| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010767160161507403, | |
| "eval_steps": 4, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026917900403768506, | |
| "grad_norm": 2.0982859134674072, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026917900403768506, | |
| "eval_loss": 0.7193137407302856, | |
| "eval_runtime": 10.1138, | |
| "eval_samples_per_second": 7.811, | |
| "eval_steps_per_second": 7.811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005383580080753701, | |
| "grad_norm": 2.031587839126587, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7275, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008075370121130552, | |
| "grad_norm": 2.1216890811920166, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6912, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010767160161507403, | |
| "grad_norm": 1.755471110343933, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6835, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010767160161507403, | |
| "eval_loss": 0.6272252202033997, | |
| "eval_runtime": 10.0256, | |
| "eval_samples_per_second": 7.88, | |
| "eval_steps_per_second": 7.88, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1576510477565952.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |