| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.061208875286916604, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01224177505738332, | |
| "grad_norm": 0.011717167682945728, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9278, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01224177505738332, | |
| "eval_loss": 11.928644180297852, | |
| "eval_runtime": 11.5494, | |
| "eval_samples_per_second": 11.949, | |
| "eval_steps_per_second": 5.974, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02448355011476664, | |
| "grad_norm": 0.010304996743798256, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9219, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02448355011476664, | |
| "eval_loss": 11.928644180297852, | |
| "eval_runtime": 0.6024, | |
| "eval_samples_per_second": 229.091, | |
| "eval_steps_per_second": 114.545, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.036725325172149964, | |
| "grad_norm": 0.012828883714973927, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9263, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04896710022953328, | |
| "grad_norm": 0.015544447116553783, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04896710022953328, | |
| "eval_loss": 11.928632736206055, | |
| "eval_runtime": 0.601, | |
| "eval_samples_per_second": 229.62, | |
| "eval_steps_per_second": 114.81, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.061208875286916604, | |
| "grad_norm": 0.013846633024513721, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9278, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3308519424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |