| { |
| "best_metric": 0.08365064859390259, |
| "best_model_checkpoint": "./Genesis_quant_v18_8k_linear_padding_head_benchmarking/checkpoint-3614", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 3614, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.28, |
| "learning_rate": 2.8339789706696182e-05, |
| "loss": 0.0439, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 2.6679579413392364e-05, |
| "loss": 0.0339, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 2.5019369120088545e-05, |
| "loss": 0.0219, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_epoch": 1.0, |
| "eval_head_type": "linear", |
| "eval_loss": 0.03443923220038414, |
| "eval_mae2": 0.23664554953575134, |
| "eval_mse1": 0.02161429077386856, |
| "eval_mse2": 0.13640384376049042, |
| "eval_n_valid": 904, |
| "eval_pearson2": 0.757525353160554, |
| "eval_r2_2": 0.38493316923911924, |
| "eval_rmse2": 0.36932891607284546, |
| "eval_runtime": 8.9423, |
| "eval_samples_per_second": 101.092, |
| "eval_spearman2": 0.7637428902304154, |
| "eval_steps_per_second": 25.273, |
| "step": 1807 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 2.3359158826784726e-05, |
| "loss": 0.0189, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 2.1698948533480908e-05, |
| "loss": 0.0147, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 2.003873824017709e-05, |
| "loss": 0.0123, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 1.837852794687327e-05, |
| "loss": 0.0139, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_epoch": 2.0, |
| "eval_head_type": "linear", |
| "eval_loss": 0.02601287141442299, |
| "eval_mae2": 0.18473036587238312, |
| "eval_mse1": 0.018763288855552673, |
| "eval_mse2": 0.08365064859390259, |
| "eval_n_valid": 904, |
| "eval_pearson2": 0.8231394464607437, |
| "eval_r2_2": 0.6228058801891168, |
| "eval_rmse2": 0.28922420740127563, |
| "eval_runtime": 8.9375, |
| "eval_samples_per_second": 101.147, |
| "eval_spearman2": 0.7646683676720165, |
| "eval_steps_per_second": 25.287, |
| "step": 3614 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 9035, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
