| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 95.04950495049505, | |
| "eval_steps": 1000, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.920792079207921, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.925593026621833e-05, | |
| "loss": 2.5159, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 15.841584158415841, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.518141803042527e-05, | |
| "loss": 0.6793, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 23.762376237623762, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.783564079088477e-05, | |
| "loss": 0.5226, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 31.683168316831683, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.77504540106735e-05, | |
| "loss": 0.5165, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 39.603960396039604, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.565605430620013e-05, | |
| "loss": 0.5156, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 47.524752475247524, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.242811110572242e-05, | |
| "loss": 0.5153, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 55.445544554455445, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.902436565662977e-05, | |
| "loss": 0.5158, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 63.366336633663366, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.6415287796261706e-05, | |
| "loss": 0.5153, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 71.2871287128713, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.5513811136094787e-05, | |
| "loss": 0.5154, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 79.20792079207921, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.109234034661289e-06, | |
| "loss": 0.5154, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 87.12871287128714, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.810072119441103e-06, | |
| "loss": 0.5151, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 95.04950495049505, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.5156, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.742978448084173e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |