| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.2872340425531914, | |
| "eval_steps": 25, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9295, | |
| "eval_samples_per_second": 17.068, | |
| "eval_steps_per_second": 4.438, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0957446808510638, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.2659574468085106, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.4361702127659575, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.6063829787234043, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.7765957446808511, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.021276595744681, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.1914893617021276, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.3617021276595747, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.5319148936170213, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.702127659574468, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.872340425531915, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 3.117021276595745, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.2872340425531914, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8932788789405286e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |