| { | |
| "best_metric": 0.8681809306144714, | |
| "best_model_checkpoint": "./lora-warewe/checkpoint-400", | |
| "epoch": 0.9932490106308683, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.9531, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.8714, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.7052, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.3201, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00015, | |
| "loss": 1.1551, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.1199, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.0598, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.0233, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027, | |
| "loss": 1.0086, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0003, | |
| "loss": 0.999, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002972875226039783, | |
| "loss": 0.9961, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00029457504520795656, | |
| "loss": 0.9831, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002918625678119349, | |
| "loss": 0.9637, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00028915009041591315, | |
| "loss": 0.9546, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002864376130198915, | |
| "loss": 0.9575, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00028372513562386974, | |
| "loss": 0.9337, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00028101265822784807, | |
| "loss": 0.942, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002783001808318264, | |
| "loss": 0.9265, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002755877034358047, | |
| "loss": 0.9324, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.000272875226039783, | |
| "loss": 0.9288, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.9210162162780762, | |
| "eval_runtime": 559.4854, | |
| "eval_samples_per_second": 3.575, | |
| "eval_steps_per_second": 0.447, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00027016274864376125, | |
| "loss": 0.9201, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00026745027124773957, | |
| "loss": 0.9242, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002647377938517179, | |
| "loss": 0.9114, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00026202531645569616, | |
| "loss": 0.9223, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002593128390596745, | |
| "loss": 0.9018, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002566003616636528, | |
| "loss": 0.9038, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002538878842676311, | |
| "loss": 0.9087, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002511754068716094, | |
| "loss": 0.9141, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00024846292947558766, | |
| "loss": 0.8942, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.000245750452079566, | |
| "loss": 0.8865, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00024303797468354428, | |
| "loss": 0.8863, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00024032549728752258, | |
| "loss": 0.8981, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002376130198915009, | |
| "loss": 0.8837, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002349005424954792, | |
| "loss": 0.8887, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002321880650994575, | |
| "loss": 0.8781, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00022947558770343578, | |
| "loss": 0.891, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00022676311030741408, | |
| "loss": 0.8852, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00022405063291139237, | |
| "loss": 0.8736, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002213381555153707, | |
| "loss": 0.8799, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.000218625678119349, | |
| "loss": 0.8847, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.8681809306144714, | |
| "eval_runtime": 405.865, | |
| "eval_samples_per_second": 4.928, | |
| "eval_steps_per_second": 0.616, | |
| "step": 400 | |
| } | |
| ], | |
| "max_steps": 1206, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.0266814048894976e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |