{ "best_metric": null, "best_model_checkpoint": null, "epoch": 8.695652173913043, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.7391304347826086, "grad_norm": 0.5635470151901245, "learning_rate": 4.849231551964771e-05, "loss": 2.7421, "step": 10 }, { "epoch": 3.4782608695652173, "grad_norm": 0.5530717968940735, "learning_rate": 3.7500000000000003e-05, "loss": 2.3269, "step": 20 }, { "epoch": 5.217391304347826, "grad_norm": 0.3990781903266907, "learning_rate": 2.0658795558326743e-05, "loss": 2.0529, "step": 30 }, { "epoch": 6.956521739130435, "grad_norm": 0.346131294965744, "learning_rate": 5.848888922025553e-06, "loss": 1.9645, "step": 40 }, { "epoch": 8.695652173913043, "grad_norm": 0.3258317708969116, "learning_rate": 0.0, "loss": 1.9208, "step": 50 }, { "epoch": 8.695652173913043, "eval_loss": 1.8110594749450684, "eval_runtime": 6.1598, "eval_samples_per_second": 58.931, "eval_steps_per_second": 14.773, "step": 50 }, { "epoch": 8.695652173913043, "step": 50, "total_flos": 1.2046864862727373e+17, "train_loss": 2.2014216232299804, "train_runtime": 478.0303, "train_samples_per_second": 30.354, "train_steps_per_second": 0.105 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.2046864862727373e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }