| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009588493807431082, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031961646024770275, | |
| "grad_norm": 1.6692992448806763, | |
| "learning_rate": 1e-05, | |
| "loss": 5.2274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031961646024770275, | |
| "eval_loss": 6.05078125, | |
| "eval_runtime": 100.6272, | |
| "eval_samples_per_second": 5.237, | |
| "eval_steps_per_second": 2.624, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006392329204954055, | |
| "grad_norm": 1.1485488414764404, | |
| "learning_rate": 2e-05, | |
| "loss": 5.9317, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009588493807431082, | |
| "grad_norm": 0.9786986708641052, | |
| "learning_rate": 3e-05, | |
| "loss": 5.7836, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009588493807431082, | |
| "eval_loss": 5.9795355796813965, | |
| "eval_runtime": 11.5612, | |
| "eval_samples_per_second": 45.583, | |
| "eval_steps_per_second": 22.835, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2091163255308288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |