| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004100881689563256, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004100881689563256, | |
| "grad_norm": 4.216660499572754, | |
| "learning_rate": 2e-05, | |
| "loss": 5.0075, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004100881689563256, | |
| "eval_loss": 1.1946476697921753, | |
| "eval_runtime": 71.0133, | |
| "eval_samples_per_second": 14.462, | |
| "eval_steps_per_second": 7.238, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008201763379126512, | |
| "grad_norm": 3.781083583831787, | |
| "learning_rate": 4e-05, | |
| "loss": 4.2077, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001230264506868977, | |
| "grad_norm": 4.4667582511901855, | |
| "learning_rate": 6e-05, | |
| "loss": 4.8488, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001230264506868977, | |
| "eval_loss": 1.1840327978134155, | |
| "eval_runtime": 71.2494, | |
| "eval_samples_per_second": 14.414, | |
| "eval_steps_per_second": 7.214, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016403526758253025, | |
| "grad_norm": 4.2728447914123535, | |
| "learning_rate": 8e-05, | |
| "loss": 4.3262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002050440844781628, | |
| "grad_norm": 3.940521240234375, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8905, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002460529013737954, | |
| "grad_norm": 3.8386030197143555, | |
| "learning_rate": 0.00012, | |
| "loss": 4.5264, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002460529013737954, | |
| "eval_loss": 1.1354962587356567, | |
| "eval_runtime": 71.2872, | |
| "eval_samples_per_second": 14.407, | |
| "eval_steps_per_second": 7.21, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002870617182694279, | |
| "grad_norm": 3.8614327907562256, | |
| "learning_rate": 0.00014, | |
| "loss": 4.3887, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003280705351650605, | |
| "grad_norm": 4.717683792114258, | |
| "learning_rate": 0.00016, | |
| "loss": 4.9963, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0036907935206069303, | |
| "grad_norm": 4.848432540893555, | |
| "learning_rate": 0.00018, | |
| "loss": 5.0174, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0036907935206069303, | |
| "eval_loss": 1.108507513999939, | |
| "eval_runtime": 71.2102, | |
| "eval_samples_per_second": 14.422, | |
| "eval_steps_per_second": 7.218, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004100881689563256, | |
| "grad_norm": 3.995793104171753, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7904, | |
| "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": 3505339571896320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |