| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.12, |
| "eval_steps": 100, |
| "global_step": 1400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "learning_rate": 2.460393662986078e-05, |
| "loss": 1.8265, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_loss": 1.7948205471038818, |
| "eval_runtime": 2217.6297, |
| "eval_samples_per_second": 9.019, |
| "eval_steps_per_second": 1.127, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 2.420387261961914e-05, |
| "loss": 1.791, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_loss": 1.7855218648910522, |
| "eval_runtime": 2218.3372, |
| "eval_samples_per_second": 9.016, |
| "eval_steps_per_second": 1.127, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 2.38038086093775e-05, |
| "loss": 1.7848, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_loss": 1.7765330076217651, |
| "eval_runtime": 2217.7749, |
| "eval_samples_per_second": 9.018, |
| "eval_steps_per_second": 1.127, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 2.340374459913586e-05, |
| "loss": 1.7843, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_loss": 1.7692365646362305, |
| "eval_runtime": 2218.7844, |
| "eval_samples_per_second": 9.014, |
| "eval_steps_per_second": 1.127, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 2.3003680588894225e-05, |
| "loss": 1.7736, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 1.7632160186767578, |
| "eval_runtime": 2217.4605, |
| "eval_samples_per_second": 9.019, |
| "eval_steps_per_second": 1.127, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 2.2603616578652586e-05, |
| "loss": 1.7612, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_loss": 1.757413625717163, |
| "eval_runtime": 2218.4914, |
| "eval_samples_per_second": 9.015, |
| "eval_steps_per_second": 1.127, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 2.2203552568410947e-05, |
| "loss": 1.7632, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_loss": 1.7510673999786377, |
| "eval_runtime": 2217.7554, |
| "eval_samples_per_second": 9.018, |
| "eval_steps_per_second": 1.127, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 2.1803488558169307e-05, |
| "loss": 1.7579, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_loss": 1.7483996152877808, |
| "eval_runtime": 2217.6281, |
| "eval_samples_per_second": 9.019, |
| "eval_steps_per_second": 1.127, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 2.1403424547927668e-05, |
| "loss": 1.7482, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_loss": 1.7426660060882568, |
| "eval_runtime": 2217.5916, |
| "eval_samples_per_second": 9.019, |
| "eval_steps_per_second": 1.127, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 2.1003360537686032e-05, |
| "loss": 1.7484, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 1.738135576248169, |
| "eval_runtime": 2217.1723, |
| "eval_samples_per_second": 9.02, |
| "eval_steps_per_second": 1.128, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 2.0603296527444393e-05, |
| "loss": 1.7448, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_loss": 1.7337851524353027, |
| "eval_runtime": 2217.4606, |
| "eval_samples_per_second": 9.019, |
| "eval_steps_per_second": 1.127, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 2.0203232517202754e-05, |
| "loss": 1.7351, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_loss": 1.7301291227340698, |
| "eval_runtime": 2216.9509, |
| "eval_samples_per_second": 9.021, |
| "eval_steps_per_second": 1.128, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 1.9803168506961114e-05, |
| "loss": 1.6193, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.04, |
| "eval_loss": 1.747913122177124, |
| "eval_runtime": 2217.695, |
| "eval_samples_per_second": 9.018, |
| "eval_steps_per_second": 1.127, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 1.9403104496719475e-05, |
| "loss": 1.4984, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_loss": 1.7492424249649048, |
| "eval_runtime": 2223.4607, |
| "eval_samples_per_second": 8.995, |
| "eval_steps_per_second": 1.124, |
| "step": 1400 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 6250, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 100, |
| "total_flos": 3.381415454441472e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
