| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00017519961806483262, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7519961806483262e-05, | |
| "grad_norm": 0.3499121069908142, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0405, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7519961806483262e-05, | |
| "eval_loss": 2.979212760925293, | |
| "eval_runtime": 600.1858, | |
| "eval_samples_per_second": 40.043, | |
| "eval_steps_per_second": 20.022, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.5039923612966525e-05, | |
| "grad_norm": 0.40081438422203064, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8075, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.2559885419449784e-05, | |
| "grad_norm": 0.4182718098163605, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3757, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.2559885419449784e-05, | |
| "eval_loss": 2.9779281616210938, | |
| "eval_runtime": 604.108, | |
| "eval_samples_per_second": 39.783, | |
| "eval_steps_per_second": 19.892, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.007984722593305e-05, | |
| "grad_norm": 0.42494556307792664, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7062, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.759980903241631e-05, | |
| "grad_norm": 0.36632823944091797, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2727, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010511977083889957, | |
| "grad_norm": 0.34499257802963257, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9886, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010511977083889957, | |
| "eval_loss": 2.9602231979370117, | |
| "eval_runtime": 607.6117, | |
| "eval_samples_per_second": 39.553, | |
| "eval_steps_per_second": 19.777, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00012263973264538283, | |
| "grad_norm": 0.4552798867225647, | |
| "learning_rate": 0.00014, | |
| "loss": 2.9689, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001401596944518661, | |
| "grad_norm": 0.4305766522884369, | |
| "learning_rate": 0.00016, | |
| "loss": 3.3484, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015767965625834935, | |
| "grad_norm": 0.3637130558490753, | |
| "learning_rate": 0.00018, | |
| "loss": 3.0223, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00015767965625834935, | |
| "eval_loss": 2.9118614196777344, | |
| "eval_runtime": 603.9303, | |
| "eval_samples_per_second": 39.794, | |
| "eval_steps_per_second": 19.898, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00017519961806483262, | |
| "grad_norm": 0.42786943912506104, | |
| "learning_rate": 0.0002, | |
| "loss": 3.228, | |
| "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": 389157910216704.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |