| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00031412790241093166, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.490310026788129e-05, | |
| "grad_norm": 0.5575522184371948, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9513, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.490310026788129e-05, | |
| "eval_loss": 6.950506687164307, | |
| "eval_runtime": 29.0808, | |
| "eval_samples_per_second": 414.844, | |
| "eval_steps_per_second": 207.422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.980620053576259e-05, | |
| "grad_norm": 0.46428191661834717, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9515, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010470930080364388, | |
| "grad_norm": 0.6071829199790955, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9461, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010470930080364388, | |
| "eval_loss": 6.949868202209473, | |
| "eval_runtime": 28.4926, | |
| "eval_samples_per_second": 423.409, | |
| "eval_steps_per_second": 211.704, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013961240107152517, | |
| "grad_norm": 0.49404385685920715, | |
| "learning_rate": 8e-05, | |
| "loss": 6.9545, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00017451550133940646, | |
| "grad_norm": 0.48088663816452026, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9399, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020941860160728776, | |
| "grad_norm": 0.5026301145553589, | |
| "learning_rate": 0.00012, | |
| "loss": 6.9608, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020941860160728776, | |
| "eval_loss": 6.946343898773193, | |
| "eval_runtime": 28.6679, | |
| "eval_samples_per_second": 420.819, | |
| "eval_steps_per_second": 210.41, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002443217018751691, | |
| "grad_norm": 0.5813419222831726, | |
| "learning_rate": 0.00014, | |
| "loss": 6.9556, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00027922480214305034, | |
| "grad_norm": 0.6712679266929626, | |
| "learning_rate": 0.00016, | |
| "loss": 6.9495, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00031412790241093166, | |
| "grad_norm": 0.5434843897819519, | |
| "learning_rate": 0.00018, | |
| "loss": 6.9555, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00031412790241093166, | |
| "eval_loss": 6.940571308135986, | |
| "eval_runtime": 28.3785, | |
| "eval_samples_per_second": 425.111, | |
| "eval_steps_per_second": 212.555, | |
| "step": 9 | |
| } | |
| ], | |
| "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": 15160799232.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |