| { | |
| "best_metric": 1.5137468576431274, | |
| "best_model_checkpoint": "output/platina/checkpoint-348", | |
| "epoch": 4.0, | |
| "global_step": 348, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.1151037062646087e-06, | |
| "loss": 1.8191, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.424162455503776e-06, | |
| "loss": 1.778, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.819597714903368e-06, | |
| "loss": 1.7677, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.7126002200070792e-05, | |
| "loss": 1.8796, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.610584242060141e-05, | |
| "loss": 1.8322, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.646718096799441e-05, | |
| "loss": 1.7206, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.787316749192729e-05, | |
| "loss": 1.7349, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.995298981028814e-05, | |
| "loss": 1.7768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.231392912895959e-05, | |
| "loss": 1.7442, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.455412745239765e-05, | |
| "loss": 1.7635, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.627565211250085e-05, | |
| "loss": 1.7607, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00010709743268385943, | |
| "loss": 1.8494, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001166676497022313, | |
| "loss": 1.7513, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00012467517242513996, | |
| "loss": 1.6916, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00013085967378942764, | |
| "loss": 1.8089, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00013502009372533583, | |
| "loss": 1.7891, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00013702117568213136, | |
| "loss": 1.8074, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.717990517616272, | |
| "eval_runtime": 5.9537, | |
| "eval_samples_per_second": 22.003, | |
| "eval_steps_per_second": 2.855, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00013679786386078908, | |
| "loss": 1.6816, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00013435741819832448, | |
| "loss": 1.6466, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00012977917834497524, | |
| "loss": 1.7089, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012321198430740717, | |
| "loss": 1.6398, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011486933761363929, | |
| "loss": 1.5449, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00010502246031172626, | |
| "loss": 1.6906, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.399147745631814e-05, | |
| "loss": 1.5677, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.213500974321104e-05, | |
| "loss": 1.6043, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 6.983851463858842e-05, | |
| "loss": 1.658, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 5.750175503648031e-05, | |
| "loss": 1.6382, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.5525802842298056e-05, | |
| "loss": 1.5709, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.4300000000000054e-05, | |
| "loss": 1.6331, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.418930086396666e-05, | |
| "loss": 1.5709, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.552240741902345e-05, | |
| "loss": 1.5756, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.581083076314943e-06, | |
| "loss": 1.6289, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.5909924568597513e-06, | |
| "loss": 1.5374, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.143649642832784e-07, | |
| "loss": 1.5678, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.5926672220230103, | |
| "eval_runtime": 5.7532, | |
| "eval_samples_per_second": 22.77, | |
| "eval_steps_per_second": 2.955, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.4720656268161284e-08, | |
| "loss": 1.6048, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.603829878288063e-06, | |
| "loss": 1.4474, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.341005502881008e-06, | |
| "loss": 1.5889, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.1134750783984455e-05, | |
| "loss": 1.4795, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.87967092540732e-05, | |
| "loss": 1.5209, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.8077788251711776e-05, | |
| "loss": 1.6414, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 3.8676257001728066e-05, | |
| "loss": 1.5243, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.0247555976895465e-05, | |
| "loss": 1.5045, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 6.241549863571236e-05, | |
| "loss": 1.4689, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.47845013642876e-05, | |
| "loss": 1.5789, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 8.695244402310448e-05, | |
| "loss": 1.5342, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.852374299827188e-05, | |
| "loss": 1.4686, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00010912221174828818, | |
| "loss": 1.5636, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00011840329074592676, | |
| "loss": 1.5472, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.00012606524921601552, | |
| "loss": 1.5416, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.00013185899449711896, | |
| "loss": 1.5624, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.00013559617012171192, | |
| "loss": 1.5904, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00013715527934373185, | |
| "loss": 1.5604, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.5875556468963623, | |
| "eval_runtime": 5.7815, | |
| "eval_samples_per_second": 22.659, | |
| "eval_steps_per_second": 2.94, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0001364856350357167, | |
| "loss": 1.5918, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0001336090075431402, | |
| "loss": 1.4197, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00012861891692368514, | |
| "loss": 1.5324, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00012167759258097666, | |
| "loss": 1.4255, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.00011301069913603348, | |
| "loss": 1.5272, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00010290000000000009, | |
| "loss": 1.52, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 9.167419715770211e-05, | |
| "loss": 1.4541, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 7.969824496351975e-05, | |
| "loss": 1.4829, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 6.736148536141163e-05, | |
| "loss": 1.4054, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 5.506499025678901e-05, | |
| "loss": 1.4169, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 4.320852254368191e-05, | |
| "loss": 1.4294, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 3.217753968827379e-05, | |
| "loss": 1.4879, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 2.2330662386360752e-05, | |
| "loss": 1.4319, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.3988015692592839e-05, | |
| "loss": 1.4294, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.420821655024771e-06, | |
| "loss": 1.4842, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 2.8425818016755186e-06, | |
| "loss": 1.3857, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 4.02136139210924e-07, | |
| "loss": 1.3751, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.5137468576431274, | |
| "eval_runtime": 5.7841, | |
| "eval_samples_per_second": 22.648, | |
| "eval_steps_per_second": 2.939, | |
| "step": 348 | |
| } | |
| ], | |
| "max_steps": 348, | |
| "num_train_epochs": 4, | |
| "total_flos": 362150756352000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |