| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003831858067977162, | |
| "eval_steps": 7, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001532743227190865, | |
| "eval_loss": NaN, | |
| "eval_runtime": 109.1287, | |
| "eval_samples_per_second": 25.172, | |
| "eval_steps_per_second": 12.591, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045982296815725947, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009196459363145189, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010729202590336053, | |
| "eval_loss": NaN, | |
| "eval_runtime": 108.2295, | |
| "eval_samples_per_second": 25.381, | |
| "eval_steps_per_second": 12.695, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013794689044717783, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018392918726290379, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021458405180672106, | |
| "eval_loss": NaN, | |
| "eval_runtime": 107.8682, | |
| "eval_samples_per_second": 25.466, | |
| "eval_steps_per_second": 12.738, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0022991148407862975, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027589378089435566, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003218760777100816, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003218760777100816, | |
| "eval_loss": NaN, | |
| "eval_runtime": 108.0265, | |
| "eval_samples_per_second": 25.429, | |
| "eval_steps_per_second": 12.719, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0036785837452580758, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 460861090037760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |