| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01283147989734816, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000427715996578272, | |
| "eval_loss": 2.9688284397125244, | |
| "eval_runtime": 14.9293, | |
| "eval_samples_per_second": 65.978, | |
| "eval_steps_per_second": 33.022, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012831479897348161, | |
| "grad_norm": 1.316524863243103, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7893, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025662959794696323, | |
| "grad_norm": 1.1522525548934937, | |
| "learning_rate": 0.00012, | |
| "loss": 3.0151, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003421727972626176, | |
| "eval_loss": 2.836156129837036, | |
| "eval_runtime": 13.5098, | |
| "eval_samples_per_second": 72.91, | |
| "eval_steps_per_second": 36.492, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003849443969204448, | |
| "grad_norm": 1.1620888710021973, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2736, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0051325919589392645, | |
| "grad_norm": 1.7971843481063843, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.9401, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00641573994867408, | |
| "grad_norm": 1.240454077720642, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.5096, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006843455945252352, | |
| "eval_loss": 2.646683692932129, | |
| "eval_runtime": 13.4282, | |
| "eval_samples_per_second": 73.353, | |
| "eval_steps_per_second": 36.714, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007698887938408896, | |
| "grad_norm": 1.0643540620803833, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.3632, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008982035928143712, | |
| "grad_norm": 0.879787266254425, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.231, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010265183917878529, | |
| "grad_norm": 1.407170057296753, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.8816, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010265183917878529, | |
| "eval_loss": 2.5725584030151367, | |
| "eval_runtime": 13.8741, | |
| "eval_samples_per_second": 70.996, | |
| "eval_steps_per_second": 35.534, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011548331907613344, | |
| "grad_norm": 0.7667973637580872, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.3877, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01283147989734816, | |
| "grad_norm": 1.2102265357971191, | |
| "learning_rate": 0.0, | |
| "loss": 2.7211, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 256849534255104.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |