{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.013350020859407593, "eval_steps": 2, "global_step": 4, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003337505214851898, "grad_norm": 4.640351295471191, "learning_rate": 1e-05, "loss": 9.3435, "step": 1 }, { "epoch": 0.003337505214851898, "eval_loss": 10.924598693847656, "eval_runtime": 54.096, "eval_samples_per_second": 9.335, "eval_steps_per_second": 4.677, "step": 1 }, { "epoch": 0.006675010429703796, "grad_norm": 5.415709972381592, "learning_rate": 2e-05, "loss": 10.9627, "step": 2 }, { "epoch": 0.006675010429703796, "eval_loss": 10.874074935913086, "eval_runtime": 8.5937, "eval_samples_per_second": 58.764, "eval_steps_per_second": 29.44, "step": 2 }, { "epoch": 0.010012515644555695, "grad_norm": 6.440147399902344, "learning_rate": 3e-05, "loss": 11.64, "step": 3 }, { "epoch": 0.013350020859407593, "grad_norm": 4.595988750457764, "learning_rate": 4e-05, "loss": 10.4073, "step": 4 }, { "epoch": 0.013350020859407593, "eval_loss": 10.809618949890137, "eval_runtime": 8.6431, "eval_samples_per_second": 58.428, "eval_steps_per_second": 29.272, "step": 4 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 54868240760832.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }