| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00017722876245585895, | |
| "eval_steps": 8, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7722876245585897e-05, | |
| "eval_loss": 2.3748350143432617, | |
| "eval_runtime": 1997.5262, | |
| "eval_samples_per_second": 11.894, | |
| "eval_steps_per_second": 5.947, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.316862873675769e-05, | |
| "grad_norm": 0.9981592297554016, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1914, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010633725747351538, | |
| "grad_norm": 1.1429567337036133, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4293, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014178300996468718, | |
| "eval_loss": 1.9845657348632812, | |
| "eval_runtime": 2004.6184, | |
| "eval_samples_per_second": 11.852, | |
| "eval_steps_per_second": 5.926, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015950588621027308, | |
| "grad_norm": 0.9357064366340637, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0415, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3388107349032960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |