| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9797979797979797, | |
| "eval_steps": 500, | |
| "global_step": 98, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 0.4713294208049774, | |
| "learning_rate": 0.0002, | |
| "loss": 3.2814, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 0.8114767670631409, | |
| "learning_rate": 0.00017727272727272728, | |
| "loss": 3.2061, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 0.9482328295707703, | |
| "learning_rate": 0.00015454545454545454, | |
| "loss": 2.6241, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 1.0774873495101929, | |
| "learning_rate": 0.0001318181818181818, | |
| "loss": 2.3206, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "grad_norm": 0.9080483317375183, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 2.0241, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "grad_norm": 0.7166955471038818, | |
| "learning_rate": 8.636363636363637e-05, | |
| "loss": 1.7966, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4141414141414141, | |
| "grad_norm": 0.8821200728416443, | |
| "learning_rate": 6.363636363636364e-05, | |
| "loss": 1.8161, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.6161616161616161, | |
| "grad_norm": 0.9654076099395752, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 1.6785, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 0.7666375041007996, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.7247, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9797979797979797, | |
| "step": 98, | |
| "total_flos": 226829006180352.0, | |
| "train_loss": 2.221530009289177, | |
| "train_runtime": 2745.7828, | |
| "train_samples_per_second": 0.144, | |
| "train_steps_per_second": 0.036 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 98, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 226829006180352.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |