Invalid JSON:Unexpected token 'N', ..."al_loss": NaN,
"... is not valid JSON
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07370215118153761, | |
| "eval_steps": 40, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036851075590768807, | |
| "eval_loss": NaN, | |
| "eval_runtime": 99.3489, | |
| "eval_samples_per_second": 46.01, | |
| "eval_steps_per_second": 23.01, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014740430236307523, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014740430236307523, | |
| "eval_loss": NaN, | |
| "eval_runtime": 97.8099, | |
| "eval_samples_per_second": 46.734, | |
| "eval_steps_per_second": 23.372, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.029480860472615045, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.029480860472615045, | |
| "eval_loss": NaN, | |
| "eval_runtime": 98.4188, | |
| "eval_samples_per_second": 46.444, | |
| "eval_steps_per_second": 23.227, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04422129070892257, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04422129070892257, | |
| "eval_loss": NaN, | |
| "eval_runtime": 99.877, | |
| "eval_samples_per_second": 45.766, | |
| "eval_steps_per_second": 22.888, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05896172094523009, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05896172094523009, | |
| "eval_loss": NaN, | |
| "eval_runtime": 98.8283, | |
| "eval_samples_per_second": 46.252, | |
| "eval_steps_per_second": 23.131, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07370215118153761, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07370215118153761, | |
| "eval_loss": NaN, | |
| "eval_runtime": 98.4516, | |
| "eval_samples_per_second": 46.429, | |
| "eval_steps_per_second": 23.22, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9533761389330432.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |