{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.02485089463220676, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004970178926441351, "eval_loss": NaN, "eval_runtime": 507.4186, "eval_samples_per_second": 26.714, "eval_steps_per_second": 3.34, "step": 1 }, { "epoch": 0.004970178926441352, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.004970178926441352, "eval_loss": NaN, "eval_runtime": 507.0999, "eval_samples_per_second": 26.73, "eval_steps_per_second": 3.343, "step": 10 }, { "epoch": 0.009940357852882704, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.009940357852882704, "eval_loss": NaN, "eval_runtime": 506.9377, "eval_samples_per_second": 26.739, "eval_steps_per_second": 3.344, "step": 20 }, { "epoch": 0.014910536779324055, "grad_norm": NaN, "learning_rate": 3.705904774487396e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.014910536779324055, "eval_loss": NaN, "eval_runtime": 506.652, "eval_samples_per_second": 26.754, "eval_steps_per_second": 3.345, "step": 30 }, { "epoch": 0.019880715705765408, "grad_norm": NaN, "learning_rate": 1.0332332985438248e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.019880715705765408, "eval_loss": NaN, "eval_runtime": 507.1417, "eval_samples_per_second": 26.728, "eval_steps_per_second": 3.342, "step": 40 }, { "epoch": 0.02485089463220676, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.02485089463220676, "eval_loss": NaN, "eval_runtime": 506.5817, "eval_samples_per_second": 26.758, "eval_steps_per_second": 3.346, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.18877213622272e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }