| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0175054704595186, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00175054704595186, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3215, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00175054704595186, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.9088, | |
| "eval_samples_per_second": 20.237, | |
| "eval_steps_per_second": 10.161, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00350109409190372, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00525164113785558, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1376, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00525164113785558, | |
| "eval_loss": NaN, | |
| "eval_runtime": 10.2096, | |
| "eval_samples_per_second": 23.605, | |
| "eval_steps_per_second": 11.852, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00700218818380744, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0087527352297593, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01050328227571116, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.211, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01050328227571116, | |
| "eval_loss": NaN, | |
| "eval_runtime": 10.211, | |
| "eval_samples_per_second": 23.602, | |
| "eval_steps_per_second": 11.85, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01225382932166302, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01400437636761488, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0471, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01575492341356674, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01575492341356674, | |
| "eval_loss": NaN, | |
| "eval_runtime": 10.2198, | |
| "eval_samples_per_second": 23.582, | |
| "eval_steps_per_second": 11.84, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0175054704595186, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0578, | |
| "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": 2190838490726400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |