| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 22, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 1.260422945022583, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 7.1496, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.48790422081947327, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 7.1673, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.7496576905250549, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 7.114, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.8951925039291382, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 7.0869, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.6558501720428467, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 7.0352, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 0.7042173743247986, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 7.0699, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 0.6520460247993469, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 7.104, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.3574787676334381, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 6.9986, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 0.38745859265327454, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 7.0597, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 0.3738166093826294, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 7.1351, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.8463465571403503, | |
| "learning_rate": 0.0, | |
| "loss": 7.018, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 22, | |
| "total_flos": 76810131809976.0, | |
| "train_loss": 7.085298581556841, | |
| "train_runtime": 567.2339, | |
| "train_samples_per_second": 0.621, | |
| "train_steps_per_second": 0.039 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 22, | |
| "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": 76810131809976.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |