| { | |
| "best_metric": 0.8990687138182734, | |
| "best_model_checkpoint": "vit-cxr4-384/checkpoint-2400", | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 2552, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.982366771159875e-05, | |
| "loss": 0.7452, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9627742946708465e-05, | |
| "loss": 0.5821, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.943181818181818e-05, | |
| "loss": 0.5277, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.92358934169279e-05, | |
| "loss": 0.5076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.903996865203762e-05, | |
| "loss": 0.4483, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.8844043887147336e-05, | |
| "loss": 0.5492, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.864811912225706e-05, | |
| "loss": 0.3997, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.845219435736678e-05, | |
| "loss": 0.4182, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.4935, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.807993730407524e-05, | |
| "loss": 0.3694, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8233603344656388, | |
| "eval_f1": 0.8251422659079152, | |
| "eval_loss": 0.3850725293159485, | |
| "eval_precision": 0.8075949367088607, | |
| "eval_recall": 0.8434690639873083, | |
| "eval_runtime": 172.1875, | |
| "eval_samples_per_second": 22.226, | |
| "eval_steps_per_second": 0.929, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.788401253918495e-05, | |
| "loss": 0.3867, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.768808777429467e-05, | |
| "loss": 0.4248, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.749216300940439e-05, | |
| "loss": 0.331, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.7296238244514106e-05, | |
| "loss": 0.3978, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.7100313479623823e-05, | |
| "loss": 0.3176, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.690438871473354e-05, | |
| "loss": 0.5361, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.670846394984326e-05, | |
| "loss": 0.3897, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.651253918495298e-05, | |
| "loss": 0.3066, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.63166144200627e-05, | |
| "loss": 0.3042, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.612068965517242e-05, | |
| "loss": 0.3084, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8364253984844525, | |
| "eval_f1": 0.8566193311956023, | |
| "eval_loss": 0.4478375017642975, | |
| "eval_precision": 0.7555555555555555, | |
| "eval_recall": 0.9888947646747752, | |
| "eval_runtime": 168.684, | |
| "eval_samples_per_second": 22.687, | |
| "eval_steps_per_second": 0.949, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.592476489028214e-05, | |
| "loss": 0.4338, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.5728840125391855e-05, | |
| "loss": 0.3653, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.553291536050157e-05, | |
| "loss": 0.3125, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.533699059561129e-05, | |
| "loss": 0.4054, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.514106583072101e-05, | |
| "loss": 0.3616, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.4945141065830726e-05, | |
| "loss": 0.3286, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.474921630094044e-05, | |
| "loss": 0.3067, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.4553291536050155e-05, | |
| "loss": 0.3698, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.435736677115987e-05, | |
| "loss": 0.3418, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.416144200626959e-05, | |
| "loss": 0.3177, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.8651685393258427, | |
| "eval_f1": 0.8752417794970986, | |
| "eval_loss": 0.30726760625839233, | |
| "eval_precision": 0.8062360801781737, | |
| "eval_recall": 0.9571655208884188, | |
| "eval_runtime": 167.4202, | |
| "eval_samples_per_second": 22.859, | |
| "eval_steps_per_second": 0.956, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.396551724137931e-05, | |
| "loss": 0.2805, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.3769592476489026e-05, | |
| "loss": 0.3783, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.357366771159875e-05, | |
| "loss": 0.2961, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.337774294670847e-05, | |
| "loss": 0.2732, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.318181818181819e-05, | |
| "loss": 0.2852, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.2985893416927904e-05, | |
| "loss": 0.307, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.278996865203762e-05, | |
| "loss": 0.3855, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.259404388714734e-05, | |
| "loss": 0.3382, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.239811912225706e-05, | |
| "loss": 0.2779, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.2202194357366776e-05, | |
| "loss": 0.3413, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.8677815521296054, | |
| "eval_f1": 0.8757977417771232, | |
| "eval_loss": 0.2936372458934784, | |
| "eval_precision": 0.8172240036646816, | |
| "eval_recall": 0.9434161819143311, | |
| "eval_runtime": 166.7592, | |
| "eval_samples_per_second": 22.949, | |
| "eval_steps_per_second": 0.959, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.2006269592476494e-05, | |
| "loss": 0.266, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.1810344827586205e-05, | |
| "loss": 0.3177, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.161442006269592e-05, | |
| "loss": 0.2613, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.141849529780564e-05, | |
| "loss": 0.3307, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.122257053291536e-05, | |
| "loss": 0.2463, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.1026645768025076e-05, | |
| "loss": 0.2588, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.08307210031348e-05, | |
| "loss": 0.4268, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.063479623824452e-05, | |
| "loss": 0.3498, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.0438871473354236e-05, | |
| "loss": 0.3102, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.0242946708463954e-05, | |
| "loss": 0.2612, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.8709171674941207, | |
| "eval_f1": 0.8747464503042597, | |
| "eval_loss": 0.29362666606903076, | |
| "eval_precision": 0.8402338041889917, | |
| "eval_recall": 0.9122157588577472, | |
| "eval_runtime": 166.9694, | |
| "eval_samples_per_second": 22.92, | |
| "eval_steps_per_second": 0.958, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.004702194357367e-05, | |
| "loss": 0.3364, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.985109717868339e-05, | |
| "loss": 0.2959, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.965517241379311e-05, | |
| "loss": 0.289, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.9459247648902825e-05, | |
| "loss": 0.3726, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.926332288401254e-05, | |
| "loss": 0.2789, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.906739811912226e-05, | |
| "loss": 0.3125, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.887147335423197e-05, | |
| "loss": 0.3008, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.867554858934169e-05, | |
| "loss": 0.3505, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.847962382445141e-05, | |
| "loss": 0.3043, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3.828369905956113e-05, | |
| "loss": 0.3607, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.876927096942775, | |
| "eval_f1": 0.8852059468681452, | |
| "eval_loss": 0.2716532349586487, | |
| "eval_precision": 0.8209764918625678, | |
| "eval_recall": 0.9603384452670545, | |
| "eval_runtime": 165.7826, | |
| "eval_samples_per_second": 23.084, | |
| "eval_steps_per_second": 0.965, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 3.808777429467085e-05, | |
| "loss": 0.3092, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 3.789184952978057e-05, | |
| "loss": 0.2916, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 3.7695924764890286e-05, | |
| "loss": 0.2446, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.3083, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 3.730407523510972e-05, | |
| "loss": 0.2633, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 3.710815047021944e-05, | |
| "loss": 0.2867, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3.691222570532916e-05, | |
| "loss": 0.2652, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3.6716300940438875e-05, | |
| "loss": 0.2317, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.652037617554859e-05, | |
| "loss": 0.2298, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 3.632445141065831e-05, | |
| "loss": 0.274, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.8719623726156258, | |
| "eval_f1": 0.8765120967741936, | |
| "eval_loss": 0.2875473201274872, | |
| "eval_precision": 0.8372652864708714, | |
| "eval_recall": 0.9196192490745637, | |
| "eval_runtime": 165.0637, | |
| "eval_samples_per_second": 23.185, | |
| "eval_steps_per_second": 0.969, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3.612852664576803e-05, | |
| "loss": 0.2862, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3.593260188087774e-05, | |
| "loss": 0.2746, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.573667711598746e-05, | |
| "loss": 0.2948, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.554075235109718e-05, | |
| "loss": 0.2878, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.53448275862069e-05, | |
| "loss": 0.2381, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.514890282131662e-05, | |
| "loss": 0.2854, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.4952978056426335e-05, | |
| "loss": 0.2571, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.475705329153605e-05, | |
| "loss": 0.2587, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.456112852664577e-05, | |
| "loss": 0.2867, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.436520376175549e-05, | |
| "loss": 0.3127, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.8761431931016462, | |
| "eval_f1": 0.8853965183752417, | |
| "eval_loss": 0.26641419529914856, | |
| "eval_precision": 0.8155902004454343, | |
| "eval_recall": 0.9682707562136436, | |
| "eval_runtime": 175.8421, | |
| "eval_samples_per_second": 21.764, | |
| "eval_steps_per_second": 0.91, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.4169278996865206e-05, | |
| "loss": 0.3393, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.3973354231974924e-05, | |
| "loss": 0.2543, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.377742946708464e-05, | |
| "loss": 0.2367, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.358150470219436e-05, | |
| "loss": 0.3035, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.338557993730408e-05, | |
| "loss": 0.3645, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3189655172413796e-05, | |
| "loss": 0.2589, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.299373040752351e-05, | |
| "loss": 0.244, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.279780564263323e-05, | |
| "loss": 0.2688, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.260188087774295e-05, | |
| "loss": 0.2616, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.240595611285267e-05, | |
| "loss": 0.2875, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.8771883982231513, | |
| "eval_f1": 0.8825, | |
| "eval_loss": 0.2643195688724518, | |
| "eval_precision": 0.8368895211000474, | |
| "eval_recall": 0.9333685880486515, | |
| "eval_runtime": 172.9293, | |
| "eval_samples_per_second": 22.13, | |
| "eval_steps_per_second": 0.925, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.2210031347962385e-05, | |
| "loss": 0.2741, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.20141065830721e-05, | |
| "loss": 0.2502, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.2983, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.162225705329154e-05, | |
| "loss": 0.26, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.1426332288401256e-05, | |
| "loss": 0.2931, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.1230407523510974e-05, | |
| "loss": 0.2665, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.103448275862069e-05, | |
| "loss": 0.2586, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.083855799373041e-05, | |
| "loss": 0.2245, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.064263322884013e-05, | |
| "loss": 0.2973, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.044670846394985e-05, | |
| "loss": 0.2652, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.8745753854193885, | |
| "eval_f1": 0.8841139546112989, | |
| "eval_loss": 0.2659239172935486, | |
| "eval_precision": 0.8134162594402488, | |
| "eval_recall": 0.9682707562136436, | |
| "eval_runtime": 172.1185, | |
| "eval_samples_per_second": 22.235, | |
| "eval_steps_per_second": 0.93, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.0250783699059566e-05, | |
| "loss": 0.2408, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.0054858934169277e-05, | |
| "loss": 0.284, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.9858934169278995e-05, | |
| "loss": 0.2906, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.9663009404388713e-05, | |
| "loss": 0.2415, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.946708463949843e-05, | |
| "loss": 0.2642, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.9271159874608152e-05, | |
| "loss": 0.2606, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.907523510971787e-05, | |
| "loss": 0.3017, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.8879310344827588e-05, | |
| "loss": 0.2525, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.8683385579937305e-05, | |
| "loss": 0.2373, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.8487460815047023e-05, | |
| "loss": 0.2661, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.8792788084661615, | |
| "eval_f1": 0.885473475458602, | |
| "eval_loss": 0.2590779662132263, | |
| "eval_precision": 0.8334111059262715, | |
| "eval_recall": 0.9444738233738763, | |
| "eval_runtime": 172.4587, | |
| "eval_samples_per_second": 22.191, | |
| "eval_steps_per_second": 0.928, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.829153605015674e-05, | |
| "loss": 0.2587, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.809561128526646e-05, | |
| "loss": 0.2987, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.7899686520376177e-05, | |
| "loss": 0.2422, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.7703761755485898e-05, | |
| "loss": 0.2469, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.7507836990595616e-05, | |
| "loss": 0.2884, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.7311912225705334e-05, | |
| "loss": 0.264, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.711598746081505e-05, | |
| "loss": 0.3332, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.6920062695924762e-05, | |
| "loss": 0.241, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.672413793103448e-05, | |
| "loss": 0.2405, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.65282131661442e-05, | |
| "loss": 0.3019, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.8756205905408937, | |
| "eval_f1": 0.8723175965665235, | |
| "eval_loss": 0.27287837862968445, | |
| "eval_precision": 0.8851388132825259, | |
| "eval_recall": 0.8598625066102591, | |
| "eval_runtime": 172.6345, | |
| "eval_samples_per_second": 22.168, | |
| "eval_steps_per_second": 0.927, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.633228840125392e-05, | |
| "loss": 0.241, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.6136363636363637e-05, | |
| "loss": 0.1991, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.5940438871473355e-05, | |
| "loss": 0.2499, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.5744514106583073e-05, | |
| "loss": 0.335, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.554858934169279e-05, | |
| "loss": 0.2865, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.535266457680251e-05, | |
| "loss": 0.2706, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.5156739811912226e-05, | |
| "loss": 0.3153, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.4960815047021947e-05, | |
| "loss": 0.2667, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.4764890282131662e-05, | |
| "loss": 0.2463, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.456896551724138e-05, | |
| "loss": 0.229, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.8871178468774497, | |
| "eval_f1": 0.8937007874015748, | |
| "eval_loss": 0.25479769706726074, | |
| "eval_precision": 0.8357109986194201, | |
| "eval_recall": 0.9603384452670545, | |
| "eval_runtime": 173.7953, | |
| "eval_samples_per_second": 22.02, | |
| "eval_steps_per_second": 0.921, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.4373040752351098e-05, | |
| "loss": 0.2328, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.4177115987460815e-05, | |
| "loss": 0.1678, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2.3981191222570533e-05, | |
| "loss": 0.2616, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.378526645768025e-05, | |
| "loss": 0.2398, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.3589341692789972e-05, | |
| "loss": 0.275, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.339341692789969e-05, | |
| "loss": 0.1851, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.3197492163009404e-05, | |
| "loss": 0.2828, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.3001567398119122e-05, | |
| "loss": 0.2727, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.280564263322884e-05, | |
| "loss": 0.259, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.2609717868338558e-05, | |
| "loss": 0.1841, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.8863339430363208, | |
| "eval_f1": 0.8890589135424637, | |
| "eval_loss": 0.24377945065498352, | |
| "eval_precision": 0.8586206896551725, | |
| "eval_recall": 0.9217345319936542, | |
| "eval_runtime": 176.1028, | |
| "eval_samples_per_second": 21.732, | |
| "eval_steps_per_second": 0.909, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.2413793103448276e-05, | |
| "loss": 0.2321, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.2217868338557997e-05, | |
| "loss": 0.2112, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2.2021943573667715e-05, | |
| "loss": 0.1736, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.182601880877743e-05, | |
| "loss": 0.2211, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.1630094043887147e-05, | |
| "loss": 0.1855, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.1434169278996865e-05, | |
| "loss": 0.2346, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.1238244514106583e-05, | |
| "loss": 0.1662, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.10423197492163e-05, | |
| "loss": 0.2776, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.0846394984326022e-05, | |
| "loss": 0.2281, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.065047021943574e-05, | |
| "loss": 0.2257, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.8905147635223413, | |
| "eval_f1": 0.8930849706557795, | |
| "eval_loss": 0.2364816665649414, | |
| "eval_precision": 0.8629191321499013, | |
| "eval_recall": 0.9254362771020624, | |
| "eval_runtime": 173.2602, | |
| "eval_samples_per_second": 22.088, | |
| "eval_steps_per_second": 0.923, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.0454545454545457e-05, | |
| "loss": 0.2546, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.0258620689655172e-05, | |
| "loss": 0.139, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.006269592476489e-05, | |
| "loss": 0.2382, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.9866771159874607e-05, | |
| "loss": 0.2475, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.9670846394984325e-05, | |
| "loss": 0.262, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.9474921630094046e-05, | |
| "loss": 0.211, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.9278996865203764e-05, | |
| "loss": 0.2436, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.9083072100313482e-05, | |
| "loss": 0.1954, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.8887147335423197e-05, | |
| "loss": 0.174, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.8691222570532914e-05, | |
| "loss": 0.2217, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.8803240135876665, | |
| "eval_f1": 0.8773433315479378, | |
| "eval_loss": 0.25091663002967834, | |
| "eval_precision": 0.8887683125339121, | |
| "eval_recall": 0.8662083553675304, | |
| "eval_runtime": 168.9717, | |
| "eval_samples_per_second": 22.649, | |
| "eval_steps_per_second": 0.947, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.8495297805642632e-05, | |
| "loss": 0.2478, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.829937304075235e-05, | |
| "loss": 0.2255, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.810344827586207e-05, | |
| "loss": 0.1823, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.790752351097179e-05, | |
| "loss": 0.1716, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.7711598746081507e-05, | |
| "loss": 0.2434, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.7515673981191225e-05, | |
| "loss": 0.1945, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.731974921630094e-05, | |
| "loss": 0.1695, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.7123824451410657e-05, | |
| "loss": 0.181, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.6927899686520378e-05, | |
| "loss": 0.2047, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.6731974921630096e-05, | |
| "loss": 0.2619, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_accuracy": 0.8873791481578259, | |
| "eval_f1": 0.893711467324291, | |
| "eval_loss": 0.25879478454589844, | |
| "eval_precision": 0.8373382624768947, | |
| "eval_recall": 0.958223162347964, | |
| "eval_runtime": 167.0043, | |
| "eval_samples_per_second": 22.916, | |
| "eval_steps_per_second": 0.958, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.6536050156739814e-05, | |
| "loss": 0.2562, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.634012539184953e-05, | |
| "loss": 0.2448, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.614420062695925e-05, | |
| "loss": 0.2452, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.5948275862068967e-05, | |
| "loss": 0.225, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.5752351097178682e-05, | |
| "loss": 0.1817, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.5556426332288403e-05, | |
| "loss": 0.1978, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.536050156739812e-05, | |
| "loss": 0.1928, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.5164576802507839e-05, | |
| "loss": 0.2085, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.4968652037617556e-05, | |
| "loss": 0.1174, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.4772727272727274e-05, | |
| "loss": 0.2222, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_accuracy": 0.8907760648027175, | |
| "eval_f1": 0.8931492842535788, | |
| "eval_loss": 0.2520654797554016, | |
| "eval_precision": 0.8644235526966848, | |
| "eval_recall": 0.9238498149127445, | |
| "eval_runtime": 168.4799, | |
| "eval_samples_per_second": 22.715, | |
| "eval_steps_per_second": 0.95, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.4576802507836992e-05, | |
| "loss": 0.2499, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.4380877742946708e-05, | |
| "loss": 0.231, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.4184952978056426e-05, | |
| "loss": 0.2446, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.3989028213166144e-05, | |
| "loss": 0.2212, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.3793103448275863e-05, | |
| "loss": 0.1873, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.3597178683385581e-05, | |
| "loss": 0.1655, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.3401253918495299e-05, | |
| "loss": 0.1798, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.3205329153605017e-05, | |
| "loss": 0.212, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.3009404388714735e-05, | |
| "loss": 0.2339, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.281347962382445e-05, | |
| "loss": 0.2044, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_accuracy": 0.8899921609615887, | |
| "eval_f1": 0.895972325179145, | |
| "eval_loss": 0.2598423957824707, | |
| "eval_precision": 0.8409090909090909, | |
| "eval_recall": 0.9587519830777367, | |
| "eval_runtime": 168.1275, | |
| "eval_samples_per_second": 22.762, | |
| "eval_steps_per_second": 0.952, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.2617554858934169e-05, | |
| "loss": 0.1993, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.2421630094043888e-05, | |
| "loss": 0.2176, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.2225705329153606e-05, | |
| "loss": 0.1554, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.2029780564263324e-05, | |
| "loss": 0.2332, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.1833855799373042e-05, | |
| "loss": 0.1662, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.163793103448276e-05, | |
| "loss": 0.1932, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.1442006269592477e-05, | |
| "loss": 0.1996, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.1246081504702195e-05, | |
| "loss": 0.1516, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.1050156739811913e-05, | |
| "loss": 0.2517, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.085423197492163e-05, | |
| "loss": 0.2238, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_accuracy": 0.8764044943820225, | |
| "eval_f1": 0.8690838638250762, | |
| "eval_loss": 0.264072448015213, | |
| "eval_precision": 0.9117305458768873, | |
| "eval_recall": 0.8302485457429931, | |
| "eval_runtime": 166.9078, | |
| "eval_samples_per_second": 22.929, | |
| "eval_steps_per_second": 0.959, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.0658307210031348e-05, | |
| "loss": 0.2006, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.0462382445141066e-05, | |
| "loss": 0.1282, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.0266457680250784e-05, | |
| "loss": 0.1714, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.0070532915360502e-05, | |
| "loss": 0.1795, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.87460815047022e-06, | |
| "loss": 0.1915, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.678683385579938e-06, | |
| "loss": 0.2153, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.482758620689655e-06, | |
| "loss": 0.2176, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.286833855799373e-06, | |
| "loss": 0.2194, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.1527, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.89498432601881e-06, | |
| "loss": 0.249, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_accuracy": 0.8926051737653514, | |
| "eval_f1": 0.8979389123416935, | |
| "eval_loss": 0.2367783486843109, | |
| "eval_precision": 0.846441947565543, | |
| "eval_recall": 0.9561078794288737, | |
| "eval_runtime": 167.7276, | |
| "eval_samples_per_second": 22.817, | |
| "eval_steps_per_second": 0.954, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.699059561128527e-06, | |
| "loss": 0.175, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.503134796238245e-06, | |
| "loss": 0.2238, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.307210031347962e-06, | |
| "loss": 0.2249, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.111285266457682e-06, | |
| "loss": 0.2395, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 7.915360501567398e-06, | |
| "loss": 0.1775, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 7.719435736677116e-06, | |
| "loss": 0.2111, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.5235109717868345e-06, | |
| "loss": 0.2092, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 7.3275862068965514e-06, | |
| "loss": 0.2313, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.131661442006269e-06, | |
| "loss": 0.1508, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 6.935736677115988e-06, | |
| "loss": 0.1773, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_accuracy": 0.894172981447609, | |
| "eval_f1": 0.8963929393706831, | |
| "eval_loss": 0.22330810129642487, | |
| "eval_precision": 0.8681863230921705, | |
| "eval_recall": 0.9264939185616076, | |
| "eval_runtime": 166.0964, | |
| "eval_samples_per_second": 23.041, | |
| "eval_steps_per_second": 0.963, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 6.739811912225706e-06, | |
| "loss": 0.165, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 6.543887147335423e-06, | |
| "loss": 0.2013, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 6.347962382445141e-06, | |
| "loss": 0.2334, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 6.152037617554859e-06, | |
| "loss": 0.1951, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 5.956112852664577e-06, | |
| "loss": 0.165, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 5.760188087774295e-06, | |
| "loss": 0.1469, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 5.564263322884013e-06, | |
| "loss": 0.2499, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 5.368338557993731e-06, | |
| "loss": 0.1992, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 5.172413793103448e-06, | |
| "loss": 0.2433, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.976489028213167e-06, | |
| "loss": 0.1447, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.8957407891298668, | |
| "eval_f1": 0.8970322580645161, | |
| "eval_loss": 0.22690534591674805, | |
| "eval_precision": 0.876008064516129, | |
| "eval_recall": 0.9190904283447912, | |
| "eval_runtime": 166.3913, | |
| "eval_samples_per_second": 23.0, | |
| "eval_steps_per_second": 0.962, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.780564263322884e-06, | |
| "loss": 0.2265, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 4.584639498432603e-06, | |
| "loss": 0.1754, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.38871473354232e-06, | |
| "loss": 0.1462, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.1927899686520374e-06, | |
| "loss": 0.1796, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.996865203761756e-06, | |
| "loss": 0.1956, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.800940438871473e-06, | |
| "loss": 0.2103, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.6050156739811913e-06, | |
| "loss": 0.1791, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.409090909090909e-06, | |
| "loss": 0.1634, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.2131661442006274e-06, | |
| "loss": 0.1923, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.017241379310345e-06, | |
| "loss": 0.245, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_accuracy": 0.8952181865691142, | |
| "eval_f1": 0.8990687138182734, | |
| "eval_loss": 0.23547519743442535, | |
| "eval_precision": 0.8578290105667628, | |
| "eval_recall": 0.9444738233738763, | |
| "eval_runtime": 166.9651, | |
| "eval_samples_per_second": 22.921, | |
| "eval_steps_per_second": 0.958, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.821316614420063e-06, | |
| "loss": 0.1853, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.625391849529781e-06, | |
| "loss": 0.1623, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.4294670846394982e-06, | |
| "loss": 0.2096, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.233542319749216e-06, | |
| "loss": 0.183, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.0376175548589343e-06, | |
| "loss": 0.1839, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.841692789968652e-06, | |
| "loss": 0.2006, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.64576802507837e-06, | |
| "loss": 0.179, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.4498432601880878e-06, | |
| "loss": 0.1804, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.2539184952978056e-06, | |
| "loss": 0.1566, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.0579937304075236e-06, | |
| "loss": 0.1685, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_accuracy": 0.8933890776064802, | |
| "eval_f1": 0.8964992389649924, | |
| "eval_loss": 0.23118489980697632, | |
| "eval_precision": 0.8615309605070697, | |
| "eval_recall": 0.9344262295081968, | |
| "eval_runtime": 171.1147, | |
| "eval_samples_per_second": 22.365, | |
| "eval_steps_per_second": 0.935, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.620689655172415e-07, | |
| "loss": 0.1461, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.661442006269593e-07, | |
| "loss": 0.2458, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 4.7021943573667715e-07, | |
| "loss": 0.1939, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.74294670846395e-07, | |
| "loss": 0.1551, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 7.836990595611285e-08, | |
| "loss": 0.1953, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 2552, | |
| "total_flos": 1.3995088604806644e+19, | |
| "train_loss": 0.259534664043345, | |
| "train_runtime": 9346.2499, | |
| "train_samples_per_second": 6.553, | |
| "train_steps_per_second": 0.273 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8926332288401254, | |
| "eval_f1": 0.8949654996166624, | |
| "eval_loss": 0.24127539992332458, | |
| "eval_precision": 0.8524829600778968, | |
| "eval_recall": 0.9419042495965573, | |
| "eval_runtime": 177.3711, | |
| "eval_samples_per_second": 21.582, | |
| "eval_steps_per_second": 0.902, | |
| "step": 2552 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2552, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 1.3995088604806644e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |