Invalid JSON:Unexpected token 'N', ..."al_loss": NaN,
"... is not valid JSON
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000621708828887079, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2434176577741581e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1428.245, | |
| "eval_samples_per_second": 23.71, | |
| "eval_steps_per_second": 11.855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001243417657774158, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 27.4276, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00016164429551064055, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1426.0419, | |
| "eval_samples_per_second": 23.746, | |
| "eval_steps_per_second": 11.873, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0002486835315548316, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 23.8968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003232885910212811, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1426.2612, | |
| "eval_samples_per_second": 23.742, | |
| "eval_steps_per_second": 11.872, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0003730252973322474, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 58.9554, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00048493288653192164, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1426.7038, | |
| "eval_samples_per_second": 23.735, | |
| "eval_steps_per_second": 11.868, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0004973670631096632, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 6.4295, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.000621708828887079, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 5.6689, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.17005277462528e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |