| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998833002684094, | |
| "eval_steps": 250, | |
| "global_step": 1071, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2333994631812347, | |
| "grad_norm": 3.6896331310272217, | |
| "learning_rate": 9.014628666901862e-05, | |
| "loss": 0.422, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2333994631812347, | |
| "eval_loss": 0.23629401624202728, | |
| "eval_runtime": 28.8465, | |
| "eval_samples_per_second": 3.016, | |
| "eval_steps_per_second": 3.016, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "grad_norm": 3.746055841445923, | |
| "learning_rate": 5.873208115525416e-05, | |
| "loss": 0.1827, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "eval_loss": 0.19270068407058716, | |
| "eval_runtime": 28.8521, | |
| "eval_samples_per_second": 3.015, | |
| "eval_steps_per_second": 3.015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "grad_norm": 2.8079304695129395, | |
| "learning_rate": 2.2552653673166675e-05, | |
| "loss": 0.1623, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "eval_loss": 0.1794940084218979, | |
| "eval_runtime": 28.9263, | |
| "eval_samples_per_second": 3.008, | |
| "eval_steps_per_second": 3.008, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "grad_norm": 3.099646806716919, | |
| "learning_rate": 1.3516368772988675e-06, | |
| "loss": 0.1494, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "eval_loss": 0.174073725938797, | |
| "eval_runtime": 28.8527, | |
| "eval_samples_per_second": 3.015, | |
| "eval_steps_per_second": 3.015, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1071, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.533261660957696e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |