| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07207207207207207, | |
| "eval_steps": 5, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014414414414414415, | |
| "grad_norm": 2.5799503326416016, | |
| "learning_rate": 1e-05, | |
| "loss": 23.6318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014414414414414415, | |
| "eval_loss": NaN, | |
| "eval_runtime": 128.8315, | |
| "eval_samples_per_second": 0.908, | |
| "eval_steps_per_second": 0.458, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02882882882882883, | |
| "grad_norm": 3.7943718433380127, | |
| "learning_rate": 2e-05, | |
| "loss": 26.805, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.043243243243243246, | |
| "grad_norm": 4.626277923583984, | |
| "learning_rate": 3e-05, | |
| "loss": 27.3763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05765765765765766, | |
| "grad_norm": 3.004248857498169, | |
| "learning_rate": 4e-05, | |
| "loss": 23.8077, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "grad_norm": 2.720515727996826, | |
| "learning_rate": 5e-05, | |
| "loss": 24.3285, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.3853, | |
| "eval_samples_per_second": 15.842, | |
| "eval_steps_per_second": 7.989, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6332448610713600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |