| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0437636761487965, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00437636761487965, | |
| "grad_norm": 0.04688813164830208, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3621, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00437636761487965, | |
| "eval_loss": 10.361506462097168, | |
| "eval_runtime": 0.2642, | |
| "eval_samples_per_second": 367.212, | |
| "eval_steps_per_second": 185.499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0087527352297593, | |
| "grad_norm": 0.05414605513215065, | |
| "learning_rate": 4e-05, | |
| "loss": 10.372, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01312910284463895, | |
| "grad_norm": 0.04111277312040329, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3652, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01312910284463895, | |
| "eval_loss": 10.36146354675293, | |
| "eval_runtime": 0.2654, | |
| "eval_samples_per_second": 365.436, | |
| "eval_steps_per_second": 184.602, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0175054704595186, | |
| "grad_norm": 0.04674595221877098, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3633, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02188183807439825, | |
| "grad_norm": 0.04465850070118904, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3515, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0262582056892779, | |
| "grad_norm": 0.05227944254875183, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3638, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0262582056892779, | |
| "eval_loss": 10.361228942871094, | |
| "eval_runtime": 0.2806, | |
| "eval_samples_per_second": 345.638, | |
| "eval_steps_per_second": 174.6, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030634573304157548, | |
| "grad_norm": 0.0490323081612587, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3595, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0350109409190372, | |
| "grad_norm": 0.04133357107639313, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3662, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03938730853391685, | |
| "grad_norm": 0.05223460495471954, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3736, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03938730853391685, | |
| "eval_loss": 10.360846519470215, | |
| "eval_runtime": 0.2677, | |
| "eval_samples_per_second": 362.393, | |
| "eval_steps_per_second": 183.065, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0437636761487965, | |
| "grad_norm": 0.05663596838712692, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3641, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 129309081600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |