| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 17910, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.944165270798437e-05, | |
| "loss": 3.7464, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8883305415968732e-05, | |
| "loss": 3.0711, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.83249581239531e-05, | |
| "loss": 2.8204, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.7766610831937466e-05, | |
| "loss": 2.6566, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.720826353992183e-05, | |
| "loss": 2.5476, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.66499162479062e-05, | |
| "loss": 2.4642, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.6091568955890565e-05, | |
| "loss": 2.3983, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.553322166387493e-05, | |
| "loss": 2.3347, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.4974874371859299e-05, | |
| "loss": 2.2982, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.4416527079843662e-05, | |
| "loss": 2.2627, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.385817978782803e-05, | |
| "loss": 2.2366, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.3299832495812398e-05, | |
| "loss": 2.1983, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.2741485203796761e-05, | |
| "loss": 2.1904, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.2183137911781128e-05, | |
| "loss": 2.1333, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.1624790619765495e-05, | |
| "loss": 2.1207, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.106644332774986e-05, | |
| "loss": 2.1035, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.0508096035734227e-05, | |
| "loss": 2.0814, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9788250923156738, | |
| "eval_runtime": 99.7037, | |
| "eval_samples_per_second": 302.537, | |
| "eval_steps_per_second": 4.734, | |
| "step": 8955 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.949748743718594e-06, | |
| "loss": 2.0605, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.39140145170296e-06, | |
| "loss": 2.0316, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 8.833054159687326e-06, | |
| "loss": 2.0237, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 8.274706867671693e-06, | |
| "loss": 2.0168, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 7.716359575656058e-06, | |
| "loss": 1.9817, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 7.158012283640425e-06, | |
| "loss": 1.9987, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.599664991624791e-06, | |
| "loss": 1.9769, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 6.041317699609157e-06, | |
| "loss": 1.9657, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.482970407593524e-06, | |
| "loss": 1.9676, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.92462311557789e-06, | |
| "loss": 1.9505, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.366275823562256e-06, | |
| "loss": 1.9629, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.8079285315466224e-06, | |
| "loss": 1.9709, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.2495812395309884e-06, | |
| "loss": 1.9377, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.691233947515355e-06, | |
| "loss": 1.9388, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.132886655499721e-06, | |
| "loss": 1.9248, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.5745393634840873e-06, | |
| "loss": 1.9169, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.0161920714684535e-06, | |
| "loss": 1.9248, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.5784477945281974e-07, | |
| "loss": 1.9237, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8554816246032715, | |
| "eval_runtime": 89.1269, | |
| "eval_samples_per_second": 338.439, | |
| "eval_steps_per_second": 5.296, | |
| "step": 17910 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 17910, | |
| "total_flos": 3.772502476406784e+16, | |
| "train_loss": 2.197303864837425, | |
| "train_runtime": 7444.9411, | |
| "train_samples_per_second": 153.96, | |
| "train_steps_per_second": 2.406 | |
| } | |
| ], | |
| "max_steps": 17910, | |
| "num_train_epochs": 2, | |
| "total_flos": 3.772502476406784e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |