| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.945945945945946, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4805, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5187, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.9957341762950346e-05, | |
| "loss": 0.4365, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.982973099683902e-05, | |
| "loss": 0.4007, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.961825643172819e-05, | |
| "loss": 0.3944, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.932472229404356e-05, | |
| "loss": 0.3724, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.8951632913550625e-05, | |
| "loss": 0.3217, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.8502171357296144e-05, | |
| "loss": 0.3093, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.7980172272802398e-05, | |
| "loss": 0.3106, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.7390089172206594e-05, | |
| "loss": 0.306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.6736956436465573e-05, | |
| "loss": 0.313, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.6026346363792565e-05, | |
| "loss": 0.3213, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.526432162877356e-05, | |
| "loss": 0.2503, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.4457383557765385e-05, | |
| "loss": 0.271, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.3612416661871532e-05, | |
| "loss": 0.2319, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.2736629900720832e-05, | |
| "loss": 0.2549, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.1837495178165706e-05, | |
| "loss": 0.2571, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.092268359463302e-05, | |
| "loss": 0.2518, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2384, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.07731640536698e-06, | |
| "loss": 0.1869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 8.162504821834296e-06, | |
| "loss": 0.2296, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 7.263370099279173e-06, | |
| "loss": 0.2035, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.387583338128471e-06, | |
| "loss": 0.1887, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 5.542616442234618e-06, | |
| "loss": 0.19, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.7356783712264405e-06, | |
| "loss": 0.187, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.973653636207437e-06, | |
| "loss": 0.1957, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 3.2630435635344283e-06, | |
| "loss": 0.1932, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.6099108277934105e-06, | |
| "loss": 0.2026, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.019827727197605e-06, | |
| "loss": 0.1922, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.4978286427038602e-06, | |
| "loss": 0.1889, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 1.0483670864493777e-06, | |
| "loss": 0.2075, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 6.752777059564431e-07, | |
| "loss": 0.1633, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.817435682718096e-07, | |
| "loss": 0.158, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.7026900316098217e-07, | |
| "loss": 0.1605, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.2658237049655325e-08, | |
| "loss": 0.1666, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0, | |
| "loss": 0.1882, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "step": 36, | |
| "total_flos": 1.8313009197744128e+17, | |
| "train_loss": 0.26231372563375366, | |
| "train_runtime": 5201.7559, | |
| "train_samples_per_second": 0.899, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "max_steps": 36, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.8313009197744128e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |