|
{ |
|
"best_metric": 14.889152449594015, |
|
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Coptic-Scriptorium/checkpoint-500", |
|
"epoch": 76.92307692307692, |
|
"global_step": 3000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 7.6e-05, |
|
"loss": 5.3836, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 5.13, |
|
"learning_rate": 7.948993288590604e-05, |
|
"loss": 4.1364, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 7.69, |
|
"learning_rate": 7.895302013422819e-05, |
|
"loss": 3.8943, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 10.26, |
|
"learning_rate": 7.841610738255034e-05, |
|
"loss": 3.7384, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 12.82, |
|
"learning_rate": 7.787919463087249e-05, |
|
"loss": 3.5767, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 12.82, |
|
"eval_las": 14.889152449594015, |
|
"eval_loss": 4.103353500366211, |
|
"eval_runtime": 2.9493, |
|
"eval_samples_per_second": 129.182, |
|
"eval_steps_per_second": 16.275, |
|
"eval_uas": 31.748928017516647, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 15.38, |
|
"learning_rate": 7.734228187919463e-05, |
|
"loss": 3.4084, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 17.95, |
|
"learning_rate": 7.680536912751678e-05, |
|
"loss": 3.2001, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 20.51, |
|
"learning_rate": 7.626845637583893e-05, |
|
"loss": 2.9538, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 23.08, |
|
"learning_rate": 7.573154362416108e-05, |
|
"loss": 2.7223, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 25.64, |
|
"learning_rate": 7.519463087248323e-05, |
|
"loss": 2.4472, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 25.64, |
|
"eval_las": 11.248973633792538, |
|
"eval_loss": 5.691993713378906, |
|
"eval_runtime": 2.9489, |
|
"eval_samples_per_second": 129.203, |
|
"eval_steps_per_second": 16.278, |
|
"eval_uas": 27.926284098166228, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 28.21, |
|
"learning_rate": 7.465771812080537e-05, |
|
"loss": 2.2519, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 30.77, |
|
"learning_rate": 7.412080536912752e-05, |
|
"loss": 2.0317, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 33.33, |
|
"learning_rate": 7.358389261744967e-05, |
|
"loss": 1.8544, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 35.9, |
|
"learning_rate": 7.304697986577182e-05, |
|
"loss": 1.7134, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 38.46, |
|
"learning_rate": 7.251006711409397e-05, |
|
"loss": 1.5671, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 38.46, |
|
"eval_las": 9.871362101997994, |
|
"eval_loss": 7.934547424316406, |
|
"eval_runtime": 2.9464, |
|
"eval_samples_per_second": 129.311, |
|
"eval_steps_per_second": 16.291, |
|
"eval_uas": 25.444758689900553, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 41.03, |
|
"learning_rate": 7.197315436241612e-05, |
|
"loss": 1.4647, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 43.59, |
|
"learning_rate": 7.143624161073826e-05, |
|
"loss": 1.3584, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 46.15, |
|
"learning_rate": 7.089932885906041e-05, |
|
"loss": 1.2918, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 48.72, |
|
"learning_rate": 7.036241610738256e-05, |
|
"loss": 1.2333, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 51.28, |
|
"learning_rate": 6.982550335570471e-05, |
|
"loss": 1.2108, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 51.28, |
|
"eval_las": 9.570294681142231, |
|
"eval_loss": 10.208051681518555, |
|
"eval_runtime": 2.9507, |
|
"eval_samples_per_second": 129.123, |
|
"eval_steps_per_second": 16.267, |
|
"eval_uas": 24.58717270322051, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 53.85, |
|
"learning_rate": 6.928859060402686e-05, |
|
"loss": 1.1363, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 56.41, |
|
"learning_rate": 6.8751677852349e-05, |
|
"loss": 1.1452, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 58.97, |
|
"learning_rate": 6.821476510067115e-05, |
|
"loss": 1.0937, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 61.54, |
|
"learning_rate": 6.76778523489933e-05, |
|
"loss": 1.0555, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 64.1, |
|
"learning_rate": 6.714093959731544e-05, |
|
"loss": 1.0311, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 64.1, |
|
"eval_las": 9.707143508803942, |
|
"eval_loss": 11.06482219696045, |
|
"eval_runtime": 2.9481, |
|
"eval_samples_per_second": 129.236, |
|
"eval_steps_per_second": 16.282, |
|
"eval_uas": 24.368214578961776, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 66.67, |
|
"learning_rate": 6.660402684563758e-05, |
|
"loss": 1.0068, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 69.23, |
|
"learning_rate": 6.606711409395973e-05, |
|
"loss": 1.0095, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 71.79, |
|
"learning_rate": 6.553020134228188e-05, |
|
"loss": 0.9792, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 74.36, |
|
"learning_rate": 6.499328859060403e-05, |
|
"loss": 0.988, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 76.92, |
|
"learning_rate": 6.445637583892618e-05, |
|
"loss": 0.9661, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 76.92, |
|
"eval_las": 9.670650488094152, |
|
"eval_loss": 10.523516654968262, |
|
"eval_runtime": 2.9465, |
|
"eval_samples_per_second": 129.304, |
|
"eval_steps_per_second": 16.29, |
|
"eval_uas": 24.41383085484901, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 76.92, |
|
"step": 3000, |
|
"total_flos": 1.5763284763250688e+16, |
|
"train_loss": 2.0616751454671225, |
|
"train_runtime": 1642.7036, |
|
"train_samples_per_second": 292.201, |
|
"train_steps_per_second": 9.131 |
|
} |
|
], |
|
"max_steps": 15000, |
|
"num_train_epochs": 385, |
|
"total_flos": 1.5763284763250688e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|