{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.3988035892323031, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03988035892323031, "grad_norm": 16.628543853759766, "learning_rate": 0.00012, "loss": 2.1274, "step": 10 }, { "epoch": 0.07976071784646062, "grad_norm": 12.371907234191895, "learning_rate": 0.00019950829025450114, "loss": 0.7722, "step": 20 }, { "epoch": 0.11964107676969092, "grad_norm": 9.106270790100098, "learning_rate": 0.00019652089102773488, "loss": 0.4456, "step": 30 }, { "epoch": 0.15952143569292124, "grad_norm": 5.712669372558594, "learning_rate": 0.00019090065350491626, "loss": 0.3662, "step": 40 }, { "epoch": 0.19940179461615154, "grad_norm": 2.922630548477173, "learning_rate": 0.00018280088311480201, "loss": 0.2983, "step": 50 }, { "epoch": 0.23928215353938184, "grad_norm": 5.451596260070801, "learning_rate": 0.00017244252047910892, "loss": 0.3034, "step": 60 }, { "epoch": 0.27916251246261214, "grad_norm": 3.604940414428711, "learning_rate": 0.00016010811472830252, "loss": 0.2754, "step": 70 }, { "epoch": 0.3190428713858425, "grad_norm": 2.805121660232544, "learning_rate": 0.0001461341162978688, "loss": 0.2659, "step": 80 }, { "epoch": 0.3589232303090728, "grad_norm": 3.4018733501434326, "learning_rate": 0.00013090169943749476, "loss": 0.2767, "step": 90 }, { "epoch": 0.3988035892323031, "grad_norm": 3.0557034015655518, "learning_rate": 0.0001148263647711842, "loss": 0.286, "step": 100 } ], "logging_steps": 10, "max_steps": 200, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1450485964480512.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }