| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.977715877437326, | |
| "eval_steps": 500, | |
| "global_step": 1790, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2e-05, | |
| "loss": 95.476, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2e-05, | |
| "loss": 48.4218, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 13.7763, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2e-05, | |
| "loss": 1.648, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4463, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9103, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6693, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8188, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7446, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6158, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9035, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9486, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7198, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5337, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3312, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8632, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8279, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9823, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7963, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7861, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9859, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0639, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7174, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7996, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7602, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8562, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1248, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5689, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7794, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9319, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0026, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5143, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8727, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7792, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7502, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7851, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3474, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5022, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9111, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2783, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1359, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 2e-05, | |
| "loss": 1.839, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7254, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 2e-05, | |
| "loss": 1.331, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6719, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8933, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7205, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7708, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8574, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7874, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7614, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.788, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5983, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7172, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7758, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7793, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 2e-05, | |
| "loss": 0.958, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9366, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.876, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9187, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6457, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6107, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2681, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2e-05, | |
| "loss": 0.824, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7997, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6423, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7917, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6285, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7219, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3192, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9599, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0558, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 2e-05, | |
| "loss": 0.829, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6611, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9619, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 2e-05, | |
| "loss": 0.838, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6923, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7675, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 2e-05, | |
| "loss": 1.038, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5607, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8019, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7824, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.55, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 2e-05, | |
| "loss": 0.625, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8339, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5907, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9135, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3289, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1937, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "step": 1790, | |
| "total_flos": 4485735925153792.0, | |
| "train_loss": 0.6437026796394221, | |
| "train_runtime": 3731.8169, | |
| "train_samples_per_second": 15.389, | |
| "train_steps_per_second": 0.48 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 1790, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 4485735925153792.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |