| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 40.0, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.7897256016731262, | |
| "learning_rate": 0.00019994755690455152, | |
| "loss": 1.18, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.3124788701534271, | |
| "learning_rate": 0.0001981178176898239, | |
| "loss": 0.5251, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 0.0885872170329094, | |
| "learning_rate": 0.00019372067050063438, | |
| "loss": 0.3762, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.05624234303832054, | |
| "learning_rate": 0.00018687117365181512, | |
| "loss": 0.3055, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 0.048317451030015945, | |
| "learning_rate": 0.00017774855506796496, | |
| "loss": 0.2558, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.04710673913359642, | |
| "learning_rate": 0.00016659152250116812, | |
| "loss": 0.2102, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "grad_norm": 0.04203253239393234, | |
| "learning_rate": 0.0001536920173648984, | |
| "loss": 0.1676, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.049825090914964676, | |
| "learning_rate": 0.00013938757562492873, | |
| "loss": 0.13, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7825224737580646e+18, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |