| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.996101364522417, |
| "eval_steps": 50, |
| "global_step": 512, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 1.923076923076923e-05, |
| "loss": 2.7497, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 2.7052, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 5.769230769230769e-05, |
| "loss": 2.6213, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 2.6018, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 9.615384615384617e-05, |
| "loss": 2.5872, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 9.998328666948438e-05, |
| "loss": 2.5665, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 9.991540791356342e-05, |
| "loss": 2.5494, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 9.979538999730047e-05, |
| "loss": 2.5143, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 9.962335828546048e-05, |
| "loss": 2.441, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 9.939949247384046e-05, |
| "loss": 2.4432, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.19, |
| "eval_accuracy": 0.5032714541605602, |
| "eval_loss": 2.3850491046905518, |
| "eval_runtime": 14.1442, |
| "eval_samples_per_second": 21.21, |
| "eval_steps_per_second": 10.605, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 9.912402640156811e-05, |
| "loss": 2.4841, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 9.879724780684519e-05, |
| "loss": 2.4121, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 9.84194980263903e-05, |
| "loss": 2.4448, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 9.799117163889559e-05, |
| "loss": 2.4297, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 9.751271605286941e-05, |
| "loss": 2.4581, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 9.698463103929542e-05, |
| "loss": 2.435, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 9.640746820959684e-05, |
| "loss": 2.3842, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 9.57818304394503e-05, |
| "loss": 2.3872, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 9.51083712390519e-05, |
| "loss": 2.426, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 9.438779407049281e-05, |
| "loss": 2.3655, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.39, |
| "eval_accuracy": 0.5129278619117408, |
| "eval_loss": 2.3123531341552734, |
| "eval_runtime": 14.1415, |
| "eval_samples_per_second": 21.214, |
| "eval_steps_per_second": 10.607, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 9.362085161295769e-05, |
| "loss": 2.402, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 9.280834497651334e-05, |
| "loss": 2.3523, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 9.195112286530873e-05, |
| "loss": 2.3354, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 9.105008069106093e-05, |
| "loss": 2.37, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 9.01061596377522e-05, |
| "loss": 2.3597, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 8.912034567851599e-05, |
| "loss": 2.3646, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 8.809366854573831e-05, |
| "loss": 2.3601, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 8.702720065545024e-05, |
| "loss": 2.3424, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 8.592205598713539e-05, |
| "loss": 2.3362, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 8.47793889201221e-05, |
| "loss": 2.374, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.58, |
| "eval_accuracy": 0.5214769581501384, |
| "eval_loss": 2.258837938308716, |
| "eval_runtime": 14.3574, |
| "eval_samples_per_second": 20.895, |
| "eval_steps_per_second": 10.448, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 8.360039302777612e-05, |
| "loss": 2.3383, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 8.238629983075294e-05, |
| "loss": 2.319, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 8.113837751061246e-05, |
| "loss": 2.3517, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 7.985792958513931e-05, |
| "loss": 2.307, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 7.854629354675291e-05, |
| "loss": 2.2915, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 7.720483946542914e-05, |
| "loss": 2.3198, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 7.583496855759316e-05, |
| "loss": 2.3304, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 7.443811172247821e-05, |
| "loss": 2.2926, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 7.30157280474793e-05, |
| "loss": 2.2753, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 7.156930328406268e-05, |
| "loss": 2.3558, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.78, |
| "eval_accuracy": 0.5291418335775933, |
| "eval_loss": 2.2132091522216797, |
| "eval_runtime": 14.0805, |
| "eval_samples_per_second": 21.306, |
| "eval_steps_per_second": 10.653, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 7.01003482958237e-05, |
| "loss": 2.3026, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 6.861039748031351e-05, |
| "loss": 2.3327, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 6.710100716628344e-05, |
| "loss": 2.3047, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 6.557375398802123e-05, |
| "loss": 2.2849, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 6.403023323847695e-05, |
| "loss": 2.2972, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 6.247205720289907e-05, |
| "loss": 2.3069, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 6.09008534747213e-05, |
| "loss": 2.3305, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 5.9318263255459116e-05, |
| "loss": 2.2845, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 5.772593964039203e-05, |
| "loss": 2.2698, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 5.6125545891822274e-05, |
| "loss": 2.2677, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.97, |
| "eval_accuracy": 0.5348330890734408, |
| "eval_loss": 2.182823896408081, |
| "eval_runtime": 14.0998, |
| "eval_samples_per_second": 21.277, |
| "eval_steps_per_second": 10.638, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 5.451875370171341e-05, |
| "loss": 2.2776, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 5.290724144552379e-05, |
| "loss": 2.1158, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 5.129269242905882e-05, |
| "loss": 2.0758, |
| "step": 265 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 4.967679313017303e-05, |
| "loss": 2.053, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 4.806123143715916e-05, |
| "loss": 2.0824, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 4.6447694885663514e-05, |
| "loss": 2.062, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 4.4837868895969936e-05, |
| "loss": 2.0986, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 4.323343501249346e-05, |
| "loss": 2.0749, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 4.1636069147322246e-05, |
| "loss": 2.0365, |
| "step": 295 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 4.004743982964298e-05, |
| "loss": 2.0701, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.17, |
| "eval_accuracy": 0.5372854583943983, |
| "eval_loss": 2.178772211074829, |
| "eval_runtime": 14.087, |
| "eval_samples_per_second": 21.296, |
| "eval_steps_per_second": 10.648, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 3.846920646287799e-05, |
| "loss": 2.0554, |
| "step": 305 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 3.6903017591354706e-05, |
| "loss": 2.0432, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 3.535050917831797e-05, |
| "loss": 2.0663, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 3.381330289708396e-05, |
| "loss": 2.0673, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 3.2293004437120624e-05, |
| "loss": 2.0106, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 3.079120182682412e-05, |
| "loss": 2.0177, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 2.9309463774743046e-05, |
| "loss": 2.0314, |
| "step": 335 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 2.7849338030983257e-05, |
| "loss": 2.06, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 2.641234977050484e-05, |
| "loss": 2.0765, |
| "step": 345 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 2.0766, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.36, |
| "eval_accuracy": 0.5397508549096238, |
| "eval_loss": 2.1673190593719482, |
| "eval_runtime": 14.2515, |
| "eval_samples_per_second": 21.05, |
| "eval_steps_per_second": 10.525, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 2.361376399001592e-05, |
| "loss": 2.0481, |
| "step": 355 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 2.225508973396016e-05, |
| "loss": 2.0246, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 2.0925396435598664e-05, |
| "loss": 2.0563, |
| "step": 365 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 1.9626073026625818e-05, |
| "loss": 2.0373, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 1.835847671585526e-05, |
| "loss": 2.0495, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 1.7123931571546827e-05, |
| "loss": 2.0612, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 1.592372713835055e-05, |
| "loss": 2.0543, |
| "step": 385 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 1.4759117090312197e-05, |
| "loss": 2.0719, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 1.3631317921347563e-05, |
| "loss": 2.0468, |
| "step": 395 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 1.25415076745532e-05, |
| "loss": 2.0669, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.56, |
| "eval_accuracy": 0.5402182055039896, |
| "eval_loss": 2.165104866027832, |
| "eval_runtime": 14.1201, |
| "eval_samples_per_second": 21.246, |
| "eval_steps_per_second": 10.623, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 1.1490824711681025e-05, |
| "loss": 2.0491, |
| "step": 405 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 1.0480366524062042e-05, |
| "loss": 2.0686, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 9.511188586221376e-06, |
| "loss": 2.0816, |
| "step": 415 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 8.584303253381847e-06, |
| "loss": 2.0808, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 7.700678704007947e-06, |
| "loss": 2.0244, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 6.861237928494579e-06, |
| "loss": 2.0715, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 6.066857765057055e-06, |
| "loss": 2.0629, |
| "step": 435 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 5.318367983829392e-06, |
| "loss": 2.0738, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 4.616550420127563e-06, |
| "loss": 2.0449, |
| "step": 445 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 3.962138157783085e-06, |
| "loss": 2.0314, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.75, |
| "eval_accuracy": 0.5405943657384791, |
| "eval_loss": 2.1640877723693848, |
| "eval_runtime": 14.1591, |
| "eval_samples_per_second": 21.188, |
| "eval_steps_per_second": 10.594, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 3.3558147633999728e-06, |
| "loss": 2.0818, |
| "step": 455 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 2.798213572335001e-06, |
| "loss": 2.0991, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 2.2899170271469428e-06, |
| "loss": 2.0317, |
| "step": 465 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 1.8314560692059835e-06, |
| "loss": 2.0518, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 1.4233095840986753e-06, |
| "loss": 2.013, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 1.0659039014077944e-06, |
| "loss": 2.0317, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 7.596123493895991e-07, |
| "loss": 2.038, |
| "step": 485 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 5.047548650136513e-07, |
| "loss": 2.0414, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 3.0159765977250673e-07, |
| "loss": 2.0509, |
| "step": 495 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 1.503529416103988e-07, |
| "loss": 2.0281, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.95, |
| "eval_accuracy": 0.5406627585083863, |
| "eval_loss": 2.163918972015381, |
| "eval_runtime": 14.1546, |
| "eval_samples_per_second": 21.194, |
| "eval_steps_per_second": 10.597, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 5.11786932613223e-08, |
| "loss": 2.0471, |
| "step": 505 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 4.178507228136397e-09, |
| "loss": 2.055, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 512, |
| "total_flos": 4.1654970530503066e+17, |
| "train_loss": 2.223597173579037, |
| "train_runtime": 8040.0291, |
| "train_samples_per_second": 4.084, |
| "train_steps_per_second": 0.064, |
| "train_tokens_per_second": 8363.146 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 512, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 50, |
| "total_flos": 4.1654970530503066e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
