| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013534088986635088, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027068177973270176, | |
| "grad_norm": 5.961866855621338, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027068177973270176, | |
| "eval_loss": 1.6664624214172363, | |
| "eval_runtime": 95.3405, | |
| "eval_samples_per_second": 6.534, | |
| "eval_steps_per_second": 3.272, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005413635594654035, | |
| "grad_norm": 6.682415008544922, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5725, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005413635594654035, | |
| "eval_loss": 1.4917327165603638, | |
| "eval_runtime": 15.1796, | |
| "eval_samples_per_second": 41.042, | |
| "eval_steps_per_second": 20.554, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008120453391981051, | |
| "grad_norm": 4.559573650360107, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4786, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01082727118930807, | |
| "grad_norm": 3.610630989074707, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3065, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01082727118930807, | |
| "eval_loss": 1.2848633527755737, | |
| "eval_runtime": 15.6321, | |
| "eval_samples_per_second": 39.854, | |
| "eval_steps_per_second": 19.959, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013534088986635088, | |
| "grad_norm": 2.9939472675323486, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2759, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |