1.9213508367538452, | |
| "eval_runtime": 460.4826, | |
| "eval_samples_per_second": 868.654, | |
| "eval_steps_per_second": 54.291, | |
| "step": 1576000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.3940000000000002e-07, | |
| "loss": 2.0543, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_loss": 1.9136959314346313, | |
| "eval_runtime": 459.174, | |
| "eval_samples_per_second": 871.129, | |
| "eval_steps_per_second": 54.446, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_loss": 1.9180983304977417, | |
| "eval_runtime": 458.6403, | |
| "eval_samples_per_second": 872.143, | |
| "eval_steps_per_second": 54.509, | |
| "step": 1592000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.3666666666666665e-07, | |
| "loss": 2.0513, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "eval_loss": 1.9187287092208862, | |
| "eval_runtime": 460.1583, | |
| "eval_samples_per_second": 869.266, | |
| "eval_steps_per_second": 54.329, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "eval_loss": 1.917602300643921, | |
| "eval_runtime": 459.5652, | |
| "eval_samples_per_second": 870.388, | |
| "eval_steps_per_second": 54.399, | |
| "step": 1608000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1.3393333333333333e-07, | |
| "loss": 2.0587, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_loss": 1.9144842624664307, | |
| "eval_runtime": 459.7836, | |
| "eval_samples_per_second": 869.974, | |
| "eval_steps_per_second": 54.373, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "eval_loss": 1.9191675186157227, | |
| "eval_runtime": 461.323, | |
| "eval_samples_per_second": 867.071, | |
| "eval_steps_per_second": 54.192, | |
| "step": 1624000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 1.312e-07, | |
| "loss": 2.053, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "eval_loss": 1.9202276468276978, | |
| "eval_runtime": 461.1419, | |
| "eval_samples_per_second": 867.412, | |
| "eval_steps_per_second": 54.213, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "eval_loss": 1.9182982444763184, | |
| "eval_runtime": 460.6765, | |
| "eval_samples_per_second": 868.288, | |
| "eval_steps_per_second": 54.268, | |
| "step": 1640000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 1.2846666666666667e-07, | |
| "loss": 2.0543, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "eval_loss": 1.9163408279418945, | |
| "eval_runtime": 460.4522, | |
| "eval_samples_per_second": 868.711, | |
| "eval_steps_per_second": 54.294, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_loss": 1.9171490669250488, | |
| "eval_runtime": 461.2694, | |
| "eval_samples_per_second": 867.172, | |
| "eval_steps_per_second": 54.198, | |
| "step": 1656000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.2573333333333332e-07, | |
| "loss": 2.0492, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 1.918287754058838, | |
| "eval_runtime": 461.4172, | |
| "eval_samples_per_second": 866.894, | |
| "eval_steps_per_second": 54.181, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_loss": 1.9172468185424805, | |
| "eval_runtime": 462.6921, | |
| "eval_samples_per_second": 864.506, | |
| "eval_steps_per_second": 54.032, | |
| "step": 1672000 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.23e-07, | |
| "loss": 2.0505, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 1.919048547744751, | |
| "eval_runtime": 461.0722, | |
| "eval_samples_per_second": 867.543, | |
| "eval_steps_per_second": 54.221, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_loss": 1.9181376695632935, | |
| "eval_runtime": 462.8167, | |
| "eval_samples_per_second": 864.273, | |
| "eval_steps_per_second": 54.017, | |
| "step": 1688000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.2026666666666666e-07, | |
| "loss": 2.0548, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "eval_loss": 1.916041612625122, | |
| "eval_runtime": 464.4737, | |
| "eval_samples_per_second": 861.19, | |
| "eval_steps_per_second": 53.824, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "eval_loss": 1.9167762994766235, | |
| "eval_runtime": 461.6336, | |
| "eval_samples_per_second": 866.488, | |
| "eval_steps_per_second": 54.156, | |
| "step": 1704000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 1.1753333333333334e-07, | |
| "loss": 2.0524, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_loss": 1.9155387878417969, | |
| "eval_runtime": 462.6415, | |
| "eval_samples_per_second": 864.6, | |
| "eval_steps_per_second": 54.038, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "eval_loss": 1.9161415100097656, | |
| "eval_runtime": 464.1686, | |
| "eval_samples_per_second": 861.756, | |
| "eval_steps_per_second": 53.86, | |
| "step": 1720000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 1.1480000000000001e-07, | |
| "loss": 2.0539, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "eval_loss": 1.9188584089279175, | |
| "eval_runtime": 460.6378, | |
| "eval_samples_per_second": 868.361, | |
| "eval_steps_per_second": 54.273, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "eval_loss": 1.916890263557434, | |
| "eval_runtime": 462.8071, | |
| "eval_samples_per_second": 864.291, | |
| "eval_steps_per_second": 54.018, | |
| "step": 1736000 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 1.1206666666666666e-07, | |
| "loss": 2.0542, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 1.91769278049469, | |
| "eval_runtime": 465.0529, | |
| "eval_samples_per_second": 860.117, | |
| "eval_steps_per_second": 53.757, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "eval_loss": 1.9140154123306274, | |
| "eval_runtime": 464.2522, | |
| "eval_samples_per_second": 861.601, | |
| "eval_steps_per_second": 53.85, | |
| "step": 1752000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1.0933333333333333e-07, | |
| "loss": 2.0509, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "eval_loss": 1.9151808023452759, | |
| "eval_runtime": 464.5418, | |
| "eval_samples_per_second": 861.064, | |
| "eval_steps_per_second": 53.816, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "eval_loss": 1.9160494804382324, | |
| "eval_runtime": 461.3857, | |
| "eval_samples_per_second": 866.954, | |
| "eval_steps_per_second": 54.185, | |
| "step": 1768000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 1.066e-07, | |
| "loss": 2.0507, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_loss": 1.9155534505844116, | |
| "eval_runtime": 462.7795, | |
| "eval_samples_per_second": 864.343, | |
| "eval_steps_per_second": 54.021, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_loss": 1.9139437675476074, | |
| "eval_runtime": 462.6977, | |
| "eval_samples_per_second": 864.495, | |
| "eval_steps_per_second": 54.031, | |
| "step": 1784000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 1.0386666666666667e-07, | |
| "loss": 2.057, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "eval_loss": 1.913998007774353, | |
| "eval_runtime": 463.7624, | |
| "eval_samples_per_second": 862.511, | |
| "eval_steps_per_second": 53.907, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "eval_loss": 1.924768090248108, | |
| "eval_runtime": 462.9309, | |
| "eval_samples_per_second": 864.06, | |
| "eval_steps_per_second": 54.004, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 1.0113333333333334e-07, | |
| "loss": 2.0515, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_loss": 1.914266586303711, | |
| "eval_runtime": 464.2581, | |
| "eval_samples_per_second": 861.59, | |
| "eval_steps_per_second": 53.849, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "eval_loss": 1.9187840223312378, | |
| "eval_runtime": 464.8964, | |
| "eval_samples_per_second": 860.407, | |
| "eval_steps_per_second": 53.775, | |
| "step": 1816000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 9.84e-08, | |
| "loss": 2.0503, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "eval_loss": 1.9127299785614014, | |
| "eval_runtime": 463.729, | |
| "eval_samples_per_second": 862.573, | |
| "eval_steps_per_second": 53.911, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_loss": 1.913232445716858, | |
| "eval_runtime": 463.083, | |
| "eval_samples_per_second": 863.776, | |
| "eval_steps_per_second": 53.986, | |
| "step": 1832000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 9.566666666666666e-08, | |
| "loss": 2.0534, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "eval_loss": 1.9128867387771606, | |
| "eval_runtime": 462.6549, | |
| "eval_samples_per_second": 864.575, | |
| "eval_steps_per_second": 54.036, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_loss": 1.9195021390914917, | |
| "eval_runtime": 465.694, | |
| "eval_samples_per_second": 858.933, | |
| "eval_steps_per_second": 53.683, | |
| "step": 1848000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 9.293333333333333e-08, | |
| "loss": 2.0553, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_loss": 1.9157421588897705, | |
| "eval_runtime": 463.4557, | |
| "eval_samples_per_second": 863.081, | |
| "eval_steps_per_second": 53.943, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "eval_loss": 1.9176615476608276, | |
| "eval_runtime": 465.2945, | |
| "eval_samples_per_second": 859.671, | |
| "eval_steps_per_second": 53.729, | |
| "step": 1864000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 9.02e-08, | |
| "loss": 2.0496, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "eval_loss": 1.9148454666137695, | |
| "eval_runtime": 466.7911, | |
| "eval_samples_per_second": 856.914, | |
| "eval_steps_per_second": 53.557, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "eval_loss": 1.9132306575775146, | |
| "eval_runtime": 465.1058, | |
| "eval_samples_per_second": 860.019, | |
| "eval_steps_per_second": 53.751, | |
| "step": 1880000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 8.746666666666667e-08, | |
| "loss": 2.0537, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_loss": 1.9183893203735352, | |
| "eval_runtime": 467.2319, | |
| "eval_samples_per_second": 856.106, | |
| "eval_steps_per_second": 53.507, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "eval_loss": 1.916000485420227, | |
| "eval_runtime": 467.99, | |
| "eval_samples_per_second": 854.719, | |
| "eval_steps_per_second": 53.42, | |
| "step": 1896000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 8.473333333333334e-08, | |
| "loss": 2.0505, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_loss": 1.9151054620742798, | |
| "eval_runtime": 466.6412, | |
| "eval_samples_per_second": 857.19, | |
| "eval_steps_per_second": 53.574, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_loss": 1.9209744930267334, | |
| "eval_runtime": 464.783, | |
| "eval_samples_per_second": 860.617, | |
| "eval_steps_per_second": 53.789, | |
| "step": 1912000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 8.2e-08, | |
| "loss": 2.0536, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "eval_loss": 1.91732656955719, | |
| "eval_runtime": 464.5366, | |
| "eval_samples_per_second": 861.073, | |
| "eval_steps_per_second": 53.817, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "eval_loss": 1.913880467414856, | |
| "eval_runtime": 464.6612, | |
| "eval_samples_per_second": 860.842, | |
| "eval_steps_per_second": 53.803, | |
| "step": 1928000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 7.926666666666666e-08, | |
| "loss": 2.0493, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "eval_loss": 1.9209164381027222, | |
| "eval_runtime": 464.8966, | |
| "eval_samples_per_second": 860.406, | |
| "eval_steps_per_second": 53.775, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "eval_loss": 1.915098786354065, | |
| "eval_runtime": 464.4023, | |
| "eval_samples_per_second": 861.322, | |
| "eval_steps_per_second": 53.833, | |
| "step": 1944000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 7.653333333333333e-08, | |
| "loss": 2.052, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_loss": 1.9173537492752075, | |
| "eval_runtime": 467.4898, | |
| "eval_samples_per_second": 855.634, | |
| "eval_steps_per_second": 53.477, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "eval_loss": 1.9146358966827393, | |
| "eval_runtime": 468.2303, | |
| "eval_samples_per_second": 854.28, | |
| "eval_steps_per_second": 53.393, | |
| "step": 1960000 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 7.38e-08, | |
| "loss": 2.0575, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "eval_loss": 1.916880488395691, | |
| "eval_runtime": 468.5926, | |
| "eval_samples_per_second": 853.62, | |
| "eval_steps_per_second": 53.351, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_loss": 1.917311668395996, | |
| "eval_runtime": 472.4841, | |
| "eval_samples_per_second": 846.589, | |
| "eval_steps_per_second": 52.912, | |
| "step": 1976000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 7.106666666666667e-08, | |
| "loss": 2.0499, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "eval_loss": 1.9174522161483765, | |
| "eval_runtime": 469.1988, | |
| "eval_samples_per_second": 852.517, | |
| "eval_steps_per_second": 53.282, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "eval_loss": 1.9136085510253906, | |
| "eval_runtime": 466.8287, | |
| "eval_samples_per_second": 856.845, | |
| "eval_steps_per_second": 53.553, | |
| "step": 1992000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 6.833333333333332e-08, | |
| "loss": 2.0573, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "eval_loss": 1.9158679246902466, | |
| "eval_runtime": 465.8052, | |
| "eval_samples_per_second": 858.728, | |
| "eval_steps_per_second": 53.671, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "eval_loss": 1.9147690534591675, | |
| "eval_runtime": 466.5227, | |
| "eval_samples_per_second": 857.407, | |
| "eval_steps_per_second": 53.588, | |
| "step": 2008000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 6.56e-08, | |
| "loss": 2.0556, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "eval_loss": 1.9174126386642456, | |
| "eval_runtime": 469.2355, | |
| "eval_samples_per_second": 852.45, | |
| "eval_steps_per_second": 53.278, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "eval_loss": 1.9146034717559814, | |
| "eval_runtime": 467.1331, | |
| "eval_samples_per_second": 856.287, | |
| "eval_steps_per_second": 53.518, | |
| "step": 2024000 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 6.286666666666666e-08, | |
| "loss": 2.0558, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "eval_loss": 1.9152125120162964, | |
| "eval_runtime": 468.9591, | |
| "eval_samples_per_second": 852.953, | |
| "eval_steps_per_second": 53.31, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "eval_loss": 1.9124705791473389, | |
| "eval_runtime": 465.7043, | |
| "eval_samples_per_second": 858.914, | |
| "eval_steps_per_second": 53.682, | |
| "step": 2040000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 6.013333333333333e-08, | |
| "loss": 2.0493, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "eval_loss": 1.915554165840149, | |
| "eval_runtime": 465.8577, | |
| "eval_samples_per_second": 858.631, | |
| "eval_steps_per_second": 53.664, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "eval_loss": 1.9120720624923706, | |
| "eval_runtime": 469.0695, | |
| "eval_samples_per_second": 852.752, | |
| "eval_steps_per_second": 53.297, | |
| "step": 2056000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 5.7400000000000004e-08, | |
| "loss": 2.0492, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_loss": 1.9226574897766113, | |
| "eval_runtime": 468.1309, | |
| "eval_samples_per_second": 854.462, | |
| "eval_steps_per_second": 53.404, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "eval_loss": 1.913604974746704, | |
| "eval_runtime": 468.2708, | |
| "eval_samples_per_second": 854.207, | |
| "eval_steps_per_second": 53.388, | |
| "step": 2072000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 5.4666666666666666e-08, | |
| "loss": 2.0576, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_loss": 1.9147344827651978, | |
| "eval_runtime": 467.7482, | |
| "eval_samples_per_second": 855.161, | |
| "eval_steps_per_second": 53.448, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "eval_loss": 1.9158565998077393, | |
| "eval_runtime": 469.501, | |
| "eval_samples_per_second": 851.968, | |
| "eval_steps_per_second": 53.248, | |
| "step": 2088000 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 5.1933333333333335e-08, | |
| "loss": 2.0512, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "eval_loss": 1.9115842580795288, | |
| "eval_runtime": 468.26, | |
| "eval_samples_per_second": 854.226, | |
| "eval_steps_per_second": 53.389, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_loss": 1.9158958196640015, | |
| "eval_runtime": 468.1507, | |
| "eval_samples_per_second": 854.426, | |
| "eval_steps_per_second": 53.402, | |
| "step": 2104000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.92e-08, | |
| "loss": 2.05, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_loss": 1.9130182266235352, | |
| "eval_runtime": 469.4638, | |
| "eval_samples_per_second": 852.036, | |
| "eval_steps_per_second": 53.252, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "eval_loss": 1.9151562452316284, | |
| "eval_runtime": 467.3378, | |
| "eval_samples_per_second": 855.912, | |
| "eval_steps_per_second": 53.494, | |
| "step": 2120000 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 4.6466666666666666e-08, | |
| "loss": 2.0437, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_loss": 1.9175945520401, | |
| "eval_runtime": 468.2097, | |
| "eval_samples_per_second": 854.318, | |
| "eval_steps_per_second": 53.395, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_loss": 1.9192650318145752, | |
| "eval_runtime": 468.4437, | |
| "eval_samples_per_second": 853.891, | |
| "eval_steps_per_second": 53.368, | |
| "step": 2136000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.3733333333333335e-08, | |
| "loss": 2.053, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 1.912379503250122, | |
| "eval_runtime": 471.2112, | |
| "eval_samples_per_second": 848.876, | |
| "eval_steps_per_second": 53.055, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "eval_loss": 1.9138758182525635, | |
| "eval_runtime": 468.8194, | |
| "eval_samples_per_second": 853.207, | |
| "eval_steps_per_second": 53.325, | |
| "step": 2152000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.1e-08, | |
| "loss": 2.0496, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 1.9128222465515137, | |
| "eval_runtime": 467.3919, | |
| "eval_samples_per_second": 855.813, | |
| "eval_steps_per_second": 53.488, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "eval_loss": 1.9161826372146606, | |
| "eval_runtime": 468.6823, | |
| "eval_samples_per_second": 853.457, | |
| "eval_steps_per_second": 53.341, | |
| "step": 2168000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 3.8266666666666665e-08, | |
| "loss": 2.0495, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "eval_loss": 1.9065207242965698, | |
| "eval_runtime": 469.3819, | |
| "eval_samples_per_second": 852.185, | |
| "eval_steps_per_second": 53.262, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_loss": 1.921074628829956, | |
| "eval_runtime": 469.081, | |
| "eval_samples_per_second": 852.731, | |
| "eval_steps_per_second": 53.296, | |
| "step": 2184000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 3.5533333333333334e-08, | |
| "loss": 2.0468, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "eval_loss": 1.9094847440719604, | |
| "eval_runtime": 468.9812, | |
| "eval_samples_per_second": 852.913, | |
| "eval_steps_per_second": 53.307, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "eval_loss": 1.9163267612457275, | |
| "eval_runtime": 468.7925, | |
| "eval_samples_per_second": 853.256, | |
| "eval_steps_per_second": 53.329, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 3.28e-08, | |
| "loss": 2.0507, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_loss": 1.9105992317199707, | |
| "eval_runtime": 471.2899, | |
| "eval_samples_per_second": 848.734, | |
| "eval_steps_per_second": 53.046, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "eval_loss": 1.9164973497390747, | |
| "eval_runtime": 469.3289, | |
| "eval_samples_per_second": 852.281, | |
| "eval_steps_per_second": 53.268, | |
| "step": 2216000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 3.0066666666666665e-08, | |
| "loss": 2.0526, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "eval_loss": 1.9179142713546753, | |
| "eval_runtime": 469.3963, | |
| "eval_samples_per_second": 852.158, | |
| "eval_steps_per_second": 53.26, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "eval_loss": 1.9178262948989868, | |
| "eval_runtime": 473.0856, | |
| "eval_samples_per_second": 845.513, | |
| "eval_steps_per_second": 52.845, | |
| "step": 2232000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 2.7333333333333333e-08, | |
| "loss": 2.0537, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "eval_loss": 1.9163259267807007, | |
| "eval_runtime": 469.0021, | |
| "eval_samples_per_second": 852.875, | |
| "eval_steps_per_second": 53.305, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "eval_loss": 1.9158776998519897, | |
| "eval_runtime": 470.6196, | |
| "eval_samples_per_second": 849.943, | |
| "eval_steps_per_second": 53.121, | |
| "step": 2248000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 2.46e-08, | |
| "loss": 2.0502, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "eval_loss": 1.9146416187286377, | |
| "eval_runtime": 469.9739, | |
| "eval_samples_per_second": 851.111, | |
| "eval_steps_per_second": 53.194, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_loss": 1.916868805885315, | |
| "eval_runtime": 469.5771, | |
| "eval_samples_per_second": 851.83, | |
| "eval_steps_per_second": 53.239, | |
| "step": 2264000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 2.1866666666666667e-08, | |
| "loss": 2.0492, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 1.9164165258407593, | |
| "eval_runtime": 472.7938, | |
| "eval_samples_per_second": 846.035, | |
| "eval_steps_per_second": 52.877, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_loss": 1.915380835533142, | |
| "eval_runtime": 469.8644, | |
| "eval_samples_per_second": 851.309, | |
| "eval_steps_per_second": 53.207, | |
| "step": 2280000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 1.9133333333333333e-08, | |
| "loss": 2.0505, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "eval_loss": 1.9065546989440918, | |
| "eval_runtime": 471.3395, | |
| "eval_samples_per_second": 848.645, | |
| "eval_steps_per_second": 53.04, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 1.9140393733978271, | |
| "eval_runtime": 469.7103, | |
| "eval_samples_per_second": 851.589, | |
| "eval_steps_per_second": 53.224, | |
| "step": 2296000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 1.64e-08, | |
| "loss": 2.0516, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "eval_loss": 1.9124903678894043, | |
| "eval_runtime": 471.0408, | |
| "eval_samples_per_second": 849.183, | |
| "eval_steps_per_second": 53.074, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "eval_loss": 1.918357014656067, | |
| "eval_runtime": 471.1356, | |
| "eval_samples_per_second": 849.012, | |
| "eval_steps_per_second": 53.063, | |
| "step": 2312000 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 1.3666666666666667e-08, | |
| "loss": 2.0559, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "eval_loss": 1.9178434610366821, | |
| "eval_runtime": 471.2114, | |
| "eval_samples_per_second": 848.876, | |
| "eval_steps_per_second": 53.055, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_loss": 1.9164119958877563, | |
| "eval_runtime": 471.4668, | |
| "eval_samples_per_second": 848.416, | |
| "eval_steps_per_second": 53.026, | |
| "step": 2328000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 1.0933333333333334e-08, | |
| "loss": 2.0528, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_loss": 1.9086965322494507, | |
| "eval_runtime": 472.3709, | |
| "eval_samples_per_second": 846.792, | |
| "eval_steps_per_second": 52.925, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "eval_loss": 1.9164988994598389, | |
| "eval_runtime": 472.0245, | |
| "eval_samples_per_second": 847.414, | |
| "eval_steps_per_second": 52.963, | |
| "step": 2344000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 8.2e-09, | |
| "loss": 2.0559, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "eval_loss": 1.9113143682479858, | |
| "eval_runtime": 472.9967, | |
| "eval_samples_per_second": 845.672, | |
| "eval_steps_per_second": 52.854, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_loss": 1.914596676826477, | |
| "eval_runtime": 474.1092, | |
| "eval_samples_per_second": 843.687, | |
| "eval_steps_per_second": 52.73, | |
| "step": 2360000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 5.466666666666667e-09, | |
| "loss": 2.058, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_loss": 1.9156023263931274, | |
| "eval_runtime": 472.5333, | |
| "eval_samples_per_second": 846.501, | |
| "eval_steps_per_second": 52.906, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.9136894941329956, | |
| "eval_runtime": 476.1927, | |
| "eval_samples_per_second": 839.996, | |
| "eval_steps_per_second": 52.5, | |
| "step": 2376000 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 2.7333333333333334e-09, | |
| "loss": 2.053, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "eval_loss": 1.9081106185913086, | |
| "eval_runtime": 473.1832, | |
| "eval_samples_per_second": 845.339, | |
| "eval_steps_per_second": 52.834, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "eval_loss": 1.9148355722427368, | |
| "eval_runtime": 472.3079, | |
| "eval_samples_per_second": 846.905, | |
| "eval_steps_per_second": 52.932, | |
| "step": 2392000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.0, | |
| "loss": 2.0566, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "eval_loss": 1.9141788482666016, | |
| "eval_runtime": 473.7193, | |
| "eval_samples_per_second": 844.382, | |
| "eval_steps_per_second": 52.774, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "step": 2400000, | |
| "total_flos": 1.620927064872531e+18, | |
| "train_loss": 2.0669708544921876, | |
| "train_runtime": 368218.0367, | |
| "train_samples_per_second": 208.572, | |
| "train_steps_per_second": 6.518 | |
| } | |
| ], | |
| "logging_steps": 16000, | |
| "max_steps": 2400000, | |
| "num_train_epochs": 11, | |
| "save_steps": 32000, | |
| "total_flos": 1.620927064872531e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |