| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.28, |
| "eval_steps": 1000, |
| "global_step": 14000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002, |
| "grad_norm": 2.427967071533203, |
| "learning_rate": 7.920000000000001e-05, |
| "loss": 8.595370483398437, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.004, |
| "grad_norm": 2.0173449516296387, |
| "learning_rate": 0.00015920000000000002, |
| "loss": 6.985690307617188, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.006, |
| "grad_norm": 2.1842076778411865, |
| "learning_rate": 0.00023920000000000001, |
| "loss": 6.733137817382812, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.008, |
| "grad_norm": 1.4833307266235352, |
| "learning_rate": 0.0003192, |
| "loss": 6.513255004882812, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.232273578643799, |
| "learning_rate": 0.0003992, |
| "loss": 6.504192504882813, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.012, |
| "grad_norm": 2.256459951400757, |
| "learning_rate": 0.00047920000000000005, |
| "loss": 6.356998901367188, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.014, |
| "grad_norm": 1.6759421825408936, |
| "learning_rate": 0.0005592, |
| "loss": 6.304365234375, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.016, |
| "grad_norm": 1.164450764656067, |
| "learning_rate": 0.0006392, |
| "loss": 6.234349975585937, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.018, |
| "grad_norm": 2.5291967391967773, |
| "learning_rate": 0.0007191999999999999, |
| "loss": 6.173318481445312, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 1.1007851362228394, |
| "learning_rate": 0.0007992, |
| "loss": 6.1113330078125, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.02, |
| "eval_accuracy": 0.14623679060665362, |
| "eval_loss": 6.150835037231445, |
| "eval_runtime": 13.1402, |
| "eval_samples_per_second": 76.102, |
| "eval_steps_per_second": 9.513, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.022, |
| "grad_norm": 0.8226528167724609, |
| "learning_rate": 0.0008792, |
| "loss": 6.04904052734375, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.024, |
| "grad_norm": 1.1409642696380615, |
| "learning_rate": 0.0009592000000000001, |
| "loss": 5.977291259765625, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.026, |
| "grad_norm": 0.9230883121490479, |
| "learning_rate": 0.0010391999999999999, |
| "loss": 5.983433837890625, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.028, |
| "grad_norm": 0.7991492748260498, |
| "learning_rate": 0.0011192, |
| "loss": 5.960853271484375, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.9952593445777893, |
| "learning_rate": 0.0011992, |
| "loss": 5.900661010742187, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.032, |
| "grad_norm": 2.6635053157806396, |
| "learning_rate": 0.0012791999999999999, |
| "loss": 5.839690551757813, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.034, |
| "grad_norm": 0.7056213021278381, |
| "learning_rate": 0.0013592, |
| "loss": 5.864632568359375, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.036, |
| "grad_norm": 0.7523426413536072, |
| "learning_rate": 0.0014392, |
| "loss": 5.8030767822265625, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.038, |
| "grad_norm": 0.572576105594635, |
| "learning_rate": 0.0015192, |
| "loss": 5.829718017578125, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.8802671432495117, |
| "learning_rate": 0.0015992, |
| "loss": 5.767376098632813, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_accuracy": 0.163426614481409, |
| "eval_loss": 5.823215484619141, |
| "eval_runtime": 6.7868, |
| "eval_samples_per_second": 147.345, |
| "eval_steps_per_second": 18.418, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.042, |
| "grad_norm": 0.6110609173774719, |
| "learning_rate": 0.0016792, |
| "loss": 5.67332275390625, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.044, |
| "grad_norm": 0.579617977142334, |
| "learning_rate": 0.0017592, |
| "loss": 5.706051025390625, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.046, |
| "grad_norm": 0.5633976459503174, |
| "learning_rate": 0.0018392, |
| "loss": 5.6666259765625, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.048, |
| "grad_norm": 0.6478831768035889, |
| "learning_rate": 0.0019192, |
| "loss": 5.682818603515625, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.8043723702430725, |
| "learning_rate": 0.0019992, |
| "loss": 5.635286254882812, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.052, |
| "grad_norm": 0.554682195186615, |
| "learning_rate": 0.001999978563623903, |
| "loss": 5.5472607421875, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.054, |
| "grad_norm": 0.6824977397918701, |
| "learning_rate": 0.0019999133871331223, |
| "loss": 5.5920654296875, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.056, |
| "grad_norm": 0.40844905376434326, |
| "learning_rate": 0.0019998044711915177, |
| "loss": 5.528501586914063, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.058, |
| "grad_norm": 0.6135262250900269, |
| "learning_rate": 0.0019996518205634257, |
| "loss": 5.487052612304687, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.4022127687931061, |
| "learning_rate": 0.0019994554419262797, |
| "loss": 5.5177392578125, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.06, |
| "eval_accuracy": 0.18825440313111547, |
| "eval_loss": 5.509125232696533, |
| "eval_runtime": 6.779, |
| "eval_samples_per_second": 147.515, |
| "eval_steps_per_second": 18.439, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.062, |
| "grad_norm": 0.7171342968940735, |
| "learning_rate": 0.001999215343870317, |
| "loss": 5.417413330078125, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 0.4542510509490967, |
| "learning_rate": 0.0019989315368982054, |
| "loss": 5.4095831298828125, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.066, |
| "grad_norm": 0.5080035924911499, |
| "learning_rate": 0.0019986040334245797, |
| "loss": 5.417955932617187, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.068, |
| "grad_norm": 0.3587779700756073, |
| "learning_rate": 0.001998232847775504, |
| "loss": 5.3721466064453125, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.45940911769866943, |
| "learning_rate": 0.0019978179961878404, |
| "loss": 5.320546875, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.072, |
| "grad_norm": 0.3420865535736084, |
| "learning_rate": 0.001997359496808541, |
| "loss": 5.28208984375, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.074, |
| "grad_norm": 0.42247381806373596, |
| "learning_rate": 0.001996857369693855, |
| "loss": 5.29147216796875, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.076, |
| "grad_norm": 0.3335079550743103, |
| "learning_rate": 0.0019963116368084486, |
| "loss": 5.352775268554687, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.078, |
| "grad_norm": 0.6875544786453247, |
| "learning_rate": 0.001995722322024446, |
| "loss": 5.303611450195312, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.3652666211128235, |
| "learning_rate": 0.001995089451120385, |
| "loss": 5.26600830078125, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_accuracy": 0.19674755381604697, |
| "eval_loss": 5.325084686279297, |
| "eval_runtime": 6.607, |
| "eval_samples_per_second": 151.355, |
| "eval_steps_per_second": 18.919, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.082, |
| "grad_norm": 0.5043853521347046, |
| "learning_rate": 0.0019944130517800893, |
| "loss": 5.239017944335938, |
| "step": 4100 |
| }, |
| { |
| "epoch": 0.084, |
| "grad_norm": 0.3757055699825287, |
| "learning_rate": 0.001993693153591457, |
| "loss": 5.197454833984375, |
| "step": 4200 |
| }, |
| { |
| "epoch": 0.086, |
| "grad_norm": 0.3453492820262909, |
| "learning_rate": 0.0019929297880451674, |
| "loss": 5.198365478515625, |
| "step": 4300 |
| }, |
| { |
| "epoch": 0.088, |
| "grad_norm": 0.4262433350086212, |
| "learning_rate": 0.0019921229885333023, |
| "loss": 5.171350708007813, |
| "step": 4400 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.40825143456459045, |
| "learning_rate": 0.001991272790347886, |
| "loss": 5.089209899902344, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.092, |
| "grad_norm": 0.4957910180091858, |
| "learning_rate": 0.0019903792306793415, |
| "loss": 5.19048828125, |
| "step": 4600 |
| }, |
| { |
| "epoch": 0.094, |
| "grad_norm": 0.3308526873588562, |
| "learning_rate": 0.001989442348614863, |
| "loss": 5.067187805175781, |
| "step": 4700 |
| }, |
| { |
| "epoch": 0.096, |
| "grad_norm": 0.8154045343399048, |
| "learning_rate": 0.0019884621851367075, |
| "loss": 4.980618591308594, |
| "step": 4800 |
| }, |
| { |
| "epoch": 0.098, |
| "grad_norm": 0.31783750653266907, |
| "learning_rate": 0.001987438783120401, |
| "loss": 5.060207214355469, |
| "step": 4900 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.3620655834674835, |
| "learning_rate": 0.001986372187332862, |
| "loss": 5.093417358398438, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_accuracy": 0.2061839530332681, |
| "eval_loss": 5.202327251434326, |
| "eval_runtime": 6.6926, |
| "eval_samples_per_second": 149.419, |
| "eval_steps_per_second": 18.677, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.102, |
| "grad_norm": 0.5922824144363403, |
| "learning_rate": 0.0019852624444304467, |
| "loss": 5.105964965820313, |
| "step": 5100 |
| }, |
| { |
| "epoch": 0.104, |
| "grad_norm": 0.3136729598045349, |
| "learning_rate": 0.0019841096029569044, |
| "loss": 5.011907348632812, |
| "step": 5200 |
| }, |
| { |
| "epoch": 0.106, |
| "grad_norm": 0.5342575311660767, |
| "learning_rate": 0.0019829137133412556, |
| "loss": 5.081852111816406, |
| "step": 5300 |
| }, |
| { |
| "epoch": 0.108, |
| "grad_norm": 0.26439738273620605, |
| "learning_rate": 0.001981674827895587, |
| "loss": 4.994610595703125, |
| "step": 5400 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.37755730748176575, |
| "learning_rate": 0.00198039300081276, |
| "loss": 5.054569396972656, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.112, |
| "grad_norm": 0.2924644947052002, |
| "learning_rate": 0.0019790682881640448, |
| "loss": 4.945042419433594, |
| "step": 5600 |
| }, |
| { |
| "epoch": 0.114, |
| "grad_norm": 0.35851046442985535, |
| "learning_rate": 0.001977700747896664, |
| "loss": 4.959053039550781, |
| "step": 5700 |
| }, |
| { |
| "epoch": 0.116, |
| "grad_norm": 0.5607061386108398, |
| "learning_rate": 0.001976290439831259, |
| "loss": 5.00759521484375, |
| "step": 5800 |
| }, |
| { |
| "epoch": 0.118, |
| "grad_norm": 0.41018638014793396, |
| "learning_rate": 0.0019748374256592736, |
| "loss": 4.933994750976563, |
| "step": 5900 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.28882530331611633, |
| "learning_rate": 0.0019733417689402543, |
| "loss": 5.069781799316406, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_accuracy": 0.21534050880626224, |
| "eval_loss": 5.081418037414551, |
| "eval_runtime": 6.8091, |
| "eval_samples_per_second": 146.862, |
| "eval_steps_per_second": 18.358, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.122, |
| "grad_norm": 0.3777143955230713, |
| "learning_rate": 0.0019718035350990712, |
| "loss": 5.025782775878906, |
| "step": 6100 |
| }, |
| { |
| "epoch": 0.124, |
| "grad_norm": 0.32341495156288147, |
| "learning_rate": 0.0019702227914230566, |
| "loss": 5.048944702148438, |
| "step": 6200 |
| }, |
| { |
| "epoch": 0.126, |
| "grad_norm": 0.6978408098220825, |
| "learning_rate": 0.001968599607059059, |
| "loss": 5.073916015625, |
| "step": 6300 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 0.32388925552368164, |
| "learning_rate": 0.0019669340530104207, |
| "loss": 5.03993896484375, |
| "step": 6400 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.36633092164993286, |
| "learning_rate": 0.001965226202133872, |
| "loss": 5.047967529296875, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.132, |
| "grad_norm": 0.36229783296585083, |
| "learning_rate": 0.0019634761291363427, |
| "loss": 4.99884033203125, |
| "step": 6600 |
| }, |
| { |
| "epoch": 0.134, |
| "grad_norm": 0.26596584916114807, |
| "learning_rate": 0.0019616839105716954, |
| "loss": 4.971425476074219, |
| "step": 6700 |
| }, |
| { |
| "epoch": 0.136, |
| "grad_norm": 0.2571287751197815, |
| "learning_rate": 0.0019598496248373755, |
| "loss": 4.944924926757812, |
| "step": 6800 |
| }, |
| { |
| "epoch": 0.138, |
| "grad_norm": 0.33811017870903015, |
| "learning_rate": 0.001957973352170984, |
| "loss": 5.022549438476562, |
| "step": 6900 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.3483704924583435, |
| "learning_rate": 0.001956055174646765, |
| "loss": 4.955761108398438, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.14, |
| "eval_accuracy": 0.2182211350293542, |
| "eval_loss": 5.020055770874023, |
| "eval_runtime": 6.8173, |
| "eval_samples_per_second": 146.686, |
| "eval_steps_per_second": 18.336, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.142, |
| "grad_norm": 0.29454681277275085, |
| "learning_rate": 0.0019540951761720174, |
| "loss": 4.994992370605469, |
| "step": 7100 |
| }, |
| { |
| "epoch": 0.144, |
| "grad_norm": 0.7461824417114258, |
| "learning_rate": 0.0019520934424834247, |
| "loss": 4.95612060546875, |
| "step": 7200 |
| }, |
| { |
| "epoch": 0.146, |
| "grad_norm": 0.2770542502403259, |
| "learning_rate": 0.0019500500611433025, |
| "loss": 4.9815975952148435, |
| "step": 7300 |
| }, |
| { |
| "epoch": 0.148, |
| "grad_norm": 0.627005934715271, |
| "learning_rate": 0.0019479651215357707, |
| "loss": 4.982627563476562, |
| "step": 7400 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.5774574279785156, |
| "learning_rate": 0.0019458387148628417, |
| "loss": 4.9119635009765625, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.152, |
| "grad_norm": 0.6212947368621826, |
| "learning_rate": 0.001943670934140432, |
| "loss": 4.96866455078125, |
| "step": 7600 |
| }, |
| { |
| "epoch": 0.154, |
| "grad_norm": 0.4175465703010559, |
| "learning_rate": 0.0019414618741942936, |
| "loss": 4.972650146484375, |
| "step": 7700 |
| }, |
| { |
| "epoch": 0.156, |
| "grad_norm": 0.30829882621765137, |
| "learning_rate": 0.0019392116316558638, |
| "loss": 4.9120181274414065, |
| "step": 7800 |
| }, |
| { |
| "epoch": 0.158, |
| "grad_norm": 0.2758282423019409, |
| "learning_rate": 0.001936920304958042, |
| "loss": 4.90683837890625, |
| "step": 7900 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.30226844549179077, |
| "learning_rate": 0.0019345879943308804, |
| "loss": 4.854488220214844, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_accuracy": 0.22608414872798435, |
| "eval_loss": 4.913477420806885, |
| "eval_runtime": 6.8714, |
| "eval_samples_per_second": 145.531, |
| "eval_steps_per_second": 18.191, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.162, |
| "grad_norm": 0.712541401386261, |
| "learning_rate": 0.0019322148017972016, |
| "loss": 4.847081909179687, |
| "step": 8100 |
| }, |
| { |
| "epoch": 0.164, |
| "grad_norm": 0.47257572412490845, |
| "learning_rate": 0.001929800831168135, |
| "loss": 4.90064453125, |
| "step": 8200 |
| }, |
| { |
| "epoch": 0.166, |
| "grad_norm": 0.3497978150844574, |
| "learning_rate": 0.001927346188038576, |
| "loss": 4.955650329589844, |
| "step": 8300 |
| }, |
| { |
| "epoch": 0.168, |
| "grad_norm": 0.3204037845134735, |
| "learning_rate": 0.0019248509797825672, |
| "loss": 4.851766967773438, |
| "step": 8400 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.3258970379829407, |
| "learning_rate": 0.0019223153155486009, |
| "loss": 4.883788452148438, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.172, |
| "grad_norm": 0.4524133503437042, |
| "learning_rate": 0.0019197393062548454, |
| "loss": 4.840924682617188, |
| "step": 8600 |
| }, |
| { |
| "epoch": 0.174, |
| "grad_norm": 0.28501275181770325, |
| "learning_rate": 0.0019171230645842923, |
| "loss": 4.877713317871094, |
| "step": 8700 |
| }, |
| { |
| "epoch": 0.176, |
| "grad_norm": 0.4920591711997986, |
| "learning_rate": 0.0019144667049798272, |
| "loss": 4.900206298828125, |
| "step": 8800 |
| }, |
| { |
| "epoch": 0.178, |
| "grad_norm": 0.30207598209381104, |
| "learning_rate": 0.0019117703436392253, |
| "loss": 4.907836303710938, |
| "step": 8900 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.3460649251937866, |
| "learning_rate": 0.001909034098510066, |
| "loss": 4.8303515625, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.18, |
| "eval_accuracy": 0.22981996086105674, |
| "eval_loss": 4.851044178009033, |
| "eval_runtime": 6.9243, |
| "eval_samples_per_second": 144.418, |
| "eval_steps_per_second": 18.052, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.182, |
| "grad_norm": 0.26366087794303894, |
| "learning_rate": 0.001906258089284576, |
| "loss": 4.757725524902344, |
| "step": 9100 |
| }, |
| { |
| "epoch": 0.184, |
| "grad_norm": 0.3308315873146057, |
| "learning_rate": 0.0019034424373943915, |
| "loss": 4.747350769042969, |
| "step": 9200 |
| }, |
| { |
| "epoch": 0.186, |
| "grad_norm": 0.24568253755569458, |
| "learning_rate": 0.0019005872660052478, |
| "loss": 4.785510559082031, |
| "step": 9300 |
| }, |
| { |
| "epoch": 0.188, |
| "grad_norm": 0.43289270997047424, |
| "learning_rate": 0.001897692700011591, |
| "loss": 4.789692687988281, |
| "step": 9400 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.25019797682762146, |
| "learning_rate": 0.0018947588660311143, |
| "loss": 4.792172241210937, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.192, |
| "grad_norm": 0.6229330897331238, |
| "learning_rate": 0.0018917858923992211, |
| "loss": 4.777132873535156, |
| "step": 9600 |
| }, |
| { |
| "epoch": 0.194, |
| "grad_norm": 0.350772500038147, |
| "learning_rate": 0.0018887739091634085, |
| "loss": 4.744659423828125, |
| "step": 9700 |
| }, |
| { |
| "epoch": 0.196, |
| "grad_norm": 0.23172135651111603, |
| "learning_rate": 0.0018857230480775807, |
| "loss": 4.748968811035156, |
| "step": 9800 |
| }, |
| { |
| "epoch": 0.198, |
| "grad_norm": 0.3821462392807007, |
| "learning_rate": 0.0018826334425962855, |
| "loss": 4.802294616699219, |
| "step": 9900 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.2725774645805359, |
| "learning_rate": 0.0018795052278688753, |
| "loss": 4.774011535644531, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_accuracy": 0.23221135029354206, |
| "eval_loss": 4.819427967071533, |
| "eval_runtime": 6.9031, |
| "eval_samples_per_second": 144.863, |
| "eval_steps_per_second": 18.108, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.202, |
| "grad_norm": 0.4188442528247833, |
| "learning_rate": 0.0018763385407335963, |
| "loss": 4.784246215820312, |
| "step": 10100 |
| }, |
| { |
| "epoch": 0.204, |
| "grad_norm": 0.24621133506298065, |
| "learning_rate": 0.001873133519711602, |
| "loss": 4.787679748535156, |
| "step": 10200 |
| }, |
| { |
| "epoch": 0.206, |
| "grad_norm": 0.5215740203857422, |
| "learning_rate": 0.0018698903050008956, |
| "loss": 4.709499206542969, |
| "step": 10300 |
| }, |
| { |
| "epoch": 0.208, |
| "grad_norm": 0.4617030918598175, |
| "learning_rate": 0.0018666090384701947, |
| "loss": 4.747078552246093, |
| "step": 10400 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.29167914390563965, |
| "learning_rate": 0.001863289863652727, |
| "loss": 4.661806945800781, |
| "step": 10500 |
| }, |
| { |
| "epoch": 0.212, |
| "grad_norm": 0.4101203680038452, |
| "learning_rate": 0.0018599329257399516, |
| "loss": 4.659268493652344, |
| "step": 10600 |
| }, |
| { |
| "epoch": 0.214, |
| "grad_norm": 0.31853312253952026, |
| "learning_rate": 0.0018565383715752083, |
| "loss": 4.701767272949219, |
| "step": 10700 |
| }, |
| { |
| "epoch": 0.216, |
| "grad_norm": 0.2906162440776825, |
| "learning_rate": 0.0018531063496472927, |
| "loss": 4.690833435058594, |
| "step": 10800 |
| }, |
| { |
| "epoch": 0.218, |
| "grad_norm": 0.3280249238014221, |
| "learning_rate": 0.0018496370100839622, |
| "loss": 4.6896670532226565, |
| "step": 10900 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.3699072301387787, |
| "learning_rate": 0.0018461305046453683, |
| "loss": 4.636054382324219, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.22, |
| "eval_accuracy": 0.2340371819960861, |
| "eval_loss": 4.797712326049805, |
| "eval_runtime": 6.7202, |
| "eval_samples_per_second": 148.805, |
| "eval_steps_per_second": 18.601, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.222, |
| "grad_norm": 0.24158497154712677, |
| "learning_rate": 0.0018425869867174187, |
| "loss": 4.711828002929687, |
| "step": 11100 |
| }, |
| { |
| "epoch": 0.224, |
| "grad_norm": 0.4193456172943115, |
| "learning_rate": 0.0018390066113050665, |
| "loss": 4.724891357421875, |
| "step": 11200 |
| }, |
| { |
| "epoch": 0.226, |
| "grad_norm": 0.3414510190486908, |
| "learning_rate": 0.0018353895350255317, |
| "loss": 4.649370727539062, |
| "step": 11300 |
| }, |
| { |
| "epoch": 0.228, |
| "grad_norm": 0.2959993779659271, |
| "learning_rate": 0.0018317359161014477, |
| "loss": 4.620471801757812, |
| "step": 11400 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.35871621966362, |
| "learning_rate": 0.001828045914353943, |
| "loss": 4.65095458984375, |
| "step": 11500 |
| }, |
| { |
| "epoch": 0.232, |
| "grad_norm": 0.8000448942184448, |
| "learning_rate": 0.0018243196911956476, |
| "loss": 4.606728210449218, |
| "step": 11600 |
| }, |
| { |
| "epoch": 0.234, |
| "grad_norm": 0.3677903115749359, |
| "learning_rate": 0.0018205574096236336, |
| "loss": 4.599508361816406, |
| "step": 11700 |
| }, |
| { |
| "epoch": 0.236, |
| "grad_norm": 0.5635560750961304, |
| "learning_rate": 0.0018167592342122857, |
| "loss": 4.591564331054688, |
| "step": 11800 |
| }, |
| { |
| "epoch": 0.238, |
| "grad_norm": 0.29384273290634155, |
| "learning_rate": 0.0018129253311061002, |
| "loss": 4.715082092285156, |
| "step": 11900 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.34943443536758423, |
| "learning_rate": 0.0018090558680124193, |
| "loss": 4.741492919921875, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_accuracy": 0.24006849315068493, |
| "eval_loss": 4.731167316436768, |
| "eval_runtime": 6.7722, |
| "eval_samples_per_second": 147.662, |
| "eval_steps_per_second": 18.458, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.242, |
| "grad_norm": 0.40804609656333923, |
| "learning_rate": 0.0018051510141940939, |
| "loss": 4.809200744628907, |
| "step": 12100 |
| }, |
| { |
| "epoch": 0.244, |
| "grad_norm": 0.23709678649902344, |
| "learning_rate": 0.00180121094046208, |
| "loss": 4.694277648925781, |
| "step": 12200 |
| }, |
| { |
| "epoch": 0.246, |
| "grad_norm": 0.3795485496520996, |
| "learning_rate": 0.001797235819167967, |
| "loss": 4.7016690063476565, |
| "step": 12300 |
| }, |
| { |
| "epoch": 0.248, |
| "grad_norm": 0.2936651110649109, |
| "learning_rate": 0.0017932258241964375, |
| "loss": 4.7381680297851565, |
| "step": 12400 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.3166375160217285, |
| "learning_rate": 0.0017891811309576622, |
| "loss": 4.715390014648437, |
| "step": 12500 |
| }, |
| { |
| "epoch": 0.252, |
| "grad_norm": 0.43418648838996887, |
| "learning_rate": 0.001785101916379627, |
| "loss": 4.731936340332031, |
| "step": 12600 |
| }, |
| { |
| "epoch": 0.254, |
| "grad_norm": 0.6372531652450562, |
| "learning_rate": 0.0017809883589003912, |
| "loss": 4.717911071777344, |
| "step": 12700 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 0.3290679454803467, |
| "learning_rate": 0.0017768406384602862, |
| "loss": 4.715725708007812, |
| "step": 12800 |
| }, |
| { |
| "epoch": 0.258, |
| "grad_norm": 0.5329638123512268, |
| "learning_rate": 0.00177265893649404, |
| "loss": 4.697486572265625, |
| "step": 12900 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.4434824287891388, |
| "learning_rate": 0.0017684434359228438, |
| "loss": 4.648684387207031, |
| "step": 13000 |
| }, |
| { |
| "epoch": 0.26, |
| "eval_accuracy": 0.2430587084148728, |
| "eval_loss": 4.6857452392578125, |
| "eval_runtime": 6.673, |
| "eval_samples_per_second": 149.859, |
| "eval_steps_per_second": 18.732, |
| "step": 13000 |
| }, |
| { |
| "epoch": 0.262, |
| "grad_norm": 1.1536272764205933, |
| "learning_rate": 0.0017641943211463488, |
| "loss": 4.693533935546875, |
| "step": 13100 |
| }, |
| { |
| "epoch": 0.264, |
| "grad_norm": 0.2765742838382721, |
| "learning_rate": 0.0017599117780346006, |
| "loss": 4.62672119140625, |
| "step": 13200 |
| }, |
| { |
| "epoch": 0.266, |
| "grad_norm": 0.3210831880569458, |
| "learning_rate": 0.0017555959939199084, |
| "loss": 4.677549438476563, |
| "step": 13300 |
| }, |
| { |
| "epoch": 0.268, |
| "grad_norm": 0.45882949233055115, |
| "learning_rate": 0.0017512471575886505, |
| "loss": 4.613779602050781, |
| "step": 13400 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.26687324047088623, |
| "learning_rate": 0.0017468654592730168, |
| "loss": 4.792513427734375, |
| "step": 13500 |
| }, |
| { |
| "epoch": 0.272, |
| "grad_norm": 0.48945170640945435, |
| "learning_rate": 0.0017424510906426853, |
| "loss": 4.670322875976563, |
| "step": 13600 |
| }, |
| { |
| "epoch": 0.274, |
| "grad_norm": 0.4301573634147644, |
| "learning_rate": 0.0017380042447964414, |
| "loss": 4.652569885253906, |
| "step": 13700 |
| }, |
| { |
| "epoch": 0.276, |
| "grad_norm": 0.40779948234558105, |
| "learning_rate": 0.0017335251162537279, |
| "loss": 4.63238525390625, |
| "step": 13800 |
| }, |
| { |
| "epoch": 0.278, |
| "grad_norm": 0.3157722055912018, |
| "learning_rate": 0.0017290139009461377, |
| "loss": 4.648804321289062, |
| "step": 13900 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5345812439918518, |
| "learning_rate": 0.0017244707962088424, |
| "loss": 4.689738159179687, |
| "step": 14000 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_accuracy": 0.24557729941291584, |
| "eval_loss": 4.648989200592041, |
| "eval_runtime": 6.7439, |
| "eval_samples_per_second": 148.281, |
| "eval_steps_per_second": 18.535, |
| "step": 14000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 50000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 2000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
