{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0003188318002837603, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.5941590014188015e-05, "eval_loss": 1.6990032196044922, "eval_runtime": 5081.1835, "eval_samples_per_second": 5.198, "eval_steps_per_second": 2.599, "step": 1 }, { "epoch": 4.7824770042564044e-05, "grad_norm": 0.6024008393287659, "learning_rate": 3e-05, "loss": 7.4336, "step": 3 }, { "epoch": 9.564954008512809e-05, "grad_norm": 0.5880036354064941, "learning_rate": 6e-05, "loss": 6.6894, "step": 6 }, { "epoch": 0.00012753272011350412, "eval_loss": 1.6758214235305786, "eval_runtime": 5106.4017, "eval_samples_per_second": 5.173, "eval_steps_per_second": 2.586, "step": 8 }, { "epoch": 0.00014347431012769212, "grad_norm": 0.6464680433273315, "learning_rate": 9e-05, "loss": 7.0782, "step": 9 }, { "epoch": 0.00019129908017025618, "grad_norm": 0.8096962571144104, "learning_rate": 9.755282581475769e-05, "loss": 6.3456, "step": 12 }, { "epoch": 0.00023912385021282023, "grad_norm": 0.9577824473381042, "learning_rate": 8.535533905932738e-05, "loss": 5.6146, "step": 15 }, { "epoch": 0.00025506544022700823, "eval_loss": 1.4773930311203003, "eval_runtime": 5097.0629, "eval_samples_per_second": 5.182, "eval_steps_per_second": 2.591, "step": 16 }, { "epoch": 0.00028694862025538425, "grad_norm": 1.3272778987884521, "learning_rate": 6.545084971874738e-05, "loss": 5.7386, "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": 1.320382384570368e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }