{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0013530197710014038, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.765098855007019e-05, "eval_loss": 10.389067649841309, "eval_runtime": 19.6431, "eval_samples_per_second": 316.854, "eval_steps_per_second": 158.427, "step": 1 }, { "epoch": 0.00020295296565021057, "grad_norm": 0.04908648505806923, "learning_rate": 6e-05, "loss": 10.3899, "step": 3 }, { "epoch": 0.00040590593130042114, "grad_norm": 0.04139264300465584, "learning_rate": 0.00012, "loss": 10.3883, "step": 6 }, { "epoch": 0.0005412079084005615, "eval_loss": 10.388261795043945, "eval_runtime": 19.5117, "eval_samples_per_second": 318.988, "eval_steps_per_second": 159.494, "step": 8 }, { "epoch": 0.0006088588969506317, "grad_norm": 0.04659366235136986, "learning_rate": 0.00018, "loss": 10.388, "step": 9 }, { "epoch": 0.0008118118626008423, "grad_norm": 0.03790257126092911, "learning_rate": 0.00019510565162951537, "loss": 10.3883, "step": 12 }, { "epoch": 0.0010147648282510528, "grad_norm": 0.05327346920967102, "learning_rate": 0.00017071067811865476, "loss": 10.3855, "step": 15 }, { "epoch": 0.001082415816801123, "eval_loss": 10.3860445022583, "eval_runtime": 19.5451, "eval_samples_per_second": 318.444, "eval_steps_per_second": 159.222, "step": 16 }, { "epoch": 0.0012177177939012634, "grad_norm": 0.04953443259000778, "learning_rate": 0.00013090169943749476, "loss": 10.3828, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 523024465920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }