| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0055710306406684, | |
| "eval_steps": 50, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.2773, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3981, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.3499, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3669, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.5399, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.3177, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.3217, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3754, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.352, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2789, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.3447761535644531, | |
| "eval_runtime": 177.2113, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 1.129, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.388, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4127, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 0.374, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.4176, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.2909, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3463, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.4037, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.2081, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.29, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1879, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.31108421087265015, | |
| "eval_runtime": 177.3154, | |
| "eval_samples_per_second": 2.25, | |
| "eval_steps_per_second": 1.128, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.9999412890861116e-05, | |
| "loss": 0.3191, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.9997651591020244e-05, | |
| "loss": 0.3487, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.999471618320339e-05, | |
| "loss": 0.2979, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.999060680528294e-05, | |
| "loss": 0.4943, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.9985323650271165e-05, | |
| "loss": 0.3237, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.997886696631114e-05, | |
| "loss": 0.3702, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.997123705666514e-05, | |
| "loss": 0.3141, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.9962434279700316e-05, | |
| "loss": 0.3956, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.9952459048871945e-05, | |
| "loss": 0.2972, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.9941311832703954e-05, | |
| "loss": 0.323, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.2948896288871765, | |
| "eval_runtime": 177.2222, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.129, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.9928993154766957e-05, | |
| "loss": 0.3052, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.99155035936536e-05, | |
| "loss": 0.3417, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.9900843782951475e-05, | |
| "loss": 0.2436, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.9885014411213285e-05, | |
| "loss": 0.274, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.986801622192453e-05, | |
| "loss": 0.3599, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.9849850013468585e-05, | |
| "loss": 0.3956, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.983051663908922e-05, | |
| "loss": 0.2769, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.98100170068505e-05, | |
| "loss": 0.3369, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.9788352079594136e-05, | |
| "loss": 0.4247, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.976552287489426e-05, | |
| "loss": 0.3049, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.28148066997528076, | |
| "eval_runtime": 177.3094, | |
| "eval_samples_per_second": 2.25, | |
| "eval_steps_per_second": 1.128, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.974153046500967e-05, | |
| "loss": 0.3088, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.9716375976833396e-05, | |
| "loss": 0.34, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.969006059183984e-05, | |
| "loss": 0.2245, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.9662585546029246e-05, | |
| "loss": 0.4144, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.963395212986964e-05, | |
| "loss": 0.3311, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.960416168823626e-05, | |
| "loss": 0.2514, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.957321562034833e-05, | |
| "loss": 0.3464, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.954111537970342e-05, | |
| "loss": 0.24, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.950786247400908e-05, | |
| "loss": 0.2474, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.94734584651121e-05, | |
| "loss": 0.2993, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.2721606492996216, | |
| "eval_runtime": 177.2024, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 1.129, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.943790496892513e-05, | |
| "loss": 0.2876, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.9401203655350766e-05, | |
| "loss": 0.396, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.936335624820313e-05, | |
| "loss": 0.2472, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.932436452512693e-05, | |
| "loss": 0.2673, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.9284230317513906e-05, | |
| "loss": 0.2537, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.9242955510416877e-05, | |
| "loss": 0.2601, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.920054204246115e-05, | |
| "loss": 0.2689, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.915699190575349e-05, | |
| "loss": 0.2658, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.911230714578858e-05, | |
| "loss": 0.2916, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.906648986135287e-05, | |
| "loss": 0.1683, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.2587164044380188, | |
| "eval_runtime": 177.1919, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 1.129, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.901954220442609e-05, | |
| "loss": 0.2327, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.897146638008012e-05, | |
| "loss": 0.1792, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.89222646463754e-05, | |
| "loss": 0.2767, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.8871939314254965e-05, | |
| "loss": 0.2448, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.8820492747435773e-05, | |
| "loss": 0.3314, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.8767927362297816e-05, | |
| "loss": 0.2794, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.871424562777052e-05, | |
| "loss": 0.3167, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.865945006521684e-05, | |
| "loss": 0.2845, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.860354324831482e-05, | |
| "loss": 0.2463, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.854652780293672e-05, | |
| "loss": 0.4197, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.25140881538391113, | |
| "eval_runtime": 177.2007, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 1.129, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.848840640702564e-05, | |
| "loss": 0.1682, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.8429181790469824e-05, | |
| "loss": 0.1677, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.836885673497434e-05, | |
| "loss": 0.2691, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.830743407393051e-05, | |
| "loss": 0.2319, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.8244916692282786e-05, | |
| "loss": 0.3504, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.818130752639326e-05, | |
| "loss": 0.2515, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.8116609563903725e-05, | |
| "loss": 0.2558, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.8050825843595395e-05, | |
| "loss": 0.2106, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.798395945524614e-05, | |
| "loss": 0.2607, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.791601353948537e-05, | |
| "loss": 0.2709, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.24746671319007874, | |
| "eval_runtime": 177.2021, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 1.129, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.784699128764654e-05, | |
| "loss": 0.2166, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.777689594161724e-05, | |
| "loss": 0.194, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.770573079368691e-05, | |
| "loss": 0.2225, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.763349918639227e-05, | |
| "loss": 0.3093, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.756020451236025e-05, | |
| "loss": 0.2138, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.748585021414869e-05, | |
| "loss": 0.2779, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.7410439784084626e-05, | |
| "loss": 0.1564, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.7333976764100275e-05, | |
| "loss": 0.1869, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.725646474556665e-05, | |
| "loss": 0.3141, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.717790736912493e-05, | |
| "loss": 0.3625, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.24145641922950745, | |
| "eval_runtime": 177.2307, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.128, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.709830832451538e-05, | |
| "loss": 0.1778, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.701767135040414e-05, | |
| "loss": 0.2132, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.693600023420758e-05, | |
| "loss": 0.2449, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.685329881191436e-05, | |
| "loss": 0.1909, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.676957096790536e-05, | |
| "loss": 0.2419, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.668482063477118e-05, | |
| "loss": 0.2918, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.659905179312742e-05, | |
| "loss": 0.3548, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.6512268471427745e-05, | |
| "loss": 0.1435, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.642447474577466e-05, | |
| "loss": 0.2817, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.6335674739728055e-05, | |
| "loss": 0.2872, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.23039554059505463, | |
| "eval_runtime": 177.2172, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.129, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.624587262411153e-05, | |
| "loss": 0.2396, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.615507261681651e-05, | |
| "loss": 0.177, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.606327898260413e-05, | |
| "loss": 0.3332, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.597049603290491e-05, | |
| "loss": 0.246, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.5876728125616264e-05, | |
| "loss": 0.3666, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.578197966489781e-05, | |
| "loss": 0.2239, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.568625510096454e-05, | |
| "loss": 0.246, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.5589558929877736e-05, | |
| "loss": 0.2086, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.5491895693333876e-05, | |
| "loss": 0.2635, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.5393269978451234e-05, | |
| "loss": 0.1746, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.2252800166606903, | |
| "eval_runtime": 177.2253, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.129, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.5293686417554525e-05, | |
| "loss": 0.2149, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.519314968795722e-05, | |
| "loss": 0.1499, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.5091664511741944e-05, | |
| "loss": 0.418, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.4989235655538654e-05, | |
| "loss": 0.1811, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.4885867930300744e-05, | |
| "loss": 0.308, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.478156619107912e-05, | |
| "loss": 0.1722, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.4676335336794124e-05, | |
| "loss": 0.2718, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.457018031000545e-05, | |
| "loss": 0.2606, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.446310609668e-05, | |
| "loss": 0.1796, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.435511772595773e-05, | |
| "loss": 0.1841, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.21893376111984253, | |
| "eval_runtime": 177.1964, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 1.129, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.424622026991536e-05, | |
| "loss": 0.0985, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.4136418843328244e-05, | |
| "loss": 0.2228, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.402571860343006e-05, | |
| "loss": 0.1185, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.39141247496706e-05, | |
| "loss": 0.1903, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.3801642523471585e-05, | |
| "loss": 0.0503, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.3688277207980446e-05, | |
| "loss": 0.1138, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.357403412782219e-05, | |
| "loss": 0.1712, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.345891864884937e-05, | |
| "loss": 0.1137, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.334293617788992e-05, | |
| "loss": 0.1466, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.322609216249336e-05, | |
| "loss": 0.1264, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.22615452110767365, | |
| "eval_runtime": 177.2186, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.129, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.3108392090674816e-05, | |
| "loss": 0.1117, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.2989841490657325e-05, | |
| "loss": 0.212, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.287044593061213e-05, | |
| "loss": 0.1206, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.27502110183972e-05, | |
| "loss": 0.2377, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.262914240129379e-05, | |
| "loss": 0.1839, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.250724576574122e-05, | |
| "loss": 0.1335, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.2384526837069785e-05, | |
| "loss": 0.0865, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.226099137923186e-05, | |
| "loss": 0.164, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.213664519453114e-05, | |
| "loss": 0.1225, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.201149412335015e-05, | |
| "loss": 0.0872, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.22944454848766327, | |
| "eval_runtime": 177.2171, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.129, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.188554404387588e-05, | |
| "loss": 0.169, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.1758800871823756e-05, | |
| "loss": 0.2083, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.163127056015975e-05, | |
| "loss": 0.1313, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.150295909882077e-05, | |
| "loss": 0.1935, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.1373872514433355e-05, | |
| "loss": 0.097, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.124401687003057e-05, | |
| "loss": 0.1333, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.111339826476725e-05, | |
| "loss": 0.1156, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.098202283363356e-05, | |
| "loss": 0.1681, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.084989674716679e-05, | |
| "loss": 0.2055, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.071702621116158e-05, | |
| "loss": 0.1379, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.22864395380020142, | |
| "eval_runtime": 177.2169, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.129, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.0583417466378396e-05, | |
| "loss": 0.1359, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.0449076788250446e-05, | |
| "loss": 0.1283, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.031401048658892e-05, | |
| "loss": 0.1762, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.0178224905286635e-05, | |
| "loss": 0.2163, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.004172642202002e-05, | |
| "loss": 0.2701, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.990452144794966e-05, | |
| "loss": 0.247, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.9766616427419076e-05, | |
| "loss": 0.1633, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.96280178376521e-05, | |
| "loss": 0.2521, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.948873218844863e-05, | |
| "loss": 0.1352, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.934876602187886e-05, | |
| "loss": 0.1648, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 0.21747413277626038, | |
| "eval_runtime": 177.23, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.128, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.920812591197604e-05, | |
| "loss": 0.159, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.9066818464427676e-05, | |
| "loss": 0.1805, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.892485031626527e-05, | |
| "loss": 0.1216, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.878222813555261e-05, | |
| "loss": 0.1362, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.863895862107255e-05, | |
| "loss": 0.1452, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 3.849504850201237e-05, | |
| "loss": 0.2143, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.835050453764779e-05, | |
| "loss": 0.1941, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.820533351702538e-05, | |
| "loss": 0.2172, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.80595422586438e-05, | |
| "loss": 0.1827, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 3.791313761013343e-05, | |
| "loss": 0.1103, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 0.21774926781654358, | |
| "eval_runtime": 177.2164, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.129, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 3.7766126447934857e-05, | |
| "loss": 0.3314, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3.761851567697583e-05, | |
| "loss": 0.1565, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 3.7470312230346956e-05, | |
| "loss": 0.1062, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 3.732152306897607e-05, | |
| "loss": 0.2157, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 3.717215518130127e-05, | |
| "loss": 0.0835, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3.702221558294274e-05, | |
| "loss": 0.2165, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.687171131637314e-05, | |
| "loss": 0.1374, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 3.6720649450586884e-05, | |
| "loss": 0.1446, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.656903708076815e-05, | |
| "loss": 0.1472, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.641688132795757e-05, | |
| "loss": 0.1456, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 0.2085915505886078, | |
| "eval_runtime": 177.2388, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.128, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 3.626418933871776e-05, | |
| "loss": 0.1535, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.611096828479773e-05, | |
| "loss": 0.1476, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 3.595722536279595e-05, | |
| "loss": 0.1419, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.5802967793822384e-05, | |
| "loss": 0.1428, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.564820282315932e-05, | |
| "loss": 0.1682, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.549293771992104e-05, | |
| "loss": 0.11, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.533717977671243e-05, | |
| "loss": 0.1534, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 3.518093630928644e-05, | |
| "loss": 0.1175, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 3.502421465620049e-05, | |
| "loss": 0.1287, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 3.486702217847176e-05, | |
| "loss": 0.1042, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.210044726729393, | |
| "eval_runtime": 177.2695, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.128, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.470936625923147e-05, | |
| "loss": 0.1185, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.455125430337809e-05, | |
| "loss": 0.1479, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 3.439269373722957e-05, | |
| "loss": 0.1272, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.4233692008174493e-05, | |
| "loss": 0.1147, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.407425658432233e-05, | |
| "loss": 0.1177, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3.3914394954152636e-05, | |
| "loss": 0.2132, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.375411462616332e-05, | |
| "loss": 0.0528, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.359342312851802e-05, | |
| "loss": 0.1488, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.343232800869247e-05, | |
| "loss": 0.111, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.327083683312004e-05, | |
| "loss": 0.2429, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.20871932804584503, | |
| "eval_runtime": 177.3553, | |
| "eval_samples_per_second": 2.25, | |
| "eval_steps_per_second": 1.128, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.3108957186836346e-05, | |
| "loss": 0.0577, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.294669667312295e-05, | |
| "loss": 0.1302, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.27840629131503e-05, | |
| "loss": 0.1289, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.262106354561973e-05, | |
| "loss": 0.153, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.245770622640471e-05, | |
| "loss": 0.1765, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.2293998628191246e-05, | |
| "loss": 0.1737, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.212994844011748e-05, | |
| "loss": 0.1098, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.196556336741261e-05, | |
| "loss": 0.1077, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.18008511310349e-05, | |
| "loss": 0.2765, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.163581946730909e-05, | |
| "loss": 0.1372, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.2058500349521637, | |
| "eval_runtime": 177.254, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.128, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 0.1052, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.130482887776356e-05, | |
| "loss": 0.0977, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.113888549815184e-05, | |
| "loss": 0.1577, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.097265378287784e-05, | |
| "loss": 0.144, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.080614153963429e-05, | |
| "loss": 0.2272, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.063935658928998e-05, | |
| "loss": 0.1185, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.047230676552239e-05, | |
| "loss": 0.1589, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.0304999914449773e-05, | |
| "loss": 0.1232, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.0137443894262635e-05, | |
| "loss": 0.1844, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.996964657485463e-05, | |
| "loss": 0.0875, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.19900214672088623, | |
| "eval_runtime": 177.2089, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 1.129, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.980161583745294e-05, | |
| "loss": 0.1628, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.9633359574248075e-05, | |
| "loss": 0.1706, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.9464885688023242e-05, | |
| "loss": 0.0676, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.9296202091783072e-05, | |
| "loss": 0.0926, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.912731670838207e-05, | |
| "loss": 0.1236, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.895823747015237e-05, | |
| "loss": 0.1689, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.878897231853127e-05, | |
| "loss": 0.0756, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.8619529203688163e-05, | |
| "loss": 0.1322, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.8449916084151128e-05, | |
| "loss": 0.1436, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.8280140926433192e-05, | |
| "loss": 0.1575, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.2005121409893036, | |
| "eval_runtime": 177.219, | |
| "eval_samples_per_second": 2.251, | |
| "eval_steps_per_second": 1.129, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.8110211704658073e-05, | |
| "loss": 0.1007, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.7940136400185695e-05, | |
| "loss": 0.1053, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.7769923001237318e-05, | |
| "loss": 0.221, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.7599579502520295e-05, | |
| "loss": 0.1379, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.7429113904852616e-05, | |
| "loss": 0.164, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.7258534214787108e-05, | |
| "loss": 0.141, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.7087848444235353e-05, | |
| "loss": 0.1734, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.6917064610091423e-05, | |
| "loss": 0.2103, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.674619073385531e-05, | |
| "loss": 0.1622, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.6575234841256137e-05, | |
| "loss": 0.0639, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.19528049230575562, | |
| "eval_runtime": 177.2074, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 1.129, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2392, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "total_flos": 5.908256757514568e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |