{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.025396825396825397, "eval_steps": 13, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005079365079365079, "eval_loss": 0.7444761991500854, "eval_runtime": 39.6962, "eval_samples_per_second": 20.884, "eval_steps_per_second": 10.454, "step": 1 }, { "epoch": 0.005079365079365079, "grad_norm": 0.5165723562240601, "learning_rate": 0.00019396926207859084, "loss": 0.2948, "step": 10 }, { "epoch": 0.006603174603174603, "eval_loss": 0.031044673174619675, "eval_runtime": 39.7388, "eval_samples_per_second": 20.861, "eval_steps_per_second": 10.443, "step": 13 }, { "epoch": 0.010158730158730159, "grad_norm": 0.5607534050941467, "learning_rate": 0.00015000000000000001, "loss": 0.0207, "step": 20 }, { "epoch": 0.013206349206349206, "eval_loss": 0.021534565836191177, "eval_runtime": 39.7708, "eval_samples_per_second": 20.844, "eval_steps_per_second": 10.435, "step": 26 }, { "epoch": 0.015238095238095238, "grad_norm": 0.38220691680908203, "learning_rate": 8.263518223330697e-05, "loss": 0.0224, "step": 30 }, { "epoch": 0.019809523809523808, "eval_loss": 0.018612399697303772, "eval_runtime": 39.8574, "eval_samples_per_second": 20.799, "eval_steps_per_second": 10.412, "step": 39 }, { "epoch": 0.020317460317460317, "grad_norm": 0.07513657957315445, "learning_rate": 2.339555568810221e-05, "loss": 0.0119, "step": 40 }, { "epoch": 0.025396825396825397, "grad_norm": 0.38701480627059937, "learning_rate": 0.0, "loss": 0.0152, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.02619680866304e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }