| { |
| "best_metric": 0.9671150655371568, |
| "best_model_checkpoint": "models/longformer_classifier/checkpoint-6544", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 13088, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "learning_rate": 1.9235941320293402e-05, |
| "loss": 7.0429, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 1.84718826405868e-05, |
| "loss": 6.7762, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 1.7707823960880196e-05, |
| "loss": 6.3278, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 1.6943765281173596e-05, |
| "loss": 5.1982, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 1.6179706601466993e-05, |
| "loss": 6.9234, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 1.5415647921760393e-05, |
| "loss": 3.3308, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 1.4651589242053792e-05, |
| "loss": 11.0545, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 1.3887530562347189e-05, |
| "loss": 11.4149, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 1.3123471882640589e-05, |
| "loss": 3.9411, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 1.2359413202933986e-05, |
| "loss": 5.0606, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 1.1595354523227385e-05, |
| "loss": 4.0193, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 1.0831295843520783e-05, |
| "loss": 6.3164, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 1.006723716381418e-05, |
| "loss": 10.0802, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.9671150655371568, |
| "eval_loss": 6.602837085723877, |
| "eval_precision": 0.9564744352317358, |
| "eval_recall": 0.9779951100244498, |
| "eval_runtime": 1373.3102, |
| "eval_samples_per_second": 1.191, |
| "eval_steps_per_second": 1.191, |
| "step": 6544 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 9.30317848410758e-06, |
| "loss": 6.419, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 8.539119804400979e-06, |
| "loss": 3.2558, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 7.775061124694378e-06, |
| "loss": 6.4214, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 7.011002444987775e-06, |
| "loss": 5.2197, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 6.246943765281174e-06, |
| "loss": 7.7577, |
| "step": 9000 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 5.482885085574573e-06, |
| "loss": 4.2541, |
| "step": 9500 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 4.718826405867971e-06, |
| "loss": 6.9299, |
| "step": 10000 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 3.954767726161369e-06, |
| "loss": 4.4269, |
| "step": 10500 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 3.190709046454768e-06, |
| "loss": 4.4276, |
| "step": 11000 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 2.4266503667481666e-06, |
| "loss": 4.2753, |
| "step": 11500 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 1.6625916870415647e-06, |
| "loss": 4.9898, |
| "step": 12000 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 8.985330073349634e-07, |
| "loss": 5.014, |
| "step": 12500 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 1.3447432762836187e-07, |
| "loss": 4.3745, |
| "step": 13000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.9671150655371568, |
| "eval_loss": 5.483180999755859, |
| "eval_precision": 0.9564744352317358, |
| "eval_recall": 0.9779951100244498, |
| "eval_runtime": 9134.9046, |
| "eval_samples_per_second": 0.179, |
| "eval_steps_per_second": 0.179, |
| "step": 13088 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 13088, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 3.3581297093376e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
