| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8888888888888888, | |
| "eval_steps": 500, | |
| "global_step": 14, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018571428571428572, | |
| "loss": 71.7659, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 23.091283798217773, | |
| "learning_rate": 0.00015714285714285716, | |
| "loss": 70.0374, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 34.86846160888672, | |
| "learning_rate": 0.00012857142857142858, | |
| "loss": 63.5778, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.126984126984127, | |
| "grad_norm": 57.71058654785156, | |
| "learning_rate": 0.0001, | |
| "loss": 75.8754, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.380952380952381, | |
| "grad_norm": 32.576454162597656, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 52.6561, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.6349206349206349, | |
| "grad_norm": 18.392147064208984, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 48.4818, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 21.46400260925293, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 49.3458, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "step": 14, | |
| "total_flos": 217126740172968.0, | |
| "train_loss": 61.677159445626394, | |
| "train_runtime": 515.49, | |
| "train_samples_per_second": 0.489, | |
| "train_steps_per_second": 0.027 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 14, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 217126740172968.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |