{ "best_metric": 0.9943937063217163, "best_model_checkpoint": "./models/deberta-v3-base-all-v4/checkpoint-73069", "epoch": 1.0, "global_step": 73069, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 6.952483269238665e-06, "loss": 0.8446, "step": 500 }, { "epoch": 0.01, "learning_rate": 6.9045833390357056e-06, "loss": 0.4856, "step": 1000 }, { "epoch": 0.02, "learning_rate": 6.856683408832747e-06, "loss": 0.4123, "step": 1500 }, { "epoch": 0.03, "learning_rate": 6.808783478629788e-06, "loss": 0.3721, "step": 2000 }, { "epoch": 0.03, "learning_rate": 6.760883548426829e-06, "loss": 0.3444, "step": 2500 }, { "epoch": 0.04, "learning_rate": 6.713079418084276e-06, "loss": 0.3378, "step": 3000 }, { "epoch": 0.05, "learning_rate": 6.665179487881318e-06, "loss": 0.3262, "step": 3500 }, { "epoch": 0.05, "learning_rate": 6.617279557678359e-06, "loss": 0.3156, "step": 4000 }, { "epoch": 0.06, "learning_rate": 6.5693796274754e-06, "loss": 0.3139, "step": 4500 }, { "epoch": 0.07, "learning_rate": 6.521479697272441e-06, "loss": 0.2942, "step": 5000 }, { "epoch": 0.08, "learning_rate": 6.473579767069482e-06, "loss": 0.3003, "step": 5500 }, { "epoch": 0.08, "learning_rate": 6.4256798368665235e-06, "loss": 0.2993, "step": 6000 }, { "epoch": 0.09, "learning_rate": 6.377779906663564e-06, "loss": 0.2774, "step": 6500 }, { "epoch": 0.1, "learning_rate": 6.329975776321012e-06, "loss": 0.2698, "step": 7000 }, { "epoch": 0.1, "learning_rate": 6.282075846118053e-06, "loss": 0.2782, "step": 7500 }, { "epoch": 0.11, "learning_rate": 6.234175915915094e-06, "loss": 0.2947, "step": 8000 }, { "epoch": 0.12, "learning_rate": 6.186275985712135e-06, "loss": 0.2804, "step": 8500 }, { "epoch": 0.12, "learning_rate": 6.138471855369582e-06, "loss": 0.2591, "step": 9000 }, { "epoch": 0.13, "learning_rate": 6.0905719251666235e-06, "loss": 0.2836, "step": 9500 }, { "epoch": 0.14, "learning_rate": 6.042671994963664e-06, "loss": 0.2657, "step": 10000 }, { "epoch": 0.14, "learning_rate": 5.994772064760705e-06, "loss": 0.2613, "step": 10500 }, { "epoch": 0.15, "learning_rate": 5.946872134557747e-06, "loss": 0.263, "step": 11000 }, { "epoch": 0.16, "learning_rate": 5.8991638040756e-06, "loss": 0.2522, "step": 11500 }, { "epoch": 0.16, "learning_rate": 5.851263873872641e-06, "loss": 0.2656, "step": 12000 }, { "epoch": 0.17, "learning_rate": 5.803363943669682e-06, "loss": 0.2611, "step": 12500 }, { "epoch": 0.18, "learning_rate": 5.755464013466723e-06, "loss": 0.2613, "step": 13000 }, { "epoch": 0.18, "learning_rate": 5.707564083263764e-06, "loss": 0.2592, "step": 13500 }, { "epoch": 0.19, "learning_rate": 5.659664153060805e-06, "loss": 0.2625, "step": 14000 }, { "epoch": 0.2, "learning_rate": 5.611860022718252e-06, "loss": 0.2774, "step": 14500 }, { "epoch": 0.21, "learning_rate": 5.5639600925152934e-06, "loss": 0.2428, "step": 15000 }, { "epoch": 0.21, "learning_rate": 5.5160601623123355e-06, "loss": 0.259, "step": 15500 }, { "epoch": 0.22, "learning_rate": 5.468160232109376e-06, "loss": 0.242, "step": 16000 }, { "epoch": 0.23, "learning_rate": 5.420260301906417e-06, "loss": 0.2703, "step": 16500 }, { "epoch": 0.23, "learning_rate": 5.372456171563864e-06, "loss": 0.2466, "step": 17000 }, { "epoch": 0.24, "learning_rate": 5.324556241360905e-06, "loss": 0.2475, "step": 17500 }, { "epoch": 0.25, "learning_rate": 5.2766563111579465e-06, "loss": 0.2443, "step": 18000 }, { "epoch": 0.25, "learning_rate": 5.228756380954988e-06, "loss": 0.253, "step": 18500 }, { "epoch": 0.26, "learning_rate": 5.180856450752029e-06, "loss": 0.2561, "step": 19000 }, { "epoch": 0.27, "learning_rate": 5.13295652054907e-06, "loss": 0.2422, "step": 19500 }, { "epoch": 0.27, "learning_rate": 5.085056590346111e-06, "loss": 0.2437, "step": 20000 }, { "epoch": 0.28, "learning_rate": 5.037252460003558e-06, "loss": 0.2504, "step": 20500 }, { "epoch": 0.29, "learning_rate": 4.9893525298005995e-06, "loss": 0.2238, "step": 21000 }, { "epoch": 0.29, "learning_rate": 4.941452599597641e-06, "loss": 0.2154, "step": 21500 }, { "epoch": 0.3, "learning_rate": 4.893552669394681e-06, "loss": 0.2391, "step": 22000 }, { "epoch": 0.31, "learning_rate": 4.845652739191722e-06, "loss": 0.2445, "step": 22500 }, { "epoch": 0.31, "learning_rate": 4.797752808988764e-06, "loss": 0.2496, "step": 23000 }, { "epoch": 0.32, "learning_rate": 4.749948678646211e-06, "loss": 0.2444, "step": 23500 }, { "epoch": 0.33, "learning_rate": 4.702048748443253e-06, "loss": 0.2332, "step": 24000 }, { "epoch": 0.34, "learning_rate": 4.654148818240294e-06, "loss": 0.2163, "step": 24500 }, { "epoch": 0.34, "learning_rate": 4.606248888037334e-06, "loss": 0.234, "step": 25000 }, { "epoch": 0.35, "learning_rate": 4.558444757694781e-06, "loss": 0.2451, "step": 25500 }, { "epoch": 0.36, "learning_rate": 4.510544827491822e-06, "loss": 0.2478, "step": 26000 }, { "epoch": 0.36, "learning_rate": 4.462644897288864e-06, "loss": 0.2378, "step": 26500 }, { "epoch": 0.37, "learning_rate": 4.414744967085906e-06, "loss": 0.2292, "step": 27000 }, { "epoch": 0.38, "learning_rate": 4.366940836743353e-06, "loss": 0.2391, "step": 27500 }, { "epoch": 0.38, "learning_rate": 4.319040906540393e-06, "loss": 0.218, "step": 28000 }, { "epoch": 0.39, "learning_rate": 4.271140976337434e-06, "loss": 0.2338, "step": 28500 }, { "epoch": 0.4, "learning_rate": 4.2232410461344755e-06, "loss": 0.23, "step": 29000 }, { "epoch": 0.4, "learning_rate": 4.175341115931517e-06, "loss": 0.253, "step": 29500 }, { "epoch": 0.41, "learning_rate": 4.127441185728558e-06, "loss": 0.2252, "step": 30000 }, { "epoch": 0.42, "learning_rate": 4.079541255525599e-06, "loss": 0.2029, "step": 30500 }, { "epoch": 0.42, "learning_rate": 4.03164132532264e-06, "loss": 0.2322, "step": 31000 }, { "epoch": 0.43, "learning_rate": 3.9837413951196815e-06, "loss": 0.235, "step": 31500 }, { "epoch": 0.44, "learning_rate": 3.9359372647771285e-06, "loss": 0.2329, "step": 32000 }, { "epoch": 0.44, "learning_rate": 3.88803733457417e-06, "loss": 0.2244, "step": 32500 }, { "epoch": 0.45, "learning_rate": 3.840137404371211e-06, "loss": 0.2217, "step": 33000 }, { "epoch": 0.46, "learning_rate": 3.7922374741682517e-06, "loss": 0.2155, "step": 33500 }, { "epoch": 0.47, "learning_rate": 3.7444333438256988e-06, "loss": 0.2253, "step": 34000 }, { "epoch": 0.47, "learning_rate": 3.69653341362274e-06, "loss": 0.2218, "step": 34500 }, { "epoch": 0.48, "learning_rate": 3.648633483419781e-06, "loss": 0.2258, "step": 35000 }, { "epoch": 0.49, "learning_rate": 3.6007335532168224e-06, "loss": 0.2336, "step": 35500 }, { "epoch": 0.49, "learning_rate": 3.552833623013864e-06, "loss": 0.2199, "step": 36000 }, { "epoch": 0.5, "learning_rate": 3.5049336928109044e-06, "loss": 0.2278, "step": 36500 }, { "epoch": 0.51, "learning_rate": 3.457129562468352e-06, "loss": 0.211, "step": 37000 }, { "epoch": 0.51, "learning_rate": 3.409325432125799e-06, "loss": 0.2304, "step": 37500 }, { "epoch": 0.52, "learning_rate": 3.36142550192284e-06, "loss": 0.2323, "step": 38000 }, { "epoch": 0.53, "learning_rate": 3.3135255717198813e-06, "loss": 0.2188, "step": 38500 }, { "epoch": 0.53, "learning_rate": 3.265625641516922e-06, "loss": 0.2224, "step": 39000 }, { "epoch": 0.54, "learning_rate": 3.2177257113139633e-06, "loss": 0.2233, "step": 39500 }, { "epoch": 0.55, "learning_rate": 3.169825781111005e-06, "loss": 0.2133, "step": 40000 }, { "epoch": 0.55, "learning_rate": 3.1219258509080457e-06, "loss": 0.2073, "step": 40500 }, { "epoch": 0.56, "learning_rate": 3.074025920705087e-06, "loss": 0.221, "step": 41000 }, { "epoch": 0.57, "learning_rate": 3.026125990502128e-06, "loss": 0.2268, "step": 41500 }, { "epoch": 0.57, "learning_rate": 2.9782260602991693e-06, "loss": 0.2129, "step": 42000 }, { "epoch": 0.58, "learning_rate": 2.9304219299566163e-06, "loss": 0.2144, "step": 42500 }, { "epoch": 0.59, "learning_rate": 2.8825219997536575e-06, "loss": 0.2192, "step": 43000 }, { "epoch": 0.6, "learning_rate": 2.8346220695506987e-06, "loss": 0.2211, "step": 43500 }, { "epoch": 0.6, "learning_rate": 2.7868179392081458e-06, "loss": 0.2356, "step": 44000 }, { "epoch": 0.61, "learning_rate": 2.738918009005187e-06, "loss": 0.2254, "step": 44500 }, { "epoch": 0.62, "learning_rate": 2.6910180788022277e-06, "loss": 0.2258, "step": 45000 }, { "epoch": 0.62, "learning_rate": 2.6431181485992694e-06, "loss": 0.222, "step": 45500 }, { "epoch": 0.63, "learning_rate": 2.59521821839631e-06, "loss": 0.2096, "step": 46000 }, { "epoch": 0.64, "learning_rate": 2.5473182881933514e-06, "loss": 0.2082, "step": 46500 }, { "epoch": 0.64, "learning_rate": 2.4994183579903926e-06, "loss": 0.2008, "step": 47000 }, { "epoch": 0.65, "learning_rate": 2.45161422764784e-06, "loss": 0.2216, "step": 47500 }, { "epoch": 0.66, "learning_rate": 2.403714297444881e-06, "loss": 0.2275, "step": 48000 }, { "epoch": 0.66, "learning_rate": 2.355814367241922e-06, "loss": 0.2146, "step": 48500 }, { "epoch": 0.67, "learning_rate": 2.307914437038963e-06, "loss": 0.2075, "step": 49000 }, { "epoch": 0.68, "learning_rate": 2.2600145068360044e-06, "loss": 0.2183, "step": 49500 }, { "epoch": 0.68, "learning_rate": 2.2121145766330456e-06, "loss": 0.2179, "step": 50000 }, { "epoch": 0.69, "learning_rate": 2.1642146464300864e-06, "loss": 0.2062, "step": 50500 }, { "epoch": 0.7, "learning_rate": 2.116314716227128e-06, "loss": 0.2115, "step": 51000 }, { "epoch": 0.7, "learning_rate": 2.068510585884575e-06, "loss": 0.2176, "step": 51500 }, { "epoch": 0.71, "learning_rate": 2.020610655681616e-06, "loss": 0.2205, "step": 52000 }, { "epoch": 0.72, "learning_rate": 1.972710725478657e-06, "loss": 0.2213, "step": 52500 }, { "epoch": 0.73, "learning_rate": 1.9248107952756983e-06, "loss": 0.201, "step": 53000 }, { "epoch": 0.73, "learning_rate": 1.8769108650727395e-06, "loss": 0.2026, "step": 53500 }, { "epoch": 0.74, "learning_rate": 1.8290109348697807e-06, "loss": 0.2089, "step": 54000 }, { "epoch": 0.75, "learning_rate": 1.7811110046668217e-06, "loss": 0.2035, "step": 54500 }, { "epoch": 0.75, "learning_rate": 1.733211074463863e-06, "loss": 0.2035, "step": 55000 }, { "epoch": 0.76, "learning_rate": 1.6853111442609041e-06, "loss": 0.2055, "step": 55500 }, { "epoch": 0.77, "learning_rate": 1.6375070139183511e-06, "loss": 0.2278, "step": 56000 }, { "epoch": 0.77, "learning_rate": 1.5897028835757984e-06, "loss": 0.2108, "step": 56500 }, { "epoch": 0.78, "learning_rate": 1.5418029533728394e-06, "loss": 0.2169, "step": 57000 }, { "epoch": 0.79, "learning_rate": 1.4939030231698806e-06, "loss": 0.2157, "step": 57500 }, { "epoch": 0.79, "learning_rate": 1.4460030929669216e-06, "loss": 0.2313, "step": 58000 }, { "epoch": 0.8, "learning_rate": 1.3981031627639628e-06, "loss": 0.2176, "step": 58500 }, { "epoch": 0.81, "learning_rate": 1.3503948322818158e-06, "loss": 0.2175, "step": 59000 }, { "epoch": 0.81, "learning_rate": 1.3024949020788568e-06, "loss": 0.2199, "step": 59500 }, { "epoch": 0.82, "learning_rate": 1.2545949718758982e-06, "loss": 0.2193, "step": 60000 }, { "epoch": 0.83, "learning_rate": 1.2066950416729392e-06, "loss": 0.2095, "step": 60500 }, { "epoch": 0.83, "learning_rate": 1.1587951114699804e-06, "loss": 0.2035, "step": 61000 }, { "epoch": 0.84, "learning_rate": 1.1108951812670216e-06, "loss": 0.2105, "step": 61500 }, { "epoch": 0.85, "learning_rate": 1.0629952510640626e-06, "loss": 0.2146, "step": 62000 }, { "epoch": 0.86, "learning_rate": 1.0150953208611039e-06, "loss": 0.184, "step": 62500 }, { "epoch": 0.86, "learning_rate": 9.672911905185509e-07, "loss": 0.2144, "step": 63000 }, { "epoch": 0.87, "learning_rate": 9.194870601759979e-07, "loss": 0.2116, "step": 63500 }, { "epoch": 0.88, "learning_rate": 8.716829298334451e-07, "loss": 0.2216, "step": 64000 }, { "epoch": 0.88, "learning_rate": 8.237829996304862e-07, "loss": 0.2055, "step": 64500 }, { "epoch": 0.89, "learning_rate": 7.758830694275273e-07, "loss": 0.2006, "step": 65000 }, { "epoch": 0.9, "learning_rate": 7.279831392245685e-07, "loss": 0.2044, "step": 65500 }, { "epoch": 0.9, "learning_rate": 6.800832090216097e-07, "loss": 0.2116, "step": 66000 }, { "epoch": 0.91, "learning_rate": 6.321832788186509e-07, "loss": 0.223, "step": 66500 }, { "epoch": 0.92, "learning_rate": 5.842833486156921e-07, "loss": 0.2058, "step": 67000 }, { "epoch": 0.92, "learning_rate": 5.363834184127332e-07, "loss": 0.2205, "step": 67500 }, { "epoch": 0.93, "learning_rate": 4.884834882097743e-07, "loss": 0.1975, "step": 68000 }, { "epoch": 0.94, "learning_rate": 4.4067935786722134e-07, "loss": 0.199, "step": 68500 }, { "epoch": 0.94, "learning_rate": 3.9277942766426255e-07, "loss": 0.1955, "step": 69000 }, { "epoch": 0.95, "learning_rate": 3.448794974613037e-07, "loss": 0.2121, "step": 69500 }, { "epoch": 0.96, "learning_rate": 2.9697956725834486e-07, "loss": 0.2023, "step": 70000 }, { "epoch": 0.96, "learning_rate": 2.4907963705538596e-07, "loss": 0.2043, "step": 70500 }, { "epoch": 0.97, "learning_rate": 2.0117970685242714e-07, "loss": 0.2183, "step": 71000 }, { "epoch": 0.98, "learning_rate": 1.5337557650987422e-07, "loss": 0.2032, "step": 71500 }, { "epoch": 0.99, "learning_rate": 1.0547564630691538e-07, "loss": 0.2127, "step": 72000 }, { "epoch": 0.99, "learning_rate": 5.757571610395654e-08, "loss": 0.189, "step": 72500 }, { "epoch": 1.0, "learning_rate": 9.675785900997687e-09, "loss": 0.2012, "step": 73000 }, { "epoch": 1.0, "eval_loss": 0.9943937063217163, "eval_rmse": 0.997192919254303, "eval_runtime": 2.2905, "eval_samples_per_second": 668.41, "eval_steps_per_second": 20.956, "step": 73069 } ], "max_steps": 73069, "num_train_epochs": 1, "total_flos": 7.295661144915454e+16, "trial_name": null, "trial_params": null }