| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.952286282306163, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-05, | |
| "loss": 9.1779, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 3.894397258758545, | |
| "eval_runtime": 33.2081, | |
| "eval_samples_per_second": 11.774, | |
| "eval_steps_per_second": 1.686, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9391, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.7052955627441406, | |
| "eval_runtime": 33.2014, | |
| "eval_samples_per_second": 11.777, | |
| "eval_steps_per_second": 1.687, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4896, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.597261667251587, | |
| "eval_runtime": 33.2105, | |
| "eval_samples_per_second": 11.773, | |
| "eval_steps_per_second": 1.686, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4279, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.559727668762207, | |
| "eval_runtime": 33.1972, | |
| "eval_samples_per_second": 11.778, | |
| "eval_steps_per_second": 1.687, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3676, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.5377521514892578, | |
| "eval_runtime": 33.1973, | |
| "eval_samples_per_second": 11.778, | |
| "eval_steps_per_second": 1.687, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.965729952021933e-05, | |
| "loss": 1.3666, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.5202970504760742, | |
| "eval_runtime": 33.2, | |
| "eval_samples_per_second": 11.777, | |
| "eval_steps_per_second": 1.687, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.9314599040438655e-05, | |
| "loss": 1.3432, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 1.5091770887374878, | |
| "eval_runtime": 33.2069, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.8971898560657985e-05, | |
| "loss": 1.3226, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.5007234811782837, | |
| "eval_runtime": 33.2119, | |
| "eval_samples_per_second": 11.773, | |
| "eval_steps_per_second": 1.686, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.8629198080877314e-05, | |
| "loss": 1.3145, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 1.4917149543762207, | |
| "eval_runtime": 33.2096, | |
| "eval_samples_per_second": 11.774, | |
| "eval_steps_per_second": 1.686, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 4.8286497601096644e-05, | |
| "loss": 1.2897, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.487337350845337, | |
| "eval_runtime": 33.2063, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 4.794379712131597e-05, | |
| "loss": 1.2956, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 1.481351613998413, | |
| "eval_runtime": 33.2118, | |
| "eval_samples_per_second": 11.773, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.76010966415353e-05, | |
| "loss": 1.2791, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 1.4768741130828857, | |
| "eval_runtime": 33.2069, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.725839616175463e-05, | |
| "loss": 1.2679, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 1.4751813411712646, | |
| "eval_runtime": 33.1963, | |
| "eval_samples_per_second": 11.778, | |
| "eval_steps_per_second": 1.687, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.6915695681973956e-05, | |
| "loss": 1.2583, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 1.4700709581375122, | |
| "eval_runtime": 33.2157, | |
| "eval_samples_per_second": 11.772, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.6572995202193286e-05, | |
| "loss": 1.2813, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 1.4654401540756226, | |
| "eval_runtime": 33.205, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.6230294722412615e-05, | |
| "loss": 1.25, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 1.4636775255203247, | |
| "eval_runtime": 33.207, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.5887594242631945e-05, | |
| "loss": 1.2393, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 1.4608376026153564, | |
| "eval_runtime": 33.2094, | |
| "eval_samples_per_second": 11.774, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 4.554489376285127e-05, | |
| "loss": 1.2599, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "eval_loss": 1.4582923650741577, | |
| "eval_runtime": 33.2003, | |
| "eval_samples_per_second": 11.777, | |
| "eval_steps_per_second": 1.687, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 4.52021932830706e-05, | |
| "loss": 1.2336, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "eval_loss": 1.455262303352356, | |
| "eval_runtime": 33.2047, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.687, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 4.485949280328993e-05, | |
| "loss": 1.2374, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "eval_loss": 1.4536148309707642, | |
| "eval_runtime": 33.2036, | |
| "eval_samples_per_second": 11.776, | |
| "eval_steps_per_second": 1.687, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 4.451679232350926e-05, | |
| "loss": 1.2171, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "eval_loss": 1.4514210224151611, | |
| "eval_runtime": 33.2199, | |
| "eval_samples_per_second": 11.77, | |
| "eval_steps_per_second": 1.686, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 4.417409184372858e-05, | |
| "loss": 1.2154, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_loss": 1.450243592262268, | |
| "eval_runtime": 33.2384, | |
| "eval_samples_per_second": 11.763, | |
| "eval_steps_per_second": 1.685, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.383139136394791e-05, | |
| "loss": 1.2247, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_loss": 1.4490052461624146, | |
| "eval_runtime": 33.2063, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 4.348869088416724e-05, | |
| "loss": 1.2234, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "eval_loss": 1.4472484588623047, | |
| "eval_runtime": 33.2181, | |
| "eval_samples_per_second": 11.771, | |
| "eval_steps_per_second": 1.686, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 4.314599040438657e-05, | |
| "loss": 1.2152, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_loss": 1.4455540180206299, | |
| "eval_runtime": 33.205, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 4.280328992460589e-05, | |
| "loss": 1.1883, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_loss": 1.4456433057785034, | |
| "eval_runtime": 33.2111, | |
| "eval_samples_per_second": 11.773, | |
| "eval_steps_per_second": 1.686, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 4.246058944482523e-05, | |
| "loss": 1.1947, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "eval_loss": 1.4448508024215698, | |
| "eval_runtime": 33.1978, | |
| "eval_samples_per_second": 11.778, | |
| "eval_steps_per_second": 1.687, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 4.211788896504456e-05, | |
| "loss": 1.2127, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_loss": 1.4433377981185913, | |
| "eval_runtime": 33.2104, | |
| "eval_samples_per_second": 11.773, | |
| "eval_steps_per_second": 1.686, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 4.177518848526388e-05, | |
| "loss": 1.1959, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_loss": 1.4412949085235596, | |
| "eval_runtime": 33.2197, | |
| "eval_samples_per_second": 11.77, | |
| "eval_steps_per_second": 1.686, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 4.143248800548321e-05, | |
| "loss": 1.1913, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_loss": 1.4401354789733887, | |
| "eval_runtime": 33.21, | |
| "eval_samples_per_second": 11.774, | |
| "eval_steps_per_second": 1.686, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 4.108978752570254e-05, | |
| "loss": 1.1966, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "eval_loss": 1.4406956434249878, | |
| "eval_runtime": 33.2007, | |
| "eval_samples_per_second": 11.777, | |
| "eval_steps_per_second": 1.687, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 4.0747087045921863e-05, | |
| "loss": 1.1798, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "eval_loss": 1.4382696151733398, | |
| "eval_runtime": 33.2065, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 4.040438656614119e-05, | |
| "loss": 1.1736, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 1.4385173320770264, | |
| "eval_runtime": 33.2237, | |
| "eval_samples_per_second": 11.769, | |
| "eval_steps_per_second": 1.686, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 4.006168608636052e-05, | |
| "loss": 1.1661, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "eval_loss": 1.4370990991592407, | |
| "eval_runtime": 33.2081, | |
| "eval_samples_per_second": 11.774, | |
| "eval_steps_per_second": 1.686, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 3.971898560657985e-05, | |
| "loss": 1.1802, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_loss": 1.4352325201034546, | |
| "eval_runtime": 33.2067, | |
| "eval_samples_per_second": 11.775, | |
| "eval_steps_per_second": 1.686, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 3.9376285126799175e-05, | |
| "loss": 1.1649, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "eval_loss": 1.436591386795044, | |
| "eval_runtime": 33.2379, | |
| "eval_samples_per_second": 11.764, | |
| "eval_steps_per_second": 1.685, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 3.9033584647018505e-05, | |
| "loss": 1.1654, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "eval_loss": 1.4353548288345337, | |
| "eval_runtime": 33.2162, | |
| "eval_samples_per_second": 11.771, | |
| "eval_steps_per_second": 1.686, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 3.8690884167237835e-05, | |
| "loss": 1.1604, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "eval_loss": 1.4346917867660522, | |
| "eval_runtime": 33.2322, | |
| "eval_samples_per_second": 11.766, | |
| "eval_steps_per_second": 1.685, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 3.8348183687457165e-05, | |
| "loss": 1.1555, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "eval_loss": 1.4331263303756714, | |
| "eval_runtime": 33.2124, | |
| "eval_samples_per_second": 11.773, | |
| "eval_steps_per_second": 1.686, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 3.800548320767649e-05, | |
| "loss": 1.1617, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_loss": 1.4325422048568726, | |
| "eval_runtime": 33.2006, | |
| "eval_samples_per_second": 11.777, | |
| "eval_steps_per_second": 1.687, | |
| "step": 4000 | |
| } | |
| ], | |
| "max_steps": 15090, | |
| "num_train_epochs": 30, | |
| "total_flos": 8.075550264813158e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |