{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9898856043491103, "eval_steps": 500, "global_step": 15500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03193179368868098, "grad_norm": 0.7292457818984985, "learning_rate": 1.596424010217114e-05, "loss": 0.2137, "step": 500 }, { "epoch": 0.06386358737736196, "grad_norm": 0.5248128175735474, "learning_rate": 3.192848020434228e-05, "loss": 0.1666, "step": 1000 }, { "epoch": 0.09579538106604293, "grad_norm": 0.43739259243011475, "learning_rate": 4.789272030651341e-05, "loss": 0.1602, "step": 1500 }, { "epoch": 0.12772717475472392, "grad_norm": 0.5603083968162537, "learning_rate": 4.846011921657678e-05, "loss": 0.1554, "step": 2000 }, { "epoch": 0.15965896844340488, "grad_norm": 0.43410736322402954, "learning_rate": 4.66860630144763e-05, "loss": 0.1494, "step": 2500 }, { "epoch": 0.19159076213208587, "grad_norm": 0.4648713767528534, "learning_rate": 4.491200681237582e-05, "loss": 0.1477, "step": 3000 }, { "epoch": 0.22352255582076686, "grad_norm": 0.4585404098033905, "learning_rate": 4.3137950610275335e-05, "loss": 0.1425, "step": 3500 }, { "epoch": 0.25545434950944784, "grad_norm": 0.50547856092453, "learning_rate": 4.136389440817485e-05, "loss": 0.1419, "step": 4000 }, { "epoch": 0.2873861431981288, "grad_norm": 0.4558180570602417, "learning_rate": 3.958983820607437e-05, "loss": 0.1416, "step": 4500 }, { "epoch": 0.31931793688680976, "grad_norm": 0.2979300618171692, "learning_rate": 3.781578200397389e-05, "loss": 0.1345, "step": 5000 }, { "epoch": 0.35124973057549075, "grad_norm": 0.4641869366168976, "learning_rate": 3.6041725801873405e-05, "loss": 0.135, "step": 5500 }, { "epoch": 0.38318152426417174, "grad_norm": 0.3632723093032837, "learning_rate": 3.426766959977292e-05, "loss": 0.1336, "step": 6000 }, { "epoch": 0.4151133179528527, "grad_norm": 0.4551422894001007, "learning_rate": 3.249361339767244e-05, "loss": 0.1325, "step": 6500 }, { "epoch": 0.4470451116415337, "grad_norm": 0.3884586989879608, "learning_rate": 3.071955719557196e-05, "loss": 0.1305, "step": 7000 }, { "epoch": 0.47897690533021464, "grad_norm": 0.4581831991672516, "learning_rate": 2.8945500993471475e-05, "loss": 0.128, "step": 7500 }, { "epoch": 0.5109086990188957, "grad_norm": 0.3475557267665863, "learning_rate": 2.7171444791370993e-05, "loss": 0.1265, "step": 8000 }, { "epoch": 0.5428404927075766, "grad_norm": 0.3038561940193176, "learning_rate": 2.539738858927051e-05, "loss": 0.1255, "step": 8500 }, { "epoch": 0.5747722863962575, "grad_norm": 0.35071220993995667, "learning_rate": 2.3623332387170028e-05, "loss": 0.1231, "step": 9000 }, { "epoch": 0.6067040800849386, "grad_norm": 0.5389020442962646, "learning_rate": 2.1849276185069545e-05, "loss": 0.1229, "step": 9500 }, { "epoch": 0.6386358737736195, "grad_norm": 0.3098318874835968, "learning_rate": 2.0075219982969063e-05, "loss": 0.1187, "step": 10000 }, { "epoch": 0.6705676674623006, "grad_norm": 0.3259791433811188, "learning_rate": 1.830116378086858e-05, "loss": 0.1215, "step": 10500 }, { "epoch": 0.7024994611509815, "grad_norm": 0.5782085061073303, "learning_rate": 1.6527107578768098e-05, "loss": 0.1185, "step": 11000 }, { "epoch": 0.7344312548396624, "grad_norm": 0.3013227880001068, "learning_rate": 1.4753051376667615e-05, "loss": 0.119, "step": 11500 }, { "epoch": 0.7663630485283435, "grad_norm": 0.4509045481681824, "learning_rate": 1.297899517456713e-05, "loss": 0.1185, "step": 12000 }, { "epoch": 0.7982948422170244, "grad_norm": 0.4086337089538574, "learning_rate": 1.1204938972466649e-05, "loss": 0.1159, "step": 12500 }, { "epoch": 0.8302266359057054, "grad_norm": 0.29173970222473145, "learning_rate": 9.430882770366166e-06, "loss": 0.1147, "step": 13000 }, { "epoch": 0.8621584295943864, "grad_norm": 0.2581717371940613, "learning_rate": 7.656826568265684e-06, "loss": 0.1124, "step": 13500 }, { "epoch": 0.8940902232830674, "grad_norm": 0.37844014167785645, "learning_rate": 5.8827703661652e-06, "loss": 0.1123, "step": 14000 }, { "epoch": 0.9260220169717484, "grad_norm": 0.35460665822029114, "learning_rate": 4.108714164064718e-06, "loss": 0.1118, "step": 14500 }, { "epoch": 0.9579538106604293, "grad_norm": 0.5382795333862305, "learning_rate": 2.3346579619642353e-06, "loss": 0.1127, "step": 15000 }, { "epoch": 0.9898856043491103, "grad_norm": 0.3714085519313812, "learning_rate": 5.606017598637525e-07, "loss": 0.1099, "step": 15500 } ], "logging_steps": 500, "max_steps": 15658, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.653612317438976e+19, "train_batch_size": 2, "trial_name": null, "trial_params": null }