| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3235, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3318, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.9957341762950346e-05, | |
| "loss": 0.1817, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.982973099683902e-05, | |
| "loss": 0.3706, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.961825643172819e-05, | |
| "loss": 0.226, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.932472229404356e-05, | |
| "loss": 0.2469, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.8951632913550625e-05, | |
| "loss": 0.205, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.8502171357296144e-05, | |
| "loss": 0.1897, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.7980172272802398e-05, | |
| "loss": 0.1877, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.7390089172206594e-05, | |
| "loss": 0.1749, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.6736956436465573e-05, | |
| "loss": 0.1953, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6026346363792565e-05, | |
| "loss": 0.1823, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.526432162877356e-05, | |
| "loss": 0.1802, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.4457383557765385e-05, | |
| "loss": 0.1737, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.3612416661871532e-05, | |
| "loss": 0.1664, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.2736629900720832e-05, | |
| "loss": 0.1587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.1837495178165706e-05, | |
| "loss": 0.1749, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.092268359463302e-05, | |
| "loss": 0.1735, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1592, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 9.07731640536698e-06, | |
| "loss": 0.1638, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 8.162504821834296e-06, | |
| "loss": 0.1553, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 7.263370099279173e-06, | |
| "loss": 0.1475, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 6.387583338128471e-06, | |
| "loss": 0.1499, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5.542616442234618e-06, | |
| "loss": 0.1455, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 4.7356783712264405e-06, | |
| "loss": 0.1354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 3.973653636207437e-06, | |
| "loss": 0.1481, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.2630435635344283e-06, | |
| "loss": 0.1273, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.6099108277934105e-06, | |
| "loss": 0.1226, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.019827727197605e-06, | |
| "loss": 0.1122, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.4978286427038602e-06, | |
| "loss": 0.1125, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 1.0483670864493777e-06, | |
| "loss": 0.1077, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 6.752777059564431e-07, | |
| "loss": 0.1143, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 3.817435682718096e-07, | |
| "loss": 0.1218, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 1.7026900316098217e-07, | |
| "loss": 0.108, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 4.2658237049655325e-08, | |
| "loss": 0.1063, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1127, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 36, | |
| "total_flos": 853961342976.0, | |
| "train_loss": 0.1720208062065972, | |
| "train_runtime": 419.0995, | |
| "train_samples_per_second": 4.81, | |
| "train_steps_per_second": 0.086 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 111, | |
| "total_flos": 853961342976.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |