|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 9.796875, |
|
"global_step": 12540, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0001, |
|
"loss": 10.386, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0001, |
|
"loss": 7.4061, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0001, |
|
"loss": 6.4112, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0001, |
|
"loss": 6.091, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0001, |
|
"loss": 5.8571, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.0001, |
|
"loss": 5.7144, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.0001, |
|
"loss": 5.6228, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.0001, |
|
"loss": 5.546, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.0001, |
|
"loss": 5.4904, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.0001, |
|
"loss": 5.4413, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.0001, |
|
"loss": 5.3603, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.0001, |
|
"loss": 5.3346, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.0001, |
|
"loss": 5.2744, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.0001, |
|
"loss": 5.231, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0001, |
|
"loss": 5.1782, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.0001, |
|
"loss": 5.1613, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 0.0001, |
|
"loss": 5.1091, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 0.0001, |
|
"loss": 5.0939, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 0.0001, |
|
"loss": 5.0667, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.0001, |
|
"loss": 5.0054, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.0001, |
|
"loss": 4.96, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.0001, |
|
"loss": 4.9301, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.0001, |
|
"loss": 4.9302, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.0001, |
|
"loss": 4.9129, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.0001, |
|
"loss": 4.8627, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 0.0001, |
|
"loss": 4.8336, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 0.0001, |
|
"loss": 4.8018, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.0001, |
|
"loss": 4.7479, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 0.0001, |
|
"loss": 4.7572, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 0.0001, |
|
"loss": 4.759, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 0.0001, |
|
"loss": 4.7441, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 0.0001, |
|
"loss": 4.7195, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 0.0001, |
|
"loss": 4.6821, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 0.0001, |
|
"loss": 4.6587, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 0.0001, |
|
"loss": 4.6228, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 0.0001, |
|
"loss": 4.6248, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 0.0001, |
|
"loss": 4.5801, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 0.0001, |
|
"loss": 4.5934, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 0.0001, |
|
"loss": 4.5781, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 0.0001, |
|
"loss": 4.5763, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 0.0001, |
|
"loss": 4.5598, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 0.0001, |
|
"loss": 4.4796, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 0.0001, |
|
"loss": 4.5204, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 0.0001, |
|
"loss": 4.4858, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 0.0001, |
|
"loss": 4.4882, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 3.59, |
|
"learning_rate": 0.0001, |
|
"loss": 4.4852, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 0.0001, |
|
"loss": 4.4302, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 0.0001, |
|
"loss": 4.4267, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"learning_rate": 0.0001, |
|
"loss": 4.4298, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3892, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3886, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3915, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3706, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 4.22, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3528, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3272, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3679, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 4.45, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3608, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 4.53, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3262, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3097, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2973, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2756, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 4.84, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3174, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2786, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2484, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 5.08, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2634, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 5.16, |
|
"learning_rate": 0.0001, |
|
"loss": 4.228, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 5.23, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2745, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 5.31, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2297, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 5.39, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1989, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 5.47, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2074, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 5.55, |
|
"learning_rate": 0.0001, |
|
"loss": 4.201, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 5.62, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2109, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 5.7, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1945, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 5.78, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1744, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 5.86, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1741, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 5.94, |
|
"learning_rate": 0.0001, |
|
"loss": 4.19, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1612, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 6.09, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1559, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 6.17, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1378, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 6.25, |
|
"learning_rate": 0.0001, |
|
"loss": 4.144, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 6.33, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1601, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 6.41, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1339, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 6.48, |
|
"learning_rate": 0.0001, |
|
"loss": 4.13, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 6.56, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0877, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 6.64, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1022, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 6.72, |
|
"learning_rate": 0.0001, |
|
"loss": 4.1034, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 6.8, |
|
"learning_rate": 0.0001, |
|
"loss": 4.091, |
|
"step": 8700 |
|
}, |
|
{ |
|
"epoch": 6.88, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0914, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 6.95, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0937, |
|
"step": 8900 |
|
}, |
|
{ |
|
"epoch": 7.03, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0897, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 7.11, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0844, |
|
"step": 9100 |
|
}, |
|
{ |
|
"epoch": 7.19, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0574, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 7.27, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0837, |
|
"step": 9300 |
|
}, |
|
{ |
|
"epoch": 7.34, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0766, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 7.42, |
|
"learning_rate": 0.0001, |
|
"loss": 4.066, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 7.5, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9944, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 7.58, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0126, |
|
"step": 9700 |
|
}, |
|
{ |
|
"epoch": 7.66, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0273, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 7.73, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0706, |
|
"step": 9900 |
|
}, |
|
{ |
|
"epoch": 7.81, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0008, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 7.89, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0323, |
|
"step": 10100 |
|
}, |
|
{ |
|
"epoch": 7.97, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9864, |
|
"step": 10200 |
|
}, |
|
{ |
|
"epoch": 8.05, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0265, |
|
"step": 10300 |
|
}, |
|
{ |
|
"epoch": 8.12, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9874, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 8.2, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9839, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 8.28, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9583, |
|
"step": 10600 |
|
}, |
|
{ |
|
"epoch": 8.36, |
|
"learning_rate": 0.0001, |
|
"loss": 4.007, |
|
"step": 10700 |
|
}, |
|
{ |
|
"epoch": 8.44, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9567, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 8.52, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9888, |
|
"step": 10900 |
|
}, |
|
{ |
|
"epoch": 8.59, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9993, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 8.67, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9914, |
|
"step": 11100 |
|
}, |
|
{ |
|
"epoch": 8.75, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0094, |
|
"step": 11200 |
|
}, |
|
{ |
|
"epoch": 8.83, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9338, |
|
"step": 11300 |
|
}, |
|
{ |
|
"epoch": 8.91, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9472, |
|
"step": 11400 |
|
}, |
|
{ |
|
"epoch": 8.98, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9595, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 9.06, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9545, |
|
"step": 11600 |
|
}, |
|
{ |
|
"epoch": 9.14, |
|
"learning_rate": 0.0001, |
|
"loss": 3.993, |
|
"step": 11700 |
|
}, |
|
{ |
|
"epoch": 9.22, |
|
"learning_rate": 0.0001, |
|
"loss": 3.895, |
|
"step": 11800 |
|
}, |
|
{ |
|
"epoch": 9.3, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9527, |
|
"step": 11900 |
|
}, |
|
{ |
|
"epoch": 9.38, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9205, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 9.45, |
|
"learning_rate": 0.0001, |
|
"loss": 3.914, |
|
"step": 12100 |
|
}, |
|
{ |
|
"epoch": 9.53, |
|
"learning_rate": 0.0001, |
|
"loss": 3.8872, |
|
"step": 12200 |
|
}, |
|
{ |
|
"epoch": 9.61, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9171, |
|
"step": 12300 |
|
}, |
|
{ |
|
"epoch": 9.69, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9148, |
|
"step": 12400 |
|
}, |
|
{ |
|
"epoch": 9.77, |
|
"learning_rate": 0.0001, |
|
"loss": 3.9181, |
|
"step": 12500 |
|
} |
|
], |
|
"max_steps": 12800, |
|
"num_train_epochs": 10, |
|
"total_flos": 9380392619673600.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|