| { | |
| "best_metric": 0.6941899657249451, | |
| "best_model_checkpoint": "./output/checkpoint-100", | |
| "epoch": 99.61538461538461, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 24.615384615384617, | |
| "grad_norm": 10.499377250671387, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 1.1965, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 49.61538461538461, | |
| "grad_norm": 3.6972644329071045, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.9153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 49.61538461538461, | |
| "eval_loss": 0.783072292804718, | |
| "eval_runtime": 0.1621, | |
| "eval_samples_per_second": 37.007, | |
| "eval_steps_per_second": 18.504, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 74.61538461538461, | |
| "grad_norm": 2.7592525482177734, | |
| "learning_rate": 5.400000000000001e-06, | |
| "loss": 0.8036, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 99.61538461538461, | |
| "grad_norm": 2.6778719425201416, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 0.7641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 99.61538461538461, | |
| "eval_loss": 0.6941899657249451, | |
| "eval_runtime": 0.1355, | |
| "eval_samples_per_second": 44.292, | |
| "eval_steps_per_second": 22.146, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 132027365701440.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |