trainer_state.json

{
 "best_metric": 0.00286100001416597,
 "best_model_checkpoint": "cola-pixel-handwritten-mean-vatrpp-256-64-4-2e-5-15000-42/checkpoint-100",
 "epoch": 33.32835820895522,
 "global_step": 1100,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 3.03,
 "learning_rate": 9.800000000000001e-06,
 "loss": 0.655,
 "step": 100
 },
 {
 "epoch": 3.03,
 "eval_loss": 0.6341390013694763,
 "eval_matthews_correlation": 0.00286100001416597,
 "eval_runtime": 7.8213,
 "eval_samples_per_second": 133.354,
 "eval_steps_per_second": 16.749,
 "step": 100
 },
 {
 "epoch": 6.06,
 "learning_rate": 1.98e-05,
 "loss": 0.6174,
 "step": 200
 },
 {
 "epoch": 6.06,
 "eval_loss": 0.6281591057777405,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 7.9503,
 "eval_samples_per_second": 131.19,
 "eval_steps_per_second": 16.477,
 "step": 200
 },
 {
 "epoch": 9.09,
 "learning_rate": 1.9867567567567568e-05,
 "loss": 0.6196,
 "step": 300
 },
 {
 "epoch": 9.09,
 "eval_loss": 0.6198328137397766,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 7.8212,
 "eval_samples_per_second": 133.356,
 "eval_steps_per_second": 16.749,
 "step": 300
 },
 {
 "epoch": 12.12,
 "learning_rate": 1.9733783783783785e-05,
 "loss": 0.6158,
 "step": 400
 },
 {
 "epoch": 12.12,
 "eval_loss": 0.6199322938919067,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 7.8954,
 "eval_samples_per_second": 132.102,
 "eval_steps_per_second": 16.592,
 "step": 400
 },
 {
 "epoch": 15.15,
 "learning_rate": 1.9600000000000002e-05,
 "loss": 0.6175,
 "step": 500
 },
 {
 "epoch": 15.15,
 "eval_loss": 0.6180645823478699,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 8.2397,
 "eval_samples_per_second": 126.583,
 "eval_steps_per_second": 15.899,
 "step": 500
 },
 {
 "epoch": 18.18,
 "learning_rate": 1.9464864864864867e-05,
 "loss": 0.6152,
 "step": 600
 },
 {
 "epoch": 18.18,
 "eval_loss": 0.619079053401947,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 7.8304,
 "eval_samples_per_second": 133.198,
 "eval_steps_per_second": 16.73,
 "step": 600
 },
 {
 "epoch": 21.21,
 "learning_rate": 1.932972972972973e-05,
 "loss": 0.617,
 "step": 700
 },
 {
 "epoch": 21.21,
 "eval_loss": 0.6184842586517334,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 8.2213,
 "eval_samples_per_second": 126.865,
 "eval_steps_per_second": 15.934,
 "step": 700
 },
 {
 "epoch": 24.24,
 "learning_rate": 1.9194594594594596e-05,
 "loss": 0.6191,
 "step": 800
 },
 {
 "epoch": 24.24,
 "eval_loss": 0.6185177564620972,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 7.887,
 "eval_samples_per_second": 132.243,
 "eval_steps_per_second": 16.61,
 "step": 800
 },
 {
 "epoch": 27.27,
 "learning_rate": 1.905945945945946e-05,
 "loss": 0.6162,
 "step": 900
 },
 {
 "epoch": 27.27,
 "eval_loss": 0.6183082461357117,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 7.8268,
 "eval_samples_per_second": 133.26,
 "eval_steps_per_second": 16.737,
 "step": 900
 },
 {
 "epoch": 30.3,
 "learning_rate": 1.8924324324324325e-05,
 "loss": 0.6166,
 "step": 1000
 },
 {
 "epoch": 30.3,
 "eval_loss": 0.6183302402496338,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 7.795,
 "eval_samples_per_second": 133.803,
 "eval_steps_per_second": 16.806,
 "step": 1000
 },
 {
 "epoch": 33.33,
 "learning_rate": 1.878918918918919e-05,
 "loss": 0.6177,
 "step": 1100
 },
 {
 "epoch": 33.33,
 "eval_loss": 0.6182125210762024,
 "eval_matthews_correlation": 0.0,
 "eval_runtime": 7.8695,
 "eval_samples_per_second": 132.537,
 "eval_steps_per_second": 16.647,
 "step": 1100
 },
 {
 "epoch": 33.33,
 "step": 1100,
 "total_flos": 7.341930418964005e+18,
 "train_loss": 0.6206500174782493,
 "train_runtime": 3140.0413,
 "train_samples_per_second": 1222.914,
 "train_steps_per_second": 4.777
 }
 ],
 "max_steps": 15000,
 "num_train_epochs": 455,
 "total_flos": 7.341930418964005e+18,
 "trial_name": null,
 "trial_params": null
}