| { |
| "best_metric": 0.6673863530158997, |
| "best_model_checkpoint": "output/queen/checkpoint-136", |
| "epoch": 2.0, |
| "global_step": 136, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00013537785052914348, |
| "loss": 0.8946, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0001300082017869573, |
| "loss": 1.1571, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00012137631040942562, |
| "loss": 1.0891, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00010994073605561692, |
| "loss": 1.0026, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 9.63089809342121e-05, |
| "loss": 0.8956, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 8.120521692221655e-05, |
| "loss": 1.0037, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 6.543181473690228e-05, |
| "loss": 0.9259, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 4.982671888105533e-05, |
| "loss": 0.9391, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 3.52189327703136e-05, |
| "loss": 0.897, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 2.2384478845846266e-05, |
| "loss": 0.969, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 1.2005173242556645e-05, |
| "loss": 0.9795, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 4.632405062861206e-06, |
| "loss": 1.0966, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 6.578444419609618e-07, |
| "loss": 0.9097, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.9767317771911621, |
| "eval_runtime": 2.0747, |
| "eval_samples_per_second": 46.272, |
| "eval_steps_per_second": 5.784, |
| "step": 68 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.7435600757598877, |
| "eval_runtime": 1.811, |
| "eval_samples_per_second": 48.039, |
| "eval_steps_per_second": 6.074, |
| "step": 69 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 2.926355061606355e-07, |
| "loss": 1.3103, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 3.5561795752596966e-06, |
| "loss": 0.9826, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 1.027510448894829e-05, |
| "loss": 0.9993, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 2.0092474810602806e-05, |
| "loss": 0.8551, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 3.2486753626613595e-05, |
| "loss": 1.0815, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 4.6799508616681124e-05, |
| "loss": 0.8781, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 6.227039054081734e-05, |
| "loss": 0.9205, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 7.807752594969924e-05, |
| "loss": 0.7833, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 9.338117830043863e-05, |
| "loss": 1.083, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 0.00010736835802938959, |
| "loss": 1.0006, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 0.00011929601172133724, |
| "loss": 1.0609, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.00012853049599834086, |
| "loss": 0.9702, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.00013458123912165544, |
| "loss": 1.0468, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 0.00013712680207144277, |
| "loss": 1.0231, |
| "step": 135 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.6673863530158997, |
| "eval_runtime": 2.2427, |
| "eval_samples_per_second": 42.36, |
| "eval_steps_per_second": 5.351, |
| "step": 136 |
| } |
| ], |
| "max_steps": 136, |
| "num_train_epochs": 2, |
| "total_flos": 139660591104000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
