| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6261, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 1.6416, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 1.5057, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 1.4117, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 1.3346, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 1.2955, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 1.2537, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2431, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 1.2217, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 1.2118, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 1.2114, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.181685175319702e-05, | |
| "loss": 1.195, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 1.1987, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.5072087818176382e-06, | |
| "loss": 1.1865, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.1638, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 15, | |
| "total_flos": 9719654252544.0, | |
| "train_loss": 1.3133884429931642, | |
| "train_runtime": 333.4396, | |
| "train_samples_per_second": 5.575, | |
| "train_steps_per_second": 0.045 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50000, | |
| "total_flos": 9719654252544.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |