| { | |
| "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": 0.3489128649234772, | |
| "eval_mse": 0.34891289472579956, | |
| "eval_runtime": 4.7891, | |
| "eval_samples_per_second": 208.807, | |
| "eval_steps_per_second": 26.101, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.331812181114852e-05, | |
| "loss": 0.3355, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.23772406578063965, | |
| "eval_mse": 0.23772406578063965, | |
| "eval_runtime": 4.8126, | |
| "eval_samples_per_second": 207.789, | |
| "eval_steps_per_second": 25.974, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.2444075644016266, | |
| "eval_mse": 0.2444075644016266, | |
| "eval_runtime": 4.8651, | |
| "eval_samples_per_second": 205.548, | |
| "eval_steps_per_second": 25.693, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.9544766252686105e-05, | |
| "loss": 0.1182, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.3121347725391388, | |
| "eval_mse": 0.3121347725391388, | |
| "eval_runtime": 4.9119, | |
| "eval_samples_per_second": 203.588, | |
| "eval_steps_per_second": 25.448, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 3.577141069422369e-05, | |
| "loss": 0.0651, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.22353506088256836, | |
| "eval_mse": 0.22353507578372955, | |
| "eval_runtime": 4.9339, | |
| "eval_samples_per_second": 202.678, | |
| "eval_steps_per_second": 25.335, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.19977863132953644, | |
| "eval_mse": 0.19977861642837524, | |
| "eval_runtime": 4.7835, | |
| "eval_samples_per_second": 209.051, | |
| "eval_steps_per_second": 26.131, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 3.199805513576128e-05, | |
| "loss": 0.0498, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.2336214929819107, | |
| "eval_mse": 0.2336214929819107, | |
| "eval_runtime": 4.7754, | |
| "eval_samples_per_second": 209.407, | |
| "eval_steps_per_second": 26.176, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.21180056035518646, | |
| "eval_mse": 0.21180060505867004, | |
| "eval_runtime": 4.9099, | |
| "eval_samples_per_second": 203.671, | |
| "eval_steps_per_second": 25.459, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 2.822469957729886e-05, | |
| "loss": 0.0358, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.22979474067687988, | |
| "eval_mse": 0.22979475557804108, | |
| "eval_runtime": 4.8765, | |
| "eval_samples_per_second": 205.065, | |
| "eval_steps_per_second": 25.633, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 2.445134401883645e-05, | |
| "loss": 0.0279, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.2303524762392044, | |
| "eval_mse": 0.2303524762392044, | |
| "eval_runtime": 4.9464, | |
| "eval_samples_per_second": 202.165, | |
| "eval_steps_per_second": 25.271, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.21912191808223724, | |
| "eval_mse": 0.21912193298339844, | |
| "eval_runtime": 4.8937, | |
| "eval_samples_per_second": 204.345, | |
| "eval_steps_per_second": 25.543, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 2.0677988460374033e-05, | |
| "loss": 0.0236, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.20294061303138733, | |
| "eval_mse": 0.20294061303138733, | |
| "eval_runtime": 4.6751, | |
| "eval_samples_per_second": 213.901, | |
| "eval_steps_per_second": 26.738, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 1.6904632901911617e-05, | |
| "loss": 0.0195, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.21014319360256195, | |
| "eval_mse": 0.21014319360256195, | |
| "eval_runtime": 4.8248, | |
| "eval_samples_per_second": 207.262, | |
| "eval_steps_per_second": 25.908, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.2216099053621292, | |
| "eval_mse": 0.2216099053621292, | |
| "eval_runtime": 4.7789, | |
| "eval_samples_per_second": 209.252, | |
| "eval_steps_per_second": 26.157, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 1.3131277343449203e-05, | |
| "loss": 0.0156, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.21098460257053375, | |
| "eval_mse": 0.21098460257053375, | |
| "eval_runtime": 4.7959, | |
| "eval_samples_per_second": 208.509, | |
| "eval_steps_per_second": 26.064, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.21815571188926697, | |
| "eval_mse": 0.21815571188926697, | |
| "eval_runtime": 4.9214, | |
| "eval_samples_per_second": 203.196, | |
| "eval_steps_per_second": 25.4, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 9.357921784986788e-06, | |
| "loss": 0.0127, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.21420633792877197, | |
| "eval_mse": 0.21420633792877197, | |
| "eval_runtime": 4.7835, | |
| "eval_samples_per_second": 209.054, | |
| "eval_steps_per_second": 26.132, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 5.5845662265243735e-06, | |
| "loss": 0.0109, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.2126861810684204, | |
| "eval_mse": 0.2126861810684204, | |
| "eval_runtime": 4.8516, | |
| "eval_samples_per_second": 206.117, | |
| "eval_steps_per_second": 25.765, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.21384698152542114, | |
| "eval_mse": 0.21384698152542114, | |
| "eval_runtime": 4.9235, | |
| "eval_samples_per_second": 203.109, | |
| "eval_steps_per_second": 25.389, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 1.8112106680619593e-06, | |
| "loss": 0.0094, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.2143700271844864, | |
| "eval_mse": 0.2143700271844864, | |
| "eval_runtime": 4.7927, | |
| "eval_samples_per_second": 208.649, | |
| "eval_steps_per_second": 26.081, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 6240, | |
| "total_flos": 6577191107414016.0, | |
| "train_loss": 0.05834093816005267, | |
| "train_runtime": 2383.5567, | |
| "train_samples_per_second": 41.954, | |
| "train_steps_per_second": 2.618 | |
| } | |
| ], | |
| "max_steps": 6240, | |
| "num_train_epochs": 20, | |
| "total_flos": 6577191107414016.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |