| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 1600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 31.25, | |
| "grad_norm": 4.7310919761657715, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 1.633, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "grad_norm": 1.100446105003357, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.1162, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 93.75, | |
| "grad_norm": 0.6620476841926575, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.0385, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 1600, | |
| "total_flos": 1.6588112479488e+16, | |
| "train_loss": 0.5603914216160775, | |
| "train_runtime": 845.3181, | |
| "train_samples_per_second": 148.347, | |
| "train_steps_per_second": 1.893 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6588112479488e+16, | |
| "train_batch_size": 80, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |