{ "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": 2.315487861633301, "eval_runtime": 60.7301, "eval_samples_per_second": 70.36, "eval_steps_per_second": 35.188, "step": 1 }, { "epoch": 0.0002956101886978371, "grad_norm": 0.6159582138061523, "learning_rate": 6e-05, "loss": 1.9754, "step": 3 }, { "epoch": 0.0005912203773956742, "grad_norm": 0.6258386969566345, "learning_rate": 0.00012, "loss": 2.0414, "step": 6 }, { "epoch": 0.0007882938365275657, "eval_loss": 2.1932437419891357, "eval_runtime": 58.8063, "eval_samples_per_second": 72.662, "eval_steps_per_second": 36.34, "step": 8 }, { "epoch": 0.0008868305660935114, "grad_norm": 0.47844335436820984, "learning_rate": 0.00018, "loss": 1.983, "step": 9 }, { "epoch": 0.0011824407547913484, "grad_norm": 0.3948184847831726, "learning_rate": 0.00019510565162951537, "loss": 1.9305, "step": 12 }, { "epoch": 0.0014780509434891855, "grad_norm": 0.4077311158180237, "learning_rate": 0.00017071067811865476, "loss": 1.9214, "step": 15 }, { "epoch": 0.0015765876730551313, "eval_loss": 1.999603509902954, "eval_runtime": 59.355, "eval_samples_per_second": 71.991, "eval_steps_per_second": 36.004, "step": 16 }, { "epoch": 0.0017736611321870228, "grad_norm": 0.42993485927581787, "learning_rate": 0.00013090169943749476, "loss": 1.7603, "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 }