| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.9984, | |
| "global_step": 6240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.2721790075302124, | |
| "eval_mse": 0.2721790075302124, | |
| "eval_runtime": 13.7261, | |
| "eval_samples_per_second": 72.854, | |
| "eval_steps_per_second": 9.107, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.4640443499072686e-05, | |
| "loss": 0.2992, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.24081240594387054, | |
| "eval_mse": 0.24081240594387054, | |
| "eval_runtime": 13.7912, | |
| "eval_samples_per_second": 72.51, | |
| "eval_steps_per_second": 9.064, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.22090023756027222, | |
| "eval_mse": 0.22090023756027222, | |
| "eval_runtime": 13.7775, | |
| "eval_samples_per_second": 72.582, | |
| "eval_steps_per_second": 9.073, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.1622983263961825e-05, | |
| "loss": 0.1095, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.18391327559947968, | |
| "eval_mse": 0.18391327559947968, | |
| "eval_runtime": 13.7422, | |
| "eval_samples_per_second": 72.769, | |
| "eval_steps_per_second": 9.096, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 2.860552302885096e-05, | |
| "loss": 0.0676, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.1835608184337616, | |
| "eval_mse": 0.1835608184337616, | |
| "eval_runtime": 13.7549, | |
| "eval_samples_per_second": 72.702, | |
| "eval_steps_per_second": 9.088, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.1830635964870453, | |
| "eval_mse": 0.1830635964870453, | |
| "eval_runtime": 13.799, | |
| "eval_samples_per_second": 72.469, | |
| "eval_steps_per_second": 9.059, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 2.5588062793740103e-05, | |
| "loss": 0.0507, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.18448784947395325, | |
| "eval_mse": 0.18448786437511444, | |
| "eval_runtime": 13.7961, | |
| "eval_samples_per_second": 72.484, | |
| "eval_steps_per_second": 9.061, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.18527822196483612, | |
| "eval_mse": 0.18527822196483612, | |
| "eval_runtime": 13.7973, | |
| "eval_samples_per_second": 72.478, | |
| "eval_steps_per_second": 9.06, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 2.257060255862924e-05, | |
| "loss": 0.0402, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.18943239748477936, | |
| "eval_mse": 0.18943239748477936, | |
| "eval_runtime": 13.7202, | |
| "eval_samples_per_second": 72.885, | |
| "eval_steps_per_second": 9.111, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 1.9553142323518382e-05, | |
| "loss": 0.0327, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.17714717984199524, | |
| "eval_mse": 0.17714717984199524, | |
| "eval_runtime": 13.7644, | |
| "eval_samples_per_second": 72.651, | |
| "eval_steps_per_second": 9.081, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.18594859540462494, | |
| "eval_mse": 0.18594858050346375, | |
| "eval_runtime": 13.6617, | |
| "eval_samples_per_second": 73.197, | |
| "eval_steps_per_second": 9.15, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 1.6535682088407518e-05, | |
| "loss": 0.0268, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.18873579800128937, | |
| "eval_mse": 0.18873581290245056, | |
| "eval_runtime": 13.705, | |
| "eval_samples_per_second": 72.966, | |
| "eval_steps_per_second": 9.121, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 1.3518221853296657e-05, | |
| "loss": 0.0211, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.19864311814308167, | |
| "eval_mse": 0.19864313304424286, | |
| "eval_runtime": 13.7757, | |
| "eval_samples_per_second": 72.592, | |
| "eval_steps_per_second": 9.074, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.17751657962799072, | |
| "eval_mse": 0.17751657962799072, | |
| "eval_runtime": 13.7818, | |
| "eval_samples_per_second": 72.56, | |
| "eval_steps_per_second": 9.07, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 1.0500761618185796e-05, | |
| "loss": 0.0161, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.1854146122932434, | |
| "eval_mse": 0.1854146122932434, | |
| "eval_runtime": 13.8239, | |
| "eval_samples_per_second": 72.339, | |
| "eval_steps_per_second": 9.042, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.1844572126865387, | |
| "eval_mse": 0.1844572275876999, | |
| "eval_runtime": 13.7435, | |
| "eval_samples_per_second": 72.762, | |
| "eval_steps_per_second": 9.095, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 7.483301383074935e-06, | |
| "loss": 0.0126, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.18561576306819916, | |
| "eval_mse": 0.18561576306819916, | |
| "eval_runtime": 13.7414, | |
| "eval_samples_per_second": 72.773, | |
| "eval_steps_per_second": 9.097, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 4.465841147964074e-06, | |
| "loss": 0.01, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.17724011838436127, | |
| "eval_mse": 0.17724011838436127, | |
| "eval_runtime": 13.7177, | |
| "eval_samples_per_second": 72.898, | |
| "eval_steps_per_second": 9.112, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.18078790605068207, | |
| "eval_mse": 0.18078790605068207, | |
| "eval_runtime": 13.8059, | |
| "eval_samples_per_second": 72.433, | |
| "eval_steps_per_second": 9.054, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 1.4483809128532133e-06, | |
| "loss": 0.008, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.18189798295497894, | |
| "eval_mse": 0.18189798295497894, | |
| "eval_runtime": 13.7884, | |
| "eval_samples_per_second": 72.524, | |
| "eval_steps_per_second": 9.066, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 6240, | |
| "total_flos": 2.3296341506770944e+16, | |
| "train_loss": 0.05592835318201628, | |
| "train_runtime": 6478.1274, | |
| "train_samples_per_second": 15.437, | |
| "train_steps_per_second": 0.963 | |
| } | |
| ], | |
| "max_steps": 6240, | |
| "num_train_epochs": 20, | |
| "total_flos": 2.3296341506770944e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |