| { | |
| "best_metric": 0.2892071891250798, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-pos-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": 7.92e-05, | |
| "loss": 2.1425, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 7.946845637583894e-05, | |
| "loss": 1.9316, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 7.893154362416109e-05, | |
| "loss": 1.9066, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 7.839463087248322e-05, | |
| "loss": 1.8917, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 7.785771812080537e-05, | |
| "loss": 1.88, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "eval_accuracy": 0.2892071891250798, | |
| "eval_loss": 1.9474276304244995, | |
| "eval_runtime": 1.9459, | |
| "eval_samples_per_second": 195.796, | |
| "eval_steps_per_second": 24.667, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 7.732080536912752e-05, | |
| "loss": 1.8777, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 7.678389261744967e-05, | |
| "loss": 1.8674, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 20.51, | |
| "learning_rate": 7.624697986577182e-05, | |
| "loss": 1.8495, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 7.571006711409396e-05, | |
| "loss": 1.838, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 7.517315436241611e-05, | |
| "loss": 1.8131, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "eval_accuracy": 0.28847732871088405, | |
| "eval_loss": 1.996766209602356, | |
| "eval_runtime": 1.9595, | |
| "eval_samples_per_second": 194.438, | |
| "eval_steps_per_second": 24.496, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 7.463624161073826e-05, | |
| "loss": 1.7921, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 7.409932885906041e-05, | |
| "loss": 1.7496, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 7.356241610738256e-05, | |
| "loss": 1.7099, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "learning_rate": 7.30255033557047e-05, | |
| "loss": 1.6553, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 7.248859060402685e-05, | |
| "loss": 1.5873, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "eval_accuracy": 0.261290028282091, | |
| "eval_loss": 2.346529960632324, | |
| "eval_runtime": 1.9481, | |
| "eval_samples_per_second": 195.576, | |
| "eval_steps_per_second": 24.639, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 41.03, | |
| "learning_rate": 7.1951677852349e-05, | |
| "loss": 1.5155, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 43.59, | |
| "learning_rate": 7.141476510067115e-05, | |
| "loss": 1.4393, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 7.08778523489933e-05, | |
| "loss": 1.362, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 48.72, | |
| "learning_rate": 7.034093959731545e-05, | |
| "loss": 1.2868, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 6.98040268456376e-05, | |
| "loss": 1.2522, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "eval_accuracy": 0.23583614633701305, | |
| "eval_loss": 3.054924249649048, | |
| "eval_runtime": 1.9514, | |
| "eval_samples_per_second": 195.244, | |
| "eval_steps_per_second": 24.598, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 6.927248322147651e-05, | |
| "loss": 1.1646, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 56.41, | |
| "learning_rate": 6.873557046979866e-05, | |
| "loss": 1.1278, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 58.97, | |
| "learning_rate": 6.820402684563758e-05, | |
| "loss": 1.0644, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 6.766711409395973e-05, | |
| "loss": 1.021, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "learning_rate": 6.713020134228188e-05, | |
| "loss": 0.9782, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "eval_accuracy": 0.2366572393029833, | |
| "eval_loss": 3.7386221885681152, | |
| "eval_runtime": 1.9495, | |
| "eval_samples_per_second": 195.433, | |
| "eval_steps_per_second": 24.622, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 6.659328859060403e-05, | |
| "loss": 0.9309, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 6.605637583892618e-05, | |
| "loss": 0.9079, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 71.79, | |
| "learning_rate": 6.551946308724832e-05, | |
| "loss": 0.8622, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 74.36, | |
| "learning_rate": 6.498255033557047e-05, | |
| "loss": 0.8537, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "learning_rate": 6.444563758389262e-05, | |
| "loss": 0.8122, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "eval_accuracy": 0.22726028647021257, | |
| "eval_loss": 3.944620132446289, | |
| "eval_runtime": 1.958, | |
| "eval_samples_per_second": 194.582, | |
| "eval_steps_per_second": 24.514, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "step": 3000, | |
| "total_flos": 1.2335402138867712e+16, | |
| "train_loss": 1.4690344212849935, | |
| "train_runtime": 809.6738, | |
| "train_samples_per_second": 592.831, | |
| "train_steps_per_second": 18.526 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 385, | |
| "total_flos": 1.2335402138867712e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |