| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015318392794228029, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003063678558845606, | |
| "grad_norm": 2.937537670135498, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.9979, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006127357117691212, | |
| "grad_norm": 2.9786553382873535, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.9223, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.009191035676536818, | |
| "grad_norm": 2.899183750152588, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 2.9009, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.012254714235382424, | |
| "grad_norm": 2.9656615257263184, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 2.8884, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.015318392794228029, | |
| "grad_norm": 2.785738468170166, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 2.8738, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2500, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.7832077697024e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |