| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02236302646291465, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007454342154304882, | |
| "eval_loss": 3.5522725582122803, | |
| "eval_runtime": 6.2707, | |
| "eval_samples_per_second": 90.101, | |
| "eval_steps_per_second": 45.13, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022363026462914647, | |
| "grad_norm": 1.7406411170959473, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004472605292582929, | |
| "grad_norm": 1.7950012683868408, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4204, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005963473723443906, | |
| "eval_loss": 2.907726287841797, | |
| "eval_runtime": 5.4209, | |
| "eval_samples_per_second": 104.225, | |
| "eval_steps_per_second": 52.205, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006708907938874394, | |
| "grad_norm": 1.8308537006378174, | |
| "learning_rate": 0.00018, | |
| "loss": 3.0121, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008945210585165859, | |
| "grad_norm": 1.5710326433181763, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.4607, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011181513231457324, | |
| "grad_norm": 2.107144594192505, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0398, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011926947446887812, | |
| "eval_loss": 1.6485852003097534, | |
| "eval_runtime": 5.6206, | |
| "eval_samples_per_second": 100.523, | |
| "eval_steps_per_second": 50.35, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013417815877748788, | |
| "grad_norm": 2.864588499069214, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015654118524040254, | |
| "grad_norm": 4.60991907119751, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.2822, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017890421170331718, | |
| "grad_norm": 2.014559030532837, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.0077, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017890421170331718, | |
| "eval_loss": 1.0028789043426514, | |
| "eval_runtime": 5.6501, | |
| "eval_samples_per_second": 99.998, | |
| "eval_steps_per_second": 50.088, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02012672381662318, | |
| "grad_norm": 2.1602630615234375, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.9325, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02236302646291465, | |
| "grad_norm": 2.1503665447235107, | |
| "learning_rate": 0.0, | |
| "loss": 0.8752, | |
| "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": 208256379125760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |