| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02336448598130841, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002336448598130841, | |
| "grad_norm": 1.4442662177316379e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002336448598130841, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.0049, | |
| "eval_samples_per_second": 180.121, | |
| "eval_steps_per_second": 90.558, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004672897196261682, | |
| "grad_norm": 1.1143864867335651e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007009345794392523, | |
| "grad_norm": 2.338065860385541e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007009345794392523, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.0091, | |
| "eval_samples_per_second": 179.367, | |
| "eval_steps_per_second": 90.179, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 2.0676250642281957e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011682242990654205, | |
| "grad_norm": 2.9906777854193933e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014018691588785047, | |
| "grad_norm": 1.0526019650569651e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014018691588785047, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.1316, | |
| "eval_samples_per_second": 159.949, | |
| "eval_steps_per_second": 80.416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016355140186915886, | |
| "grad_norm": 1.5138394701352809e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 2.2455924408859573e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02102803738317757, | |
| "grad_norm": 2.8332990041235462e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02102803738317757, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.0298, | |
| "eval_samples_per_second": 175.767, | |
| "eval_steps_per_second": 88.369, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02336448598130841, | |
| "grad_norm": 1.8658038243302144e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 199228784640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |