| { | |
| "best_metric": 0.26204365491867065, | |
| "best_model_checkpoint": "./vit-base-binary-isic-sharpened-patch-32/checkpoint-1200", | |
| "epoch": 4.0, | |
| "global_step": 4328, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019953789279112755, | |
| "loss": 0.5918, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001990757855822551, | |
| "loss": 0.4247, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019861367837338263, | |
| "loss": 0.4236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019815157116451017, | |
| "loss": 0.4569, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001976894639556377, | |
| "loss": 0.4222, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019722735674676528, | |
| "loss": 0.429, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001967652495378928, | |
| "loss": 0.3076, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019630314232902034, | |
| "loss": 0.3494, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019588724584103511, | |
| "loss": 0.3608, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019542513863216268, | |
| "loss": 0.3258, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.7798564838544336, | |
| "eval_f1": 0.7798564838544336, | |
| "eval_loss": 0.4317772090435028, | |
| "eval_precision": 0.7798564838544336, | |
| "eval_recall": 0.7798564838544336, | |
| "eval_runtime": 68.1306, | |
| "eval_samples_per_second": 114.545, | |
| "eval_steps_per_second": 14.325, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019496303142329022, | |
| "loss": 0.4003, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019450092421441774, | |
| "loss": 0.2738, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001940388170055453, | |
| "loss": 0.4808, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019357670979667284, | |
| "loss": 0.3336, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019311460258780039, | |
| "loss": 0.3665, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001926524953789279, | |
| "loss": 0.2733, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001922365988909427, | |
| "loss": 0.4325, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00019177449168207025, | |
| "loss": 0.2481, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019131238447319779, | |
| "loss": 0.3147, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019085027726432533, | |
| "loss": 0.3002, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.8511019989748847, | |
| "eval_f1": 0.8511019989748847, | |
| "eval_loss": 0.3273237943649292, | |
| "eval_precision": 0.8511019989748847, | |
| "eval_recall": 0.8511019989748847, | |
| "eval_runtime": 68.9428, | |
| "eval_samples_per_second": 113.195, | |
| "eval_steps_per_second": 14.157, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019038817005545287, | |
| "loss": 0.4185, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001899260628465804, | |
| "loss": 0.3972, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00018946395563770795, | |
| "loss": 0.297, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00018900184842883552, | |
| "loss": 0.2821, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00018853974121996306, | |
| "loss": 0.3197, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00018807763401109057, | |
| "loss": 0.265, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001876155268022181, | |
| "loss": 0.3609, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00018715341959334568, | |
| "loss": 0.3413, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00018669131238447322, | |
| "loss": 0.3213, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00018622920517560073, | |
| "loss": 0.3154, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.8507175807278319, | |
| "eval_f1": 0.8507175807278319, | |
| "eval_loss": 0.31652987003326416, | |
| "eval_precision": 0.8507175807278319, | |
| "eval_recall": 0.8507175807278319, | |
| "eval_runtime": 68.3938, | |
| "eval_samples_per_second": 114.104, | |
| "eval_steps_per_second": 14.27, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00018576709796672827, | |
| "loss": 0.3267, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00018530499075785584, | |
| "loss": 0.295, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00018484288354898338, | |
| "loss": 0.3796, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001843807763401109, | |
| "loss": 0.2566, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00018391866913123846, | |
| "loss": 0.2474, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.000183456561922366, | |
| "loss": 0.3685, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00018299445471349355, | |
| "loss": 0.2341, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00018253234750462106, | |
| "loss": 0.3525, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00018207024029574863, | |
| "loss": 0.409, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00018160813308687617, | |
| "loss": 0.412, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.8546899026140441, | |
| "eval_f1": 0.854689902614044, | |
| "eval_loss": 0.3700454831123352, | |
| "eval_precision": 0.8546899026140441, | |
| "eval_recall": 0.8546899026140441, | |
| "eval_runtime": 68.5534, | |
| "eval_samples_per_second": 113.838, | |
| "eval_steps_per_second": 14.237, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001811460258780037, | |
| "loss": 0.3592, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018068391866913125, | |
| "loss": 0.2842, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001802218114602588, | |
| "loss": 0.4147, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00017975970425138633, | |
| "loss": 0.2868, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017929759704251387, | |
| "loss": 0.24, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001788354898336414, | |
| "loss": 0.2723, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017837338262476895, | |
| "loss": 0.2125, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001779112754158965, | |
| "loss": 0.3297, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00017744916820702404, | |
| "loss": 0.2854, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00017698706099815158, | |
| "loss": 0.3264, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.8635315222962583, | |
| "eval_f1": 0.8635315222962583, | |
| "eval_loss": 0.2830676734447479, | |
| "eval_precision": 0.8635315222962583, | |
| "eval_recall": 0.8635315222962583, | |
| "eval_runtime": 68.6278, | |
| "eval_samples_per_second": 113.715, | |
| "eval_steps_per_second": 14.222, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00017652495378927912, | |
| "loss": 0.2027, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00017606284658040666, | |
| "loss": 0.3993, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001756007393715342, | |
| "loss": 0.2834, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00017513863216266177, | |
| "loss": 0.3107, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00017467652495378928, | |
| "loss": 0.2652, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00017421441774491682, | |
| "loss": 0.2235, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00017375231053604436, | |
| "loss": 0.2878, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00017329020332717193, | |
| "loss": 0.4394, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00017282809611829944, | |
| "loss": 0.2745, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00017236598890942698, | |
| "loss": 0.2851, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.8519989748846746, | |
| "eval_f1": 0.8519989748846746, | |
| "eval_loss": 0.3019918203353882, | |
| "eval_precision": 0.8519989748846746, | |
| "eval_recall": 0.8519989748846746, | |
| "eval_runtime": 68.0595, | |
| "eval_samples_per_second": 114.664, | |
| "eval_steps_per_second": 14.34, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00017190388170055452, | |
| "loss": 0.3236, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001714417744916821, | |
| "loss": 0.2732, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00017097966728280963, | |
| "loss": 0.2727, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00017051756007393715, | |
| "loss": 0.281, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017005545286506471, | |
| "loss": 0.2348, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00016959334565619225, | |
| "loss": 0.2904, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0001691312384473198, | |
| "loss": 0.2566, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001686691312384473, | |
| "loss": 0.2884, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00016820702402957488, | |
| "loss": 0.2929, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00016774491682070242, | |
| "loss": 0.2582, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.8385443362378268, | |
| "eval_f1": 0.8385443362378268, | |
| "eval_loss": 0.3071436285972595, | |
| "eval_precision": 0.8385443362378268, | |
| "eval_recall": 0.8385443362378268, | |
| "eval_runtime": 68.3062, | |
| "eval_samples_per_second": 114.25, | |
| "eval_steps_per_second": 14.289, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00016728280961182996, | |
| "loss": 0.2791, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016682070240295747, | |
| "loss": 0.2725, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016635859519408504, | |
| "loss": 0.2403, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00016589648798521258, | |
| "loss": 0.2836, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00016543438077634012, | |
| "loss": 0.1784, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00016497227356746766, | |
| "loss": 0.3475, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0001645101663585952, | |
| "loss": 0.236, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00016404805914972274, | |
| "loss": 0.2286, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00016358595194085028, | |
| "loss": 0.3194, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00016312384473197782, | |
| "loss": 0.2376, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.8578933880061507, | |
| "eval_f1": 0.8578933880061507, | |
| "eval_loss": 0.30125078558921814, | |
| "eval_precision": 0.8578933880061507, | |
| "eval_recall": 0.8578933880061507, | |
| "eval_runtime": 68.2331, | |
| "eval_samples_per_second": 114.373, | |
| "eval_steps_per_second": 14.304, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00016266173752310537, | |
| "loss": 0.2476, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001621996303142329, | |
| "loss": 0.264, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00016173752310536045, | |
| "loss": 0.2826, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00016127541589648801, | |
| "loss": 0.308, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016081330868761553, | |
| "loss": 0.3804, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016035120147874307, | |
| "loss": 0.2403, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001598890942698706, | |
| "loss": 0.2706, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00015942698706099818, | |
| "loss": 0.2969, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001589648798521257, | |
| "loss": 0.2004, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00015850277264325323, | |
| "loss": 0.2635, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.8544336237826755, | |
| "eval_f1": 0.8544336237826755, | |
| "eval_loss": 0.2908886969089508, | |
| "eval_precision": 0.8544336237826755, | |
| "eval_recall": 0.8544336237826755, | |
| "eval_runtime": 67.9165, | |
| "eval_samples_per_second": 114.906, | |
| "eval_steps_per_second": 14.371, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00015804066543438077, | |
| "loss": 0.1825, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00015757855822550834, | |
| "loss": 0.2, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00015711645101663585, | |
| "loss": 0.2883, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0001566543438077634, | |
| "loss": 0.2481, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00015619223659889096, | |
| "loss": 0.2548, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0001557301293900185, | |
| "loss": 0.2288, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00015526802218114602, | |
| "loss": 0.1572, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00015480591497227356, | |
| "loss": 0.2619, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00015434380776340113, | |
| "loss": 0.2353, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015388170055452867, | |
| "loss": 0.2837, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.8216299333675039, | |
| "eval_f1": 0.8216299333675039, | |
| "eval_loss": 0.3623135983943939, | |
| "eval_precision": 0.8216299333675039, | |
| "eval_recall": 0.8216299333675039, | |
| "eval_runtime": 68.0151, | |
| "eval_samples_per_second": 114.739, | |
| "eval_steps_per_second": 14.35, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001534195933456562, | |
| "loss": 0.2815, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00015295748613678372, | |
| "loss": 0.3687, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0001524953789279113, | |
| "loss": 0.2673, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00015203327171903883, | |
| "loss": 0.2105, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00015157116451016637, | |
| "loss": 0.2569, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0001511090573012939, | |
| "loss": 0.3272, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015064695009242145, | |
| "loss": 0.2471, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.000150184842883549, | |
| "loss": 0.2204, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00014972273567467653, | |
| "loss": 0.2292, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00014926062846580407, | |
| "loss": 0.2036, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.8763454638646848, | |
| "eval_f1": 0.8763454638646848, | |
| "eval_loss": 0.29849833250045776, | |
| "eval_precision": 0.8763454638646848, | |
| "eval_recall": 0.8763454638646848, | |
| "eval_runtime": 68.3104, | |
| "eval_samples_per_second": 114.243, | |
| "eval_steps_per_second": 14.288, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00014879852125693161, | |
| "loss": 0.1718, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014833641404805916, | |
| "loss": 0.204, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001478743068391867, | |
| "loss": 0.1793, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00014741219963031424, | |
| "loss": 0.1866, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014695009242144178, | |
| "loss": 0.2001, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014648798521256932, | |
| "loss": 0.1736, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014602587800369686, | |
| "loss": 0.282, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014556377079482443, | |
| "loss": 0.1727, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00014510166358595194, | |
| "loss": 0.1913, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00014463955637707948, | |
| "loss": 0.1586, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_accuracy": 0.8933880061506919, | |
| "eval_f1": 0.8933880061506919, | |
| "eval_loss": 0.26204365491867065, | |
| "eval_precision": 0.8933880061506919, | |
| "eval_recall": 0.8933880061506919, | |
| "eval_runtime": 68.1338, | |
| "eval_samples_per_second": 114.539, | |
| "eval_steps_per_second": 14.325, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00014417744916820702, | |
| "loss": 0.1711, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001437153419593346, | |
| "loss": 0.1848, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001432532347504621, | |
| "loss": 0.1595, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00014279112754158964, | |
| "loss": 0.1966, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001423290203327172, | |
| "loss": 0.1483, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00014186691312384475, | |
| "loss": 0.2722, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00014140480591497227, | |
| "loss": 0.1284, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0001409426987060998, | |
| "loss": 0.1319, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00014048059149722737, | |
| "loss": 0.2384, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00014001848428835492, | |
| "loss": 0.1914, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.8799333675038442, | |
| "eval_f1": 0.8799333675038442, | |
| "eval_loss": 0.2995173931121826, | |
| "eval_precision": 0.8799333675038442, | |
| "eval_recall": 0.8799333675038442, | |
| "eval_runtime": 68.0366, | |
| "eval_samples_per_second": 114.703, | |
| "eval_steps_per_second": 14.345, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00013955637707948243, | |
| "loss": 0.1901, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00013909426987061, | |
| "loss": 0.1405, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00013863216266173754, | |
| "loss": 0.1304, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00013817005545286508, | |
| "loss": 0.2019, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00013770794824399262, | |
| "loss": 0.1196, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00013724584103512016, | |
| "loss": 0.1431, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0001367837338262477, | |
| "loss": 0.2222, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00013632162661737524, | |
| "loss": 0.2002, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00013585951940850278, | |
| "loss": 0.1371, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00013539741219963032, | |
| "loss": 0.1604, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_accuracy": 0.8839056893900564, | |
| "eval_f1": 0.8839056893900565, | |
| "eval_loss": 0.3001473844051361, | |
| "eval_precision": 0.8839056893900564, | |
| "eval_recall": 0.8839056893900564, | |
| "eval_runtime": 68.8495, | |
| "eval_samples_per_second": 113.349, | |
| "eval_steps_per_second": 14.176, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00013493530499075786, | |
| "loss": 0.1666, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0001344731977818854, | |
| "loss": 0.1761, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00013401109057301294, | |
| "loss": 0.2774, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00013354898336414049, | |
| "loss": 0.1625, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00013308687615526803, | |
| "loss": 0.2134, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00013262476894639557, | |
| "loss": 0.1669, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001321626617375231, | |
| "loss": 0.196, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00013170055452865065, | |
| "loss": 0.1536, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0001312384473197782, | |
| "loss": 0.151, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00013077634011090573, | |
| "loss": 0.1788, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_accuracy": 0.8882624295233214, | |
| "eval_f1": 0.8882624295233214, | |
| "eval_loss": 0.30128252506256104, | |
| "eval_precision": 0.8882624295233214, | |
| "eval_recall": 0.8882624295233214, | |
| "eval_runtime": 68.2286, | |
| "eval_samples_per_second": 114.38, | |
| "eval_steps_per_second": 14.305, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00013031423290203327, | |
| "loss": 0.2006, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0001298521256931608, | |
| "loss": 0.1379, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00012939001848428835, | |
| "loss": 0.1907, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0001289279112754159, | |
| "loss": 0.1546, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00012846580406654346, | |
| "loss": 0.2214, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.000128003696857671, | |
| "loss": 0.1565, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00012754158964879852, | |
| "loss": 0.1409, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00012707948243992606, | |
| "loss": 0.1588, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00012661737523105362, | |
| "loss": 0.141, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00012615526802218116, | |
| "loss": 0.1975, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.8815991799077396, | |
| "eval_f1": 0.8815991799077396, | |
| "eval_loss": 0.33689072728157043, | |
| "eval_precision": 0.8815991799077396, | |
| "eval_recall": 0.8815991799077396, | |
| "eval_runtime": 68.5762, | |
| "eval_samples_per_second": 113.8, | |
| "eval_steps_per_second": 14.232, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00012569316081330868, | |
| "loss": 0.1438, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00012523105360443625, | |
| "loss": 0.1645, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0001247689463955638, | |
| "loss": 0.2284, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00012430683918669133, | |
| "loss": 0.1867, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00012384473197781884, | |
| "loss": 0.1882, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001233826247689464, | |
| "loss": 0.1211, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00012292051756007395, | |
| "loss": 0.231, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0001224584103512015, | |
| "loss": 0.1927, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00012199630314232902, | |
| "loss": 0.1678, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00012153419593345656, | |
| "loss": 0.1228, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_accuracy": 0.8835212711430036, | |
| "eval_f1": 0.8835212711430036, | |
| "eval_loss": 0.3013974726200104, | |
| "eval_precision": 0.8835212711430036, | |
| "eval_recall": 0.8835212711430036, | |
| "eval_runtime": 68.3344, | |
| "eval_samples_per_second": 114.203, | |
| "eval_steps_per_second": 14.283, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00012107208872458411, | |
| "loss": 0.1684, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00012060998151571165, | |
| "loss": 0.2203, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00012014787430683921, | |
| "loss": 0.1346, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00011968576709796673, | |
| "loss": 0.1954, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00011922365988909428, | |
| "loss": 0.1607, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00011876155268022182, | |
| "loss": 0.2526, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00011829944547134937, | |
| "loss": 0.1386, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0001178373382624769, | |
| "loss": 0.1348, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00011737523105360444, | |
| "loss": 0.1582, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00011691312384473199, | |
| "loss": 0.1982, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_accuracy": 0.8956945156330087, | |
| "eval_f1": 0.8956945156330087, | |
| "eval_loss": 0.30940642952919006, | |
| "eval_precision": 0.8956945156330087, | |
| "eval_recall": 0.8956945156330087, | |
| "eval_runtime": 68.6164, | |
| "eval_samples_per_second": 113.734, | |
| "eval_steps_per_second": 14.224, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00011645101663585953, | |
| "loss": 0.1018, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00011598890942698706, | |
| "loss": 0.148, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0001155268022181146, | |
| "loss": 0.211, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00011506469500924216, | |
| "loss": 0.1488, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0001146025878003697, | |
| "loss": 0.1544, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00011414048059149722, | |
| "loss": 0.1358, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00011367837338262476, | |
| "loss": 0.1038, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00011321626617375232, | |
| "loss": 0.0979, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00011275415896487986, | |
| "loss": 0.1672, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00011229205175600739, | |
| "loss": 0.1602, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.8717324449000513, | |
| "eval_f1": 0.8717324449000513, | |
| "eval_loss": 0.35228291153907776, | |
| "eval_precision": 0.8717324449000513, | |
| "eval_recall": 0.8717324449000513, | |
| "eval_runtime": 68.3631, | |
| "eval_samples_per_second": 114.155, | |
| "eval_steps_per_second": 14.277, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00011182994454713494, | |
| "loss": 0.1843, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00011136783733826248, | |
| "loss": 0.1559, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00011090573012939002, | |
| "loss": 0.1523, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00011044362292051758, | |
| "loss": 0.1559, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0001099815157116451, | |
| "loss": 0.1694, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00010951940850277264, | |
| "loss": 0.1712, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0001090573012939002, | |
| "loss": 0.1188, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00010859519408502774, | |
| "loss": 0.1098, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00010813308687615527, | |
| "loss": 0.1341, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00010767097966728281, | |
| "loss": 0.0748, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_accuracy": 0.8889031266017426, | |
| "eval_f1": 0.8889031266017426, | |
| "eval_loss": 0.3153642416000366, | |
| "eval_precision": 0.8889031266017426, | |
| "eval_recall": 0.8889031266017426, | |
| "eval_runtime": 68.6371, | |
| "eval_samples_per_second": 113.7, | |
| "eval_steps_per_second": 14.22, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00010720887245841036, | |
| "loss": 0.1478, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0001067467652495379, | |
| "loss": 0.0981, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00010628465804066543, | |
| "loss": 0.1564, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00010582255083179298, | |
| "loss": 0.1175, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00010536044362292052, | |
| "loss": 0.111, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00010489833641404806, | |
| "loss": 0.092, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010443622920517559, | |
| "loss": 0.22, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010397412199630315, | |
| "loss": 0.2015, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010351201478743069, | |
| "loss": 0.1481, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010304990757855824, | |
| "loss": 0.1385, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.8885187083546899, | |
| "eval_f1": 0.8885187083546898, | |
| "eval_loss": 0.29923757910728455, | |
| "eval_precision": 0.8885187083546899, | |
| "eval_recall": 0.8885187083546899, | |
| "eval_runtime": 68.1064, | |
| "eval_samples_per_second": 114.585, | |
| "eval_steps_per_second": 14.331, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010258780036968578, | |
| "loss": 0.1644, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010212569316081331, | |
| "loss": 0.2008, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010166358595194085, | |
| "loss": 0.098, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001012014787430684, | |
| "loss": 0.0939, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010073937153419595, | |
| "loss": 0.1489, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010027726432532347, | |
| "loss": 0.1203, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.981515711645101e-05, | |
| "loss": 0.1295, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.935304990757857e-05, | |
| "loss": 0.1278, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.889094269870611e-05, | |
| "loss": 0.1903, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.842883548983365e-05, | |
| "loss": 0.0977, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.8913377754997437, | |
| "eval_f1": 0.8913377754997437, | |
| "eval_loss": 0.2889121472835541, | |
| "eval_precision": 0.8913377754997437, | |
| "eval_recall": 0.8913377754997437, | |
| "eval_runtime": 68.4748, | |
| "eval_samples_per_second": 113.969, | |
| "eval_steps_per_second": 14.253, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.796672828096119e-05, | |
| "loss": 0.0756, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.750462107208873e-05, | |
| "loss": 0.0404, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.704251386321627e-05, | |
| "loss": 0.1256, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.658040665434381e-05, | |
| "loss": 0.0615, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.611829944547135e-05, | |
| "loss": 0.0658, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.565619223659889e-05, | |
| "loss": 0.0737, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.519408502772643e-05, | |
| "loss": 0.0916, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.473197781885397e-05, | |
| "loss": 0.1466, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.426987060998153e-05, | |
| "loss": 0.1003, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.380776340110906e-05, | |
| "loss": 0.1028, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.8967196309584828, | |
| "eval_f1": 0.896719630958483, | |
| "eval_loss": 0.2841860353946686, | |
| "eval_precision": 0.8967196309584828, | |
| "eval_recall": 0.8967196309584828, | |
| "eval_runtime": 68.3963, | |
| "eval_samples_per_second": 114.1, | |
| "eval_steps_per_second": 14.27, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.334565619223661e-05, | |
| "loss": 0.0405, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.288354898336414e-05, | |
| "loss": 0.1219, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.242144177449169e-05, | |
| "loss": 0.0436, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 9.195933456561923e-05, | |
| "loss": 0.1133, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.149722735674677e-05, | |
| "loss": 0.0337, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 9.103512014787431e-05, | |
| "loss": 0.0352, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 9.057301293900185e-05, | |
| "loss": 0.0833, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.01109057301294e-05, | |
| "loss": 0.1337, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.964879852125694e-05, | |
| "loss": 0.0989, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.918669131238448e-05, | |
| "loss": 0.1025, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_accuracy": 0.8965914915427986, | |
| "eval_f1": 0.8965914915427986, | |
| "eval_loss": 0.29971516132354736, | |
| "eval_precision": 0.8965914915427986, | |
| "eval_recall": 0.8965914915427986, | |
| "eval_runtime": 68.5274, | |
| "eval_samples_per_second": 113.881, | |
| "eval_steps_per_second": 14.242, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.872458410351202e-05, | |
| "loss": 0.0251, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 8.826247689463956e-05, | |
| "loss": 0.0982, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 8.78003696857671e-05, | |
| "loss": 0.1471, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.733826247689464e-05, | |
| "loss": 0.1594, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.687615526802218e-05, | |
| "loss": 0.0332, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.641404805914972e-05, | |
| "loss": 0.1071, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.595194085027726e-05, | |
| "loss": 0.0798, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.548983364140482e-05, | |
| "loss": 0.0821, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.502772643253236e-05, | |
| "loss": 0.0215, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.45656192236599e-05, | |
| "loss": 0.0482, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.9042798564838544, | |
| "eval_f1": 0.9042798564838544, | |
| "eval_loss": 0.34095844626426697, | |
| "eval_precision": 0.9042798564838544, | |
| "eval_recall": 0.9042798564838544, | |
| "eval_runtime": 68.072, | |
| "eval_samples_per_second": 114.643, | |
| "eval_steps_per_second": 14.338, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 8.410351201478744e-05, | |
| "loss": 0.1222, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.364140480591498e-05, | |
| "loss": 0.027, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 8.317929759704252e-05, | |
| "loss": 0.0643, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.271719038817006e-05, | |
| "loss": 0.0407, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.22550831792976e-05, | |
| "loss": 0.0333, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 8.179297597042514e-05, | |
| "loss": 0.0403, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.133086876155268e-05, | |
| "loss": 0.0177, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.086876155268022e-05, | |
| "loss": 0.1517, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 8.040665434380776e-05, | |
| "loss": 0.0199, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.99445471349353e-05, | |
| "loss": 0.1243, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.9044079958995387, | |
| "eval_f1": 0.9044079958995387, | |
| "eval_loss": 0.3357454836368561, | |
| "eval_precision": 0.9044079958995387, | |
| "eval_recall": 0.9044079958995387, | |
| "eval_runtime": 68.0304, | |
| "eval_samples_per_second": 114.713, | |
| "eval_steps_per_second": 14.347, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 7.948243992606285e-05, | |
| "loss": 0.0602, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.902033271719039e-05, | |
| "loss": 0.1411, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.855822550831793e-05, | |
| "loss": 0.035, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.809611829944548e-05, | |
| "loss": 0.0841, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.763401109057301e-05, | |
| "loss": 0.0555, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.717190388170056e-05, | |
| "loss": 0.0816, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.67097966728281e-05, | |
| "loss": 0.084, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.624768946395564e-05, | |
| "loss": 0.0386, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.578558225508319e-05, | |
| "loss": 0.1072, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.532347504621073e-05, | |
| "loss": 0.0591, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.9076114812916453, | |
| "eval_f1": 0.9076114812916453, | |
| "eval_loss": 0.30792462825775146, | |
| "eval_precision": 0.9076114812916453, | |
| "eval_recall": 0.9076114812916453, | |
| "eval_runtime": 68.2884, | |
| "eval_samples_per_second": 114.28, | |
| "eval_steps_per_second": 14.292, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.486136783733827e-05, | |
| "loss": 0.0895, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 7.439926062846581e-05, | |
| "loss": 0.0695, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.393715341959335e-05, | |
| "loss": 0.0611, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.347504621072089e-05, | |
| "loss": 0.0626, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.301293900184843e-05, | |
| "loss": 0.0839, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.255083179297597e-05, | |
| "loss": 0.0461, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.208872458410351e-05, | |
| "loss": 0.0526, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.162661737523105e-05, | |
| "loss": 0.0316, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.11645101663586e-05, | |
| "loss": 0.0486, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.070240295748613e-05, | |
| "loss": 0.0324, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_accuracy": 0.9147872885699642, | |
| "eval_f1": 0.9147872885699642, | |
| "eval_loss": 0.34335237741470337, | |
| "eval_precision": 0.9147872885699642, | |
| "eval_recall": 0.9147872885699642, | |
| "eval_runtime": 68.5353, | |
| "eval_samples_per_second": 113.868, | |
| "eval_steps_per_second": 14.241, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.024029574861369e-05, | |
| "loss": 0.0122, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.977818853974121e-05, | |
| "loss": 0.1058, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.931608133086877e-05, | |
| "loss": 0.0387, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.885397412199631e-05, | |
| "loss": 0.0595, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.839186691312385e-05, | |
| "loss": 0.0854, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.792975970425139e-05, | |
| "loss": 0.0681, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.746765249537893e-05, | |
| "loss": 0.0257, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.700554528650647e-05, | |
| "loss": 0.0952, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.654343807763401e-05, | |
| "loss": 0.0649, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 6.608133086876155e-05, | |
| "loss": 0.0677, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_accuracy": 0.9082521783700667, | |
| "eval_f1": 0.9082521783700667, | |
| "eval_loss": 0.31558722257614136, | |
| "eval_precision": 0.9082521783700667, | |
| "eval_recall": 0.9082521783700667, | |
| "eval_runtime": 68.148, | |
| "eval_samples_per_second": 114.516, | |
| "eval_steps_per_second": 14.322, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 6.56192236598891e-05, | |
| "loss": 0.108, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 6.515711645101664e-05, | |
| "loss": 0.1035, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 6.469500924214418e-05, | |
| "loss": 0.038, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 6.423290203327173e-05, | |
| "loss": 0.049, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 6.377079482439926e-05, | |
| "loss": 0.0731, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.330868761552681e-05, | |
| "loss": 0.0664, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.284658040665434e-05, | |
| "loss": 0.1097, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 6.23844731977819e-05, | |
| "loss": 0.0406, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 6.192236598890942e-05, | |
| "loss": 0.0191, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.146025878003697e-05, | |
| "loss": 0.0397, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_accuracy": 0.9123526396719631, | |
| "eval_f1": 0.9123526396719631, | |
| "eval_loss": 0.3390035331249237, | |
| "eval_precision": 0.9123526396719631, | |
| "eval_recall": 0.9123526396719631, | |
| "eval_runtime": 68.6139, | |
| "eval_samples_per_second": 113.738, | |
| "eval_steps_per_second": 14.225, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 6.099815157116451e-05, | |
| "loss": 0.0474, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 6.0536044362292056e-05, | |
| "loss": 0.0715, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 6.0073937153419604e-05, | |
| "loss": 0.0389, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.961182994454714e-05, | |
| "loss": 0.1132, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 5.9149722735674685e-05, | |
| "loss": 0.1018, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 5.868761552680222e-05, | |
| "loss": 0.0425, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 5.8225508317929767e-05, | |
| "loss": 0.0667, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.77634011090573e-05, | |
| "loss": 0.0111, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.730129390018485e-05, | |
| "loss": 0.0256, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.683918669131238e-05, | |
| "loss": 0.0103, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_accuracy": 0.9105586878523834, | |
| "eval_f1": 0.9105586878523834, | |
| "eval_loss": 0.3102366626262665, | |
| "eval_precision": 0.9105586878523834, | |
| "eval_recall": 0.9105586878523834, | |
| "eval_runtime": 68.32, | |
| "eval_samples_per_second": 114.227, | |
| "eval_steps_per_second": 14.286, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.637707948243993e-05, | |
| "loss": 0.0942, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 5.591497227356747e-05, | |
| "loss": 0.0908, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 5.545286506469501e-05, | |
| "loss": 0.0738, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 5.499075785582255e-05, | |
| "loss": 0.0424, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.45286506469501e-05, | |
| "loss": 0.031, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.406654343807763e-05, | |
| "loss": 0.0198, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.360443622920518e-05, | |
| "loss": 0.1189, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.3142329020332715e-05, | |
| "loss": 0.0706, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.268022181146026e-05, | |
| "loss": 0.0433, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.2218114602587796e-05, | |
| "loss": 0.0359, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.9133777549974372, | |
| "eval_f1": 0.9133777549974372, | |
| "eval_loss": 0.28472408652305603, | |
| "eval_precision": 0.9133777549974372, | |
| "eval_recall": 0.9133777549974372, | |
| "eval_runtime": 68.1744, | |
| "eval_samples_per_second": 114.471, | |
| "eval_steps_per_second": 14.316, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.1756007393715344e-05, | |
| "loss": 0.0368, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 5.129390018484289e-05, | |
| "loss": 0.0264, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.0831792975970425e-05, | |
| "loss": 0.0445, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.036968576709797e-05, | |
| "loss": 0.0577, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.9907578558225506e-05, | |
| "loss": 0.0188, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.9445471349353054e-05, | |
| "loss": 0.0377, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.8983364140480595e-05, | |
| "loss": 0.0034, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.8521256931608135e-05, | |
| "loss": 0.0107, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.8059149722735676e-05, | |
| "loss": 0.0663, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.759704251386322e-05, | |
| "loss": 0.0073, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_accuracy": 0.9077396207073296, | |
| "eval_f1": 0.9077396207073296, | |
| "eval_loss": 0.4039416015148163, | |
| "eval_precision": 0.9077396207073296, | |
| "eval_recall": 0.9077396207073296, | |
| "eval_runtime": 68.3922, | |
| "eval_samples_per_second": 114.107, | |
| "eval_steps_per_second": 14.271, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.7134935304990764e-05, | |
| "loss": 0.0183, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 4.6672828096118305e-05, | |
| "loss": 0.0279, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.6210720887245846e-05, | |
| "loss": 0.0031, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 4.5748613678373387e-05, | |
| "loss": 0.018, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.528650646950093e-05, | |
| "loss": 0.0357, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.482439926062847e-05, | |
| "loss": 0.0251, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.436229205175601e-05, | |
| "loss": 0.0225, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 4.390018484288355e-05, | |
| "loss": 0.0069, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 4.343807763401109e-05, | |
| "loss": 0.0369, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.297597042513863e-05, | |
| "loss": 0.0156, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_accuracy": 0.9100461301896463, | |
| "eval_f1": 0.9100461301896463, | |
| "eval_loss": 0.36297839879989624, | |
| "eval_precision": 0.9100461301896463, | |
| "eval_recall": 0.9100461301896463, | |
| "eval_runtime": 68.0978, | |
| "eval_samples_per_second": 114.6, | |
| "eval_steps_per_second": 14.332, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 4.251386321626618e-05, | |
| "loss": 0.0581, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 4.205175600739372e-05, | |
| "loss": 0.0071, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.158964879852126e-05, | |
| "loss": 0.0056, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.11275415896488e-05, | |
| "loss": 0.0045, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.066543438077634e-05, | |
| "loss": 0.0107, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.020332717190388e-05, | |
| "loss": 0.0397, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.974121996303142e-05, | |
| "loss": 0.0055, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.9279112754158964e-05, | |
| "loss": 0.0028, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.8817005545286504e-05, | |
| "loss": 0.0409, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.835489833641405e-05, | |
| "loss": 0.003, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_accuracy": 0.9142747309072271, | |
| "eval_f1": 0.9142747309072271, | |
| "eval_loss": 0.3671279847621918, | |
| "eval_precision": 0.9142747309072271, | |
| "eval_recall": 0.9142747309072271, | |
| "eval_runtime": 68.7404, | |
| "eval_samples_per_second": 113.529, | |
| "eval_steps_per_second": 14.198, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 3.789279112754159e-05, | |
| "loss": 0.0518, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.743068391866913e-05, | |
| "loss": 0.0201, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.6968576709796674e-05, | |
| "loss": 0.0636, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.6506469500924215e-05, | |
| "loss": 0.0068, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.6044362292051755e-05, | |
| "loss": 0.0017, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.55822550831793e-05, | |
| "loss": 0.0016, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.5120147874306844e-05, | |
| "loss": 0.0102, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 3.4658040665434384e-05, | |
| "loss": 0.0447, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.4195933456561925e-05, | |
| "loss": 0.0414, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.3733826247689466e-05, | |
| "loss": 0.0262, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_accuracy": 0.9151717068170169, | |
| "eval_f1": 0.9151717068170169, | |
| "eval_loss": 0.3538494110107422, | |
| "eval_precision": 0.9151717068170169, | |
| "eval_recall": 0.9151717068170169, | |
| "eval_runtime": 68.3495, | |
| "eval_samples_per_second": 114.178, | |
| "eval_steps_per_second": 14.28, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.3271719038817007e-05, | |
| "loss": 0.0023, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.280961182994455e-05, | |
| "loss": 0.0051, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.234750462107209e-05, | |
| "loss": 0.0071, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.188539741219963e-05, | |
| "loss": 0.0188, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.142329020332717e-05, | |
| "loss": 0.0025, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.096118299445471e-05, | |
| "loss": 0.0142, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.0499075785582254e-05, | |
| "loss": 0.004, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.0036968576709802e-05, | |
| "loss": 0.0016, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.9574861367837343e-05, | |
| "loss": 0.013, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.9112754158964883e-05, | |
| "loss": 0.0035, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "eval_accuracy": 0.9150435674013326, | |
| "eval_f1": 0.9150435674013326, | |
| "eval_loss": 0.3822227716445923, | |
| "eval_precision": 0.9150435674013326, | |
| "eval_recall": 0.9150435674013326, | |
| "eval_runtime": 68.2595, | |
| "eval_samples_per_second": 114.328, | |
| "eval_steps_per_second": 14.298, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2.8650646950092424e-05, | |
| "loss": 0.0065, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.8188539741219965e-05, | |
| "loss": 0.0026, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.7726432532347505e-05, | |
| "loss": 0.032, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 2.726432532347505e-05, | |
| "loss": 0.0032, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.680221811460259e-05, | |
| "loss": 0.0545, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.634011090573013e-05, | |
| "loss": 0.0207, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.5878003696857672e-05, | |
| "loss": 0.0684, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 2.5415896487985213e-05, | |
| "loss": 0.0084, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.4953789279112753e-05, | |
| "loss": 0.0339, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 2.4491682070240297e-05, | |
| "loss": 0.0441, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.9187596104561763, | |
| "eval_f1": 0.9187596104561763, | |
| "eval_loss": 0.3571091592311859, | |
| "eval_precision": 0.9187596104561763, | |
| "eval_recall": 0.9187596104561763, | |
| "eval_runtime": 67.9741, | |
| "eval_samples_per_second": 114.808, | |
| "eval_steps_per_second": 14.358, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 2.4029574861367838e-05, | |
| "loss": 0.0018, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.3567467652495382e-05, | |
| "loss": 0.0153, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 2.3105360443622923e-05, | |
| "loss": 0.0046, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 2.2643253234750464e-05, | |
| "loss": 0.0039, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.2181146025878004e-05, | |
| "loss": 0.0058, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2.1719038817005545e-05, | |
| "loss": 0.0023, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 2.125693160813309e-05, | |
| "loss": 0.0132, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2.079482439926063e-05, | |
| "loss": 0.0047, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 2.033271719038817e-05, | |
| "loss": 0.022, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.987060998151571e-05, | |
| "loss": 0.0017, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.9156842644797539, | |
| "eval_f1": 0.9156842644797539, | |
| "eval_loss": 0.37933284044265747, | |
| "eval_precision": 0.9156842644797539, | |
| "eval_recall": 0.9156842644797539, | |
| "eval_runtime": 68.4442, | |
| "eval_samples_per_second": 114.02, | |
| "eval_steps_per_second": 14.26, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.9408502772643252e-05, | |
| "loss": 0.047, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.8946395563770796e-05, | |
| "loss": 0.0494, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.8484288354898337e-05, | |
| "loss": 0.0146, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.8022181146025878e-05, | |
| "loss": 0.0397, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.7560073937153422e-05, | |
| "loss": 0.0047, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.7097966728280963e-05, | |
| "loss": 0.0017, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.6635859519408503e-05, | |
| "loss": 0.0299, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.6173752310536044e-05, | |
| "loss": 0.0049, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.5711645101663585e-05, | |
| "loss": 0.003, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.5249537892791127e-05, | |
| "loss": 0.0471, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_accuracy": 0.9213223987698617, | |
| "eval_f1": 0.9213223987698617, | |
| "eval_loss": 0.3491326570510864, | |
| "eval_precision": 0.9213223987698617, | |
| "eval_recall": 0.9213223987698617, | |
| "eval_runtime": 68.4265, | |
| "eval_samples_per_second": 114.049, | |
| "eval_steps_per_second": 14.263, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.4787430683918671e-05, | |
| "loss": 0.002, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.4325323475046212e-05, | |
| "loss": 0.0124, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.3863216266173753e-05, | |
| "loss": 0.003, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.3401109057301295e-05, | |
| "loss": 0.002, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.2939001848428836e-05, | |
| "loss": 0.0017, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.2476894639556377e-05, | |
| "loss": 0.0392, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.2014787430683919e-05, | |
| "loss": 0.0018, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.1552680221811461e-05, | |
| "loss": 0.0029, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.1090573012939002e-05, | |
| "loss": 0.002, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.0628465804066545e-05, | |
| "loss": 0.0018, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_accuracy": 0.9237570476678626, | |
| "eval_f1": 0.9237570476678626, | |
| "eval_loss": 0.3485581874847412, | |
| "eval_precision": 0.9237570476678626, | |
| "eval_recall": 0.9237570476678626, | |
| "eval_runtime": 68.4231, | |
| "eval_samples_per_second": 114.055, | |
| "eval_steps_per_second": 14.264, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.0166358595194085e-05, | |
| "loss": 0.0025, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 9.704251386321626e-06, | |
| "loss": 0.0016, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 9.242144177449168e-06, | |
| "loss": 0.0017, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 8.780036968576711e-06, | |
| "loss": 0.0079, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 8.317929759704252e-06, | |
| "loss": 0.0013, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 7.855822550831792e-06, | |
| "loss": 0.0014, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.393715341959336e-06, | |
| "loss": 0.0516, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 6.931608133086876e-06, | |
| "loss": 0.0365, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.469500924214418e-06, | |
| "loss": 0.101, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.0073937153419595e-06, | |
| "loss": 0.0405, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_accuracy": 0.9247821629933367, | |
| "eval_f1": 0.9247821629933367, | |
| "eval_loss": 0.34783050417900085, | |
| "eval_precision": 0.9247821629933367, | |
| "eval_recall": 0.9247821629933367, | |
| "eval_runtime": 68.4105, | |
| "eval_samples_per_second": 114.076, | |
| "eval_steps_per_second": 14.267, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 5.545286506469501e-06, | |
| "loss": 0.0275, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 5.083179297597043e-06, | |
| "loss": 0.0171, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.621072088724584e-06, | |
| "loss": 0.0017, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.158964879852126e-06, | |
| "loss": 0.0015, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.696857670979668e-06, | |
| "loss": 0.0016, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3.234750462107209e-06, | |
| "loss": 0.0016, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 2.7726432532347505e-06, | |
| "loss": 0.0016, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 2.310536044362292e-06, | |
| "loss": 0.0019, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.848428835489834e-06, | |
| "loss": 0.002, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 1.3863216266173753e-06, | |
| "loss": 0.0231, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_accuracy": 0.9264479753972322, | |
| "eval_f1": 0.9264479753972322, | |
| "eval_loss": 0.3471040725708008, | |
| "eval_precision": 0.9264479753972322, | |
| "eval_recall": 0.9264479753972322, | |
| "eval_runtime": 68.418, | |
| "eval_samples_per_second": 114.063, | |
| "eval_steps_per_second": 14.265, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 9.24214417744917e-07, | |
| "loss": 0.0042, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.621072088724585e-07, | |
| "loss": 0.0024, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 4328, | |
| "total_flos": 5.46724420897407e+18, | |
| "train_loss": 0.13911021860271638, | |
| "train_runtime": 4391.8871, | |
| "train_samples_per_second": 15.76, | |
| "train_steps_per_second": 0.985 | |
| } | |
| ], | |
| "max_steps": 4328, | |
| "num_train_epochs": 4, | |
| "total_flos": 5.46724420897407e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |