| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020080321285140562, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002008032128514056, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002008032128514056, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.3844, | |
| "eval_samples_per_second": 15.69, | |
| "eval_steps_per_second": 7.845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004016064257028112, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006024096385542169, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006024096385542169, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.5964, | |
| "eval_samples_per_second": 16.671, | |
| "eval_steps_per_second": 8.336, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010040160642570281, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.7707, | |
| "eval_samples_per_second": 12.522, | |
| "eval_steps_per_second": 6.261, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014056224899598393, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.1843, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.642, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018072289156626505, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018072289156626505, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.3379, | |
| "eval_samples_per_second": 17.021, | |
| "eval_steps_per_second": 8.51, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "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": 4394922956292096.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |