| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.184896900177523, | |
| "global_step": 48000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.1748, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0, | |
| "loss": 0.1589, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0, | |
| "loss": 0.1687, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0, | |
| "loss": 0.1555, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0, | |
| "loss": 0.1682, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.1689, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0, | |
| "loss": 0.181, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0, | |
| "loss": 0.1665, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0, | |
| "loss": 0.1844, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0, | |
| "loss": 0.1766, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.1633, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0, | |
| "loss": 0.1734, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0, | |
| "loss": 0.1744, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0, | |
| "loss": 0.1907, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0, | |
| "loss": 0.1611, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0, | |
| "loss": 0.1562, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0, | |
| "loss": 0.1617, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0, | |
| "loss": 0.1815, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0, | |
| "loss": 0.1606, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0, | |
| "loss": 0.1529, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0, | |
| "loss": 0.1671, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0, | |
| "loss": 0.1657, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0, | |
| "loss": 0.1585, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0, | |
| "loss": 0.1605, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0, | |
| "loss": 0.1576, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0, | |
| "loss": 0.1728, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0, | |
| "loss": 0.1747, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0, | |
| "loss": 0.1813, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0, | |
| "loss": 0.1624, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0, | |
| "loss": 0.1552, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0, | |
| "loss": 0.1734, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0, | |
| "loss": 0.1718, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0, | |
| "loss": 0.1636, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0, | |
| "loss": 0.1717, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0, | |
| "loss": 0.1693, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0, | |
| "loss": 0.1829, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0, | |
| "loss": 0.1595, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0, | |
| "loss": 0.1541, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0, | |
| "loss": 0.1601, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.1694, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0, | |
| "loss": 0.1701, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0, | |
| "loss": 0.1722, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0, | |
| "loss": 0.1576, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 51.4928, | |
| "eval_gen_len": 10.36, | |
| "eval_loss": 0.14327587187290192, | |
| "eval_runtime": 1372.0451, | |
| "eval_samples_per_second": 5.057, | |
| "eval_steps_per_second": 1.686, | |
| "step": 21969 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.177, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.1711, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0, | |
| "loss": 0.1725, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0, | |
| "loss": 0.1864, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0, | |
| "loss": 0.1573, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.165, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.1863, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0, | |
| "loss": 0.1751, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0, | |
| "loss": 0.1746, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0, | |
| "loss": 0.1685, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0, | |
| "loss": 0.175, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.1627, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0, | |
| "loss": 0.1504, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0, | |
| "loss": 0.1495, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0, | |
| "loss": 0.1744, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0, | |
| "loss": 0.1668, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0, | |
| "loss": 0.1571, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0, | |
| "loss": 0.1643, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0, | |
| "loss": 0.1653, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0, | |
| "loss": 0.1646, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0, | |
| "loss": 0.179, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0, | |
| "loss": 0.1783, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0, | |
| "loss": 0.1625, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0, | |
| "loss": 0.1576, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0, | |
| "loss": 0.1631, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0, | |
| "loss": 0.1681, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0, | |
| "loss": 0.1646, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0, | |
| "loss": 0.1714, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0, | |
| "loss": 0.174, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0, | |
| "loss": 0.1548, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0, | |
| "loss": 0.1722, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0, | |
| "loss": 0.1718, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0, | |
| "loss": 0.1723, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0, | |
| "loss": 0.1668, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0, | |
| "loss": 0.1584, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0, | |
| "loss": 0.1676, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0, | |
| "loss": 0.1732, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0, | |
| "loss": 0.1749, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0, | |
| "loss": 0.1652, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0, | |
| "loss": 0.1763, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.1599, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0, | |
| "loss": 0.1575, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0, | |
| "loss": 0.171, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0, | |
| "loss": 0.1668, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 51.4928, | |
| "eval_gen_len": 10.36, | |
| "eval_loss": 0.14327587187290192, | |
| "eval_runtime": 1365.3738, | |
| "eval_samples_per_second": 5.081, | |
| "eval_steps_per_second": 1.694, | |
| "step": 43938 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1646, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0, | |
| "loss": 0.1607, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0, | |
| "loss": 0.1772, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0, | |
| "loss": 0.1794, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0, | |
| "loss": 0.1545, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.1701, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.1616, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0, | |
| "loss": 0.1557, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0, | |
| "loss": 0.1677, | |
| "step": 48000 | |
| } | |
| ], | |
| "max_steps": 65907, | |
| "num_train_epochs": 3, | |
| "total_flos": 6.441712416646042e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |