{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.000884016973125884, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 8.84016973125884e-05, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 8.84016973125884e-05, "eval_loss": NaN, "eval_runtime": 158.7809, "eval_samples_per_second": 29.997, "eval_steps_per_second": 15.002, "step": 1 }, { "epoch": 0.0001768033946251768, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0002652050919377652, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0002652050919377652, "eval_loss": NaN, "eval_runtime": 146.8825, "eval_samples_per_second": 32.427, "eval_steps_per_second": 16.217, "step": 3 }, { "epoch": 0.0003536067892503536, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.000442008486562942, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0005304101838755304, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0005304101838755304, "eval_loss": NaN, "eval_runtime": 146.9678, "eval_samples_per_second": 32.408, "eval_steps_per_second": 16.208, "step": 6 }, { "epoch": 0.0006188118811881188, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0007072135785007072, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0007956152758132957, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0007956152758132957, "eval_loss": NaN, "eval_runtime": 146.8513, "eval_samples_per_second": 32.434, "eval_steps_per_second": 16.22, "step": 9 }, { "epoch": 0.000884016973125884, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "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": 1849564248145920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }