| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9971803864933636, | |
| "eval_steps": 500, | |
| "global_step": 14500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.828072347156317e-05, | |
| "loss": 1.3416, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.656144694312634e-05, | |
| "loss": 1.1277, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.4842170414689496e-05, | |
| "loss": 1.0744, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.312289388625267e-05, | |
| "loss": 1.034, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.140361735781583e-05, | |
| "loss": 1.013, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9684340829379003e-05, | |
| "loss": 0.9948, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.796506430094217e-05, | |
| "loss": 0.9951, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.624578777250533e-05, | |
| "loss": 0.9735, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.45265112440685e-05, | |
| "loss": 0.9796, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.280723471563166e-05, | |
| "loss": 0.9688, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.108795818719483e-05, | |
| "loss": 0.9511, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9368681658757994e-05, | |
| "loss": 0.9531, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.764940513032116e-05, | |
| "loss": 0.9337, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.593012860188433e-05, | |
| "loss": 0.9208, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4210852073447495e-05, | |
| "loss": 0.9241, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.249157554501066e-05, | |
| "loss": 0.9049, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.0772299016573828e-05, | |
| "loss": 0.9192, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9053022488136992e-05, | |
| "loss": 0.9219, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.733374595970016e-05, | |
| "loss": 0.9034, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5614469431263325e-05, | |
| "loss": 0.9074, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.3895192902826493e-05, | |
| "loss": 0.9088, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2175916374389657e-05, | |
| "loss": 0.9119, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0456639845952824e-05, | |
| "loss": 0.8996, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.73736331751599e-06, | |
| "loss": 0.8881, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.018086789079156e-06, | |
| "loss": 0.9013, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.298810260642322e-06, | |
| "loss": 0.8916, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.5795337322054882e-06, | |
| "loss": 0.8953, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.8602572037686543e-06, | |
| "loss": 0.8992, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.4098067533182036e-07, | |
| "loss": 0.8785, | |
| "step": 14500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 14541, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 3788734464000000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |