| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07467330429371499, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002489110143123833, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2808, | |
| "eval_samples_per_second": 39.712, | |
| "eval_steps_per_second": 19.856, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0074673304293715, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012445550715619166, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2705, | |
| "eval_samples_per_second": 39.808, | |
| "eval_steps_per_second": 19.904, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014934660858743, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0224019912881145, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024891101431238332, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2767, | |
| "eval_samples_per_second": 39.75, | |
| "eval_steps_per_second": 19.875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029869321717486, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.037336652146857496, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.037336652146857496, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3264, | |
| "eval_samples_per_second": 39.294, | |
| "eval_steps_per_second": 19.647, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.044803982576229, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.049782202862476664, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2831, | |
| "eval_samples_per_second": 39.691, | |
| "eval_steps_per_second": 19.845, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0522713130056005, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.059738643434972, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06222775357809583, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3392, | |
| "eval_samples_per_second": 39.178, | |
| "eval_steps_per_second": 19.589, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0672059738643435, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07467330429371499, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07467330429371499, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2884, | |
| "eval_samples_per_second": 39.642, | |
| "eval_steps_per_second": 19.821, | |
| "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": 2302869944401920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |