| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.88, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 10.592474836534368, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.7036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 7.189941789922346, | |
| "learning_rate": 4.578674030756364e-06, | |
| "loss": 1.6651, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.845848560333252, | |
| "eval_runtime": 5.483, | |
| "eval_samples_per_second": 10.943, | |
| "eval_steps_per_second": 0.73, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 5.93037457835698, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.4257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.8387283086776733, | |
| "eval_runtime": 5.3207, | |
| "eval_samples_per_second": 11.277, | |
| "eval_steps_per_second": 0.752, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 6.061518818483694, | |
| "learning_rate": 4.2132596924363666e-07, | |
| "loss": 1.1921, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 1.8483096361160278, | |
| "eval_runtime": 5.3166, | |
| "eval_samples_per_second": 11.285, | |
| "eval_steps_per_second": 0.752, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "step": 18, | |
| "total_flos": 3716488888320.0, | |
| "train_loss": 1.3722783128420513, | |
| "train_runtime": 323.7392, | |
| "train_samples_per_second": 3.614, | |
| "train_steps_per_second": 0.056 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3716488888320.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |