| { | |
| "best_metric": 3.0450499057769775, | |
| "best_model_checkpoint": "output/metallica/checkpoint-315", | |
| "epoch": 5.0, | |
| "global_step": 315, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00013507870183531476, | |
| "loss": 3.3881, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012884599993319768, | |
| "loss": 3.3444, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011888735840752609, | |
| "loss": 3.3036, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001058186737011911, | |
| "loss": 3.3353, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.044818420726556e-05, | |
| "loss": 3.2497, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.372648442002871e-05, | |
| "loss": 3.2277, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.668773501204858e-05, | |
| "loss": 3.0355, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.0385704725240065e-05, | |
| "loss": 2.898, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.5828599592490882e-05, | |
| "loss": 2.9592, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3916710004507539e-05, | |
| "loss": 2.9574, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.38673186569003e-06, | |
| "loss": 2.9963, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.662053209561833e-07, | |
| "loss": 2.9366, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.13543438911438, | |
| "eval_runtime": 3.4469, | |
| "eval_samples_per_second": 47.289, | |
| "eval_steps_per_second": 6.092, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.408888099334633e-07, | |
| "loss": 2.948, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.137086214086682e-06, | |
| "loss": 2.811, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.1920020081922749e-05, | |
| "loss": 2.9051, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.320835154085542e-05, | |
| "loss": 2.813, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.7303948905573005e-05, | |
| "loss": 2.6726, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.333506393059682e-05, | |
| "loss": 2.817, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.031024545323179e-05, | |
| "loss": 2.8553, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 8.71796561146101e-05, | |
| "loss": 2.7581, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 2.8057, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0001164990457207046, | |
| "loss": 2.7321, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00012713575447996587, | |
| "loss": 2.67, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00013415229447692924, | |
| "loss": 2.7242, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00013711472479561806, | |
| "loss": 2.7872, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.1001694202423096, | |
| "eval_runtime": 3.559, | |
| "eval_samples_per_second": 45.8, | |
| "eval_steps_per_second": 5.901, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00013583983266641012, | |
| "loss": 2.5963, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00013040646433810595, | |
| "loss": 2.4975, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0001211506487979619, | |
| "loss": 2.5517, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00010864481591530664, | |
| "loss": 2.454, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 9.36623942715347e-05, | |
| "loss": 2.4655, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.712997813881747e-05, | |
| "loss": 2.5144, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 6.007002186118257e-05, | |
| "loss": 2.4411, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.3537605728465284e-05, | |
| "loss": 2.49, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.8555184084693446e-05, | |
| "loss": 2.2522, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.6049351202038163e-05, | |
| "loss": 2.4637, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 6.793535661894062e-06, | |
| "loss": 2.4223, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.3601673335899086e-06, | |
| "loss": 2.255, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 3.0634868144989014, | |
| "eval_runtime": 3.6817, | |
| "eval_samples_per_second": 44.273, | |
| "eval_steps_per_second": 5.704, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 8.527520438192717e-08, | |
| "loss": 2.3823, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.047705523070765e-06, | |
| "loss": 2.3682, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.0064245520034058e-05, | |
| "loss": 2.3272, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 2.0700954279295363e-05, | |
| "loss": 2.2495, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.4300000000000014e-05, | |
| "loss": 2.0865, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 5.0020343885389815e-05, | |
| "loss": 2.279, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 6.688975454676822e-05, | |
| "loss": 2.1852, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 8.386493606940314e-05, | |
| "loss": 2.2131, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 9.989605109442691e-05, | |
| "loss": 2.2336, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.00011399164845914455, | |
| "loss": 2.2808, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00012527997991807721, | |
| "loss": 2.4415, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.00013306291378591332, | |
| "loss": 2.1738, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 0.00013685911119006654, | |
| "loss": 2.3683, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3.110128879547119, | |
| "eval_runtime": 3.7075, | |
| "eval_samples_per_second": 43.965, | |
| "eval_steps_per_second": 5.664, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00013643379467904383, | |
| "loss": 2.0957, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.00013181326813430994, | |
| "loss": 2.1122, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00012328328999549248, | |
| "loss": 2.0913, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00011137140040750914, | |
| "loss": 2.0899, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 9.681429527476003e-05, | |
| "loss": 2.0885, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 8.051226498795145e-05, | |
| "loss": 2.054, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 6.347351557997137e-05, | |
| "loss": 2.0165, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.675181579273458e-05, | |
| "loss": 1.945, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 3.138132629880886e-05, | |
| "loss": 1.9216, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 1.8312641592473912e-05, | |
| "loss": 1.9411, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 8.354000066802353e-06, | |
| "loss": 1.7585, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 2.121298164685252e-06, | |
| "loss": 1.947, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.9567, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 3.0450499057769775, | |
| "eval_runtime": 3.7841, | |
| "eval_samples_per_second": 43.076, | |
| "eval_steps_per_second": 5.55, | |
| "step": 315 | |
| } | |
| ], | |
| "max_steps": 315, | |
| "num_train_epochs": 5, | |
| "total_flos": 327268270080000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |