| { | |
| "best_metric": 1.3656095266342163, | |
| "best_model_checkpoint": "output/bring-me-the-horizon/checkpoint-216", | |
| "epoch": 8.0, | |
| "global_step": 216, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012505669320030482, | |
| "loss": 2.9107, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.292589525111794e-05, | |
| "loss": 2.6407, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.218294542987356e-05, | |
| "loss": 2.5181, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.725216267546246e-05, | |
| "loss": 2.4529, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.001712368734975e-07, | |
| "loss": 2.466, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.72078013420105, | |
| "eval_runtime": 0.543, | |
| "eval_samples_per_second": 75.509, | |
| "eval_steps_per_second": 11.05, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.857716640189785e-06, | |
| "loss": 2.5427, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.671999039779749e-05, | |
| "loss": 2.3173, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.686881626551516e-05, | |
| "loss": 2.2888, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00011409021435531856, | |
| "loss": 2.3614, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00013520660867542716, | |
| "loss": 2.1993, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.672280788421631, | |
| "eval_runtime": 0.5476, | |
| "eval_samples_per_second": 74.866, | |
| "eval_steps_per_second": 10.956, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00013274211424821946, | |
| "loss": 2.2735, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00010756924162575734, | |
| "loss": 2.1555, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.860000000000001e-05, | |
| "loss": 2.1802, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.9630758374242683e-05, | |
| "loss": 1.978, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.457885751780558e-06, | |
| "loss": 2.4223, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.926320195198059, | |
| "eval_runtime": 0.4807, | |
| "eval_samples_per_second": 74.883, | |
| "eval_steps_per_second": 10.4, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.9933913245728396e-06, | |
| "loss": 2.1228, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 2.310978564468141e-05, | |
| "loss": 1.9814, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 6.033118373448485e-05, | |
| "loss": 2.1607, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.00010048000960220248, | |
| "loss": 2.1746, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.00012934228335981018, | |
| "loss": 1.8565, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.8828926086425781, | |
| "eval_runtime": 0.4815, | |
| "eval_samples_per_second": 74.766, | |
| "eval_steps_per_second": 10.384, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.0001366998287631265, | |
| "loss": 2.1214, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00011994783732453755, | |
| "loss": 1.898, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 8.501705457012643e-05, | |
| "loss": 1.8994, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.42741047488822e-05, | |
| "loss": 1.9389, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 1.2143306799695228e-05, | |
| "loss": 1.7737, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.7275, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.8320238590240479, | |
| "eval_runtime": 0.4801, | |
| "eval_samples_per_second": 74.982, | |
| "eval_steps_per_second": 10.414, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 1.2143306799695106e-05, | |
| "loss": 1.6759, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 4.4274104748882125e-05, | |
| "loss": 1.934, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 8.501705457012647e-05, | |
| "loss": 1.7796, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 0.00011994783732453749, | |
| "loss": 1.5568, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 0.00013669982876312649, | |
| "loss": 1.7681, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.8055299520492554, | |
| "eval_runtime": 0.4812, | |
| "eval_samples_per_second": 74.816, | |
| "eval_steps_per_second": 10.391, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.00012934228335981018, | |
| "loss": 1.5298, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.00010048000960220254, | |
| "loss": 1.5527, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 6.033118373448493e-05, | |
| "loss": 1.6001, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 2.3109785644681573e-05, | |
| "loss": 1.5066, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.9933913245728244e-06, | |
| "loss": 1.5358, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.7874510288238525, | |
| "eval_runtime": 0.4807, | |
| "eval_samples_per_second": 74.894, | |
| "eval_steps_per_second": 10.402, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 4.457885751780527e-06, | |
| "loss": 1.45, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 2.963075837424261e-05, | |
| "loss": 1.4034, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 6.859999999999982e-05, | |
| "loss": 1.3896, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.00010756924162575728, | |
| "loss": 1.3993, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 0.00013274211424821943, | |
| "loss": 1.4986, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.761746883392334, | |
| "eval_runtime": 0.4842, | |
| "eval_samples_per_second": 74.353, | |
| "eval_steps_per_second": 10.327, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 0.00012115064879796188, | |
| "loss": 1.688, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.00013673615134109727, | |
| "loss": 1.5172, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.3656095266342163, | |
| "eval_runtime": 0.4451, | |
| "eval_samples_per_second": 74.143, | |
| "eval_steps_per_second": 11.234, | |
| "step": 216 | |
| } | |
| ], | |
| "max_steps": 2916, | |
| "num_train_epochs": 108, | |
| "total_flos": 222490165248000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |