| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001493521848980049, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.97840616326683e-05, | |
| "grad_norm": 8.102911949157715, | |
| "learning_rate": 2e-05, | |
| "loss": 13.1234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.97840616326683e-05, | |
| "eval_loss": 3.1932132244110107, | |
| "eval_runtime": 103.3636, | |
| "eval_samples_per_second": 81.828, | |
| "eval_steps_per_second": 40.914, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.95681232653366e-05, | |
| "grad_norm": 13.588043212890625, | |
| "learning_rate": 4e-05, | |
| "loss": 13.195, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001493521848980049, | |
| "grad_norm": 16.6812686920166, | |
| "learning_rate": 6e-05, | |
| "loss": 13.3648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001493521848980049, | |
| "eval_loss": 3.1755757331848145, | |
| "eval_runtime": 103.8399, | |
| "eval_samples_per_second": 81.452, | |
| "eval_steps_per_second": 40.726, | |
| "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": 26274378547200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |