| { | |
| "best_metric": 0.2892984216768543, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-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": 5e-05, | |
| "loss": 2.1362, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 4.966442953020135e-05, | |
| "loss": 1.9133, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.932885906040269e-05, | |
| "loss": 1.8901, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 4.8993288590604034e-05, | |
| "loss": 1.8743, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 4.865771812080537e-05, | |
| "loss": 1.8572, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "eval_accuracy": 0.2892984216768543, | |
| "eval_loss": 1.9470784664154053, | |
| "eval_runtime": 1.9235, | |
| "eval_samples_per_second": 198.078, | |
| "eval_steps_per_second": 24.955, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.832214765100672e-05, | |
| "loss": 1.8448, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 4.798657718120805e-05, | |
| "loss": 1.8263, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 20.51, | |
| "learning_rate": 4.76510067114094e-05, | |
| "loss": 1.7988, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 4.731543624161074e-05, | |
| "loss": 1.7733, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 4.697986577181208e-05, | |
| "loss": 1.7321, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "eval_accuracy": 0.27597846911778123, | |
| "eval_loss": 2.090031147003174, | |
| "eval_runtime": 1.9389, | |
| "eval_samples_per_second": 196.498, | |
| "eval_steps_per_second": 24.756, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 4.664429530201342e-05, | |
| "loss": 1.6957, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 4.630872483221477e-05, | |
| "loss": 1.6365, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 4.597315436241611e-05, | |
| "loss": 1.5917, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "learning_rate": 4.5637583892617453e-05, | |
| "loss": 1.5378, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 4.530201342281879e-05, | |
| "loss": 1.4759, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "eval_accuracy": 0.2506158197244777, | |
| "eval_loss": 2.431821584701538, | |
| "eval_runtime": 1.933, | |
| "eval_samples_per_second": 197.107, | |
| "eval_steps_per_second": 24.832, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 41.03, | |
| "learning_rate": 4.496644295302014e-05, | |
| "loss": 1.4153, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 43.59, | |
| "learning_rate": 4.463087248322148e-05, | |
| "loss": 1.354, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 4.4295302013422824e-05, | |
| "loss": 1.2879, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 48.72, | |
| "learning_rate": 4.395973154362416e-05, | |
| "loss": 1.2279, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 4.36241610738255e-05, | |
| "loss": 1.1962, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "eval_accuracy": 0.2390292856491196, | |
| "eval_loss": 2.9406466484069824, | |
| "eval_runtime": 1.9342, | |
| "eval_samples_per_second": 196.977, | |
| "eval_steps_per_second": 24.816, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 4.328859060402685e-05, | |
| "loss": 1.1217, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 56.41, | |
| "learning_rate": 4.295302013422819e-05, | |
| "loss": 1.0833, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 58.97, | |
| "learning_rate": 4.2617449664429534e-05, | |
| "loss": 1.0293, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 4.228187919463087e-05, | |
| "loss": 0.9821, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "learning_rate": 4.194630872483222e-05, | |
| "loss": 0.9384, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "eval_accuracy": 0.22935863516102545, | |
| "eval_loss": 3.6179699897766113, | |
| "eval_runtime": 1.942, | |
| "eval_samples_per_second": 196.187, | |
| "eval_steps_per_second": 24.716, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 4.161073825503356e-05, | |
| "loss": 0.8994, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 4.1275167785234905e-05, | |
| "loss": 0.8775, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 71.79, | |
| "learning_rate": 4.0942953020134226e-05, | |
| "loss": 0.8304, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 74.36, | |
| "learning_rate": 4.060738255033557e-05, | |
| "loss": 0.8287, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "learning_rate": 4.027181208053691e-05, | |
| "loss": 0.7909, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "eval_accuracy": 0.23273423957668096, | |
| "eval_loss": 4.074990749359131, | |
| "eval_runtime": 1.9336, | |
| "eval_samples_per_second": 197.047, | |
| "eval_steps_per_second": 24.825, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "step": 3000, | |
| "total_flos": 1.2335402138867712e+16, | |
| "train_loss": 1.4148986282348632, | |
| "train_runtime": 758.2535, | |
| "train_samples_per_second": 633.034, | |
| "train_steps_per_second": 19.782 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 385, | |
| "total_flos": 1.2335402138867712e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |