| { | |
| "best_metric": 0.7611846765843823, | |
| "best_model_checkpoint": "./finetuned/wikitext103_roberta-base_v2/checkpoint-123000", | |
| "epoch": 20.0, | |
| "global_step": 147800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.983085250338295e-05, | |
| "loss": 1.4212, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.7235698186111409, | |
| "eval_loss": 1.3007760047912598, | |
| "eval_runtime": 2.6682, | |
| "eval_samples_per_second": 185.892, | |
| "eval_steps_per_second": 5.997, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.96617050067659e-05, | |
| "loss": 1.3933, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.7226983316766515, | |
| "eval_loss": 1.2827116250991821, | |
| "eval_runtime": 2.1995, | |
| "eval_samples_per_second": 225.505, | |
| "eval_steps_per_second": 7.274, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.949255751014885e-05, | |
| "loss": 1.3917, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.7266257137444863, | |
| "eval_loss": 1.2815688848495483, | |
| "eval_runtime": 2.1563, | |
| "eval_samples_per_second": 230.027, | |
| "eval_steps_per_second": 7.42, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.93234100135318e-05, | |
| "loss": 1.3824, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.7251124131353045, | |
| "eval_loss": 1.294681191444397, | |
| "eval_runtime": 2.1464, | |
| "eval_samples_per_second": 231.089, | |
| "eval_steps_per_second": 7.454, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.915426251691475e-05, | |
| "loss": 1.3835, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.7289371440736602, | |
| "eval_loss": 1.2555147409439087, | |
| "eval_runtime": 2.2812, | |
| "eval_samples_per_second": 217.427, | |
| "eval_steps_per_second": 7.014, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.89851150202977e-05, | |
| "loss": 1.3758, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.7279413775189347, | |
| "eval_loss": 1.2611732482910156, | |
| "eval_runtime": 2.2556, | |
| "eval_samples_per_second": 219.898, | |
| "eval_steps_per_second": 7.093, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.881596752368065e-05, | |
| "loss": 1.3745, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.7244728228792188, | |
| "eval_loss": 1.279096007347107, | |
| "eval_runtime": 1.9103, | |
| "eval_samples_per_second": 259.647, | |
| "eval_steps_per_second": 8.376, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.86468200270636e-05, | |
| "loss": 1.3761, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.7286496152595643, | |
| "eval_loss": 1.2621806859970093, | |
| "eval_runtime": 2.2565, | |
| "eval_samples_per_second": 219.811, | |
| "eval_steps_per_second": 7.091, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.847767253044655e-05, | |
| "loss": 1.3735, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.7359971845474972, | |
| "eval_loss": 1.231848955154419, | |
| "eval_runtime": 2.2526, | |
| "eval_samples_per_second": 220.188, | |
| "eval_steps_per_second": 7.103, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.83085250338295e-05, | |
| "loss": 1.3717, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.7259761388286334, | |
| "eval_loss": 1.2777374982833862, | |
| "eval_runtime": 2.343, | |
| "eval_samples_per_second": 211.693, | |
| "eval_steps_per_second": 6.829, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.813937753721245e-05, | |
| "loss": 1.3675, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.7309145880574452, | |
| "eval_loss": 1.2589675188064575, | |
| "eval_runtime": 2.0349, | |
| "eval_samples_per_second": 243.741, | |
| "eval_steps_per_second": 7.863, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.79702300405954e-05, | |
| "loss": 1.3585, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.7253910822602958, | |
| "eval_loss": 1.2838590145111084, | |
| "eval_runtime": 2.2225, | |
| "eval_samples_per_second": 223.175, | |
| "eval_steps_per_second": 7.199, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.780108254397835e-05, | |
| "loss": 1.3579, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.7347076623797687, | |
| "eval_loss": 1.2341055870056152, | |
| "eval_runtime": 1.8958, | |
| "eval_samples_per_second": 261.625, | |
| "eval_steps_per_second": 8.44, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.76319350473613e-05, | |
| "loss": 1.3588, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.7326682357975821, | |
| "eval_loss": 1.2412930727005005, | |
| "eval_runtime": 2.1422, | |
| "eval_samples_per_second": 231.54, | |
| "eval_steps_per_second": 7.469, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.746278755074425e-05, | |
| "loss": 1.351, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.7317281968967362, | |
| "eval_loss": 1.2459222078323364, | |
| "eval_runtime": 2.2341, | |
| "eval_samples_per_second": 222.016, | |
| "eval_steps_per_second": 7.162, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.72936400541272e-05, | |
| "loss": 1.3394, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_accuracy": 0.7314233839745815, | |
| "eval_loss": 1.242180347442627, | |
| "eval_runtime": 2.2469, | |
| "eval_samples_per_second": 220.751, | |
| "eval_steps_per_second": 7.121, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.712449255751015e-05, | |
| "loss": 1.3429, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_accuracy": 0.734901599848407, | |
| "eval_loss": 1.2285393476486206, | |
| "eval_runtime": 2.1498, | |
| "eval_samples_per_second": 230.723, | |
| "eval_steps_per_second": 7.443, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.69553450608931e-05, | |
| "loss": 1.3393, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_accuracy": 0.7324128503075872, | |
| "eval_loss": 1.2404521703720093, | |
| "eval_runtime": 2.2579, | |
| "eval_samples_per_second": 219.671, | |
| "eval_steps_per_second": 7.086, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.678619756427605e-05, | |
| "loss": 1.3421, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_accuracy": 0.735434836099188, | |
| "eval_loss": 1.2255122661590576, | |
| "eval_runtime": 2.2664, | |
| "eval_samples_per_second": 218.847, | |
| "eval_steps_per_second": 7.06, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.6617050067659e-05, | |
| "loss": 1.3426, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_accuracy": 0.7333513221802482, | |
| "eval_loss": 1.2296382188796997, | |
| "eval_runtime": 2.1344, | |
| "eval_samples_per_second": 232.385, | |
| "eval_steps_per_second": 7.496, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.644790257104195e-05, | |
| "loss": 1.3326, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_accuracy": 0.7351480394040008, | |
| "eval_loss": 1.2158225774765015, | |
| "eval_runtime": 2.1342, | |
| "eval_samples_per_second": 232.406, | |
| "eval_steps_per_second": 7.497, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.62787550744249e-05, | |
| "loss": 1.3355, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_accuracy": 0.7364017876607805, | |
| "eval_loss": 1.2255741357803345, | |
| "eval_runtime": 2.1391, | |
| "eval_samples_per_second": 231.876, | |
| "eval_steps_per_second": 7.48, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.610960757780785e-05, | |
| "loss": 1.3324, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.7355829363706523, | |
| "eval_loss": 1.2208420038223267, | |
| "eval_runtime": 2.251, | |
| "eval_samples_per_second": 220.348, | |
| "eval_steps_per_second": 7.108, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.59404600811908e-05, | |
| "loss": 1.3331, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_accuracy": 0.7347190272757148, | |
| "eval_loss": 1.2230000495910645, | |
| "eval_runtime": 2.1329, | |
| "eval_samples_per_second": 232.552, | |
| "eval_steps_per_second": 7.502, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.577131258457375e-05, | |
| "loss": 1.3326, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_accuracy": 0.7316047842477829, | |
| "eval_loss": 1.250501275062561, | |
| "eval_runtime": 2.2566, | |
| "eval_samples_per_second": 219.795, | |
| "eval_steps_per_second": 7.09, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.56021650879567e-05, | |
| "loss": 1.3339, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.7321860715246034, | |
| "eval_loss": 1.2471247911453247, | |
| "eval_runtime": 1.8846, | |
| "eval_samples_per_second": 263.185, | |
| "eval_steps_per_second": 8.49, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.543301759133965e-05, | |
| "loss": 1.3286, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.7358603599923753, | |
| "eval_loss": 1.218480110168457, | |
| "eval_runtime": 2.183, | |
| "eval_samples_per_second": 227.211, | |
| "eval_steps_per_second": 7.329, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.52638700947226e-05, | |
| "loss": 1.3314, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_accuracy": 0.7363198956152989, | |
| "eval_loss": 1.2333292961120605, | |
| "eval_runtime": 1.922, | |
| "eval_samples_per_second": 258.068, | |
| "eval_steps_per_second": 8.325, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 4.509472259810555e-05, | |
| "loss": 1.325, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_accuracy": 0.7320171162387606, | |
| "eval_loss": 1.2384274005889893, | |
| "eval_runtime": 2.1484, | |
| "eval_samples_per_second": 230.871, | |
| "eval_steps_per_second": 7.447, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.49255751014885e-05, | |
| "loss": 1.3251, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.7332704232946886, | |
| "eval_loss": 1.2141916751861572, | |
| "eval_runtime": 2.1498, | |
| "eval_samples_per_second": 230.723, | |
| "eval_steps_per_second": 7.443, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.475642760487145e-05, | |
| "loss": 1.3136, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.7346380072100398, | |
| "eval_loss": 1.2162067890167236, | |
| "eval_runtime": 2.2669, | |
| "eval_samples_per_second": 218.8, | |
| "eval_steps_per_second": 7.058, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.45872801082544e-05, | |
| "loss": 1.3202, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.7368549767669357, | |
| "eval_loss": 1.220727801322937, | |
| "eval_runtime": 2.1251, | |
| "eval_samples_per_second": 233.399, | |
| "eval_steps_per_second": 7.529, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 4.441813261163735e-05, | |
| "loss": 1.3168, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_accuracy": 0.7391136589130195, | |
| "eval_loss": 1.1931146383285522, | |
| "eval_runtime": 2.2628, | |
| "eval_samples_per_second": 219.196, | |
| "eval_steps_per_second": 7.071, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.42489851150203e-05, | |
| "loss": 1.3134, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_accuracy": 0.7398447820343461, | |
| "eval_loss": 1.1856846809387207, | |
| "eval_runtime": 2.1315, | |
| "eval_samples_per_second": 232.703, | |
| "eval_steps_per_second": 7.507, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 4.407983761840325e-05, | |
| "loss": 1.3085, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_accuracy": 0.7383094012462748, | |
| "eval_loss": 1.2111510038375854, | |
| "eval_runtime": 2.2389, | |
| "eval_samples_per_second": 221.538, | |
| "eval_steps_per_second": 7.146, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 4.39106901217862e-05, | |
| "loss": 1.3165, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_accuracy": 0.736477152685609, | |
| "eval_loss": 1.2284483909606934, | |
| "eval_runtime": 2.2655, | |
| "eval_samples_per_second": 218.936, | |
| "eval_steps_per_second": 7.062, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.374154262516915e-05, | |
| "loss": 1.3144, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.7387957989256795, | |
| "eval_loss": 1.2013208866119385, | |
| "eval_runtime": 2.1477, | |
| "eval_samples_per_second": 230.94, | |
| "eval_steps_per_second": 7.45, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.35723951285521e-05, | |
| "loss": 1.319, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_accuracy": 0.7355637897925513, | |
| "eval_loss": 1.217348337173462, | |
| "eval_runtime": 1.8976, | |
| "eval_samples_per_second": 261.38, | |
| "eval_steps_per_second": 8.432, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 4.340324763193505e-05, | |
| "loss": 1.3147, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_accuracy": 0.7403712864559268, | |
| "eval_loss": 1.1786144971847534, | |
| "eval_runtime": 2.1417, | |
| "eval_samples_per_second": 231.588, | |
| "eval_steps_per_second": 7.471, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.3234100135318e-05, | |
| "loss": 1.311, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_accuracy": 0.7372879017795558, | |
| "eval_loss": 1.2008836269378662, | |
| "eval_runtime": 2.2409, | |
| "eval_samples_per_second": 221.338, | |
| "eval_steps_per_second": 7.14, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.306495263870095e-05, | |
| "loss": 1.3131, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_accuracy": 0.7366438077684113, | |
| "eval_loss": 1.1992290019989014, | |
| "eval_runtime": 2.3077, | |
| "eval_samples_per_second": 214.937, | |
| "eval_steps_per_second": 6.933, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 4.28958051420839e-05, | |
| "loss": 1.3036, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_accuracy": 0.7369976679863333, | |
| "eval_loss": 1.2166584730148315, | |
| "eval_runtime": 2.1243, | |
| "eval_samples_per_second": 233.491, | |
| "eval_steps_per_second": 7.532, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 4.272665764546685e-05, | |
| "loss": 1.3122, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_accuracy": 0.7378714413413875, | |
| "eval_loss": 1.2138844728469849, | |
| "eval_runtime": 2.155, | |
| "eval_samples_per_second": 230.165, | |
| "eval_steps_per_second": 7.425, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.25575101488498e-05, | |
| "loss": 1.3091, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.7364524804942348, | |
| "eval_loss": 1.2197295427322388, | |
| "eval_runtime": 2.0278, | |
| "eval_samples_per_second": 244.602, | |
| "eval_steps_per_second": 7.89, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.238836265223275e-05, | |
| "loss": 1.304, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.7371755128447044, | |
| "eval_loss": 1.186427354812622, | |
| "eval_runtime": 2.0462, | |
| "eval_samples_per_second": 242.4, | |
| "eval_steps_per_second": 7.819, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.22192151556157e-05, | |
| "loss": 1.3015, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_accuracy": 0.7355039424985249, | |
| "eval_loss": 1.2046276330947876, | |
| "eval_runtime": 2.0572, | |
| "eval_samples_per_second": 241.108, | |
| "eval_steps_per_second": 7.778, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.205006765899865e-05, | |
| "loss": 1.2916, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_accuracy": 0.7344874591057797, | |
| "eval_loss": 1.2312067747116089, | |
| "eval_runtime": 2.3523, | |
| "eval_samples_per_second": 210.856, | |
| "eval_steps_per_second": 6.802, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 4.18809201623816e-05, | |
| "loss": 1.2966, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.7372955288985823, | |
| "eval_loss": 1.2116466760635376, | |
| "eval_runtime": 2.306, | |
| "eval_samples_per_second": 215.094, | |
| "eval_steps_per_second": 6.939, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 4.171177266576455e-05, | |
| "loss": 1.2991, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_accuracy": 0.737794624029042, | |
| "eval_loss": 1.2262712717056274, | |
| "eval_runtime": 2.2208, | |
| "eval_samples_per_second": 223.344, | |
| "eval_steps_per_second": 7.205, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.15426251691475e-05, | |
| "loss": 1.3003, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_accuracy": 0.741288193792419, | |
| "eval_loss": 1.184373378753662, | |
| "eval_runtime": 2.336, | |
| "eval_samples_per_second": 212.325, | |
| "eval_steps_per_second": 6.849, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 4.137347767253045e-05, | |
| "loss": 1.2942, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_accuracy": 0.7368591999133871, | |
| "eval_loss": 1.195932149887085, | |
| "eval_runtime": 2.1558, | |
| "eval_samples_per_second": 230.073, | |
| "eval_steps_per_second": 7.422, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.12043301759134e-05, | |
| "loss": 1.2988, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_accuracy": 0.7381074306659838, | |
| "eval_loss": 1.2017642259597778, | |
| "eval_runtime": 2.1521, | |
| "eval_samples_per_second": 230.473, | |
| "eval_steps_per_second": 7.435, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 4.103518267929635e-05, | |
| "loss": 1.2936, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_accuracy": 0.7388343788536808, | |
| "eval_loss": 1.1992815732955933, | |
| "eval_runtime": 2.3209, | |
| "eval_samples_per_second": 213.713, | |
| "eval_steps_per_second": 6.894, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 4.08660351826793e-05, | |
| "loss": 1.2937, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_accuracy": 0.7358311660164716, | |
| "eval_loss": 1.2154779434204102, | |
| "eval_runtime": 2.1442, | |
| "eval_samples_per_second": 231.319, | |
| "eval_steps_per_second": 7.462, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 4.069688768606225e-05, | |
| "loss": 1.3021, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_accuracy": 0.7395591959907313, | |
| "eval_loss": 1.1794347763061523, | |
| "eval_runtime": 2.2631, | |
| "eval_samples_per_second": 219.166, | |
| "eval_steps_per_second": 7.07, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 4.05277401894452e-05, | |
| "loss": 1.2937, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_accuracy": 0.7401357600670687, | |
| "eval_loss": 1.1982717514038086, | |
| "eval_runtime": 2.0447, | |
| "eval_samples_per_second": 242.582, | |
| "eval_steps_per_second": 7.825, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 4.035859269282815e-05, | |
| "loss": 1.291, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_accuracy": 0.7448072021259288, | |
| "eval_loss": 1.1694941520690918, | |
| "eval_runtime": 2.1453, | |
| "eval_samples_per_second": 231.207, | |
| "eval_steps_per_second": 7.458, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.01894451962111e-05, | |
| "loss": 1.2932, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_accuracy": 0.7410137752905726, | |
| "eval_loss": 1.1980637311935425, | |
| "eval_runtime": 2.2686, | |
| "eval_samples_per_second": 218.634, | |
| "eval_steps_per_second": 7.053, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.002029769959405e-05, | |
| "loss": 1.2938, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.7382663617554176, | |
| "eval_loss": 1.1999621391296387, | |
| "eval_runtime": 2.1418, | |
| "eval_samples_per_second": 231.579, | |
| "eval_steps_per_second": 7.47, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 3.9851150202977e-05, | |
| "loss": 1.2789, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_accuracy": 0.7402127426252879, | |
| "eval_loss": 1.1918007135391235, | |
| "eval_runtime": 2.3184, | |
| "eval_samples_per_second": 213.944, | |
| "eval_steps_per_second": 6.901, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 3.968200270635995e-05, | |
| "loss": 1.2806, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_accuracy": 0.7368392751519062, | |
| "eval_loss": 1.2065249681472778, | |
| "eval_runtime": 2.1671, | |
| "eval_samples_per_second": 228.872, | |
| "eval_steps_per_second": 7.383, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 3.95128552097429e-05, | |
| "loss": 1.2799, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_accuracy": 0.7374173525839968, | |
| "eval_loss": 1.2035958766937256, | |
| "eval_runtime": 2.0293, | |
| "eval_samples_per_second": 244.417, | |
| "eval_steps_per_second": 7.884, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 3.934370771312585e-05, | |
| "loss": 1.2851, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_accuracy": 0.7374529736652525, | |
| "eval_loss": 1.2056316137313843, | |
| "eval_runtime": 2.2747, | |
| "eval_samples_per_second": 218.047, | |
| "eval_steps_per_second": 7.034, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 3.91745602165088e-05, | |
| "loss": 1.2789, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_accuracy": 0.7414960437229791, | |
| "eval_loss": 1.185698390007019, | |
| "eval_runtime": 2.1279, | |
| "eval_samples_per_second": 233.09, | |
| "eval_steps_per_second": 7.519, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.900541271989175e-05, | |
| "loss": 1.2847, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_accuracy": 0.7375549926676443, | |
| "eval_loss": 1.1947497129440308, | |
| "eval_runtime": 2.2844, | |
| "eval_samples_per_second": 217.128, | |
| "eval_steps_per_second": 7.004, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 3.88362652232747e-05, | |
| "loss": 1.2843, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_accuracy": 0.7398512049167071, | |
| "eval_loss": 1.1868607997894287, | |
| "eval_runtime": 1.8928, | |
| "eval_samples_per_second": 262.041, | |
| "eval_steps_per_second": 8.453, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 3.866711772665765e-05, | |
| "loss": 1.2822, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_accuracy": 0.738583059254866, | |
| "eval_loss": 1.1962590217590332, | |
| "eval_runtime": 2.3042, | |
| "eval_samples_per_second": 215.256, | |
| "eval_steps_per_second": 6.944, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 3.84979702300406e-05, | |
| "loss": 1.2755, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_accuracy": 0.7423808354478731, | |
| "eval_loss": 1.189677357673645, | |
| "eval_runtime": 2.1343, | |
| "eval_samples_per_second": 232.399, | |
| "eval_steps_per_second": 7.497, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 3.832882273342355e-05, | |
| "loss": 1.283, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_accuracy": 0.7438030006523157, | |
| "eval_loss": 1.1673452854156494, | |
| "eval_runtime": 2.1405, | |
| "eval_samples_per_second": 231.723, | |
| "eval_steps_per_second": 7.475, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 3.81596752368065e-05, | |
| "loss": 1.2765, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_accuracy": 0.7418567866813223, | |
| "eval_loss": 1.1855015754699707, | |
| "eval_runtime": 2.2371, | |
| "eval_samples_per_second": 221.718, | |
| "eval_steps_per_second": 7.152, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 3.799052774018945e-05, | |
| "loss": 1.2762, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_accuracy": 0.7412275877241228, | |
| "eval_loss": 1.1773431301116943, | |
| "eval_runtime": 2.1867, | |
| "eval_samples_per_second": 226.824, | |
| "eval_steps_per_second": 7.317, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 3.7821380243572397e-05, | |
| "loss": 1.2776, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_accuracy": 0.740787246819894, | |
| "eval_loss": 1.1897586584091187, | |
| "eval_runtime": 1.9025, | |
| "eval_samples_per_second": 260.712, | |
| "eval_steps_per_second": 8.41, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 3.7652232746955347e-05, | |
| "loss": 1.2847, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_accuracy": 0.7437667084947351, | |
| "eval_loss": 1.1624772548675537, | |
| "eval_runtime": 1.9202, | |
| "eval_samples_per_second": 258.302, | |
| "eval_steps_per_second": 8.332, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 3.7483085250338296e-05, | |
| "loss": 1.2732, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "eval_accuracy": 0.7396705597179374, | |
| "eval_loss": 1.194719672203064, | |
| "eval_runtime": 2.2563, | |
| "eval_samples_per_second": 219.831, | |
| "eval_steps_per_second": 7.091, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 3.7313937753721246e-05, | |
| "loss": 1.2667, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "eval_accuracy": 0.7384741591468417, | |
| "eval_loss": 1.2097489833831787, | |
| "eval_runtime": 2.0162, | |
| "eval_samples_per_second": 246.011, | |
| "eval_steps_per_second": 7.936, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 3.7144790257104196e-05, | |
| "loss": 1.2678, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "eval_accuracy": 0.7397711324624852, | |
| "eval_loss": 1.187340497970581, | |
| "eval_runtime": 1.9242, | |
| "eval_samples_per_second": 257.772, | |
| "eval_steps_per_second": 8.315, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 3.6975642760487146e-05, | |
| "loss": 1.2681, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "eval_accuracy": 0.7467894879436467, | |
| "eval_loss": 1.1681954860687256, | |
| "eval_runtime": 2.1385, | |
| "eval_samples_per_second": 231.938, | |
| "eval_steps_per_second": 7.482, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 3.6806495263870096e-05, | |
| "loss": 1.2699, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "eval_accuracy": 0.745684382221014, | |
| "eval_loss": 1.1739610433578491, | |
| "eval_runtime": 1.9046, | |
| "eval_samples_per_second": 260.416, | |
| "eval_steps_per_second": 8.401, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 3.6637347767253046e-05, | |
| "loss": 1.2675, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "eval_accuracy": 0.7378905091781449, | |
| "eval_loss": 1.212327003479004, | |
| "eval_runtime": 2.151, | |
| "eval_samples_per_second": 230.592, | |
| "eval_steps_per_second": 7.438, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 3.6468200270635996e-05, | |
| "loss": 1.2604, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_accuracy": 0.7395626782561456, | |
| "eval_loss": 1.195254921913147, | |
| "eval_runtime": 2.1404, | |
| "eval_samples_per_second": 231.731, | |
| "eval_steps_per_second": 7.475, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 3.6299052774018946e-05, | |
| "loss": 1.2688, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "eval_accuracy": 0.7397589090237662, | |
| "eval_loss": 1.1849150657653809, | |
| "eval_runtime": 2.1374, | |
| "eval_samples_per_second": 232.054, | |
| "eval_steps_per_second": 7.486, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 3.6129905277401896e-05, | |
| "loss": 1.2698, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "eval_accuracy": 0.7413877684508885, | |
| "eval_loss": 1.1708790063858032, | |
| "eval_runtime": 2.1318, | |
| "eval_samples_per_second": 232.668, | |
| "eval_steps_per_second": 7.505, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 3.5960757780784846e-05, | |
| "loss": 1.2689, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_accuracy": 0.7438135277526475, | |
| "eval_loss": 1.1763643026351929, | |
| "eval_runtime": 1.9258, | |
| "eval_samples_per_second": 257.551, | |
| "eval_steps_per_second": 8.308, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 3.5791610284167796e-05, | |
| "loss": 1.269, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "eval_accuracy": 0.7409149325968664, | |
| "eval_loss": 1.1824229955673218, | |
| "eval_runtime": 2.2453, | |
| "eval_samples_per_second": 220.905, | |
| "eval_steps_per_second": 7.126, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 3.5622462787550746e-05, | |
| "loss": 1.2715, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "eval_accuracy": 0.7408733194884687, | |
| "eval_loss": 1.178514003753662, | |
| "eval_runtime": 2.0475, | |
| "eval_samples_per_second": 242.248, | |
| "eval_steps_per_second": 7.814, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 3.5453315290933695e-05, | |
| "loss": 1.2628, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "eval_accuracy": 0.7433914472797822, | |
| "eval_loss": 1.173943281173706, | |
| "eval_runtime": 2.1375, | |
| "eval_samples_per_second": 232.048, | |
| "eval_steps_per_second": 7.485, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 3.5284167794316645e-05, | |
| "loss": 1.2617, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_accuracy": 0.7406168909338969, | |
| "eval_loss": 1.1814693212509155, | |
| "eval_runtime": 2.1357, | |
| "eval_samples_per_second": 232.237, | |
| "eval_steps_per_second": 7.492, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 3.5115020297699595e-05, | |
| "loss": 1.2565, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "eval_accuracy": 0.7414824236191919, | |
| "eval_loss": 1.1885017156600952, | |
| "eval_runtime": 2.2461, | |
| "eval_samples_per_second": 220.826, | |
| "eval_steps_per_second": 7.123, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 3.4945872801082545e-05, | |
| "loss": 1.2639, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_accuracy": 0.741952133873027, | |
| "eval_loss": 1.1781718730926514, | |
| "eval_runtime": 2.0174, | |
| "eval_samples_per_second": 245.859, | |
| "eval_steps_per_second": 7.931, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 3.4776725304465495e-05, | |
| "loss": 1.2557, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_accuracy": 0.7382356866408648, | |
| "eval_loss": 1.2061494588851929, | |
| "eval_runtime": 2.2612, | |
| "eval_samples_per_second": 219.356, | |
| "eval_steps_per_second": 7.076, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 3.4607577807848445e-05, | |
| "loss": 1.2503, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "eval_accuracy": 0.739681675962454, | |
| "eval_loss": 1.1741236448287964, | |
| "eval_runtime": 2.1411, | |
| "eval_samples_per_second": 231.661, | |
| "eval_steps_per_second": 7.473, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 3.4438430311231395e-05, | |
| "loss": 1.2514, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_accuracy": 0.7435828154552824, | |
| "eval_loss": 1.167312741279602, | |
| "eval_runtime": 2.0431, | |
| "eval_samples_per_second": 242.763, | |
| "eval_steps_per_second": 7.831, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 3.4269282814614345e-05, | |
| "loss": 1.254, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "eval_accuracy": 0.7399956502827316, | |
| "eval_loss": 1.1828943490982056, | |
| "eval_runtime": 2.2651, | |
| "eval_samples_per_second": 218.976, | |
| "eval_steps_per_second": 7.064, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 3.4100135317997295e-05, | |
| "loss": 1.2583, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "eval_accuracy": 0.7390757539268417, | |
| "eval_loss": 1.1776684522628784, | |
| "eval_runtime": 2.0336, | |
| "eval_samples_per_second": 243.904, | |
| "eval_steps_per_second": 7.868, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 3.3930987821380245e-05, | |
| "loss": 1.2518, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "eval_accuracy": 0.7411625020238545, | |
| "eval_loss": 1.1892728805541992, | |
| "eval_runtime": 2.2474, | |
| "eval_samples_per_second": 220.698, | |
| "eval_steps_per_second": 7.119, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 3.3761840324763195e-05, | |
| "loss": 1.2519, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "eval_accuracy": 0.7410831524506257, | |
| "eval_loss": 1.1775306463241577, | |
| "eval_runtime": 2.127, | |
| "eval_samples_per_second": 233.19, | |
| "eval_steps_per_second": 7.522, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 3.3592692828146145e-05, | |
| "loss": 1.2477, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_accuracy": 0.7451821862348178, | |
| "eval_loss": 1.1809273958206177, | |
| "eval_runtime": 1.902, | |
| "eval_samples_per_second": 260.776, | |
| "eval_steps_per_second": 8.412, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 3.3423545331529095e-05, | |
| "loss": 1.2546, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "eval_accuracy": 0.7455485978763953, | |
| "eval_loss": 1.1651870012283325, | |
| "eval_runtime": 2.1247, | |
| "eval_samples_per_second": 233.443, | |
| "eval_steps_per_second": 7.53, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 3.3254397834912044e-05, | |
| "loss": 1.2564, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_accuracy": 0.7435488746599247, | |
| "eval_loss": 1.1729925870895386, | |
| "eval_runtime": 2.2521, | |
| "eval_samples_per_second": 220.235, | |
| "eval_steps_per_second": 7.104, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 3.3085250338294994e-05, | |
| "loss": 1.254, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "eval_accuracy": 0.7427022407392571, | |
| "eval_loss": 1.1740801334381104, | |
| "eval_runtime": 2.2515, | |
| "eval_samples_per_second": 220.294, | |
| "eval_steps_per_second": 7.106, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 3.2916102841677944e-05, | |
| "loss": 1.2495, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "eval_accuracy": 0.7475704632944787, | |
| "eval_loss": 1.1539645195007324, | |
| "eval_runtime": 2.1379, | |
| "eval_samples_per_second": 231.999, | |
| "eval_steps_per_second": 7.484, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 3.2746955345060894e-05, | |
| "loss": 1.2502, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_accuracy": 0.7488099797559774, | |
| "eval_loss": 1.145354151725769, | |
| "eval_runtime": 2.0467, | |
| "eval_samples_per_second": 242.344, | |
| "eval_steps_per_second": 7.818, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 3.2577807848443844e-05, | |
| "loss": 1.2527, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_accuracy": 0.7429261278858414, | |
| "eval_loss": 1.1704862117767334, | |
| "eval_runtime": 1.8944, | |
| "eval_samples_per_second": 261.83, | |
| "eval_steps_per_second": 8.446, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 3.2408660351826794e-05, | |
| "loss": 1.2418, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_accuracy": 0.7441042170292774, | |
| "eval_loss": 1.1714463233947754, | |
| "eval_runtime": 2.2491, | |
| "eval_samples_per_second": 220.532, | |
| "eval_steps_per_second": 7.114, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 3.2239512855209744e-05, | |
| "loss": 1.2386, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.74550079317324, | |
| "eval_loss": 1.1619137525558472, | |
| "eval_runtime": 2.2788, | |
| "eval_samples_per_second": 217.662, | |
| "eval_steps_per_second": 7.021, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 3.2070365358592694e-05, | |
| "loss": 1.2407, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "eval_accuracy": 0.7428433966802983, | |
| "eval_loss": 1.1702818870544434, | |
| "eval_runtime": 2.2482, | |
| "eval_samples_per_second": 220.624, | |
| "eval_steps_per_second": 7.117, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 3.1901217861975644e-05, | |
| "loss": 1.2429, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "eval_accuracy": 0.7437382207533255, | |
| "eval_loss": 1.1596566438674927, | |
| "eval_runtime": 2.0269, | |
| "eval_samples_per_second": 244.711, | |
| "eval_steps_per_second": 7.894, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 3.1732070365358594e-05, | |
| "loss": 1.2398, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "eval_accuracy": 0.7411157814291173, | |
| "eval_loss": 1.1802175045013428, | |
| "eval_runtime": 1.903, | |
| "eval_samples_per_second": 260.643, | |
| "eval_steps_per_second": 8.408, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 3.1562922868741544e-05, | |
| "loss": 1.2507, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "eval_accuracy": 0.7465291873021028, | |
| "eval_loss": 1.153898000717163, | |
| "eval_runtime": 2.134, | |
| "eval_samples_per_second": 232.429, | |
| "eval_steps_per_second": 7.498, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 3.1393775372124494e-05, | |
| "loss": 1.2369, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "eval_accuracy": 0.7421205732433082, | |
| "eval_loss": 1.1711477041244507, | |
| "eval_runtime": 2.2417, | |
| "eval_samples_per_second": 221.263, | |
| "eval_steps_per_second": 7.138, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 3.1224627875507443e-05, | |
| "loss": 1.2463, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_accuracy": 0.7408580787198625, | |
| "eval_loss": 1.1848827600479126, | |
| "eval_runtime": 2.2658, | |
| "eval_samples_per_second": 218.909, | |
| "eval_steps_per_second": 7.062, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 3.1055480378890393e-05, | |
| "loss": 1.2389, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "eval_accuracy": 0.7447417175239756, | |
| "eval_loss": 1.172045111656189, | |
| "eval_runtime": 2.1226, | |
| "eval_samples_per_second": 233.68, | |
| "eval_steps_per_second": 7.538, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 3.088633288227334e-05, | |
| "loss": 1.2395, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "eval_accuracy": 0.7455846610856063, | |
| "eval_loss": 1.1613755226135254, | |
| "eval_runtime": 2.2492, | |
| "eval_samples_per_second": 220.523, | |
| "eval_steps_per_second": 7.114, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 3.071718538565629e-05, | |
| "loss": 1.2429, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_accuracy": 0.7459984960790633, | |
| "eval_loss": 1.1604408025741577, | |
| "eval_runtime": 2.2523, | |
| "eval_samples_per_second": 220.221, | |
| "eval_steps_per_second": 7.104, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 3.054803788903924e-05, | |
| "loss": 1.2384, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_accuracy": 0.7408438637823945, | |
| "eval_loss": 1.1852344274520874, | |
| "eval_runtime": 2.2645, | |
| "eval_samples_per_second": 219.035, | |
| "eval_steps_per_second": 7.066, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 3.0378890392422193e-05, | |
| "loss": 1.2419, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "eval_accuracy": 0.7460735114607351, | |
| "eval_loss": 1.1592859029769897, | |
| "eval_runtime": 2.2667, | |
| "eval_samples_per_second": 218.824, | |
| "eval_steps_per_second": 7.059, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 3.0209742895805143e-05, | |
| "loss": 1.2381, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "eval_accuracy": 0.7454180674547229, | |
| "eval_loss": 1.161791205406189, | |
| "eval_runtime": 2.2508, | |
| "eval_samples_per_second": 220.362, | |
| "eval_steps_per_second": 7.108, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 3.0040595399188093e-05, | |
| "loss": 1.2384, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "eval_accuracy": 0.7445992935958163, | |
| "eval_loss": 1.1550912857055664, | |
| "eval_runtime": 2.2277, | |
| "eval_samples_per_second": 222.654, | |
| "eval_steps_per_second": 7.182, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 2.9871447902571043e-05, | |
| "loss": 1.2314, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_accuracy": 0.7451252345598434, | |
| "eval_loss": 1.1473671197891235, | |
| "eval_runtime": 2.0323, | |
| "eval_samples_per_second": 244.059, | |
| "eval_steps_per_second": 7.873, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 2.9702300405953993e-05, | |
| "loss": 1.2277, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "eval_accuracy": 0.7435493080290383, | |
| "eval_loss": 1.1636135578155518, | |
| "eval_runtime": 2.2565, | |
| "eval_samples_per_second": 219.81, | |
| "eval_steps_per_second": 7.091, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 2.9533152909336943e-05, | |
| "loss": 1.23, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "eval_accuracy": 0.7482466354355656, | |
| "eval_loss": 1.1545356512069702, | |
| "eval_runtime": 2.1398, | |
| "eval_samples_per_second": 231.799, | |
| "eval_steps_per_second": 7.477, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 2.9364005412719893e-05, | |
| "loss": 1.2292, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "eval_accuracy": 0.7456762809270702, | |
| "eval_loss": 1.169358730316162, | |
| "eval_runtime": 2.2505, | |
| "eval_samples_per_second": 220.392, | |
| "eval_steps_per_second": 7.109, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 2.9194857916102843e-05, | |
| "loss": 1.2337, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_accuracy": 0.7437165882071332, | |
| "eval_loss": 1.1681973934173584, | |
| "eval_runtime": 2.2595, | |
| "eval_samples_per_second": 219.518, | |
| "eval_steps_per_second": 7.081, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 2.9025710419485792e-05, | |
| "loss": 1.2274, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "eval_accuracy": 0.7484281932495036, | |
| "eval_loss": 1.1518677473068237, | |
| "eval_runtime": 2.0234, | |
| "eval_samples_per_second": 245.13, | |
| "eval_steps_per_second": 7.907, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 2.885656292286874e-05, | |
| "loss": 1.232, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_accuracy": 0.7435426377844804, | |
| "eval_loss": 1.1693381071090698, | |
| "eval_runtime": 2.153, | |
| "eval_samples_per_second": 230.381, | |
| "eval_steps_per_second": 7.432, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 2.868741542625169e-05, | |
| "loss": 1.2315, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "eval_accuracy": 0.7434497229246247, | |
| "eval_loss": 1.1637970209121704, | |
| "eval_runtime": 2.1389, | |
| "eval_samples_per_second": 231.9, | |
| "eval_steps_per_second": 7.481, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 2.851826792963464e-05, | |
| "loss": 1.2293, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "eval_accuracy": 0.746056909476852, | |
| "eval_loss": 1.1639689207077026, | |
| "eval_runtime": 1.9056, | |
| "eval_samples_per_second": 260.282, | |
| "eval_steps_per_second": 8.396, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 2.8349120433017595e-05, | |
| "loss": 1.2287, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "eval_accuracy": 0.7519274622651754, | |
| "eval_loss": 1.146359920501709, | |
| "eval_runtime": 2.1418, | |
| "eval_samples_per_second": 231.582, | |
| "eval_steps_per_second": 7.47, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 2.8179972936400545e-05, | |
| "loss": 1.2283, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "eval_accuracy": 0.7480988335904306, | |
| "eval_loss": 1.1439129114151, | |
| "eval_runtime": 2.1515, | |
| "eval_samples_per_second": 230.532, | |
| "eval_steps_per_second": 7.437, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 2.8010825439783495e-05, | |
| "loss": 1.2279, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "eval_accuracy": 0.7476770091832853, | |
| "eval_loss": 1.1496102809906006, | |
| "eval_runtime": 2.1443, | |
| "eval_samples_per_second": 231.311, | |
| "eval_steps_per_second": 7.462, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 2.7841677943166445e-05, | |
| "loss": 1.2276, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.7448800151502855, | |
| "eval_loss": 1.1544512510299683, | |
| "eval_runtime": 2.1443, | |
| "eval_samples_per_second": 231.308, | |
| "eval_steps_per_second": 7.462, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 2.7672530446549395e-05, | |
| "loss": 1.2301, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "eval_accuracy": 0.7486796972831709, | |
| "eval_loss": 1.131188154220581, | |
| "eval_runtime": 2.2612, | |
| "eval_samples_per_second": 219.354, | |
| "eval_steps_per_second": 7.076, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 2.7503382949932345e-05, | |
| "loss": 1.2248, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7464872620949183, | |
| "eval_loss": 1.1444239616394043, | |
| "eval_runtime": 1.9117, | |
| "eval_samples_per_second": 259.451, | |
| "eval_steps_per_second": 8.369, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 2.7334235453315295e-05, | |
| "loss": 1.2266, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "eval_accuracy": 0.7430061513773736, | |
| "eval_loss": 1.1525160074234009, | |
| "eval_runtime": 2.256, | |
| "eval_samples_per_second": 219.857, | |
| "eval_steps_per_second": 7.092, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 2.716508795669824e-05, | |
| "loss": 1.2198, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "eval_accuracy": 0.7462388784038825, | |
| "eval_loss": 1.1551423072814941, | |
| "eval_runtime": 2.2513, | |
| "eval_samples_per_second": 220.317, | |
| "eval_steps_per_second": 7.107, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 2.699594046008119e-05, | |
| "loss": 1.219, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_accuracy": 0.7479334406870639, | |
| "eval_loss": 1.143385887145996, | |
| "eval_runtime": 2.2558, | |
| "eval_samples_per_second": 219.879, | |
| "eval_steps_per_second": 7.093, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 2.682679296346414e-05, | |
| "loss": 1.2212, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "eval_accuracy": 0.7415982885151786, | |
| "eval_loss": 1.1707236766815186, | |
| "eval_runtime": 2.2452, | |
| "eval_samples_per_second": 220.92, | |
| "eval_steps_per_second": 7.126, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 2.665764546684709e-05, | |
| "loss": 1.2265, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "eval_accuracy": 0.7421521035598706, | |
| "eval_loss": 1.1743712425231934, | |
| "eval_runtime": 2.1289, | |
| "eval_samples_per_second": 232.985, | |
| "eval_steps_per_second": 7.516, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 2.648849797023004e-05, | |
| "loss": 1.2216, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "eval_accuracy": 0.7392663666010835, | |
| "eval_loss": 1.1817814111709595, | |
| "eval_runtime": 2.1373, | |
| "eval_samples_per_second": 232.069, | |
| "eval_steps_per_second": 7.486, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.631935047361299e-05, | |
| "loss": 1.2226, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "eval_accuracy": 0.7454341644794401, | |
| "eval_loss": 1.1662167310714722, | |
| "eval_runtime": 2.1776, | |
| "eval_samples_per_second": 227.77, | |
| "eval_steps_per_second": 7.347, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 2.615020297699594e-05, | |
| "loss": 1.2224, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "eval_accuracy": 0.7460155894249055, | |
| "eval_loss": 1.1345940828323364, | |
| "eval_runtime": 2.131, | |
| "eval_samples_per_second": 232.753, | |
| "eval_steps_per_second": 7.508, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 2.598105548037889e-05, | |
| "loss": 1.2186, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "eval_accuracy": 0.7462514417531718, | |
| "eval_loss": 1.153380036354065, | |
| "eval_runtime": 2.3136, | |
| "eval_samples_per_second": 214.386, | |
| "eval_steps_per_second": 6.916, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 2.581190798376184e-05, | |
| "loss": 1.2179, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "eval_accuracy": 0.7477791705270042, | |
| "eval_loss": 1.1399047374725342, | |
| "eval_runtime": 2.2709, | |
| "eval_samples_per_second": 218.413, | |
| "eval_steps_per_second": 7.046, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 2.564276048714479e-05, | |
| "loss": 1.2177, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "eval_accuracy": 0.7441804462995666, | |
| "eval_loss": 1.1545348167419434, | |
| "eval_runtime": 2.2419, | |
| "eval_samples_per_second": 221.237, | |
| "eval_steps_per_second": 7.137, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 2.547361299052774e-05, | |
| "loss": 1.2154, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "eval_accuracy": 0.7426768214742224, | |
| "eval_loss": 1.171052098274231, | |
| "eval_runtime": 2.1267, | |
| "eval_samples_per_second": 233.224, | |
| "eval_steps_per_second": 7.523, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 2.530446549391069e-05, | |
| "loss": 1.2179, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "eval_accuracy": 0.7514139509830325, | |
| "eval_loss": 1.1348686218261719, | |
| "eval_runtime": 1.8985, | |
| "eval_samples_per_second": 261.263, | |
| "eval_steps_per_second": 8.428, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 2.513531799729364e-05, | |
| "loss": 1.2184, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "eval_accuracy": 0.749460868615729, | |
| "eval_loss": 1.1427435874938965, | |
| "eval_runtime": 2.1257, | |
| "eval_samples_per_second": 233.336, | |
| "eval_steps_per_second": 7.527, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 2.496617050067659e-05, | |
| "loss": 1.2193, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "eval_accuracy": 0.7494911077780159, | |
| "eval_loss": 1.1222712993621826, | |
| "eval_runtime": 2.0347, | |
| "eval_samples_per_second": 243.77, | |
| "eval_steps_per_second": 7.864, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 2.479702300405954e-05, | |
| "loss": 1.2063, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "eval_accuracy": 0.7488264163021444, | |
| "eval_loss": 1.1357399225234985, | |
| "eval_runtime": 1.9046, | |
| "eval_samples_per_second": 260.423, | |
| "eval_steps_per_second": 8.401, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 2.462787550744249e-05, | |
| "loss": 1.2025, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "eval_accuracy": 0.7486311066000695, | |
| "eval_loss": 1.1476197242736816, | |
| "eval_runtime": 2.1786, | |
| "eval_samples_per_second": 227.67, | |
| "eval_steps_per_second": 7.344, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 2.445872801082544e-05, | |
| "loss": 1.2097, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "eval_accuracy": 0.7492516383053316, | |
| "eval_loss": 1.1382330656051636, | |
| "eval_runtime": 2.1295, | |
| "eval_samples_per_second": 232.922, | |
| "eval_steps_per_second": 7.514, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 2.428958051420839e-05, | |
| "loss": 1.2106, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "eval_accuracy": 0.7500204253928484, | |
| "eval_loss": 1.1413904428482056, | |
| "eval_runtime": 2.1753, | |
| "eval_samples_per_second": 228.019, | |
| "eval_steps_per_second": 7.355, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 2.412043301759134e-05, | |
| "loss": 1.2146, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "eval_accuracy": 0.7533006412674462, | |
| "eval_loss": 1.113772988319397, | |
| "eval_runtime": 2.136, | |
| "eval_samples_per_second": 232.208, | |
| "eval_steps_per_second": 7.491, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 2.395128552097429e-05, | |
| "loss": 1.2129, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "eval_accuracy": 0.7477787948952668, | |
| "eval_loss": 1.1447216272354126, | |
| "eval_runtime": 2.2641, | |
| "eval_samples_per_second": 219.075, | |
| "eval_steps_per_second": 7.067, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 2.378213802435724e-05, | |
| "loss": 1.2078, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "eval_accuracy": 0.7508962988920937, | |
| "eval_loss": 1.155730128288269, | |
| "eval_runtime": 2.1359, | |
| "eval_samples_per_second": 232.221, | |
| "eval_steps_per_second": 7.491, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 2.3612990527740193e-05, | |
| "loss": 1.204, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "eval_accuracy": 0.7537665293735096, | |
| "eval_loss": 1.1243318319320679, | |
| "eval_runtime": 2.2543, | |
| "eval_samples_per_second": 220.027, | |
| "eval_steps_per_second": 7.098, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 2.3443843031123143e-05, | |
| "loss": 1.2101, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "eval_accuracy": 0.7507114399544679, | |
| "eval_loss": 1.1352229118347168, | |
| "eval_runtime": 2.1504, | |
| "eval_samples_per_second": 230.651, | |
| "eval_steps_per_second": 7.44, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 2.327469553450609e-05, | |
| "loss": 1.207, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "eval_accuracy": 0.7526499865482916, | |
| "eval_loss": 1.1365910768508911, | |
| "eval_runtime": 2.2554, | |
| "eval_samples_per_second": 219.92, | |
| "eval_steps_per_second": 7.094, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 2.310554803788904e-05, | |
| "loss": 1.2067, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "eval_accuracy": 0.7482271408617169, | |
| "eval_loss": 1.145031213760376, | |
| "eval_runtime": 2.1262, | |
| "eval_samples_per_second": 233.276, | |
| "eval_steps_per_second": 7.525, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 2.293640054127199e-05, | |
| "loss": 1.1997, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "eval_accuracy": 0.7503758591065293, | |
| "eval_loss": 1.1333723068237305, | |
| "eval_runtime": 2.1437, | |
| "eval_samples_per_second": 231.381, | |
| "eval_steps_per_second": 7.464, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 2.276725304465494e-05, | |
| "loss": 1.2114, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "eval_accuracy": 0.7523950883821346, | |
| "eval_loss": 1.13480544090271, | |
| "eval_runtime": 2.256, | |
| "eval_samples_per_second": 219.855, | |
| "eval_steps_per_second": 7.092, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 2.259810554803789e-05, | |
| "loss": 1.2087, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "eval_accuracy": 0.7507978579542381, | |
| "eval_loss": 1.1221325397491455, | |
| "eval_runtime": 2.149, | |
| "eval_samples_per_second": 230.81, | |
| "eval_steps_per_second": 7.445, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 2.242895805142084e-05, | |
| "loss": 1.2065, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_accuracy": 0.7486237532021583, | |
| "eval_loss": 1.130583643913269, | |
| "eval_runtime": 2.2591, | |
| "eval_samples_per_second": 219.556, | |
| "eval_steps_per_second": 7.082, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 2.225981055480379e-05, | |
| "loss": 1.1985, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "eval_accuracy": 0.7470671686582637, | |
| "eval_loss": 1.1648321151733398, | |
| "eval_runtime": 2.2577, | |
| "eval_samples_per_second": 219.693, | |
| "eval_steps_per_second": 7.087, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 2.209066305818674e-05, | |
| "loss": 1.205, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "eval_accuracy": 0.7526795068095737, | |
| "eval_loss": 1.1088367700576782, | |
| "eval_runtime": 2.1263, | |
| "eval_samples_per_second": 233.267, | |
| "eval_steps_per_second": 7.525, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 2.192151556156969e-05, | |
| "loss": 1.2026, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "eval_accuracy": 0.7512794548290868, | |
| "eval_loss": 1.1253347396850586, | |
| "eval_runtime": 2.1489, | |
| "eval_samples_per_second": 230.816, | |
| "eval_steps_per_second": 7.446, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 2.175236806495264e-05, | |
| "loss": 1.2, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "eval_accuracy": 0.7473735779217244, | |
| "eval_loss": 1.1330283880233765, | |
| "eval_runtime": 2.2554, | |
| "eval_samples_per_second": 219.915, | |
| "eval_steps_per_second": 7.094, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 2.1583220568335592e-05, | |
| "loss": 1.1997, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "eval_accuracy": 0.7493864048660762, | |
| "eval_loss": 1.1423763036727905, | |
| "eval_runtime": 2.2628, | |
| "eval_samples_per_second": 219.193, | |
| "eval_steps_per_second": 7.071, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 2.1414073071718542e-05, | |
| "loss": 1.1989, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "eval_accuracy": 0.7477665276950566, | |
| "eval_loss": 1.1288686990737915, | |
| "eval_runtime": 2.2744, | |
| "eval_samples_per_second": 218.08, | |
| "eval_steps_per_second": 7.035, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 2.124492557510149e-05, | |
| "loss": 1.1956, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "eval_accuracy": 0.75250470912615, | |
| "eval_loss": 1.1163060665130615, | |
| "eval_runtime": 2.1424, | |
| "eval_samples_per_second": 231.521, | |
| "eval_steps_per_second": 7.468, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 2.107577807848444e-05, | |
| "loss": 1.1997, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "eval_accuracy": 0.7502406674510643, | |
| "eval_loss": 1.135400414466858, | |
| "eval_runtime": 2.132, | |
| "eval_samples_per_second": 232.649, | |
| "eval_steps_per_second": 7.505, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 2.090663058186739e-05, | |
| "loss": 1.2011, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "eval_accuracy": 0.7487909354704988, | |
| "eval_loss": 1.137099027633667, | |
| "eval_runtime": 2.022, | |
| "eval_samples_per_second": 245.301, | |
| "eval_steps_per_second": 7.913, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 2.073748308525034e-05, | |
| "loss": 1.1998, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "eval_accuracy": 0.7525347250536846, | |
| "eval_loss": 1.1276001930236816, | |
| "eval_runtime": 2.1283, | |
| "eval_samples_per_second": 233.052, | |
| "eval_steps_per_second": 7.518, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 2.056833558863329e-05, | |
| "loss": 1.1957, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "eval_accuracy": 0.7557962751805397, | |
| "eval_loss": 1.1078341007232666, | |
| "eval_runtime": 2.1602, | |
| "eval_samples_per_second": 229.608, | |
| "eval_steps_per_second": 7.407, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 2.039918809201624e-05, | |
| "loss": 1.2027, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "eval_accuracy": 0.745357875418331, | |
| "eval_loss": 1.1625709533691406, | |
| "eval_runtime": 2.1381, | |
| "eval_samples_per_second": 231.987, | |
| "eval_steps_per_second": 7.483, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 2.0230040595399188e-05, | |
| "loss": 1.2013, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "eval_accuracy": 0.7526884647845145, | |
| "eval_loss": 1.1228464841842651, | |
| "eval_runtime": 1.9029, | |
| "eval_samples_per_second": 260.656, | |
| "eval_steps_per_second": 8.408, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 2.0060893098782138e-05, | |
| "loss": 1.1944, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "eval_accuracy": 0.7478242411377627, | |
| "eval_loss": 1.1413049697875977, | |
| "eval_runtime": 2.1489, | |
| "eval_samples_per_second": 230.819, | |
| "eval_steps_per_second": 7.446, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 1.9891745602165088e-05, | |
| "loss": 1.1946, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "eval_accuracy": 0.7513838877841672, | |
| "eval_loss": 1.124992847442627, | |
| "eval_runtime": 2.2528, | |
| "eval_samples_per_second": 220.169, | |
| "eval_steps_per_second": 7.102, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 1.972259810554804e-05, | |
| "loss": 1.196, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "eval_accuracy": 0.7467797423793904, | |
| "eval_loss": 1.1447776556015015, | |
| "eval_runtime": 2.243, | |
| "eval_samples_per_second": 221.135, | |
| "eval_steps_per_second": 7.133, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 1.955345060893099e-05, | |
| "loss": 1.1893, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "eval_accuracy": 0.7478244470188862, | |
| "eval_loss": 1.1357169151306152, | |
| "eval_runtime": 2.1342, | |
| "eval_samples_per_second": 232.401, | |
| "eval_steps_per_second": 7.497, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 1.938430311231394e-05, | |
| "loss": 1.1865, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "eval_accuracy": 0.7525039957378796, | |
| "eval_loss": 1.120892882347107, | |
| "eval_runtime": 2.1457, | |
| "eval_samples_per_second": 231.161, | |
| "eval_steps_per_second": 7.457, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 1.9215155615696888e-05, | |
| "loss": 1.1921, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "eval_accuracy": 0.7517412799431865, | |
| "eval_loss": 1.1200112104415894, | |
| "eval_runtime": 2.2546, | |
| "eval_samples_per_second": 219.99, | |
| "eval_steps_per_second": 7.096, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 1.9046008119079838e-05, | |
| "loss": 1.1928, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "eval_accuracy": 0.751185221513814, | |
| "eval_loss": 1.1144980192184448, | |
| "eval_runtime": 1.9441, | |
| "eval_samples_per_second": 255.124, | |
| "eval_steps_per_second": 8.23, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 1.8876860622462788e-05, | |
| "loss": 1.1904, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "eval_accuracy": 0.754587343566813, | |
| "eval_loss": 1.1108394861221313, | |
| "eval_runtime": 2.252, | |
| "eval_samples_per_second": 220.248, | |
| "eval_steps_per_second": 7.105, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 1.8707713125845738e-05, | |
| "loss": 1.1955, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "eval_accuracy": 0.7540812503345287, | |
| "eval_loss": 1.106156826019287, | |
| "eval_runtime": 2.2623, | |
| "eval_samples_per_second": 219.243, | |
| "eval_steps_per_second": 7.072, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 1.8538565629228687e-05, | |
| "loss": 1.1898, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "eval_accuracy": 0.7519862396592678, | |
| "eval_loss": 1.126400351524353, | |
| "eval_runtime": 2.1347, | |
| "eval_samples_per_second": 232.346, | |
| "eval_steps_per_second": 7.495, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 1.8369418132611637e-05, | |
| "loss": 1.1917, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "eval_accuracy": 0.7535633076368476, | |
| "eval_loss": 1.112923502922058, | |
| "eval_runtime": 2.2569, | |
| "eval_samples_per_second": 219.772, | |
| "eval_steps_per_second": 7.089, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 1.8200270635994587e-05, | |
| "loss": 1.1895, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "eval_accuracy": 0.7494371965607963, | |
| "eval_loss": 1.1288461685180664, | |
| "eval_runtime": 2.1453, | |
| "eval_samples_per_second": 231.202, | |
| "eval_steps_per_second": 7.458, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 1.8031123139377537e-05, | |
| "loss": 1.1966, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "eval_accuracy": 0.7474297006435763, | |
| "eval_loss": 1.1435807943344116, | |
| "eval_runtime": 2.2544, | |
| "eval_samples_per_second": 220.014, | |
| "eval_steps_per_second": 7.097, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 1.7861975642760487e-05, | |
| "loss": 1.1887, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.7530491066652402, | |
| "eval_loss": 1.1220248937606812, | |
| "eval_runtime": 2.0377, | |
| "eval_samples_per_second": 243.414, | |
| "eval_steps_per_second": 7.852, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "learning_rate": 1.769282814614344e-05, | |
| "loss": 1.1856, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.7499591391991283, | |
| "eval_loss": 1.1441563367843628, | |
| "eval_runtime": 2.2428, | |
| "eval_samples_per_second": 221.15, | |
| "eval_steps_per_second": 7.134, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 1.752368064952639e-05, | |
| "loss": 1.1934, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.7487198734618374, | |
| "eval_loss": 1.134777545928955, | |
| "eval_runtime": 2.1446, | |
| "eval_samples_per_second": 231.279, | |
| "eval_steps_per_second": 7.461, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 1.7354533152909337e-05, | |
| "loss": 1.1848, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "eval_accuracy": 0.7521449252264457, | |
| "eval_loss": 1.1171698570251465, | |
| "eval_runtime": 2.2564, | |
| "eval_samples_per_second": 219.819, | |
| "eval_steps_per_second": 7.091, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 1.7185385656292287e-05, | |
| "loss": 1.1821, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "eval_accuracy": 0.7566415837311541, | |
| "eval_loss": 1.1042215824127197, | |
| "eval_runtime": 2.1261, | |
| "eval_samples_per_second": 233.296, | |
| "eval_steps_per_second": 7.526, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 1.7016238159675237e-05, | |
| "loss": 1.1817, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "eval_accuracy": 0.7495432072227, | |
| "eval_loss": 1.1272791624069214, | |
| "eval_runtime": 2.029, | |
| "eval_samples_per_second": 244.45, | |
| "eval_steps_per_second": 7.885, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "learning_rate": 1.6847090663058187e-05, | |
| "loss": 1.1773, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "eval_accuracy": 0.7539743031358885, | |
| "eval_loss": 1.0957542657852173, | |
| "eval_runtime": 2.193, | |
| "eval_samples_per_second": 226.174, | |
| "eval_steps_per_second": 7.296, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 1.6677943166441137e-05, | |
| "loss": 1.1774, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "eval_accuracy": 0.7510550791645386, | |
| "eval_loss": 1.1139615774154663, | |
| "eval_runtime": 2.0354, | |
| "eval_samples_per_second": 243.69, | |
| "eval_steps_per_second": 7.861, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 1.6508795669824086e-05, | |
| "loss": 1.1841, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "eval_accuracy": 0.7535410764872521, | |
| "eval_loss": 1.1085665225982666, | |
| "eval_runtime": 2.2775, | |
| "eval_samples_per_second": 217.784, | |
| "eval_steps_per_second": 7.025, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "learning_rate": 1.6339648173207036e-05, | |
| "loss": 1.1825, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "eval_accuracy": 0.7575840393550151, | |
| "eval_loss": 1.0903350114822388, | |
| "eval_runtime": 2.1352, | |
| "eval_samples_per_second": 232.293, | |
| "eval_steps_per_second": 7.493, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 1.6170500676589986e-05, | |
| "loss": 1.1845, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "eval_accuracy": 0.7486053092575125, | |
| "eval_loss": 1.129094123840332, | |
| "eval_runtime": 2.2564, | |
| "eval_samples_per_second": 219.823, | |
| "eval_steps_per_second": 7.091, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 1.6001353179972936e-05, | |
| "loss": 1.1853, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_accuracy": 0.7485774103500107, | |
| "eval_loss": 1.1317797899246216, | |
| "eval_runtime": 2.2139, | |
| "eval_samples_per_second": 224.036, | |
| "eval_steps_per_second": 7.227, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 1.5832205683355886e-05, | |
| "loss": 1.1761, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "eval_accuracy": 0.7552630190471166, | |
| "eval_loss": 1.1218476295471191, | |
| "eval_runtime": 2.2116, | |
| "eval_samples_per_second": 224.271, | |
| "eval_steps_per_second": 7.235, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 1.566305818673884e-05, | |
| "loss": 1.1825, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "eval_accuracy": 0.7484677617063006, | |
| "eval_loss": 1.130650520324707, | |
| "eval_runtime": 2.1348, | |
| "eval_samples_per_second": 232.339, | |
| "eval_steps_per_second": 7.495, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 1.549391069012179e-05, | |
| "loss": 1.1849, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "eval_accuracy": 0.7503921250473254, | |
| "eval_loss": 1.1273096799850464, | |
| "eval_runtime": 2.1346, | |
| "eval_samples_per_second": 232.367, | |
| "eval_steps_per_second": 7.496, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 1.5324763193504736e-05, | |
| "loss": 1.1792, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "eval_accuracy": 0.7496725963112518, | |
| "eval_loss": 1.1290724277496338, | |
| "eval_runtime": 2.0388, | |
| "eval_samples_per_second": 243.277, | |
| "eval_steps_per_second": 7.848, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "learning_rate": 1.5155615696887688e-05, | |
| "loss": 1.1852, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "eval_accuracy": 0.7521213264014223, | |
| "eval_loss": 1.1133606433868408, | |
| "eval_runtime": 2.1407, | |
| "eval_samples_per_second": 231.702, | |
| "eval_steps_per_second": 7.474, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.4986468200270637e-05, | |
| "loss": 1.1745, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "eval_accuracy": 0.7510633656887338, | |
| "eval_loss": 1.1251685619354248, | |
| "eval_runtime": 2.2562, | |
| "eval_samples_per_second": 219.835, | |
| "eval_steps_per_second": 7.091, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 1.4817320703653587e-05, | |
| "loss": 1.1746, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "eval_accuracy": 0.7508518468038707, | |
| "eval_loss": 1.114823579788208, | |
| "eval_runtime": 2.1373, | |
| "eval_samples_per_second": 232.068, | |
| "eval_steps_per_second": 7.486, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 1.4648173207036536e-05, | |
| "loss": 1.1765, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "eval_accuracy": 0.7499047204224969, | |
| "eval_loss": 1.120153784751892, | |
| "eval_runtime": 1.9047, | |
| "eval_samples_per_second": 260.406, | |
| "eval_steps_per_second": 8.4, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 1.4479025710419486e-05, | |
| "loss": 1.1762, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "eval_accuracy": 0.7526651867686152, | |
| "eval_loss": 1.11342453956604, | |
| "eval_runtime": 2.1108, | |
| "eval_samples_per_second": 234.982, | |
| "eval_steps_per_second": 7.58, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 1.4309878213802435e-05, | |
| "loss": 1.1752, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "eval_accuracy": 0.7550594107753242, | |
| "eval_loss": 1.1170574426651, | |
| "eval_runtime": 2.0286, | |
| "eval_samples_per_second": 244.505, | |
| "eval_steps_per_second": 7.887, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 1.4140730717185385e-05, | |
| "loss": 1.176, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "eval_accuracy": 0.7526875882289065, | |
| "eval_loss": 1.1155229806900024, | |
| "eval_runtime": 2.2532, | |
| "eval_samples_per_second": 220.127, | |
| "eval_steps_per_second": 7.101, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 1.3971583220568335e-05, | |
| "loss": 1.1732, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "eval_accuracy": 0.7481485413956945, | |
| "eval_loss": 1.133280873298645, | |
| "eval_runtime": 2.1464, | |
| "eval_samples_per_second": 231.081, | |
| "eval_steps_per_second": 7.454, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 1.3802435723951287e-05, | |
| "loss": 1.1753, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "eval_accuracy": 0.7574028502663674, | |
| "eval_loss": 1.0981875658035278, | |
| "eval_runtime": 2.0246, | |
| "eval_samples_per_second": 244.982, | |
| "eval_steps_per_second": 7.903, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 1.3633288227334237e-05, | |
| "loss": 1.1713, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "eval_accuracy": 0.749116988864623, | |
| "eval_loss": 1.1342977285385132, | |
| "eval_runtime": 2.1397, | |
| "eval_samples_per_second": 231.806, | |
| "eval_steps_per_second": 7.478, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 1.3464140730717187e-05, | |
| "loss": 1.1692, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "eval_accuracy": 0.7548563905532121, | |
| "eval_loss": 1.1020859479904175, | |
| "eval_runtime": 2.038, | |
| "eval_samples_per_second": 243.371, | |
| "eval_steps_per_second": 7.851, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 1.3294993234100137e-05, | |
| "loss": 1.17, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "eval_accuracy": 0.7503776331328444, | |
| "eval_loss": 1.110732078552246, | |
| "eval_runtime": 2.2439, | |
| "eval_samples_per_second": 221.039, | |
| "eval_steps_per_second": 7.13, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 1.3125845737483087e-05, | |
| "loss": 1.1699, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "eval_accuracy": 0.7505413012882971, | |
| "eval_loss": 1.1227320432662964, | |
| "eval_runtime": 2.1354, | |
| "eval_samples_per_second": 232.28, | |
| "eval_steps_per_second": 7.493, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 1.2956698240866036e-05, | |
| "loss": 1.1763, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "eval_accuracy": 0.7523848348960457, | |
| "eval_loss": 1.1152479648590088, | |
| "eval_runtime": 2.2475, | |
| "eval_samples_per_second": 220.693, | |
| "eval_steps_per_second": 7.119, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 1.2787550744248986e-05, | |
| "loss": 1.1729, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "eval_accuracy": 0.7563491422261722, | |
| "eval_loss": 1.0939308404922485, | |
| "eval_runtime": 2.0291, | |
| "eval_samples_per_second": 244.44, | |
| "eval_steps_per_second": 7.885, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 1.2618403247631935e-05, | |
| "loss": 1.1731, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "eval_accuracy": 0.7446182644738601, | |
| "eval_loss": 1.153084397315979, | |
| "eval_runtime": 2.1368, | |
| "eval_samples_per_second": 232.12, | |
| "eval_steps_per_second": 7.488, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 1.2449255751014885e-05, | |
| "loss": 1.1744, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_accuracy": 0.748938913662494, | |
| "eval_loss": 1.1451458930969238, | |
| "eval_runtime": 2.2627, | |
| "eval_samples_per_second": 219.205, | |
| "eval_steps_per_second": 7.071, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 1.2280108254397836e-05, | |
| "loss": 1.169, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "eval_accuracy": 0.7527127355796688, | |
| "eval_loss": 1.1211124658584595, | |
| "eval_runtime": 2.254, | |
| "eval_samples_per_second": 220.058, | |
| "eval_steps_per_second": 7.099, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 1.2110960757780786e-05, | |
| "loss": 1.1644, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "eval_accuracy": 0.7553240179845462, | |
| "eval_loss": 1.1134895086288452, | |
| "eval_runtime": 2.1385, | |
| "eval_samples_per_second": 231.943, | |
| "eval_steps_per_second": 7.482, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 1.1941813261163736e-05, | |
| "loss": 1.1726, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "eval_accuracy": 0.7551064057320073, | |
| "eval_loss": 1.0903879404067993, | |
| "eval_runtime": 2.141, | |
| "eval_samples_per_second": 231.664, | |
| "eval_steps_per_second": 7.473, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "learning_rate": 1.1772665764546684e-05, | |
| "loss": 1.1653, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "eval_accuracy": 0.7585871152701898, | |
| "eval_loss": 1.0806618928909302, | |
| "eval_runtime": 2.2591, | |
| "eval_samples_per_second": 219.56, | |
| "eval_steps_per_second": 7.083, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 1.1603518267929634e-05, | |
| "loss": 1.1651, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "eval_accuracy": 0.7487410264652309, | |
| "eval_loss": 1.1385972499847412, | |
| "eval_runtime": 2.0137, | |
| "eval_samples_per_second": 246.318, | |
| "eval_steps_per_second": 7.946, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 1.1434370771312584e-05, | |
| "loss": 1.1663, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "eval_accuracy": 0.7531269501044577, | |
| "eval_loss": 1.1114603281021118, | |
| "eval_runtime": 2.038, | |
| "eval_samples_per_second": 243.378, | |
| "eval_steps_per_second": 7.851, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 1.1265223274695536e-05, | |
| "loss": 1.1635, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "eval_accuracy": 0.7503972421965474, | |
| "eval_loss": 1.1271893978118896, | |
| "eval_runtime": 2.2587, | |
| "eval_samples_per_second": 219.592, | |
| "eval_steps_per_second": 7.084, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 1.1096075778078486e-05, | |
| "loss": 1.1646, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "eval_accuracy": 0.7541348344725908, | |
| "eval_loss": 1.0982328653335571, | |
| "eval_runtime": 2.0235, | |
| "eval_samples_per_second": 245.115, | |
| "eval_steps_per_second": 7.907, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "learning_rate": 1.0926928281461436e-05, | |
| "loss": 1.1639, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "eval_accuracy": 0.7544710600476913, | |
| "eval_loss": 1.1104248762130737, | |
| "eval_runtime": 2.0141, | |
| "eval_samples_per_second": 246.267, | |
| "eval_steps_per_second": 7.944, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 1.0757780784844384e-05, | |
| "loss": 1.1598, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "eval_accuracy": 0.7492906747372119, | |
| "eval_loss": 1.1334669589996338, | |
| "eval_runtime": 2.1233, | |
| "eval_samples_per_second": 233.593, | |
| "eval_steps_per_second": 7.535, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 1.0588633288227334e-05, | |
| "loss": 1.1612, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "eval_accuracy": 0.7535777086433112, | |
| "eval_loss": 1.1088109016418457, | |
| "eval_runtime": 2.1482, | |
| "eval_samples_per_second": 230.894, | |
| "eval_steps_per_second": 7.448, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 1.0419485791610285e-05, | |
| "loss": 1.159, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "eval_accuracy": 0.755389401298914, | |
| "eval_loss": 1.0895658731460571, | |
| "eval_runtime": 1.8998, | |
| "eval_samples_per_second": 261.073, | |
| "eval_steps_per_second": 8.422, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 1.0250338294993235e-05, | |
| "loss": 1.1686, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "eval_accuracy": 0.7521880806829505, | |
| "eval_loss": 1.1212115287780762, | |
| "eval_runtime": 2.1408, | |
| "eval_samples_per_second": 231.688, | |
| "eval_steps_per_second": 7.474, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 1.0081190798376185e-05, | |
| "loss": 1.158, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "eval_accuracy": 0.7528032891926527, | |
| "eval_loss": 1.1104135513305664, | |
| "eval_runtime": 2.2497, | |
| "eval_samples_per_second": 220.471, | |
| "eval_steps_per_second": 7.112, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 9.912043301759135e-06, | |
| "loss": 1.1633, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "eval_accuracy": 0.7537655533726261, | |
| "eval_loss": 1.097953200340271, | |
| "eval_runtime": 2.0401, | |
| "eval_samples_per_second": 243.13, | |
| "eval_steps_per_second": 7.843, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 9.742895805142083e-06, | |
| "loss": 1.1622, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "eval_accuracy": 0.750889583782618, | |
| "eval_loss": 1.1274609565734863, | |
| "eval_runtime": 2.0243, | |
| "eval_samples_per_second": 245.026, | |
| "eval_steps_per_second": 7.904, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 9.573748308525033e-06, | |
| "loss": 1.1625, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "eval_accuracy": 0.754607674067687, | |
| "eval_loss": 1.1065136194229126, | |
| "eval_runtime": 1.9032, | |
| "eval_samples_per_second": 260.616, | |
| "eval_steps_per_second": 8.407, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 9.404600811907985e-06, | |
| "loss": 1.1582, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "eval_accuracy": 0.7515266766659524, | |
| "eval_loss": 1.1181069612503052, | |
| "eval_runtime": 2.1333, | |
| "eval_samples_per_second": 232.507, | |
| "eval_steps_per_second": 7.5, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 16.31, | |
| "learning_rate": 9.235453315290935e-06, | |
| "loss": 1.1568, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 16.31, | |
| "eval_accuracy": 0.7558363160425237, | |
| "eval_loss": 1.1019920110702515, | |
| "eval_runtime": 2.1312, | |
| "eval_samples_per_second": 232.728, | |
| "eval_steps_per_second": 7.507, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 16.37, | |
| "learning_rate": 9.066305818673885e-06, | |
| "loss": 1.1573, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 16.37, | |
| "eval_accuracy": 0.7532534995625547, | |
| "eval_loss": 1.115644097328186, | |
| "eval_runtime": 2.1433, | |
| "eval_samples_per_second": 231.416, | |
| "eval_steps_per_second": 7.465, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 8.897158322056835e-06, | |
| "loss": 1.1549, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "eval_accuracy": 0.7508123310487945, | |
| "eval_loss": 1.1205765008926392, | |
| "eval_runtime": 2.2601, | |
| "eval_samples_per_second": 219.456, | |
| "eval_steps_per_second": 7.079, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 8.728010825439783e-06, | |
| "loss": 1.1592, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "eval_accuracy": 0.7542723559759243, | |
| "eval_loss": 1.0985246896743774, | |
| "eval_runtime": 2.2649, | |
| "eval_samples_per_second": 218.998, | |
| "eval_steps_per_second": 7.064, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "learning_rate": 8.558863328822733e-06, | |
| "loss": 1.1584, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "eval_accuracy": 0.7531888104231674, | |
| "eval_loss": 1.1170583963394165, | |
| "eval_runtime": 2.028, | |
| "eval_samples_per_second": 244.575, | |
| "eval_steps_per_second": 7.89, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 8.389715832205684e-06, | |
| "loss": 1.1589, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "eval_accuracy": 0.7611846765843823, | |
| "eval_loss": 1.0686120986938477, | |
| "eval_runtime": 2.0269, | |
| "eval_samples_per_second": 244.714, | |
| "eval_steps_per_second": 7.894, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "learning_rate": 8.220568335588634e-06, | |
| "loss": 1.1566, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "eval_accuracy": 0.7563581433672069, | |
| "eval_loss": 1.094774603843689, | |
| "eval_runtime": 2.1272, | |
| "eval_samples_per_second": 233.175, | |
| "eval_steps_per_second": 7.522, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 8.051420838971584e-06, | |
| "loss": 1.157, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "eval_accuracy": 0.7568443220476267, | |
| "eval_loss": 1.0895816087722778, | |
| "eval_runtime": 1.8979, | |
| "eval_samples_per_second": 261.337, | |
| "eval_steps_per_second": 8.43, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 16.85, | |
| "learning_rate": 7.882273342354534e-06, | |
| "loss": 1.1598, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 16.85, | |
| "eval_accuracy": 0.7582212358242888, | |
| "eval_loss": 1.086458683013916, | |
| "eval_runtime": 2.2441, | |
| "eval_samples_per_second": 221.026, | |
| "eval_steps_per_second": 7.13, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 7.713125845737482e-06, | |
| "loss": 1.1567, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "eval_accuracy": 0.7565769744554401, | |
| "eval_loss": 1.1091084480285645, | |
| "eval_runtime": 2.2461, | |
| "eval_samples_per_second": 220.83, | |
| "eval_steps_per_second": 7.124, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "learning_rate": 7.543978349120433e-06, | |
| "loss": 1.1643, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "eval_accuracy": 0.7521943363306939, | |
| "eval_loss": 1.1232304573059082, | |
| "eval_runtime": 1.9345, | |
| "eval_samples_per_second": 256.4, | |
| "eval_steps_per_second": 8.271, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 7.374830852503384e-06, | |
| "loss": 1.1536, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "eval_accuracy": 0.7583081570996979, | |
| "eval_loss": 1.0930777788162231, | |
| "eval_runtime": 2.1324, | |
| "eval_samples_per_second": 232.599, | |
| "eval_steps_per_second": 7.503, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 7.205683355886334e-06, | |
| "loss": 1.1486, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "eval_accuracy": 0.7540195062318956, | |
| "eval_loss": 1.1099752187728882, | |
| "eval_runtime": 1.917, | |
| "eval_samples_per_second": 258.744, | |
| "eval_steps_per_second": 8.347, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "learning_rate": 7.036535859269283e-06, | |
| "loss": 1.1551, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "eval_accuracy": 0.7537926501999014, | |
| "eval_loss": 1.1018755435943604, | |
| "eval_runtime": 2.2805, | |
| "eval_samples_per_second": 217.494, | |
| "eval_steps_per_second": 7.016, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 6.867388362652233e-06, | |
| "loss": 1.1491, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "eval_accuracy": 0.7546221700303138, | |
| "eval_loss": 1.096489667892456, | |
| "eval_runtime": 2.0207, | |
| "eval_samples_per_second": 245.455, | |
| "eval_steps_per_second": 7.918, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 6.698240866035183e-06, | |
| "loss": 1.152, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "eval_accuracy": 0.7590838783208054, | |
| "eval_loss": 1.0724998712539673, | |
| "eval_runtime": 2.2748, | |
| "eval_samples_per_second": 218.043, | |
| "eval_steps_per_second": 7.034, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 6.5290933694181334e-06, | |
| "loss": 1.1521, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "eval_accuracy": 0.7526631431935811, | |
| "eval_loss": 1.1246150732040405, | |
| "eval_runtime": 2.2564, | |
| "eval_samples_per_second": 219.819, | |
| "eval_steps_per_second": 7.091, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 17.46, | |
| "learning_rate": 6.359945872801083e-06, | |
| "loss": 1.1518, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 17.46, | |
| "eval_accuracy": 0.7570206230802984, | |
| "eval_loss": 1.1025118827819824, | |
| "eval_runtime": 2.2644, | |
| "eval_samples_per_second": 219.041, | |
| "eval_steps_per_second": 7.066, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 6.190798376184033e-06, | |
| "loss": 1.1525, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "eval_accuracy": 0.7553470100392842, | |
| "eval_loss": 1.1027612686157227, | |
| "eval_runtime": 2.2829, | |
| "eval_samples_per_second": 217.27, | |
| "eval_steps_per_second": 7.009, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 6.021650879566982e-06, | |
| "loss": 1.1509, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "eval_accuracy": 0.753968902322795, | |
| "eval_loss": 1.1140735149383545, | |
| "eval_runtime": 2.0112, | |
| "eval_samples_per_second": 246.621, | |
| "eval_steps_per_second": 7.956, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 5.852503382949932e-06, | |
| "loss": 1.1522, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "eval_accuracy": 0.7523416805483493, | |
| "eval_loss": 1.1235767602920532, | |
| "eval_runtime": 2.0162, | |
| "eval_samples_per_second": 246.006, | |
| "eval_steps_per_second": 7.936, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 17.73, | |
| "learning_rate": 5.683355886332883e-06, | |
| "loss": 1.1488, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 17.73, | |
| "eval_accuracy": 0.7589817903428665, | |
| "eval_loss": 1.0937731266021729, | |
| "eval_runtime": 2.1303, | |
| "eval_samples_per_second": 232.835, | |
| "eval_steps_per_second": 7.511, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 5.514208389715832e-06, | |
| "loss": 1.1477, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "eval_accuracy": 0.7519756032882524, | |
| "eval_loss": 1.1069520711898804, | |
| "eval_runtime": 2.1341, | |
| "eval_samples_per_second": 232.421, | |
| "eval_steps_per_second": 7.497, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 5.345060893098782e-06, | |
| "loss": 1.1498, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "eval_accuracy": 0.7560714094247574, | |
| "eval_loss": 1.0885875225067139, | |
| "eval_runtime": 2.2647, | |
| "eval_samples_per_second": 219.014, | |
| "eval_steps_per_second": 7.065, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 5.175913396481733e-06, | |
| "loss": 1.1489, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "eval_accuracy": 0.75788641382883, | |
| "eval_loss": 1.0874009132385254, | |
| "eval_runtime": 2.1397, | |
| "eval_samples_per_second": 231.808, | |
| "eval_steps_per_second": 7.478, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 5.006765899864682e-06, | |
| "loss": 1.1462, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7556547699093623, | |
| "eval_loss": 1.1015816926956177, | |
| "eval_runtime": 2.2706, | |
| "eval_samples_per_second": 218.448, | |
| "eval_steps_per_second": 7.047, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 4.837618403247632e-06, | |
| "loss": 1.1448, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "eval_accuracy": 0.7546062508530094, | |
| "eval_loss": 1.0937751531600952, | |
| "eval_runtime": 2.022, | |
| "eval_samples_per_second": 245.305, | |
| "eval_steps_per_second": 7.913, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 4.6684709066305826e-06, | |
| "loss": 1.1425, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "eval_accuracy": 0.7552112751822265, | |
| "eval_loss": 1.0958871841430664, | |
| "eval_runtime": 2.2598, | |
| "eval_samples_per_second": 219.486, | |
| "eval_steps_per_second": 7.08, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 18.2, | |
| "learning_rate": 4.499323410013532e-06, | |
| "loss": 1.1414, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 18.2, | |
| "eval_accuracy": 0.7558802565930149, | |
| "eval_loss": 1.0867284536361694, | |
| "eval_runtime": 2.029, | |
| "eval_samples_per_second": 244.456, | |
| "eval_steps_per_second": 7.886, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "learning_rate": 4.330175913396482e-06, | |
| "loss": 1.1453, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "eval_accuracy": 0.7591597591597592, | |
| "eval_loss": 1.0756407976150513, | |
| "eval_runtime": 2.1403, | |
| "eval_samples_per_second": 231.744, | |
| "eval_steps_per_second": 7.476, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 4.161028416779432e-06, | |
| "loss": 1.1448, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "eval_accuracy": 0.7545405695862439, | |
| "eval_loss": 1.0937347412109375, | |
| "eval_runtime": 2.2479, | |
| "eval_samples_per_second": 220.651, | |
| "eval_steps_per_second": 7.118, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 3.991880920162381e-06, | |
| "loss": 1.1471, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "eval_accuracy": 0.7537506745817593, | |
| "eval_loss": 1.1153604984283447, | |
| "eval_runtime": 2.2669, | |
| "eval_samples_per_second": 218.8, | |
| "eval_steps_per_second": 7.058, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 3.822733423545332e-06, | |
| "loss": 1.1484, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "eval_accuracy": 0.7537701926689208, | |
| "eval_loss": 1.1114356517791748, | |
| "eval_runtime": 2.0201, | |
| "eval_samples_per_second": 245.53, | |
| "eval_steps_per_second": 7.92, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "learning_rate": 3.6535859269282817e-06, | |
| "loss": 1.1463, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "eval_accuracy": 0.7513940144923632, | |
| "eval_loss": 1.1001887321472168, | |
| "eval_runtime": 2.1485, | |
| "eval_samples_per_second": 230.858, | |
| "eval_steps_per_second": 7.447, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 3.4844384303112316e-06, | |
| "loss": 1.1512, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "eval_accuracy": 0.7586606950140298, | |
| "eval_loss": 1.0663777589797974, | |
| "eval_runtime": 2.1796, | |
| "eval_samples_per_second": 227.562, | |
| "eval_steps_per_second": 7.341, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "learning_rate": 3.315290933694182e-06, | |
| "loss": 1.1464, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "eval_accuracy": 0.7583911006384086, | |
| "eval_loss": 1.0735660791397095, | |
| "eval_runtime": 2.251, | |
| "eval_samples_per_second": 220.348, | |
| "eval_steps_per_second": 7.108, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 18.74, | |
| "learning_rate": 3.1461434370771314e-06, | |
| "loss": 1.1457, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 18.74, | |
| "eval_accuracy": 0.7604149648750205, | |
| "eval_loss": 1.080166220664978, | |
| "eval_runtime": 2.1301, | |
| "eval_samples_per_second": 232.857, | |
| "eval_steps_per_second": 7.512, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 2.9769959404600813e-06, | |
| "loss": 1.1464, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "eval_accuracy": 0.75420555676145, | |
| "eval_loss": 1.1091315746307373, | |
| "eval_runtime": 2.1281, | |
| "eval_samples_per_second": 233.067, | |
| "eval_steps_per_second": 7.518, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.8078484438430312e-06, | |
| "loss": 1.1415, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "eval_accuracy": 0.7594658329138073, | |
| "eval_loss": 1.0856248140335083, | |
| "eval_runtime": 2.2679, | |
| "eval_samples_per_second": 218.701, | |
| "eval_steps_per_second": 7.055, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "learning_rate": 2.638700947225981e-06, | |
| "loss": 1.149, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "eval_accuracy": 0.7557433607017732, | |
| "eval_loss": 1.0958749055862427, | |
| "eval_runtime": 2.1355, | |
| "eval_samples_per_second": 232.263, | |
| "eval_steps_per_second": 7.492, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 2.469553450608931e-06, | |
| "loss": 1.1445, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "eval_accuracy": 0.7600160578081092, | |
| "eval_loss": 1.0713545083999634, | |
| "eval_runtime": 2.0458, | |
| "eval_samples_per_second": 242.449, | |
| "eval_steps_per_second": 7.821, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "learning_rate": 2.300405953991881e-06, | |
| "loss": 1.1378, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "eval_accuracy": 0.7528535980148884, | |
| "eval_loss": 1.1179081201553345, | |
| "eval_runtime": 2.239, | |
| "eval_samples_per_second": 221.527, | |
| "eval_steps_per_second": 7.146, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 2.131258457374831e-06, | |
| "loss": 1.143, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "eval_accuracy": 0.7608561044555122, | |
| "eval_loss": 1.085029125213623, | |
| "eval_runtime": 2.2698, | |
| "eval_samples_per_second": 218.525, | |
| "eval_steps_per_second": 7.049, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 19.22, | |
| "learning_rate": 1.962110960757781e-06, | |
| "loss": 1.1412, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 19.22, | |
| "eval_accuracy": 0.7571760842796552, | |
| "eval_loss": 1.1089389324188232, | |
| "eval_runtime": 2.2591, | |
| "eval_samples_per_second": 219.56, | |
| "eval_steps_per_second": 7.083, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 19.28, | |
| "learning_rate": 1.7929634641407306e-06, | |
| "loss": 1.1393, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 19.28, | |
| "eval_accuracy": 0.7580414678206476, | |
| "eval_loss": 1.095458984375, | |
| "eval_runtime": 1.8948, | |
| "eval_samples_per_second": 261.767, | |
| "eval_steps_per_second": 8.444, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 1.6238159675236807e-06, | |
| "loss": 1.1492, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "eval_accuracy": 0.755947708880288, | |
| "eval_loss": 1.0982964038848877, | |
| "eval_runtime": 2.019, | |
| "eval_samples_per_second": 245.66, | |
| "eval_steps_per_second": 7.925, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 1.4546684709066306e-06, | |
| "loss": 1.1455, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "eval_accuracy": 0.7540966020328801, | |
| "eval_loss": 1.12480628490448, | |
| "eval_runtime": 1.9105, | |
| "eval_samples_per_second": 259.614, | |
| "eval_steps_per_second": 8.375, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 1.2855209742895805e-06, | |
| "loss": 1.1442, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "eval_accuracy": 0.7567218409366169, | |
| "eval_loss": 1.1033666133880615, | |
| "eval_runtime": 2.1366, | |
| "eval_samples_per_second": 232.142, | |
| "eval_steps_per_second": 7.488, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "learning_rate": 1.1163734776725304e-06, | |
| "loss": 1.1385, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "eval_accuracy": 0.7598665473187404, | |
| "eval_loss": 1.0718320608139038, | |
| "eval_runtime": 2.1421, | |
| "eval_samples_per_second": 231.551, | |
| "eval_steps_per_second": 7.469, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 9.472259810554805e-07, | |
| "loss": 1.1393, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "eval_accuracy": 0.7511771590321439, | |
| "eval_loss": 1.1188093423843384, | |
| "eval_runtime": 1.937, | |
| "eval_samples_per_second": 256.065, | |
| "eval_steps_per_second": 8.26, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "learning_rate": 7.780784844384303e-07, | |
| "loss": 1.1408, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "eval_accuracy": 0.7571148718506829, | |
| "eval_loss": 1.096737027168274, | |
| "eval_runtime": 2.128, | |
| "eval_samples_per_second": 233.085, | |
| "eval_steps_per_second": 7.519, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 19.76, | |
| "learning_rate": 6.089309878213802e-07, | |
| "loss": 1.1443, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 19.76, | |
| "eval_accuracy": 0.7525236340330075, | |
| "eval_loss": 1.115225911140442, | |
| "eval_runtime": 2.0196, | |
| "eval_samples_per_second": 245.588, | |
| "eval_steps_per_second": 7.922, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "learning_rate": 4.397834912043302e-07, | |
| "loss": 1.1495, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "eval_accuracy": 0.7534898820473974, | |
| "eval_loss": 1.1063731908798218, | |
| "eval_runtime": 2.0319, | |
| "eval_samples_per_second": 244.111, | |
| "eval_steps_per_second": 7.875, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 2.7063599458728015e-07, | |
| "loss": 1.1397, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "eval_accuracy": 0.7602626366768863, | |
| "eval_loss": 1.0799843072891235, | |
| "eval_runtime": 2.3196, | |
| "eval_samples_per_second": 213.833, | |
| "eval_steps_per_second": 6.898, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 19.96, | |
| "learning_rate": 1.0148849797023004e-07, | |
| "loss": 1.1399, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 19.96, | |
| "eval_accuracy": 0.7566619534479008, | |
| "eval_loss": 1.0812491178512573, | |
| "eval_runtime": 2.2409, | |
| "eval_samples_per_second": 221.343, | |
| "eval_steps_per_second": 7.14, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 147800, | |
| "total_flos": 1.2450139383539958e+18, | |
| "train_loss": 1.2263236557646922, | |
| "train_runtime": 47907.234, | |
| "train_samples_per_second": 98.713, | |
| "train_steps_per_second": 3.085 | |
| } | |
| ], | |
| "max_steps": 147800, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.2450139383539958e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |