{ "best_metric": null, "best_model_checkpoint": null, "epoch": 16.748538011695906, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.7485380116959064, "grad_norm": 8.254446983337402, "learning_rate": 1.8775510204081636e-05, "loss": 2.7739, "step": 10 }, { "epoch": 3.374269005847953, "grad_norm": 1.915563941001892, "learning_rate": 1.6938775510204085e-05, "loss": 0.2, "step": 20 }, { "epoch": 5.0, "grad_norm": 0.6233114004135132, "learning_rate": 1.530612244897959e-05, "loss": 0.1332, "step": 30 }, { "epoch": 6.748538011695906, "grad_norm": 0.4581431746482849, "learning_rate": 1.326530612244898e-05, "loss": 0.1231, "step": 40 }, { "epoch": 8.374269005847953, "grad_norm": 1.2758772373199463, "learning_rate": 1.1632653061224491e-05, "loss": 0.1117, "step": 50 }, { "epoch": 10.0, "grad_norm": 0.4534628987312317, "learning_rate": 9.795918367346939e-06, "loss": 0.104, "step": 60 }, { "epoch": 11.748538011695906, "grad_norm": 0.8441503643989563, "learning_rate": 7.959183673469388e-06, "loss": 0.1108, "step": 70 }, { "epoch": 13.374269005847953, "grad_norm": 0.4053587019443512, "learning_rate": 6.122448979591837e-06, "loss": 0.1028, "step": 80 }, { "epoch": 15.0, "grad_norm": 0.5017651915550232, "learning_rate": 4.2857142857142855e-06, "loss": 0.1028, "step": 90 }, { "epoch": 16.748538011695906, "grad_norm": 0.732860803604126, "learning_rate": 2.4489795918367347e-06, "loss": 0.1099, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 20, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 140491976867840.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }