| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02886002886002886, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005772005772005772, | |
| "eval_loss": 2.856306791305542, | |
| "eval_runtime": 24.6309, | |
| "eval_samples_per_second": 29.638, | |
| "eval_steps_per_second": 14.819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005772005772005772, | |
| "grad_norm": 1.4742867946624756, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.5179, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007503607503607504, | |
| "eval_loss": 2.239126443862915, | |
| "eval_runtime": 23.4847, | |
| "eval_samples_per_second": 31.084, | |
| "eval_steps_per_second": 15.542, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011544011544011544, | |
| "grad_norm": 1.954991102218628, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.1294, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015007215007215007, | |
| "eval_loss": 2.1028270721435547, | |
| "eval_runtime": 23.5169, | |
| "eval_samples_per_second": 31.042, | |
| "eval_steps_per_second": 15.521, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017316017316017316, | |
| "grad_norm": 1.1958589553833008, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.9523, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022510822510822513, | |
| "eval_loss": 2.0787417888641357, | |
| "eval_runtime": 23.5292, | |
| "eval_samples_per_second": 31.025, | |
| "eval_steps_per_second": 15.513, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.023088023088023088, | |
| "grad_norm": 2.168440103530884, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 2.0701, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02886002886002886, | |
| "grad_norm": 1.8920999765396118, | |
| "learning_rate": 0.0, | |
| "loss": 1.9333, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9571494984155136.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |