| { | |
| "best_metric": 0.9394697348674337, | |
| "best_model_checkpoint": "convnextv2-tiny-22k-384-finetuned-zkdeng/t20spiders-1000/checkpoint-1250", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 3.0306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.9932, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.9368, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.8148, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6421, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.4e-05, | |
| "loss": 2.4974, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 2.2817, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 2.0781, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.8205, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4e-05, | |
| "loss": 1.637, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.4023, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.2539, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.977777777777778e-05, | |
| "loss": 1.1394, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.933333333333334e-05, | |
| "loss": 1.0543, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.9862, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.844444444444445e-05, | |
| "loss": 0.9572, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.8641, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.755555555555556e-05, | |
| "loss": 0.812, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.711111111111111e-05, | |
| "loss": 0.7983, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.7808, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.6222222222222224e-05, | |
| "loss": 0.7194, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.577777777777778e-05, | |
| "loss": 0.7287, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.5333333333333335e-05, | |
| "loss": 0.6561, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.4888888888888894e-05, | |
| "loss": 0.663, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.6401, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8739369684842421, | |
| "eval_f1": 0.8740592498514836, | |
| "eval_loss": 0.4404308795928955, | |
| "eval_precision": 0.8775990272880249, | |
| "eval_recall": 0.8746347926917346, | |
| "eval_runtime": 40.5207, | |
| "eval_samples_per_second": 49.333, | |
| "eval_steps_per_second": 3.085, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.5997, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.355555555555556e-05, | |
| "loss": 0.589, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.311111111111111e-05, | |
| "loss": 0.5772, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.266666666666667e-05, | |
| "loss": 0.5522, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.528, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.177777777777778e-05, | |
| "loss": 0.5451, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.133333333333333e-05, | |
| "loss": 0.5514, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.088888888888889e-05, | |
| "loss": 0.52, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.0444444444444444e-05, | |
| "loss": 0.5137, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5622, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3.9555555555555556e-05, | |
| "loss": 0.4974, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.9111111111111115e-05, | |
| "loss": 0.5295, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.866666666666667e-05, | |
| "loss": 0.5689, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.8222222222222226e-05, | |
| "loss": 0.5419, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.464, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3.733333333333334e-05, | |
| "loss": 0.5126, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.688888888888889e-05, | |
| "loss": 0.475, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.644444444444445e-05, | |
| "loss": 0.5073, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.4599, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.5344, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.511111111111111e-05, | |
| "loss": 0.4297, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.466666666666667e-05, | |
| "loss": 0.4628, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.4222222222222224e-05, | |
| "loss": 0.4752, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3.377777777777778e-05, | |
| "loss": 0.4443, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4281, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9194597298649325, | |
| "eval_f1": 0.9197509360762094, | |
| "eval_loss": 0.2785426378250122, | |
| "eval_precision": 0.9220909050125684, | |
| "eval_recall": 0.9197284240270884, | |
| "eval_runtime": 40.0493, | |
| "eval_samples_per_second": 49.913, | |
| "eval_steps_per_second": 3.121, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.2888888888888894e-05, | |
| "loss": 0.4908, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.2444444444444446e-05, | |
| "loss": 0.3572, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.3934, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.155555555555556e-05, | |
| "loss": 0.3569, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.3695, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.066666666666667e-05, | |
| "loss": 0.437, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.0222222222222225e-05, | |
| "loss": 0.3635, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.9777777777777777e-05, | |
| "loss": 0.3828, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.9333333333333336e-05, | |
| "loss": 0.3957, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.4001, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.8444444444444447e-05, | |
| "loss": 0.386, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.3908, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.7555555555555555e-05, | |
| "loss": 0.3772, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.7111111111111114e-05, | |
| "loss": 0.3696, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.402, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.6222222222222226e-05, | |
| "loss": 0.3849, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.5777777777777778e-05, | |
| "loss": 0.3695, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.5333333333333337e-05, | |
| "loss": 0.3935, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.488888888888889e-05, | |
| "loss": 0.3855, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.3249, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.3861, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.3555555555555556e-05, | |
| "loss": 0.4361, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.3111111111111112e-05, | |
| "loss": 0.4055, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.2666666666666668e-05, | |
| "loss": 0.33, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.3803, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9244622311155578, | |
| "eval_f1": 0.9249258490449901, | |
| "eval_loss": 0.2285059541463852, | |
| "eval_precision": 0.9267835905150354, | |
| "eval_recall": 0.9250601936006297, | |
| "eval_runtime": 40.1666, | |
| "eval_samples_per_second": 49.768, | |
| "eval_steps_per_second": 3.112, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2.177777777777778e-05, | |
| "loss": 0.3654, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.1333333333333335e-05, | |
| "loss": 0.3263, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.088888888888889e-05, | |
| "loss": 0.2524, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 2.0444444444444446e-05, | |
| "loss": 0.3482, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3732, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.9555555555555557e-05, | |
| "loss": 0.3111, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 1.9111111111111113e-05, | |
| "loss": 0.3258, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.866666666666667e-05, | |
| "loss": 0.3643, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 1.8222222222222224e-05, | |
| "loss": 0.2817, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.3178, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.7333333333333336e-05, | |
| "loss": 0.3233, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1.688888888888889e-05, | |
| "loss": 0.3234, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.6444444444444447e-05, | |
| "loss": 0.3186, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.296, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.3392, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.5111111111111112e-05, | |
| "loss": 0.2949, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.4666666666666668e-05, | |
| "loss": 0.3436, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.4222222222222224e-05, | |
| "loss": 0.2941, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.3777777777777778e-05, | |
| "loss": 0.3307, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.3143, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.2888888888888889e-05, | |
| "loss": 0.2712, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.2444444444444445e-05, | |
| "loss": 0.2731, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.3389, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.1555555555555556e-05, | |
| "loss": 0.3186, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3044, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.935967983991996, | |
| "eval_f1": 0.9361947038683628, | |
| "eval_loss": 0.19686730206012726, | |
| "eval_precision": 0.9378823267571136, | |
| "eval_recall": 0.9357103464241803, | |
| "eval_runtime": 40.3278, | |
| "eval_samples_per_second": 49.569, | |
| "eval_steps_per_second": 3.1, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1.0666666666666667e-05, | |
| "loss": 0.3045, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.0222222222222223e-05, | |
| "loss": 0.2946, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 0.2414, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.2243, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.314, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 0.2857, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.3168, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 7.555555555555556e-06, | |
| "loss": 0.3076, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 7.111111111111112e-06, | |
| "loss": 0.2735, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.2528, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 6.222222222222222e-06, | |
| "loss": 0.2471, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 5.777777777777778e-06, | |
| "loss": 0.2444, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.2529, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 0.3072, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.3376, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.2794, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 3.555555555555556e-06, | |
| "loss": 0.2291, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 3.111111111111111e-06, | |
| "loss": 0.2254, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.2416, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.257, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 0.2931, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.2698, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 0.2654, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.2815, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2596, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9394697348674337, | |
| "eval_f1": 0.939741803575447, | |
| "eval_loss": 0.18301530182361603, | |
| "eval_precision": 0.9403530279488119, | |
| "eval_recall": 0.9396844259408355, | |
| "eval_runtime": 40.2733, | |
| "eval_samples_per_second": 49.636, | |
| "eval_steps_per_second": 3.104, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1250, | |
| "total_flos": 5.918123737786614e+18, | |
| "train_loss": 0.603860605430603, | |
| "train_runtime": 3719.6599, | |
| "train_samples_per_second": 21.499, | |
| "train_steps_per_second": 0.336 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1250, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 5.918123737786614e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |