| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 164, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06097560975609756, | |
| "grad_norm": 2.8818812370300293, | |
| "learning_rate": 2.2778456926584984e-06, | |
| "loss": 0.7153, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12195121951219512, | |
| "grad_norm": 1.8926554918289185, | |
| "learning_rate": 2.129933634693661e-06, | |
| "loss": 0.67, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18292682926829268, | |
| "grad_norm": 2.1769344806671143, | |
| "learning_rate": 1.9820215767288233e-06, | |
| "loss": 0.638, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 1.9136947393417358, | |
| "learning_rate": 1.834109518763986e-06, | |
| "loss": 0.6009, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3048780487804878, | |
| "grad_norm": 1.2495990991592407, | |
| "learning_rate": 1.6861974607991482e-06, | |
| "loss": 0.5909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "grad_norm": 1.0768756866455078, | |
| "learning_rate": 1.5382854028343109e-06, | |
| "loss": 0.5695, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4268292682926829, | |
| "grad_norm": 1.384157657623291, | |
| "learning_rate": 1.3903733448694731e-06, | |
| "loss": 0.5484, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 1.2738723754882812, | |
| "learning_rate": 1.2424612869046356e-06, | |
| "loss": 0.5688, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5487804878048781, | |
| "grad_norm": 1.511283278465271, | |
| "learning_rate": 1.094549228939798e-06, | |
| "loss": 0.4933, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 1.630743384361267, | |
| "learning_rate": 9.466371709749605e-07, | |
| "loss": 0.5173, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6707317073170732, | |
| "grad_norm": 1.6964328289031982, | |
| "learning_rate": 7.987251130101229e-07, | |
| "loss": 0.5205, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 1.619503140449524, | |
| "learning_rate": 6.508130550452854e-07, | |
| "loss": 0.5227, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7926829268292683, | |
| "grad_norm": 0.9739822149276733, | |
| "learning_rate": 5.029009970804477e-07, | |
| "loss": 0.4964, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8536585365853658, | |
| "grad_norm": 1.1013520956039429, | |
| "learning_rate": 3.5498893911561014e-07, | |
| "loss": 0.4978, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9146341463414634, | |
| "grad_norm": 1.492324948310852, | |
| "learning_rate": 2.0707688115077262e-07, | |
| "loss": 0.5045, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 1.4458919763565063, | |
| "learning_rate": 5.916482318593503e-08, | |
| "loss": 0.4941, | |
| "step": 160 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 164, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 692539560173568.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.425757750623336e-06, | |
| "num_train_epochs": 1, | |
| "per_device_train_batch_size": 32, | |
| "seed": 7 | |
| } | |
| } | |