{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0885341074020318, | |
"eval_steps": 500, | |
"global_step": 1500, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.36, | |
"grad_norm": 0.018075617030262947, | |
"learning_rate": 4.3952588292210934e-05, | |
"loss": 0.1598, | |
"step": 500 | |
}, | |
{ | |
"epoch": 0.73, | |
"grad_norm": 0.014405773021280766, | |
"learning_rate": 3.790517658442187e-05, | |
"loss": 0.0001, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 1.09, | |
"grad_norm": 0.0018536851275712252, | |
"learning_rate": 3.18577648766328e-05, | |
"loss": 0.0001, | |
"step": 1500 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 4134, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 7598530363392.0, | |
"train_batch_size": 4, | |
"trial_name": null, | |
"trial_params": null | |
} | |