| { | |
| "best_metric": 2.7756218910217285, | |
| "best_model_checkpoint": "output/post-malone/checkpoint-320", | |
| "epoch": 5.0, | |
| "global_step": 320, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00013514414396914573, | |
| "loss": 3.4543, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012909979873429716, | |
| "loss": 3.3387, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00011942924719935021, | |
| "loss": 3.3541, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010671211798514472, | |
| "loss": 3.1751, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.171064394270629e-05, | |
| "loss": 3.3546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.532397582660788e-05, | |
| "loss": 3.0662, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.853428945236219e-05, | |
| "loss": 3.0141, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 3.1162, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.773502771181907e-05, | |
| "loss": 2.9451, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.557148289931624e-05, | |
| "loss": 2.8693, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.586334491731787e-06, | |
| "loss": 2.8391, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3181297643383925e-06, | |
| "loss": 3.057, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.9327073097229004, | |
| "eval_runtime": 4.0481, | |
| "eval_samples_per_second": 22.479, | |
| "eval_steps_per_second": 2.964, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 8.263170432517302e-08, | |
| "loss": 2.9592, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.9538929687704672e-06, | |
| "loss": 2.9051, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.759817353981332e-06, | |
| "loss": 2.8939, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.009247481060283e-05, | |
| "loss": 2.9256, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.333255174834499e-05, | |
| "loss": 2.7927, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 4.8686471140343875e-05, | |
| "loss": 2.8323, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 6.523395754113913e-05, | |
| "loss": 2.8623, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.19831960903064e-05, | |
| "loss": 2.6679, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.793027940931736e-05, | |
| "loss": 2.5538, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00011211937929362609, | |
| "loss": 2.6828, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012370003665957224, | |
| "loss": 2.8431, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00013197813593027427, | |
| "loss": 2.8521, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00013645750858358398, | |
| "loss": 2.8483, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.8603508472442627, | |
| "eval_runtime": 4.0668, | |
| "eval_samples_per_second": 22.376, | |
| "eval_steps_per_second": 2.951, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0001368696722497127, | |
| "loss": 2.668, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00013318992287155525, | |
| "loss": 2.6112, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0001256388154039546, | |
| "loss": 2.332, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0001146689443025055, | |
| "loss": 2.5603, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00010093781614626346, | |
| "loss": 2.464, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.526844034136393e-05, | |
| "loss": 2.6616, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.860000000000001e-05, | |
| "loss": 2.4311, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 5.1931559658636174e-05, | |
| "loss": 2.5385, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.6262183853736576e-05, | |
| "loss": 2.3496, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.253105569749459e-05, | |
| "loss": 2.5517, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.1561184596045404e-05, | |
| "loss": 2.5856, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 4.010077128444796e-06, | |
| "loss": 2.3964, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.303277502872907e-07, | |
| "loss": 2.4138, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.8137447834014893, | |
| "eval_runtime": 4.0649, | |
| "eval_samples_per_second": 22.387, | |
| "eval_steps_per_second": 2.952, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.424914164160148e-07, | |
| "loss": 2.1884, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 5.22186406972573e-06, | |
| "loss": 2.2931, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.3499963340427727e-05, | |
| "loss": 2.2962, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 2.5080620706373927e-05, | |
| "loss": 2.4955, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.92697205906826e-05, | |
| "loss": 2.256, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 5.5216803909693624e-05, | |
| "loss": 2.383, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 7.196604245886083e-05, | |
| "loss": 2.2025, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 8.851352885965614e-05, | |
| "loss": 2.5095, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.00010386744825165498, | |
| "loss": 2.2003, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.0001171075251893971, | |
| "loss": 2.2947, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.00012744018264601866, | |
| "loss": 2.2396, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.0001342461070312295, | |
| "loss": 2.5862, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00013711736829567482, | |
| "loss": 2.312, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.801469087600708, | |
| "eval_runtime": 4.0493, | |
| "eval_samples_per_second": 22.473, | |
| "eval_steps_per_second": 2.964, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 0.00013588187023566163, | |
| "loss": 2.1297, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00013061366550826822, | |
| "loss": 2.2352, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.00012162851710068381, | |
| "loss": 1.8696, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00010946497228818094, | |
| "loss": 2.0845, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 9.485208346024522e-05, | |
| "loss": 2.2216, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 7.866571054763782e-05, | |
| "loss": 2.2363, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 6.18760241733922e-05, | |
| "loss": 2.0753, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 4.54893560572937e-05, | |
| "loss": 2.2625, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 3.0487882014855336e-05, | |
| "loss": 2.0837, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.7770752800649797e-05, | |
| "loss": 2.1588, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 8.100201265702867e-06, | |
| "loss": 2.021, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 2.055856030854276e-06, | |
| "loss": 2.1558, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.0356, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.7756218910217285, | |
| "eval_runtime": 4.0379, | |
| "eval_samples_per_second": 22.536, | |
| "eval_steps_per_second": 2.972, | |
| "step": 320 | |
| } | |
| ], | |
| "max_steps": 320, | |
| "num_train_epochs": 5, | |
| "total_flos": 334453800960000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |