| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00414871549385671, | |
| "eval_steps": 10, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031913196106590075, | |
| "eval_loss": 0.6470243334770203, | |
| "eval_runtime": 43.757, | |
| "eval_samples_per_second": 30.167, | |
| "eval_steps_per_second": 15.083, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015956598053295037, | |
| "grad_norm": 0.10389410704374313, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0031913196106590075, | |
| "grad_norm": 0.10804926604032516, | |
| "learning_rate": 0.0001, | |
| "loss": 0.584, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031913196106590075, | |
| "eval_loss": 0.6408673524856567, | |
| "eval_runtime": 43.8281, | |
| "eval_samples_per_second": 30.118, | |
| "eval_steps_per_second": 15.059, | |
| "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": 658664343994368.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |