| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04008016032064128, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004008016032064128, | |
| "grad_norm": 2.0643436908721924, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004008016032064128, | |
| "eval_loss": 1.9321434497833252, | |
| "eval_runtime": 2.327, | |
| "eval_samples_per_second": 45.122, | |
| "eval_steps_per_second": 22.776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008016032064128256, | |
| "grad_norm": 2.7145376205444336, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0837, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012024048096192385, | |
| "grad_norm": 2.351701259613037, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0507, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012024048096192385, | |
| "eval_loss": 1.9191216230392456, | |
| "eval_runtime": 2.325, | |
| "eval_samples_per_second": 45.161, | |
| "eval_steps_per_second": 22.796, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01603206412825651, | |
| "grad_norm": 2.490091562271118, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8264, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02004008016032064, | |
| "grad_norm": 2.168489456176758, | |
| "learning_rate": 0.0001, | |
| "loss": 1.966, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02404809619238477, | |
| "grad_norm": 2.344045639038086, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7798, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02404809619238477, | |
| "eval_loss": 1.7123405933380127, | |
| "eval_runtime": 2.3355, | |
| "eval_samples_per_second": 44.958, | |
| "eval_steps_per_second": 22.693, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028056112224448898, | |
| "grad_norm": 3.1197409629821777, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03206412825651302, | |
| "grad_norm": 2.1753883361816406, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7457, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.036072144288577156, | |
| "grad_norm": 2.092257022857666, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2922, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.036072144288577156, | |
| "eval_loss": 1.3578931093215942, | |
| "eval_runtime": 2.3295, | |
| "eval_samples_per_second": 45.073, | |
| "eval_steps_per_second": 22.751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04008016032064128, | |
| "grad_norm": 2.7192161083221436, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3041, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 673031965900800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |