| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5195344970906068, | |
| "eval_steps": 500, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10390689941812137, | |
| "grad_norm": 1.8855979442596436, | |
| "learning_rate": 1.9310058187863676e-05, | |
| "loss": 0.8022, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.20781379883624274, | |
| "grad_norm": 0.8622527122497559, | |
| "learning_rate": 1.86173455250762e-05, | |
| "loss": 0.5316, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3117206982543641, | |
| "grad_norm": 1.404678225517273, | |
| "learning_rate": 1.7924632862288724e-05, | |
| "loss": 0.4832, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.41562759767248547, | |
| "grad_norm": 1.3559819459915161, | |
| "learning_rate": 1.7233305624826823e-05, | |
| "loss": 0.4518, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5195344970906068, | |
| "grad_norm": 0.8163271546363831, | |
| "learning_rate": 1.6540592962039347e-05, | |
| "loss": 0.4389, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 14436, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 3044789452800000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |