| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007341936576963262, | |
| "eval_steps": 10, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.647643520740971e-05, | |
| "eval_loss": 18.57196617126465, | |
| "eval_runtime": 916.5457, | |
| "eval_samples_per_second": 8.135, | |
| "eval_steps_per_second": 4.067, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028238217603704857, | |
| "grad_norm": 7.614293575286865, | |
| "learning_rate": 5e-05, | |
| "loss": 18.4224, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005647643520740971, | |
| "grad_norm": 17.468368530273438, | |
| "learning_rate": 0.0001, | |
| "loss": 17.7677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005647643520740971, | |
| "eval_loss": 15.393836975097656, | |
| "eval_runtime": 920.5368, | |
| "eval_samples_per_second": 8.1, | |
| "eval_steps_per_second": 4.05, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2404433522589696.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |