| { | |
| "best_metric": 2.596395254135132, | |
| "best_model_checkpoint": "./model_tweets_2020_Q4_50/checkpoint-2112000", | |
| "epoch": 10.105348255564257, | |
| "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": 2.9659674167633057, | |
| "eval_runtime": 427.2887, | |
| "eval_samples_per_second": 468.063, | |
| "eval_steps_per_second": 29.254, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.0726666666666665e-07, | |
| "loss": 3.1627, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.875443458557129, | |
| "eval_runtime": 428.9511, | |
| "eval_samples_per_second": 466.249, | |
| "eval_steps_per_second": 29.141, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 2.8262600898742676, | |
| "eval_runtime": 428.7189, | |
| "eval_samples_per_second": 466.501, | |
| "eval_steps_per_second": 29.157, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.0453333333333336e-07, | |
| "loss": 2.9611, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 2.7973239421844482, | |
| "eval_runtime": 427.7192, | |
| "eval_samples_per_second": 467.592, | |
| "eval_steps_per_second": 29.225, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 2.774101734161377, | |
| "eval_runtime": 430.9135, | |
| "eval_samples_per_second": 464.126, | |
| "eval_steps_per_second": 29.008, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.018e-07, | |
| "loss": 2.8986, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.757391929626465, | |
| "eval_runtime": 434.8184, | |
| "eval_samples_per_second": 459.958, | |
| "eval_steps_per_second": 28.748, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 2.741281509399414, | |
| "eval_runtime": 431.3008, | |
| "eval_samples_per_second": 463.709, | |
| "eval_steps_per_second": 28.982, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.9906666666666667e-07, | |
| "loss": 2.8726, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.724008798599243, | |
| "eval_runtime": 431.9972, | |
| "eval_samples_per_second": 462.961, | |
| "eval_steps_per_second": 28.935, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 2.7238657474517822, | |
| "eval_runtime": 428.6784, | |
| "eval_samples_per_second": 466.546, | |
| "eval_steps_per_second": 29.159, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.963333333333333e-07, | |
| "loss": 2.8558, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 2.7132034301757812, | |
| "eval_runtime": 428.5232, | |
| "eval_samples_per_second": 466.714, | |
| "eval_steps_per_second": 29.17, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 2.702976942062378, | |
| "eval_runtime": 434.0957, | |
| "eval_samples_per_second": 460.723, | |
| "eval_steps_per_second": 28.795, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.936e-07, | |
| "loss": 2.8459, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 2.7112441062927246, | |
| "eval_runtime": 430.6879, | |
| "eval_samples_per_second": 464.369, | |
| "eval_steps_per_second": 29.023, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.6918396949768066, | |
| "eval_runtime": 432.9686, | |
| "eval_samples_per_second": 461.923, | |
| "eval_steps_per_second": 28.87, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3.908666666666667e-07, | |
| "loss": 2.8379, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 2.701714515686035, | |
| "eval_runtime": 431.7861, | |
| "eval_samples_per_second": 463.188, | |
| "eval_steps_per_second": 28.95, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.6920413970947266, | |
| "eval_runtime": 432.0079, | |
| "eval_samples_per_second": 462.95, | |
| "eval_steps_per_second": 28.935, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.8813333333333334e-07, | |
| "loss": 2.8265, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 2.6970582008361816, | |
| "eval_runtime": 428.3996, | |
| "eval_samples_per_second": 466.849, | |
| "eval_steps_per_second": 29.178, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 2.692416191101074, | |
| "eval_runtime": 431.1394, | |
| "eval_samples_per_second": 463.882, | |
| "eval_steps_per_second": 28.993, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.854e-07, | |
| "loss": 2.8227, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 2.69515323638916, | |
| "eval_runtime": 428.2249, | |
| "eval_samples_per_second": 467.04, | |
| "eval_steps_per_second": 29.19, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 2.681142807006836, | |
| "eval_runtime": 427.7295, | |
| "eval_samples_per_second": 467.581, | |
| "eval_steps_per_second": 29.224, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.8266666666666665e-07, | |
| "loss": 2.8209, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 2.6828596591949463, | |
| "eval_runtime": 429.1179, | |
| "eval_samples_per_second": 466.068, | |
| "eval_steps_per_second": 29.13, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 2.6882851123809814, | |
| "eval_runtime": 430.1324, | |
| "eval_samples_per_second": 464.968, | |
| "eval_steps_per_second": 29.061, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.799333333333333e-07, | |
| "loss": 2.8147, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 2.6675167083740234, | |
| "eval_runtime": 428.1706, | |
| "eval_samples_per_second": 467.099, | |
| "eval_steps_per_second": 29.194, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 2.66744327545166, | |
| "eval_runtime": 427.87, | |
| "eval_samples_per_second": 467.427, | |
| "eval_steps_per_second": 29.214, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.772e-07, | |
| "loss": 2.8077, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 2.6661171913146973, | |
| "eval_runtime": 426.1667, | |
| "eval_samples_per_second": 469.295, | |
| "eval_steps_per_second": 29.331, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 2.6773271560668945, | |
| "eval_runtime": 430.5929, | |
| "eval_samples_per_second": 464.471, | |
| "eval_steps_per_second": 29.03, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.7446666666666667e-07, | |
| "loss": 2.8058, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 2.6734445095062256, | |
| "eval_runtime": 431.7928, | |
| "eval_samples_per_second": 463.18, | |
| "eval_steps_per_second": 28.949, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 2.6741647720336914, | |
| "eval_runtime": 433.2608, | |
| "eval_samples_per_second": 461.611, | |
| "eval_steps_per_second": 28.851, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.7173333333333333e-07, | |
| "loss": 2.812, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 2.6665947437286377, | |
| "eval_runtime": 429.9196, | |
| "eval_samples_per_second": 465.199, | |
| "eval_steps_per_second": 29.075, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 2.6641786098480225, | |
| "eval_runtime": 432.0068, | |
| "eval_samples_per_second": 462.951, | |
| "eval_steps_per_second": 28.935, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.69e-07, | |
| "loss": 2.8025, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 2.668074607849121, | |
| "eval_runtime": 429.4276, | |
| "eval_samples_per_second": 465.732, | |
| "eval_steps_per_second": 29.109, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 2.6663010120391846, | |
| "eval_runtime": 430.5757, | |
| "eval_samples_per_second": 464.49, | |
| "eval_steps_per_second": 29.031, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.6626666666666664e-07, | |
| "loss": 2.809, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 2.6645491123199463, | |
| "eval_runtime": 429.4305, | |
| "eval_samples_per_second": 465.728, | |
| "eval_steps_per_second": 29.108, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 2.6528775691986084, | |
| "eval_runtime": 430.2815, | |
| "eval_samples_per_second": 464.807, | |
| "eval_steps_per_second": 29.051, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.6353333333333335e-07, | |
| "loss": 2.8073, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.662346839904785, | |
| "eval_runtime": 427.2132, | |
| "eval_samples_per_second": 468.146, | |
| "eval_steps_per_second": 29.259, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 2.655132293701172, | |
| "eval_runtime": 427.6981, | |
| "eval_samples_per_second": 467.615, | |
| "eval_steps_per_second": 29.226, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.608e-07, | |
| "loss": 2.8005, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 2.664275646209717, | |
| "eval_runtime": 428.4044, | |
| "eval_samples_per_second": 466.844, | |
| "eval_steps_per_second": 29.178, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 2.6627519130706787, | |
| "eval_runtime": 432.9315, | |
| "eval_samples_per_second": 461.962, | |
| "eval_steps_per_second": 28.873, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.5806666666666666e-07, | |
| "loss": 2.7988, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 2.658301591873169, | |
| "eval_runtime": 430.042, | |
| "eval_samples_per_second": 465.066, | |
| "eval_steps_per_second": 29.067, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 2.659410238265991, | |
| "eval_runtime": 430.2191, | |
| "eval_samples_per_second": 464.875, | |
| "eval_steps_per_second": 29.055, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.553333333333333e-07, | |
| "loss": 2.7887, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 2.654367685317993, | |
| "eval_runtime": 428.3466, | |
| "eval_samples_per_second": 466.907, | |
| "eval_steps_per_second": 29.182, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 2.6515774726867676, | |
| "eval_runtime": 428.1496, | |
| "eval_samples_per_second": 467.122, | |
| "eval_steps_per_second": 29.195, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.5259999999999997e-07, | |
| "loss": 2.7964, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 2.655459403991699, | |
| "eval_runtime": 428.9032, | |
| "eval_samples_per_second": 466.301, | |
| "eval_steps_per_second": 29.144, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 2.65506911277771, | |
| "eval_runtime": 431.185, | |
| "eval_samples_per_second": 463.833, | |
| "eval_steps_per_second": 28.99, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.498666666666667e-07, | |
| "loss": 2.7919, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 2.6507833003997803, | |
| "eval_runtime": 429.9054, | |
| "eval_samples_per_second": 465.214, | |
| "eval_steps_per_second": 29.076, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 2.648573637008667, | |
| "eval_runtime": 426.8576, | |
| "eval_samples_per_second": 468.536, | |
| "eval_steps_per_second": 29.284, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.4713333333333333e-07, | |
| "loss": 2.8058, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 2.648383140563965, | |
| "eval_runtime": 426.9677, | |
| "eval_samples_per_second": 468.415, | |
| "eval_steps_per_second": 29.276, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 2.653191566467285, | |
| "eval_runtime": 429.3713, | |
| "eval_samples_per_second": 465.793, | |
| "eval_steps_per_second": 29.112, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.444e-07, | |
| "loss": 2.796, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 2.6472740173339844, | |
| "eval_runtime": 426.8024, | |
| "eval_samples_per_second": 468.596, | |
| "eval_steps_per_second": 29.288, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 2.6489272117614746, | |
| "eval_runtime": 428.8708, | |
| "eval_samples_per_second": 466.336, | |
| "eval_steps_per_second": 29.146, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.416666666666667e-07, | |
| "loss": 2.799, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 2.6475629806518555, | |
| "eval_runtime": 427.9765, | |
| "eval_samples_per_second": 467.311, | |
| "eval_steps_per_second": 29.207, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 2.6416804790496826, | |
| "eval_runtime": 426.9442, | |
| "eval_samples_per_second": 468.441, | |
| "eval_steps_per_second": 29.278, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.3893333333333335e-07, | |
| "loss": 2.7991, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 2.6544759273529053, | |
| "eval_runtime": 427.1377, | |
| "eval_samples_per_second": 468.228, | |
| "eval_steps_per_second": 29.265, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 2.6465859413146973, | |
| "eval_runtime": 428.9124, | |
| "eval_samples_per_second": 466.291, | |
| "eval_steps_per_second": 29.143, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.3619999999999995e-07, | |
| "loss": 2.792, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 2.6396875381469727, | |
| "eval_runtime": 428.572, | |
| "eval_samples_per_second": 466.661, | |
| "eval_steps_per_second": 29.167, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 2.642756938934326, | |
| "eval_runtime": 428.9912, | |
| "eval_samples_per_second": 466.205, | |
| "eval_steps_per_second": 29.138, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.3346666666666666e-07, | |
| "loss": 2.7972, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 2.644583225250244, | |
| "eval_runtime": 427.6258, | |
| "eval_samples_per_second": 467.694, | |
| "eval_steps_per_second": 29.231, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 2.6433892250061035, | |
| "eval_runtime": 429.7813, | |
| "eval_samples_per_second": 465.348, | |
| "eval_steps_per_second": 29.085, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.307333333333333e-07, | |
| "loss": 2.798, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 2.648988962173462, | |
| "eval_runtime": 429.7597, | |
| "eval_samples_per_second": 465.372, | |
| "eval_steps_per_second": 29.086, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 2.6502037048339844, | |
| "eval_runtime": 430.0385, | |
| "eval_samples_per_second": 465.07, | |
| "eval_steps_per_second": 29.067, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.28e-07, | |
| "loss": 2.7914, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 2.6407032012939453, | |
| "eval_runtime": 430.7536, | |
| "eval_samples_per_second": 464.298, | |
| "eval_steps_per_second": 29.019, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 2.6283910274505615, | |
| "eval_runtime": 433.2696, | |
| "eval_samples_per_second": 461.602, | |
| "eval_steps_per_second": 28.85, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.252666666666667e-07, | |
| "loss": 2.7932, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 2.642556667327881, | |
| "eval_runtime": 432.5252, | |
| "eval_samples_per_second": 462.396, | |
| "eval_steps_per_second": 28.9, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 2.6423070430755615, | |
| "eval_runtime": 432.6328, | |
| "eval_samples_per_second": 462.281, | |
| "eval_steps_per_second": 28.893, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.2253333333333334e-07, | |
| "loss": 2.787, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 2.638451337814331, | |
| "eval_runtime": 436.1841, | |
| "eval_samples_per_second": 458.517, | |
| "eval_steps_per_second": 28.658, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 2.6388065814971924, | |
| "eval_runtime": 430.5381, | |
| "eval_samples_per_second": 464.53, | |
| "eval_steps_per_second": 29.033, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.198e-07, | |
| "loss": 2.7893, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 2.642207145690918, | |
| "eval_runtime": 428.0052, | |
| "eval_samples_per_second": 467.279, | |
| "eval_steps_per_second": 29.205, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 2.6409590244293213, | |
| "eval_runtime": 429.1736, | |
| "eval_samples_per_second": 466.007, | |
| "eval_steps_per_second": 29.126, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.1706666666666665e-07, | |
| "loss": 2.7889, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 2.633716583251953, | |
| "eval_runtime": 430.2951, | |
| "eval_samples_per_second": 464.793, | |
| "eval_steps_per_second": 29.05, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 2.627978801727295, | |
| "eval_runtime": 437.5919, | |
| "eval_samples_per_second": 457.042, | |
| "eval_steps_per_second": 28.565, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 3.1433333333333336e-07, | |
| "loss": 2.791, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 2.6364176273345947, | |
| "eval_runtime": 435.9143, | |
| "eval_samples_per_second": 458.801, | |
| "eval_steps_per_second": 28.675, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 2.6341359615325928, | |
| "eval_runtime": 436.6584, | |
| "eval_samples_per_second": 458.019, | |
| "eval_steps_per_second": 28.626, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.116e-07, | |
| "loss": 2.7883, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 2.6317176818847656, | |
| "eval_runtime": 433.1883, | |
| "eval_samples_per_second": 461.688, | |
| "eval_steps_per_second": 28.856, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 2.6277999877929688, | |
| "eval_runtime": 430.7277, | |
| "eval_samples_per_second": 464.326, | |
| "eval_steps_per_second": 29.021, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.0886666666666667e-07, | |
| "loss": 2.7889, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 2.635715961456299, | |
| "eval_runtime": 431.7357, | |
| "eval_samples_per_second": 463.242, | |
| "eval_steps_per_second": 28.953, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 2.6340713500976562, | |
| "eval_runtime": 431.0234, | |
| "eval_samples_per_second": 464.007, | |
| "eval_steps_per_second": 29.001, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 3.061333333333333e-07, | |
| "loss": 2.7838, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 2.633284091949463, | |
| "eval_runtime": 430.0207, | |
| "eval_samples_per_second": 465.089, | |
| "eval_steps_per_second": 29.068, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 2.638205051422119, | |
| "eval_runtime": 430.4236, | |
| "eval_samples_per_second": 464.654, | |
| "eval_steps_per_second": 29.041, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.034e-07, | |
| "loss": 2.7873, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 2.6274592876434326, | |
| "eval_runtime": 429.469, | |
| "eval_samples_per_second": 465.687, | |
| "eval_steps_per_second": 29.106, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 2.6260039806365967, | |
| "eval_runtime": 430.4416, | |
| "eval_samples_per_second": 464.634, | |
| "eval_steps_per_second": 29.04, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.0066666666666663e-07, | |
| "loss": 2.7813, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 2.63725209236145, | |
| "eval_runtime": 430.3994, | |
| "eval_samples_per_second": 464.68, | |
| "eval_steps_per_second": 29.043, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 2.6348888874053955, | |
| "eval_runtime": 430.1402, | |
| "eval_samples_per_second": 464.96, | |
| "eval_steps_per_second": 29.06, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.9793333333333334e-07, | |
| "loss": 2.7858, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.622281789779663, | |
| "eval_runtime": 429.8357, | |
| "eval_samples_per_second": 465.289, | |
| "eval_steps_per_second": 29.081, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 2.6275925636291504, | |
| "eval_runtime": 429.5654, | |
| "eval_samples_per_second": 465.582, | |
| "eval_steps_per_second": 29.099, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.952e-07, | |
| "loss": 2.7895, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 2.6354682445526123, | |
| "eval_runtime": 432.8071, | |
| "eval_samples_per_second": 462.095, | |
| "eval_steps_per_second": 28.881, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 2.6269936561584473, | |
| "eval_runtime": 431.2646, | |
| "eval_samples_per_second": 463.748, | |
| "eval_steps_per_second": 28.985, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.9246666666666665e-07, | |
| "loss": 2.7873, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 2.624408006668091, | |
| "eval_runtime": 431.1254, | |
| "eval_samples_per_second": 463.898, | |
| "eval_steps_per_second": 28.994, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 2.6397435665130615, | |
| "eval_runtime": 428.8853, | |
| "eval_samples_per_second": 466.32, | |
| "eval_steps_per_second": 29.145, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.897333333333333e-07, | |
| "loss": 2.7866, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 2.6303048133850098, | |
| "eval_runtime": 428.8276, | |
| "eval_samples_per_second": 466.383, | |
| "eval_steps_per_second": 29.149, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.6166625022888184, | |
| "eval_runtime": 430.118, | |
| "eval_samples_per_second": 464.984, | |
| "eval_steps_per_second": 29.062, | |
| "step": 712000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 2.8699999999999996e-07, | |
| "loss": 2.7865, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 2.6264894008636475, | |
| "eval_runtime": 430.8627, | |
| "eval_samples_per_second": 464.18, | |
| "eval_steps_per_second": 29.012, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_loss": 2.640347957611084, | |
| "eval_runtime": 433.7872, | |
| "eval_samples_per_second": 461.051, | |
| "eval_steps_per_second": 28.816, | |
| "step": 728000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.8426666666666667e-07, | |
| "loss": 2.7716, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 2.6247291564941406, | |
| "eval_runtime": 428.0225, | |
| "eval_samples_per_second": 467.26, | |
| "eval_steps_per_second": 29.204, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_loss": 2.625520706176758, | |
| "eval_runtime": 430.348, | |
| "eval_samples_per_second": 464.736, | |
| "eval_steps_per_second": 29.046, | |
| "step": 744000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2.815333333333333e-07, | |
| "loss": 2.779, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 2.6315715312957764, | |
| "eval_runtime": 429.049, | |
| "eval_samples_per_second": 466.143, | |
| "eval_steps_per_second": 29.134, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 2.6269681453704834, | |
| "eval_runtime": 429.2822, | |
| "eval_samples_per_second": 465.889, | |
| "eval_steps_per_second": 29.118, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2.7880000000000003e-07, | |
| "loss": 2.7811, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 2.626842498779297, | |
| "eval_runtime": 430.4013, | |
| "eval_samples_per_second": 464.678, | |
| "eval_steps_per_second": 29.043, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 2.6146929264068604, | |
| "eval_runtime": 427.5353, | |
| "eval_samples_per_second": 467.793, | |
| "eval_steps_per_second": 29.237, | |
| "step": 776000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 2.7606666666666664e-07, | |
| "loss": 2.7797, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_loss": 2.6270837783813477, | |
| "eval_runtime": 429.6573, | |
| "eval_samples_per_second": 465.483, | |
| "eval_steps_per_second": 29.093, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 2.6242685317993164, | |
| "eval_runtime": 427.6055, | |
| "eval_samples_per_second": 467.716, | |
| "eval_steps_per_second": 29.233, | |
| "step": 792000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 2.733333333333333e-07, | |
| "loss": 2.7798, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_loss": 2.623974323272705, | |
| "eval_runtime": 428.5522, | |
| "eval_samples_per_second": 466.683, | |
| "eval_steps_per_second": 29.168, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 2.622472047805786, | |
| "eval_runtime": 434.6013, | |
| "eval_samples_per_second": 460.187, | |
| "eval_steps_per_second": 28.762, | |
| "step": 808000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.706e-07, | |
| "loss": 2.7774, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 2.6231884956359863, | |
| "eval_runtime": 429.2208, | |
| "eval_samples_per_second": 465.956, | |
| "eval_steps_per_second": 29.123, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 2.6246674060821533, | |
| "eval_runtime": 427.3461, | |
| "eval_samples_per_second": 468.0, | |
| "eval_steps_per_second": 29.25, | |
| "step": 824000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.6786666666666666e-07, | |
| "loss": 2.7744, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_loss": 2.6269562244415283, | |
| "eval_runtime": 427.4671, | |
| "eval_samples_per_second": 467.868, | |
| "eval_steps_per_second": 29.242, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_loss": 2.6175224781036377, | |
| "eval_runtime": 431.5837, | |
| "eval_samples_per_second": 463.405, | |
| "eval_steps_per_second": 28.963, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2.651333333333333e-07, | |
| "loss": 2.7786, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 2.6263880729675293, | |
| "eval_runtime": 429.7254, | |
| "eval_samples_per_second": 465.409, | |
| "eval_steps_per_second": 29.088, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 2.6192069053649902, | |
| "eval_runtime": 429.8114, | |
| "eval_samples_per_second": 465.316, | |
| "eval_steps_per_second": 29.083, | |
| "step": 856000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 2.624e-07, | |
| "loss": 2.7829, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 2.6278185844421387, | |
| "eval_runtime": 429.9283, | |
| "eval_samples_per_second": 465.189, | |
| "eval_steps_per_second": 29.075, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_loss": 2.623713731765747, | |
| "eval_runtime": 439.0054, | |
| "eval_samples_per_second": 455.571, | |
| "eval_steps_per_second": 28.473, | |
| "step": 872000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 2.596666666666667e-07, | |
| "loss": 2.776, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "eval_loss": 2.6201553344726562, | |
| "eval_runtime": 437.9731, | |
| "eval_samples_per_second": 456.644, | |
| "eval_steps_per_second": 28.541, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_loss": 2.621598482131958, | |
| "eval_runtime": 438.0301, | |
| "eval_samples_per_second": 456.585, | |
| "eval_steps_per_second": 28.537, | |
| "step": 888000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 2.5693333333333333e-07, | |
| "loss": 2.7797, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 2.617363929748535, | |
| "eval_runtime": 441.0259, | |
| "eval_samples_per_second": 453.484, | |
| "eval_steps_per_second": 28.343, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_loss": 2.6238625049591064, | |
| "eval_runtime": 429.8157, | |
| "eval_samples_per_second": 465.311, | |
| "eval_steps_per_second": 29.082, | |
| "step": 904000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 2.542e-07, | |
| "loss": 2.7744, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_loss": 2.616323709487915, | |
| "eval_runtime": 431.7594, | |
| "eval_samples_per_second": 463.216, | |
| "eval_steps_per_second": 28.951, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_loss": 2.6197702884674072, | |
| "eval_runtime": 428.7684, | |
| "eval_samples_per_second": 466.448, | |
| "eval_steps_per_second": 29.153, | |
| "step": 920000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 2.5146666666666664e-07, | |
| "loss": 2.7713, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_loss": 2.623600959777832, | |
| "eval_runtime": 427.7444, | |
| "eval_samples_per_second": 467.564, | |
| "eval_steps_per_second": 29.223, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 2.622565507888794, | |
| "eval_runtime": 440.6765, | |
| "eval_samples_per_second": 453.843, | |
| "eval_steps_per_second": 28.365, | |
| "step": 936000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 2.4873333333333335e-07, | |
| "loss": 2.7853, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 2.6175239086151123, | |
| "eval_runtime": 438.6983, | |
| "eval_samples_per_second": 455.89, | |
| "eval_steps_per_second": 28.493, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 2.618924140930176, | |
| "eval_runtime": 435.2773, | |
| "eval_samples_per_second": 459.473, | |
| "eval_steps_per_second": 28.717, | |
| "step": 952000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 2.46e-07, | |
| "loss": 2.7766, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 2.619227647781372, | |
| "eval_runtime": 436.1097, | |
| "eval_samples_per_second": 458.596, | |
| "eval_steps_per_second": 28.663, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_loss": 2.631781578063965, | |
| "eval_runtime": 434.7218, | |
| "eval_samples_per_second": 460.06, | |
| "eval_steps_per_second": 28.754, | |
| "step": 968000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 2.4326666666666666e-07, | |
| "loss": 2.7851, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 2.6210079193115234, | |
| "eval_runtime": 434.5133, | |
| "eval_samples_per_second": 460.28, | |
| "eval_steps_per_second": 28.768, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_loss": 2.6172115802764893, | |
| "eval_runtime": 432.096, | |
| "eval_samples_per_second": 462.855, | |
| "eval_steps_per_second": 28.929, | |
| "step": 984000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 2.405333333333333e-07, | |
| "loss": 2.7804, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_loss": 2.6199557781219482, | |
| "eval_runtime": 431.3352, | |
| "eval_samples_per_second": 463.672, | |
| "eval_steps_per_second": 28.98, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "eval_loss": 2.6156609058380127, | |
| "eval_runtime": 427.025, | |
| "eval_samples_per_second": 468.352, | |
| "eval_steps_per_second": 29.272, | |
| "step": 1000000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 2.3779999999999997e-07, | |
| "loss": 2.773, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 2.60978364944458, | |
| "eval_runtime": 428.465, | |
| "eval_samples_per_second": 466.778, | |
| "eval_steps_per_second": 29.174, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "eval_loss": 2.6156139373779297, | |
| "eval_runtime": 427.2949, | |
| "eval_samples_per_second": 468.056, | |
| "eval_steps_per_second": 29.254, | |
| "step": 1016000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 2.3506666666666668e-07, | |
| "loss": 2.7818, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_loss": 2.6148924827575684, | |
| "eval_runtime": 426.9113, | |
| "eval_samples_per_second": 468.477, | |
| "eval_steps_per_second": 29.28, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 2.612070083618164, | |
| "eval_runtime": 441.0262, | |
| "eval_samples_per_second": 453.483, | |
| "eval_steps_per_second": 28.343, | |
| "step": 1032000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.3233333333333334e-07, | |
| "loss": 2.7736, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_loss": 2.615013599395752, | |
| "eval_runtime": 435.5985, | |
| "eval_samples_per_second": 459.134, | |
| "eval_steps_per_second": 28.696, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "eval_loss": 2.6156115531921387, | |
| "eval_runtime": 436.5917, | |
| "eval_samples_per_second": 458.089, | |
| "eval_steps_per_second": 28.631, | |
| "step": 1048000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 2.2960000000000002e-07, | |
| "loss": 2.7761, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "eval_loss": 2.6170592308044434, | |
| "eval_runtime": 437.6326, | |
| "eval_samples_per_second": 457.0, | |
| "eval_steps_per_second": 28.563, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 2.6124441623687744, | |
| "eval_runtime": 430.5486, | |
| "eval_samples_per_second": 464.519, | |
| "eval_steps_per_second": 29.033, | |
| "step": 1064000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 2.2686666666666667e-07, | |
| "loss": 2.7789, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 2.6276962757110596, | |
| "eval_runtime": 428.8138, | |
| "eval_samples_per_second": 466.398, | |
| "eval_steps_per_second": 29.15, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 2.6138463020324707, | |
| "eval_runtime": 431.2439, | |
| "eval_samples_per_second": 463.77, | |
| "eval_steps_per_second": 28.986, | |
| "step": 1080000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.2413333333333333e-07, | |
| "loss": 2.7744, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_loss": 2.6080663204193115, | |
| "eval_runtime": 429.0451, | |
| "eval_samples_per_second": 466.147, | |
| "eval_steps_per_second": 29.134, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "eval_loss": 2.620119571685791, | |
| "eval_runtime": 435.3098, | |
| "eval_samples_per_second": 459.438, | |
| "eval_steps_per_second": 28.715, | |
| "step": 1096000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 2.214e-07, | |
| "loss": 2.77, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_loss": 2.6170663833618164, | |
| "eval_runtime": 430.7548, | |
| "eval_samples_per_second": 464.297, | |
| "eval_steps_per_second": 29.019, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_loss": 2.609856128692627, | |
| "eval_runtime": 430.7439, | |
| "eval_samples_per_second": 464.308, | |
| "eval_steps_per_second": 29.02, | |
| "step": 1112000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 2.1866666666666667e-07, | |
| "loss": 2.772, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "eval_loss": 2.614119052886963, | |
| "eval_runtime": 430.1555, | |
| "eval_samples_per_second": 464.944, | |
| "eval_steps_per_second": 29.059, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 2.6174395084381104, | |
| "eval_runtime": 430.2468, | |
| "eval_samples_per_second": 464.845, | |
| "eval_steps_per_second": 29.053, | |
| "step": 1128000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 2.1593333333333332e-07, | |
| "loss": 2.7709, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "eval_loss": 2.6200435161590576, | |
| "eval_runtime": 429.4394, | |
| "eval_samples_per_second": 465.719, | |
| "eval_steps_per_second": 29.108, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "eval_loss": 2.6149799823760986, | |
| "eval_runtime": 429.9204, | |
| "eval_samples_per_second": 465.198, | |
| "eval_steps_per_second": 29.075, | |
| "step": 1144000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 2.132e-07, | |
| "loss": 2.7724, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 2.6041531562805176, | |
| "eval_runtime": 433.3404, | |
| "eval_samples_per_second": 461.526, | |
| "eval_steps_per_second": 28.846, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "eval_loss": 2.615821361541748, | |
| "eval_runtime": 427.3883, | |
| "eval_samples_per_second": 467.954, | |
| "eval_steps_per_second": 29.247, | |
| "step": 1160000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 2.1046666666666666e-07, | |
| "loss": 2.7763, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 2.616694211959839, | |
| "eval_runtime": 424.8183, | |
| "eval_samples_per_second": 470.785, | |
| "eval_steps_per_second": 29.424, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_loss": 2.617375612258911, | |
| "eval_runtime": 425.4075, | |
| "eval_samples_per_second": 470.133, | |
| "eval_steps_per_second": 29.384, | |
| "step": 1176000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 2.0773333333333334e-07, | |
| "loss": 2.7736, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 2.609928846359253, | |
| "eval_runtime": 429.8799, | |
| "eval_samples_per_second": 465.242, | |
| "eval_steps_per_second": 29.078, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_loss": 2.607574462890625, | |
| "eval_runtime": 427.5829, | |
| "eval_samples_per_second": 467.741, | |
| "eval_steps_per_second": 29.234, | |
| "step": 1192000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 2.05e-07, | |
| "loss": 2.7692, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 2.6088333129882812, | |
| "eval_runtime": 427.3086, | |
| "eval_samples_per_second": 468.041, | |
| "eval_steps_per_second": 29.253, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "eval_loss": 2.6174449920654297, | |
| "eval_runtime": 426.9323, | |
| "eval_samples_per_second": 468.454, | |
| "eval_steps_per_second": 29.279, | |
| "step": 1208000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.0226666666666668e-07, | |
| "loss": 2.7794, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_loss": 2.604072332382202, | |
| "eval_runtime": 425.7765, | |
| "eval_samples_per_second": 469.725, | |
| "eval_steps_per_second": 29.358, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "eval_loss": 2.60508394241333, | |
| "eval_runtime": 429.4647, | |
| "eval_samples_per_second": 465.691, | |
| "eval_steps_per_second": 29.106, | |
| "step": 1224000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 1.9953333333333333e-07, | |
| "loss": 2.7709, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "eval_loss": 2.6092872619628906, | |
| "eval_runtime": 431.1236, | |
| "eval_samples_per_second": 463.899, | |
| "eval_steps_per_second": 28.994, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_loss": 2.6061949729919434, | |
| "eval_runtime": 430.933, | |
| "eval_samples_per_second": 464.105, | |
| "eval_steps_per_second": 29.007, | |
| "step": 1240000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 1.968e-07, | |
| "loss": 2.7727, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "eval_loss": 2.6051762104034424, | |
| "eval_runtime": 428.4194, | |
| "eval_samples_per_second": 466.828, | |
| "eval_steps_per_second": 29.177, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "eval_loss": 2.612610340118408, | |
| "eval_runtime": 426.271, | |
| "eval_samples_per_second": 469.18, | |
| "eval_steps_per_second": 29.324, | |
| "step": 1256000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 1.9406666666666667e-07, | |
| "loss": 2.7686, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_loss": 2.609870433807373, | |
| "eval_runtime": 424.9717, | |
| "eval_samples_per_second": 470.615, | |
| "eval_steps_per_second": 29.414, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "eval_loss": 2.619239568710327, | |
| "eval_runtime": 428.8052, | |
| "eval_samples_per_second": 466.408, | |
| "eval_steps_per_second": 29.151, | |
| "step": 1272000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 1.9133333333333333e-07, | |
| "loss": 2.7668, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "eval_loss": 2.616584539413452, | |
| "eval_runtime": 426.4046, | |
| "eval_samples_per_second": 469.033, | |
| "eval_steps_per_second": 29.315, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "eval_loss": 2.6041982173919678, | |
| "eval_runtime": 425.6206, | |
| "eval_samples_per_second": 469.897, | |
| "eval_steps_per_second": 29.369, | |
| "step": 1288000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 1.886e-07, | |
| "loss": 2.7777, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "eval_loss": 2.603804349899292, | |
| "eval_runtime": 425.5755, | |
| "eval_samples_per_second": 469.947, | |
| "eval_steps_per_second": 29.372, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "eval_loss": 2.6119117736816406, | |
| "eval_runtime": 426.6248, | |
| "eval_samples_per_second": 468.791, | |
| "eval_steps_per_second": 29.3, | |
| "step": 1304000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 1.8586666666666666e-07, | |
| "loss": 2.7737, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_loss": 2.615492343902588, | |
| "eval_runtime": 426.0601, | |
| "eval_samples_per_second": 469.413, | |
| "eval_steps_per_second": 29.339, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "eval_loss": 2.6235928535461426, | |
| "eval_runtime": 427.3368, | |
| "eval_samples_per_second": 468.01, | |
| "eval_steps_per_second": 29.251, | |
| "step": 1320000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 1.8313333333333332e-07, | |
| "loss": 2.7757, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_loss": 2.6123950481414795, | |
| "eval_runtime": 427.0533, | |
| "eval_samples_per_second": 468.321, | |
| "eval_steps_per_second": 29.27, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "eval_loss": 2.5992510318756104, | |
| "eval_runtime": 425.5905, | |
| "eval_samples_per_second": 469.931, | |
| "eval_steps_per_second": 29.371, | |
| "step": 1336000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 1.804e-07, | |
| "loss": 2.7757, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "eval_loss": 2.613180160522461, | |
| "eval_runtime": 424.8849, | |
| "eval_samples_per_second": 470.711, | |
| "eval_steps_per_second": 29.42, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "eval_loss": 2.6062958240509033, | |
| "eval_runtime": 424.2489, | |
| "eval_samples_per_second": 471.417, | |
| "eval_steps_per_second": 29.464, | |
| "step": 1352000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 1.7766666666666666e-07, | |
| "loss": 2.7748, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 2.612989902496338, | |
| "eval_runtime": 424.5958, | |
| "eval_samples_per_second": 471.032, | |
| "eval_steps_per_second": 29.44, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "eval_loss": 2.610032796859741, | |
| "eval_runtime": 427.5632, | |
| "eval_samples_per_second": 467.762, | |
| "eval_steps_per_second": 29.235, | |
| "step": 1368000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 1.7493333333333334e-07, | |
| "loss": 2.769, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 2.602424383163452, | |
| "eval_runtime": 424.7302, | |
| "eval_samples_per_second": 470.882, | |
| "eval_steps_per_second": 29.43, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "eval_loss": 2.6061973571777344, | |
| "eval_runtime": 428.6827, | |
| "eval_samples_per_second": 466.541, | |
| "eval_steps_per_second": 29.159, | |
| "step": 1384000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 1.722e-07, | |
| "loss": 2.7713, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_loss": 2.6137661933898926, | |
| "eval_runtime": 430.6966, | |
| "eval_samples_per_second": 464.359, | |
| "eval_steps_per_second": 29.023, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_loss": 2.6025471687316895, | |
| "eval_runtime": 430.8099, | |
| "eval_samples_per_second": 464.237, | |
| "eval_steps_per_second": 29.015, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 1.6946666666666668e-07, | |
| "loss": 2.7766, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 2.6087875366210938, | |
| "eval_runtime": 427.6043, | |
| "eval_samples_per_second": 467.717, | |
| "eval_steps_per_second": 29.233, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_loss": 2.6138193607330322, | |
| "eval_runtime": 428.3638, | |
| "eval_samples_per_second": 466.888, | |
| "eval_steps_per_second": 29.181, | |
| "step": 1416000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.6673333333333333e-07, | |
| "loss": 2.7727, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.604793071746826, | |
| "eval_runtime": 426.9803, | |
| "eval_samples_per_second": 468.401, | |
| "eval_steps_per_second": 29.275, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "eval_loss": 2.606837511062622, | |
| "eval_runtime": 429.9514, | |
| "eval_samples_per_second": 465.164, | |
| "eval_steps_per_second": 29.073, | |
| "step": 1432000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 1.64e-07, | |
| "loss": 2.7737, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 2.614352226257324, | |
| "eval_runtime": 427.0139, | |
| "eval_samples_per_second": 468.364, | |
| "eval_steps_per_second": 29.273, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_loss": 2.6051464080810547, | |
| "eval_runtime": 430.2406, | |
| "eval_samples_per_second": 464.852, | |
| "eval_steps_per_second": 29.054, | |
| "step": 1448000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1.6126666666666667e-07, | |
| "loss": 2.778, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 2.6157853603363037, | |
| "eval_runtime": 431.1381, | |
| "eval_samples_per_second": 463.884, | |
| "eval_steps_per_second": 28.993, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "eval_loss": 2.615216016769409, | |
| "eval_runtime": 425.9498, | |
| "eval_samples_per_second": 469.534, | |
| "eval_steps_per_second": 29.346, | |
| "step": 1464000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 1.5853333333333332e-07, | |
| "loss": 2.7767, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "eval_loss": 2.6018834114074707, | |
| "eval_runtime": 426.8729, | |
| "eval_samples_per_second": 468.519, | |
| "eval_steps_per_second": 29.283, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "eval_loss": 2.611650228500366, | |
| "eval_runtime": 425.3068, | |
| "eval_samples_per_second": 470.244, | |
| "eval_steps_per_second": 29.391, | |
| "step": 1480000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 1.558e-07, | |
| "loss": 2.7706, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "eval_loss": 2.6065428256988525, | |
| "eval_runtime": 427.2148, | |
| "eval_samples_per_second": 468.144, | |
| "eval_steps_per_second": 29.259, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_loss": 2.612178087234497, | |
| "eval_runtime": 424.5636, | |
| "eval_samples_per_second": 471.067, | |
| "eval_steps_per_second": 29.442, | |
| "step": 1496000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 1.5306666666666666e-07, | |
| "loss": 2.7775, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "eval_loss": 2.610006809234619, | |
| "eval_runtime": 424.709, | |
| "eval_samples_per_second": 470.906, | |
| "eval_steps_per_second": 29.432, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "eval_loss": 2.6100497245788574, | |
| "eval_runtime": 424.7106, | |
| "eval_samples_per_second": 470.904, | |
| "eval_steps_per_second": 29.432, | |
| "step": 1512000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.5033333333333332e-07, | |
| "loss": 2.7753, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_loss": 2.605093479156494, | |
| "eval_runtime": 427.9079, | |
| "eval_samples_per_second": 467.386, | |
| "eval_steps_per_second": 29.212, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "eval_loss": 2.6036603450775146, | |
| "eval_runtime": 425.7208, | |
| "eval_samples_per_second": 469.787, | |
| "eval_steps_per_second": 29.362, | |
| "step": 1528000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1.476e-07, | |
| "loss": 2.7691, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 2.6037118434906006, | |
| "eval_runtime": 425.0126, | |
| "eval_samples_per_second": 470.57, | |
| "eval_steps_per_second": 29.411, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "eval_loss": 2.599247932434082, | |
| "eval_runtime": 425.3525, | |
| "eval_samples_per_second": 470.194, | |
| "eval_steps_per_second": 29.387, | |
| "step": 1544000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.4486666666666665e-07, | |
| "loss": 2.758, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_loss": 2.6080071926116943, | |
| "eval_runtime": 424.5489, | |
| "eval_samples_per_second": 471.084, | |
| "eval_steps_per_second": 29.443, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "eval_loss": 2.6138691902160645, | |
| "eval_runtime": 427.0402, | |
| "eval_samples_per_second": 468.335, | |
| "eval_steps_per_second": 29.271, | |
| "step": 1560000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 1.4213333333333334e-07, | |
| "loss": 2.7722, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_loss": 2.6000304222106934, | |
| "eval_runtime": 426.0372, | |
| "eval_samples_per_second": 469.438, | |
| "eval_steps_per_second": 29.34, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "eval_loss": 2.6107337474823, | |
| "eval_runtime": 428.351, | |
| "eval_samples_per_second": 466.902, | |
| "eval_steps_per_second": 29.182, | |
| "step": 1576000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.3940000000000002e-07, | |
| "loss": 2.7737, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_loss": 2.6056902408599854, | |
| "eval_runtime": 427.5761, | |
| "eval_samples_per_second": 467.748, | |
| "eval_steps_per_second": 29.235, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_loss": 2.6063265800476074, | |
| "eval_runtime": 427.3328, | |
| "eval_samples_per_second": 468.015, | |
| "eval_steps_per_second": 29.251, | |
| "step": 1592000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.3666666666666665e-07, | |
| "loss": 2.7722, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "eval_loss": 2.602761745452881, | |
| "eval_runtime": 427.2826, | |
| "eval_samples_per_second": 468.07, | |
| "eval_steps_per_second": 29.255, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "eval_loss": 2.5995423793792725, | |
| "eval_runtime": 431.7911, | |
| "eval_samples_per_second": 463.182, | |
| "eval_steps_per_second": 28.949, | |
| "step": 1608000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1.3393333333333333e-07, | |
| "loss": 2.7659, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_loss": 2.604205846786499, | |
| "eval_runtime": 430.2172, | |
| "eval_samples_per_second": 464.877, | |
| "eval_steps_per_second": 29.055, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "eval_loss": 2.601318597793579, | |
| "eval_runtime": 426.9357, | |
| "eval_samples_per_second": 468.45, | |
| "eval_steps_per_second": 29.278, | |
| "step": 1624000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 1.312e-07, | |
| "loss": 2.7769, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "eval_loss": 2.60282826423645, | |
| "eval_runtime": 430.2987, | |
| "eval_samples_per_second": 464.789, | |
| "eval_steps_per_second": 29.05, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "eval_loss": 2.608042001724243, | |
| "eval_runtime": 428.8831, | |
| "eval_samples_per_second": 466.323, | |
| "eval_steps_per_second": 29.145, | |
| "step": 1640000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 1.2846666666666667e-07, | |
| "loss": 2.7732, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "eval_loss": 2.5994017124176025, | |
| "eval_runtime": 427.4593, | |
| "eval_samples_per_second": 467.876, | |
| "eval_steps_per_second": 29.243, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_loss": 2.6063311100006104, | |
| "eval_runtime": 427.0875, | |
| "eval_samples_per_second": 468.283, | |
| "eval_steps_per_second": 29.268, | |
| "step": 1656000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.2573333333333332e-07, | |
| "loss": 2.7708, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 2.6120190620422363, | |
| "eval_runtime": 426.6328, | |
| "eval_samples_per_second": 468.783, | |
| "eval_steps_per_second": 29.299, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_loss": 2.602278470993042, | |
| "eval_runtime": 426.2122, | |
| "eval_samples_per_second": 469.245, | |
| "eval_steps_per_second": 29.328, | |
| "step": 1672000 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.23e-07, | |
| "loss": 2.7614, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 2.6091384887695312, | |
| "eval_runtime": 428.3432, | |
| "eval_samples_per_second": 466.911, | |
| "eval_steps_per_second": 29.182, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_loss": 2.600266218185425, | |
| "eval_runtime": 426.5859, | |
| "eval_samples_per_second": 468.834, | |
| "eval_steps_per_second": 29.302, | |
| "step": 1688000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.2026666666666666e-07, | |
| "loss": 2.7655, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "eval_loss": 2.6015985012054443, | |
| "eval_runtime": 427.3154, | |
| "eval_samples_per_second": 468.034, | |
| "eval_steps_per_second": 29.252, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "eval_loss": 2.605762481689453, | |
| "eval_runtime": 431.3039, | |
| "eval_samples_per_second": 463.706, | |
| "eval_steps_per_second": 28.982, | |
| "step": 1704000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 1.1753333333333334e-07, | |
| "loss": 2.7747, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_loss": 2.6045358180999756, | |
| "eval_runtime": 430.9287, | |
| "eval_samples_per_second": 464.109, | |
| "eval_steps_per_second": 29.007, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "eval_loss": 2.609701633453369, | |
| "eval_runtime": 430.8027, | |
| "eval_samples_per_second": 464.245, | |
| "eval_steps_per_second": 29.016, | |
| "step": 1720000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 1.1480000000000001e-07, | |
| "loss": 2.7685, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "eval_loss": 2.606764316558838, | |
| "eval_runtime": 430.5036, | |
| "eval_samples_per_second": 464.568, | |
| "eval_steps_per_second": 29.036, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "eval_loss": 2.6037065982818604, | |
| "eval_runtime": 428.2126, | |
| "eval_samples_per_second": 467.053, | |
| "eval_steps_per_second": 29.191, | |
| "step": 1736000 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 1.1206666666666666e-07, | |
| "loss": 2.7736, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 2.612487554550171, | |
| "eval_runtime": 426.9199, | |
| "eval_samples_per_second": 468.467, | |
| "eval_steps_per_second": 29.279, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "eval_loss": 2.6112568378448486, | |
| "eval_runtime": 424.0556, | |
| "eval_samples_per_second": 471.632, | |
| "eval_steps_per_second": 29.477, | |
| "step": 1752000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1.0933333333333333e-07, | |
| "loss": 2.7666, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "eval_loss": 2.597158193588257, | |
| "eval_runtime": 424.796, | |
| "eval_samples_per_second": 470.81, | |
| "eval_steps_per_second": 29.426, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "eval_loss": 2.6080923080444336, | |
| "eval_runtime": 426.0498, | |
| "eval_samples_per_second": 469.424, | |
| "eval_steps_per_second": 29.339, | |
| "step": 1768000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 1.066e-07, | |
| "loss": 2.7658, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_loss": 2.6089766025543213, | |
| "eval_runtime": 426.2325, | |
| "eval_samples_per_second": 469.223, | |
| "eval_steps_per_second": 29.327, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_loss": 2.6126182079315186, | |
| "eval_runtime": 425.9411, | |
| "eval_samples_per_second": 469.544, | |
| "eval_steps_per_second": 29.347, | |
| "step": 1784000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 1.0386666666666667e-07, | |
| "loss": 2.7802, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "eval_loss": 2.6020755767822266, | |
| "eval_runtime": 425.4923, | |
| "eval_samples_per_second": 470.039, | |
| "eval_steps_per_second": 29.378, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "eval_loss": 2.608738660812378, | |
| "eval_runtime": 423.4207, | |
| "eval_samples_per_second": 472.339, | |
| "eval_steps_per_second": 29.521, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 1.0113333333333334e-07, | |
| "loss": 2.7749, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_loss": 2.5985732078552246, | |
| "eval_runtime": 427.6655, | |
| "eval_samples_per_second": 467.651, | |
| "eval_steps_per_second": 29.228, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "eval_loss": 2.600249767303467, | |
| "eval_runtime": 425.4151, | |
| "eval_samples_per_second": 470.124, | |
| "eval_steps_per_second": 29.383, | |
| "step": 1816000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 9.84e-08, | |
| "loss": 2.7689, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "eval_loss": 2.6023120880126953, | |
| "eval_runtime": 426.7002, | |
| "eval_samples_per_second": 468.708, | |
| "eval_steps_per_second": 29.295, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_loss": 2.5969133377075195, | |
| "eval_runtime": 429.4646, | |
| "eval_samples_per_second": 465.691, | |
| "eval_steps_per_second": 29.106, | |
| "step": 1832000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 9.566666666666666e-08, | |
| "loss": 2.7699, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "eval_loss": 2.5974552631378174, | |
| "eval_runtime": 425.4534, | |
| "eval_samples_per_second": 470.082, | |
| "eval_steps_per_second": 29.38, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_loss": 2.606982946395874, | |
| "eval_runtime": 427.6242, | |
| "eval_samples_per_second": 467.696, | |
| "eval_steps_per_second": 29.231, | |
| "step": 1848000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 9.293333333333333e-08, | |
| "loss": 2.7715, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_loss": 2.603482484817505, | |
| "eval_runtime": 429.5475, | |
| "eval_samples_per_second": 465.602, | |
| "eval_steps_per_second": 29.1, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "eval_loss": 2.6048595905303955, | |
| "eval_runtime": 430.2797, | |
| "eval_samples_per_second": 464.809, | |
| "eval_steps_per_second": 29.051, | |
| "step": 1864000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 9.02e-08, | |
| "loss": 2.7653, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "eval_loss": 2.6129438877105713, | |
| "eval_runtime": 430.4774, | |
| "eval_samples_per_second": 464.596, | |
| "eval_steps_per_second": 29.038, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "eval_loss": 2.602692127227783, | |
| "eval_runtime": 426.0433, | |
| "eval_samples_per_second": 469.431, | |
| "eval_steps_per_second": 29.34, | |
| "step": 1880000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 8.746666666666667e-08, | |
| "loss": 2.7729, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_loss": 2.5999996662139893, | |
| "eval_runtime": 427.4645, | |
| "eval_samples_per_second": 467.87, | |
| "eval_steps_per_second": 29.242, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "eval_loss": 2.6137943267822266, | |
| "eval_runtime": 427.597, | |
| "eval_samples_per_second": 467.726, | |
| "eval_steps_per_second": 29.233, | |
| "step": 1896000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 8.473333333333334e-08, | |
| "loss": 2.7693, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_loss": 2.6051719188690186, | |
| "eval_runtime": 428.0224, | |
| "eval_samples_per_second": 467.261, | |
| "eval_steps_per_second": 29.204, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_loss": 2.6060233116149902, | |
| "eval_runtime": 430.6968, | |
| "eval_samples_per_second": 464.359, | |
| "eval_steps_per_second": 29.023, | |
| "step": 1912000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 8.2e-08, | |
| "loss": 2.7585, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "eval_loss": 2.6064672470092773, | |
| "eval_runtime": 427.6059, | |
| "eval_samples_per_second": 467.716, | |
| "eval_steps_per_second": 29.233, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "eval_loss": 2.6105079650878906, | |
| "eval_runtime": 438.1262, | |
| "eval_samples_per_second": 456.485, | |
| "eval_steps_per_second": 28.531, | |
| "step": 1928000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 7.926666666666666e-08, | |
| "loss": 2.7652, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "eval_loss": 2.607515335083008, | |
| "eval_runtime": 438.8385, | |
| "eval_samples_per_second": 455.744, | |
| "eval_steps_per_second": 28.484, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "eval_loss": 2.607562780380249, | |
| "eval_runtime": 434.8048, | |
| "eval_samples_per_second": 459.972, | |
| "eval_steps_per_second": 28.749, | |
| "step": 1944000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 7.653333333333333e-08, | |
| "loss": 2.7508, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_loss": 2.6083250045776367, | |
| "eval_runtime": 436.0024, | |
| "eval_samples_per_second": 458.709, | |
| "eval_steps_per_second": 28.67, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "eval_loss": 2.6111507415771484, | |
| "eval_runtime": 436.2282, | |
| "eval_samples_per_second": 458.471, | |
| "eval_steps_per_second": 28.655, | |
| "step": 1960000 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 7.38e-08, | |
| "loss": 2.7678, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "eval_loss": 2.6018521785736084, | |
| "eval_runtime": 437.0443, | |
| "eval_samples_per_second": 457.615, | |
| "eval_steps_per_second": 28.601, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_loss": 2.602910280227661, | |
| "eval_runtime": 435.5894, | |
| "eval_samples_per_second": 459.143, | |
| "eval_steps_per_second": 28.697, | |
| "step": 1976000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 7.106666666666667e-08, | |
| "loss": 2.7653, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "eval_loss": 2.6087162494659424, | |
| "eval_runtime": 434.8171, | |
| "eval_samples_per_second": 459.959, | |
| "eval_steps_per_second": 28.748, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "eval_loss": 2.606381416320801, | |
| "eval_runtime": 429.8668, | |
| "eval_samples_per_second": 465.256, | |
| "eval_steps_per_second": 29.079, | |
| "step": 1992000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 6.833333333333332e-08, | |
| "loss": 2.7661, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "eval_loss": 2.603147506713867, | |
| "eval_runtime": 424.748, | |
| "eval_samples_per_second": 470.863, | |
| "eval_steps_per_second": 29.429, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "eval_loss": 2.6050961017608643, | |
| "eval_runtime": 424.2051, | |
| "eval_samples_per_second": 471.465, | |
| "eval_steps_per_second": 29.467, | |
| "step": 2008000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 6.56e-08, | |
| "loss": 2.7742, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "eval_loss": 2.6091232299804688, | |
| "eval_runtime": 425.2363, | |
| "eval_samples_per_second": 470.322, | |
| "eval_steps_per_second": 29.395, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "eval_loss": 2.5978386402130127, | |
| "eval_runtime": 421.3464, | |
| "eval_samples_per_second": 474.664, | |
| "eval_steps_per_second": 29.667, | |
| "step": 2024000 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 6.286666666666666e-08, | |
| "loss": 2.7748, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "eval_loss": 2.6131348609924316, | |
| "eval_runtime": 421.1531, | |
| "eval_samples_per_second": 474.882, | |
| "eval_steps_per_second": 29.68, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "eval_loss": 2.6030309200286865, | |
| "eval_runtime": 423.5077, | |
| "eval_samples_per_second": 472.242, | |
| "eval_steps_per_second": 29.515, | |
| "step": 2040000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 6.013333333333333e-08, | |
| "loss": 2.7706, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "eval_loss": 2.6036195755004883, | |
| "eval_runtime": 424.684, | |
| "eval_samples_per_second": 470.934, | |
| "eval_steps_per_second": 29.434, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "eval_loss": 2.599808692932129, | |
| "eval_runtime": 421.9265, | |
| "eval_samples_per_second": 474.011, | |
| "eval_steps_per_second": 29.626, | |
| "step": 2056000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 5.7400000000000004e-08, | |
| "loss": 2.769, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_loss": 2.6013376712799072, | |
| "eval_runtime": 424.7682, | |
| "eval_samples_per_second": 470.84, | |
| "eval_steps_per_second": 29.428, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "eval_loss": 2.6000382900238037, | |
| "eval_runtime": 422.3044, | |
| "eval_samples_per_second": 473.587, | |
| "eval_steps_per_second": 29.6, | |
| "step": 2072000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 5.4666666666666666e-08, | |
| "loss": 2.7733, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_loss": 2.606200695037842, | |
| "eval_runtime": 421.4091, | |
| "eval_samples_per_second": 474.593, | |
| "eval_steps_per_second": 29.662, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "eval_loss": 2.605668783187866, | |
| "eval_runtime": 425.3566, | |
| "eval_samples_per_second": 470.189, | |
| "eval_steps_per_second": 29.387, | |
| "step": 2088000 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 5.1933333333333335e-08, | |
| "loss": 2.7714, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "eval_loss": 2.602085828781128, | |
| "eval_runtime": 423.0675, | |
| "eval_samples_per_second": 472.733, | |
| "eval_steps_per_second": 29.546, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_loss": 2.602846145629883, | |
| "eval_runtime": 424.1211, | |
| "eval_samples_per_second": 471.559, | |
| "eval_steps_per_second": 29.473, | |
| "step": 2104000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.92e-08, | |
| "loss": 2.7754, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_loss": 2.596395254135132, | |
| "eval_runtime": 421.9383, | |
| "eval_samples_per_second": 473.998, | |
| "eval_steps_per_second": 29.625, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "eval_loss": 2.601470470428467, | |
| "eval_runtime": 430.2725, | |
| "eval_samples_per_second": 464.817, | |
| "eval_steps_per_second": 29.051, | |
| "step": 2120000 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 4.6466666666666666e-08, | |
| "loss": 2.7683, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_loss": 2.6060473918914795, | |
| "eval_runtime": 428.5391, | |
| "eval_samples_per_second": 466.697, | |
| "eval_steps_per_second": 29.169, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_loss": 2.6081697940826416, | |
| "eval_runtime": 430.2474, | |
| "eval_samples_per_second": 464.844, | |
| "eval_steps_per_second": 29.053, | |
| "step": 2136000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.3733333333333335e-08, | |
| "loss": 2.7758, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 2.6130032539367676, | |
| "eval_runtime": 427.9829, | |
| "eval_samples_per_second": 467.304, | |
| "eval_steps_per_second": 29.207, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "eval_loss": 2.607052803039551, | |
| "eval_runtime": 426.9186, | |
| "eval_samples_per_second": 468.469, | |
| "eval_steps_per_second": 29.28, | |
| "step": 2152000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.1e-08, | |
| "loss": 2.768, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 2.6140778064727783, | |
| "eval_runtime": 426.6857, | |
| "eval_samples_per_second": 468.724, | |
| "eval_steps_per_second": 29.296, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "eval_loss": 2.600281000137329, | |
| "eval_runtime": 427.0893, | |
| "eval_samples_per_second": 468.281, | |
| "eval_steps_per_second": 29.268, | |
| "step": 2168000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 3.8266666666666665e-08, | |
| "loss": 2.7653, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "eval_loss": 2.5986554622650146, | |
| "eval_runtime": 425.4388, | |
| "eval_samples_per_second": 470.098, | |
| "eval_steps_per_second": 29.381, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_loss": 2.6066486835479736, | |
| "eval_runtime": 425.1112, | |
| "eval_samples_per_second": 470.46, | |
| "eval_steps_per_second": 29.404, | |
| "step": 2184000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 3.5533333333333334e-08, | |
| "loss": 2.7621, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "eval_loss": 2.6040539741516113, | |
| "eval_runtime": 424.0828, | |
| "eval_samples_per_second": 471.601, | |
| "eval_steps_per_second": 29.475, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "eval_loss": 2.605970859527588, | |
| "eval_runtime": 424.8928, | |
| "eval_samples_per_second": 470.702, | |
| "eval_steps_per_second": 29.419, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 3.28e-08, | |
| "loss": 2.7712, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_loss": 2.6143710613250732, | |
| "eval_runtime": 422.534, | |
| "eval_samples_per_second": 473.33, | |
| "eval_steps_per_second": 29.583, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "eval_loss": 2.5990421772003174, | |
| "eval_runtime": 423.7702, | |
| "eval_samples_per_second": 471.949, | |
| "eval_steps_per_second": 29.497, | |
| "step": 2216000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 3.0066666666666665e-08, | |
| "loss": 2.7718, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "eval_loss": 2.6039345264434814, | |
| "eval_runtime": 422.8971, | |
| "eval_samples_per_second": 472.924, | |
| "eval_steps_per_second": 29.558, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "eval_loss": 2.593075752258301, | |
| "eval_runtime": 423.1257, | |
| "eval_samples_per_second": 472.668, | |
| "eval_steps_per_second": 29.542, | |
| "step": 2232000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 2.7333333333333333e-08, | |
| "loss": 2.774, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "eval_loss": 2.6128671169281006, | |
| "eval_runtime": 423.6724, | |
| "eval_samples_per_second": 472.058, | |
| "eval_steps_per_second": 29.504, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "eval_loss": 2.6095166206359863, | |
| "eval_runtime": 427.8902, | |
| "eval_samples_per_second": 467.405, | |
| "eval_steps_per_second": 29.213, | |
| "step": 2248000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 2.46e-08, | |
| "loss": 2.765, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "eval_loss": 2.5932390689849854, | |
| "eval_runtime": 426.8467, | |
| "eval_samples_per_second": 468.548, | |
| "eval_steps_per_second": 29.285, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_loss": 2.6009600162506104, | |
| "eval_runtime": 424.1412, | |
| "eval_samples_per_second": 471.536, | |
| "eval_steps_per_second": 29.471, | |
| "step": 2264000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 2.1866666666666667e-08, | |
| "loss": 2.7754, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 2.60778546333313, | |
| "eval_runtime": 425.6089, | |
| "eval_samples_per_second": 469.91, | |
| "eval_steps_per_second": 29.37, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_loss": 2.5981459617614746, | |
| "eval_runtime": 425.6519, | |
| "eval_samples_per_second": 469.863, | |
| "eval_steps_per_second": 29.367, | |
| "step": 2280000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 1.9133333333333333e-08, | |
| "loss": 2.771, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "eval_loss": 2.6052143573760986, | |
| "eval_runtime": 424.5141, | |
| "eval_samples_per_second": 471.122, | |
| "eval_steps_per_second": 29.445, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 2.5944042205810547, | |
| "eval_runtime": 425.2866, | |
| "eval_samples_per_second": 470.266, | |
| "eval_steps_per_second": 29.392, | |
| "step": 2296000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 1.64e-08, | |
| "loss": 2.7757, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "eval_loss": 2.6045000553131104, | |
| "eval_runtime": 428.7498, | |
| "eval_samples_per_second": 466.468, | |
| "eval_steps_per_second": 29.155, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "eval_loss": 2.5971217155456543, | |
| "eval_runtime": 432.7726, | |
| "eval_samples_per_second": 462.132, | |
| "eval_steps_per_second": 28.884, | |
| "step": 2312000 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 1.3666666666666667e-08, | |
| "loss": 2.7685, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "eval_loss": 2.610078811645508, | |
| "eval_runtime": 432.5525, | |
| "eval_samples_per_second": 462.367, | |
| "eval_steps_per_second": 28.898, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_loss": 2.596436023712158, | |
| "eval_runtime": 432.023, | |
| "eval_samples_per_second": 462.934, | |
| "eval_steps_per_second": 28.934, | |
| "step": 2328000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 1.0933333333333334e-08, | |
| "loss": 2.7708, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_loss": 2.5973622798919678, | |
| "eval_runtime": 432.5814, | |
| "eval_samples_per_second": 462.336, | |
| "eval_steps_per_second": 28.896, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "eval_loss": 2.5952794551849365, | |
| "eval_runtime": 427.2422, | |
| "eval_samples_per_second": 468.114, | |
| "eval_steps_per_second": 29.257, | |
| "step": 2344000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 8.2e-09, | |
| "loss": 2.7695, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "eval_loss": 2.598102569580078, | |
| "eval_runtime": 427.2188, | |
| "eval_samples_per_second": 468.139, | |
| "eval_steps_per_second": 29.259, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_loss": 2.6094541549682617, | |
| "eval_runtime": 427.6756, | |
| "eval_samples_per_second": 467.639, | |
| "eval_steps_per_second": 29.228, | |
| "step": 2360000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 5.466666666666667e-09, | |
| "loss": 2.7702, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_loss": 2.6042184829711914, | |
| "eval_runtime": 426.894, | |
| "eval_samples_per_second": 468.496, | |
| "eval_steps_per_second": 29.281, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.6094839572906494, | |
| "eval_runtime": 429.3589, | |
| "eval_samples_per_second": 465.806, | |
| "eval_steps_per_second": 29.113, | |
| "step": 2376000 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 2.7333333333333334e-09, | |
| "loss": 2.7614, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "eval_loss": 2.6007468700408936, | |
| "eval_runtime": 426.5863, | |
| "eval_samples_per_second": 468.834, | |
| "eval_steps_per_second": 29.302, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "eval_loss": 2.601724863052368, | |
| "eval_runtime": 428.327, | |
| "eval_samples_per_second": 466.928, | |
| "eval_steps_per_second": 29.183, | |
| "step": 2392000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.0, | |
| "loss": 2.7708, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "eval_loss": 2.611358880996704, | |
| "eval_runtime": 427.933, | |
| "eval_samples_per_second": 467.358, | |
| "eval_steps_per_second": 29.21, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "step": 2400000, | |
| "total_flos": 7.626726685368748e+17, | |
| "train_loss": 2.7854965201822917, | |
| "train_runtime": 398406.2107, | |
| "train_samples_per_second": 96.384, | |
| "train_steps_per_second": 6.024 | |
| } | |
| ], | |
| "logging_steps": 16000, | |
| "max_steps": 2400000, | |
| "num_train_epochs": 11, | |
| "save_steps": 32000, | |
| "total_flos": 7.626726685368748e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |