| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 121, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 1.1746, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 1.1302, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.9861, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9983081582712684e-05, | |
| "loss": 0.9154, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.9793406217655516e-05, | |
| "loss": 0.8791, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.8825, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.880201391180111e-05, | |
| "loss": 0.8663, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.802123192755044e-05, | |
| "loss": 0.8349, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 0.8493, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.5971585917027864e-05, | |
| "loss": 0.8408, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.4746003697476406e-05, | |
| "loss": 0.8537, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.8231, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.2022175723320382e-05, | |
| "loss": 0.8292, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0581448289104759e-05, | |
| "loss": 0.81, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.128442572523418e-06, | |
| "loss": 0.8043, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.6938412925756e-06, | |
| "loss": 0.8119, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.3079385268731575e-06, | |
| "loss": 0.8052, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.7873, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.797645087317401e-06, | |
| "loss": 0.8023, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.726263584269513e-06, | |
| "loss": 0.8073, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.808479557110081e-06, | |
| "loss": 0.8061, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.0636735967658785e-06, | |
| "loss": 0.7997, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 5.075735642696611e-07, | |
| "loss": 0.7987, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.519224698779198e-07, | |
| "loss": 0.7965, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.230499177994007e-09, | |
| "loss": 0.8183, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 121, | |
| "total_flos": 2375150469120.0, | |
| "train_loss": 0.8479397050605333, | |
| "train_runtime": 621.2868, | |
| "train_samples_per_second": 1.167, | |
| "train_steps_per_second": 0.195 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 121, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 2375150469120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |