| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011422044545973729, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001142204454597373, | |
| "grad_norm": 3.2880048820516095e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001142204454597373, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 2.0961, | |
| "eval_samples_per_second": 176.044, | |
| "eval_steps_per_second": 88.261, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002284408909194746, | |
| "grad_norm": 2.4804628992569633e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034266133637921186, | |
| "grad_norm": 3.536332951625809e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034266133637921186, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 2.0599, | |
| "eval_samples_per_second": 179.137, | |
| "eval_steps_per_second": 89.811, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004568817818389492, | |
| "grad_norm": 3.0596766009693965e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0057110222729868645, | |
| "grad_norm": 3.4058648452628404e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006853226727584237, | |
| "grad_norm": 2.799735557346139e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006853226727584237, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 2.1111, | |
| "eval_samples_per_second": 174.791, | |
| "eval_steps_per_second": 87.632, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00799543118218161, | |
| "grad_norm": 3.5134296922478825e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009137635636778984, | |
| "grad_norm": 4.129979060962796e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010279840091376356, | |
| "grad_norm": 3.466810812824406e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010279840091376356, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 2.1322, | |
| "eval_samples_per_second": 173.063, | |
| "eval_steps_per_second": 86.766, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011422044545973729, | |
| "grad_norm": 4.669372719945386e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 224132382720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |