| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 18.0, |
| "eval_steps": 500, |
| "global_step": 774, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.0032397201284766197, |
| "eval_runtime": 0.161, |
| "eval_samples_per_second": 186.377, |
| "eval_steps_per_second": 12.425, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.001469723880290985, |
| "eval_runtime": 0.1562, |
| "eval_samples_per_second": 192.018, |
| "eval_steps_per_second": 12.801, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.0005289791151881218, |
| "eval_runtime": 0.1567, |
| "eval_samples_per_second": 191.456, |
| "eval_steps_per_second": 12.764, |
| "step": 129 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 7.859647303121164e-05, |
| "eval_runtime": 0.1557, |
| "eval_samples_per_second": 192.637, |
| "eval_steps_per_second": 12.842, |
| "step": 172 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 6.687522545689717e-05, |
| "eval_runtime": 0.1565, |
| "eval_samples_per_second": 191.718, |
| "eval_steps_per_second": 12.781, |
| "step": 215 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 4.788968726643361e-05, |
| "eval_runtime": 0.1567, |
| "eval_samples_per_second": 191.395, |
| "eval_steps_per_second": 12.76, |
| "step": 258 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 4.127044667256996e-05, |
| "eval_runtime": 0.1567, |
| "eval_samples_per_second": 191.404, |
| "eval_steps_per_second": 12.76, |
| "step": 301 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 2.980121280415915e-05, |
| "eval_runtime": 0.1566, |
| "eval_samples_per_second": 191.556, |
| "eval_steps_per_second": 12.77, |
| "step": 344 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 2.245928772026673e-05, |
| "eval_runtime": 0.1565, |
| "eval_samples_per_second": 191.743, |
| "eval_steps_per_second": 12.783, |
| "step": 387 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 1.9881872503901832e-05, |
| "eval_runtime": 0.1561, |
| "eval_samples_per_second": 192.133, |
| "eval_steps_per_second": 12.809, |
| "step": 430 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 1.6299421986332163e-05, |
| "eval_runtime": 0.1568, |
| "eval_samples_per_second": 191.35, |
| "eval_steps_per_second": 12.757, |
| "step": 473 |
| }, |
| { |
| "epoch": 11.627906976744185, |
| "grad_norm": 0.014970483258366585, |
| "learning_rate": 1.7700258397932818e-05, |
| "loss": 0.0425, |
| "step": 500 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 1.5209545381367207e-05, |
| "eval_runtime": 0.1563, |
| "eval_samples_per_second": 191.949, |
| "eval_steps_per_second": 12.797, |
| "step": 516 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 1.3919359844294377e-05, |
| "eval_runtime": 0.1565, |
| "eval_samples_per_second": 191.656, |
| "eval_steps_per_second": 12.777, |
| "step": 559 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 1.3256098100100644e-05, |
| "eval_runtime": 0.1565, |
| "eval_samples_per_second": 191.7, |
| "eval_steps_per_second": 12.78, |
| "step": 602 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 1.3537169252231251e-05, |
| "eval_runtime": 0.1566, |
| "eval_samples_per_second": 191.56, |
| "eval_steps_per_second": 12.771, |
| "step": 645 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 1.2793268979294226e-05, |
| "eval_runtime": 0.156, |
| "eval_samples_per_second": 192.252, |
| "eval_steps_per_second": 12.817, |
| "step": 688 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 1.2600863556144759e-05, |
| "eval_runtime": 0.1563, |
| "eval_samples_per_second": 191.996, |
| "eval_steps_per_second": 12.8, |
| "step": 731 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 1.2519586562120821e-05, |
| "eval_runtime": 0.1564, |
| "eval_samples_per_second": 191.866, |
| "eval_steps_per_second": 12.791, |
| "step": 774 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 774, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 18, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1992913412984592.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
