| { | |
| "best_metric": 1.093778133392334, | |
| "best_model_checkpoint": "output_dir/checkpoint-36", | |
| "epoch": 1.083725305738476, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 1.1282, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 1.1856, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8e-06, | |
| "loss": 1.1748, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.1748, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.1107146739959717, | |
| "eval_runtime": 9.0527, | |
| "eval_samples_per_second": 1.215, | |
| "eval_steps_per_second": 0.221, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3e-06, | |
| "loss": 1.1506, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.6e-06, | |
| "loss": 1.1282, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 1.1833, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.1521, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.1096446514129639, | |
| "eval_runtime": 9.0523, | |
| "eval_samples_per_second": 1.215, | |
| "eval_steps_per_second": 0.221, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5.4e-06, | |
| "loss": 1.1579, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6e-06, | |
| "loss": 1.1198, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.6e-06, | |
| "loss": 1.2155, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.2e-06, | |
| "loss": 1.1188, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.1087640523910522, | |
| "eval_runtime": 9.0422, | |
| "eval_samples_per_second": 1.217, | |
| "eval_steps_per_second": 0.221, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.8e-06, | |
| "loss": 1.1327, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 1.1311, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9e-06, | |
| "loss": 1.1268, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.1316, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.1073920726776123, | |
| "eval_runtime": 9.0556, | |
| "eval_samples_per_second": 1.215, | |
| "eval_steps_per_second": 0.221, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.02e-05, | |
| "loss": 1.1142, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.08e-05, | |
| "loss": 1.1369, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.1400000000000001e-05, | |
| "loss": 1.139, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.1231, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.1051356792449951, | |
| "eval_runtime": 9.0525, | |
| "eval_samples_per_second": 1.215, | |
| "eval_steps_per_second": 0.221, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.26e-05, | |
| "loss": 1.1243, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.32e-05, | |
| "loss": 1.1161, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.3800000000000002e-05, | |
| "loss": 1.1153, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.44e-05, | |
| "loss": 1.1217, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.1019339561462402, | |
| "eval_runtime": 9.0337, | |
| "eval_samples_per_second": 1.218, | |
| "eval_steps_per_second": 0.221, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.1115, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.56e-05, | |
| "loss": 1.1215, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.62e-05, | |
| "loss": 1.1057, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 1.1184, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.0975638628005981, | |
| "eval_runtime": 9.0363, | |
| "eval_samples_per_second": 1.217, | |
| "eval_steps_per_second": 0.221, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.74e-05, | |
| "loss": 1.117, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.1143, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.86e-05, | |
| "loss": 1.1195, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.1062, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.0937966108322144, | |
| "eval_runtime": 9.0438, | |
| "eval_samples_per_second": 1.216, | |
| "eval_steps_per_second": 0.221, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.98e-05, | |
| "loss": 1.1314, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.04e-05, | |
| "loss": 1.1049, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.1e-05, | |
| "loss": 1.1067, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.16e-05, | |
| "loss": 1.1027, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.093778133392334, | |
| "eval_runtime": 9.0523, | |
| "eval_samples_per_second": 1.215, | |
| "eval_steps_per_second": 0.221, | |
| "step": 36 | |
| } | |
| ], | |
| "max_steps": 99, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.8344233538578022e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |