| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026666666666666666, | |
| "grad_norm": 5.618410110473633, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.3687, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005333333333333333, | |
| "grad_norm": 4.196040153503418, | |
| "learning_rate": 5.0666666666666674e-05, | |
| "loss": 1.0961, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 2.4813344478607178, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.2139, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "step": 75, | |
| "total_flos": 649967869886464.0, | |
| "train_loss": 1.1922254180908203, | |
| "train_runtime": 103.6611, | |
| "train_samples_per_second": 0.724, | |
| "train_steps_per_second": 0.724 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 649967869886464.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |