| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.6153846153846154, | |
| "eval_steps": 500, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.1644846200942993, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 8.9729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.6153846153846154, | |
| "grad_norm": 1.4217939376831055, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0559, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.6153846153846154, | |
| "grad_norm": 2.3738677501678467, | |
| "learning_rate": 5e-05, | |
| "loss": 10.0118, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.6153846153846154, | |
| "grad_norm": 2.8046391010284424, | |
| "learning_rate": 0.0, | |
| "loss": 9.9665, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 3.6153846153846154, | |
| "step": 4, | |
| "total_flos": 11516965239360.0, | |
| "train_loss": 9.751765489578247, | |
| "train_runtime": 35.6843, | |
| "train_samples_per_second": 2.802, | |
| "train_steps_per_second": 0.112 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 4, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 11516965239360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |