| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04219409282700422, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004219409282700422, | |
| "grad_norm": 1.5075968804012518e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004219409282700422, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 0.555, | |
| "eval_samples_per_second": 180.188, | |
| "eval_steps_per_second": 90.094, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008438818565400843, | |
| "grad_norm": 1.3019131984037813e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012658227848101266, | |
| "grad_norm": 1.9596942365751602e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012658227848101266, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 0.5506, | |
| "eval_samples_per_second": 181.633, | |
| "eval_steps_per_second": 90.816, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016877637130801686, | |
| "grad_norm": 2.6459263608558103e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02109704641350211, | |
| "grad_norm": 1.7657370335655287e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02531645569620253, | |
| "grad_norm": 1.8836599338101223e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02531645569620253, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 0.5501, | |
| "eval_samples_per_second": 181.793, | |
| "eval_steps_per_second": 90.896, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.029535864978902954, | |
| "grad_norm": 1.9297593098599464e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03375527426160337, | |
| "grad_norm": 2.264007162011694e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0379746835443038, | |
| "grad_norm": 1.6398485968238674e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0379746835443038, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 0.5532, | |
| "eval_samples_per_second": 180.758, | |
| "eval_steps_per_second": 90.379, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04219409282700422, | |
| "grad_norm": 1.7036009012372233e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 199228784640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |