| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.217435897435898, |
| "eval_steps": 500, |
| "global_step": 4928, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.020512820512820513, |
| "grad_norm": 0.875, |
| "learning_rate": 2.9999969395283144e-06, |
| "loss": 0.6637, |
| "num_input_tokens_seen": 75456, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.041025641025641026, |
| "grad_norm": 1.4140625, |
| "learning_rate": 2.9999877581257458e-06, |
| "loss": 0.6963, |
| "num_input_tokens_seen": 160992, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06153846153846154, |
| "grad_norm": 1.59375, |
| "learning_rate": 2.9999724558297605e-06, |
| "loss": 0.6919, |
| "num_input_tokens_seen": 253856, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.08205128205128205, |
| "grad_norm": 2.40625, |
| "learning_rate": 2.999951032702801e-06, |
| "loss": 0.6605, |
| "num_input_tokens_seen": 328640, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.10256410256410256, |
| "grad_norm": 0.75390625, |
| "learning_rate": 2.9999234888322877e-06, |
| "loss": 0.5888, |
| "num_input_tokens_seen": 401504, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.12307692307692308, |
| "grad_norm": 1.578125, |
| "learning_rate": 2.9998898243306162e-06, |
| "loss": 0.6087, |
| "num_input_tokens_seen": 475168, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.14358974358974358, |
| "grad_norm": 0.89453125, |
| "learning_rate": 2.99985003933516e-06, |
| "loss": 0.6405, |
| "num_input_tokens_seen": 547168, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.1641025641025641, |
| "grad_norm": 1.1015625, |
| "learning_rate": 2.999804134008266e-06, |
| "loss": 0.6443, |
| "num_input_tokens_seen": 618176, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.69921875, |
| "learning_rate": 2.9997521085372565e-06, |
| "loss": 0.6554, |
| "num_input_tokens_seen": 701184, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.20512820512820512, |
| "grad_norm": 1.0234375, |
| "learning_rate": 2.999693963134429e-06, |
| "loss": 0.6903, |
| "num_input_tokens_seen": 782656, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.22564102564102564, |
| "grad_norm": 0.796875, |
| "learning_rate": 2.9996296980370526e-06, |
| "loss": 0.6915, |
| "num_input_tokens_seen": 869280, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.24615384615384617, |
| "grad_norm": 0.8515625, |
| "learning_rate": 2.99955931350737e-06, |
| "loss": 0.584, |
| "num_input_tokens_seen": 944032, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 0.91796875, |
| "learning_rate": 2.999482809832594e-06, |
| "loss": 0.5908, |
| "num_input_tokens_seen": 1025568, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.28717948717948716, |
| "grad_norm": 0.84375, |
| "learning_rate": 2.9994001873249074e-06, |
| "loss": 0.5811, |
| "num_input_tokens_seen": 1105344, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 0.6953125, |
| "learning_rate": 2.999311446321462e-06, |
| "loss": 0.5792, |
| "num_input_tokens_seen": 1182016, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.3282051282051282, |
| "grad_norm": 0.99609375, |
| "learning_rate": 2.999216587184378e-06, |
| "loss": 0.5923, |
| "num_input_tokens_seen": 1265440, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.3487179487179487, |
| "grad_norm": 0.91015625, |
| "learning_rate": 2.9991156103007394e-06, |
| "loss": 0.5896, |
| "num_input_tokens_seen": 1347296, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.90234375, |
| "learning_rate": 2.9990085160825954e-06, |
| "loss": 0.6283, |
| "num_input_tokens_seen": 1424064, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.38974358974358975, |
| "grad_norm": 0.67578125, |
| "learning_rate": 2.9988953049669577e-06, |
| "loss": 0.5329, |
| "num_input_tokens_seen": 1492416, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.41025641025641024, |
| "grad_norm": 0.44921875, |
| "learning_rate": 2.998775977415799e-06, |
| "loss": 0.5582, |
| "num_input_tokens_seen": 1572192, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4307692307692308, |
| "grad_norm": 0.59375, |
| "learning_rate": 2.998650533916051e-06, |
| "loss": 0.6529, |
| "num_input_tokens_seen": 1650592, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.4512820512820513, |
| "grad_norm": 0.515625, |
| "learning_rate": 2.998518974979602e-06, |
| "loss": 0.5449, |
| "num_input_tokens_seen": 1728128, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.4717948717948718, |
| "grad_norm": 0.494140625, |
| "learning_rate": 2.998381301143295e-06, |
| "loss": 0.573, |
| "num_input_tokens_seen": 1806080, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.49230769230769234, |
| "grad_norm": 0.38671875, |
| "learning_rate": 2.9982375129689253e-06, |
| "loss": 0.6065, |
| "num_input_tokens_seen": 1884544, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5128205128205128, |
| "grad_norm": 0.396484375, |
| "learning_rate": 2.9980876110432404e-06, |
| "loss": 0.6232, |
| "num_input_tokens_seen": 1961376, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 0.408203125, |
| "learning_rate": 2.9979315959779335e-06, |
| "loss": 0.5061, |
| "num_input_tokens_seen": 2036064, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5538461538461539, |
| "grad_norm": 0.271484375, |
| "learning_rate": 2.9977694684096447e-06, |
| "loss": 0.5657, |
| "num_input_tokens_seen": 2109376, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.5743589743589743, |
| "grad_norm": 0.27734375, |
| "learning_rate": 2.997601228999956e-06, |
| "loss": 0.5597, |
| "num_input_tokens_seen": 2181344, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.5948717948717949, |
| "grad_norm": 0.2451171875, |
| "learning_rate": 2.99742687843539e-06, |
| "loss": 0.5514, |
| "num_input_tokens_seen": 2256768, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.2265625, |
| "learning_rate": 2.997246417427407e-06, |
| "loss": 0.53, |
| "num_input_tokens_seen": 2330144, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6358974358974359, |
| "grad_norm": 0.19921875, |
| "learning_rate": 2.9970598467124008e-06, |
| "loss": 0.5365, |
| "num_input_tokens_seen": 2402688, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.6564102564102564, |
| "grad_norm": 0.1923828125, |
| "learning_rate": 2.9968671670516983e-06, |
| "loss": 0.5578, |
| "num_input_tokens_seen": 2476800, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.676923076923077, |
| "grad_norm": 0.166015625, |
| "learning_rate": 2.9966683792315528e-06, |
| "loss": 0.5492, |
| "num_input_tokens_seen": 2565792, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.6974358974358974, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 2.9964634840631435e-06, |
| "loss": 0.5144, |
| "num_input_tokens_seen": 2637792, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.717948717948718, |
| "grad_norm": 0.154296875, |
| "learning_rate": 2.9962524823825724e-06, |
| "loss": 0.5741, |
| "num_input_tokens_seen": 2718944, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.7384615384615385, |
| "grad_norm": 0.1513671875, |
| "learning_rate": 2.9960353750508583e-06, |
| "loss": 0.5846, |
| "num_input_tokens_seen": 2802240, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.7589743589743589, |
| "grad_norm": 0.1474609375, |
| "learning_rate": 2.995812162953936e-06, |
| "loss": 0.5834, |
| "num_input_tokens_seen": 2884672, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.7794871794871795, |
| "grad_norm": 0.154296875, |
| "learning_rate": 2.9955828470026515e-06, |
| "loss": 0.5493, |
| "num_input_tokens_seen": 2953536, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.138671875, |
| "learning_rate": 2.9953474281327576e-06, |
| "loss": 0.5503, |
| "num_input_tokens_seen": 3026496, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.8205128205128205, |
| "grad_norm": 0.244140625, |
| "learning_rate": 2.995105907304912e-06, |
| "loss": 0.5835, |
| "num_input_tokens_seen": 3105376, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.841025641025641, |
| "grad_norm": 0.349609375, |
| "learning_rate": 2.9948582855046704e-06, |
| "loss": 0.5583, |
| "num_input_tokens_seen": 3179776, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.8615384615384616, |
| "grad_norm": 0.1826171875, |
| "learning_rate": 2.9946045637424864e-06, |
| "loss": 0.6392, |
| "num_input_tokens_seen": 3262336, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.882051282051282, |
| "grad_norm": 0.1640625, |
| "learning_rate": 2.994344743053704e-06, |
| "loss": 0.5658, |
| "num_input_tokens_seen": 3343904, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.9025641025641026, |
| "grad_norm": 0.50390625, |
| "learning_rate": 2.9940788244985557e-06, |
| "loss": 0.5609, |
| "num_input_tokens_seen": 3419264, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 0.458984375, |
| "learning_rate": 2.9938068091621556e-06, |
| "loss": 0.5305, |
| "num_input_tokens_seen": 3496032, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.9435897435897436, |
| "grad_norm": 0.41015625, |
| "learning_rate": 2.9935286981544975e-06, |
| "loss": 0.5652, |
| "num_input_tokens_seen": 3570880, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.9641025641025641, |
| "grad_norm": 0.7734375, |
| "learning_rate": 2.9932444926104495e-06, |
| "loss": 0.5348, |
| "num_input_tokens_seen": 3644096, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.9846153846153847, |
| "grad_norm": 0.86328125, |
| "learning_rate": 2.992954193689749e-06, |
| "loss": 0.5344, |
| "num_input_tokens_seen": 3717088, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.005128205128205, |
| "grad_norm": 0.435546875, |
| "learning_rate": 2.9926578025769978e-06, |
| "loss": 0.5977, |
| "num_input_tokens_seen": 3783648, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.0256410256410255, |
| "grad_norm": 0.408203125, |
| "learning_rate": 2.992355320481658e-06, |
| "loss": 0.5304, |
| "num_input_tokens_seen": 3852160, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.0461538461538462, |
| "grad_norm": 0.75390625, |
| "learning_rate": 2.9920467486380475e-06, |
| "loss": 0.5617, |
| "num_input_tokens_seen": 3924416, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.46875, |
| "learning_rate": 2.991732088305333e-06, |
| "loss": 0.5367, |
| "num_input_tokens_seen": 4006432, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.087179487179487, |
| "grad_norm": 0.5234375, |
| "learning_rate": 2.991411340767526e-06, |
| "loss": 0.5207, |
| "num_input_tokens_seen": 4081888, |
| "step": 265 |
| }, |
| { |
| "epoch": 1.1076923076923078, |
| "grad_norm": 0.41015625, |
| "learning_rate": 2.9910845073334793e-06, |
| "loss": 0.556, |
| "num_input_tokens_seen": 4155968, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.1282051282051282, |
| "grad_norm": 0.421875, |
| "learning_rate": 2.9907515893368784e-06, |
| "loss": 0.537, |
| "num_input_tokens_seen": 4234272, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.1487179487179486, |
| "grad_norm": 0.40234375, |
| "learning_rate": 2.9904125881362378e-06, |
| "loss": 0.5305, |
| "num_input_tokens_seen": 4302368, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.1692307692307693, |
| "grad_norm": 0.5625, |
| "learning_rate": 2.990067505114896e-06, |
| "loss": 0.5337, |
| "num_input_tokens_seen": 4376640, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.1897435897435897, |
| "grad_norm": 0.451171875, |
| "learning_rate": 2.9897163416810084e-06, |
| "loss": 0.592, |
| "num_input_tokens_seen": 4458208, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.2102564102564102, |
| "grad_norm": 0.40625, |
| "learning_rate": 2.9893590992675427e-06, |
| "loss": 0.5808, |
| "num_input_tokens_seen": 4537920, |
| "step": 295 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 0.58984375, |
| "learning_rate": 2.988995779332273e-06, |
| "loss": 0.5569, |
| "num_input_tokens_seen": 4606880, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.2512820512820513, |
| "grad_norm": 0.431640625, |
| "learning_rate": 2.9886263833577725e-06, |
| "loss": 0.5422, |
| "num_input_tokens_seen": 4682816, |
| "step": 305 |
| }, |
| { |
| "epoch": 1.2717948717948717, |
| "grad_norm": 0.5234375, |
| "learning_rate": 2.98825091285141e-06, |
| "loss": 0.5296, |
| "num_input_tokens_seen": 4756032, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.2923076923076924, |
| "grad_norm": 0.4453125, |
| "learning_rate": 2.987869369345341e-06, |
| "loss": 0.5012, |
| "num_input_tokens_seen": 4827232, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.3128205128205128, |
| "grad_norm": 0.392578125, |
| "learning_rate": 2.987481754396502e-06, |
| "loss": 0.5289, |
| "num_input_tokens_seen": 4902368, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.326171875, |
| "learning_rate": 2.9870880695866067e-06, |
| "loss": 0.5245, |
| "num_input_tokens_seen": 4978080, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.353846153846154, |
| "grad_norm": 0.62109375, |
| "learning_rate": 2.986688316522136e-06, |
| "loss": 0.5325, |
| "num_input_tokens_seen": 5047456, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.3743589743589744, |
| "grad_norm": 0.390625, |
| "learning_rate": 2.9862824968343352e-06, |
| "loss": 0.5068, |
| "num_input_tokens_seen": 5118720, |
| "step": 335 |
| }, |
| { |
| "epoch": 1.3948717948717948, |
| "grad_norm": 0.345703125, |
| "learning_rate": 2.9858706121792036e-06, |
| "loss": 0.5165, |
| "num_input_tokens_seen": 5196288, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.4153846153846155, |
| "grad_norm": 0.251953125, |
| "learning_rate": 2.985452664237488e-06, |
| "loss": 0.5025, |
| "num_input_tokens_seen": 5272480, |
| "step": 345 |
| }, |
| { |
| "epoch": 1.435897435897436, |
| "grad_norm": 0.302734375, |
| "learning_rate": 2.98502865471468e-06, |
| "loss": 0.5285, |
| "num_input_tokens_seen": 5343296, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.4564102564102563, |
| "grad_norm": 0.314453125, |
| "learning_rate": 2.9845985853410053e-06, |
| "loss": 0.4983, |
| "num_input_tokens_seen": 5415904, |
| "step": 355 |
| }, |
| { |
| "epoch": 1.476923076923077, |
| "grad_norm": 0.236328125, |
| "learning_rate": 2.9841624578714167e-06, |
| "loss": 0.5789, |
| "num_input_tokens_seen": 5502176, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.4974358974358974, |
| "grad_norm": 0.2060546875, |
| "learning_rate": 2.9837202740855897e-06, |
| "loss": 0.5394, |
| "num_input_tokens_seen": 5580352, |
| "step": 365 |
| }, |
| { |
| "epoch": 1.5179487179487179, |
| "grad_norm": 0.267578125, |
| "learning_rate": 2.9832720357879107e-06, |
| "loss": 0.5664, |
| "num_input_tokens_seen": 5662912, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 0.22265625, |
| "learning_rate": 2.9828177448074753e-06, |
| "loss": 0.5546, |
| "num_input_tokens_seen": 5743776, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.558974358974359, |
| "grad_norm": 0.20703125, |
| "learning_rate": 2.9823574029980757e-06, |
| "loss": 0.5412, |
| "num_input_tokens_seen": 5812384, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.5794871794871796, |
| "grad_norm": 0.1630859375, |
| "learning_rate": 2.981891012238196e-06, |
| "loss": 0.5587, |
| "num_input_tokens_seen": 5892768, |
| "step": 385 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.1640625, |
| "learning_rate": 2.9814185744310036e-06, |
| "loss": 0.535, |
| "num_input_tokens_seen": 5974592, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.6205128205128205, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 2.9809400915043424e-06, |
| "loss": 0.512, |
| "num_input_tokens_seen": 6050080, |
| "step": 395 |
| }, |
| { |
| "epoch": 1.641025641025641, |
| "grad_norm": 0.142578125, |
| "learning_rate": 2.9804555654107243e-06, |
| "loss": 0.5392, |
| "num_input_tokens_seen": 6137248, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.6615384615384614, |
| "grad_norm": 0.1376953125, |
| "learning_rate": 2.9799649981273185e-06, |
| "loss": 0.6444, |
| "num_input_tokens_seen": 6232704, |
| "step": 405 |
| }, |
| { |
| "epoch": 1.682051282051282, |
| "grad_norm": 0.1435546875, |
| "learning_rate": 2.9794683916559493e-06, |
| "loss": 0.5202, |
| "num_input_tokens_seen": 6304064, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.7025641025641025, |
| "grad_norm": 0.1455078125, |
| "learning_rate": 2.9789657480230842e-06, |
| "loss": 0.5344, |
| "num_input_tokens_seen": 6392928, |
| "step": 415 |
| }, |
| { |
| "epoch": 1.7230769230769232, |
| "grad_norm": 0.16015625, |
| "learning_rate": 2.9784570692798236e-06, |
| "loss": 0.4614, |
| "num_input_tokens_seen": 6473120, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.7435897435897436, |
| "grad_norm": 0.19921875, |
| "learning_rate": 2.977942357501898e-06, |
| "loss": 0.5036, |
| "num_input_tokens_seen": 6545312, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.764102564102564, |
| "grad_norm": 0.41796875, |
| "learning_rate": 2.977421614789655e-06, |
| "loss": 0.5308, |
| "num_input_tokens_seen": 6629984, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.7846153846153845, |
| "grad_norm": 0.1767578125, |
| "learning_rate": 2.976894843268051e-06, |
| "loss": 0.5475, |
| "num_input_tokens_seen": 6715936, |
| "step": 435 |
| }, |
| { |
| "epoch": 1.8051282051282052, |
| "grad_norm": 0.150390625, |
| "learning_rate": 2.976362045086647e-06, |
| "loss": 0.5704, |
| "num_input_tokens_seen": 6797472, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.8256410256410256, |
| "grad_norm": 0.416015625, |
| "learning_rate": 2.975823222419594e-06, |
| "loss": 0.4781, |
| "num_input_tokens_seen": 6867808, |
| "step": 445 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 0.25, |
| "learning_rate": 2.9752783774656267e-06, |
| "loss": 0.5247, |
| "num_input_tokens_seen": 6944480, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.8666666666666667, |
| "grad_norm": 0.703125, |
| "learning_rate": 2.974727512448056e-06, |
| "loss": 0.5161, |
| "num_input_tokens_seen": 7024064, |
| "step": 455 |
| }, |
| { |
| "epoch": 1.8871794871794871, |
| "grad_norm": 0.65234375, |
| "learning_rate": 2.974170629614757e-06, |
| "loss": 0.5049, |
| "num_input_tokens_seen": 7103488, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.9076923076923076, |
| "grad_norm": 0.734375, |
| "learning_rate": 2.9736077312381624e-06, |
| "loss": 0.5712, |
| "num_input_tokens_seen": 7190304, |
| "step": 465 |
| }, |
| { |
| "epoch": 1.9282051282051282, |
| "grad_norm": 0.40234375, |
| "learning_rate": 2.9730388196152513e-06, |
| "loss": 0.5222, |
| "num_input_tokens_seen": 7265056, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.9487179487179487, |
| "grad_norm": 0.28125, |
| "learning_rate": 2.972463897067541e-06, |
| "loss": 0.4829, |
| "num_input_tokens_seen": 7336992, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.9692307692307693, |
| "grad_norm": 0.56640625, |
| "learning_rate": 2.971882965941077e-06, |
| "loss": 0.5218, |
| "num_input_tokens_seen": 7413984, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.9897435897435898, |
| "grad_norm": 0.357421875, |
| "learning_rate": 2.9712960286064237e-06, |
| "loss": 0.5543, |
| "num_input_tokens_seen": 7492768, |
| "step": 485 |
| }, |
| { |
| "epoch": 2.01025641025641, |
| "grad_norm": 0.26171875, |
| "learning_rate": 2.970703087458655e-06, |
| "loss": 0.5036, |
| "num_input_tokens_seen": 7563904, |
| "step": 490 |
| }, |
| { |
| "epoch": 2.0307692307692307, |
| "grad_norm": 0.38671875, |
| "learning_rate": 2.9701041449173426e-06, |
| "loss": 0.556, |
| "num_input_tokens_seen": 7634464, |
| "step": 495 |
| }, |
| { |
| "epoch": 2.051282051282051, |
| "grad_norm": 0.375, |
| "learning_rate": 2.96949920342655e-06, |
| "loss": 0.5742, |
| "num_input_tokens_seen": 7711168, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.071794871794872, |
| "grad_norm": 0.365234375, |
| "learning_rate": 2.968888265454818e-06, |
| "loss": 0.4905, |
| "num_input_tokens_seen": 7786656, |
| "step": 505 |
| }, |
| { |
| "epoch": 2.0923076923076924, |
| "grad_norm": 0.271484375, |
| "learning_rate": 2.968271333495158e-06, |
| "loss": 0.5134, |
| "num_input_tokens_seen": 7858240, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.112820512820513, |
| "grad_norm": 0.373046875, |
| "learning_rate": 2.967648410065041e-06, |
| "loss": 0.6211, |
| "num_input_tokens_seen": 7952064, |
| "step": 515 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.45703125, |
| "learning_rate": 2.9670194977063857e-06, |
| "loss": 0.515, |
| "num_input_tokens_seen": 8026688, |
| "step": 520 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 0.400390625, |
| "learning_rate": 2.96638459898555e-06, |
| "loss": 0.5464, |
| "num_input_tokens_seen": 8104064, |
| "step": 525 |
| }, |
| { |
| "epoch": 2.174358974358974, |
| "grad_norm": 0.421875, |
| "learning_rate": 2.9657437164933205e-06, |
| "loss": 0.5331, |
| "num_input_tokens_seen": 8187968, |
| "step": 530 |
| }, |
| { |
| "epoch": 2.194871794871795, |
| "grad_norm": 0.396484375, |
| "learning_rate": 2.9650968528449e-06, |
| "loss": 0.5236, |
| "num_input_tokens_seen": 8261312, |
| "step": 535 |
| }, |
| { |
| "epoch": 2.2153846153846155, |
| "grad_norm": 0.34765625, |
| "learning_rate": 2.9644440106799e-06, |
| "loss": 0.4345, |
| "num_input_tokens_seen": 8336032, |
| "step": 540 |
| }, |
| { |
| "epoch": 2.235897435897436, |
| "grad_norm": 0.353515625, |
| "learning_rate": 2.963785192662327e-06, |
| "loss": 0.4853, |
| "num_input_tokens_seen": 8405024, |
| "step": 545 |
| }, |
| { |
| "epoch": 2.2564102564102564, |
| "grad_norm": 0.365234375, |
| "learning_rate": 2.9631204014805716e-06, |
| "loss": 0.5, |
| "num_input_tokens_seen": 8483456, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.276923076923077, |
| "grad_norm": 0.38671875, |
| "learning_rate": 2.9624496398474014e-06, |
| "loss": 0.4863, |
| "num_input_tokens_seen": 8560768, |
| "step": 555 |
| }, |
| { |
| "epoch": 2.2974358974358973, |
| "grad_norm": 0.32421875, |
| "learning_rate": 2.961772910499945e-06, |
| "loss": 0.48, |
| "num_input_tokens_seen": 8637888, |
| "step": 560 |
| }, |
| { |
| "epoch": 2.3179487179487177, |
| "grad_norm": 0.376953125, |
| "learning_rate": 2.9610902161996838e-06, |
| "loss": 0.5768, |
| "num_input_tokens_seen": 8715360, |
| "step": 565 |
| }, |
| { |
| "epoch": 2.3384615384615386, |
| "grad_norm": 0.265625, |
| "learning_rate": 2.96040155973244e-06, |
| "loss": 0.4751, |
| "num_input_tokens_seen": 8795200, |
| "step": 570 |
| }, |
| { |
| "epoch": 2.358974358974359, |
| "grad_norm": 0.283203125, |
| "learning_rate": 2.959706943908365e-06, |
| "loss": 0.5161, |
| "num_input_tokens_seen": 8883136, |
| "step": 575 |
| }, |
| { |
| "epoch": 2.3794871794871795, |
| "grad_norm": 0.271484375, |
| "learning_rate": 2.9590063715619287e-06, |
| "loss": 0.5588, |
| "num_input_tokens_seen": 8961568, |
| "step": 580 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.2373046875, |
| "learning_rate": 2.9582998455519062e-06, |
| "loss": 0.5527, |
| "num_input_tokens_seen": 9043360, |
| "step": 585 |
| }, |
| { |
| "epoch": 2.4205128205128204, |
| "grad_norm": 0.21875, |
| "learning_rate": 2.9575873687613676e-06, |
| "loss": 0.4897, |
| "num_input_tokens_seen": 9116448, |
| "step": 590 |
| }, |
| { |
| "epoch": 2.4410256410256412, |
| "grad_norm": 0.21484375, |
| "learning_rate": 2.9568689440976676e-06, |
| "loss": 0.5359, |
| "num_input_tokens_seen": 9193120, |
| "step": 595 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 0.205078125, |
| "learning_rate": 2.95614457449243e-06, |
| "loss": 0.5763, |
| "num_input_tokens_seen": 9269920, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.482051282051282, |
| "grad_norm": 0.1845703125, |
| "learning_rate": 2.9554142629015382e-06, |
| "loss": 0.4631, |
| "num_input_tokens_seen": 9339968, |
| "step": 605 |
| }, |
| { |
| "epoch": 2.5025641025641026, |
| "grad_norm": 0.1650390625, |
| "learning_rate": 2.954678012305123e-06, |
| "loss": 0.5349, |
| "num_input_tokens_seen": 9426976, |
| "step": 610 |
| }, |
| { |
| "epoch": 2.523076923076923, |
| "grad_norm": 0.1708984375, |
| "learning_rate": 2.9539358257075495e-06, |
| "loss": 0.5532, |
| "num_input_tokens_seen": 9509056, |
| "step": 615 |
| }, |
| { |
| "epoch": 2.5435897435897434, |
| "grad_norm": 0.1611328125, |
| "learning_rate": 2.9531877061374066e-06, |
| "loss": 0.4748, |
| "num_input_tokens_seen": 9590720, |
| "step": 620 |
| }, |
| { |
| "epoch": 2.564102564102564, |
| "grad_norm": 0.15234375, |
| "learning_rate": 2.9524336566474915e-06, |
| "loss": 0.5022, |
| "num_input_tokens_seen": 9667648, |
| "step": 625 |
| }, |
| { |
| "epoch": 2.5846153846153848, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 2.9516736803148014e-06, |
| "loss": 0.5005, |
| "num_input_tokens_seen": 9738016, |
| "step": 630 |
| }, |
| { |
| "epoch": 2.605128205128205, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 2.9509077802405174e-06, |
| "loss": 0.5297, |
| "num_input_tokens_seen": 9816224, |
| "step": 635 |
| }, |
| { |
| "epoch": 2.6256410256410256, |
| "grad_norm": 0.13671875, |
| "learning_rate": 2.9501359595499933e-06, |
| "loss": 0.5399, |
| "num_input_tokens_seen": 9891104, |
| "step": 640 |
| }, |
| { |
| "epoch": 2.646153846153846, |
| "grad_norm": 0.177734375, |
| "learning_rate": 2.9493582213927425e-06, |
| "loss": 0.4901, |
| "num_input_tokens_seen": 9969792, |
| "step": 645 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.142578125, |
| "learning_rate": 2.9485745689424267e-06, |
| "loss": 0.4591, |
| "num_input_tokens_seen": 10044608, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.6871794871794874, |
| "grad_norm": 0.2451171875, |
| "learning_rate": 2.9477850053968405e-06, |
| "loss": 0.5729, |
| "num_input_tokens_seen": 10132640, |
| "step": 655 |
| }, |
| { |
| "epoch": 2.707692307692308, |
| "grad_norm": 0.150390625, |
| "learning_rate": 2.9469895339778995e-06, |
| "loss": 0.5405, |
| "num_input_tokens_seen": 10207968, |
| "step": 660 |
| }, |
| { |
| "epoch": 2.7282051282051283, |
| "grad_norm": 0.30859375, |
| "learning_rate": 2.946188157931627e-06, |
| "loss": 0.4786, |
| "num_input_tokens_seen": 10277408, |
| "step": 665 |
| }, |
| { |
| "epoch": 2.7487179487179487, |
| "grad_norm": 0.314453125, |
| "learning_rate": 2.9453808805281423e-06, |
| "loss": 0.5035, |
| "num_input_tokens_seen": 10349184, |
| "step": 670 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 0.2490234375, |
| "learning_rate": 2.944567705061644e-06, |
| "loss": 0.4719, |
| "num_input_tokens_seen": 10434112, |
| "step": 675 |
| }, |
| { |
| "epoch": 2.7897435897435896, |
| "grad_norm": 0.65234375, |
| "learning_rate": 2.9437486348504e-06, |
| "loss": 0.5118, |
| "num_input_tokens_seen": 10506208, |
| "step": 680 |
| }, |
| { |
| "epoch": 2.81025641025641, |
| "grad_norm": 0.68359375, |
| "learning_rate": 2.9429236732367318e-06, |
| "loss": 0.5014, |
| "num_input_tokens_seen": 10577696, |
| "step": 685 |
| }, |
| { |
| "epoch": 2.830769230769231, |
| "grad_norm": 0.71484375, |
| "learning_rate": 2.942092823587001e-06, |
| "loss": 0.4827, |
| "num_input_tokens_seen": 10657984, |
| "step": 690 |
| }, |
| { |
| "epoch": 2.8512820512820514, |
| "grad_norm": 0.71484375, |
| "learning_rate": 2.941256089291597e-06, |
| "loss": 0.5177, |
| "num_input_tokens_seen": 10734688, |
| "step": 695 |
| }, |
| { |
| "epoch": 2.871794871794872, |
| "grad_norm": 0.6328125, |
| "learning_rate": 2.940413473764923e-06, |
| "loss": 0.4517, |
| "num_input_tokens_seen": 10812640, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.8923076923076922, |
| "grad_norm": 0.70703125, |
| "learning_rate": 2.9395649804453786e-06, |
| "loss": 0.4574, |
| "num_input_tokens_seen": 10884800, |
| "step": 705 |
| }, |
| { |
| "epoch": 2.9128205128205127, |
| "grad_norm": 0.27734375, |
| "learning_rate": 2.9387106127953515e-06, |
| "loss": 0.5092, |
| "num_input_tokens_seen": 10962016, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.9333333333333336, |
| "grad_norm": 0.34375, |
| "learning_rate": 2.937850374301198e-06, |
| "loss": 0.4888, |
| "num_input_tokens_seen": 11033280, |
| "step": 715 |
| }, |
| { |
| "epoch": 2.953846153846154, |
| "grad_norm": 0.375, |
| "learning_rate": 2.9369842684732336e-06, |
| "loss": 0.5447, |
| "num_input_tokens_seen": 11113696, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.9743589743589745, |
| "grad_norm": 0.396484375, |
| "learning_rate": 2.936112298845713e-06, |
| "loss": 0.5438, |
| "num_input_tokens_seen": 11195104, |
| "step": 725 |
| }, |
| { |
| "epoch": 2.994871794871795, |
| "grad_norm": 0.2470703125, |
| "learning_rate": 2.935234468976822e-06, |
| "loss": 0.46, |
| "num_input_tokens_seen": 11270304, |
| "step": 730 |
| }, |
| { |
| "epoch": 3.0153846153846153, |
| "grad_norm": 0.392578125, |
| "learning_rate": 2.934350782448658e-06, |
| "loss": 0.569, |
| "num_input_tokens_seen": 11350784, |
| "step": 735 |
| }, |
| { |
| "epoch": 3.0358974358974358, |
| "grad_norm": 0.318359375, |
| "learning_rate": 2.9334612428672175e-06, |
| "loss": 0.5246, |
| "num_input_tokens_seen": 11429568, |
| "step": 740 |
| }, |
| { |
| "epoch": 3.056410256410256, |
| "grad_norm": 0.35546875, |
| "learning_rate": 2.9325658538623822e-06, |
| "loss": 0.4587, |
| "num_input_tokens_seen": 11502784, |
| "step": 745 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 0.3671875, |
| "learning_rate": 2.931664619087902e-06, |
| "loss": 0.5095, |
| "num_input_tokens_seen": 11575680, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.0974358974358975, |
| "grad_norm": 0.35546875, |
| "learning_rate": 2.9307575422213813e-06, |
| "loss": 0.4916, |
| "num_input_tokens_seen": 11649856, |
| "step": 755 |
| }, |
| { |
| "epoch": 3.117948717948718, |
| "grad_norm": 0.404296875, |
| "learning_rate": 2.929844626964265e-06, |
| "loss": 0.5647, |
| "num_input_tokens_seen": 11727616, |
| "step": 760 |
| }, |
| { |
| "epoch": 3.1384615384615384, |
| "grad_norm": 0.421875, |
| "learning_rate": 2.9289258770418208e-06, |
| "loss": 0.4448, |
| "num_input_tokens_seen": 11806208, |
| "step": 765 |
| }, |
| { |
| "epoch": 3.158974358974359, |
| "grad_norm": 0.39453125, |
| "learning_rate": 2.9280012962031263e-06, |
| "loss": 0.5086, |
| "num_input_tokens_seen": 11884096, |
| "step": 770 |
| }, |
| { |
| "epoch": 3.1794871794871793, |
| "grad_norm": 0.29296875, |
| "learning_rate": 2.9270708882210525e-06, |
| "loss": 0.4796, |
| "num_input_tokens_seen": 11956416, |
| "step": 775 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.33203125, |
| "learning_rate": 2.92613465689225e-06, |
| "loss": 0.4797, |
| "num_input_tokens_seen": 12032384, |
| "step": 780 |
| }, |
| { |
| "epoch": 3.2205128205128206, |
| "grad_norm": 0.287109375, |
| "learning_rate": 2.92519260603713e-06, |
| "loss": 0.4523, |
| "num_input_tokens_seen": 12107328, |
| "step": 785 |
| }, |
| { |
| "epoch": 3.241025641025641, |
| "grad_norm": 0.326171875, |
| "learning_rate": 2.9242447394998545e-06, |
| "loss": 0.4795, |
| "num_input_tokens_seen": 12178848, |
| "step": 790 |
| }, |
| { |
| "epoch": 3.2615384615384615, |
| "grad_norm": 0.2734375, |
| "learning_rate": 2.923291061148314e-06, |
| "loss": 0.5164, |
| "num_input_tokens_seen": 12252160, |
| "step": 795 |
| }, |
| { |
| "epoch": 3.282051282051282, |
| "grad_norm": 0.271484375, |
| "learning_rate": 2.9223315748741146e-06, |
| "loss": 0.4949, |
| "num_input_tokens_seen": 12325120, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.3025641025641024, |
| "grad_norm": 0.244140625, |
| "learning_rate": 2.9213662845925662e-06, |
| "loss": 0.4848, |
| "num_input_tokens_seen": 12398144, |
| "step": 805 |
| }, |
| { |
| "epoch": 3.3230769230769233, |
| "grad_norm": 0.2265625, |
| "learning_rate": 2.9203951942426586e-06, |
| "loss": 0.5114, |
| "num_input_tokens_seen": 12475008, |
| "step": 810 |
| }, |
| { |
| "epoch": 3.3435897435897437, |
| "grad_norm": 0.2109375, |
| "learning_rate": 2.9194183077870516e-06, |
| "loss": 0.6022, |
| "num_input_tokens_seen": 12562336, |
| "step": 815 |
| }, |
| { |
| "epoch": 3.364102564102564, |
| "grad_norm": 0.1923828125, |
| "learning_rate": 2.9184356292120562e-06, |
| "loss": 0.4922, |
| "num_input_tokens_seen": 12646560, |
| "step": 820 |
| }, |
| { |
| "epoch": 3.3846153846153846, |
| "grad_norm": 0.1962890625, |
| "learning_rate": 2.9174471625276198e-06, |
| "loss": 0.5707, |
| "num_input_tokens_seen": 12718848, |
| "step": 825 |
| }, |
| { |
| "epoch": 3.405128205128205, |
| "grad_norm": 0.1650390625, |
| "learning_rate": 2.916452911767307e-06, |
| "loss": 0.4784, |
| "num_input_tokens_seen": 12798240, |
| "step": 830 |
| }, |
| { |
| "epoch": 3.4256410256410255, |
| "grad_norm": 0.1552734375, |
| "learning_rate": 2.915452880988287e-06, |
| "loss": 0.4423, |
| "num_input_tokens_seen": 12872608, |
| "step": 835 |
| }, |
| { |
| "epoch": 3.4461538461538463, |
| "grad_norm": 0.1396484375, |
| "learning_rate": 2.914447074271314e-06, |
| "loss": 0.4809, |
| "num_input_tokens_seen": 12952896, |
| "step": 840 |
| }, |
| { |
| "epoch": 3.466666666666667, |
| "grad_norm": 0.1650390625, |
| "learning_rate": 2.913435495720712e-06, |
| "loss": 0.5316, |
| "num_input_tokens_seen": 13036768, |
| "step": 845 |
| }, |
| { |
| "epoch": 3.4871794871794872, |
| "grad_norm": 0.140625, |
| "learning_rate": 2.9124181494643574e-06, |
| "loss": 0.4592, |
| "num_input_tokens_seen": 13114784, |
| "step": 850 |
| }, |
| { |
| "epoch": 3.5076923076923077, |
| "grad_norm": 0.138671875, |
| "learning_rate": 2.911395039653663e-06, |
| "loss": 0.4878, |
| "num_input_tokens_seen": 13188448, |
| "step": 855 |
| }, |
| { |
| "epoch": 3.528205128205128, |
| "grad_norm": 0.1298828125, |
| "learning_rate": 2.9103661704635604e-06, |
| "loss": 0.5066, |
| "num_input_tokens_seen": 13262592, |
| "step": 860 |
| }, |
| { |
| "epoch": 3.5487179487179485, |
| "grad_norm": 0.11962890625, |
| "learning_rate": 2.909331546092483e-06, |
| "loss": 0.4649, |
| "num_input_tokens_seen": 13339936, |
| "step": 865 |
| }, |
| { |
| "epoch": 3.569230769230769, |
| "grad_norm": 0.14453125, |
| "learning_rate": 2.908291170762349e-06, |
| "loss": 0.5233, |
| "num_input_tokens_seen": 13416256, |
| "step": 870 |
| }, |
| { |
| "epoch": 3.58974358974359, |
| "grad_norm": 0.306640625, |
| "learning_rate": 2.9072450487185434e-06, |
| "loss": 0.5018, |
| "num_input_tokens_seen": 13487392, |
| "step": 875 |
| }, |
| { |
| "epoch": 3.6102564102564103, |
| "grad_norm": 0.337890625, |
| "learning_rate": 2.9061931842299026e-06, |
| "loss": 0.4602, |
| "num_input_tokens_seen": 13569984, |
| "step": 880 |
| }, |
| { |
| "epoch": 3.6307692307692307, |
| "grad_norm": 0.1640625, |
| "learning_rate": 2.9051355815886952e-06, |
| "loss": 0.5309, |
| "num_input_tokens_seen": 13650944, |
| "step": 885 |
| }, |
| { |
| "epoch": 3.651282051282051, |
| "grad_norm": 0.30859375, |
| "learning_rate": 2.904072245110605e-06, |
| "loss": 0.5186, |
| "num_input_tokens_seen": 13720736, |
| "step": 890 |
| }, |
| { |
| "epoch": 3.6717948717948716, |
| "grad_norm": 0.333984375, |
| "learning_rate": 2.9030031791347136e-06, |
| "loss": 0.4839, |
| "num_input_tokens_seen": 13791616, |
| "step": 895 |
| }, |
| { |
| "epoch": 3.6923076923076925, |
| "grad_norm": 0.25, |
| "learning_rate": 2.901928388023483e-06, |
| "loss": 0.5199, |
| "num_input_tokens_seen": 13867488, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.712820512820513, |
| "grad_norm": 0.69921875, |
| "learning_rate": 2.900847876162736e-06, |
| "loss": 0.5414, |
| "num_input_tokens_seen": 13954848, |
| "step": 905 |
| }, |
| { |
| "epoch": 3.7333333333333334, |
| "grad_norm": 0.80859375, |
| "learning_rate": 2.899761647961641e-06, |
| "loss": 0.5451, |
| "num_input_tokens_seen": 14037792, |
| "step": 910 |
| }, |
| { |
| "epoch": 3.753846153846154, |
| "grad_norm": 1.0, |
| "learning_rate": 2.898669707852692e-06, |
| "loss": 0.4448, |
| "num_input_tokens_seen": 14107520, |
| "step": 915 |
| }, |
| { |
| "epoch": 3.7743589743589743, |
| "grad_norm": 0.3125, |
| "learning_rate": 2.897572060291692e-06, |
| "loss": 0.5213, |
| "num_input_tokens_seen": 14193888, |
| "step": 920 |
| }, |
| { |
| "epoch": 3.7948717948717947, |
| "grad_norm": 0.5, |
| "learning_rate": 2.896468709757733e-06, |
| "loss": 0.4968, |
| "num_input_tokens_seen": 14270976, |
| "step": 925 |
| }, |
| { |
| "epoch": 3.815384615384615, |
| "grad_norm": 0.58203125, |
| "learning_rate": 2.8953596607531788e-06, |
| "loss": 0.5769, |
| "num_input_tokens_seen": 14351232, |
| "step": 930 |
| }, |
| { |
| "epoch": 3.835897435897436, |
| "grad_norm": 0.26171875, |
| "learning_rate": 2.894244917803647e-06, |
| "loss": 0.4925, |
| "num_input_tokens_seen": 14426912, |
| "step": 935 |
| }, |
| { |
| "epoch": 3.8564102564102565, |
| "grad_norm": 0.333984375, |
| "learning_rate": 2.8931244854579904e-06, |
| "loss": 0.481, |
| "num_input_tokens_seen": 14515776, |
| "step": 940 |
| }, |
| { |
| "epoch": 3.876923076923077, |
| "grad_norm": 0.322265625, |
| "learning_rate": 2.891998368288277e-06, |
| "loss": 0.4699, |
| "num_input_tokens_seen": 14587104, |
| "step": 945 |
| }, |
| { |
| "epoch": 3.8974358974358974, |
| "grad_norm": 0.341796875, |
| "learning_rate": 2.890866570889773e-06, |
| "loss": 0.5206, |
| "num_input_tokens_seen": 14663680, |
| "step": 950 |
| }, |
| { |
| "epoch": 3.917948717948718, |
| "grad_norm": 0.35546875, |
| "learning_rate": 2.8897290978809245e-06, |
| "loss": 0.5117, |
| "num_input_tokens_seen": 14747360, |
| "step": 955 |
| }, |
| { |
| "epoch": 3.9384615384615387, |
| "grad_norm": 0.3671875, |
| "learning_rate": 2.888585953903336e-06, |
| "loss": 0.4891, |
| "num_input_tokens_seen": 14826464, |
| "step": 960 |
| }, |
| { |
| "epoch": 3.958974358974359, |
| "grad_norm": 0.376953125, |
| "learning_rate": 2.8874371436217534e-06, |
| "loss": 0.4943, |
| "num_input_tokens_seen": 14916416, |
| "step": 965 |
| }, |
| { |
| "epoch": 3.9794871794871796, |
| "grad_norm": 0.32421875, |
| "learning_rate": 2.8862826717240464e-06, |
| "loss": 0.5222, |
| "num_input_tokens_seen": 14995072, |
| "step": 970 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.337890625, |
| "learning_rate": 2.8851225429211855e-06, |
| "loss": 0.5197, |
| "num_input_tokens_seen": 15070304, |
| "step": 975 |
| }, |
| { |
| "epoch": 4.02051282051282, |
| "grad_norm": 0.380859375, |
| "learning_rate": 2.883956761947226e-06, |
| "loss": 0.501, |
| "num_input_tokens_seen": 15152480, |
| "step": 980 |
| }, |
| { |
| "epoch": 4.041025641025641, |
| "grad_norm": 0.478515625, |
| "learning_rate": 2.8827853335592876e-06, |
| "loss": 0.5142, |
| "num_input_tokens_seen": 15229184, |
| "step": 985 |
| }, |
| { |
| "epoch": 4.061538461538461, |
| "grad_norm": 0.376953125, |
| "learning_rate": 2.8816082625375353e-06, |
| "loss": 0.5239, |
| "num_input_tokens_seen": 15311072, |
| "step": 990 |
| }, |
| { |
| "epoch": 4.082051282051282, |
| "grad_norm": 0.380859375, |
| "learning_rate": 2.8804255536851584e-06, |
| "loss": 0.4823, |
| "num_input_tokens_seen": 15383232, |
| "step": 995 |
| }, |
| { |
| "epoch": 4.102564102564102, |
| "grad_norm": 0.34375, |
| "learning_rate": 2.8792372118283528e-06, |
| "loss": 0.5416, |
| "num_input_tokens_seen": 15464064, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.123076923076923, |
| "grad_norm": 0.416015625, |
| "learning_rate": 2.878043241816301e-06, |
| "loss": 0.4889, |
| "num_input_tokens_seen": 15536480, |
| "step": 1005 |
| }, |
| { |
| "epoch": 4.143589743589744, |
| "grad_norm": 0.3828125, |
| "learning_rate": 2.876843648521152e-06, |
| "loss": 0.5338, |
| "num_input_tokens_seen": 15618816, |
| "step": 1010 |
| }, |
| { |
| "epoch": 4.164102564102564, |
| "grad_norm": 0.2578125, |
| "learning_rate": 2.8756384368380003e-06, |
| "loss": 0.5101, |
| "num_input_tokens_seen": 15694304, |
| "step": 1015 |
| }, |
| { |
| "epoch": 4.184615384615385, |
| "grad_norm": 0.25390625, |
| "learning_rate": 2.874427611684867e-06, |
| "loss": 0.4792, |
| "num_input_tokens_seen": 15770784, |
| "step": 1020 |
| }, |
| { |
| "epoch": 4.205128205128205, |
| "grad_norm": 0.27734375, |
| "learning_rate": 2.8732111780026813e-06, |
| "loss": 0.4959, |
| "num_input_tokens_seen": 15837312, |
| "step": 1025 |
| }, |
| { |
| "epoch": 4.225641025641026, |
| "grad_norm": 0.22265625, |
| "learning_rate": 2.871989140755257e-06, |
| "loss": 0.5227, |
| "num_input_tokens_seen": 15908096, |
| "step": 1030 |
| }, |
| { |
| "epoch": 4.246153846153846, |
| "grad_norm": 0.2392578125, |
| "learning_rate": 2.870761504929275e-06, |
| "loss": 0.473, |
| "num_input_tokens_seen": 15982720, |
| "step": 1035 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.1943359375, |
| "learning_rate": 2.869528275534261e-06, |
| "loss": 0.4911, |
| "num_input_tokens_seen": 16056256, |
| "step": 1040 |
| }, |
| { |
| "epoch": 4.287179487179487, |
| "grad_norm": 0.1787109375, |
| "learning_rate": 2.8682894576025677e-06, |
| "loss": 0.4678, |
| "num_input_tokens_seen": 16128256, |
| "step": 1045 |
| }, |
| { |
| "epoch": 4.3076923076923075, |
| "grad_norm": 0.1650390625, |
| "learning_rate": 2.8670450561893498e-06, |
| "loss": 0.4534, |
| "num_input_tokens_seen": 16203808, |
| "step": 1050 |
| }, |
| { |
| "epoch": 4.328205128205128, |
| "grad_norm": 0.1796875, |
| "learning_rate": 2.865795076372549e-06, |
| "loss": 0.5788, |
| "num_input_tokens_seen": 16290464, |
| "step": 1055 |
| }, |
| { |
| "epoch": 4.348717948717948, |
| "grad_norm": 0.1845703125, |
| "learning_rate": 2.8645395232528683e-06, |
| "loss": 0.4744, |
| "num_input_tokens_seen": 16362688, |
| "step": 1060 |
| }, |
| { |
| "epoch": 4.36923076923077, |
| "grad_norm": 0.146484375, |
| "learning_rate": 2.863278401953754e-06, |
| "loss": 0.4801, |
| "num_input_tokens_seen": 16434976, |
| "step": 1065 |
| }, |
| { |
| "epoch": 4.38974358974359, |
| "grad_norm": 0.134765625, |
| "learning_rate": 2.862011717621375e-06, |
| "loss": 0.5035, |
| "num_input_tokens_seen": 16514880, |
| "step": 1070 |
| }, |
| { |
| "epoch": 4.410256410256411, |
| "grad_norm": 0.15625, |
| "learning_rate": 2.860739475424599e-06, |
| "loss": 0.5456, |
| "num_input_tokens_seen": 16592544, |
| "step": 1075 |
| }, |
| { |
| "epoch": 4.430769230769231, |
| "grad_norm": 0.125, |
| "learning_rate": 2.859461680554975e-06, |
| "loss": 0.4773, |
| "num_input_tokens_seen": 16675360, |
| "step": 1080 |
| }, |
| { |
| "epoch": 4.4512820512820515, |
| "grad_norm": 0.1103515625, |
| "learning_rate": 2.858178338226709e-06, |
| "loss": 0.4793, |
| "num_input_tokens_seen": 16753728, |
| "step": 1085 |
| }, |
| { |
| "epoch": 4.471794871794872, |
| "grad_norm": 0.11572265625, |
| "learning_rate": 2.8568894536766462e-06, |
| "loss": 0.4698, |
| "num_input_tokens_seen": 16829696, |
| "step": 1090 |
| }, |
| { |
| "epoch": 4.492307692307692, |
| "grad_norm": 0.19140625, |
| "learning_rate": 2.8555950321642444e-06, |
| "loss": 0.4648, |
| "num_input_tokens_seen": 16908128, |
| "step": 1095 |
| }, |
| { |
| "epoch": 4.512820512820513, |
| "grad_norm": 0.2333984375, |
| "learning_rate": 2.8542950789715587e-06, |
| "loss": 0.4473, |
| "num_input_tokens_seen": 16979136, |
| "step": 1100 |
| }, |
| { |
| "epoch": 4.533333333333333, |
| "grad_norm": 0.216796875, |
| "learning_rate": 2.8529895994032153e-06, |
| "loss": 0.5128, |
| "num_input_tokens_seen": 17063296, |
| "step": 1105 |
| }, |
| { |
| "epoch": 4.553846153846154, |
| "grad_norm": 0.15234375, |
| "learning_rate": 2.851678598786392e-06, |
| "loss": 0.4834, |
| "num_input_tokens_seen": 17145984, |
| "step": 1110 |
| }, |
| { |
| "epoch": 4.574358974358974, |
| "grad_norm": 0.296875, |
| "learning_rate": 2.8503620824707946e-06, |
| "loss": 0.4581, |
| "num_input_tokens_seen": 17221152, |
| "step": 1115 |
| }, |
| { |
| "epoch": 4.5948717948717945, |
| "grad_norm": 0.267578125, |
| "learning_rate": 2.8490400558286395e-06, |
| "loss": 0.5189, |
| "num_input_tokens_seen": 17298688, |
| "step": 1120 |
| }, |
| { |
| "epoch": 4.615384615384615, |
| "grad_norm": 0.302734375, |
| "learning_rate": 2.847712524254626e-06, |
| "loss": 0.4739, |
| "num_input_tokens_seen": 17374240, |
| "step": 1125 |
| }, |
| { |
| "epoch": 4.635897435897435, |
| "grad_norm": 0.6640625, |
| "learning_rate": 2.846379493165918e-06, |
| "loss": 0.5376, |
| "num_input_tokens_seen": 17451360, |
| "step": 1130 |
| }, |
| { |
| "epoch": 4.656410256410257, |
| "grad_norm": 0.82421875, |
| "learning_rate": 2.8450409680021204e-06, |
| "loss": 0.5152, |
| "num_input_tokens_seen": 17535776, |
| "step": 1135 |
| }, |
| { |
| "epoch": 4.676923076923077, |
| "grad_norm": 0.90234375, |
| "learning_rate": 2.8436969542252576e-06, |
| "loss": 0.4957, |
| "num_input_tokens_seen": 17616256, |
| "step": 1140 |
| }, |
| { |
| "epoch": 4.697435897435898, |
| "grad_norm": 0.31640625, |
| "learning_rate": 2.842347457319752e-06, |
| "loss": 0.4963, |
| "num_input_tokens_seen": 17691616, |
| "step": 1145 |
| }, |
| { |
| "epoch": 4.717948717948718, |
| "grad_norm": 0.5078125, |
| "learning_rate": 2.8409924827923985e-06, |
| "loss": 0.4868, |
| "num_input_tokens_seen": 17767264, |
| "step": 1150 |
| }, |
| { |
| "epoch": 4.7384615384615385, |
| "grad_norm": 0.36328125, |
| "learning_rate": 2.839632036172346e-06, |
| "loss": 0.5595, |
| "num_input_tokens_seen": 17847648, |
| "step": 1155 |
| }, |
| { |
| "epoch": 4.758974358974359, |
| "grad_norm": 0.296875, |
| "learning_rate": 2.8382661230110716e-06, |
| "loss": 0.6248, |
| "num_input_tokens_seen": 17932992, |
| "step": 1160 |
| }, |
| { |
| "epoch": 4.779487179487179, |
| "grad_norm": 0.326171875, |
| "learning_rate": 2.8368947488823613e-06, |
| "loss": 0.4935, |
| "num_input_tokens_seen": 18008544, |
| "step": 1165 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 0.3203125, |
| "learning_rate": 2.8355179193822834e-06, |
| "loss": 0.472, |
| "num_input_tokens_seen": 18091904, |
| "step": 1170 |
| }, |
| { |
| "epoch": 4.82051282051282, |
| "grad_norm": 0.396484375, |
| "learning_rate": 2.834135640129168e-06, |
| "loss": 0.4618, |
| "num_input_tokens_seen": 18169760, |
| "step": 1175 |
| }, |
| { |
| "epoch": 4.841025641025641, |
| "grad_norm": 0.2890625, |
| "learning_rate": 2.8327479167635834e-06, |
| "loss": 0.4375, |
| "num_input_tokens_seen": 18242016, |
| "step": 1180 |
| }, |
| { |
| "epoch": 4.861538461538462, |
| "grad_norm": 0.314453125, |
| "learning_rate": 2.831354754948315e-06, |
| "loss": 0.4954, |
| "num_input_tokens_seen": 18316192, |
| "step": 1185 |
| }, |
| { |
| "epoch": 4.8820512820512825, |
| "grad_norm": 0.330078125, |
| "learning_rate": 2.829956160368338e-06, |
| "loss": 0.4885, |
| "num_input_tokens_seen": 18402720, |
| "step": 1190 |
| }, |
| { |
| "epoch": 4.902564102564103, |
| "grad_norm": 0.482421875, |
| "learning_rate": 2.828552138730798e-06, |
| "loss": 0.4452, |
| "num_input_tokens_seen": 18472768, |
| "step": 1195 |
| }, |
| { |
| "epoch": 4.923076923076923, |
| "grad_norm": 0.33984375, |
| "learning_rate": 2.8271426957649868e-06, |
| "loss": 0.4602, |
| "num_input_tokens_seen": 18548128, |
| "step": 1200 |
| }, |
| { |
| "epoch": 4.943589743589744, |
| "grad_norm": 0.412109375, |
| "learning_rate": 2.8257278372223177e-06, |
| "loss": 0.4391, |
| "num_input_tokens_seen": 18622112, |
| "step": 1205 |
| }, |
| { |
| "epoch": 4.964102564102564, |
| "grad_norm": 0.484375, |
| "learning_rate": 2.824307568876304e-06, |
| "loss": 0.4614, |
| "num_input_tokens_seen": 18704288, |
| "step": 1210 |
| }, |
| { |
| "epoch": 4.984615384615385, |
| "grad_norm": 0.35546875, |
| "learning_rate": 2.8228818965225326e-06, |
| "loss": 0.5284, |
| "num_input_tokens_seen": 18780128, |
| "step": 1215 |
| }, |
| { |
| "epoch": 5.005128205128205, |
| "grad_norm": 0.326171875, |
| "learning_rate": 2.8214508259786443e-06, |
| "loss": 0.5213, |
| "num_input_tokens_seen": 18850496, |
| "step": 1220 |
| }, |
| { |
| "epoch": 5.0256410256410255, |
| "grad_norm": 0.333984375, |
| "learning_rate": 2.820014363084307e-06, |
| "loss": 0.5071, |
| "num_input_tokens_seen": 18926816, |
| "step": 1225 |
| }, |
| { |
| "epoch": 5.046153846153846, |
| "grad_norm": 0.341796875, |
| "learning_rate": 2.8185725137011922e-06, |
| "loss": 0.4964, |
| "num_input_tokens_seen": 19002624, |
| "step": 1230 |
| }, |
| { |
| "epoch": 5.066666666666666, |
| "grad_norm": 0.3359375, |
| "learning_rate": 2.8171252837129523e-06, |
| "loss": 0.5196, |
| "num_input_tokens_seen": 19083296, |
| "step": 1235 |
| }, |
| { |
| "epoch": 5.087179487179487, |
| "grad_norm": 0.28125, |
| "learning_rate": 2.815672679025196e-06, |
| "loss": 0.5272, |
| "num_input_tokens_seen": 19158048, |
| "step": 1240 |
| }, |
| { |
| "epoch": 5.107692307692307, |
| "grad_norm": 0.26171875, |
| "learning_rate": 2.814214705565464e-06, |
| "loss": 0.5034, |
| "num_input_tokens_seen": 19233888, |
| "step": 1245 |
| }, |
| { |
| "epoch": 5.128205128205128, |
| "grad_norm": 0.2890625, |
| "learning_rate": 2.8127513692832047e-06, |
| "loss": 0.5069, |
| "num_input_tokens_seen": 19317472, |
| "step": 1250 |
| }, |
| { |
| "epoch": 5.148717948717949, |
| "grad_norm": 0.2265625, |
| "learning_rate": 2.8112826761497507e-06, |
| "loss": 0.5116, |
| "num_input_tokens_seen": 19398496, |
| "step": 1255 |
| }, |
| { |
| "epoch": 5.1692307692307695, |
| "grad_norm": 0.21484375, |
| "learning_rate": 2.8098086321582937e-06, |
| "loss": 0.4286, |
| "num_input_tokens_seen": 19466400, |
| "step": 1260 |
| }, |
| { |
| "epoch": 5.18974358974359, |
| "grad_norm": 0.2119140625, |
| "learning_rate": 2.8083292433238602e-06, |
| "loss": 0.5058, |
| "num_input_tokens_seen": 19550336, |
| "step": 1265 |
| }, |
| { |
| "epoch": 5.21025641025641, |
| "grad_norm": 0.2177734375, |
| "learning_rate": 2.8068445156832864e-06, |
| "loss": 0.4587, |
| "num_input_tokens_seen": 19625792, |
| "step": 1270 |
| }, |
| { |
| "epoch": 5.230769230769231, |
| "grad_norm": 0.1943359375, |
| "learning_rate": 2.805354455295196e-06, |
| "loss": 0.4901, |
| "num_input_tokens_seen": 19711776, |
| "step": 1275 |
| }, |
| { |
| "epoch": 5.251282051282051, |
| "grad_norm": 0.173828125, |
| "learning_rate": 2.8038590682399718e-06, |
| "loss": 0.5474, |
| "num_input_tokens_seen": 19794208, |
| "step": 1280 |
| }, |
| { |
| "epoch": 5.271794871794872, |
| "grad_norm": 0.1611328125, |
| "learning_rate": 2.8023583606197336e-06, |
| "loss": 0.4452, |
| "num_input_tokens_seen": 19872128, |
| "step": 1285 |
| }, |
| { |
| "epoch": 5.292307692307692, |
| "grad_norm": 0.1357421875, |
| "learning_rate": 2.800852338558312e-06, |
| "loss": 0.5081, |
| "num_input_tokens_seen": 19953856, |
| "step": 1290 |
| }, |
| { |
| "epoch": 5.312820512820513, |
| "grad_norm": 0.1376953125, |
| "learning_rate": 2.7993410082012247e-06, |
| "loss": 0.4863, |
| "num_input_tokens_seen": 20026848, |
| "step": 1295 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "grad_norm": 0.138671875, |
| "learning_rate": 2.79782437571565e-06, |
| "loss": 0.4979, |
| "num_input_tokens_seen": 20100928, |
| "step": 1300 |
| }, |
| { |
| "epoch": 5.3538461538461535, |
| "grad_norm": 0.1318359375, |
| "learning_rate": 2.7963024472904013e-06, |
| "loss": 0.4676, |
| "num_input_tokens_seen": 20173504, |
| "step": 1305 |
| }, |
| { |
| "epoch": 5.374358974358975, |
| "grad_norm": 0.12451171875, |
| "learning_rate": 2.7947752291359053e-06, |
| "loss": 0.4256, |
| "num_input_tokens_seen": 20244608, |
| "step": 1310 |
| }, |
| { |
| "epoch": 5.394871794871795, |
| "grad_norm": 0.130859375, |
| "learning_rate": 2.7932427274841715e-06, |
| "loss": 0.4576, |
| "num_input_tokens_seen": 20324992, |
| "step": 1315 |
| }, |
| { |
| "epoch": 5.415384615384616, |
| "grad_norm": 0.1376953125, |
| "learning_rate": 2.7917049485887705e-06, |
| "loss": 0.5155, |
| "num_input_tokens_seen": 20402304, |
| "step": 1320 |
| }, |
| { |
| "epoch": 5.435897435897436, |
| "grad_norm": 0.20703125, |
| "learning_rate": 2.790161898724808e-06, |
| "loss": 0.4304, |
| "num_input_tokens_seen": 20480800, |
| "step": 1325 |
| }, |
| { |
| "epoch": 5.456410256410257, |
| "grad_norm": 0.138671875, |
| "learning_rate": 2.7886135841888973e-06, |
| "loss": 0.4759, |
| "num_input_tokens_seen": 20560096, |
| "step": 1330 |
| }, |
| { |
| "epoch": 5.476923076923077, |
| "grad_norm": 0.15234375, |
| "learning_rate": 2.787060011299135e-06, |
| "loss": 0.4974, |
| "num_input_tokens_seen": 20645216, |
| "step": 1335 |
| }, |
| { |
| "epoch": 5.4974358974358974, |
| "grad_norm": 0.341796875, |
| "learning_rate": 2.785501186395077e-06, |
| "loss": 0.5174, |
| "num_input_tokens_seen": 20738688, |
| "step": 1340 |
| }, |
| { |
| "epoch": 5.517948717948718, |
| "grad_norm": 0.271484375, |
| "learning_rate": 2.7839371158377077e-06, |
| "loss": 0.5272, |
| "num_input_tokens_seen": 20812928, |
| "step": 1345 |
| }, |
| { |
| "epoch": 5.538461538461538, |
| "grad_norm": 0.296875, |
| "learning_rate": 2.78236780600942e-06, |
| "loss": 0.5129, |
| "num_input_tokens_seen": 20890592, |
| "step": 1350 |
| }, |
| { |
| "epoch": 5.558974358974359, |
| "grad_norm": 0.57421875, |
| "learning_rate": 2.780793263313984e-06, |
| "loss": 0.484, |
| "num_input_tokens_seen": 20961984, |
| "step": 1355 |
| }, |
| { |
| "epoch": 5.579487179487179, |
| "grad_norm": 0.8671875, |
| "learning_rate": 2.7792134941765247e-06, |
| "loss": 0.4793, |
| "num_input_tokens_seen": 21030784, |
| "step": 1360 |
| }, |
| { |
| "epoch": 5.6, |
| "grad_norm": 0.267578125, |
| "learning_rate": 2.7776285050434937e-06, |
| "loss": 0.4521, |
| "num_input_tokens_seen": 21108960, |
| "step": 1365 |
| }, |
| { |
| "epoch": 5.62051282051282, |
| "grad_norm": 0.267578125, |
| "learning_rate": 2.7760383023826425e-06, |
| "loss": 0.4192, |
| "num_input_tokens_seen": 21181728, |
| "step": 1370 |
| }, |
| { |
| "epoch": 5.641025641025641, |
| "grad_norm": 0.64453125, |
| "learning_rate": 2.7744428926829993e-06, |
| "loss": 0.5131, |
| "num_input_tokens_seen": 21255328, |
| "step": 1375 |
| }, |
| { |
| "epoch": 5.661538461538462, |
| "grad_norm": 0.271484375, |
| "learning_rate": 2.7728422824548387e-06, |
| "loss": 0.483, |
| "num_input_tokens_seen": 21324064, |
| "step": 1380 |
| }, |
| { |
| "epoch": 5.682051282051282, |
| "grad_norm": 0.341796875, |
| "learning_rate": 2.7712364782296567e-06, |
| "loss": 0.4858, |
| "num_input_tokens_seen": 21399040, |
| "step": 1385 |
| }, |
| { |
| "epoch": 5.702564102564103, |
| "grad_norm": 0.318359375, |
| "learning_rate": 2.769625486560145e-06, |
| "loss": 0.4629, |
| "num_input_tokens_seen": 21472640, |
| "step": 1390 |
| }, |
| { |
| "epoch": 5.723076923076923, |
| "grad_norm": 0.39453125, |
| "learning_rate": 2.7680093140201625e-06, |
| "loss": 0.5023, |
| "num_input_tokens_seen": 21544448, |
| "step": 1395 |
| }, |
| { |
| "epoch": 5.743589743589744, |
| "grad_norm": 0.28515625, |
| "learning_rate": 2.766387967204709e-06, |
| "loss": 0.4903, |
| "num_input_tokens_seen": 21611136, |
| "step": 1400 |
| }, |
| { |
| "epoch": 5.764102564102564, |
| "grad_norm": 0.2578125, |
| "learning_rate": 2.7647614527299007e-06, |
| "loss": 0.5558, |
| "num_input_tokens_seen": 21703040, |
| "step": 1405 |
| }, |
| { |
| "epoch": 5.7846153846153845, |
| "grad_norm": 0.45703125, |
| "learning_rate": 2.763129777232938e-06, |
| "loss": 0.5612, |
| "num_input_tokens_seen": 21784096, |
| "step": 1410 |
| }, |
| { |
| "epoch": 5.805128205128205, |
| "grad_norm": 0.333984375, |
| "learning_rate": 2.7614929473720847e-06, |
| "loss": 0.4683, |
| "num_input_tokens_seen": 21855072, |
| "step": 1415 |
| }, |
| { |
| "epoch": 5.825641025641025, |
| "grad_norm": 0.38671875, |
| "learning_rate": 2.7598509698266346e-06, |
| "loss": 0.5171, |
| "num_input_tokens_seen": 21933312, |
| "step": 1420 |
| }, |
| { |
| "epoch": 5.846153846153846, |
| "grad_norm": 0.359375, |
| "learning_rate": 2.758203851296889e-06, |
| "loss": 0.5214, |
| "num_input_tokens_seen": 22019008, |
| "step": 1425 |
| }, |
| { |
| "epoch": 5.866666666666667, |
| "grad_norm": 0.326171875, |
| "learning_rate": 2.756551598504128e-06, |
| "loss": 0.4975, |
| "num_input_tokens_seen": 22092864, |
| "step": 1430 |
| }, |
| { |
| "epoch": 5.887179487179488, |
| "grad_norm": 0.392578125, |
| "learning_rate": 2.7548942181905816e-06, |
| "loss": 0.4853, |
| "num_input_tokens_seen": 22171584, |
| "step": 1435 |
| }, |
| { |
| "epoch": 5.907692307692308, |
| "grad_norm": 0.375, |
| "learning_rate": 2.753231717119405e-06, |
| "loss": 0.483, |
| "num_input_tokens_seen": 22241376, |
| "step": 1440 |
| }, |
| { |
| "epoch": 5.9282051282051285, |
| "grad_norm": 0.373046875, |
| "learning_rate": 2.751564102074646e-06, |
| "loss": 0.4965, |
| "num_input_tokens_seen": 22313664, |
| "step": 1445 |
| }, |
| { |
| "epoch": 5.948717948717949, |
| "grad_norm": 0.34765625, |
| "learning_rate": 2.749891379861225e-06, |
| "loss": 0.5342, |
| "num_input_tokens_seen": 22397408, |
| "step": 1450 |
| }, |
| { |
| "epoch": 5.969230769230769, |
| "grad_norm": 0.3359375, |
| "learning_rate": 2.748213557304899e-06, |
| "loss": 0.4233, |
| "num_input_tokens_seen": 22473664, |
| "step": 1455 |
| }, |
| { |
| "epoch": 5.98974358974359, |
| "grad_norm": 0.349609375, |
| "learning_rate": 2.74653064125224e-06, |
| "loss": 0.5244, |
| "num_input_tokens_seen": 22553760, |
| "step": 1460 |
| }, |
| { |
| "epoch": 6.01025641025641, |
| "grad_norm": 0.298828125, |
| "learning_rate": 2.7448426385706036e-06, |
| "loss": 0.5211, |
| "num_input_tokens_seen": 22624608, |
| "step": 1465 |
| }, |
| { |
| "epoch": 6.030769230769231, |
| "grad_norm": 0.271484375, |
| "learning_rate": 2.7431495561481027e-06, |
| "loss": 0.5618, |
| "num_input_tokens_seen": 22710048, |
| "step": 1470 |
| }, |
| { |
| "epoch": 6.051282051282051, |
| "grad_norm": 0.2734375, |
| "learning_rate": 2.741451400893578e-06, |
| "loss": 0.5172, |
| "num_input_tokens_seen": 22787392, |
| "step": 1475 |
| }, |
| { |
| "epoch": 6.0717948717948715, |
| "grad_norm": 0.22265625, |
| "learning_rate": 2.739748179736571e-06, |
| "loss": 0.5035, |
| "num_input_tokens_seen": 22865120, |
| "step": 1480 |
| }, |
| { |
| "epoch": 6.092307692307692, |
| "grad_norm": 0.205078125, |
| "learning_rate": 2.7380398996272955e-06, |
| "loss": 0.519, |
| "num_input_tokens_seen": 22952832, |
| "step": 1485 |
| }, |
| { |
| "epoch": 6.112820512820512, |
| "grad_norm": 0.2138671875, |
| "learning_rate": 2.736326567536609e-06, |
| "loss": 0.4438, |
| "num_input_tokens_seen": 23028544, |
| "step": 1490 |
| }, |
| { |
| "epoch": 6.133333333333334, |
| "grad_norm": 0.2021484375, |
| "learning_rate": 2.7346081904559827e-06, |
| "loss": 0.4669, |
| "num_input_tokens_seen": 23100096, |
| "step": 1495 |
| }, |
| { |
| "epoch": 6.153846153846154, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 2.732884775397477e-06, |
| "loss": 0.4702, |
| "num_input_tokens_seen": 23183392, |
| "step": 1500 |
| }, |
| { |
| "epoch": 6.174358974358975, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 2.731156329393709e-06, |
| "loss": 0.5031, |
| "num_input_tokens_seen": 23266208, |
| "step": 1505 |
| }, |
| { |
| "epoch": 6.194871794871795, |
| "grad_norm": 0.1484375, |
| "learning_rate": 2.729422859497825e-06, |
| "loss": 0.5005, |
| "num_input_tokens_seen": 23348064, |
| "step": 1510 |
| }, |
| { |
| "epoch": 6.2153846153846155, |
| "grad_norm": 0.1552734375, |
| "learning_rate": 2.7276843727834727e-06, |
| "loss": 0.4798, |
| "num_input_tokens_seen": 23420128, |
| "step": 1515 |
| }, |
| { |
| "epoch": 6.235897435897436, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 2.725940876344771e-06, |
| "loss": 0.5059, |
| "num_input_tokens_seen": 23497056, |
| "step": 1520 |
| }, |
| { |
| "epoch": 6.256410256410256, |
| "grad_norm": 0.1376953125, |
| "learning_rate": 2.7241923772962823e-06, |
| "loss": 0.4582, |
| "num_input_tokens_seen": 23564928, |
| "step": 1525 |
| }, |
| { |
| "epoch": 6.276923076923077, |
| "grad_norm": 0.1220703125, |
| "learning_rate": 2.722438882772982e-06, |
| "loss": 0.4295, |
| "num_input_tokens_seen": 23646624, |
| "step": 1530 |
| }, |
| { |
| "epoch": 6.297435897435897, |
| "grad_norm": 0.1484375, |
| "learning_rate": 2.720680399930231e-06, |
| "loss": 0.4682, |
| "num_input_tokens_seen": 23716960, |
| "step": 1535 |
| }, |
| { |
| "epoch": 6.317948717948718, |
| "grad_norm": 0.1611328125, |
| "learning_rate": 2.7189169359437443e-06, |
| "loss": 0.4944, |
| "num_input_tokens_seen": 23796032, |
| "step": 1540 |
| }, |
| { |
| "epoch": 6.338461538461538, |
| "grad_norm": 0.1318359375, |
| "learning_rate": 2.7171484980095653e-06, |
| "loss": 0.4405, |
| "num_input_tokens_seen": 23868768, |
| "step": 1545 |
| }, |
| { |
| "epoch": 6.358974358974359, |
| "grad_norm": 0.1953125, |
| "learning_rate": 2.715375093344032e-06, |
| "loss": 0.4742, |
| "num_input_tokens_seen": 23937824, |
| "step": 1550 |
| }, |
| { |
| "epoch": 6.37948717948718, |
| "grad_norm": 0.146484375, |
| "learning_rate": 2.713596729183751e-06, |
| "loss": 0.4654, |
| "num_input_tokens_seen": 24009472, |
| "step": 1555 |
| }, |
| { |
| "epoch": 6.4, |
| "grad_norm": 0.146484375, |
| "learning_rate": 2.7118134127855667e-06, |
| "loss": 0.4686, |
| "num_input_tokens_seen": 24096256, |
| "step": 1560 |
| }, |
| { |
| "epoch": 6.420512820512821, |
| "grad_norm": 0.3203125, |
| "learning_rate": 2.7100251514265317e-06, |
| "loss": 0.5152, |
| "num_input_tokens_seen": 24180640, |
| "step": 1565 |
| }, |
| { |
| "epoch": 6.441025641025641, |
| "grad_norm": 0.392578125, |
| "learning_rate": 2.7082319524038764e-06, |
| "loss": 0.4762, |
| "num_input_tokens_seen": 24251296, |
| "step": 1570 |
| }, |
| { |
| "epoch": 6.461538461538462, |
| "grad_norm": 0.74609375, |
| "learning_rate": 2.706433823034981e-06, |
| "loss": 0.5113, |
| "num_input_tokens_seen": 24329760, |
| "step": 1575 |
| }, |
| { |
| "epoch": 6.482051282051282, |
| "grad_norm": 0.55078125, |
| "learning_rate": 2.7046307706573445e-06, |
| "loss": 0.4942, |
| "num_input_tokens_seen": 24420896, |
| "step": 1580 |
| }, |
| { |
| "epoch": 6.5025641025641026, |
| "grad_norm": 0.703125, |
| "learning_rate": 2.702822802628554e-06, |
| "loss": 0.475, |
| "num_input_tokens_seen": 24495360, |
| "step": 1585 |
| }, |
| { |
| "epoch": 6.523076923076923, |
| "grad_norm": 0.2216796875, |
| "learning_rate": 2.701009926326256e-06, |
| "loss": 0.4801, |
| "num_input_tokens_seen": 24572192, |
| "step": 1590 |
| }, |
| { |
| "epoch": 6.543589743589743, |
| "grad_norm": 0.267578125, |
| "learning_rate": 2.6991921491481267e-06, |
| "loss": 0.4776, |
| "num_input_tokens_seen": 24647552, |
| "step": 1595 |
| }, |
| { |
| "epoch": 6.564102564102564, |
| "grad_norm": 0.578125, |
| "learning_rate": 2.6973694785118394e-06, |
| "loss": 0.4878, |
| "num_input_tokens_seen": 24719136, |
| "step": 1600 |
| }, |
| { |
| "epoch": 6.584615384615384, |
| "grad_norm": 0.37109375, |
| "learning_rate": 2.695541921855037e-06, |
| "loss": 0.5138, |
| "num_input_tokens_seen": 24800320, |
| "step": 1605 |
| }, |
| { |
| "epoch": 6.605128205128205, |
| "grad_norm": 0.310546875, |
| "learning_rate": 2.6937094866353006e-06, |
| "loss": 0.4782, |
| "num_input_tokens_seen": 24877088, |
| "step": 1610 |
| }, |
| { |
| "epoch": 6.625641025641025, |
| "grad_norm": 0.498046875, |
| "learning_rate": 2.6918721803301174e-06, |
| "loss": 0.5043, |
| "num_input_tokens_seen": 24954272, |
| "step": 1615 |
| }, |
| { |
| "epoch": 6.6461538461538465, |
| "grad_norm": 0.294921875, |
| "learning_rate": 2.690030010436853e-06, |
| "loss": 0.4237, |
| "num_input_tokens_seen": 25023744, |
| "step": 1620 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 0.64453125, |
| "learning_rate": 2.688182984472719e-06, |
| "loss": 0.5302, |
| "num_input_tokens_seen": 25105664, |
| "step": 1625 |
| }, |
| { |
| "epoch": 6.687179487179487, |
| "grad_norm": 0.3515625, |
| "learning_rate": 2.686331109974743e-06, |
| "loss": 0.4991, |
| "num_input_tokens_seen": 25183680, |
| "step": 1630 |
| }, |
| { |
| "epoch": 6.707692307692308, |
| "grad_norm": 0.443359375, |
| "learning_rate": 2.684474394499738e-06, |
| "loss": 0.5142, |
| "num_input_tokens_seen": 25265920, |
| "step": 1635 |
| }, |
| { |
| "epoch": 6.728205128205128, |
| "grad_norm": 0.4609375, |
| "learning_rate": 2.6826128456242708e-06, |
| "loss": 0.4651, |
| "num_input_tokens_seen": 25343648, |
| "step": 1640 |
| }, |
| { |
| "epoch": 6.748717948717949, |
| "grad_norm": 0.361328125, |
| "learning_rate": 2.680746470944631e-06, |
| "loss": 0.5633, |
| "num_input_tokens_seen": 25418176, |
| "step": 1645 |
| }, |
| { |
| "epoch": 6.769230769230769, |
| "grad_norm": 0.375, |
| "learning_rate": 2.6788752780768007e-06, |
| "loss": 0.5124, |
| "num_input_tokens_seen": 25504832, |
| "step": 1650 |
| }, |
| { |
| "epoch": 6.78974358974359, |
| "grad_norm": 0.62109375, |
| "learning_rate": 2.6769992746564256e-06, |
| "loss": 0.5046, |
| "num_input_tokens_seen": 25582112, |
| "step": 1655 |
| }, |
| { |
| "epoch": 6.81025641025641, |
| "grad_norm": 0.35546875, |
| "learning_rate": 2.6751184683387777e-06, |
| "loss": 0.484, |
| "num_input_tokens_seen": 25656992, |
| "step": 1660 |
| }, |
| { |
| "epoch": 6.8307692307692305, |
| "grad_norm": 0.3203125, |
| "learning_rate": 2.67323286679873e-06, |
| "loss": 0.4526, |
| "num_input_tokens_seen": 25729600, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.851282051282051, |
| "grad_norm": 0.365234375, |
| "learning_rate": 2.671342477730723e-06, |
| "loss": 0.4563, |
| "num_input_tokens_seen": 25801536, |
| "step": 1670 |
| }, |
| { |
| "epoch": 6.871794871794872, |
| "grad_norm": 0.380859375, |
| "learning_rate": 2.6694473088487324e-06, |
| "loss": 0.4951, |
| "num_input_tokens_seen": 25882912, |
| "step": 1675 |
| }, |
| { |
| "epoch": 6.892307692307693, |
| "grad_norm": 0.32421875, |
| "learning_rate": 2.6675473678862403e-06, |
| "loss": 0.5223, |
| "num_input_tokens_seen": 25957952, |
| "step": 1680 |
| }, |
| { |
| "epoch": 6.912820512820513, |
| "grad_norm": 0.353515625, |
| "learning_rate": 2.6656426625961993e-06, |
| "loss": 0.5471, |
| "num_input_tokens_seen": 26034432, |
| "step": 1685 |
| }, |
| { |
| "epoch": 6.933333333333334, |
| "grad_norm": 0.251953125, |
| "learning_rate": 2.6637332007510063e-06, |
| "loss": 0.4252, |
| "num_input_tokens_seen": 26106656, |
| "step": 1690 |
| }, |
| { |
| "epoch": 6.953846153846154, |
| "grad_norm": 0.31640625, |
| "learning_rate": 2.661818990142465e-06, |
| "loss": 0.5269, |
| "num_input_tokens_seen": 26186976, |
| "step": 1695 |
| }, |
| { |
| "epoch": 6.9743589743589745, |
| "grad_norm": 0.25, |
| "learning_rate": 2.65990003858176e-06, |
| "loss": 0.4487, |
| "num_input_tokens_seen": 26259264, |
| "step": 1700 |
| }, |
| { |
| "epoch": 6.994871794871795, |
| "grad_norm": 0.2353515625, |
| "learning_rate": 2.6579763538994197e-06, |
| "loss": 0.4705, |
| "num_input_tokens_seen": 26333248, |
| "step": 1705 |
| }, |
| { |
| "epoch": 7.015384615384615, |
| "grad_norm": 0.205078125, |
| "learning_rate": 2.656047943945287e-06, |
| "loss": 0.4443, |
| "num_input_tokens_seen": 26404832, |
| "step": 1710 |
| }, |
| { |
| "epoch": 7.035897435897436, |
| "grad_norm": 0.1865234375, |
| "learning_rate": 2.6541148165884885e-06, |
| "loss": 0.4615, |
| "num_input_tokens_seen": 26484608, |
| "step": 1715 |
| }, |
| { |
| "epoch": 7.056410256410256, |
| "grad_norm": 0.1943359375, |
| "learning_rate": 2.652176979717399e-06, |
| "loss": 0.5042, |
| "num_input_tokens_seen": 26556224, |
| "step": 1720 |
| }, |
| { |
| "epoch": 7.076923076923077, |
| "grad_norm": 0.16796875, |
| "learning_rate": 2.6502344412396116e-06, |
| "loss": 0.4601, |
| "num_input_tokens_seen": 26629632, |
| "step": 1725 |
| }, |
| { |
| "epoch": 7.097435897435897, |
| "grad_norm": 0.146484375, |
| "learning_rate": 2.6482872090819053e-06, |
| "loss": 0.534, |
| "num_input_tokens_seen": 26709568, |
| "step": 1730 |
| }, |
| { |
| "epoch": 7.1179487179487175, |
| "grad_norm": 0.201171875, |
| "learning_rate": 2.646335291190211e-06, |
| "loss": 0.4875, |
| "num_input_tokens_seen": 26785728, |
| "step": 1735 |
| }, |
| { |
| "epoch": 7.138461538461539, |
| "grad_norm": 0.150390625, |
| "learning_rate": 2.6443786955295827e-06, |
| "loss": 0.5223, |
| "num_input_tokens_seen": 26865024, |
| "step": 1740 |
| }, |
| { |
| "epoch": 7.158974358974359, |
| "grad_norm": 0.140625, |
| "learning_rate": 2.6424174300841606e-06, |
| "loss": 0.4365, |
| "num_input_tokens_seen": 26934720, |
| "step": 1745 |
| }, |
| { |
| "epoch": 7.17948717948718, |
| "grad_norm": 0.138671875, |
| "learning_rate": 2.6404515028571406e-06, |
| "loss": 0.4951, |
| "num_input_tokens_seen": 27008192, |
| "step": 1750 |
| }, |
| { |
| "epoch": 7.2, |
| "grad_norm": 0.11962890625, |
| "learning_rate": 2.638480921870743e-06, |
| "loss": 0.5132, |
| "num_input_tokens_seen": 27092000, |
| "step": 1755 |
| }, |
| { |
| "epoch": 7.220512820512821, |
| "grad_norm": 0.1298828125, |
| "learning_rate": 2.636505695166177e-06, |
| "loss": 0.4713, |
| "num_input_tokens_seen": 27172160, |
| "step": 1760 |
| }, |
| { |
| "epoch": 7.241025641025641, |
| "grad_norm": 0.16015625, |
| "learning_rate": 2.63452583080361e-06, |
| "loss": 0.479, |
| "num_input_tokens_seen": 27255712, |
| "step": 1765 |
| }, |
| { |
| "epoch": 7.2615384615384615, |
| "grad_norm": 0.1396484375, |
| "learning_rate": 2.6325413368621337e-06, |
| "loss": 0.4967, |
| "num_input_tokens_seen": 27343136, |
| "step": 1770 |
| }, |
| { |
| "epoch": 7.282051282051282, |
| "grad_norm": 0.2470703125, |
| "learning_rate": 2.630552221439732e-06, |
| "loss": 0.4843, |
| "num_input_tokens_seen": 27417312, |
| "step": 1775 |
| }, |
| { |
| "epoch": 7.302564102564102, |
| "grad_norm": 0.1396484375, |
| "learning_rate": 2.6285584926532465e-06, |
| "loss": 0.4738, |
| "num_input_tokens_seen": 27505824, |
| "step": 1780 |
| }, |
| { |
| "epoch": 7.323076923076923, |
| "grad_norm": 0.2890625, |
| "learning_rate": 2.626560158638344e-06, |
| "loss": 0.5716, |
| "num_input_tokens_seen": 27583776, |
| "step": 1785 |
| }, |
| { |
| "epoch": 7.343589743589743, |
| "grad_norm": 0.357421875, |
| "learning_rate": 2.6245572275494845e-06, |
| "loss": 0.515, |
| "num_input_tokens_seen": 27658912, |
| "step": 1790 |
| }, |
| { |
| "epoch": 7.364102564102564, |
| "grad_norm": 0.2314453125, |
| "learning_rate": 2.6225497075598865e-06, |
| "loss": 0.47, |
| "num_input_tokens_seen": 27733472, |
| "step": 1795 |
| }, |
| { |
| "epoch": 7.384615384615385, |
| "grad_norm": 0.51953125, |
| "learning_rate": 2.6205376068614943e-06, |
| "loss": 0.4749, |
| "num_input_tokens_seen": 27812160, |
| "step": 1800 |
| }, |
| { |
| "epoch": 7.4051282051282055, |
| "grad_norm": 0.55078125, |
| "learning_rate": 2.6185209336649438e-06, |
| "loss": 0.4727, |
| "num_input_tokens_seen": 27885024, |
| "step": 1805 |
| }, |
| { |
| "epoch": 7.425641025641026, |
| "grad_norm": 0.75, |
| "learning_rate": 2.61649969619953e-06, |
| "loss": 0.478, |
| "num_input_tokens_seen": 27956480, |
| "step": 1810 |
| }, |
| { |
| "epoch": 7.446153846153846, |
| "grad_norm": 0.28125, |
| "learning_rate": 2.614473902713173e-06, |
| "loss": 0.4778, |
| "num_input_tokens_seen": 28028032, |
| "step": 1815 |
| }, |
| { |
| "epoch": 7.466666666666667, |
| "grad_norm": 0.49609375, |
| "learning_rate": 2.612443561472385e-06, |
| "loss": 0.4443, |
| "num_input_tokens_seen": 28112992, |
| "step": 1820 |
| }, |
| { |
| "epoch": 7.487179487179487, |
| "grad_norm": 0.5, |
| "learning_rate": 2.610408680762234e-06, |
| "loss": 0.5186, |
| "num_input_tokens_seen": 28191520, |
| "step": 1825 |
| }, |
| { |
| "epoch": 7.507692307692308, |
| "grad_norm": 0.314453125, |
| "learning_rate": 2.6083692688863135e-06, |
| "loss": 0.5152, |
| "num_input_tokens_seen": 28277440, |
| "step": 1830 |
| }, |
| { |
| "epoch": 7.528205128205128, |
| "grad_norm": 0.29296875, |
| "learning_rate": 2.6063253341667064e-06, |
| "loss": 0.5173, |
| "num_input_tokens_seen": 28357440, |
| "step": 1835 |
| }, |
| { |
| "epoch": 7.5487179487179485, |
| "grad_norm": 0.326171875, |
| "learning_rate": 2.604276884943953e-06, |
| "loss": 0.4585, |
| "num_input_tokens_seen": 28426656, |
| "step": 1840 |
| }, |
| { |
| "epoch": 7.569230769230769, |
| "grad_norm": 0.279296875, |
| "learning_rate": 2.602223929577013e-06, |
| "loss": 0.4611, |
| "num_input_tokens_seen": 28499968, |
| "step": 1845 |
| }, |
| { |
| "epoch": 7.589743589743589, |
| "grad_norm": 0.310546875, |
| "learning_rate": 2.6001664764432363e-06, |
| "loss": 0.4929, |
| "num_input_tokens_seen": 28573664, |
| "step": 1850 |
| }, |
| { |
| "epoch": 7.61025641025641, |
| "grad_norm": 0.318359375, |
| "learning_rate": 2.5981045339383244e-06, |
| "loss": 0.5018, |
| "num_input_tokens_seen": 28658144, |
| "step": 1855 |
| }, |
| { |
| "epoch": 7.63076923076923, |
| "grad_norm": 0.328125, |
| "learning_rate": 2.596038110476301e-06, |
| "loss": 0.483, |
| "num_input_tokens_seen": 28730944, |
| "step": 1860 |
| }, |
| { |
| "epoch": 7.651282051282052, |
| "grad_norm": 0.52734375, |
| "learning_rate": 2.593967214489473e-06, |
| "loss": 0.5111, |
| "num_input_tokens_seen": 28816384, |
| "step": 1865 |
| }, |
| { |
| "epoch": 7.671794871794872, |
| "grad_norm": 0.37109375, |
| "learning_rate": 2.591891854428398e-06, |
| "loss": 0.4689, |
| "num_input_tokens_seen": 28891616, |
| "step": 1870 |
| }, |
| { |
| "epoch": 7.6923076923076925, |
| "grad_norm": 0.33203125, |
| "learning_rate": 2.5898120387618507e-06, |
| "loss": 0.4917, |
| "num_input_tokens_seen": 28970400, |
| "step": 1875 |
| }, |
| { |
| "epoch": 7.712820512820513, |
| "grad_norm": 0.33203125, |
| "learning_rate": 2.587727775976787e-06, |
| "loss": 0.4956, |
| "num_input_tokens_seen": 29051520, |
| "step": 1880 |
| }, |
| { |
| "epoch": 7.733333333333333, |
| "grad_norm": 0.3046875, |
| "learning_rate": 2.585639074578309e-06, |
| "loss": 0.438, |
| "num_input_tokens_seen": 29128544, |
| "step": 1885 |
| }, |
| { |
| "epoch": 7.753846153846154, |
| "grad_norm": 0.306640625, |
| "learning_rate": 2.5835459430896333e-06, |
| "loss": 0.4644, |
| "num_input_tokens_seen": 29210496, |
| "step": 1890 |
| }, |
| { |
| "epoch": 7.774358974358974, |
| "grad_norm": 0.365234375, |
| "learning_rate": 2.5814483900520522e-06, |
| "loss": 0.4901, |
| "num_input_tokens_seen": 29282400, |
| "step": 1895 |
| }, |
| { |
| "epoch": 7.794871794871795, |
| "grad_norm": 0.4140625, |
| "learning_rate": 2.5793464240249014e-06, |
| "loss": 0.4879, |
| "num_input_tokens_seen": 29352256, |
| "step": 1900 |
| }, |
| { |
| "epoch": 7.815384615384615, |
| "grad_norm": 0.330078125, |
| "learning_rate": 2.5772400535855242e-06, |
| "loss": 0.4552, |
| "num_input_tokens_seen": 29426336, |
| "step": 1905 |
| }, |
| { |
| "epoch": 7.835897435897436, |
| "grad_norm": 0.353515625, |
| "learning_rate": 2.575129287329237e-06, |
| "loss": 0.5417, |
| "num_input_tokens_seen": 29512224, |
| "step": 1910 |
| }, |
| { |
| "epoch": 7.856410256410256, |
| "grad_norm": 0.27734375, |
| "learning_rate": 2.5730141338692926e-06, |
| "loss": 0.4637, |
| "num_input_tokens_seen": 29590112, |
| "step": 1915 |
| }, |
| { |
| "epoch": 7.876923076923077, |
| "grad_norm": 0.31640625, |
| "learning_rate": 2.5708946018368487e-06, |
| "loss": 0.4486, |
| "num_input_tokens_seen": 29672608, |
| "step": 1920 |
| }, |
| { |
| "epoch": 7.897435897435898, |
| "grad_norm": 0.228515625, |
| "learning_rate": 2.568770699880928e-06, |
| "loss": 0.5094, |
| "num_input_tokens_seen": 29755520, |
| "step": 1925 |
| }, |
| { |
| "epoch": 7.917948717948718, |
| "grad_norm": 0.2197265625, |
| "learning_rate": 2.566642436668387e-06, |
| "loss": 0.5111, |
| "num_input_tokens_seen": 29833344, |
| "step": 1930 |
| }, |
| { |
| "epoch": 7.938461538461539, |
| "grad_norm": 0.1923828125, |
| "learning_rate": 2.5645098208838774e-06, |
| "loss": 0.4737, |
| "num_input_tokens_seen": 29904800, |
| "step": 1935 |
| }, |
| { |
| "epoch": 7.958974358974359, |
| "grad_norm": 0.2080078125, |
| "learning_rate": 2.562372861229813e-06, |
| "loss": 0.4384, |
| "num_input_tokens_seen": 29975488, |
| "step": 1940 |
| }, |
| { |
| "epoch": 7.97948717948718, |
| "grad_norm": 0.197265625, |
| "learning_rate": 2.5602315664263337e-06, |
| "loss": 0.4383, |
| "num_input_tokens_seen": 30046496, |
| "step": 1945 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.1611328125, |
| "learning_rate": 2.5580859452112685e-06, |
| "loss": 0.4782, |
| "num_input_tokens_seen": 30119840, |
| "step": 1950 |
| }, |
| { |
| "epoch": 8.02051282051282, |
| "grad_norm": 0.1484375, |
| "learning_rate": 2.555936006340101e-06, |
| "loss": 0.5371, |
| "num_input_tokens_seen": 30207040, |
| "step": 1955 |
| }, |
| { |
| "epoch": 8.04102564102564, |
| "grad_norm": 0.1376953125, |
| "learning_rate": 2.553781758585935e-06, |
| "loss": 0.4867, |
| "num_input_tokens_seen": 30283968, |
| "step": 1960 |
| }, |
| { |
| "epoch": 8.061538461538461, |
| "grad_norm": 0.1376953125, |
| "learning_rate": 2.551623210739455e-06, |
| "loss": 0.4309, |
| "num_input_tokens_seen": 30355552, |
| "step": 1965 |
| }, |
| { |
| "epoch": 8.082051282051282, |
| "grad_norm": 0.12109375, |
| "learning_rate": 2.549460371608895e-06, |
| "loss": 0.5087, |
| "num_input_tokens_seen": 30435776, |
| "step": 1970 |
| }, |
| { |
| "epoch": 8.102564102564102, |
| "grad_norm": 0.1328125, |
| "learning_rate": 2.5472932500199976e-06, |
| "loss": 0.4746, |
| "num_input_tokens_seen": 30507616, |
| "step": 1975 |
| }, |
| { |
| "epoch": 8.123076923076923, |
| "grad_norm": 0.1396484375, |
| "learning_rate": 2.5451218548159823e-06, |
| "loss": 0.4833, |
| "num_input_tokens_seen": 30583456, |
| "step": 1980 |
| }, |
| { |
| "epoch": 8.143589743589743, |
| "grad_norm": 0.12890625, |
| "learning_rate": 2.5429461948575077e-06, |
| "loss": 0.4849, |
| "num_input_tokens_seen": 30654176, |
| "step": 1985 |
| }, |
| { |
| "epoch": 8.164102564102564, |
| "grad_norm": 0.1416015625, |
| "learning_rate": 2.540766279022634e-06, |
| "loss": 0.4812, |
| "num_input_tokens_seen": 30721920, |
| "step": 1990 |
| }, |
| { |
| "epoch": 8.184615384615384, |
| "grad_norm": 0.216796875, |
| "learning_rate": 2.53858211620679e-06, |
| "loss": 0.4976, |
| "num_input_tokens_seen": 30791264, |
| "step": 1995 |
| }, |
| { |
| "epoch": 8.205128205128204, |
| "grad_norm": 0.20703125, |
| "learning_rate": 2.536393715322732e-06, |
| "loss": 0.4556, |
| "num_input_tokens_seen": 30862336, |
| "step": 2000 |
| }, |
| { |
| "epoch": 8.225641025641025, |
| "grad_norm": 0.150390625, |
| "learning_rate": 2.5342010853005127e-06, |
| "loss": 0.4496, |
| "num_input_tokens_seen": 30940064, |
| "step": 2005 |
| }, |
| { |
| "epoch": 8.246153846153845, |
| "grad_norm": 0.318359375, |
| "learning_rate": 2.532004235087441e-06, |
| "loss": 0.4722, |
| "num_input_tokens_seen": 31013248, |
| "step": 2010 |
| }, |
| { |
| "epoch": 8.266666666666667, |
| "grad_norm": 0.26171875, |
| "learning_rate": 2.529803173648049e-06, |
| "loss": 0.4875, |
| "num_input_tokens_seen": 31094496, |
| "step": 2015 |
| }, |
| { |
| "epoch": 8.287179487179488, |
| "grad_norm": 0.2578125, |
| "learning_rate": 2.52759790996405e-06, |
| "loss": 0.4598, |
| "num_input_tokens_seen": 31171680, |
| "step": 2020 |
| }, |
| { |
| "epoch": 8.307692307692308, |
| "grad_norm": 0.77734375, |
| "learning_rate": 2.525388453034307e-06, |
| "loss": 0.5069, |
| "num_input_tokens_seen": 31252064, |
| "step": 2025 |
| }, |
| { |
| "epoch": 8.328205128205129, |
| "grad_norm": 0.6875, |
| "learning_rate": 2.5231748118747945e-06, |
| "loss": 0.5155, |
| "num_input_tokens_seen": 31329696, |
| "step": 2030 |
| }, |
| { |
| "epoch": 8.34871794871795, |
| "grad_norm": 0.96484375, |
| "learning_rate": 2.5209569955185604e-06, |
| "loss": 0.5436, |
| "num_input_tokens_seen": 31407648, |
| "step": 2035 |
| }, |
| { |
| "epoch": 8.36923076923077, |
| "grad_norm": 0.30078125, |
| "learning_rate": 2.51873501301569e-06, |
| "loss": 0.4953, |
| "num_input_tokens_seen": 31475200, |
| "step": 2040 |
| }, |
| { |
| "epoch": 8.38974358974359, |
| "grad_norm": 0.6328125, |
| "learning_rate": 2.5165088734332695e-06, |
| "loss": 0.4804, |
| "num_input_tokens_seen": 31547104, |
| "step": 2045 |
| }, |
| { |
| "epoch": 8.41025641025641, |
| "grad_norm": 0.52734375, |
| "learning_rate": 2.5142785858553486e-06, |
| "loss": 0.5533, |
| "num_input_tokens_seen": 31629440, |
| "step": 2050 |
| }, |
| { |
| "epoch": 8.430769230769231, |
| "grad_norm": 0.310546875, |
| "learning_rate": 2.512044159382903e-06, |
| "loss": 0.541, |
| "num_input_tokens_seen": 31713024, |
| "step": 2055 |
| }, |
| { |
| "epoch": 8.451282051282051, |
| "grad_norm": 0.71484375, |
| "learning_rate": 2.5098056031337975e-06, |
| "loss": 0.4444, |
| "num_input_tokens_seen": 31790432, |
| "step": 2060 |
| }, |
| { |
| "epoch": 8.471794871794872, |
| "grad_norm": 0.3046875, |
| "learning_rate": 2.5075629262427507e-06, |
| "loss": 0.4869, |
| "num_input_tokens_seen": 31870592, |
| "step": 2065 |
| }, |
| { |
| "epoch": 8.492307692307692, |
| "grad_norm": 0.6015625, |
| "learning_rate": 2.505316137861294e-06, |
| "loss": 0.4855, |
| "num_input_tokens_seen": 31945344, |
| "step": 2070 |
| }, |
| { |
| "epoch": 8.512820512820513, |
| "grad_norm": 0.283203125, |
| "learning_rate": 2.503065247157737e-06, |
| "loss": 0.5027, |
| "num_input_tokens_seen": 32030016, |
| "step": 2075 |
| }, |
| { |
| "epoch": 8.533333333333333, |
| "grad_norm": 0.3515625, |
| "learning_rate": 2.500810263317129e-06, |
| "loss": 0.4885, |
| "num_input_tokens_seen": 32108160, |
| "step": 2080 |
| }, |
| { |
| "epoch": 8.553846153846154, |
| "grad_norm": 0.33203125, |
| "learning_rate": 2.4985511955412238e-06, |
| "loss": 0.4451, |
| "num_input_tokens_seen": 32188288, |
| "step": 2085 |
| }, |
| { |
| "epoch": 8.574358974358974, |
| "grad_norm": 0.35546875, |
| "learning_rate": 2.4962880530484375e-06, |
| "loss": 0.4899, |
| "num_input_tokens_seen": 32266656, |
| "step": 2090 |
| }, |
| { |
| "epoch": 8.594871794871795, |
| "grad_norm": 0.3515625, |
| "learning_rate": 2.4940208450738146e-06, |
| "loss": 0.5083, |
| "num_input_tokens_seen": 32356544, |
| "step": 2095 |
| }, |
| { |
| "epoch": 8.615384615384615, |
| "grad_norm": 0.37890625, |
| "learning_rate": 2.49174958086899e-06, |
| "loss": 0.4839, |
| "num_input_tokens_seen": 32434720, |
| "step": 2100 |
| }, |
| { |
| "epoch": 8.635897435897435, |
| "grad_norm": 0.373046875, |
| "learning_rate": 2.48947426970215e-06, |
| "loss": 0.437, |
| "num_input_tokens_seen": 32507712, |
| "step": 2105 |
| }, |
| { |
| "epoch": 8.656410256410256, |
| "grad_norm": 0.361328125, |
| "learning_rate": 2.487194920857995e-06, |
| "loss": 0.435, |
| "num_input_tokens_seen": 32577216, |
| "step": 2110 |
| }, |
| { |
| "epoch": 8.676923076923076, |
| "grad_norm": 0.3359375, |
| "learning_rate": 2.484911543637702e-06, |
| "loss": 0.4768, |
| "num_input_tokens_seen": 32647552, |
| "step": 2115 |
| }, |
| { |
| "epoch": 8.697435897435897, |
| "grad_norm": 0.34765625, |
| "learning_rate": 2.4826241473588855e-06, |
| "loss": 0.4578, |
| "num_input_tokens_seen": 32727520, |
| "step": 2120 |
| }, |
| { |
| "epoch": 8.717948717948717, |
| "grad_norm": 0.365234375, |
| "learning_rate": 2.4803327413555623e-06, |
| "loss": 0.5142, |
| "num_input_tokens_seen": 32805440, |
| "step": 2125 |
| }, |
| { |
| "epoch": 8.73846153846154, |
| "grad_norm": 0.35546875, |
| "learning_rate": 2.4780373349781083e-06, |
| "loss": 0.4013, |
| "num_input_tokens_seen": 32880480, |
| "step": 2130 |
| }, |
| { |
| "epoch": 8.75897435897436, |
| "grad_norm": 0.30078125, |
| "learning_rate": 2.4757379375932265e-06, |
| "loss": 0.4616, |
| "num_input_tokens_seen": 32951936, |
| "step": 2135 |
| }, |
| { |
| "epoch": 8.77948717948718, |
| "grad_norm": 0.287109375, |
| "learning_rate": 2.473434558583903e-06, |
| "loss": 0.4791, |
| "num_input_tokens_seen": 33027104, |
| "step": 2140 |
| }, |
| { |
| "epoch": 8.8, |
| "grad_norm": 0.2451171875, |
| "learning_rate": 2.4711272073493745e-06, |
| "loss": 0.5163, |
| "num_input_tokens_seen": 33111040, |
| "step": 2145 |
| }, |
| { |
| "epoch": 8.820512820512821, |
| "grad_norm": 0.2470703125, |
| "learning_rate": 2.468815893305084e-06, |
| "loss": 0.4761, |
| "num_input_tokens_seen": 33202304, |
| "step": 2150 |
| }, |
| { |
| "epoch": 8.841025641025642, |
| "grad_norm": 0.2275390625, |
| "learning_rate": 2.466500625882646e-06, |
| "loss": 0.4405, |
| "num_input_tokens_seen": 33281376, |
| "step": 2155 |
| }, |
| { |
| "epoch": 8.861538461538462, |
| "grad_norm": 0.21484375, |
| "learning_rate": 2.464181414529809e-06, |
| "loss": 0.4538, |
| "num_input_tokens_seen": 33352640, |
| "step": 2160 |
| }, |
| { |
| "epoch": 8.882051282051282, |
| "grad_norm": 0.19140625, |
| "learning_rate": 2.4618582687104132e-06, |
| "loss": 0.4598, |
| "num_input_tokens_seen": 33423232, |
| "step": 2165 |
| }, |
| { |
| "epoch": 8.902564102564103, |
| "grad_norm": 0.169921875, |
| "learning_rate": 2.4595311979043545e-06, |
| "loss": 0.4556, |
| "num_input_tokens_seen": 33503744, |
| "step": 2170 |
| }, |
| { |
| "epoch": 8.923076923076923, |
| "grad_norm": 0.16796875, |
| "learning_rate": 2.4572002116075454e-06, |
| "loss": 0.4665, |
| "num_input_tokens_seen": 33576800, |
| "step": 2175 |
| }, |
| { |
| "epoch": 8.943589743589744, |
| "grad_norm": 0.1748046875, |
| "learning_rate": 2.454865319331876e-06, |
| "loss": 0.4683, |
| "num_input_tokens_seen": 33661120, |
| "step": 2180 |
| }, |
| { |
| "epoch": 8.964102564102564, |
| "grad_norm": 0.1484375, |
| "learning_rate": 2.4525265306051755e-06, |
| "loss": 0.5183, |
| "num_input_tokens_seen": 33733568, |
| "step": 2185 |
| }, |
| { |
| "epoch": 8.984615384615385, |
| "grad_norm": 0.15234375, |
| "learning_rate": 2.4501838549711723e-06, |
| "loss": 0.4671, |
| "num_input_tokens_seen": 33802592, |
| "step": 2190 |
| }, |
| { |
| "epoch": 9.005128205128205, |
| "grad_norm": 0.126953125, |
| "learning_rate": 2.447837301989457e-06, |
| "loss": 0.4858, |
| "num_input_tokens_seen": 33882272, |
| "step": 2195 |
| }, |
| { |
| "epoch": 9.025641025641026, |
| "grad_norm": 0.138671875, |
| "learning_rate": 2.4454868812354403e-06, |
| "loss": 0.4574, |
| "num_input_tokens_seen": 33953920, |
| "step": 2200 |
| }, |
| { |
| "epoch": 9.046153846153846, |
| "grad_norm": 0.11669921875, |
| "learning_rate": 2.4431326023003188e-06, |
| "loss": 0.4419, |
| "num_input_tokens_seen": 34027552, |
| "step": 2205 |
| }, |
| { |
| "epoch": 9.066666666666666, |
| "grad_norm": 0.11669921875, |
| "learning_rate": 2.44077447479103e-06, |
| "loss": 0.5126, |
| "num_input_tokens_seen": 34112480, |
| "step": 2210 |
| }, |
| { |
| "epoch": 9.087179487179487, |
| "grad_norm": 0.1357421875, |
| "learning_rate": 2.4384125083302178e-06, |
| "loss": 0.4517, |
| "num_input_tokens_seen": 34183840, |
| "step": 2215 |
| }, |
| { |
| "epoch": 9.107692307692307, |
| "grad_norm": 0.251953125, |
| "learning_rate": 2.4360467125561907e-06, |
| "loss": 0.5161, |
| "num_input_tokens_seen": 34258912, |
| "step": 2220 |
| }, |
| { |
| "epoch": 9.128205128205128, |
| "grad_norm": 0.240234375, |
| "learning_rate": 2.433677097122883e-06, |
| "loss": 0.4486, |
| "num_input_tokens_seen": 34329248, |
| "step": 2225 |
| }, |
| { |
| "epoch": 9.148717948717948, |
| "grad_norm": 0.166015625, |
| "learning_rate": 2.4313036716998154e-06, |
| "loss": 0.5191, |
| "num_input_tokens_seen": 34411232, |
| "step": 2230 |
| }, |
| { |
| "epoch": 9.169230769230769, |
| "grad_norm": 0.3125, |
| "learning_rate": 2.428926445972058e-06, |
| "loss": 0.5117, |
| "num_input_tokens_seen": 34486144, |
| "step": 2235 |
| }, |
| { |
| "epoch": 9.189743589743589, |
| "grad_norm": 0.2734375, |
| "learning_rate": 2.4265454296401857e-06, |
| "loss": 0.4739, |
| "num_input_tokens_seen": 34564864, |
| "step": 2240 |
| }, |
| { |
| "epoch": 9.21025641025641, |
| "grad_norm": 0.404296875, |
| "learning_rate": 2.4241606324202426e-06, |
| "loss": 0.4468, |
| "num_input_tokens_seen": 34640704, |
| "step": 2245 |
| }, |
| { |
| "epoch": 9.23076923076923, |
| "grad_norm": 0.53125, |
| "learning_rate": 2.4217720640437015e-06, |
| "loss": 0.457, |
| "num_input_tokens_seen": 34715744, |
| "step": 2250 |
| }, |
| { |
| "epoch": 9.25128205128205, |
| "grad_norm": 0.64453125, |
| "learning_rate": 2.4193797342574235e-06, |
| "loss": 0.4915, |
| "num_input_tokens_seen": 34798144, |
| "step": 2255 |
| }, |
| { |
| "epoch": 9.271794871794873, |
| "grad_norm": 0.71875, |
| "learning_rate": 2.4169836528236187e-06, |
| "loss": 0.4417, |
| "num_input_tokens_seen": 34873440, |
| "step": 2260 |
| }, |
| { |
| "epoch": 9.292307692307693, |
| "grad_norm": 0.26953125, |
| "learning_rate": 2.4145838295198066e-06, |
| "loss": 0.4999, |
| "num_input_tokens_seen": 34951552, |
| "step": 2265 |
| }, |
| { |
| "epoch": 9.312820512820513, |
| "grad_norm": 1.203125, |
| "learning_rate": 2.4121802741387743e-06, |
| "loss": 0.453, |
| "num_input_tokens_seen": 35021184, |
| "step": 2270 |
| }, |
| { |
| "epoch": 9.333333333333334, |
| "grad_norm": 0.298828125, |
| "learning_rate": 2.4097729964885407e-06, |
| "loss": 0.4473, |
| "num_input_tokens_seen": 35098080, |
| "step": 2275 |
| }, |
| { |
| "epoch": 9.353846153846154, |
| "grad_norm": 0.53515625, |
| "learning_rate": 2.4073620063923123e-06, |
| "loss": 0.4749, |
| "num_input_tokens_seen": 35170336, |
| "step": 2280 |
| }, |
| { |
| "epoch": 9.374358974358975, |
| "grad_norm": 0.314453125, |
| "learning_rate": 2.404947313688445e-06, |
| "loss": 0.5229, |
| "num_input_tokens_seen": 35255200, |
| "step": 2285 |
| }, |
| { |
| "epoch": 9.394871794871795, |
| "grad_norm": 0.4140625, |
| "learning_rate": 2.4025289282304037e-06, |
| "loss": 0.5158, |
| "num_input_tokens_seen": 35328928, |
| "step": 2290 |
| }, |
| { |
| "epoch": 9.415384615384616, |
| "grad_norm": 0.34375, |
| "learning_rate": 2.4001068598867216e-06, |
| "loss": 0.4548, |
| "num_input_tokens_seen": 35402976, |
| "step": 2295 |
| }, |
| { |
| "epoch": 9.435897435897436, |
| "grad_norm": 0.2373046875, |
| "learning_rate": 2.397681118540961e-06, |
| "loss": 0.4313, |
| "num_input_tokens_seen": 35481344, |
| "step": 2300 |
| }, |
| { |
| "epoch": 9.456410256410257, |
| "grad_norm": 0.369140625, |
| "learning_rate": 2.3952517140916724e-06, |
| "loss": 0.4664, |
| "num_input_tokens_seen": 35553664, |
| "step": 2305 |
| }, |
| { |
| "epoch": 9.476923076923077, |
| "grad_norm": 0.37890625, |
| "learning_rate": 2.392818656452354e-06, |
| "loss": 0.4948, |
| "num_input_tokens_seen": 35630592, |
| "step": 2310 |
| }, |
| { |
| "epoch": 9.497435897435897, |
| "grad_norm": 0.3046875, |
| "learning_rate": 2.39038195555141e-06, |
| "loss": 0.5035, |
| "num_input_tokens_seen": 35712864, |
| "step": 2315 |
| }, |
| { |
| "epoch": 9.517948717948718, |
| "grad_norm": 0.34765625, |
| "learning_rate": 2.387941621332114e-06, |
| "loss": 0.4964, |
| "num_input_tokens_seen": 35790784, |
| "step": 2320 |
| }, |
| { |
| "epoch": 9.538461538461538, |
| "grad_norm": 0.33203125, |
| "learning_rate": 2.3854976637525637e-06, |
| "loss": 0.4684, |
| "num_input_tokens_seen": 35868960, |
| "step": 2325 |
| }, |
| { |
| "epoch": 9.558974358974359, |
| "grad_norm": 0.345703125, |
| "learning_rate": 2.3830500927856433e-06, |
| "loss": 0.5117, |
| "num_input_tokens_seen": 35956832, |
| "step": 2330 |
| }, |
| { |
| "epoch": 9.57948717948718, |
| "grad_norm": 0.345703125, |
| "learning_rate": 2.3805989184189813e-06, |
| "loss": 0.4574, |
| "num_input_tokens_seen": 36027520, |
| "step": 2335 |
| }, |
| { |
| "epoch": 9.6, |
| "grad_norm": 0.30859375, |
| "learning_rate": 2.378144150654911e-06, |
| "loss": 0.5291, |
| "num_input_tokens_seen": 36109248, |
| "step": 2340 |
| }, |
| { |
| "epoch": 9.62051282051282, |
| "grad_norm": 0.357421875, |
| "learning_rate": 2.3756857995104286e-06, |
| "loss": 0.4528, |
| "num_input_tokens_seen": 36179584, |
| "step": 2345 |
| }, |
| { |
| "epoch": 9.64102564102564, |
| "grad_norm": 0.3671875, |
| "learning_rate": 2.3732238750171527e-06, |
| "loss": 0.4976, |
| "num_input_tokens_seen": 36257216, |
| "step": 2350 |
| }, |
| { |
| "epoch": 9.661538461538461, |
| "grad_norm": 0.30859375, |
| "learning_rate": 2.3707583872212837e-06, |
| "loss": 0.4576, |
| "num_input_tokens_seen": 36326272, |
| "step": 2355 |
| }, |
| { |
| "epoch": 9.682051282051281, |
| "grad_norm": 0.2294921875, |
| "learning_rate": 2.3682893461835626e-06, |
| "loss": 0.5315, |
| "num_input_tokens_seen": 36405504, |
| "step": 2360 |
| }, |
| { |
| "epoch": 9.702564102564102, |
| "grad_norm": 0.28515625, |
| "learning_rate": 2.3658167619792294e-06, |
| "loss": 0.5407, |
| "num_input_tokens_seen": 36481536, |
| "step": 2365 |
| }, |
| { |
| "epoch": 9.723076923076922, |
| "grad_norm": 0.267578125, |
| "learning_rate": 2.363340644697983e-06, |
| "loss": 0.4525, |
| "num_input_tokens_seen": 36563200, |
| "step": 2370 |
| }, |
| { |
| "epoch": 9.743589743589745, |
| "grad_norm": 0.205078125, |
| "learning_rate": 2.360861004443939e-06, |
| "loss": 0.5628, |
| "num_input_tokens_seen": 36661120, |
| "step": 2375 |
| }, |
| { |
| "epoch": 9.764102564102565, |
| "grad_norm": 0.2119140625, |
| "learning_rate": 2.358377851335589e-06, |
| "loss": 0.4633, |
| "num_input_tokens_seen": 36738880, |
| "step": 2380 |
| }, |
| { |
| "epoch": 9.784615384615385, |
| "grad_norm": 0.21484375, |
| "learning_rate": 2.3558911955057592e-06, |
| "loss": 0.4438, |
| "num_input_tokens_seen": 36820128, |
| "step": 2385 |
| }, |
| { |
| "epoch": 9.805128205128206, |
| "grad_norm": 0.1806640625, |
| "learning_rate": 2.35340104710157e-06, |
| "loss": 0.4609, |
| "num_input_tokens_seen": 36900128, |
| "step": 2390 |
| }, |
| { |
| "epoch": 9.825641025641026, |
| "grad_norm": 0.1708984375, |
| "learning_rate": 2.350907416284392e-06, |
| "loss": 0.4843, |
| "num_input_tokens_seen": 36969024, |
| "step": 2395 |
| }, |
| { |
| "epoch": 9.846153846153847, |
| "grad_norm": 0.162109375, |
| "learning_rate": 2.348410313229808e-06, |
| "loss": 0.4607, |
| "num_input_tokens_seen": 37053440, |
| "step": 2400 |
| }, |
| { |
| "epoch": 9.866666666666667, |
| "grad_norm": 0.146484375, |
| "learning_rate": 2.3459097481275687e-06, |
| "loss": 0.5134, |
| "num_input_tokens_seen": 37132128, |
| "step": 2405 |
| }, |
| { |
| "epoch": 9.887179487179488, |
| "grad_norm": 0.1396484375, |
| "learning_rate": 2.343405731181552e-06, |
| "loss": 0.478, |
| "num_input_tokens_seen": 37209664, |
| "step": 2410 |
| }, |
| { |
| "epoch": 9.907692307692308, |
| "grad_norm": 0.146484375, |
| "learning_rate": 2.3408982726097227e-06, |
| "loss": 0.4864, |
| "num_input_tokens_seen": 37283936, |
| "step": 2415 |
| }, |
| { |
| "epoch": 9.928205128205128, |
| "grad_norm": 0.1455078125, |
| "learning_rate": 2.3383873826440878e-06, |
| "loss": 0.4876, |
| "num_input_tokens_seen": 37359552, |
| "step": 2420 |
| }, |
| { |
| "epoch": 9.948717948717949, |
| "grad_norm": 0.13671875, |
| "learning_rate": 2.3358730715306574e-06, |
| "loss": 0.5265, |
| "num_input_tokens_seen": 37434112, |
| "step": 2425 |
| }, |
| { |
| "epoch": 9.96923076923077, |
| "grad_norm": 0.12353515625, |
| "learning_rate": 2.3333553495294033e-06, |
| "loss": 0.4759, |
| "num_input_tokens_seen": 37511456, |
| "step": 2430 |
| }, |
| { |
| "epoch": 9.98974358974359, |
| "grad_norm": 0.11865234375, |
| "learning_rate": 2.330834226914214e-06, |
| "loss": 0.4336, |
| "num_input_tokens_seen": 37584320, |
| "step": 2435 |
| }, |
| { |
| "epoch": 10.01025641025641, |
| "grad_norm": 0.123046875, |
| "learning_rate": 2.3283097139728557e-06, |
| "loss": 0.5338, |
| "num_input_tokens_seen": 37672864, |
| "step": 2440 |
| }, |
| { |
| "epoch": 10.03076923076923, |
| "grad_norm": 0.220703125, |
| "learning_rate": 2.3257818210069277e-06, |
| "loss": 0.4542, |
| "num_input_tokens_seen": 37743488, |
| "step": 2445 |
| }, |
| { |
| "epoch": 10.051282051282051, |
| "grad_norm": 0.14453125, |
| "learning_rate": 2.3232505583318246e-06, |
| "loss": 0.5379, |
| "num_input_tokens_seen": 37832256, |
| "step": 2450 |
| }, |
| { |
| "epoch": 10.071794871794872, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 2.320715936276689e-06, |
| "loss": 0.4418, |
| "num_input_tokens_seen": 37908832, |
| "step": 2455 |
| }, |
| { |
| "epoch": 10.092307692307692, |
| "grad_norm": 0.3984375, |
| "learning_rate": 2.3181779651843738e-06, |
| "loss": 0.5294, |
| "num_input_tokens_seen": 37989088, |
| "step": 2460 |
| }, |
| { |
| "epoch": 10.112820512820512, |
| "grad_norm": 0.26953125, |
| "learning_rate": 2.3156366554113967e-06, |
| "loss": 0.4438, |
| "num_input_tokens_seen": 38061024, |
| "step": 2465 |
| }, |
| { |
| "epoch": 10.133333333333333, |
| "grad_norm": 0.318359375, |
| "learning_rate": 2.3130920173278997e-06, |
| "loss": 0.4544, |
| "num_input_tokens_seen": 38136480, |
| "step": 2470 |
| }, |
| { |
| "epoch": 10.153846153846153, |
| "grad_norm": 0.55078125, |
| "learning_rate": 2.310544061317607e-06, |
| "loss": 0.4918, |
| "num_input_tokens_seen": 38213280, |
| "step": 2475 |
| }, |
| { |
| "epoch": 10.174358974358974, |
| "grad_norm": 0.8984375, |
| "learning_rate": 2.307992797777782e-06, |
| "loss": 0.4821, |
| "num_input_tokens_seen": 38283296, |
| "step": 2480 |
| }, |
| { |
| "epoch": 10.194871794871794, |
| "grad_norm": 0.27734375, |
| "learning_rate": 2.3054382371191836e-06, |
| "loss": 0.464, |
| "num_input_tokens_seen": 38360320, |
| "step": 2485 |
| }, |
| { |
| "epoch": 10.215384615384615, |
| "grad_norm": 0.251953125, |
| "learning_rate": 2.3028803897660256e-06, |
| "loss": 0.4829, |
| "num_input_tokens_seen": 38440000, |
| "step": 2490 |
| }, |
| { |
| "epoch": 10.235897435897435, |
| "grad_norm": 0.53125, |
| "learning_rate": 2.3003192661559346e-06, |
| "loss": 0.4495, |
| "num_input_tokens_seen": 38510208, |
| "step": 2495 |
| }, |
| { |
| "epoch": 10.256410256410255, |
| "grad_norm": 0.30859375, |
| "learning_rate": 2.297754876739905e-06, |
| "loss": 0.5503, |
| "num_input_tokens_seen": 38600256, |
| "step": 2500 |
| }, |
| { |
| "epoch": 10.276923076923078, |
| "grad_norm": 0.384765625, |
| "learning_rate": 2.2951872319822597e-06, |
| "loss": 0.5341, |
| "num_input_tokens_seen": 38679168, |
| "step": 2505 |
| }, |
| { |
| "epoch": 10.297435897435898, |
| "grad_norm": 0.3046875, |
| "learning_rate": 2.2926163423606027e-06, |
| "loss": 0.4903, |
| "num_input_tokens_seen": 38752064, |
| "step": 2510 |
| }, |
| { |
| "epoch": 10.317948717948719, |
| "grad_norm": 0.353515625, |
| "learning_rate": 2.2900422183657816e-06, |
| "loss": 0.4543, |
| "num_input_tokens_seen": 38829504, |
| "step": 2515 |
| }, |
| { |
| "epoch": 10.338461538461539, |
| "grad_norm": 0.330078125, |
| "learning_rate": 2.2874648705018403e-06, |
| "loss": 0.5428, |
| "num_input_tokens_seen": 38915904, |
| "step": 2520 |
| }, |
| { |
| "epoch": 10.35897435897436, |
| "grad_norm": 0.349609375, |
| "learning_rate": 2.28488430928598e-06, |
| "loss": 0.4588, |
| "num_input_tokens_seen": 38997760, |
| "step": 2525 |
| }, |
| { |
| "epoch": 10.37948717948718, |
| "grad_norm": 0.37109375, |
| "learning_rate": 2.282300545248512e-06, |
| "loss": 0.4441, |
| "num_input_tokens_seen": 39068000, |
| "step": 2530 |
| }, |
| { |
| "epoch": 10.4, |
| "grad_norm": 0.375, |
| "learning_rate": 2.27971358893282e-06, |
| "loss": 0.4441, |
| "num_input_tokens_seen": 39136480, |
| "step": 2535 |
| }, |
| { |
| "epoch": 10.42051282051282, |
| "grad_norm": 0.421875, |
| "learning_rate": 2.2771234508953116e-06, |
| "loss": 0.442, |
| "num_input_tokens_seen": 39219488, |
| "step": 2540 |
| }, |
| { |
| "epoch": 10.441025641025641, |
| "grad_norm": 0.625, |
| "learning_rate": 2.27453014170538e-06, |
| "loss": 0.5199, |
| "num_input_tokens_seen": 39295712, |
| "step": 2545 |
| }, |
| { |
| "epoch": 10.461538461538462, |
| "grad_norm": 0.345703125, |
| "learning_rate": 2.271933671945357e-06, |
| "loss": 0.5147, |
| "num_input_tokens_seen": 39371008, |
| "step": 2550 |
| }, |
| { |
| "epoch": 10.482051282051282, |
| "grad_norm": 0.359375, |
| "learning_rate": 2.2693340522104727e-06, |
| "loss": 0.5296, |
| "num_input_tokens_seen": 39450944, |
| "step": 2555 |
| }, |
| { |
| "epoch": 10.502564102564103, |
| "grad_norm": 0.310546875, |
| "learning_rate": 2.2667312931088096e-06, |
| "loss": 0.4707, |
| "num_input_tokens_seen": 39530912, |
| "step": 2560 |
| }, |
| { |
| "epoch": 10.523076923076923, |
| "grad_norm": 0.34375, |
| "learning_rate": 2.264125405261263e-06, |
| "loss": 0.4726, |
| "num_input_tokens_seen": 39602400, |
| "step": 2565 |
| }, |
| { |
| "epoch": 10.543589743589743, |
| "grad_norm": 0.37890625, |
| "learning_rate": 2.261516399301493e-06, |
| "loss": 0.4344, |
| "num_input_tokens_seen": 39679232, |
| "step": 2570 |
| }, |
| { |
| "epoch": 10.564102564102564, |
| "grad_norm": 0.302734375, |
| "learning_rate": 2.2589042858758853e-06, |
| "loss": 0.4427, |
| "num_input_tokens_seen": 39755904, |
| "step": 2575 |
| }, |
| { |
| "epoch": 10.584615384615384, |
| "grad_norm": 0.326171875, |
| "learning_rate": 2.256289075643506e-06, |
| "loss": 0.4975, |
| "num_input_tokens_seen": 39826368, |
| "step": 2580 |
| }, |
| { |
| "epoch": 10.605128205128205, |
| "grad_norm": 0.287109375, |
| "learning_rate": 2.2536707792760566e-06, |
| "loss": 0.5045, |
| "num_input_tokens_seen": 39906464, |
| "step": 2585 |
| }, |
| { |
| "epoch": 10.625641025641025, |
| "grad_norm": 0.27734375, |
| "learning_rate": 2.251049407457833e-06, |
| "loss": 0.4833, |
| "num_input_tokens_seen": 39975712, |
| "step": 2590 |
| }, |
| { |
| "epoch": 10.646153846153846, |
| "grad_norm": 0.263671875, |
| "learning_rate": 2.2484249708856823e-06, |
| "loss": 0.4984, |
| "num_input_tokens_seen": 40060032, |
| "step": 2595 |
| }, |
| { |
| "epoch": 10.666666666666666, |
| "grad_norm": 0.2333984375, |
| "learning_rate": 2.2457974802689545e-06, |
| "loss": 0.4186, |
| "num_input_tokens_seen": 40131520, |
| "step": 2600 |
| }, |
| { |
| "epoch": 10.687179487179487, |
| "grad_norm": 0.1962890625, |
| "learning_rate": 2.2431669463294646e-06, |
| "loss": 0.4441, |
| "num_input_tokens_seen": 40205760, |
| "step": 2605 |
| }, |
| { |
| "epoch": 10.707692307692307, |
| "grad_norm": 0.2119140625, |
| "learning_rate": 2.2405333798014453e-06, |
| "loss": 0.5337, |
| "num_input_tokens_seen": 40288992, |
| "step": 2610 |
| }, |
| { |
| "epoch": 10.728205128205127, |
| "grad_norm": 0.208984375, |
| "learning_rate": 2.237896791431505e-06, |
| "loss": 0.4703, |
| "num_input_tokens_seen": 40369440, |
| "step": 2615 |
| }, |
| { |
| "epoch": 10.74871794871795, |
| "grad_norm": 0.1630859375, |
| "learning_rate": 2.2352571919785812e-06, |
| "loss": 0.5217, |
| "num_input_tokens_seen": 40452288, |
| "step": 2620 |
| }, |
| { |
| "epoch": 10.76923076923077, |
| "grad_norm": 0.1572265625, |
| "learning_rate": 2.2326145922139004e-06, |
| "loss": 0.4475, |
| "num_input_tokens_seen": 40523808, |
| "step": 2625 |
| }, |
| { |
| "epoch": 10.78974358974359, |
| "grad_norm": 0.1884765625, |
| "learning_rate": 2.2299690029209313e-06, |
| "loss": 0.4734, |
| "num_input_tokens_seen": 40606496, |
| "step": 2630 |
| }, |
| { |
| "epoch": 10.810256410256411, |
| "grad_norm": 0.1259765625, |
| "learning_rate": 2.227320434895343e-06, |
| "loss": 0.4686, |
| "num_input_tokens_seen": 40684672, |
| "step": 2635 |
| }, |
| { |
| "epoch": 10.830769230769231, |
| "grad_norm": 0.1279296875, |
| "learning_rate": 2.2246688989449577e-06, |
| "loss": 0.5027, |
| "num_input_tokens_seen": 40762752, |
| "step": 2640 |
| }, |
| { |
| "epoch": 10.851282051282052, |
| "grad_norm": 0.12109375, |
| "learning_rate": 2.2220144058897104e-06, |
| "loss": 0.4582, |
| "num_input_tokens_seen": 40851776, |
| "step": 2645 |
| }, |
| { |
| "epoch": 10.871794871794872, |
| "grad_norm": 0.1318359375, |
| "learning_rate": 2.2193569665616017e-06, |
| "loss": 0.4516, |
| "num_input_tokens_seen": 40922304, |
| "step": 2650 |
| }, |
| { |
| "epoch": 10.892307692307693, |
| "grad_norm": 0.12109375, |
| "learning_rate": 2.2166965918046554e-06, |
| "loss": 0.4346, |
| "num_input_tokens_seen": 40998784, |
| "step": 2655 |
| }, |
| { |
| "epoch": 10.912820512820513, |
| "grad_norm": 0.16015625, |
| "learning_rate": 2.214033292474874e-06, |
| "loss": 0.5093, |
| "num_input_tokens_seen": 41075872, |
| "step": 2660 |
| }, |
| { |
| "epoch": 10.933333333333334, |
| "grad_norm": 0.154296875, |
| "learning_rate": 2.2113670794401935e-06, |
| "loss": 0.4853, |
| "num_input_tokens_seen": 41149728, |
| "step": 2665 |
| }, |
| { |
| "epoch": 10.953846153846154, |
| "grad_norm": 0.2333984375, |
| "learning_rate": 2.20869796358044e-06, |
| "loss": 0.5042, |
| "num_input_tokens_seen": 41220160, |
| "step": 2670 |
| }, |
| { |
| "epoch": 10.974358974358974, |
| "grad_norm": 0.1630859375, |
| "learning_rate": 2.2060259557872845e-06, |
| "loss": 0.4601, |
| "num_input_tokens_seen": 41287712, |
| "step": 2675 |
| }, |
| { |
| "epoch": 10.994871794871795, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 2.2033510669641997e-06, |
| "loss": 0.4138, |
| "num_input_tokens_seen": 41363264, |
| "step": 2680 |
| }, |
| { |
| "epoch": 11.015384615384615, |
| "grad_norm": 0.306640625, |
| "learning_rate": 2.2006733080264144e-06, |
| "loss": 0.4724, |
| "num_input_tokens_seen": 41437152, |
| "step": 2685 |
| }, |
| { |
| "epoch": 11.035897435897436, |
| "grad_norm": 0.26953125, |
| "learning_rate": 2.197992689900869e-06, |
| "loss": 0.4932, |
| "num_input_tokens_seen": 41515520, |
| "step": 2690 |
| }, |
| { |
| "epoch": 11.056410256410256, |
| "grad_norm": 0.5859375, |
| "learning_rate": 2.195309223526171e-06, |
| "loss": 0.4299, |
| "num_input_tokens_seen": 41587200, |
| "step": 2695 |
| }, |
| { |
| "epoch": 11.076923076923077, |
| "grad_norm": 0.59375, |
| "learning_rate": 2.192622919852551e-06, |
| "loss": 0.4774, |
| "num_input_tokens_seen": 41663008, |
| "step": 2700 |
| }, |
| { |
| "epoch": 11.097435897435897, |
| "grad_norm": 0.6640625, |
| "learning_rate": 2.1899337898418174e-06, |
| "loss": 0.5241, |
| "num_input_tokens_seen": 41743264, |
| "step": 2705 |
| }, |
| { |
| "epoch": 11.117948717948718, |
| "grad_norm": 0.29296875, |
| "learning_rate": 2.187241844467313e-06, |
| "loss": 0.498, |
| "num_input_tokens_seen": 41823264, |
| "step": 2710 |
| }, |
| { |
| "epoch": 11.138461538461538, |
| "grad_norm": 0.2890625, |
| "learning_rate": 2.1845470947138658e-06, |
| "loss": 0.5311, |
| "num_input_tokens_seen": 41914560, |
| "step": 2715 |
| }, |
| { |
| "epoch": 11.158974358974358, |
| "grad_norm": 0.58984375, |
| "learning_rate": 2.181849551577751e-06, |
| "loss": 0.4464, |
| "num_input_tokens_seen": 41988288, |
| "step": 2720 |
| }, |
| { |
| "epoch": 11.179487179487179, |
| "grad_norm": 0.34375, |
| "learning_rate": 2.179149226066641e-06, |
| "loss": 0.4905, |
| "num_input_tokens_seen": 42068416, |
| "step": 2725 |
| }, |
| { |
| "epoch": 11.2, |
| "grad_norm": 0.275390625, |
| "learning_rate": 2.1764461291995618e-06, |
| "loss": 0.4629, |
| "num_input_tokens_seen": 42139744, |
| "step": 2730 |
| }, |
| { |
| "epoch": 11.22051282051282, |
| "grad_norm": 0.2578125, |
| "learning_rate": 2.173740272006849e-06, |
| "loss": 0.5278, |
| "num_input_tokens_seen": 42228672, |
| "step": 2735 |
| }, |
| { |
| "epoch": 11.24102564102564, |
| "grad_norm": 0.6640625, |
| "learning_rate": 2.1710316655301016e-06, |
| "loss": 0.4513, |
| "num_input_tokens_seen": 42306528, |
| "step": 2740 |
| }, |
| { |
| "epoch": 11.261538461538462, |
| "grad_norm": 0.2470703125, |
| "learning_rate": 2.1683203208221375e-06, |
| "loss": 0.4917, |
| "num_input_tokens_seen": 42389024, |
| "step": 2745 |
| }, |
| { |
| "epoch": 11.282051282051283, |
| "grad_norm": 0.333984375, |
| "learning_rate": 2.165606248946948e-06, |
| "loss": 0.4159, |
| "num_input_tokens_seen": 42473088, |
| "step": 2750 |
| }, |
| { |
| "epoch": 11.302564102564103, |
| "grad_norm": 0.291015625, |
| "learning_rate": 2.1628894609796533e-06, |
| "loss": 0.4917, |
| "num_input_tokens_seen": 42551360, |
| "step": 2755 |
| }, |
| { |
| "epoch": 11.323076923076924, |
| "grad_norm": 0.390625, |
| "learning_rate": 2.1601699680064573e-06, |
| "loss": 0.5037, |
| "num_input_tokens_seen": 42626688, |
| "step": 2760 |
| }, |
| { |
| "epoch": 11.343589743589744, |
| "grad_norm": 0.369140625, |
| "learning_rate": 2.1574477811246014e-06, |
| "loss": 0.4756, |
| "num_input_tokens_seen": 42705056, |
| "step": 2765 |
| }, |
| { |
| "epoch": 11.364102564102565, |
| "grad_norm": 0.421875, |
| "learning_rate": 2.1547229114423207e-06, |
| "loss": 0.4985, |
| "num_input_tokens_seen": 42777632, |
| "step": 2770 |
| }, |
| { |
| "epoch": 11.384615384615385, |
| "grad_norm": 0.326171875, |
| "learning_rate": 2.1519953700787963e-06, |
| "loss": 0.4561, |
| "num_input_tokens_seen": 42845888, |
| "step": 2775 |
| }, |
| { |
| "epoch": 11.405128205128205, |
| "grad_norm": 0.36328125, |
| "learning_rate": 2.149265168164113e-06, |
| "loss": 0.5091, |
| "num_input_tokens_seen": 42922976, |
| "step": 2780 |
| }, |
| { |
| "epoch": 11.425641025641026, |
| "grad_norm": 0.353515625, |
| "learning_rate": 2.146532316839211e-06, |
| "loss": 0.4711, |
| "num_input_tokens_seen": 42996000, |
| "step": 2785 |
| }, |
| { |
| "epoch": 11.446153846153846, |
| "grad_norm": 0.38671875, |
| "learning_rate": 2.1437968272558435e-06, |
| "loss": 0.457, |
| "num_input_tokens_seen": 43074688, |
| "step": 2790 |
| }, |
| { |
| "epoch": 11.466666666666667, |
| "grad_norm": 0.31640625, |
| "learning_rate": 2.1410587105765275e-06, |
| "loss": 0.541, |
| "num_input_tokens_seen": 43157280, |
| "step": 2795 |
| }, |
| { |
| "epoch": 11.487179487179487, |
| "grad_norm": 0.361328125, |
| "learning_rate": 2.138317977974501e-06, |
| "loss": 0.4279, |
| "num_input_tokens_seen": 43234016, |
| "step": 2800 |
| }, |
| { |
| "epoch": 11.507692307692308, |
| "grad_norm": 0.306640625, |
| "learning_rate": 2.135574640633678e-06, |
| "loss": 0.5213, |
| "num_input_tokens_seen": 43310816, |
| "step": 2805 |
| }, |
| { |
| "epoch": 11.528205128205128, |
| "grad_norm": 0.275390625, |
| "learning_rate": 2.132828709748598e-06, |
| "loss": 0.4444, |
| "num_input_tokens_seen": 43382976, |
| "step": 2810 |
| }, |
| { |
| "epoch": 11.548717948717949, |
| "grad_norm": 0.279296875, |
| "learning_rate": 2.130080196524388e-06, |
| "loss": 0.4768, |
| "num_input_tokens_seen": 43462944, |
| "step": 2815 |
| }, |
| { |
| "epoch": 11.569230769230769, |
| "grad_norm": 0.283203125, |
| "learning_rate": 2.1273291121767094e-06, |
| "loss": 0.4376, |
| "num_input_tokens_seen": 43535232, |
| "step": 2820 |
| }, |
| { |
| "epoch": 11.58974358974359, |
| "grad_norm": 0.23828125, |
| "learning_rate": 2.124575467931717e-06, |
| "loss": 0.4342, |
| "num_input_tokens_seen": 43618528, |
| "step": 2825 |
| }, |
| { |
| "epoch": 11.61025641025641, |
| "grad_norm": 0.1982421875, |
| "learning_rate": 2.1218192750260114e-06, |
| "loss": 0.4596, |
| "num_input_tokens_seen": 43691904, |
| "step": 2830 |
| }, |
| { |
| "epoch": 11.63076923076923, |
| "grad_norm": 0.1904296875, |
| "learning_rate": 2.119060544706592e-06, |
| "loss": 0.4811, |
| "num_input_tokens_seen": 43760480, |
| "step": 2835 |
| }, |
| { |
| "epoch": 11.65128205128205, |
| "grad_norm": 0.1923828125, |
| "learning_rate": 2.1162992882308147e-06, |
| "loss": 0.4864, |
| "num_input_tokens_seen": 43829984, |
| "step": 2840 |
| }, |
| { |
| "epoch": 11.671794871794871, |
| "grad_norm": 0.1875, |
| "learning_rate": 2.1135355168663417e-06, |
| "loss": 0.4678, |
| "num_input_tokens_seen": 43906816, |
| "step": 2845 |
| }, |
| { |
| "epoch": 11.692307692307692, |
| "grad_norm": 0.1484375, |
| "learning_rate": 2.1107692418910985e-06, |
| "loss": 0.5001, |
| "num_input_tokens_seen": 43984960, |
| "step": 2850 |
| }, |
| { |
| "epoch": 11.712820512820512, |
| "grad_norm": 0.154296875, |
| "learning_rate": 2.1080004745932274e-06, |
| "loss": 0.4662, |
| "num_input_tokens_seen": 44061440, |
| "step": 2855 |
| }, |
| { |
| "epoch": 11.733333333333333, |
| "grad_norm": 0.1611328125, |
| "learning_rate": 2.1052292262710392e-06, |
| "loss": 0.526, |
| "num_input_tokens_seen": 44147008, |
| "step": 2860 |
| }, |
| { |
| "epoch": 11.753846153846155, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 2.102455508232971e-06, |
| "loss": 0.4821, |
| "num_input_tokens_seen": 44224224, |
| "step": 2865 |
| }, |
| { |
| "epoch": 11.774358974358975, |
| "grad_norm": 0.146484375, |
| "learning_rate": 2.099679331797536e-06, |
| "loss": 0.4923, |
| "num_input_tokens_seen": 44302816, |
| "step": 2870 |
| }, |
| { |
| "epoch": 11.794871794871796, |
| "grad_norm": 0.1650390625, |
| "learning_rate": 2.0969007082932803e-06, |
| "loss": 0.521, |
| "num_input_tokens_seen": 44376160, |
| "step": 2875 |
| }, |
| { |
| "epoch": 11.815384615384616, |
| "grad_norm": 0.125, |
| "learning_rate": 2.0941196490587354e-06, |
| "loss": 0.4932, |
| "num_input_tokens_seen": 44459200, |
| "step": 2880 |
| }, |
| { |
| "epoch": 11.835897435897436, |
| "grad_norm": 0.140625, |
| "learning_rate": 2.0913361654423723e-06, |
| "loss": 0.4866, |
| "num_input_tokens_seen": 44536128, |
| "step": 2885 |
| }, |
| { |
| "epoch": 11.856410256410257, |
| "grad_norm": 0.1357421875, |
| "learning_rate": 2.0885502688025538e-06, |
| "loss": 0.4826, |
| "num_input_tokens_seen": 44605088, |
| "step": 2890 |
| }, |
| { |
| "epoch": 11.876923076923077, |
| "grad_norm": 0.2177734375, |
| "learning_rate": 2.0857619705074912e-06, |
| "loss": 0.4433, |
| "num_input_tokens_seen": 44677984, |
| "step": 2895 |
| }, |
| { |
| "epoch": 11.897435897435898, |
| "grad_norm": 0.166015625, |
| "learning_rate": 2.082971281935195e-06, |
| "loss": 0.4122, |
| "num_input_tokens_seen": 44751200, |
| "step": 2900 |
| }, |
| { |
| "epoch": 11.917948717948718, |
| "grad_norm": 0.28515625, |
| "learning_rate": 2.0801782144734295e-06, |
| "loss": 0.4266, |
| "num_input_tokens_seen": 44824672, |
| "step": 2905 |
| }, |
| { |
| "epoch": 11.938461538461539, |
| "grad_norm": 0.341796875, |
| "learning_rate": 2.0773827795196667e-06, |
| "loss": 0.4574, |
| "num_input_tokens_seen": 44912768, |
| "step": 2910 |
| }, |
| { |
| "epoch": 11.95897435897436, |
| "grad_norm": 0.2578125, |
| "learning_rate": 2.074584988481039e-06, |
| "loss": 0.5026, |
| "num_input_tokens_seen": 44993632, |
| "step": 2915 |
| }, |
| { |
| "epoch": 11.97948717948718, |
| "grad_norm": 0.79296875, |
| "learning_rate": 2.0717848527742935e-06, |
| "loss": 0.5444, |
| "num_input_tokens_seen": 45070848, |
| "step": 2920 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.546875, |
| "learning_rate": 2.0689823838257455e-06, |
| "loss": 0.4509, |
| "num_input_tokens_seen": 45150496, |
| "step": 2925 |
| }, |
| { |
| "epoch": 12.02051282051282, |
| "grad_norm": 0.7421875, |
| "learning_rate": 2.0661775930712297e-06, |
| "loss": 0.4534, |
| "num_input_tokens_seen": 45225440, |
| "step": 2930 |
| }, |
| { |
| "epoch": 12.04102564102564, |
| "grad_norm": 0.3984375, |
| "learning_rate": 2.0633704919560573e-06, |
| "loss": 0.5264, |
| "num_input_tokens_seen": 45300992, |
| "step": 2935 |
| }, |
| { |
| "epoch": 12.061538461538461, |
| "grad_norm": 0.84765625, |
| "learning_rate": 2.0605610919349658e-06, |
| "loss": 0.4373, |
| "num_input_tokens_seen": 45378944, |
| "step": 2940 |
| }, |
| { |
| "epoch": 12.082051282051282, |
| "grad_norm": 0.53515625, |
| "learning_rate": 2.0577494044720746e-06, |
| "loss": 0.4779, |
| "num_input_tokens_seen": 45453504, |
| "step": 2945 |
| }, |
| { |
| "epoch": 12.102564102564102, |
| "grad_norm": 0.265625, |
| "learning_rate": 2.0549354410408364e-06, |
| "loss": 0.556, |
| "num_input_tokens_seen": 45532992, |
| "step": 2950 |
| }, |
| { |
| "epoch": 12.123076923076923, |
| "grad_norm": 0.2890625, |
| "learning_rate": 2.052119213123992e-06, |
| "loss": 0.5152, |
| "num_input_tokens_seen": 45609120, |
| "step": 2955 |
| }, |
| { |
| "epoch": 12.143589743589743, |
| "grad_norm": 0.318359375, |
| "learning_rate": 2.049300732213522e-06, |
| "loss": 0.4412, |
| "num_input_tokens_seen": 45690624, |
| "step": 2960 |
| }, |
| { |
| "epoch": 12.164102564102564, |
| "grad_norm": 0.46875, |
| "learning_rate": 2.046480009810602e-06, |
| "loss": 0.4553, |
| "num_input_tokens_seen": 45763264, |
| "step": 2965 |
| }, |
| { |
| "epoch": 12.184615384615384, |
| "grad_norm": 0.275390625, |
| "learning_rate": 2.0436570574255523e-06, |
| "loss": 0.4913, |
| "num_input_tokens_seen": 45849472, |
| "step": 2970 |
| }, |
| { |
| "epoch": 12.205128205128204, |
| "grad_norm": 0.41015625, |
| "learning_rate": 2.0408318865777953e-06, |
| "loss": 0.5487, |
| "num_input_tokens_seen": 45927552, |
| "step": 2975 |
| }, |
| { |
| "epoch": 12.225641025641025, |
| "grad_norm": 0.291015625, |
| "learning_rate": 2.0380045087958036e-06, |
| "loss": 0.465, |
| "num_input_tokens_seen": 46002656, |
| "step": 2980 |
| }, |
| { |
| "epoch": 12.246153846153845, |
| "grad_norm": 0.404296875, |
| "learning_rate": 2.0351749356170574e-06, |
| "loss": 0.4854, |
| "num_input_tokens_seen": 46087904, |
| "step": 2985 |
| }, |
| { |
| "epoch": 12.266666666666667, |
| "grad_norm": 0.37109375, |
| "learning_rate": 2.032343178587995e-06, |
| "loss": 0.4568, |
| "num_input_tokens_seen": 46165408, |
| "step": 2990 |
| }, |
| { |
| "epoch": 12.287179487179488, |
| "grad_norm": 0.3515625, |
| "learning_rate": 2.0295092492639657e-06, |
| "loss": 0.4926, |
| "num_input_tokens_seen": 46237344, |
| "step": 2995 |
| }, |
| { |
| "epoch": 12.307692307692308, |
| "grad_norm": 0.5, |
| "learning_rate": 2.0266731592091834e-06, |
| "loss": 0.5093, |
| "num_input_tokens_seen": 46307456, |
| "step": 3000 |
| }, |
| { |
| "epoch": 12.328205128205129, |
| "grad_norm": 0.33984375, |
| "learning_rate": 2.0238349199966793e-06, |
| "loss": 0.5077, |
| "num_input_tokens_seen": 46390688, |
| "step": 3005 |
| }, |
| { |
| "epoch": 12.34871794871795, |
| "grad_norm": 0.32421875, |
| "learning_rate": 2.020994543208254e-06, |
| "loss": 0.4541, |
| "num_input_tokens_seen": 46467904, |
| "step": 3010 |
| }, |
| { |
| "epoch": 12.36923076923077, |
| "grad_norm": 0.33203125, |
| "learning_rate": 2.018152040434432e-06, |
| "loss": 0.4975, |
| "num_input_tokens_seen": 46545632, |
| "step": 3015 |
| }, |
| { |
| "epoch": 12.38974358974359, |
| "grad_norm": 0.40234375, |
| "learning_rate": 2.015307423274411e-06, |
| "loss": 0.4988, |
| "num_input_tokens_seen": 46624768, |
| "step": 3020 |
| }, |
| { |
| "epoch": 12.41025641025641, |
| "grad_norm": 0.298828125, |
| "learning_rate": 2.0124607033360193e-06, |
| "loss": 0.4877, |
| "num_input_tokens_seen": 46694528, |
| "step": 3025 |
| }, |
| { |
| "epoch": 12.430769230769231, |
| "grad_norm": 0.3046875, |
| "learning_rate": 2.0096118922356646e-06, |
| "loss": 0.4621, |
| "num_input_tokens_seen": 46767520, |
| "step": 3030 |
| }, |
| { |
| "epoch": 12.451282051282051, |
| "grad_norm": 0.255859375, |
| "learning_rate": 2.0067610015982868e-06, |
| "loss": 0.4742, |
| "num_input_tokens_seen": 46843616, |
| "step": 3035 |
| }, |
| { |
| "epoch": 12.471794871794872, |
| "grad_norm": 0.27734375, |
| "learning_rate": 2.0039080430573133e-06, |
| "loss": 0.3993, |
| "num_input_tokens_seen": 46915136, |
| "step": 3040 |
| }, |
| { |
| "epoch": 12.492307692307692, |
| "grad_norm": 0.232421875, |
| "learning_rate": 2.0010530282546093e-06, |
| "loss": 0.464, |
| "num_input_tokens_seen": 46992000, |
| "step": 3045 |
| }, |
| { |
| "epoch": 12.512820512820513, |
| "grad_norm": 0.2060546875, |
| "learning_rate": 1.9981959688404303e-06, |
| "loss": 0.4744, |
| "num_input_tokens_seen": 47075360, |
| "step": 3050 |
| }, |
| { |
| "epoch": 12.533333333333333, |
| "grad_norm": 0.1953125, |
| "learning_rate": 1.9953368764733763e-06, |
| "loss": 0.4788, |
| "num_input_tokens_seen": 47152704, |
| "step": 3055 |
| }, |
| { |
| "epoch": 12.553846153846154, |
| "grad_norm": 0.1923828125, |
| "learning_rate": 1.992475762820342e-06, |
| "loss": 0.4704, |
| "num_input_tokens_seen": 47229696, |
| "step": 3060 |
| }, |
| { |
| "epoch": 12.574358974358974, |
| "grad_norm": 0.193359375, |
| "learning_rate": 1.9896126395564695e-06, |
| "loss": 0.4645, |
| "num_input_tokens_seen": 47307360, |
| "step": 3065 |
| }, |
| { |
| "epoch": 12.594871794871795, |
| "grad_norm": 0.1728515625, |
| "learning_rate": 1.986747518365104e-06, |
| "loss": 0.5485, |
| "num_input_tokens_seen": 47393824, |
| "step": 3070 |
| }, |
| { |
| "epoch": 12.615384615384615, |
| "grad_norm": 0.154296875, |
| "learning_rate": 1.9838804109377405e-06, |
| "loss": 0.511, |
| "num_input_tokens_seen": 47475104, |
| "step": 3075 |
| }, |
| { |
| "epoch": 12.635897435897435, |
| "grad_norm": 0.1630859375, |
| "learning_rate": 1.9810113289739818e-06, |
| "loss": 0.4624, |
| "num_input_tokens_seen": 47548704, |
| "step": 3080 |
| }, |
| { |
| "epoch": 12.656410256410256, |
| "grad_norm": 0.1435546875, |
| "learning_rate": 1.9781402841814855e-06, |
| "loss": 0.5197, |
| "num_input_tokens_seen": 47638880, |
| "step": 3085 |
| }, |
| { |
| "epoch": 12.676923076923076, |
| "grad_norm": 0.134765625, |
| "learning_rate": 1.9752672882759204e-06, |
| "loss": 0.4277, |
| "num_input_tokens_seen": 47711456, |
| "step": 3090 |
| }, |
| { |
| "epoch": 12.697435897435897, |
| "grad_norm": 0.138671875, |
| "learning_rate": 1.972392352980917e-06, |
| "loss": 0.5166, |
| "num_input_tokens_seen": 47787776, |
| "step": 3095 |
| }, |
| { |
| "epoch": 12.717948717948717, |
| "grad_norm": 0.1357421875, |
| "learning_rate": 1.969515490028019e-06, |
| "loss": 0.4201, |
| "num_input_tokens_seen": 47860480, |
| "step": 3100 |
| }, |
| { |
| "epoch": 12.73846153846154, |
| "grad_norm": 0.1064453125, |
| "learning_rate": 1.966636711156636e-06, |
| "loss": 0.4425, |
| "num_input_tokens_seen": 47936704, |
| "step": 3105 |
| }, |
| { |
| "epoch": 12.75897435897436, |
| "grad_norm": 0.154296875, |
| "learning_rate": 1.9637560281139982e-06, |
| "loss": 0.5056, |
| "num_input_tokens_seen": 48021792, |
| "step": 3110 |
| }, |
| { |
| "epoch": 12.77948717948718, |
| "grad_norm": 0.1953125, |
| "learning_rate": 1.960873452655102e-06, |
| "loss": 0.4929, |
| "num_input_tokens_seen": 48101984, |
| "step": 3115 |
| }, |
| { |
| "epoch": 12.8, |
| "grad_norm": 0.2392578125, |
| "learning_rate": 1.95798899654267e-06, |
| "loss": 0.4868, |
| "num_input_tokens_seen": 48186688, |
| "step": 3120 |
| }, |
| { |
| "epoch": 12.820512820512821, |
| "grad_norm": 0.134765625, |
| "learning_rate": 1.9551026715470954e-06, |
| "loss": 0.4668, |
| "num_input_tokens_seen": 48259872, |
| "step": 3125 |
| }, |
| { |
| "epoch": 12.841025641025642, |
| "grad_norm": 0.6953125, |
| "learning_rate": 1.952214489446401e-06, |
| "loss": 0.53, |
| "num_input_tokens_seen": 48347232, |
| "step": 3130 |
| }, |
| { |
| "epoch": 12.861538461538462, |
| "grad_norm": 0.296875, |
| "learning_rate": 1.949324462026185e-06, |
| "loss": 0.4388, |
| "num_input_tokens_seen": 48422624, |
| "step": 3135 |
| }, |
| { |
| "epoch": 12.882051282051282, |
| "grad_norm": 0.28125, |
| "learning_rate": 1.9464326010795776e-06, |
| "loss": 0.4246, |
| "num_input_tokens_seen": 48492288, |
| "step": 3140 |
| }, |
| { |
| "epoch": 12.902564102564103, |
| "grad_norm": 0.72265625, |
| "learning_rate": 1.9435389184071895e-06, |
| "loss": 0.5186, |
| "num_input_tokens_seen": 48568224, |
| "step": 3145 |
| }, |
| { |
| "epoch": 12.923076923076923, |
| "grad_norm": 0.7734375, |
| "learning_rate": 1.9406434258170666e-06, |
| "loss": 0.4351, |
| "num_input_tokens_seen": 48637280, |
| "step": 3150 |
| }, |
| { |
| "epoch": 12.943589743589744, |
| "grad_norm": 2.03125, |
| "learning_rate": 1.9377461351246395e-06, |
| "loss": 0.5281, |
| "num_input_tokens_seen": 48717088, |
| "step": 3155 |
| }, |
| { |
| "epoch": 12.964102564102564, |
| "grad_norm": 0.236328125, |
| "learning_rate": 1.9348470581526763e-06, |
| "loss": 0.4308, |
| "num_input_tokens_seen": 48787584, |
| "step": 3160 |
| }, |
| { |
| "epoch": 12.984615384615385, |
| "grad_norm": 0.52734375, |
| "learning_rate": 1.9319462067312344e-06, |
| "loss": 0.4133, |
| "num_input_tokens_seen": 48864640, |
| "step": 3165 |
| }, |
| { |
| "epoch": 13.005128205128205, |
| "grad_norm": 0.55859375, |
| "learning_rate": 1.929043592697612e-06, |
| "loss": 0.4802, |
| "num_input_tokens_seen": 48938176, |
| "step": 3170 |
| }, |
| { |
| "epoch": 13.025641025641026, |
| "grad_norm": 0.306640625, |
| "learning_rate": 1.926139227896299e-06, |
| "loss": 0.4504, |
| "num_input_tokens_seen": 49015040, |
| "step": 3175 |
| }, |
| { |
| "epoch": 13.046153846153846, |
| "grad_norm": 0.4140625, |
| "learning_rate": 1.923233124178932e-06, |
| "loss": 0.494, |
| "num_input_tokens_seen": 49091680, |
| "step": 3180 |
| }, |
| { |
| "epoch": 13.066666666666666, |
| "grad_norm": 0.3671875, |
| "learning_rate": 1.9203252934042403e-06, |
| "loss": 0.4628, |
| "num_input_tokens_seen": 49165600, |
| "step": 3185 |
| }, |
| { |
| "epoch": 13.087179487179487, |
| "grad_norm": 0.318359375, |
| "learning_rate": 1.9174157474380034e-06, |
| "loss": 0.4431, |
| "num_input_tokens_seen": 49247136, |
| "step": 3190 |
| }, |
| { |
| "epoch": 13.107692307692307, |
| "grad_norm": 0.27734375, |
| "learning_rate": 1.914504498152998e-06, |
| "loss": 0.4479, |
| "num_input_tokens_seen": 49319648, |
| "step": 3195 |
| }, |
| { |
| "epoch": 13.128205128205128, |
| "grad_norm": 0.40625, |
| "learning_rate": 1.9115915574289525e-06, |
| "loss": 0.4278, |
| "num_input_tokens_seen": 49393216, |
| "step": 3200 |
| }, |
| { |
| "epoch": 13.148717948717948, |
| "grad_norm": 0.302734375, |
| "learning_rate": 1.9086769371524966e-06, |
| "loss": 0.5124, |
| "num_input_tokens_seen": 49480864, |
| "step": 3205 |
| }, |
| { |
| "epoch": 13.169230769230769, |
| "grad_norm": 0.3515625, |
| "learning_rate": 1.9057606492171144e-06, |
| "loss": 0.4438, |
| "num_input_tokens_seen": 49559904, |
| "step": 3210 |
| }, |
| { |
| "epoch": 13.189743589743589, |
| "grad_norm": 0.412109375, |
| "learning_rate": 1.9028427055230948e-06, |
| "loss": 0.4312, |
| "num_input_tokens_seen": 49630240, |
| "step": 3215 |
| }, |
| { |
| "epoch": 13.21025641025641, |
| "grad_norm": 0.443359375, |
| "learning_rate": 1.8999231179774833e-06, |
| "loss": 0.5431, |
| "num_input_tokens_seen": 49709888, |
| "step": 3220 |
| }, |
| { |
| "epoch": 13.23076923076923, |
| "grad_norm": 0.447265625, |
| "learning_rate": 1.897001898494033e-06, |
| "loss": 0.4567, |
| "num_input_tokens_seen": 49778848, |
| "step": 3225 |
| }, |
| { |
| "epoch": 13.25128205128205, |
| "grad_norm": 0.396484375, |
| "learning_rate": 1.8940790589931568e-06, |
| "loss": 0.4227, |
| "num_input_tokens_seen": 49849024, |
| "step": 3230 |
| }, |
| { |
| "epoch": 13.271794871794873, |
| "grad_norm": 0.306640625, |
| "learning_rate": 1.8911546114018775e-06, |
| "loss": 0.4738, |
| "num_input_tokens_seen": 49917952, |
| "step": 3235 |
| }, |
| { |
| "epoch": 13.292307692307693, |
| "grad_norm": 0.3203125, |
| "learning_rate": 1.888228567653781e-06, |
| "loss": 0.4661, |
| "num_input_tokens_seen": 50003392, |
| "step": 3240 |
| }, |
| { |
| "epoch": 13.312820512820513, |
| "grad_norm": 0.330078125, |
| "learning_rate": 1.8853009396889665e-06, |
| "loss": 0.5039, |
| "num_input_tokens_seen": 50085280, |
| "step": 3245 |
| }, |
| { |
| "epoch": 13.333333333333334, |
| "grad_norm": 0.33984375, |
| "learning_rate": 1.8823717394539966e-06, |
| "loss": 0.4442, |
| "num_input_tokens_seen": 50166304, |
| "step": 3250 |
| }, |
| { |
| "epoch": 13.353846153846154, |
| "grad_norm": 0.271484375, |
| "learning_rate": 1.8794409789018507e-06, |
| "loss": 0.5048, |
| "num_input_tokens_seen": 50247200, |
| "step": 3255 |
| }, |
| { |
| "epoch": 13.374358974358975, |
| "grad_norm": 0.275390625, |
| "learning_rate": 1.8765086699918747e-06, |
| "loss": 0.4615, |
| "num_input_tokens_seen": 50321120, |
| "step": 3260 |
| }, |
| { |
| "epoch": 13.394871794871795, |
| "grad_norm": 0.275390625, |
| "learning_rate": 1.8735748246897337e-06, |
| "loss": 0.4838, |
| "num_input_tokens_seen": 50403680, |
| "step": 3265 |
| }, |
| { |
| "epoch": 13.415384615384616, |
| "grad_norm": 0.203125, |
| "learning_rate": 1.8706394549673615e-06, |
| "loss": 0.4454, |
| "num_input_tokens_seen": 50481504, |
| "step": 3270 |
| }, |
| { |
| "epoch": 13.435897435897436, |
| "grad_norm": 0.220703125, |
| "learning_rate": 1.8677025728029122e-06, |
| "loss": 0.4806, |
| "num_input_tokens_seen": 50556448, |
| "step": 3275 |
| }, |
| { |
| "epoch": 13.456410256410257, |
| "grad_norm": 0.2060546875, |
| "learning_rate": 1.8647641901807126e-06, |
| "loss": 0.4601, |
| "num_input_tokens_seen": 50630304, |
| "step": 3280 |
| }, |
| { |
| "epoch": 13.476923076923077, |
| "grad_norm": 0.2236328125, |
| "learning_rate": 1.861824319091212e-06, |
| "loss": 0.4513, |
| "num_input_tokens_seen": 50704704, |
| "step": 3285 |
| }, |
| { |
| "epoch": 13.497435897435897, |
| "grad_norm": 0.1572265625, |
| "learning_rate": 1.8588829715309324e-06, |
| "loss": 0.4704, |
| "num_input_tokens_seen": 50782464, |
| "step": 3290 |
| }, |
| { |
| "epoch": 13.517948717948718, |
| "grad_norm": 0.166015625, |
| "learning_rate": 1.855940159502423e-06, |
| "loss": 0.4959, |
| "num_input_tokens_seen": 50861696, |
| "step": 3295 |
| }, |
| { |
| "epoch": 13.538461538461538, |
| "grad_norm": 0.1591796875, |
| "learning_rate": 1.8529958950142066e-06, |
| "loss": 0.5215, |
| "num_input_tokens_seen": 50949568, |
| "step": 3300 |
| }, |
| { |
| "epoch": 13.558974358974359, |
| "grad_norm": 0.14453125, |
| "learning_rate": 1.8500501900807345e-06, |
| "loss": 0.4692, |
| "num_input_tokens_seen": 51018432, |
| "step": 3305 |
| }, |
| { |
| "epoch": 13.57948717948718, |
| "grad_norm": 0.1435546875, |
| "learning_rate": 1.847103056722335e-06, |
| "loss": 0.5015, |
| "num_input_tokens_seen": 51100352, |
| "step": 3310 |
| }, |
| { |
| "epoch": 13.6, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 1.8441545069651665e-06, |
| "loss": 0.4779, |
| "num_input_tokens_seen": 51178144, |
| "step": 3315 |
| }, |
| { |
| "epoch": 13.62051282051282, |
| "grad_norm": 0.146484375, |
| "learning_rate": 1.8412045528411652e-06, |
| "loss": 0.4971, |
| "num_input_tokens_seen": 51262432, |
| "step": 3320 |
| }, |
| { |
| "epoch": 13.64102564102564, |
| "grad_norm": 0.11279296875, |
| "learning_rate": 1.8382532063880005e-06, |
| "loss": 0.5063, |
| "num_input_tokens_seen": 51342624, |
| "step": 3325 |
| }, |
| { |
| "epoch": 13.661538461538461, |
| "grad_norm": 0.1328125, |
| "learning_rate": 1.8353004796490212e-06, |
| "loss": 0.4273, |
| "num_input_tokens_seen": 51413920, |
| "step": 3330 |
| }, |
| { |
| "epoch": 13.682051282051281, |
| "grad_norm": 0.14453125, |
| "learning_rate": 1.8323463846732099e-06, |
| "loss": 0.5491, |
| "num_input_tokens_seen": 51501184, |
| "step": 3335 |
| }, |
| { |
| "epoch": 13.702564102564102, |
| "grad_norm": 0.2109375, |
| "learning_rate": 1.8293909335151316e-06, |
| "loss": 0.4199, |
| "num_input_tokens_seen": 51570944, |
| "step": 3340 |
| }, |
| { |
| "epoch": 13.723076923076922, |
| "grad_norm": 0.236328125, |
| "learning_rate": 1.826434138234886e-06, |
| "loss": 0.4468, |
| "num_input_tokens_seen": 51650784, |
| "step": 3345 |
| }, |
| { |
| "epoch": 13.743589743589745, |
| "grad_norm": 0.150390625, |
| "learning_rate": 1.8234760108980572e-06, |
| "loss": 0.5225, |
| "num_input_tokens_seen": 51731008, |
| "step": 3350 |
| }, |
| { |
| "epoch": 13.764102564102565, |
| "grad_norm": 0.33203125, |
| "learning_rate": 1.820516563575665e-06, |
| "loss": 0.4634, |
| "num_input_tokens_seen": 51809056, |
| "step": 3355 |
| }, |
| { |
| "epoch": 13.784615384615385, |
| "grad_norm": 0.298828125, |
| "learning_rate": 1.8175558083441164e-06, |
| "loss": 0.5321, |
| "num_input_tokens_seen": 51886688, |
| "step": 3360 |
| }, |
| { |
| "epoch": 13.805128205128206, |
| "grad_norm": 0.2119140625, |
| "learning_rate": 1.814593757285154e-06, |
| "loss": 0.4633, |
| "num_input_tokens_seen": 51959488, |
| "step": 3365 |
| }, |
| { |
| "epoch": 13.825641025641026, |
| "grad_norm": 0.59765625, |
| "learning_rate": 1.8116304224858092e-06, |
| "loss": 0.4812, |
| "num_input_tokens_seen": 52035424, |
| "step": 3370 |
| }, |
| { |
| "epoch": 13.846153846153847, |
| "grad_norm": 0.859375, |
| "learning_rate": 1.8086658160383524e-06, |
| "loss": 0.506, |
| "num_input_tokens_seen": 52112576, |
| "step": 3375 |
| }, |
| { |
| "epoch": 13.866666666666667, |
| "grad_norm": 0.83984375, |
| "learning_rate": 1.8056999500402414e-06, |
| "loss": 0.5091, |
| "num_input_tokens_seen": 52200480, |
| "step": 3380 |
| }, |
| { |
| "epoch": 13.887179487179488, |
| "grad_norm": 0.296875, |
| "learning_rate": 1.8027328365940755e-06, |
| "loss": 0.4861, |
| "num_input_tokens_seen": 52274368, |
| "step": 3385 |
| }, |
| { |
| "epoch": 13.907692307692308, |
| "grad_norm": 0.462890625, |
| "learning_rate": 1.799764487807543e-06, |
| "loss": 0.5051, |
| "num_input_tokens_seen": 52350656, |
| "step": 3390 |
| }, |
| { |
| "epoch": 13.928205128205128, |
| "grad_norm": 0.279296875, |
| "learning_rate": 1.7967949157933742e-06, |
| "loss": 0.4608, |
| "num_input_tokens_seen": 52427328, |
| "step": 3395 |
| }, |
| { |
| "epoch": 13.948717948717949, |
| "grad_norm": 0.3203125, |
| "learning_rate": 1.7938241326692907e-06, |
| "loss": 0.4719, |
| "num_input_tokens_seen": 52503840, |
| "step": 3400 |
| }, |
| { |
| "epoch": 13.96923076923077, |
| "grad_norm": 0.291015625, |
| "learning_rate": 1.7908521505579554e-06, |
| "loss": 0.5062, |
| "num_input_tokens_seen": 52577056, |
| "step": 3405 |
| }, |
| { |
| "epoch": 13.98974358974359, |
| "grad_norm": 0.310546875, |
| "learning_rate": 1.7878789815869247e-06, |
| "loss": 0.5096, |
| "num_input_tokens_seen": 52656000, |
| "step": 3410 |
| }, |
| { |
| "epoch": 14.01025641025641, |
| "grad_norm": 0.291015625, |
| "learning_rate": 1.7849046378885977e-06, |
| "loss": 0.4476, |
| "num_input_tokens_seen": 52725312, |
| "step": 3415 |
| }, |
| { |
| "epoch": 14.03076923076923, |
| "grad_norm": 0.361328125, |
| "learning_rate": 1.7819291316001679e-06, |
| "loss": 0.436, |
| "num_input_tokens_seen": 52804736, |
| "step": 3420 |
| }, |
| { |
| "epoch": 14.051282051282051, |
| "grad_norm": 0.353515625, |
| "learning_rate": 1.7789524748635717e-06, |
| "loss": 0.4761, |
| "num_input_tokens_seen": 52885056, |
| "step": 3425 |
| }, |
| { |
| "epoch": 14.071794871794872, |
| "grad_norm": 0.36328125, |
| "learning_rate": 1.775974679825441e-06, |
| "loss": 0.5039, |
| "num_input_tokens_seen": 52963136, |
| "step": 3430 |
| }, |
| { |
| "epoch": 14.092307692307692, |
| "grad_norm": 0.470703125, |
| "learning_rate": 1.7729957586370525e-06, |
| "loss": 0.5039, |
| "num_input_tokens_seen": 53049856, |
| "step": 3435 |
| }, |
| { |
| "epoch": 14.112820512820512, |
| "grad_norm": 0.45703125, |
| "learning_rate": 1.7700157234542773e-06, |
| "loss": 0.5397, |
| "num_input_tokens_seen": 53127616, |
| "step": 3440 |
| }, |
| { |
| "epoch": 14.133333333333333, |
| "grad_norm": 0.34765625, |
| "learning_rate": 1.7670345864375339e-06, |
| "loss": 0.4747, |
| "num_input_tokens_seen": 53201600, |
| "step": 3445 |
| }, |
| { |
| "epoch": 14.153846153846153, |
| "grad_norm": 0.37890625, |
| "learning_rate": 1.7640523597517357e-06, |
| "loss": 0.4582, |
| "num_input_tokens_seen": 53275520, |
| "step": 3450 |
| }, |
| { |
| "epoch": 14.174358974358974, |
| "grad_norm": 0.328125, |
| "learning_rate": 1.7610690555662435e-06, |
| "loss": 0.4747, |
| "num_input_tokens_seen": 53346720, |
| "step": 3455 |
| }, |
| { |
| "epoch": 14.194871794871794, |
| "grad_norm": 0.337890625, |
| "learning_rate": 1.7580846860548146e-06, |
| "loss": 0.4758, |
| "num_input_tokens_seen": 53420864, |
| "step": 3460 |
| }, |
| { |
| "epoch": 14.215384615384615, |
| "grad_norm": 0.380859375, |
| "learning_rate": 1.7550992633955535e-06, |
| "loss": 0.4305, |
| "num_input_tokens_seen": 53490976, |
| "step": 3465 |
| }, |
| { |
| "epoch": 14.235897435897435, |
| "grad_norm": 0.357421875, |
| "learning_rate": 1.7521127997708621e-06, |
| "loss": 0.4533, |
| "num_input_tokens_seen": 53570816, |
| "step": 3470 |
| }, |
| { |
| "epoch": 14.256410256410255, |
| "grad_norm": 0.30078125, |
| "learning_rate": 1.7491253073673903e-06, |
| "loss": 0.5019, |
| "num_input_tokens_seen": 53647072, |
| "step": 3475 |
| }, |
| { |
| "epoch": 14.276923076923078, |
| "grad_norm": 0.28515625, |
| "learning_rate": 1.7461367983759862e-06, |
| "loss": 0.4575, |
| "num_input_tokens_seen": 53727648, |
| "step": 3480 |
| }, |
| { |
| "epoch": 14.297435897435898, |
| "grad_norm": 0.28515625, |
| "learning_rate": 1.7431472849916455e-06, |
| "loss": 0.4728, |
| "num_input_tokens_seen": 53800544, |
| "step": 3485 |
| }, |
| { |
| "epoch": 14.317948717948719, |
| "grad_norm": 0.298828125, |
| "learning_rate": 1.7401567794134636e-06, |
| "loss": 0.4677, |
| "num_input_tokens_seen": 53875552, |
| "step": 3490 |
| }, |
| { |
| "epoch": 14.338461538461539, |
| "grad_norm": 0.216796875, |
| "learning_rate": 1.737165293844583e-06, |
| "loss": 0.456, |
| "num_input_tokens_seen": 53954208, |
| "step": 3495 |
| }, |
| { |
| "epoch": 14.35897435897436, |
| "grad_norm": 0.205078125, |
| "learning_rate": 1.7341728404921471e-06, |
| "loss": 0.4798, |
| "num_input_tokens_seen": 54033248, |
| "step": 3500 |
| }, |
| { |
| "epoch": 14.37948717948718, |
| "grad_norm": 0.208984375, |
| "learning_rate": 1.7311794315672477e-06, |
| "loss": 0.4166, |
| "num_input_tokens_seen": 54109440, |
| "step": 3505 |
| }, |
| { |
| "epoch": 14.4, |
| "grad_norm": 0.1953125, |
| "learning_rate": 1.7281850792848752e-06, |
| "loss": 0.4663, |
| "num_input_tokens_seen": 54186368, |
| "step": 3510 |
| }, |
| { |
| "epoch": 14.42051282051282, |
| "grad_norm": 0.1591796875, |
| "learning_rate": 1.7251897958638704e-06, |
| "loss": 0.4053, |
| "num_input_tokens_seen": 54267648, |
| "step": 3515 |
| }, |
| { |
| "epoch": 14.441025641025641, |
| "grad_norm": 0.193359375, |
| "learning_rate": 1.7221935935268735e-06, |
| "loss": 0.5342, |
| "num_input_tokens_seen": 54342304, |
| "step": 3520 |
| }, |
| { |
| "epoch": 14.461538461538462, |
| "grad_norm": 0.1455078125, |
| "learning_rate": 1.719196484500274e-06, |
| "loss": 0.4992, |
| "num_input_tokens_seen": 54423808, |
| "step": 3525 |
| }, |
| { |
| "epoch": 14.482051282051282, |
| "grad_norm": 0.1494140625, |
| "learning_rate": 1.7161984810141625e-06, |
| "loss": 0.5067, |
| "num_input_tokens_seen": 54501760, |
| "step": 3530 |
| }, |
| { |
| "epoch": 14.502564102564103, |
| "grad_norm": 0.126953125, |
| "learning_rate": 1.7131995953022776e-06, |
| "loss": 0.4286, |
| "num_input_tokens_seen": 54576512, |
| "step": 3535 |
| }, |
| { |
| "epoch": 14.523076923076923, |
| "grad_norm": 0.1611328125, |
| "learning_rate": 1.7101998396019593e-06, |
| "loss": 0.436, |
| "num_input_tokens_seen": 54649696, |
| "step": 3540 |
| }, |
| { |
| "epoch": 14.543589743589743, |
| "grad_norm": 0.138671875, |
| "learning_rate": 1.7071992261540983e-06, |
| "loss": 0.4889, |
| "num_input_tokens_seen": 54728864, |
| "step": 3545 |
| }, |
| { |
| "epoch": 14.564102564102564, |
| "grad_norm": 0.1328125, |
| "learning_rate": 1.7041977672030842e-06, |
| "loss": 0.4585, |
| "num_input_tokens_seen": 54797856, |
| "step": 3550 |
| }, |
| { |
| "epoch": 14.584615384615384, |
| "grad_norm": 0.1064453125, |
| "learning_rate": 1.7011954749967564e-06, |
| "loss": 0.4646, |
| "num_input_tokens_seen": 54875168, |
| "step": 3555 |
| }, |
| { |
| "epoch": 14.605128205128205, |
| "grad_norm": 0.1474609375, |
| "learning_rate": 1.6981923617863566e-06, |
| "loss": 0.4894, |
| "num_input_tokens_seen": 54949312, |
| "step": 3560 |
| }, |
| { |
| "epoch": 14.625641025641025, |
| "grad_norm": 0.2255859375, |
| "learning_rate": 1.6951884398264742e-06, |
| "loss": 0.5159, |
| "num_input_tokens_seen": 55024768, |
| "step": 3565 |
| }, |
| { |
| "epoch": 14.646153846153846, |
| "grad_norm": 0.150390625, |
| "learning_rate": 1.692183721375001e-06, |
| "loss": 0.4221, |
| "num_input_tokens_seen": 55100128, |
| "step": 3570 |
| }, |
| { |
| "epoch": 14.666666666666666, |
| "grad_norm": 0.1435546875, |
| "learning_rate": 1.6891782186930767e-06, |
| "loss": 0.5417, |
| "num_input_tokens_seen": 55182080, |
| "step": 3575 |
| }, |
| { |
| "epoch": 14.687179487179487, |
| "grad_norm": 0.28515625, |
| "learning_rate": 1.6861719440450437e-06, |
| "loss": 0.5072, |
| "num_input_tokens_seen": 55274048, |
| "step": 3580 |
| }, |
| { |
| "epoch": 14.707692307692307, |
| "grad_norm": 0.267578125, |
| "learning_rate": 1.6831649096983923e-06, |
| "loss": 0.5008, |
| "num_input_tokens_seen": 55347648, |
| "step": 3585 |
| }, |
| { |
| "epoch": 14.728205128205127, |
| "grad_norm": 0.33203125, |
| "learning_rate": 1.680157127923715e-06, |
| "loss": 0.4411, |
| "num_input_tokens_seen": 55418368, |
| "step": 3590 |
| }, |
| { |
| "epoch": 14.74871794871795, |
| "grad_norm": 0.74609375, |
| "learning_rate": 1.677148610994652e-06, |
| "loss": 0.4654, |
| "num_input_tokens_seen": 55490176, |
| "step": 3595 |
| }, |
| { |
| "epoch": 14.76923076923077, |
| "grad_norm": 0.70703125, |
| "learning_rate": 1.6741393711878454e-06, |
| "loss": 0.4576, |
| "num_input_tokens_seen": 55570784, |
| "step": 3600 |
| }, |
| { |
| "epoch": 14.78974358974359, |
| "grad_norm": 0.2353515625, |
| "learning_rate": 1.6711294207828852e-06, |
| "loss": 0.4488, |
| "num_input_tokens_seen": 55643936, |
| "step": 3605 |
| }, |
| { |
| "epoch": 14.810256410256411, |
| "grad_norm": 0.349609375, |
| "learning_rate": 1.6681187720622627e-06, |
| "loss": 0.5175, |
| "num_input_tokens_seen": 55727936, |
| "step": 3610 |
| }, |
| { |
| "epoch": 14.830769230769231, |
| "grad_norm": 0.484375, |
| "learning_rate": 1.6651074373113176e-06, |
| "loss": 0.4271, |
| "num_input_tokens_seen": 55804992, |
| "step": 3615 |
| }, |
| { |
| "epoch": 14.851282051282052, |
| "grad_norm": 0.3203125, |
| "learning_rate": 1.66209542881819e-06, |
| "loss": 0.4631, |
| "num_input_tokens_seen": 55878976, |
| "step": 3620 |
| }, |
| { |
| "epoch": 14.871794871794872, |
| "grad_norm": 0.26171875, |
| "learning_rate": 1.6590827588737685e-06, |
| "loss": 0.5453, |
| "num_input_tokens_seen": 55969376, |
| "step": 3625 |
| }, |
| { |
| "epoch": 14.892307692307693, |
| "grad_norm": 0.34765625, |
| "learning_rate": 1.6560694397716412e-06, |
| "loss": 0.5086, |
| "num_input_tokens_seen": 56041024, |
| "step": 3630 |
| }, |
| { |
| "epoch": 14.912820512820513, |
| "grad_norm": 0.28515625, |
| "learning_rate": 1.6530554838080458e-06, |
| "loss": 0.4602, |
| "num_input_tokens_seen": 56117152, |
| "step": 3635 |
| }, |
| { |
| "epoch": 14.933333333333334, |
| "grad_norm": 0.251953125, |
| "learning_rate": 1.6500409032818175e-06, |
| "loss": 0.5046, |
| "num_input_tokens_seen": 56191264, |
| "step": 3640 |
| }, |
| { |
| "epoch": 14.953846153846154, |
| "grad_norm": 0.271484375, |
| "learning_rate": 1.6470257104943413e-06, |
| "loss": 0.53, |
| "num_input_tokens_seen": 56279264, |
| "step": 3645 |
| }, |
| { |
| "epoch": 14.974358974358974, |
| "grad_norm": 0.341796875, |
| "learning_rate": 1.6440099177494991e-06, |
| "loss": 0.4639, |
| "num_input_tokens_seen": 56350784, |
| "step": 3650 |
| }, |
| { |
| "epoch": 14.994871794871795, |
| "grad_norm": 0.32421875, |
| "learning_rate": 1.6409935373536227e-06, |
| "loss": 0.5015, |
| "num_input_tokens_seen": 56430432, |
| "step": 3655 |
| }, |
| { |
| "epoch": 15.015384615384615, |
| "grad_norm": 0.33203125, |
| "learning_rate": 1.6379765816154413e-06, |
| "loss": 0.4503, |
| "num_input_tokens_seen": 56509056, |
| "step": 3660 |
| }, |
| { |
| "epoch": 15.035897435897436, |
| "grad_norm": 0.322265625, |
| "learning_rate": 1.634959062846031e-06, |
| "loss": 0.4688, |
| "num_input_tokens_seen": 56578016, |
| "step": 3665 |
| }, |
| { |
| "epoch": 15.056410256410256, |
| "grad_norm": 0.34375, |
| "learning_rate": 1.631940993358767e-06, |
| "loss": 0.4761, |
| "num_input_tokens_seen": 56653536, |
| "step": 3670 |
| }, |
| { |
| "epoch": 15.076923076923077, |
| "grad_norm": 0.328125, |
| "learning_rate": 1.6289223854692708e-06, |
| "loss": 0.4433, |
| "num_input_tokens_seen": 56730560, |
| "step": 3675 |
| }, |
| { |
| "epoch": 15.097435897435897, |
| "grad_norm": 0.3046875, |
| "learning_rate": 1.6259032514953601e-06, |
| "loss": 0.4315, |
| "num_input_tokens_seen": 56813312, |
| "step": 3680 |
| }, |
| { |
| "epoch": 15.117948717948718, |
| "grad_norm": 0.283203125, |
| "learning_rate": 1.6228836037570015e-06, |
| "loss": 0.4885, |
| "num_input_tokens_seen": 56891264, |
| "step": 3685 |
| }, |
| { |
| "epoch": 15.138461538461538, |
| "grad_norm": 0.400390625, |
| "learning_rate": 1.619863454576256e-06, |
| "loss": 0.4703, |
| "num_input_tokens_seen": 56964864, |
| "step": 3690 |
| }, |
| { |
| "epoch": 15.158974358974358, |
| "grad_norm": 0.322265625, |
| "learning_rate": 1.6168428162772322e-06, |
| "loss": 0.4518, |
| "num_input_tokens_seen": 57050144, |
| "step": 3695 |
| }, |
| { |
| "epoch": 15.179487179487179, |
| "grad_norm": 0.328125, |
| "learning_rate": 1.6138217011860336e-06, |
| "loss": 0.4858, |
| "num_input_tokens_seen": 57125632, |
| "step": 3700 |
| }, |
| { |
| "epoch": 15.2, |
| "grad_norm": 0.296875, |
| "learning_rate": 1.6108001216307107e-06, |
| "loss": 0.459, |
| "num_input_tokens_seen": 57204128, |
| "step": 3705 |
| }, |
| { |
| "epoch": 15.22051282051282, |
| "grad_norm": 0.33984375, |
| "learning_rate": 1.6077780899412068e-06, |
| "loss": 0.4639, |
| "num_input_tokens_seen": 57281536, |
| "step": 3710 |
| }, |
| { |
| "epoch": 15.24102564102564, |
| "grad_norm": 0.27734375, |
| "learning_rate": 1.6047556184493133e-06, |
| "loss": 0.4496, |
| "num_input_tokens_seen": 57354816, |
| "step": 3715 |
| }, |
| { |
| "epoch": 15.261538461538462, |
| "grad_norm": 0.22265625, |
| "learning_rate": 1.601732719488614e-06, |
| "loss": 0.5043, |
| "num_input_tokens_seen": 57435328, |
| "step": 3720 |
| }, |
| { |
| "epoch": 15.282051282051283, |
| "grad_norm": 0.2109375, |
| "learning_rate": 1.5987094053944384e-06, |
| "loss": 0.4357, |
| "num_input_tokens_seen": 57507424, |
| "step": 3725 |
| }, |
| { |
| "epoch": 15.302564102564103, |
| "grad_norm": 0.228515625, |
| "learning_rate": 1.5956856885038086e-06, |
| "loss": 0.5211, |
| "num_input_tokens_seen": 57586880, |
| "step": 3730 |
| }, |
| { |
| "epoch": 15.323076923076924, |
| "grad_norm": 0.1982421875, |
| "learning_rate": 1.592661581155392e-06, |
| "loss": 0.5036, |
| "num_input_tokens_seen": 57669600, |
| "step": 3735 |
| }, |
| { |
| "epoch": 15.343589743589744, |
| "grad_norm": 0.1708984375, |
| "learning_rate": 1.5896370956894477e-06, |
| "loss": 0.4751, |
| "num_input_tokens_seen": 57744608, |
| "step": 3740 |
| }, |
| { |
| "epoch": 15.364102564102565, |
| "grad_norm": 0.1533203125, |
| "learning_rate": 1.5866122444477794e-06, |
| "loss": 0.4764, |
| "num_input_tokens_seen": 57818496, |
| "step": 3745 |
| }, |
| { |
| "epoch": 15.384615384615385, |
| "grad_norm": 0.1376953125, |
| "learning_rate": 1.5835870397736817e-06, |
| "loss": 0.4551, |
| "num_input_tokens_seen": 57898432, |
| "step": 3750 |
| }, |
| { |
| "epoch": 15.405128205128205, |
| "grad_norm": 0.166015625, |
| "learning_rate": 1.5805614940118928e-06, |
| "loss": 0.5198, |
| "num_input_tokens_seen": 57974624, |
| "step": 3755 |
| }, |
| { |
| "epoch": 15.425641025641026, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 1.577535619508542e-06, |
| "loss": 0.5164, |
| "num_input_tokens_seen": 58052576, |
| "step": 3760 |
| }, |
| { |
| "epoch": 15.446153846153846, |
| "grad_norm": 0.130859375, |
| "learning_rate": 1.5745094286111004e-06, |
| "loss": 0.4699, |
| "num_input_tokens_seen": 58126592, |
| "step": 3765 |
| }, |
| { |
| "epoch": 15.466666666666667, |
| "grad_norm": 0.125, |
| "learning_rate": 1.5714829336683297e-06, |
| "loss": 0.4804, |
| "num_input_tokens_seen": 58214784, |
| "step": 3770 |
| }, |
| { |
| "epoch": 15.487179487179487, |
| "grad_norm": 0.1259765625, |
| "learning_rate": 1.5684561470302337e-06, |
| "loss": 0.4731, |
| "num_input_tokens_seen": 58284480, |
| "step": 3775 |
| }, |
| { |
| "epoch": 15.507692307692308, |
| "grad_norm": 0.1279296875, |
| "learning_rate": 1.5654290810480041e-06, |
| "loss": 0.5115, |
| "num_input_tokens_seen": 58359488, |
| "step": 3780 |
| }, |
| { |
| "epoch": 15.528205128205128, |
| "grad_norm": 0.1201171875, |
| "learning_rate": 1.562401748073975e-06, |
| "loss": 0.4713, |
| "num_input_tokens_seen": 58433632, |
| "step": 3785 |
| }, |
| { |
| "epoch": 15.548717948717949, |
| "grad_norm": 0.275390625, |
| "learning_rate": 1.5593741604615679e-06, |
| "loss": 0.5218, |
| "num_input_tokens_seen": 58526048, |
| "step": 3790 |
| }, |
| { |
| "epoch": 15.569230769230769, |
| "grad_norm": 0.15234375, |
| "learning_rate": 1.5563463305652454e-06, |
| "loss": 0.4432, |
| "num_input_tokens_seen": 58593440, |
| "step": 3795 |
| }, |
| { |
| "epoch": 15.58974358974359, |
| "grad_norm": 0.1552734375, |
| "learning_rate": 1.5533182707404563e-06, |
| "loss": 0.4793, |
| "num_input_tokens_seen": 58664832, |
| "step": 3800 |
| }, |
| { |
| "epoch": 15.61025641025641, |
| "grad_norm": 0.29296875, |
| "learning_rate": 1.550289993343591e-06, |
| "loss": 0.4287, |
| "num_input_tokens_seen": 58734976, |
| "step": 3805 |
| }, |
| { |
| "epoch": 15.63076923076923, |
| "grad_norm": 0.37109375, |
| "learning_rate": 1.547261510731924e-06, |
| "loss": 0.5701, |
| "num_input_tokens_seen": 58826304, |
| "step": 3810 |
| }, |
| { |
| "epoch": 15.65128205128205, |
| "grad_norm": 0.515625, |
| "learning_rate": 1.5442328352635706e-06, |
| "loss": 0.4858, |
| "num_input_tokens_seen": 58897216, |
| "step": 3815 |
| }, |
| { |
| "epoch": 15.671794871794871, |
| "grad_norm": 0.63671875, |
| "learning_rate": 1.54120397929743e-06, |
| "loss": 0.4541, |
| "num_input_tokens_seen": 58970880, |
| "step": 3820 |
| }, |
| { |
| "epoch": 15.692307692307692, |
| "grad_norm": 0.91015625, |
| "learning_rate": 1.5381749551931405e-06, |
| "loss": 0.5178, |
| "num_input_tokens_seen": 59049408, |
| "step": 3825 |
| }, |
| { |
| "epoch": 15.712820512820512, |
| "grad_norm": 0.298828125, |
| "learning_rate": 1.5351457753110244e-06, |
| "loss": 0.4799, |
| "num_input_tokens_seen": 59122336, |
| "step": 3830 |
| }, |
| { |
| "epoch": 15.733333333333333, |
| "grad_norm": 0.2333984375, |
| "learning_rate": 1.5321164520120421e-06, |
| "loss": 0.4284, |
| "num_input_tokens_seen": 59197600, |
| "step": 3835 |
| }, |
| { |
| "epoch": 15.753846153846155, |
| "grad_norm": 0.640625, |
| "learning_rate": 1.5290869976577366e-06, |
| "loss": 0.4343, |
| "num_input_tokens_seen": 59268224, |
| "step": 3840 |
| }, |
| { |
| "epoch": 15.774358974358975, |
| "grad_norm": 0.279296875, |
| "learning_rate": 1.5260574246101875e-06, |
| "loss": 0.4371, |
| "num_input_tokens_seen": 59341408, |
| "step": 3845 |
| }, |
| { |
| "epoch": 15.794871794871796, |
| "grad_norm": 0.27734375, |
| "learning_rate": 1.5230277452319585e-06, |
| "loss": 0.5017, |
| "num_input_tokens_seen": 59423648, |
| "step": 3850 |
| }, |
| { |
| "epoch": 15.815384615384616, |
| "grad_norm": 0.35546875, |
| "learning_rate": 1.519997971886046e-06, |
| "loss": 0.4473, |
| "num_input_tokens_seen": 59495872, |
| "step": 3855 |
| }, |
| { |
| "epoch": 15.835897435897436, |
| "grad_norm": 0.31640625, |
| "learning_rate": 1.5169681169358314e-06, |
| "loss": 0.4693, |
| "num_input_tokens_seen": 59574880, |
| "step": 3860 |
| }, |
| { |
| "epoch": 15.856410256410257, |
| "grad_norm": 0.3046875, |
| "learning_rate": 1.513938192745028e-06, |
| "loss": 0.4955, |
| "num_input_tokens_seen": 59657472, |
| "step": 3865 |
| }, |
| { |
| "epoch": 15.876923076923077, |
| "grad_norm": 0.337890625, |
| "learning_rate": 1.5109082116776328e-06, |
| "loss": 0.4219, |
| "num_input_tokens_seen": 59733888, |
| "step": 3870 |
| }, |
| { |
| "epoch": 15.897435897435898, |
| "grad_norm": 0.423828125, |
| "learning_rate": 1.5078781860978732e-06, |
| "loss": 0.4462, |
| "num_input_tokens_seen": 59811392, |
| "step": 3875 |
| }, |
| { |
| "epoch": 15.917948717948718, |
| "grad_norm": 0.359375, |
| "learning_rate": 1.5048481283701594e-06, |
| "loss": 0.4938, |
| "num_input_tokens_seen": 59886784, |
| "step": 3880 |
| }, |
| { |
| "epoch": 15.938461538461539, |
| "grad_norm": 0.390625, |
| "learning_rate": 1.501818050859033e-06, |
| "loss": 0.4465, |
| "num_input_tokens_seen": 59959072, |
| "step": 3885 |
| }, |
| { |
| "epoch": 15.95897435897436, |
| "grad_norm": 0.408203125, |
| "learning_rate": 1.498787965929116e-06, |
| "loss": 0.462, |
| "num_input_tokens_seen": 60032832, |
| "step": 3890 |
| }, |
| { |
| "epoch": 15.97948717948718, |
| "grad_norm": 0.28515625, |
| "learning_rate": 1.49575788594506e-06, |
| "loss": 0.5279, |
| "num_input_tokens_seen": 60119456, |
| "step": 3895 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.30859375, |
| "learning_rate": 1.4927278232714975e-06, |
| "loss": 0.4908, |
| "num_input_tokens_seen": 60204448, |
| "step": 3900 |
| }, |
| { |
| "epoch": 16.02051282051282, |
| "grad_norm": 0.37109375, |
| "learning_rate": 1.4896977902729893e-06, |
| "loss": 0.4607, |
| "num_input_tokens_seen": 60279104, |
| "step": 3905 |
| }, |
| { |
| "epoch": 16.04102564102564, |
| "grad_norm": 0.30859375, |
| "learning_rate": 1.4866677993139761e-06, |
| "loss": 0.4405, |
| "num_input_tokens_seen": 60349504, |
| "step": 3910 |
| }, |
| { |
| "epoch": 16.06153846153846, |
| "grad_norm": 0.34375, |
| "learning_rate": 1.4836378627587266e-06, |
| "loss": 0.4744, |
| "num_input_tokens_seen": 60420640, |
| "step": 3915 |
| }, |
| { |
| "epoch": 16.08205128205128, |
| "grad_norm": 0.32421875, |
| "learning_rate": 1.4806079929712874e-06, |
| "loss": 0.4868, |
| "num_input_tokens_seen": 60497728, |
| "step": 3920 |
| }, |
| { |
| "epoch": 16.102564102564102, |
| "grad_norm": 0.341796875, |
| "learning_rate": 1.477578202315433e-06, |
| "loss": 0.5095, |
| "num_input_tokens_seen": 60579008, |
| "step": 3925 |
| }, |
| { |
| "epoch": 16.123076923076923, |
| "grad_norm": 0.271484375, |
| "learning_rate": 1.4745485031546143e-06, |
| "loss": 0.5101, |
| "num_input_tokens_seen": 60657088, |
| "step": 3930 |
| }, |
| { |
| "epoch": 16.143589743589743, |
| "grad_norm": 0.28515625, |
| "learning_rate": 1.4715189078519094e-06, |
| "loss": 0.4938, |
| "num_input_tokens_seen": 60734560, |
| "step": 3935 |
| }, |
| { |
| "epoch": 16.164102564102564, |
| "grad_norm": 0.265625, |
| "learning_rate": 1.468489428769973e-06, |
| "loss": 0.4785, |
| "num_input_tokens_seen": 60812960, |
| "step": 3940 |
| }, |
| { |
| "epoch": 16.184615384615384, |
| "grad_norm": 0.2138671875, |
| "learning_rate": 1.4654600782709843e-06, |
| "loss": 0.4953, |
| "num_input_tokens_seen": 60892768, |
| "step": 3945 |
| }, |
| { |
| "epoch": 16.205128205128204, |
| "grad_norm": 0.208984375, |
| "learning_rate": 1.4624308687165985e-06, |
| "loss": 0.4472, |
| "num_input_tokens_seen": 60964096, |
| "step": 3950 |
| }, |
| { |
| "epoch": 16.225641025641025, |
| "grad_norm": 0.1943359375, |
| "learning_rate": 1.4594018124678965e-06, |
| "loss": 0.4191, |
| "num_input_tokens_seen": 61034304, |
| "step": 3955 |
| }, |
| { |
| "epoch": 16.246153846153845, |
| "grad_norm": 0.181640625, |
| "learning_rate": 1.4563729218853329e-06, |
| "loss": 0.465, |
| "num_input_tokens_seen": 61113024, |
| "step": 3960 |
| }, |
| { |
| "epoch": 16.266666666666666, |
| "grad_norm": 0.1787109375, |
| "learning_rate": 1.4533442093286853e-06, |
| "loss": 0.4703, |
| "num_input_tokens_seen": 61184256, |
| "step": 3965 |
| }, |
| { |
| "epoch": 16.287179487179486, |
| "grad_norm": 0.1416015625, |
| "learning_rate": 1.4503156871570062e-06, |
| "loss": 0.4773, |
| "num_input_tokens_seen": 61262208, |
| "step": 3970 |
| }, |
| { |
| "epoch": 16.307692307692307, |
| "grad_norm": 0.1630859375, |
| "learning_rate": 1.4472873677285706e-06, |
| "loss": 0.4172, |
| "num_input_tokens_seen": 61334560, |
| "step": 3975 |
| }, |
| { |
| "epoch": 16.328205128205127, |
| "grad_norm": 0.1484375, |
| "learning_rate": 1.4442592634008266e-06, |
| "loss": 0.4326, |
| "num_input_tokens_seen": 61405888, |
| "step": 3980 |
| }, |
| { |
| "epoch": 16.348717948717947, |
| "grad_norm": 0.1240234375, |
| "learning_rate": 1.4412313865303438e-06, |
| "loss": 0.5303, |
| "num_input_tokens_seen": 61489280, |
| "step": 3985 |
| }, |
| { |
| "epoch": 16.369230769230768, |
| "grad_norm": 0.16015625, |
| "learning_rate": 1.4382037494727649e-06, |
| "loss": 0.4726, |
| "num_input_tokens_seen": 61562912, |
| "step": 3990 |
| }, |
| { |
| "epoch": 16.38974358974359, |
| "grad_norm": 0.1328125, |
| "learning_rate": 1.435176364582752e-06, |
| "loss": 0.458, |
| "num_input_tokens_seen": 61652064, |
| "step": 3995 |
| }, |
| { |
| "epoch": 16.41025641025641, |
| "grad_norm": 0.1171875, |
| "learning_rate": 1.4321492442139405e-06, |
| "loss": 0.5266, |
| "num_input_tokens_seen": 61737536, |
| "step": 4000 |
| }, |
| { |
| "epoch": 16.43076923076923, |
| "grad_norm": 0.158203125, |
| "learning_rate": 1.4291224007188849e-06, |
| "loss": 0.4394, |
| "num_input_tokens_seen": 61811840, |
| "step": 4005 |
| }, |
| { |
| "epoch": 16.45128205128205, |
| "grad_norm": 0.142578125, |
| "learning_rate": 1.4260958464490104e-06, |
| "loss": 0.4474, |
| "num_input_tokens_seen": 61884288, |
| "step": 4010 |
| }, |
| { |
| "epoch": 16.47179487179487, |
| "grad_norm": 0.22265625, |
| "learning_rate": 1.4230695937545616e-06, |
| "loss": 0.5, |
| "num_input_tokens_seen": 61958944, |
| "step": 4015 |
| }, |
| { |
| "epoch": 16.49230769230769, |
| "grad_norm": 0.1455078125, |
| "learning_rate": 1.420043654984553e-06, |
| "loss": 0.4766, |
| "num_input_tokens_seen": 62038016, |
| "step": 4020 |
| }, |
| { |
| "epoch": 16.51282051282051, |
| "grad_norm": 0.2890625, |
| "learning_rate": 1.4170180424867176e-06, |
| "loss": 0.4593, |
| "num_input_tokens_seen": 62107616, |
| "step": 4025 |
| }, |
| { |
| "epoch": 16.533333333333335, |
| "grad_norm": 0.359375, |
| "learning_rate": 1.4139927686074577e-06, |
| "loss": 0.4446, |
| "num_input_tokens_seen": 62188352, |
| "step": 4030 |
| }, |
| { |
| "epoch": 16.553846153846155, |
| "grad_norm": 0.259765625, |
| "learning_rate": 1.4109678456917926e-06, |
| "loss": 0.4658, |
| "num_input_tokens_seen": 62259456, |
| "step": 4035 |
| }, |
| { |
| "epoch": 16.574358974358976, |
| "grad_norm": 0.50390625, |
| "learning_rate": 1.4079432860833104e-06, |
| "loss": 0.5363, |
| "num_input_tokens_seen": 62356448, |
| "step": 4040 |
| }, |
| { |
| "epoch": 16.594871794871796, |
| "grad_norm": 0.78515625, |
| "learning_rate": 1.4049191021241176e-06, |
| "loss": 0.5006, |
| "num_input_tokens_seen": 62429824, |
| "step": 4045 |
| }, |
| { |
| "epoch": 16.615384615384617, |
| "grad_norm": 0.66796875, |
| "learning_rate": 1.4018953061547853e-06, |
| "loss": 0.4638, |
| "num_input_tokens_seen": 62514528, |
| "step": 4050 |
| }, |
| { |
| "epoch": 16.635897435897437, |
| "grad_norm": 0.267578125, |
| "learning_rate": 1.3988719105143038e-06, |
| "loss": 0.4413, |
| "num_input_tokens_seen": 62593472, |
| "step": 4055 |
| }, |
| { |
| "epoch": 16.656410256410258, |
| "grad_norm": 0.48046875, |
| "learning_rate": 1.395848927540028e-06, |
| "loss": 0.4506, |
| "num_input_tokens_seen": 62671520, |
| "step": 4060 |
| }, |
| { |
| "epoch": 16.676923076923078, |
| "grad_norm": 0.5078125, |
| "learning_rate": 1.39282636956763e-06, |
| "loss": 0.4616, |
| "num_input_tokens_seen": 62749856, |
| "step": 4065 |
| }, |
| { |
| "epoch": 16.6974358974359, |
| "grad_norm": 0.32421875, |
| "learning_rate": 1.3898042489310471e-06, |
| "loss": 0.456, |
| "num_input_tokens_seen": 62823616, |
| "step": 4070 |
| }, |
| { |
| "epoch": 16.71794871794872, |
| "grad_norm": 0.357421875, |
| "learning_rate": 1.3867825779624325e-06, |
| "loss": 0.45, |
| "num_input_tokens_seen": 62908416, |
| "step": 4075 |
| }, |
| { |
| "epoch": 16.73846153846154, |
| "grad_norm": 0.41015625, |
| "learning_rate": 1.3837613689921037e-06, |
| "loss": 0.4563, |
| "num_input_tokens_seen": 62978016, |
| "step": 4080 |
| }, |
| { |
| "epoch": 16.75897435897436, |
| "grad_norm": 0.259765625, |
| "learning_rate": 1.380740634348494e-06, |
| "loss": 0.4952, |
| "num_input_tokens_seen": 63065952, |
| "step": 4085 |
| }, |
| { |
| "epoch": 16.77948717948718, |
| "grad_norm": 0.3359375, |
| "learning_rate": 1.3777203863580993e-06, |
| "loss": 0.4327, |
| "num_input_tokens_seen": 63141792, |
| "step": 4090 |
| }, |
| { |
| "epoch": 16.8, |
| "grad_norm": 0.361328125, |
| "learning_rate": 1.3747006373454321e-06, |
| "loss": 0.5152, |
| "num_input_tokens_seen": 63223520, |
| "step": 4095 |
| }, |
| { |
| "epoch": 16.82051282051282, |
| "grad_norm": 0.326171875, |
| "learning_rate": 1.3716813996329669e-06, |
| "loss": 0.4952, |
| "num_input_tokens_seen": 63297696, |
| "step": 4100 |
| }, |
| { |
| "epoch": 16.84102564102564, |
| "grad_norm": 0.4609375, |
| "learning_rate": 1.3686626855410929e-06, |
| "loss": 0.4873, |
| "num_input_tokens_seen": 63378304, |
| "step": 4105 |
| }, |
| { |
| "epoch": 16.861538461538462, |
| "grad_norm": 0.388671875, |
| "learning_rate": 1.3656445073880615e-06, |
| "loss": 0.4461, |
| "num_input_tokens_seen": 63454400, |
| "step": 4110 |
| }, |
| { |
| "epoch": 16.882051282051282, |
| "grad_norm": 0.3671875, |
| "learning_rate": 1.3626268774899381e-06, |
| "loss": 0.4612, |
| "num_input_tokens_seen": 63526400, |
| "step": 4115 |
| }, |
| { |
| "epoch": 16.902564102564103, |
| "grad_norm": 0.33984375, |
| "learning_rate": 1.3596098081605505e-06, |
| "loss": 0.5061, |
| "num_input_tokens_seen": 63612448, |
| "step": 4120 |
| }, |
| { |
| "epoch": 16.923076923076923, |
| "grad_norm": 0.34765625, |
| "learning_rate": 1.3565933117114385e-06, |
| "loss": 0.486, |
| "num_input_tokens_seen": 63693248, |
| "step": 4125 |
| }, |
| { |
| "epoch": 16.943589743589744, |
| "grad_norm": 0.35546875, |
| "learning_rate": 1.3535774004518057e-06, |
| "loss": 0.4772, |
| "num_input_tokens_seen": 63765504, |
| "step": 4130 |
| }, |
| { |
| "epoch": 16.964102564102564, |
| "grad_norm": 0.330078125, |
| "learning_rate": 1.3505620866884666e-06, |
| "loss": 0.457, |
| "num_input_tokens_seen": 63839616, |
| "step": 4135 |
| }, |
| { |
| "epoch": 16.984615384615385, |
| "grad_norm": 0.341796875, |
| "learning_rate": 1.347547382725797e-06, |
| "loss": 0.4961, |
| "num_input_tokens_seen": 63924736, |
| "step": 4140 |
| }, |
| { |
| "epoch": 17.005128205128205, |
| "grad_norm": 0.349609375, |
| "learning_rate": 1.344533300865686e-06, |
| "loss": 0.5218, |
| "num_input_tokens_seen": 64000256, |
| "step": 4145 |
| }, |
| { |
| "epoch": 17.025641025641026, |
| "grad_norm": 0.44921875, |
| "learning_rate": 1.3415198534074823e-06, |
| "loss": 0.4501, |
| "num_input_tokens_seen": 64077472, |
| "step": 4150 |
| }, |
| { |
| "epoch": 17.046153846153846, |
| "grad_norm": 0.2578125, |
| "learning_rate": 1.3385070526479475e-06, |
| "loss": 0.4704, |
| "num_input_tokens_seen": 64157024, |
| "step": 4155 |
| }, |
| { |
| "epoch": 17.066666666666666, |
| "grad_norm": 0.2734375, |
| "learning_rate": 1.3354949108812026e-06, |
| "loss": 0.485, |
| "num_input_tokens_seen": 64226656, |
| "step": 4160 |
| }, |
| { |
| "epoch": 17.087179487179487, |
| "grad_norm": 0.2236328125, |
| "learning_rate": 1.3324834403986815e-06, |
| "loss": 0.4316, |
| "num_input_tokens_seen": 64302816, |
| "step": 4165 |
| }, |
| { |
| "epoch": 17.107692307692307, |
| "grad_norm": 0.2373046875, |
| "learning_rate": 1.3294726534890766e-06, |
| "loss": 0.4781, |
| "num_input_tokens_seen": 64371840, |
| "step": 4170 |
| }, |
| { |
| "epoch": 17.128205128205128, |
| "grad_norm": 0.189453125, |
| "learning_rate": 1.326462562438293e-06, |
| "loss": 0.4331, |
| "num_input_tokens_seen": 64451776, |
| "step": 4175 |
| }, |
| { |
| "epoch": 17.148717948717948, |
| "grad_norm": 0.2080078125, |
| "learning_rate": 1.3234531795293945e-06, |
| "loss": 0.4754, |
| "num_input_tokens_seen": 64523712, |
| "step": 4180 |
| }, |
| { |
| "epoch": 17.16923076923077, |
| "grad_norm": 0.1904296875, |
| "learning_rate": 1.3204445170425565e-06, |
| "loss": 0.4983, |
| "num_input_tokens_seen": 64594272, |
| "step": 4185 |
| }, |
| { |
| "epoch": 17.18974358974359, |
| "grad_norm": 0.1650390625, |
| "learning_rate": 1.3174365872550138e-06, |
| "loss": 0.4852, |
| "num_input_tokens_seen": 64677280, |
| "step": 4190 |
| }, |
| { |
| "epoch": 17.21025641025641, |
| "grad_norm": 0.1591796875, |
| "learning_rate": 1.3144294024410122e-06, |
| "loss": 0.4843, |
| "num_input_tokens_seen": 64758080, |
| "step": 4195 |
| }, |
| { |
| "epoch": 17.23076923076923, |
| "grad_norm": 0.1435546875, |
| "learning_rate": 1.3114229748717563e-06, |
| "loss": 0.4564, |
| "num_input_tokens_seen": 64830848, |
| "step": 4200 |
| }, |
| { |
| "epoch": 17.25128205128205, |
| "grad_norm": 0.1474609375, |
| "learning_rate": 1.308417316815362e-06, |
| "loss": 0.4432, |
| "num_input_tokens_seen": 64907296, |
| "step": 4205 |
| }, |
| { |
| "epoch": 17.27179487179487, |
| "grad_norm": 0.134765625, |
| "learning_rate": 1.3054124405368036e-06, |
| "loss": 0.4901, |
| "num_input_tokens_seen": 64987392, |
| "step": 4210 |
| }, |
| { |
| "epoch": 17.29230769230769, |
| "grad_norm": 0.1318359375, |
| "learning_rate": 1.3024083582978668e-06, |
| "loss": 0.5076, |
| "num_input_tokens_seen": 65077408, |
| "step": 4215 |
| }, |
| { |
| "epoch": 17.31282051282051, |
| "grad_norm": 0.12158203125, |
| "learning_rate": 1.2994050823570968e-06, |
| "loss": 0.4818, |
| "num_input_tokens_seen": 65159104, |
| "step": 4220 |
| }, |
| { |
| "epoch": 17.333333333333332, |
| "grad_norm": 0.099609375, |
| "learning_rate": 1.2964026249697475e-06, |
| "loss": 0.4525, |
| "num_input_tokens_seen": 65242816, |
| "step": 4225 |
| }, |
| { |
| "epoch": 17.353846153846153, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 1.293400998387734e-06, |
| "loss": 0.4444, |
| "num_input_tokens_seen": 65317376, |
| "step": 4230 |
| }, |
| { |
| "epoch": 17.374358974358973, |
| "grad_norm": 0.2314453125, |
| "learning_rate": 1.2904002148595797e-06, |
| "loss": 0.4897, |
| "num_input_tokens_seen": 65391264, |
| "step": 4235 |
| }, |
| { |
| "epoch": 17.394871794871793, |
| "grad_norm": 0.208984375, |
| "learning_rate": 1.2874002866303695e-06, |
| "loss": 0.5116, |
| "num_input_tokens_seen": 65467744, |
| "step": 4240 |
| }, |
| { |
| "epoch": 17.415384615384614, |
| "grad_norm": 0.1298828125, |
| "learning_rate": 1.2844012259416965e-06, |
| "loss": 0.4498, |
| "num_input_tokens_seen": 65535680, |
| "step": 4245 |
| }, |
| { |
| "epoch": 17.435897435897434, |
| "grad_norm": 0.2890625, |
| "learning_rate": 1.2814030450316151e-06, |
| "loss": 0.4984, |
| "num_input_tokens_seen": 65611680, |
| "step": 4250 |
| }, |
| { |
| "epoch": 17.456410256410255, |
| "grad_norm": 0.318359375, |
| "learning_rate": 1.2784057561345885e-06, |
| "loss": 0.5276, |
| "num_input_tokens_seen": 65684160, |
| "step": 4255 |
| }, |
| { |
| "epoch": 17.476923076923075, |
| "grad_norm": 0.291015625, |
| "learning_rate": 1.2754093714814407e-06, |
| "loss": 0.4434, |
| "num_input_tokens_seen": 65755104, |
| "step": 4260 |
| }, |
| { |
| "epoch": 17.4974358974359, |
| "grad_norm": 0.59765625, |
| "learning_rate": 1.2724139032993057e-06, |
| "loss": 0.4743, |
| "num_input_tokens_seen": 65835072, |
| "step": 4265 |
| }, |
| { |
| "epoch": 17.51794871794872, |
| "grad_norm": 0.89453125, |
| "learning_rate": 1.269419363811577e-06, |
| "loss": 0.4691, |
| "num_input_tokens_seen": 65916704, |
| "step": 4270 |
| }, |
| { |
| "epoch": 17.53846153846154, |
| "grad_norm": 0.6484375, |
| "learning_rate": 1.2664257652378598e-06, |
| "loss": 0.5129, |
| "num_input_tokens_seen": 65989696, |
| "step": 4275 |
| }, |
| { |
| "epoch": 17.55897435897436, |
| "grad_norm": 0.259765625, |
| "learning_rate": 1.2634331197939183e-06, |
| "loss": 0.4868, |
| "num_input_tokens_seen": 66071744, |
| "step": 4280 |
| }, |
| { |
| "epoch": 17.57948717948718, |
| "grad_norm": 0.54296875, |
| "learning_rate": 1.2604414396916286e-06, |
| "loss": 0.489, |
| "num_input_tokens_seen": 66153024, |
| "step": 4285 |
| }, |
| { |
| "epoch": 17.6, |
| "grad_norm": 0.55078125, |
| "learning_rate": 1.2574507371389267e-06, |
| "loss": 0.4855, |
| "num_input_tokens_seen": 66220384, |
| "step": 4290 |
| }, |
| { |
| "epoch": 17.620512820512822, |
| "grad_norm": 0.298828125, |
| "learning_rate": 1.25446102433976e-06, |
| "loss": 0.4791, |
| "num_input_tokens_seen": 66298912, |
| "step": 4295 |
| }, |
| { |
| "epoch": 17.641025641025642, |
| "grad_norm": 0.263671875, |
| "learning_rate": 1.2514723134940365e-06, |
| "loss": 0.4563, |
| "num_input_tokens_seen": 66373120, |
| "step": 4300 |
| }, |
| { |
| "epoch": 17.661538461538463, |
| "grad_norm": 0.26171875, |
| "learning_rate": 1.2484846167975767e-06, |
| "loss": 0.4577, |
| "num_input_tokens_seen": 66452096, |
| "step": 4305 |
| }, |
| { |
| "epoch": 17.682051282051283, |
| "grad_norm": 0.302734375, |
| "learning_rate": 1.2454979464420624e-06, |
| "loss": 0.4875, |
| "num_input_tokens_seen": 66530784, |
| "step": 4310 |
| }, |
| { |
| "epoch": 17.702564102564104, |
| "grad_norm": 0.34375, |
| "learning_rate": 1.2425123146149863e-06, |
| "loss": 0.4551, |
| "num_input_tokens_seen": 66607264, |
| "step": 4315 |
| }, |
| { |
| "epoch": 17.723076923076924, |
| "grad_norm": 0.328125, |
| "learning_rate": 1.2395277334996047e-06, |
| "loss": 0.5378, |
| "num_input_tokens_seen": 66692608, |
| "step": 4320 |
| }, |
| { |
| "epoch": 17.743589743589745, |
| "grad_norm": 0.341796875, |
| "learning_rate": 1.2365442152748846e-06, |
| "loss": 0.4518, |
| "num_input_tokens_seen": 66773504, |
| "step": 4325 |
| }, |
| { |
| "epoch": 17.764102564102565, |
| "grad_norm": 0.625, |
| "learning_rate": 1.2335617721154577e-06, |
| "loss": 0.4412, |
| "num_input_tokens_seen": 66844928, |
| "step": 4330 |
| }, |
| { |
| "epoch": 17.784615384615385, |
| "grad_norm": 0.443359375, |
| "learning_rate": 1.2305804161915671e-06, |
| "loss": 0.5214, |
| "num_input_tokens_seen": 66918080, |
| "step": 4335 |
| }, |
| { |
| "epoch": 17.805128205128206, |
| "grad_norm": 0.32421875, |
| "learning_rate": 1.2276001596690205e-06, |
| "loss": 0.47, |
| "num_input_tokens_seen": 66988992, |
| "step": 4340 |
| }, |
| { |
| "epoch": 17.825641025641026, |
| "grad_norm": 0.419921875, |
| "learning_rate": 1.2246210147091382e-06, |
| "loss": 0.4545, |
| "num_input_tokens_seen": 67068288, |
| "step": 4345 |
| }, |
| { |
| "epoch": 17.846153846153847, |
| "grad_norm": 0.3125, |
| "learning_rate": 1.2216429934687062e-06, |
| "loss": 0.4574, |
| "num_input_tokens_seen": 67142560, |
| "step": 4350 |
| }, |
| { |
| "epoch": 17.866666666666667, |
| "grad_norm": 0.40234375, |
| "learning_rate": 1.2186661080999234e-06, |
| "loss": 0.4717, |
| "num_input_tokens_seen": 67222560, |
| "step": 4355 |
| }, |
| { |
| "epoch": 17.887179487179488, |
| "grad_norm": 0.318359375, |
| "learning_rate": 1.2156903707503544e-06, |
| "loss": 0.4662, |
| "num_input_tokens_seen": 67301760, |
| "step": 4360 |
| }, |
| { |
| "epoch": 17.907692307692308, |
| "grad_norm": 0.345703125, |
| "learning_rate": 1.2127157935628789e-06, |
| "loss": 0.4958, |
| "num_input_tokens_seen": 67381856, |
| "step": 4365 |
| }, |
| { |
| "epoch": 17.92820512820513, |
| "grad_norm": 0.318359375, |
| "learning_rate": 1.2097423886756433e-06, |
| "loss": 0.5327, |
| "num_input_tokens_seen": 67467968, |
| "step": 4370 |
| }, |
| { |
| "epoch": 17.94871794871795, |
| "grad_norm": 0.248046875, |
| "learning_rate": 1.2067701682220084e-06, |
| "loss": 0.4606, |
| "num_input_tokens_seen": 67548672, |
| "step": 4375 |
| }, |
| { |
| "epoch": 17.96923076923077, |
| "grad_norm": 0.255859375, |
| "learning_rate": 1.2037991443305043e-06, |
| "loss": 0.4451, |
| "num_input_tokens_seen": 67625248, |
| "step": 4380 |
| }, |
| { |
| "epoch": 17.98974358974359, |
| "grad_norm": 0.28125, |
| "learning_rate": 1.2008293291247754e-06, |
| "loss": 0.4416, |
| "num_input_tokens_seen": 67695808, |
| "step": 4385 |
| }, |
| { |
| "epoch": 18.01025641025641, |
| "grad_norm": 0.23046875, |
| "learning_rate": 1.1978607347235367e-06, |
| "loss": 0.4741, |
| "num_input_tokens_seen": 67774400, |
| "step": 4390 |
| }, |
| { |
| "epoch": 18.03076923076923, |
| "grad_norm": 0.236328125, |
| "learning_rate": 1.1948933732405205e-06, |
| "loss": 0.446, |
| "num_input_tokens_seen": 67846848, |
| "step": 4395 |
| }, |
| { |
| "epoch": 18.05128205128205, |
| "grad_norm": 0.2060546875, |
| "learning_rate": 1.191927256784427e-06, |
| "loss": 0.4315, |
| "num_input_tokens_seen": 67917440, |
| "step": 4400 |
| }, |
| { |
| "epoch": 18.07179487179487, |
| "grad_norm": 0.181640625, |
| "learning_rate": 1.1889623974588772e-06, |
| "loss": 0.4055, |
| "num_input_tokens_seen": 67990656, |
| "step": 4405 |
| }, |
| { |
| "epoch": 18.092307692307692, |
| "grad_norm": 0.1591796875, |
| "learning_rate": 1.185998807362362e-06, |
| "loss": 0.499, |
| "num_input_tokens_seen": 68067872, |
| "step": 4410 |
| }, |
| { |
| "epoch": 18.112820512820512, |
| "grad_norm": 0.162109375, |
| "learning_rate": 1.1830364985881924e-06, |
| "loss": 0.481, |
| "num_input_tokens_seen": 68145632, |
| "step": 4415 |
| }, |
| { |
| "epoch": 18.133333333333333, |
| "grad_norm": 0.1650390625, |
| "learning_rate": 1.1800754832244515e-06, |
| "loss": 0.4931, |
| "num_input_tokens_seen": 68221472, |
| "step": 4420 |
| }, |
| { |
| "epoch": 18.153846153846153, |
| "grad_norm": 0.1513671875, |
| "learning_rate": 1.1771157733539442e-06, |
| "loss": 0.4377, |
| "num_input_tokens_seen": 68292352, |
| "step": 4425 |
| }, |
| { |
| "epoch": 18.174358974358974, |
| "grad_norm": 0.150390625, |
| "learning_rate": 1.174157381054148e-06, |
| "loss": 0.5265, |
| "num_input_tokens_seen": 68374880, |
| "step": 4430 |
| }, |
| { |
| "epoch": 18.194871794871794, |
| "grad_norm": 0.1416015625, |
| "learning_rate": 1.1712003183971644e-06, |
| "loss": 0.5103, |
| "num_input_tokens_seen": 68457280, |
| "step": 4435 |
| }, |
| { |
| "epoch": 18.215384615384615, |
| "grad_norm": 0.119140625, |
| "learning_rate": 1.1682445974496686e-06, |
| "loss": 0.5133, |
| "num_input_tokens_seen": 68540224, |
| "step": 4440 |
| }, |
| { |
| "epoch": 18.235897435897435, |
| "grad_norm": 0.11865234375, |
| "learning_rate": 1.1652902302728607e-06, |
| "loss": 0.4805, |
| "num_input_tokens_seen": 68621056, |
| "step": 4445 |
| }, |
| { |
| "epoch": 18.256410256410255, |
| "grad_norm": 0.12353515625, |
| "learning_rate": 1.1623372289224172e-06, |
| "loss": 0.4863, |
| "num_input_tokens_seen": 68697440, |
| "step": 4450 |
| }, |
| { |
| "epoch": 18.276923076923076, |
| "grad_norm": 0.125, |
| "learning_rate": 1.1593856054484403e-06, |
| "loss": 0.4685, |
| "num_input_tokens_seen": 68778944, |
| "step": 4455 |
| }, |
| { |
| "epoch": 18.297435897435896, |
| "grad_norm": 0.1982421875, |
| "learning_rate": 1.156435371895411e-06, |
| "loss": 0.4934, |
| "num_input_tokens_seen": 68859712, |
| "step": 4460 |
| }, |
| { |
| "epoch": 18.317948717948717, |
| "grad_norm": 0.1962890625, |
| "learning_rate": 1.1534865403021366e-06, |
| "loss": 0.4439, |
| "num_input_tokens_seen": 68932512, |
| "step": 4465 |
| }, |
| { |
| "epoch": 18.338461538461537, |
| "grad_norm": 0.15625, |
| "learning_rate": 1.1505391227017046e-06, |
| "loss": 0.4295, |
| "num_input_tokens_seen": 69006080, |
| "step": 4470 |
| }, |
| { |
| "epoch": 18.358974358974358, |
| "grad_norm": 0.29296875, |
| "learning_rate": 1.1475931311214338e-06, |
| "loss": 0.4644, |
| "num_input_tokens_seen": 69081984, |
| "step": 4475 |
| }, |
| { |
| "epoch": 18.379487179487178, |
| "grad_norm": 0.2421875, |
| "learning_rate": 1.144648577582821e-06, |
| "loss": 0.4899, |
| "num_input_tokens_seen": 69158240, |
| "step": 4480 |
| }, |
| { |
| "epoch": 18.4, |
| "grad_norm": 0.3671875, |
| "learning_rate": 1.141705474101498e-06, |
| "loss": 0.4763, |
| "num_input_tokens_seen": 69241184, |
| "step": 4485 |
| }, |
| { |
| "epoch": 18.42051282051282, |
| "grad_norm": 0.5859375, |
| "learning_rate": 1.138763832687177e-06, |
| "loss": 0.4784, |
| "num_input_tokens_seen": 69326112, |
| "step": 4490 |
| }, |
| { |
| "epoch": 18.44102564102564, |
| "grad_norm": 0.765625, |
| "learning_rate": 1.1358236653436052e-06, |
| "loss": 0.4624, |
| "num_input_tokens_seen": 69400832, |
| "step": 4495 |
| }, |
| { |
| "epoch": 18.46153846153846, |
| "grad_norm": 0.8984375, |
| "learning_rate": 1.1328849840685143e-06, |
| "loss": 0.4523, |
| "num_input_tokens_seen": 69478464, |
| "step": 4500 |
| }, |
| { |
| "epoch": 18.48205128205128, |
| "grad_norm": 0.43359375, |
| "learning_rate": 1.1299478008535726e-06, |
| "loss": 0.5372, |
| "num_input_tokens_seen": 69559712, |
| "step": 4505 |
| }, |
| { |
| "epoch": 18.5025641025641, |
| "grad_norm": 0.458984375, |
| "learning_rate": 1.1270121276843342e-06, |
| "loss": 0.4224, |
| "num_input_tokens_seen": 69638528, |
| "step": 4510 |
| }, |
| { |
| "epoch": 18.523076923076925, |
| "grad_norm": 0.23828125, |
| "learning_rate": 1.1240779765401926e-06, |
| "loss": 0.4726, |
| "num_input_tokens_seen": 69719264, |
| "step": 4515 |
| }, |
| { |
| "epoch": 18.543589743589745, |
| "grad_norm": 0.30078125, |
| "learning_rate": 1.1211453593943293e-06, |
| "loss": 0.4407, |
| "num_input_tokens_seen": 69798432, |
| "step": 4520 |
| }, |
| { |
| "epoch": 18.564102564102566, |
| "grad_norm": 0.310546875, |
| "learning_rate": 1.118214288213667e-06, |
| "loss": 0.4594, |
| "num_input_tokens_seen": 69869984, |
| "step": 4525 |
| }, |
| { |
| "epoch": 18.584615384615386, |
| "grad_norm": 0.318359375, |
| "learning_rate": 1.1152847749588186e-06, |
| "loss": 0.5029, |
| "num_input_tokens_seen": 69949088, |
| "step": 4530 |
| }, |
| { |
| "epoch": 18.605128205128207, |
| "grad_norm": 0.6796875, |
| "learning_rate": 1.1123568315840419e-06, |
| "loss": 0.4386, |
| "num_input_tokens_seen": 70023904, |
| "step": 4535 |
| }, |
| { |
| "epoch": 18.625641025641027, |
| "grad_norm": 0.5625, |
| "learning_rate": 1.1094304700371863e-06, |
| "loss": 0.5118, |
| "num_input_tokens_seen": 70098400, |
| "step": 4540 |
| }, |
| { |
| "epoch": 18.646153846153847, |
| "grad_norm": 0.31640625, |
| "learning_rate": 1.1065057022596483e-06, |
| "loss": 0.4559, |
| "num_input_tokens_seen": 70176576, |
| "step": 4545 |
| }, |
| { |
| "epoch": 18.666666666666668, |
| "grad_norm": 0.345703125, |
| "learning_rate": 1.1035825401863185e-06, |
| "loss": 0.4418, |
| "num_input_tokens_seen": 70255264, |
| "step": 4550 |
| }, |
| { |
| "epoch": 18.68717948717949, |
| "grad_norm": 0.345703125, |
| "learning_rate": 1.100660995745538e-06, |
| "loss": 0.435, |
| "num_input_tokens_seen": 70324160, |
| "step": 4555 |
| }, |
| { |
| "epoch": 18.70769230769231, |
| "grad_norm": 0.365234375, |
| "learning_rate": 1.0977410808590437e-06, |
| "loss": 0.5499, |
| "num_input_tokens_seen": 70411616, |
| "step": 4560 |
| }, |
| { |
| "epoch": 18.72820512820513, |
| "grad_norm": 0.470703125, |
| "learning_rate": 1.0948228074419269e-06, |
| "loss": 0.4705, |
| "num_input_tokens_seen": 70482592, |
| "step": 4565 |
| }, |
| { |
| "epoch": 18.74871794871795, |
| "grad_norm": 0.44921875, |
| "learning_rate": 1.0919061874025774e-06, |
| "loss": 0.4466, |
| "num_input_tokens_seen": 70565120, |
| "step": 4570 |
| }, |
| { |
| "epoch": 18.76923076923077, |
| "grad_norm": 0.3984375, |
| "learning_rate": 1.0889912326426393e-06, |
| "loss": 0.4323, |
| "num_input_tokens_seen": 70635168, |
| "step": 4575 |
| }, |
| { |
| "epoch": 18.78974358974359, |
| "grad_norm": 0.310546875, |
| "learning_rate": 1.0860779550569609e-06, |
| "loss": 0.5235, |
| "num_input_tokens_seen": 70720096, |
| "step": 4580 |
| }, |
| { |
| "epoch": 18.81025641025641, |
| "grad_norm": 0.322265625, |
| "learning_rate": 1.083166366533548e-06, |
| "loss": 0.4659, |
| "num_input_tokens_seen": 70807648, |
| "step": 4585 |
| }, |
| { |
| "epoch": 18.83076923076923, |
| "grad_norm": 0.314453125, |
| "learning_rate": 1.080256478953512e-06, |
| "loss": 0.4968, |
| "num_input_tokens_seen": 70888832, |
| "step": 4590 |
| }, |
| { |
| "epoch": 18.851282051282052, |
| "grad_norm": 0.33203125, |
| "learning_rate": 1.0773483041910247e-06, |
| "loss": 0.5112, |
| "num_input_tokens_seen": 70971136, |
| "step": 4595 |
| }, |
| { |
| "epoch": 18.871794871794872, |
| "grad_norm": 0.29296875, |
| "learning_rate": 1.0744418541132676e-06, |
| "loss": 0.4414, |
| "num_input_tokens_seen": 71038816, |
| "step": 4600 |
| }, |
| { |
| "epoch": 18.892307692307693, |
| "grad_norm": 0.314453125, |
| "learning_rate": 1.0715371405803858e-06, |
| "loss": 0.4874, |
| "num_input_tokens_seen": 71114720, |
| "step": 4605 |
| }, |
| { |
| "epoch": 18.912820512820513, |
| "grad_norm": 0.294921875, |
| "learning_rate": 1.0686341754454364e-06, |
| "loss": 0.4571, |
| "num_input_tokens_seen": 71189856, |
| "step": 4610 |
| }, |
| { |
| "epoch": 18.933333333333334, |
| "grad_norm": 0.23046875, |
| "learning_rate": 1.0657329705543439e-06, |
| "loss": 0.4661, |
| "num_input_tokens_seen": 71271136, |
| "step": 4615 |
| }, |
| { |
| "epoch": 18.953846153846154, |
| "grad_norm": 0.2109375, |
| "learning_rate": 1.0628335377458477e-06, |
| "loss": 0.435, |
| "num_input_tokens_seen": 71343488, |
| "step": 4620 |
| }, |
| { |
| "epoch": 18.974358974358974, |
| "grad_norm": 0.21484375, |
| "learning_rate": 1.0599358888514582e-06, |
| "loss": 0.4845, |
| "num_input_tokens_seen": 71419104, |
| "step": 4625 |
| }, |
| { |
| "epoch": 18.994871794871795, |
| "grad_norm": 0.2021484375, |
| "learning_rate": 1.0570400356954044e-06, |
| "loss": 0.5111, |
| "num_input_tokens_seen": 71491776, |
| "step": 4630 |
| }, |
| { |
| "epoch": 19.015384615384615, |
| "grad_norm": 0.18359375, |
| "learning_rate": 1.0541459900945892e-06, |
| "loss": 0.5006, |
| "num_input_tokens_seen": 71573184, |
| "step": 4635 |
| }, |
| { |
| "epoch": 19.035897435897436, |
| "grad_norm": 0.1630859375, |
| "learning_rate": 1.0512537638585379e-06, |
| "loss": 0.4828, |
| "num_input_tokens_seen": 71648768, |
| "step": 4640 |
| }, |
| { |
| "epoch": 19.056410256410256, |
| "grad_norm": 0.1572265625, |
| "learning_rate": 1.0483633687893526e-06, |
| "loss": 0.4607, |
| "num_input_tokens_seen": 71721824, |
| "step": 4645 |
| }, |
| { |
| "epoch": 19.076923076923077, |
| "grad_norm": 0.1376953125, |
| "learning_rate": 1.0454748166816645e-06, |
| "loss": 0.497, |
| "num_input_tokens_seen": 71797568, |
| "step": 4650 |
| }, |
| { |
| "epoch": 19.097435897435897, |
| "grad_norm": 0.13671875, |
| "learning_rate": 1.0425881193225808e-06, |
| "loss": 0.4607, |
| "num_input_tokens_seen": 71871136, |
| "step": 4655 |
| }, |
| { |
| "epoch": 19.117948717948718, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 1.0397032884916438e-06, |
| "loss": 0.4232, |
| "num_input_tokens_seen": 71941984, |
| "step": 4660 |
| }, |
| { |
| "epoch": 19.138461538461538, |
| "grad_norm": 0.123046875, |
| "learning_rate": 1.0368203359607767e-06, |
| "loss": 0.5216, |
| "num_input_tokens_seen": 72024736, |
| "step": 4665 |
| }, |
| { |
| "epoch": 19.15897435897436, |
| "grad_norm": 0.12109375, |
| "learning_rate": 1.0339392734942393e-06, |
| "loss": 0.4565, |
| "num_input_tokens_seen": 72096064, |
| "step": 4670 |
| }, |
| { |
| "epoch": 19.17948717948718, |
| "grad_norm": 0.1337890625, |
| "learning_rate": 1.031060112848578e-06, |
| "loss": 0.4488, |
| "num_input_tokens_seen": 72171168, |
| "step": 4675 |
| }, |
| { |
| "epoch": 19.2, |
| "grad_norm": 0.126953125, |
| "learning_rate": 1.0281828657725798e-06, |
| "loss": 0.4567, |
| "num_input_tokens_seen": 72249056, |
| "step": 4680 |
| }, |
| { |
| "epoch": 19.22051282051282, |
| "grad_norm": 0.2080078125, |
| "learning_rate": 1.0253075440072212e-06, |
| "loss": 0.4556, |
| "num_input_tokens_seen": 72338944, |
| "step": 4685 |
| }, |
| { |
| "epoch": 19.24102564102564, |
| "grad_norm": 0.1484375, |
| "learning_rate": 1.0224341592856245e-06, |
| "loss": 0.4686, |
| "num_input_tokens_seen": 72412032, |
| "step": 4690 |
| }, |
| { |
| "epoch": 19.26153846153846, |
| "grad_norm": 0.1435546875, |
| "learning_rate": 1.0195627233330052e-06, |
| "loss": 0.4087, |
| "num_input_tokens_seen": 72485760, |
| "step": 4695 |
| }, |
| { |
| "epoch": 19.28205128205128, |
| "grad_norm": 0.3046875, |
| "learning_rate": 1.0166932478666292e-06, |
| "loss": 0.4634, |
| "num_input_tokens_seen": 72565344, |
| "step": 4700 |
| }, |
| { |
| "epoch": 19.3025641025641, |
| "grad_norm": 0.275390625, |
| "learning_rate": 1.0138257445957601e-06, |
| "loss": 0.5316, |
| "num_input_tokens_seen": 72644800, |
| "step": 4705 |
| }, |
| { |
| "epoch": 19.323076923076922, |
| "grad_norm": 0.31640625, |
| "learning_rate": 1.0109602252216153e-06, |
| "loss": 0.4929, |
| "num_input_tokens_seen": 72725440, |
| "step": 4710 |
| }, |
| { |
| "epoch": 19.343589743589742, |
| "grad_norm": 0.640625, |
| "learning_rate": 1.0080967014373152e-06, |
| "loss": 0.442, |
| "num_input_tokens_seen": 72796064, |
| "step": 4715 |
| }, |
| { |
| "epoch": 19.364102564102563, |
| "grad_norm": 0.91015625, |
| "learning_rate": 1.0052351849278385e-06, |
| "loss": 0.4442, |
| "num_input_tokens_seen": 72870080, |
| "step": 4720 |
| }, |
| { |
| "epoch": 19.384615384615383, |
| "grad_norm": 0.2490234375, |
| "learning_rate": 1.0023756873699723e-06, |
| "loss": 0.4751, |
| "num_input_tokens_seen": 72944288, |
| "step": 4725 |
| }, |
| { |
| "epoch": 19.405128205128204, |
| "grad_norm": 0.333984375, |
| "learning_rate": 9.995182204322637e-07, |
| "loss": 0.5129, |
| "num_input_tokens_seen": 73021664, |
| "step": 4730 |
| }, |
| { |
| "epoch": 19.425641025641024, |
| "grad_norm": 0.81640625, |
| "learning_rate": 9.966627957749767e-07, |
| "loss": 0.4796, |
| "num_input_tokens_seen": 73097920, |
| "step": 4735 |
| }, |
| { |
| "epoch": 19.446153846153845, |
| "grad_norm": 0.333984375, |
| "learning_rate": 9.93809425050039e-07, |
| "loss": 0.4785, |
| "num_input_tokens_seen": 73170112, |
| "step": 4740 |
| }, |
| { |
| "epoch": 19.466666666666665, |
| "grad_norm": 0.2255859375, |
| "learning_rate": 9.909581199009971e-07, |
| "loss": 0.4379, |
| "num_input_tokens_seen": 73241312, |
| "step": 4745 |
| }, |
| { |
| "epoch": 19.487179487179485, |
| "grad_norm": 0.267578125, |
| "learning_rate": 9.8810889196297e-07, |
| "loss": 0.5408, |
| "num_input_tokens_seen": 73319936, |
| "step": 4750 |
| }, |
| { |
| "epoch": 19.50769230769231, |
| "grad_norm": 0.3046875, |
| "learning_rate": 9.852617528625992e-07, |
| "loss": 0.4878, |
| "num_input_tokens_seen": 73397824, |
| "step": 4755 |
| }, |
| { |
| "epoch": 19.52820512820513, |
| "grad_norm": 0.29296875, |
| "learning_rate": 9.824167142180032e-07, |
| "loss": 0.4627, |
| "num_input_tokens_seen": 73470688, |
| "step": 4760 |
| }, |
| { |
| "epoch": 19.54871794871795, |
| "grad_norm": 0.283203125, |
| "learning_rate": 9.795737876387285e-07, |
| "loss": 0.4799, |
| "num_input_tokens_seen": 73545792, |
| "step": 4765 |
| }, |
| { |
| "epoch": 19.56923076923077, |
| "grad_norm": 0.34765625, |
| "learning_rate": 9.76732984725704e-07, |
| "loss": 0.428, |
| "num_input_tokens_seen": 73617760, |
| "step": 4770 |
| }, |
| { |
| "epoch": 19.58974358974359, |
| "grad_norm": 0.3515625, |
| "learning_rate": 9.738943170711916e-07, |
| "loss": 0.4608, |
| "num_input_tokens_seen": 73707328, |
| "step": 4775 |
| }, |
| { |
| "epoch": 19.61025641025641, |
| "grad_norm": 0.515625, |
| "learning_rate": 9.710577962587412e-07, |
| "loss": 0.4951, |
| "num_input_tokens_seen": 73782976, |
| "step": 4780 |
| }, |
| { |
| "epoch": 19.630769230769232, |
| "grad_norm": 0.3828125, |
| "learning_rate": 9.68223433863141e-07, |
| "loss": 0.53, |
| "num_input_tokens_seen": 73872256, |
| "step": 4785 |
| }, |
| { |
| "epoch": 19.651282051282053, |
| "grad_norm": 0.341796875, |
| "learning_rate": 9.653912414503731e-07, |
| "loss": 0.45, |
| "num_input_tokens_seen": 73947520, |
| "step": 4790 |
| }, |
| { |
| "epoch": 19.671794871794873, |
| "grad_norm": 0.337890625, |
| "learning_rate": 9.625612305775626e-07, |
| "loss": 0.4218, |
| "num_input_tokens_seen": 74023104, |
| "step": 4795 |
| }, |
| { |
| "epoch": 19.692307692307693, |
| "grad_norm": 0.333984375, |
| "learning_rate": 9.597334127929346e-07, |
| "loss": 0.4531, |
| "num_input_tokens_seen": 74105920, |
| "step": 4800 |
| }, |
| { |
| "epoch": 19.712820512820514, |
| "grad_norm": 0.306640625, |
| "learning_rate": 9.569077996357638e-07, |
| "loss": 0.4142, |
| "num_input_tokens_seen": 74182752, |
| "step": 4805 |
| }, |
| { |
| "epoch": 19.733333333333334, |
| "grad_norm": 0.37109375, |
| "learning_rate": 9.54084402636329e-07, |
| "loss": 0.5121, |
| "num_input_tokens_seen": 74265248, |
| "step": 4810 |
| }, |
| { |
| "epoch": 19.753846153846155, |
| "grad_norm": 0.328125, |
| "learning_rate": 9.512632333158653e-07, |
| "loss": 0.523, |
| "num_input_tokens_seen": 74363232, |
| "step": 4815 |
| }, |
| { |
| "epoch": 19.774358974358975, |
| "grad_norm": 0.353515625, |
| "learning_rate": 9.484443031865176e-07, |
| "loss": 0.5103, |
| "num_input_tokens_seen": 74442848, |
| "step": 4820 |
| }, |
| { |
| "epoch": 19.794871794871796, |
| "grad_norm": 0.27734375, |
| "learning_rate": 9.456276237512949e-07, |
| "loss": 0.4725, |
| "num_input_tokens_seen": 74513376, |
| "step": 4825 |
| }, |
| { |
| "epoch": 19.815384615384616, |
| "grad_norm": 0.271484375, |
| "learning_rate": 9.428132065040198e-07, |
| "loss": 0.4921, |
| "num_input_tokens_seen": 74588928, |
| "step": 4830 |
| }, |
| { |
| "epoch": 19.835897435897436, |
| "grad_norm": 0.291015625, |
| "learning_rate": 9.40001062929285e-07, |
| "loss": 0.4331, |
| "num_input_tokens_seen": 74659040, |
| "step": 4835 |
| }, |
| { |
| "epoch": 19.856410256410257, |
| "grad_norm": 0.216796875, |
| "learning_rate": 9.371912045024046e-07, |
| "loss": 0.44, |
| "num_input_tokens_seen": 74737472, |
| "step": 4840 |
| }, |
| { |
| "epoch": 19.876923076923077, |
| "grad_norm": 0.2158203125, |
| "learning_rate": 9.343836426893687e-07, |
| "loss": 0.4831, |
| "num_input_tokens_seen": 74810592, |
| "step": 4845 |
| }, |
| { |
| "epoch": 19.897435897435898, |
| "grad_norm": 0.1943359375, |
| "learning_rate": 9.315783889467943e-07, |
| "loss": 0.4494, |
| "num_input_tokens_seen": 74880096, |
| "step": 4850 |
| }, |
| { |
| "epoch": 19.91794871794872, |
| "grad_norm": 0.1953125, |
| "learning_rate": 9.287754547218821e-07, |
| "loss": 0.5063, |
| "num_input_tokens_seen": 74951168, |
| "step": 4855 |
| }, |
| { |
| "epoch": 19.93846153846154, |
| "grad_norm": 0.1611328125, |
| "learning_rate": 9.259748514523654e-07, |
| "loss": 0.4975, |
| "num_input_tokens_seen": 75034592, |
| "step": 4860 |
| }, |
| { |
| "epoch": 19.95897435897436, |
| "grad_norm": 0.1728515625, |
| "learning_rate": 9.231765905664677e-07, |
| "loss": 0.4802, |
| "num_input_tokens_seen": 75108992, |
| "step": 4865 |
| }, |
| { |
| "epoch": 19.97948717948718, |
| "grad_norm": 0.166015625, |
| "learning_rate": 9.20380683482853e-07, |
| "loss": 0.4473, |
| "num_input_tokens_seen": 75185824, |
| "step": 4870 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.140625, |
| "learning_rate": 9.175871416105802e-07, |
| "loss": 0.4971, |
| "num_input_tokens_seen": 75263936, |
| "step": 4875 |
| }, |
| { |
| "epoch": 20.02051282051282, |
| "grad_norm": 0.134765625, |
| "learning_rate": 9.147959763490578e-07, |
| "loss": 0.493, |
| "num_input_tokens_seen": 75342752, |
| "step": 4880 |
| }, |
| { |
| "epoch": 20.04102564102564, |
| "grad_norm": 0.11669921875, |
| "learning_rate": 9.120071990879949e-07, |
| "loss": 0.4709, |
| "num_input_tokens_seen": 75420704, |
| "step": 4885 |
| }, |
| { |
| "epoch": 20.06153846153846, |
| "grad_norm": 0.13671875, |
| "learning_rate": 9.092208212073569e-07, |
| "loss": 0.5248, |
| "num_input_tokens_seen": 75496128, |
| "step": 4890 |
| }, |
| { |
| "epoch": 20.08205128205128, |
| "grad_norm": 0.1220703125, |
| "learning_rate": 9.064368540773177e-07, |
| "loss": 0.525, |
| "num_input_tokens_seen": 75585984, |
| "step": 4895 |
| }, |
| { |
| "epoch": 20.102564102564102, |
| "grad_norm": 0.1357421875, |
| "learning_rate": 9.036553090582145e-07, |
| "loss": 0.5186, |
| "num_input_tokens_seen": 75668416, |
| "step": 4900 |
| }, |
| { |
| "epoch": 20.123076923076923, |
| "grad_norm": 0.15234375, |
| "learning_rate": 9.008761975004994e-07, |
| "loss": 0.456, |
| "num_input_tokens_seen": 75744960, |
| "step": 4905 |
| }, |
| { |
| "epoch": 20.143589743589743, |
| "grad_norm": 0.203125, |
| "learning_rate": 8.98099530744696e-07, |
| "loss": 0.4507, |
| "num_input_tokens_seen": 75818688, |
| "step": 4910 |
| }, |
| { |
| "epoch": 20.164102564102564, |
| "grad_norm": 0.150390625, |
| "learning_rate": 8.953253201213517e-07, |
| "loss": 0.4552, |
| "num_input_tokens_seen": 75901824, |
| "step": 4915 |
| }, |
| { |
| "epoch": 20.184615384615384, |
| "grad_norm": 0.146484375, |
| "learning_rate": 8.925535769509895e-07, |
| "loss": 0.4153, |
| "num_input_tokens_seen": 75973248, |
| "step": 4920 |
| }, |
| { |
| "epoch": 20.205128205128204, |
| "grad_norm": 0.310546875, |
| "learning_rate": 8.897843125440653e-07, |
| "loss": 0.4452, |
| "num_input_tokens_seen": 76043840, |
| "step": 4925 |
| }, |
| { |
| "epoch": 20.217435897435898, |
| "num_input_tokens_seen": 76105440, |
| "step": 4928, |
| "total_flos": 1.6998510508071322e+18, |
| "train_loss": 0.4908539823365289, |
| "train_runtime": 36017.1103, |
| "train_samples_per_second": 3.465, |
| "train_steps_per_second": 0.216 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 7776, |
| "num_input_tokens_seen": 76105440, |
| "num_train_epochs": 32, |
| "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": 1.6998510508071322e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
