{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.47904191616766467, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.023952095808383235, "eval_loss": 0.5039941072463989, "eval_runtime": 1.8987, "eval_samples_per_second": 9.48, "eval_steps_per_second": 4.74, "step": 1 }, { "epoch": 0.0718562874251497, "grad_norm": 6.43875789642334, "learning_rate": 6e-05, "loss": 1.9809, "step": 3 }, { "epoch": 0.1437125748502994, "grad_norm": 5.396348476409912, "learning_rate": 0.00012, "loss": 1.7005, "step": 6 }, { "epoch": 0.19161676646706588, "eval_loss": 0.024824917316436768, "eval_runtime": 1.9003, "eval_samples_per_second": 9.472, "eval_steps_per_second": 4.736, "step": 8 }, { "epoch": 0.2155688622754491, "grad_norm": 3.0755698680877686, "learning_rate": 0.00018, "loss": 0.2899, "step": 9 }, { "epoch": 0.2874251497005988, "grad_norm": 0.12527230381965637, "learning_rate": 0.00019510565162951537, "loss": 0.015, "step": 12 }, { "epoch": 0.3592814371257485, "grad_norm": 0.023354211822152138, "learning_rate": 0.00017071067811865476, "loss": 0.0011, "step": 15 }, { "epoch": 0.38323353293413176, "eval_loss": 7.335327245527878e-05, "eval_runtime": 1.9021, "eval_samples_per_second": 9.463, "eval_steps_per_second": 4.732, "step": 16 }, { "epoch": 0.4311377245508982, "grad_norm": 0.013110329397022724, "learning_rate": 0.00013090169943749476, "loss": 0.0003, "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": 3684183016734720.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }