| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00044108457796782535, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.900939755198059e-05, | |
| "grad_norm": 0.7357999682426453, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.900939755198059e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 882.8523, | |
| "eval_samples_per_second": 9.732, | |
| "eval_steps_per_second": 4.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.801879510396118e-05, | |
| "grad_norm": 0.9853785634040833, | |
| "learning_rate": 4e-05, | |
| "loss": 0.533, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00014702819265594177, | |
| "grad_norm": 0.9133309125900269, | |
| "learning_rate": 6e-05, | |
| "loss": 0.4966, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014702819265594177, | |
| "eval_loss": NaN, | |
| "eval_runtime": 884.4031, | |
| "eval_samples_per_second": 9.715, | |
| "eval_steps_per_second": 4.858, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00019603759020792236, | |
| "grad_norm": 0.8823265433311462, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4234, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00024504698775990296, | |
| "grad_norm": 0.7202754020690918, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4559, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00029405638531188353, | |
| "grad_norm": 0.8189737200737, | |
| "learning_rate": 0.00012, | |
| "loss": 0.4385, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00029405638531188353, | |
| "eval_loss": NaN, | |
| "eval_runtime": 885.3943, | |
| "eval_samples_per_second": 9.704, | |
| "eval_steps_per_second": 4.852, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00034306578286386416, | |
| "grad_norm": 0.9013888239860535, | |
| "learning_rate": 0.00014, | |
| "loss": 0.4894, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00039207518041584473, | |
| "grad_norm": 0.6955869793891907, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4859, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00044108457796782535, | |
| "grad_norm": 0.5119171738624573, | |
| "learning_rate": 0.00018, | |
| "loss": 0.38, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00044108457796782535, | |
| "eval_loss": NaN, | |
| "eval_runtime": 885.7742, | |
| "eval_samples_per_second": 9.7, | |
| "eval_steps_per_second": 4.85, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3537906035589120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |