{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0005479939994657058, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00010959879989314117, "grad_norm": 0.009306421503424644, "learning_rate": 1e-05, "loss": 11.9327, "step": 1 }, { "epoch": 0.00010959879989314117, "eval_loss": 11.932991981506348, "eval_runtime": 82.9958, "eval_samples_per_second": 185.166, "eval_steps_per_second": 92.583, "step": 1 }, { "epoch": 0.00021919759978628235, "grad_norm": 0.0105437021702528, "learning_rate": 2e-05, "loss": 11.9337, "step": 2 }, { "epoch": 0.00021919759978628235, "eval_loss": 11.932991027832031, "eval_runtime": 62.2429, "eval_samples_per_second": 246.904, "eval_steps_per_second": 123.452, "step": 2 }, { "epoch": 0.0003287963996794235, "grad_norm": 0.010121379047632217, "learning_rate": 3e-05, "loss": 11.9328, "step": 3 }, { "epoch": 0.0004383951995725647, "grad_norm": 0.009038162417709827, "learning_rate": 4e-05, "loss": 11.9328, "step": 4 }, { "epoch": 0.0004383951995725647, "eval_loss": 11.93298053741455, "eval_runtime": 69.3256, "eval_samples_per_second": 221.679, "eval_steps_per_second": 110.839, "step": 4 }, { "epoch": 0.0005479939994657058, "grad_norm": 0.010185400024056435, "learning_rate": 5e-05, "loss": 11.9328, "step": 5 } ], "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": true }, "attributes": {} } }, "total_flos": 2392768512.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }