{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.001970734591318914, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 9.853672956594571e-05, "eval_loss": 2.3153233528137207, "eval_runtime": 48.8077, "eval_samples_per_second": 87.548, "eval_steps_per_second": 43.784, "step": 1 }, { "epoch": 0.0002956101886978371, "grad_norm": 0.6262503266334534, "learning_rate": 6e-05, "loss": 1.9752, "step": 3 }, { "epoch": 0.0005912203773956742, "grad_norm": 0.6291804313659668, "learning_rate": 0.00012, "loss": 2.0395, "step": 6 }, { "epoch": 0.0007882938365275657, "eval_loss": 2.1891775131225586, "eval_runtime": 47.5423, "eval_samples_per_second": 89.878, "eval_steps_per_second": 44.949, "step": 8 }, { "epoch": 0.0008868305660935114, "grad_norm": 0.47909072041511536, "learning_rate": 0.00018, "loss": 1.9808, "step": 9 }, { "epoch": 0.0011824407547913484, "grad_norm": 0.39736393094062805, "learning_rate": 0.00019510565162951537, "loss": 1.9289, "step": 12 }, { "epoch": 0.0014780509434891855, "grad_norm": 0.40689948201179504, "learning_rate": 0.00017071067811865476, "loss": 1.9195, "step": 15 }, { "epoch": 0.0015765876730551313, "eval_loss": 2.001293659210205, "eval_runtime": 47.6644, "eval_samples_per_second": 89.648, "eval_steps_per_second": 44.834, "step": 16 }, { "epoch": 0.0017736611321870228, "grad_norm": 0.4287497401237488, "learning_rate": 0.00013090169943749476, "loss": 1.7583, "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": 185695271387136.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }