| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.432396423820676e-05, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.432396423820677e-06, | |
| "grad_norm": 0.43893134593963623, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.432396423820677e-06, | |
| "eval_loss": 1.1402034759521484, | |
| "eval_runtime": 2118.3198, | |
| "eval_samples_per_second": 23.572, | |
| "eval_steps_per_second": 11.786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.6864792847641354e-05, | |
| "grad_norm": 0.2196905016899109, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0644, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.529718927146203e-05, | |
| "grad_norm": 0.25781676173210144, | |
| "learning_rate": 6e-05, | |
| "loss": 0.792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.529718927146203e-05, | |
| "eval_loss": 1.1398121118545532, | |
| "eval_runtime": 2194.0181, | |
| "eval_samples_per_second": 22.759, | |
| "eval_steps_per_second": 11.38, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.372958569528271e-05, | |
| "grad_norm": 0.4526745676994324, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2744, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 4.216198211910338e-05, | |
| "grad_norm": 0.25739386677742004, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8938, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.059437854292406e-05, | |
| "grad_norm": 0.4274653196334839, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2159, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 5.059437854292406e-05, | |
| "eval_loss": 1.1368435621261597, | |
| "eval_runtime": 2936.1113, | |
| "eval_samples_per_second": 17.007, | |
| "eval_steps_per_second": 8.503, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 5.9026774966744735e-05, | |
| "grad_norm": 0.394429475069046, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2189, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 6.745917139056541e-05, | |
| "grad_norm": 0.3088739514350891, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0721, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 7.58915678143861e-05, | |
| "grad_norm": 0.45047444105148315, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2056, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 7.58915678143861e-05, | |
| "eval_loss": 1.127229928970337, | |
| "eval_runtime": 2137.6927, | |
| "eval_samples_per_second": 23.358, | |
| "eval_steps_per_second": 11.679, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 8.432396423820676e-05, | |
| "grad_norm": 0.3507402539253235, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9767, | |
| "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": 1230072997478400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |