| { | |
| "best_metric": 0.0810636430978775, | |
| "best_model_checkpoint": "/workspace/save/checkpoint-233", | |
| "epoch": 0.9971469329529244, | |
| "eval_steps": 500, | |
| "global_step": 233, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21398002853067047, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 1.9916057044029887e-05, | |
| "loss": 0.126, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42796005706134094, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.9651642858238914e-05, | |
| "loss": 0.0777, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6419400855920114, | |
| "grad_norm": 3.828125, | |
| "learning_rate": 1.921142770711075e-05, | |
| "loss": 0.0802, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8559201141226819, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.860342994043941e-05, | |
| "loss": 0.072, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9971469329529244, | |
| "eval_loss": 0.0810636430978775, | |
| "eval_runtime": 182.3128, | |
| "eval_samples_per_second": 6.834, | |
| "eval_steps_per_second": 1.711, | |
| "step": 233 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1165, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 5.097013870044365e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |