| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004101890971737971, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.203781943475943e-05, | |
| "eval_loss": 2.414320945739746, | |
| "eval_runtime": 169.4794, | |
| "eval_samples_per_second": 30.287, | |
| "eval_steps_per_second": 15.146, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004101890971737971, | |
| "grad_norm": 1.9362826347351074, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3993, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008203781943475942, | |
| "grad_norm": 1.7552878856658936, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2122, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008203781943475942, | |
| "eval_loss": 1.9636577367782593, | |
| "eval_runtime": 169.4996, | |
| "eval_samples_per_second": 30.283, | |
| "eval_steps_per_second": 15.145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012305672915213913, | |
| "grad_norm": 1.0327292680740356, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6192, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016407563886951884, | |
| "grad_norm": 1.1551960706710815, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4912, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016407563886951884, | |
| "eval_loss": 1.425040602684021, | |
| "eval_runtime": 169.4843, | |
| "eval_samples_per_second": 30.286, | |
| "eval_steps_per_second": 15.146, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0020509454858689854, | |
| "grad_norm": 1.1303943395614624, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2962, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0024611345830427827, | |
| "grad_norm": 1.2731987237930298, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3262, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0024611345830427827, | |
| "eval_loss": 1.3036489486694336, | |
| "eval_runtime": 168.9628, | |
| "eval_samples_per_second": 30.379, | |
| "eval_steps_per_second": 15.193, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00287132368021658, | |
| "grad_norm": 1.2672828435897827, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3567, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0032815127773903768, | |
| "grad_norm": 1.2541266679763794, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3893, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032815127773903768, | |
| "eval_loss": 1.2780693769454956, | |
| "eval_runtime": 169.9851, | |
| "eval_samples_per_second": 30.197, | |
| "eval_steps_per_second": 15.101, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003691701874564174, | |
| "grad_norm": 1.1830114126205444, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2345, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004101890971737971, | |
| "grad_norm": 1.2346673011779785, | |
| "learning_rate": 0.0, | |
| "loss": 1.2622, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004101890971737971, | |
| "eval_loss": 1.2751587629318237, | |
| "eval_runtime": 170.3908, | |
| "eval_samples_per_second": 30.125, | |
| "eval_steps_per_second": 15.065, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 1809728246120448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |