diff --git "a/train" "b/train"
new file mode 100644--- /dev/null
+++ "b/train"
@@ -0,0 +1,3867 @@
+11/03/2023 11:21:35 - INFO - root -   Input args: Namespace(adam_epsilon=1e-08, cache_dir='', config_name='', data_dir='./data/oversample//comp', do_eval=True, do_lower_case=False, do_predict=True, do_predict_dev=False, do_train=True, eval_all_checkpoints=True, eval_test_set=True, evaluate_during_training=False, fp16=False, fp16_opt_level='O1', gradient_accumulation_steps=1, init_checkpoint=None, learning_rate=1e-05, local_rank=-1, log_file='train', logging_steps=50, max_grad_norm=1.0, max_seq_length=256, max_steps=-1, model_name_or_path='roberta-large', model_type='roberta', no_cuda=False, num_train_epochs=10.0, output_dir='./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//', overwrite_cache=False, overwrite_output_dir=True, per_gpu_eval_batch_size=8, per_gpu_train_batch_size=32, save_only_best_checkpoint=True, save_steps=20, seed=42, server_ip='', server_port='', task_name='comp', test_split='test', tokenizer_name='', train_split='train', warmup_steps=0, weight_decay=0.0)
+11/03/2023 11:21:35 - WARNING - __main__ -   Process rank: -1, device: cuda, n_gpu: 1, distributed training: False, 16-bits training: False
+11/03/2023 11:21:35 - INFO - __main__ -   config = RobertaConfig {
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "comp",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}
+
+11/03/2023 11:21:36 - INFO - __main__ -   Training/evaluation parameters Namespace(adam_epsilon=1e-08, cache_dir='', config_name='', data_dir='./data/oversample//comp', device=device(type='cuda'), do_eval=True, do_lower_case=False, do_predict=True, do_predict_dev=False, do_train=True, eval_all_checkpoints=True, eval_test_set=True, evaluate_during_training=False, fp16=False, fp16_opt_level='O1', gradient_accumulation_steps=1, init_checkpoint=None, learning_rate=1e-05, local_rank=-1, log_file='train', logging_steps=50, max_grad_norm=1.0, max_seq_length=256, max_steps=-1, model_name_or_path='roberta-large', model_type='roberta', n_gpu=1, no_cuda=False, num_train_epochs=10.0, output_dir='./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//', output_mode='classification', overwrite_cache=False, overwrite_output_dir=True, per_gpu_eval_batch_size=8, per_gpu_train_batch_size=32, save_only_best_checkpoint=True, save_steps=20, seed=42, server_ip='', server_port='', task_name='comp', test_split='test', tokenizer_name='', train_split='train', warmup_steps=0, weight_decay=0.0)
+11/03/2023 11:21:36 - INFO - __main__ -   loading from existing model roberta-large
+11/03/2023 11:21:45 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_train_roberta-large_256_comp_
+11/03/2023 11:21:45 - INFO - __main__ -   ***** Running training *****
+11/03/2023 11:21:45 - INFO - __main__ -     Num examples = 1696
+11/03/2023 11:21:45 - INFO - __main__ -     Num Epochs = 10
+11/03/2023 11:21:45 - INFO - __main__ -     Instantaneous batch size per GPU = 32
+11/03/2023 11:21:45 - INFO - __main__ -     Total train batch size (w. parallel, distributed & accumulation) = 32
+11/03/2023 11:21:45 - INFO - __main__ -     Gradient Accumulation steps = 1
+11/03/2023 11:21:45 - INFO - __main__ -     Total optimization steps = 530
+11/03/2023 11:22:11 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:22:11 - INFO - __main__ -   ***** Running evaluation checkpoint-20 *****
+11/03/2023 11:22:11 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:22:11 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:22:17 - INFO - __main__ -   ***** Eval results checkpoint-20 *****
+11/03/2023 11:22:17 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 11:22:17 - INFO - __main__ -    correct = 353
+11/03/2023 11:22:17 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 11:22:17 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:22:17 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:22:17 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 11:22:17 - INFO - __main__ -    num = 527
+11/03/2023 11:22:17 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 11:22:17 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:22:17 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:22:17 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 11:22:17 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:22:17 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:27:43 - INFO - root -   Input args: Namespace(adam_epsilon=1e-08, cache_dir='', config_name='', data_dir='./data/oversample//comp', do_eval=True, do_lower_case=False, do_predict=True, do_predict_dev=False, do_train=True, eval_all_checkpoints=True, eval_test_set=True, evaluate_during_training=False, fp16=False, fp16_opt_level='O1', gradient_accumulation_steps=1, init_checkpoint=None, learning_rate=1e-05, local_rank=-1, log_file='train', logging_steps=50, max_grad_norm=1.0, max_seq_length=256, max_steps=-1, model_name_or_path='roberta-large', model_type='roberta', no_cuda=False, num_train_epochs=10.0, output_dir='./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//', overwrite_cache=False, overwrite_output_dir=True, per_gpu_eval_batch_size=8, per_gpu_train_batch_size=32, save_only_best_checkpoint=True, save_steps=20, seed=42, server_ip='', server_port='', task_name='comp', test_split='test', tokenizer_name='', train_split='train', warmup_steps=0, weight_decay=0.0)
+11/03/2023 11:27:44 - WARNING - __main__ -   Process rank: -1, device: cuda, n_gpu: 1, distributed training: False, 16-bits training: False
+11/03/2023 11:27:44 - INFO - __main__ -   config = RobertaConfig {
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "comp",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}
+
+11/03/2023 11:27:44 - INFO - __main__ -   Training/evaluation parameters Namespace(adam_epsilon=1e-08, cache_dir='', config_name='', data_dir='./data/oversample//comp', device=device(type='cuda'), do_eval=True, do_lower_case=False, do_predict=True, do_predict_dev=False, do_train=True, eval_all_checkpoints=True, eval_test_set=True, evaluate_during_training=False, fp16=False, fp16_opt_level='O1', gradient_accumulation_steps=1, init_checkpoint=None, learning_rate=1e-05, local_rank=-1, log_file='train', logging_steps=50, max_grad_norm=1.0, max_seq_length=256, max_steps=-1, model_name_or_path='roberta-large', model_type='roberta', n_gpu=1, no_cuda=False, num_train_epochs=10.0, output_dir='./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//', output_mode='classification', overwrite_cache=False, overwrite_output_dir=True, per_gpu_eval_batch_size=8, per_gpu_train_batch_size=32, save_only_best_checkpoint=True, save_steps=20, seed=42, server_ip='', server_port='', task_name='comp', test_split='test', tokenizer_name='', train_split='train', warmup_steps=0, weight_decay=0.0)
+11/03/2023 11:27:44 - INFO - __main__ -   loading from existing model roberta-large
+11/03/2023 11:27:56 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_train_roberta-large_256_comp_
+11/03/2023 11:27:56 - INFO - __main__ -   ***** Running training *****
+11/03/2023 11:27:56 - INFO - __main__ -     Num examples = 1696
+11/03/2023 11:27:56 - INFO - __main__ -     Num Epochs = 10
+11/03/2023 11:27:56 - INFO - __main__ -     Instantaneous batch size per GPU = 32
+11/03/2023 11:27:56 - INFO - __main__ -     Total train batch size (w. parallel, distributed & accumulation) = 32
+11/03/2023 11:27:56 - INFO - __main__ -     Gradient Accumulation steps = 1
+11/03/2023 11:27:56 - INFO - __main__ -     Total optimization steps = 530
+11/03/2023 11:28:22 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:28:22 - INFO - __main__ -   ***** Running evaluation checkpoint-20 *****
+11/03/2023 11:28:22 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:28:22 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:28:29 - INFO - __main__ -   ***** Eval results checkpoint-20 *****
+11/03/2023 11:28:29 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 11:28:29 - INFO - __main__ -    correct = 353
+11/03/2023 11:28:29 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 11:28:29 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:28:29 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:28:29 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 11:28:29 - INFO - __main__ -    num = 527
+11/03/2023 11:28:29 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 11:28:29 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:28:29 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:28:29 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 11:28:29 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:28:29 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:28:29 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:28:29 - INFO - __main__ -   ***** Running evaluation 20 *****
+11/03/2023 11:28:29 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:28:29 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:28:32 - INFO - __main__ -   ***** Eval results 20 *****
+11/03/2023 11:28:32 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 11:28:32 - INFO - __main__ -    correct = 223
+11/03/2023 11:28:32 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 11:28:32 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:28:32 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:28:32 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 11:28:32 - INFO - __main__ -    num = 326
+11/03/2023 11:28:32 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 11:28:32 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:28:32 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:28:32 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 11:28:32 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:28:32 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:28:32 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 11:28:32 - INFO - __main__ -    result['acc']=0.6840490797546013 > best_score=0
+11/03/2023 11:28:34 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:28:36 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:28:57 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:28:57 - INFO - __main__ -   ***** Running evaluation checkpoint-40 *****
+11/03/2023 11:28:57 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:28:57 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:29:03 - INFO - __main__ -   ***** Eval results checkpoint-40 *****
+11/03/2023 11:29:03 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 11:29:03 - INFO - __main__ -    correct = 353
+11/03/2023 11:29:03 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 11:29:03 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:29:03 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:29:03 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 11:29:03 - INFO - __main__ -    num = 527
+11/03/2023 11:29:03 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 11:29:03 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:29:03 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:29:03 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 11:29:03 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:29:03 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:29:03 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:29:03 - INFO - __main__ -   ***** Running evaluation 40 *****
+11/03/2023 11:29:03 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:29:03 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:29:07 - INFO - __main__ -   ***** Eval results 40 *****
+11/03/2023 11:29:07 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 11:29:07 - INFO - __main__ -    correct = 223
+11/03/2023 11:29:07 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 11:29:07 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:29:07 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:29:07 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 11:29:07 - INFO - __main__ -    num = 326
+11/03/2023 11:29:07 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 11:29:07 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:29:07 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:29:07 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 11:29:07 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:29:07 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:29:07 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 11:29:27 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:29:27 - INFO - __main__ -   ***** Running evaluation checkpoint-60 *****
+11/03/2023 11:29:27 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:29:27 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:29:34 - INFO - __main__ -   ***** Eval results checkpoint-60 *****
+11/03/2023 11:29:34 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 11:29:34 - INFO - __main__ -    correct = 353
+11/03/2023 11:29:34 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 11:29:34 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:29:34 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:29:34 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 11:29:34 - INFO - __main__ -    num = 527
+11/03/2023 11:29:34 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 11:29:34 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:29:34 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:29:34 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 11:29:34 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:29:34 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:29:34 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:29:34 - INFO - __main__ -   ***** Running evaluation 60 *****
+11/03/2023 11:29:34 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:29:34 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:29:37 - INFO - __main__ -   ***** Eval results 60 *****
+11/03/2023 11:29:37 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 11:29:37 - INFO - __main__ -    correct = 223
+11/03/2023 11:29:37 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 11:29:37 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:29:37 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:29:37 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 11:29:37 - INFO - __main__ -    num = 326
+11/03/2023 11:29:37 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 11:29:37 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:29:37 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:29:37 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 11:29:37 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:29:37 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:29:37 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 11:29:58 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:29:58 - INFO - __main__ -   ***** Running evaluation checkpoint-80 *****
+11/03/2023 11:29:58 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:29:58 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:30:04 - INFO - __main__ -   ***** Eval results checkpoint-80 *****
+11/03/2023 11:30:04 - INFO - __main__ -    acc = 0.6660341555977229
+11/03/2023 11:30:04 - INFO - __main__ -    correct = 351
+11/03/2023 11:30:04 - INFO - __main__ -    f1_0 = 0.8032036613272312
+11/03/2023 11:30:04 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:30:04 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:30:04 - INFO - __main__ -    macro_f1 = 0.26773455377574373
+11/03/2023 11:30:04 - INFO - __main__ -    num = 527
+11/03/2023 11:30:04 - INFO - __main__ -    prec_0 = 0.6737044145873321
+11/03/2023 11:30:04 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:30:04 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:30:04 - INFO - __main__ -    rec_0 = 0.9943342776203966
+11/03/2023 11:30:04 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:30:04 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:30:04 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:30:04 - INFO - __main__ -   ***** Running evaluation 80 *****
+11/03/2023 11:30:04 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:30:04 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:30:08 - INFO - __main__ -   ***** Eval results 80 *****
+11/03/2023 11:30:08 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 11:30:08 - INFO - __main__ -    correct = 223
+11/03/2023 11:30:08 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 11:30:08 - INFO - __main__ -    f1_1 = 0
+11/03/2023 11:30:08 - INFO - __main__ -    f1_2 = 0
+11/03/2023 11:30:08 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 11:30:08 - INFO - __main__ -    num = 326
+11/03/2023 11:30:08 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 11:30:08 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 11:30:08 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 11:30:08 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 11:30:08 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 11:30:08 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 11:30:08 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 11:30:29 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:30:29 - INFO - __main__ -   ***** Running evaluation checkpoint-100 *****
+11/03/2023 11:30:29 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:30:29 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:30:35 - INFO - __main__ -   ***** Eval results checkpoint-100 *****
+11/03/2023 11:30:35 - INFO - __main__ -    acc = 0.6736242884250474
+11/03/2023 11:30:35 - INFO - __main__ -    correct = 355
+11/03/2023 11:30:35 - INFO - __main__ -    f1_0 = 0.819047619047619
+11/03/2023 11:30:35 - INFO - __main__ -    f1_1 = 0.08823529411764705
+11/03/2023 11:30:35 - INFO - __main__ -    f1_2 = 0.1095890410958904
+11/03/2023 11:30:35 - INFO - __main__ -    macro_f1 = 0.33895731808705215
+11/03/2023 11:30:35 - INFO - __main__ -    num = 527
+11/03/2023 11:30:35 - INFO - __main__ -    prec_0 = 0.7063655030800822
+11/03/2023 11:30:35 - INFO - __main__ -    prec_1 = 0.0967741935483871
+11/03/2023 11:30:35 - INFO - __main__ -    prec_2 = 0.8888888888888888
+11/03/2023 11:30:35 - INFO - __main__ -    rec_0 = 0.9745042492917847
+11/03/2023 11:30:35 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 11:30:35 - INFO - __main__ -    rec_2 = 0.058394160583941604
+11/03/2023 11:30:35 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:30:35 - INFO - __main__ -   ***** Running evaluation 100 *****
+11/03/2023 11:30:35 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:30:35 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:30:39 - INFO - __main__ -   ***** Eval results 100 *****
+11/03/2023 11:30:39 - INFO - __main__ -    acc = 0.6901840490797546
+11/03/2023 11:30:39 - INFO - __main__ -    correct = 225
+11/03/2023 11:30:39 - INFO - __main__ -    f1_0 = 0.8241965973534972
+11/03/2023 11:30:39 - INFO - __main__ -    f1_1 = 0.13953488372093023
+11/03/2023 11:30:39 - INFO - __main__ -    f1_2 = 0.1
+11/03/2023 11:30:39 - INFO - __main__ -    macro_f1 = 0.35457716035814246
+11/03/2023 11:30:39 - INFO - __main__ -    num = 326
+11/03/2023 11:30:39 - INFO - __main__ -    prec_0 = 0.7124183006535948
+11/03/2023 11:30:39 - INFO - __main__ -    prec_1 = 0.23076923076923078
+11/03/2023 11:30:39 - INFO - __main__ -    prec_2 = 0.5714285714285714
+11/03/2023 11:30:39 - INFO - __main__ -    rec_0 = 0.9775784753363229
+11/03/2023 11:30:39 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 11:30:39 - INFO - __main__ -    rec_2 = 0.0547945205479452
+11/03/2023 11:30:39 - INFO - __main__ -    Dev accuracy = 0.6901840490797546
+11/03/2023 11:30:39 - INFO - __main__ -    result['acc']=0.6901840490797546 > best_score=0.6840490797546013
+11/03/2023 11:30:41 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:30:43 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:31:04 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:31:04 - INFO - __main__ -   ***** Running evaluation checkpoint-120 *****
+11/03/2023 11:31:04 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:31:04 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:31:11 - INFO - __main__ -   ***** Eval results checkpoint-120 *****
+11/03/2023 11:31:11 - INFO - __main__ -    acc = 0.7229601518026565
+11/03/2023 11:31:11 - INFO - __main__ -    correct = 381
+11/03/2023 11:31:11 - INFO - __main__ -    f1_0 = 0.8322324966974901
+11/03/2023 11:31:11 - INFO - __main__ -    f1_1 = 0.1090909090909091
+11/03/2023 11:31:11 - INFO - __main__ -    f1_2 = 0.5206611570247933
+11/03/2023 11:31:11 - INFO - __main__ -    macro_f1 = 0.48732818760439756
+11/03/2023 11:31:11 - INFO - __main__ -    num = 527
+11/03/2023 11:31:11 - INFO - __main__ -    prec_0 = 0.7797029702970297
+11/03/2023 11:31:11 - INFO - __main__ -    prec_1 = 0.16666666666666666
+11/03/2023 11:31:11 - INFO - __main__ -    prec_2 = 0.6
+11/03/2023 11:31:11 - INFO - __main__ -    rec_0 = 0.8923512747875354
+11/03/2023 11:31:11 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 11:31:11 - INFO - __main__ -    rec_2 = 0.45985401459854014
+11/03/2023 11:31:11 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:31:11 - INFO - __main__ -   ***** Running evaluation 120 *****
+11/03/2023 11:31:11 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:31:11 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:31:14 - INFO - __main__ -   ***** Eval results 120 *****
+11/03/2023 11:31:14 - INFO - __main__ -    acc = 0.7239263803680982
+11/03/2023 11:31:14 - INFO - __main__ -    correct = 236
+11/03/2023 11:31:14 - INFO - __main__ -    f1_0 = 0.8395061728395061
+11/03/2023 11:31:14 - INFO - __main__ -    f1_1 = 0.15384615384615383
+11/03/2023 11:31:14 - INFO - __main__ -    f1_2 = 0.4566929133858268
+11/03/2023 11:31:14 - INFO - __main__ -    macro_f1 = 0.4833484133571622
+11/03/2023 11:31:14 - INFO - __main__ -    num = 326
+11/03/2023 11:31:14 - INFO - __main__ -    prec_0 = 0.7756653992395437
+11/03/2023 11:31:14 - INFO - __main__ -    prec_1 = 0.3333333333333333
+11/03/2023 11:31:14 - INFO - __main__ -    prec_2 = 0.5370370370370371
+11/03/2023 11:31:14 - INFO - __main__ -    rec_0 = 0.9147982062780269
+11/03/2023 11:31:14 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 11:31:14 - INFO - __main__ -    rec_2 = 0.3972602739726027
+11/03/2023 11:31:14 - INFO - __main__ -    Dev accuracy = 0.7239263803680982
+11/03/2023 11:31:14 - INFO - __main__ -    result['acc']=0.7239263803680982 > best_score=0.6901840490797546
+11/03/2023 11:31:16 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:31:19 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:31:40 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:31:40 - INFO - __main__ -   ***** Running evaluation checkpoint-140 *****
+11/03/2023 11:31:40 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:31:40 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:31:46 - INFO - __main__ -   ***** Eval results checkpoint-140 *****
+11/03/2023 11:31:46 - INFO - __main__ -    acc = 0.7115749525616698
+11/03/2023 11:31:46 - INFO - __main__ -    correct = 375
+11/03/2023 11:31:46 - INFO - __main__ -    f1_0 = 0.8307291666666667
+11/03/2023 11:31:46 - INFO - __main__ -    f1_1 = 0.16666666666666669
+11/03/2023 11:31:46 - INFO - __main__ -    f1_2 = 0.4672897196261682
+11/03/2023 11:31:46 - INFO - __main__ -    macro_f1 = 0.48822851765316727
+11/03/2023 11:31:46 - INFO - __main__ -    num = 527
+11/03/2023 11:31:46 - INFO - __main__ -    prec_0 = 0.7686746987951807
+11/03/2023 11:31:46 - INFO - __main__ -    prec_1 = 0.17142857142857143
+11/03/2023 11:31:46 - INFO - __main__ -    prec_2 = 0.6493506493506493
+11/03/2023 11:31:46 - INFO - __main__ -    rec_0 = 0.9036827195467422
+11/03/2023 11:31:46 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 11:31:46 - INFO - __main__ -    rec_2 = 0.36496350364963503
+11/03/2023 11:31:46 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:31:46 - INFO - __main__ -   ***** Running evaluation 140 *****
+11/03/2023 11:31:46 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:31:46 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:31:50 - INFO - __main__ -   ***** Eval results 140 *****
+11/03/2023 11:31:50 - INFO - __main__ -    acc = 0.7208588957055214
+11/03/2023 11:31:50 - INFO - __main__ -    correct = 235
+11/03/2023 11:31:50 - INFO - __main__ -    f1_0 = 0.8477366255144033
+11/03/2023 11:31:50 - INFO - __main__ -    f1_1 = 0.1739130434782609
+11/03/2023 11:31:50 - INFO - __main__ -    f1_2 = 0.41666666666666663
+11/03/2023 11:31:50 - INFO - __main__ -    macro_f1 = 0.4794387785531103
+11/03/2023 11:31:50 - INFO - __main__ -    num = 326
+11/03/2023 11:31:50 - INFO - __main__ -    prec_0 = 0.7832699619771863
+11/03/2023 11:31:50 - INFO - __main__ -    prec_1 = 0.25
+11/03/2023 11:31:50 - INFO - __main__ -    prec_2 = 0.5319148936170213
+11/03/2023 11:31:50 - INFO - __main__ -    rec_0 = 0.9237668161434978
+11/03/2023 11:31:50 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:31:50 - INFO - __main__ -    rec_2 = 0.3424657534246575
+11/03/2023 11:31:50 - INFO - __main__ -    Dev accuracy = 0.7208588957055214
+11/03/2023 11:32:11 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:32:11 - INFO - __main__ -   ***** Running evaluation checkpoint-160 *****
+11/03/2023 11:32:11 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:32:11 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:32:17 - INFO - __main__ -   ***** Eval results checkpoint-160 *****
+11/03/2023 11:32:17 - INFO - __main__ -    acc = 0.6793168880455408
+11/03/2023 11:32:17 - INFO - __main__ -    correct = 358
+11/03/2023 11:32:17 - INFO - __main__ -    f1_0 = 0.8134110787172012
+11/03/2023 11:32:17 - INFO - __main__ -    f1_1 = 0.2268041237113402
+11/03/2023 11:32:17 - INFO - __main__ -    f1_2 = 0.5018450184501846
+11/03/2023 11:32:17 - INFO - __main__ -    macro_f1 = 0.514020073626242
+11/03/2023 11:32:17 - INFO - __main__ -    num = 527
+11/03/2023 11:32:17 - INFO - __main__ -    prec_0 = 0.8378378378378378
+11/03/2023 11:32:17 - INFO - __main__ -    prec_1 = 0.18333333333333332
+11/03/2023 11:32:17 - INFO - __main__ -    prec_2 = 0.5074626865671642
+11/03/2023 11:32:17 - INFO - __main__ -    rec_0 = 0.7903682719546742
+11/03/2023 11:32:17 - INFO - __main__ -    rec_1 = 0.2972972972972973
+11/03/2023 11:32:17 - INFO - __main__ -    rec_2 = 0.49635036496350365
+11/03/2023 11:32:17 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:32:17 - INFO - __main__ -   ***** Running evaluation 160 *****
+11/03/2023 11:32:17 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:32:17 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:32:21 - INFO - __main__ -   ***** Eval results 160 *****
+11/03/2023 11:32:21 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 11:32:21 - INFO - __main__ -    correct = 223
+11/03/2023 11:32:21 - INFO - __main__ -    f1_0 = 0.8277404921700223
+11/03/2023 11:32:21 - INFO - __main__ -    f1_1 = 0.18750000000000003
+11/03/2023 11:32:21 - INFO - __main__ -    f1_2 = 0.45390070921985815
+11/03/2023 11:32:21 - INFO - __main__ -    macro_f1 = 0.48971373379662686
+11/03/2023 11:32:21 - INFO - __main__ -    num = 326
+11/03/2023 11:32:21 - INFO - __main__ -    prec_0 = 0.8258928571428571
+11/03/2023 11:32:21 - INFO - __main__ -    prec_1 = 0.17647058823529413
+11/03/2023 11:32:21 - INFO - __main__ -    prec_2 = 0.47058823529411764
+11/03/2023 11:32:21 - INFO - __main__ -    rec_0 = 0.8295964125560538
+11/03/2023 11:32:21 - INFO - __main__ -    rec_1 = 0.2
+11/03/2023 11:32:21 - INFO - __main__ -    rec_2 = 0.4383561643835616
+11/03/2023 11:32:21 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 11:32:42 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:32:42 - INFO - __main__ -   ***** Running evaluation checkpoint-180 *****
+11/03/2023 11:32:42 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:32:42 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:32:48 - INFO - __main__ -   ***** Eval results checkpoint-180 *****
+11/03/2023 11:32:48 - INFO - __main__ -    acc = 0.7020872865275142
+11/03/2023 11:32:48 - INFO - __main__ -    correct = 370
+11/03/2023 11:32:48 - INFO - __main__ -    f1_0 = 0.826923076923077
+11/03/2023 11:32:48 - INFO - __main__ -    f1_1 = 0.07547169811320754
+11/03/2023 11:32:48 - INFO - __main__ -    f1_2 = 0.28402366863905326
+11/03/2023 11:32:48 - INFO - __main__ -    macro_f1 = 0.3954728145584459
+11/03/2023 11:32:48 - INFO - __main__ -    num = 527
+11/03/2023 11:32:48 - INFO - __main__ -    prec_0 = 0.7181628392484343
+11/03/2023 11:32:48 - INFO - __main__ -    prec_1 = 0.125
+11/03/2023 11:32:48 - INFO - __main__ -    prec_2 = 0.75
+11/03/2023 11:32:48 - INFO - __main__ -    rec_0 = 0.9745042492917847
+11/03/2023 11:32:48 - INFO - __main__ -    rec_1 = 0.05405405405405406
+11/03/2023 11:32:48 - INFO - __main__ -    rec_2 = 0.17518248175182483
+11/03/2023 11:32:48 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:32:48 - INFO - __main__ -   ***** Running evaluation 180 *****
+11/03/2023 11:32:48 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:32:48 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:32:52 - INFO - __main__ -   ***** Eval results 180 *****
+11/03/2023 11:32:52 - INFO - __main__ -    acc = 0.7147239263803681
+11/03/2023 11:32:52 - INFO - __main__ -    correct = 233
+11/03/2023 11:32:52 - INFO - __main__ -    f1_0 = 0.838206627680312
+11/03/2023 11:32:52 - INFO - __main__ -    f1_1 = 0.18181818181818182
+11/03/2023 11:32:52 - INFO - __main__ -    f1_2 = 0.29473684210526313
+11/03/2023 11:32:52 - INFO - __main__ -    macro_f1 = 0.438253883867919
+11/03/2023 11:32:52 - INFO - __main__ -    num = 326
+11/03/2023 11:32:52 - INFO - __main__ -    prec_0 = 0.7413793103448276
+11/03/2023 11:32:52 - INFO - __main__ -    prec_1 = 0.2857142857142857
+11/03/2023 11:32:52 - INFO - __main__ -    prec_2 = 0.6363636363636364
+11/03/2023 11:32:52 - INFO - __main__ -    rec_0 = 0.9641255605381166
+11/03/2023 11:32:52 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:32:52 - INFO - __main__ -    rec_2 = 0.1917808219178082
+11/03/2023 11:32:52 - INFO - __main__ -    Dev accuracy = 0.7147239263803681
+11/03/2023 11:33:13 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:33:13 - INFO - __main__ -   ***** Running evaluation checkpoint-200 *****
+11/03/2023 11:33:13 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:33:13 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:33:19 - INFO - __main__ -   ***** Eval results checkpoint-200 *****
+11/03/2023 11:33:19 - INFO - __main__ -    acc = 0.7115749525616698
+11/03/2023 11:33:19 - INFO - __main__ -    correct = 375
+11/03/2023 11:33:19 - INFO - __main__ -    f1_0 = 0.8326745718050066
+11/03/2023 11:33:19 - INFO - __main__ -    f1_1 = 0.15873015873015872
+11/03/2023 11:33:19 - INFO - __main__ -    f1_2 = 0.4655172413793104
+11/03/2023 11:33:19 - INFO - __main__ -    macro_f1 = 0.48564065730482525
+11/03/2023 11:33:19 - INFO - __main__ -    num = 527
+11/03/2023 11:33:19 - INFO - __main__ -    prec_0 = 0.7783251231527094
+11/03/2023 11:33:19 - INFO - __main__ -    prec_1 = 0.19230769230769232
+11/03/2023 11:33:19 - INFO - __main__ -    prec_2 = 0.5684210526315789
+11/03/2023 11:33:19 - INFO - __main__ -    rec_0 = 0.8951841359773371
+11/03/2023 11:33:19 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 11:33:19 - INFO - __main__ -    rec_2 = 0.39416058394160586
+11/03/2023 11:33:19 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:33:19 - INFO - __main__ -   ***** Running evaluation 200 *****
+11/03/2023 11:33:19 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:33:19 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:33:23 - INFO - __main__ -   ***** Eval results 200 *****
+11/03/2023 11:33:23 - INFO - __main__ -    acc = 0.7208588957055214
+11/03/2023 11:33:23 - INFO - __main__ -    correct = 235
+11/03/2023 11:33:23 - INFO - __main__ -    f1_0 = 0.839662447257384
+11/03/2023 11:33:23 - INFO - __main__ -    f1_1 = 0.19047619047619044
+11/03/2023 11:33:23 - INFO - __main__ -    f1_2 = 0.47058823529411764
+11/03/2023 11:33:23 - INFO - __main__ -    macro_f1 = 0.5002422910092307
+11/03/2023 11:33:23 - INFO - __main__ -    num = 326
+11/03/2023 11:33:23 - INFO - __main__ -    prec_0 = 0.7928286852589641
+11/03/2023 11:33:23 - INFO - __main__ -    prec_1 = 0.3333333333333333
+11/03/2023 11:33:23 - INFO - __main__ -    prec_2 = 0.5079365079365079
+11/03/2023 11:33:23 - INFO - __main__ -    rec_0 = 0.8923766816143498
+11/03/2023 11:33:23 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:33:23 - INFO - __main__ -    rec_2 = 0.4383561643835616
+11/03/2023 11:33:23 - INFO - __main__ -    Dev accuracy = 0.7208588957055214
+11/03/2023 11:33:44 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:33:44 - INFO - __main__ -   ***** Running evaluation checkpoint-220 *****
+11/03/2023 11:33:44 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:33:44 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:33:50 - INFO - __main__ -   ***** Eval results checkpoint-220 *****
+11/03/2023 11:33:50 - INFO - __main__ -    acc = 0.713472485768501
+11/03/2023 11:33:50 - INFO - __main__ -    correct = 376
+11/03/2023 11:33:50 - INFO - __main__ -    f1_0 = 0.8284625158831004
+11/03/2023 11:33:50 - INFO - __main__ -    f1_1 = 0.15151515151515152
+11/03/2023 11:33:50 - INFO - __main__ -    f1_2 = 0.44776119402985076
+11/03/2023 11:33:50 - INFO - __main__ -    macro_f1 = 0.47591295380936754
+11/03/2023 11:33:50 - INFO - __main__ -    num = 527
+11/03/2023 11:33:50 - INFO - __main__ -    prec_0 = 0.7511520737327189
+11/03/2023 11:33:50 - INFO - __main__ -    prec_1 = 0.1724137931034483
+11/03/2023 11:33:50 - INFO - __main__ -    prec_2 = 0.703125
+11/03/2023 11:33:50 - INFO - __main__ -    rec_0 = 0.9235127478753541
+11/03/2023 11:33:50 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 11:33:50 - INFO - __main__ -    rec_2 = 0.3284671532846715
+11/03/2023 11:33:50 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:33:50 - INFO - __main__ -   ***** Running evaluation 220 *****
+11/03/2023 11:33:50 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:33:50 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:33:54 - INFO - __main__ -   ***** Eval results 220 *****
+11/03/2023 11:33:54 - INFO - __main__ -    acc = 0.7147239263803681
+11/03/2023 11:33:54 - INFO - __main__ -    correct = 233
+11/03/2023 11:33:54 - INFO - __main__ -    f1_0 = 0.8427672955974843
+11/03/2023 11:33:54 - INFO - __main__ -    f1_1 = 0.125
+11/03/2023 11:33:54 - INFO - __main__ -    f1_2 = 0.4566929133858268
+11/03/2023 11:33:54 - INFO - __main__ -    macro_f1 = 0.47482006966110374
+11/03/2023 11:33:54 - INFO - __main__ -    num = 326
+11/03/2023 11:33:54 - INFO - __main__ -    prec_0 = 0.7913385826771654
+11/03/2023 11:33:54 - INFO - __main__ -    prec_1 = 0.16666666666666666
+11/03/2023 11:33:54 - INFO - __main__ -    prec_2 = 0.5370370370370371
+11/03/2023 11:33:54 - INFO - __main__ -    rec_0 = 0.9013452914798207
+11/03/2023 11:33:54 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 11:33:54 - INFO - __main__ -    rec_2 = 0.3972602739726027
+11/03/2023 11:33:54 - INFO - __main__ -    Dev accuracy = 0.7147239263803681
+11/03/2023 11:34:15 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:34:15 - INFO - __main__ -   ***** Running evaluation checkpoint-240 *****
+11/03/2023 11:34:15 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:34:15 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:34:22 - INFO - __main__ -   ***** Eval results checkpoint-240 *****
+11/03/2023 11:34:22 - INFO - __main__ -    acc = 0.6963946869070209
+11/03/2023 11:34:22 - INFO - __main__ -    correct = 367
+11/03/2023 11:34:22 - INFO - __main__ -    f1_0 = 0.8399487836107554
+11/03/2023 11:34:22 - INFO - __main__ -    f1_1 = 0.15730337078651685
+11/03/2023 11:34:22 - INFO - __main__ -    f1_2 = 0.34782608695652173
+11/03/2023 11:34:22 - INFO - __main__ -    macro_f1 = 0.44835941378459804
+11/03/2023 11:34:22 - INFO - __main__ -    num = 527
+11/03/2023 11:34:22 - INFO - __main__ -    prec_0 = 0.7663551401869159
+11/03/2023 11:34:22 - INFO - __main__ -    prec_1 = 0.1346153846153846
+11/03/2023 11:34:22 - INFO - __main__ -    prec_2 = 0.6808510638297872
+11/03/2023 11:34:22 - INFO - __main__ -    rec_0 = 0.9291784702549575
+11/03/2023 11:34:22 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 11:34:22 - INFO - __main__ -    rec_2 = 0.23357664233576642
+11/03/2023 11:34:22 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:34:22 - INFO - __main__ -   ***** Running evaluation 240 *****
+11/03/2023 11:34:22 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:34:22 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:34:25 - INFO - __main__ -   ***** Eval results 240 *****
+11/03/2023 11:34:25 - INFO - __main__ -    acc = 0.7116564417177914
+11/03/2023 11:34:25 - INFO - __main__ -    correct = 232
+11/03/2023 11:34:25 - INFO - __main__ -    f1_0 = 0.8440748440748441
+11/03/2023 11:34:25 - INFO - __main__ -    f1_1 = 0.2580645161290323
+11/03/2023 11:34:25 - INFO - __main__ -    f1_2 = 0.3853211009174312
+11/03/2023 11:34:25 - INFO - __main__ -    macro_f1 = 0.4958201537071026
+11/03/2023 11:34:25 - INFO - __main__ -    num = 326
+11/03/2023 11:34:25 - INFO - __main__ -    prec_0 = 0.7868217054263565
+11/03/2023 11:34:25 - INFO - __main__ -    prec_1 = 0.25
+11/03/2023 11:34:25 - INFO - __main__ -    prec_2 = 0.5833333333333334
+11/03/2023 11:34:25 - INFO - __main__ -    rec_0 = 0.9103139013452914
+11/03/2023 11:34:25 - INFO - __main__ -    rec_1 = 0.26666666666666666
+11/03/2023 11:34:25 - INFO - __main__ -    rec_2 = 0.2876712328767123
+11/03/2023 11:34:25 - INFO - __main__ -    Dev accuracy = 0.7116564417177914
+11/03/2023 11:34:47 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:34:47 - INFO - __main__ -   ***** Running evaluation checkpoint-260 *****
+11/03/2023 11:34:47 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:34:47 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:34:53 - INFO - __main__ -   ***** Eval results checkpoint-260 *****
+11/03/2023 11:34:53 - INFO - __main__ -    acc = 0.7058823529411765
+11/03/2023 11:34:53 - INFO - __main__ -    correct = 372
+11/03/2023 11:34:53 - INFO - __main__ -    f1_0 = 0.8345864661654135
+11/03/2023 11:34:53 - INFO - __main__ -    f1_1 = 0.16438356164383564
+11/03/2023 11:34:53 - INFO - __main__ -    f1_2 = 0.36065573770491804
+11/03/2023 11:34:53 - INFO - __main__ -    macro_f1 = 0.4532085885047224
+11/03/2023 11:34:53 - INFO - __main__ -    num = 527
+11/03/2023 11:34:53 - INFO - __main__ -    prec_0 = 0.748314606741573
+11/03/2023 11:34:53 - INFO - __main__ -    prec_1 = 0.16666666666666666
+11/03/2023 11:34:53 - INFO - __main__ -    prec_2 = 0.717391304347826
+11/03/2023 11:34:53 - INFO - __main__ -    rec_0 = 0.943342776203966
+11/03/2023 11:34:53 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 11:34:53 - INFO - __main__ -    rec_2 = 0.24087591240875914
+11/03/2023 11:34:53 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:34:53 - INFO - __main__ -   ***** Running evaluation 260 *****
+11/03/2023 11:34:53 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:34:53 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:34:57 - INFO - __main__ -   ***** Eval results 260 *****
+11/03/2023 11:34:57 - INFO - __main__ -    acc = 0.7331288343558282
+11/03/2023 11:34:57 - INFO - __main__ -    correct = 239
+11/03/2023 11:34:57 - INFO - __main__ -    f1_0 = 0.8530612244897959
+11/03/2023 11:34:57 - INFO - __main__ -    f1_1 = 0.30769230769230765
+11/03/2023 11:34:57 - INFO - __main__ -    f1_2 = 0.4
+11/03/2023 11:34:57 - INFO - __main__ -    macro_f1 = 0.5202511773940346
+11/03/2023 11:34:57 - INFO - __main__ -    num = 326
+11/03/2023 11:34:57 - INFO - __main__ -    prec_0 = 0.7827715355805244
+11/03/2023 11:34:57 - INFO - __main__ -    prec_1 = 0.36363636363636365
+11/03/2023 11:34:57 - INFO - __main__ -    prec_2 = 0.5945945945945946
+11/03/2023 11:34:57 - INFO - __main__ -    rec_0 = 0.9372197309417041
+11/03/2023 11:34:57 - INFO - __main__ -    rec_1 = 0.26666666666666666
+11/03/2023 11:34:57 - INFO - __main__ -    rec_2 = 0.3013698630136986
+11/03/2023 11:34:57 - INFO - __main__ -    Dev accuracy = 0.7331288343558282
+11/03/2023 11:34:57 - INFO - __main__ -    result['acc']=0.7331288343558282 > best_score=0.7239263803680982
+11/03/2023 11:34:58 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:35:01 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:35:22 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:35:22 - INFO - __main__ -   ***** Running evaluation checkpoint-280 *****
+11/03/2023 11:35:22 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:35:22 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:35:28 - INFO - __main__ -   ***** Eval results checkpoint-280 *****
+11/03/2023 11:35:28 - INFO - __main__ -    acc = 0.7172675521821632
+11/03/2023 11:35:28 - INFO - __main__ -    correct = 378
+11/03/2023 11:35:28 - INFO - __main__ -    f1_0 = 0.8360864040660737
+11/03/2023 11:35:28 - INFO - __main__ -    f1_1 = 0.19718309859154928
+11/03/2023 11:35:28 - INFO - __main__ -    f1_2 = 0.4285714285714286
+11/03/2023 11:35:28 - INFO - __main__ -    macro_f1 = 0.4872803104096839
+11/03/2023 11:35:28 - INFO - __main__ -    num = 527
+11/03/2023 11:35:28 - INFO - __main__ -    prec_0 = 0.7580645161290323
+11/03/2023 11:35:28 - INFO - __main__ -    prec_1 = 0.20588235294117646
+11/03/2023 11:35:28 - INFO - __main__ -    prec_2 = 0.711864406779661
+11/03/2023 11:35:28 - INFO - __main__ -    rec_0 = 0.9320113314447592
+11/03/2023 11:35:28 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 11:35:28 - INFO - __main__ -    rec_2 = 0.30656934306569344
+11/03/2023 11:35:28 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:35:28 - INFO - __main__ -   ***** Running evaluation 280 *****
+11/03/2023 11:35:28 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:35:28 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:35:32 - INFO - __main__ -   ***** Eval results 280 *****
+11/03/2023 11:35:32 - INFO - __main__ -    acc = 0.7177914110429447
+11/03/2023 11:35:32 - INFO - __main__ -    correct = 234
+11/03/2023 11:35:32 - INFO - __main__ -    f1_0 = 0.8518518518518519
+11/03/2023 11:35:32 - INFO - __main__ -    f1_1 = 0.1702127659574468
+11/03/2023 11:35:32 - INFO - __main__ -    f1_2 = 0.3865546218487395
+11/03/2023 11:35:32 - INFO - __main__ -    macro_f1 = 0.4695397465526794
+11/03/2023 11:35:32 - INFO - __main__ -    num = 326
+11/03/2023 11:35:32 - INFO - __main__ -    prec_0 = 0.7870722433460076
+11/03/2023 11:35:32 - INFO - __main__ -    prec_1 = 0.23529411764705882
+11/03/2023 11:35:32 - INFO - __main__ -    prec_2 = 0.5
+11/03/2023 11:35:32 - INFO - __main__ -    rec_0 = 0.9282511210762332
+11/03/2023 11:35:32 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:35:32 - INFO - __main__ -    rec_2 = 0.3150684931506849
+11/03/2023 11:35:32 - INFO - __main__ -    Dev accuracy = 0.7177914110429447
+11/03/2023 11:35:53 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:35:53 - INFO - __main__ -   ***** Running evaluation checkpoint-300 *****
+11/03/2023 11:35:53 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:35:53 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:35:59 - INFO - __main__ -   ***** Eval results checkpoint-300 *****
+11/03/2023 11:35:59 - INFO - __main__ -    acc = 0.7305502846299811
+11/03/2023 11:35:59 - INFO - __main__ -    correct = 385
+11/03/2023 11:35:59 - INFO - __main__ -    f1_0 = 0.8384710234278668
+11/03/2023 11:35:59 - INFO - __main__ -    f1_1 = 0.1923076923076923
+11/03/2023 11:35:59 - INFO - __main__ -    f1_2 = 0.418848167539267
+11/03/2023 11:35:59 - INFO - __main__ -    macro_f1 = 0.48320896109160866
+11/03/2023 11:35:59 - INFO - __main__ -    num = 527
+11/03/2023 11:35:59 - INFO - __main__ -    prec_0 = 0.74235807860262
+11/03/2023 11:35:59 - INFO - __main__ -    prec_1 = 0.3333333333333333
+11/03/2023 11:35:59 - INFO - __main__ -    prec_2 = 0.7407407407407407
+11/03/2023 11:35:59 - INFO - __main__ -    rec_0 = 0.9631728045325779
+11/03/2023 11:35:59 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 11:35:59 - INFO - __main__ -    rec_2 = 0.291970802919708
+11/03/2023 11:35:59 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:35:59 - INFO - __main__ -   ***** Running evaluation 300 *****
+11/03/2023 11:35:59 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:35:59 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:36:03 - INFO - __main__ -   ***** Eval results 300 *****
+11/03/2023 11:36:03 - INFO - __main__ -    acc = 0.7331288343558282
+11/03/2023 11:36:03 - INFO - __main__ -    correct = 239
+11/03/2023 11:36:03 - INFO - __main__ -    f1_0 = 0.8548387096774194
+11/03/2023 11:36:03 - INFO - __main__ -    f1_1 = 0.05555555555555555
+11/03/2023 11:36:03 - INFO - __main__ -    f1_2 = 0.4333333333333333
+11/03/2023 11:36:03 - INFO - __main__ -    macro_f1 = 0.44790919952210273
+11/03/2023 11:36:03 - INFO - __main__ -    num = 326
+11/03/2023 11:36:03 - INFO - __main__ -    prec_0 = 0.7765567765567766
+11/03/2023 11:36:03 - INFO - __main__ -    prec_1 = 0.16666666666666666
+11/03/2023 11:36:03 - INFO - __main__ -    prec_2 = 0.5531914893617021
+11/03/2023 11:36:03 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 11:36:03 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 11:36:03 - INFO - __main__ -    rec_2 = 0.3561643835616438
+11/03/2023 11:36:03 - INFO - __main__ -    Dev accuracy = 0.7331288343558282
+11/03/2023 11:36:24 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:36:24 - INFO - __main__ -   ***** Running evaluation checkpoint-320 *****
+11/03/2023 11:36:24 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:36:24 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:36:30 - INFO - __main__ -   ***** Eval results checkpoint-320 *****
+11/03/2023 11:36:30 - INFO - __main__ -    acc = 0.7267552182163188
+11/03/2023 11:36:30 - INFO - __main__ -    correct = 383
+11/03/2023 11:36:30 - INFO - __main__ -    f1_0 = 0.8351920693928129
+11/03/2023 11:36:30 - INFO - __main__ -    f1_1 = 0.163265306122449
+11/03/2023 11:36:30 - INFO - __main__ -    f1_2 = 0.42424242424242425
+11/03/2023 11:36:30 - INFO - __main__ -    macro_f1 = 0.47423326658589543
+11/03/2023 11:36:30 - INFO - __main__ -    num = 527
+11/03/2023 11:36:30 - INFO - __main__ -    prec_0 = 0.7422907488986784
+11/03/2023 11:36:30 - INFO - __main__ -    prec_1 = 0.3333333333333333
+11/03/2023 11:36:30 - INFO - __main__ -    prec_2 = 0.6885245901639344
+11/03/2023 11:36:30 - INFO - __main__ -    rec_0 = 0.9546742209631728
+11/03/2023 11:36:30 - INFO - __main__ -    rec_1 = 0.10810810810810811
+11/03/2023 11:36:30 - INFO - __main__ -    rec_2 = 0.30656934306569344
+11/03/2023 11:36:30 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:36:30 - INFO - __main__ -   ***** Running evaluation 320 *****
+11/03/2023 11:36:30 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:36:30 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:36:34 - INFO - __main__ -   ***** Eval results 320 *****
+11/03/2023 11:36:34 - INFO - __main__ -    acc = 0.7392638036809815
+11/03/2023 11:36:34 - INFO - __main__ -    correct = 241
+11/03/2023 11:36:34 - INFO - __main__ -    f1_0 = 0.8571428571428572
+11/03/2023 11:36:34 - INFO - __main__ -    f1_1 = 0.15
+11/03/2023 11:36:34 - INFO - __main__ -    f1_2 = 0.43478260869565216
+11/03/2023 11:36:34 - INFO - __main__ -    macro_f1 = 0.4806418219461697
+11/03/2023 11:36:34 - INFO - __main__ -    num = 326
+11/03/2023 11:36:34 - INFO - __main__ -    prec_0 = 0.7773722627737226
+11/03/2023 11:36:34 - INFO - __main__ -    prec_1 = 0.3
+11/03/2023 11:36:34 - INFO - __main__ -    prec_2 = 0.5952380952380952
+11/03/2023 11:36:34 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 11:36:34 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 11:36:34 - INFO - __main__ -    rec_2 = 0.3424657534246575
+11/03/2023 11:36:34 - INFO - __main__ -    Dev accuracy = 0.7392638036809815
+11/03/2023 11:36:34 - INFO - __main__ -    result['acc']=0.7392638036809815 > best_score=0.7331288343558282
+11/03/2023 11:36:36 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:36:38 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:36:59 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:36:59 - INFO - __main__ -   ***** Running evaluation checkpoint-340 *****
+11/03/2023 11:36:59 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:36:59 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:37:06 - INFO - __main__ -   ***** Eval results checkpoint-340 *****
+11/03/2023 11:37:06 - INFO - __main__ -    acc = 0.7248576850094877
+11/03/2023 11:37:06 - INFO - __main__ -    correct = 382
+11/03/2023 11:37:06 - INFO - __main__ -    f1_0 = 0.8309677419354838
+11/03/2023 11:37:06 - INFO - __main__ -    f1_1 = 0.24561403508771934
+11/03/2023 11:37:06 - INFO - __main__ -    f1_2 = 0.47747747747747743
+11/03/2023 11:37:06 - INFO - __main__ -    macro_f1 = 0.5180197515002268
+11/03/2023 11:37:06 - INFO - __main__ -    num = 527
+11/03/2023 11:37:06 - INFO - __main__ -    prec_0 = 0.7630331753554502
+11/03/2023 11:37:06 - INFO - __main__ -    prec_1 = 0.35
+11/03/2023 11:37:06 - INFO - __main__ -    prec_2 = 0.6235294117647059
+11/03/2023 11:37:06 - INFO - __main__ -    rec_0 = 0.9121813031161473
+11/03/2023 11:37:06 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 11:37:06 - INFO - __main__ -    rec_2 = 0.38686131386861317
+11/03/2023 11:37:06 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:37:06 - INFO - __main__ -   ***** Running evaluation 340 *****
+11/03/2023 11:37:06 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:37:06 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:37:09 - INFO - __main__ -   ***** Eval results 340 *****
+11/03/2023 11:37:09 - INFO - __main__ -    acc = 0.7300613496932515
+11/03/2023 11:37:09 - INFO - __main__ -    correct = 238
+11/03/2023 11:37:09 - INFO - __main__ -    f1_0 = 0.860125260960334
+11/03/2023 11:37:09 - INFO - __main__ -    f1_1 = 0.09302325581395349
+11/03/2023 11:37:09 - INFO - __main__ -    f1_2 = 0.46153846153846156
+11/03/2023 11:37:09 - INFO - __main__ -    macro_f1 = 0.4715623261042497
+11/03/2023 11:37:09 - INFO - __main__ -    num = 326
+11/03/2023 11:37:09 - INFO - __main__ -    prec_0 = 0.8046875
+11/03/2023 11:37:09 - INFO - __main__ -    prec_1 = 0.15384615384615385
+11/03/2023 11:37:09 - INFO - __main__ -    prec_2 = 0.5263157894736842
+11/03/2023 11:37:09 - INFO - __main__ -    rec_0 = 0.9237668161434978
+11/03/2023 11:37:09 - INFO - __main__ -    rec_1 = 0.06666666666666667
+11/03/2023 11:37:09 - INFO - __main__ -    rec_2 = 0.410958904109589
+11/03/2023 11:37:09 - INFO - __main__ -    Dev accuracy = 0.7300613496932515
+11/03/2023 11:37:31 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:37:31 - INFO - __main__ -   ***** Running evaluation checkpoint-360 *****
+11/03/2023 11:37:31 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:37:31 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:37:37 - INFO - __main__ -   ***** Eval results checkpoint-360 *****
+11/03/2023 11:37:37 - INFO - __main__ -    acc = 0.7210626185958254
+11/03/2023 11:37:37 - INFO - __main__ -    correct = 380
+11/03/2023 11:37:37 - INFO - __main__ -    f1_0 = 0.8303341902313625
+11/03/2023 11:37:37 - INFO - __main__ -    f1_1 = 0.26666666666666666
+11/03/2023 11:37:37 - INFO - __main__ -    f1_2 = 0.45370370370370366
+11/03/2023 11:37:37 - INFO - __main__ -    macro_f1 = 0.5169015202005777
+11/03/2023 11:37:37 - INFO - __main__ -    num = 527
+11/03/2023 11:37:37 - INFO - __main__ -    prec_0 = 0.76
+11/03/2023 11:37:37 - INFO - __main__ -    prec_1 = 0.34782608695652173
+11/03/2023 11:37:37 - INFO - __main__ -    prec_2 = 0.620253164556962
+11/03/2023 11:37:37 - INFO - __main__ -    rec_0 = 0.9150141643059491
+11/03/2023 11:37:37 - INFO - __main__ -    rec_1 = 0.21621621621621623
+11/03/2023 11:37:37 - INFO - __main__ -    rec_2 = 0.35766423357664234
+11/03/2023 11:37:37 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:37:37 - INFO - __main__ -   ***** Running evaluation 360 *****
+11/03/2023 11:37:37 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:37:37 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:37:41 - INFO - __main__ -   ***** Eval results 360 *****
+11/03/2023 11:37:41 - INFO - __main__ -    acc = 0.7331288343558282
+11/03/2023 11:37:41 - INFO - __main__ -    correct = 239
+11/03/2023 11:37:41 - INFO - __main__ -    f1_0 = 0.8547717842323651
+11/03/2023 11:37:41 - INFO - __main__ -    f1_1 = 0.18181818181818182
+11/03/2023 11:37:41 - INFO - __main__ -    f1_2 = 0.46031746031746035
+11/03/2023 11:37:41 - INFO - __main__ -    macro_f1 = 0.49896914212266913
+11/03/2023 11:37:41 - INFO - __main__ -    num = 326
+11/03/2023 11:37:41 - INFO - __main__ -    prec_0 = 0.7953667953667953
+11/03/2023 11:37:41 - INFO - __main__ -    prec_1 = 0.2857142857142857
+11/03/2023 11:37:41 - INFO - __main__ -    prec_2 = 0.5471698113207547
+11/03/2023 11:37:41 - INFO - __main__ -    rec_0 = 0.9237668161434978
+11/03/2023 11:37:41 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:37:41 - INFO - __main__ -    rec_2 = 0.3972602739726027
+11/03/2023 11:37:41 - INFO - __main__ -    Dev accuracy = 0.7331288343558282
+11/03/2023 11:38:02 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:38:02 - INFO - __main__ -   ***** Running evaluation checkpoint-380 *****
+11/03/2023 11:38:02 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:38:02 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:38:08 - INFO - __main__ -   ***** Eval results checkpoint-380 *****
+11/03/2023 11:38:08 - INFO - __main__ -    acc = 0.7096774193548387
+11/03/2023 11:38:08 - INFO - __main__ -    correct = 374
+11/03/2023 11:38:08 - INFO - __main__ -    f1_0 = 0.8306148055207028
+11/03/2023 11:38:08 - INFO - __main__ -    f1_1 = 0.20000000000000004
+11/03/2023 11:38:08 - INFO - __main__ -    f1_2 = 0.3850267379679144
+11/03/2023 11:38:08 - INFO - __main__ -    macro_f1 = 0.4718805144962057
+11/03/2023 11:38:08 - INFO - __main__ -    num = 527
+11/03/2023 11:38:08 - INFO - __main__ -    prec_0 = 0.7454954954954955
+11/03/2023 11:38:08 - INFO - __main__ -    prec_1 = 0.21212121212121213
+11/03/2023 11:38:08 - INFO - __main__ -    prec_2 = 0.72
+11/03/2023 11:38:08 - INFO - __main__ -    rec_0 = 0.9376770538243626
+11/03/2023 11:38:08 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 11:38:08 - INFO - __main__ -    rec_2 = 0.26277372262773724
+11/03/2023 11:38:08 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:38:08 - INFO - __main__ -   ***** Running evaluation 380 *****
+11/03/2023 11:38:08 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:38:08 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:38:12 - INFO - __main__ -   ***** Eval results 380 *****
+11/03/2023 11:38:12 - INFO - __main__ -    acc = 0.745398773006135
+11/03/2023 11:38:12 - INFO - __main__ -    correct = 243
+11/03/2023 11:38:12 - INFO - __main__ -    f1_0 = 0.8635437881873727
+11/03/2023 11:38:12 - INFO - __main__ -    f1_1 = 0.2857142857142857
+11/03/2023 11:38:12 - INFO - __main__ -    f1_2 = 0.42857142857142855
+11/03/2023 11:38:12 - INFO - __main__ -    macro_f1 = 0.525943167491029
+11/03/2023 11:38:12 - INFO - __main__ -    num = 326
+11/03/2023 11:38:12 - INFO - __main__ -    prec_0 = 0.7910447761194029
+11/03/2023 11:38:12 - INFO - __main__ -    prec_1 = 0.3684210526315789
+11/03/2023 11:38:12 - INFO - __main__ -    prec_2 = 0.6153846153846154
+11/03/2023 11:38:12 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 11:38:12 - INFO - __main__ -    rec_1 = 0.23333333333333334
+11/03/2023 11:38:12 - INFO - __main__ -    rec_2 = 0.3287671232876712
+11/03/2023 11:38:12 - INFO - __main__ -    Dev accuracy = 0.745398773006135
+11/03/2023 11:38:12 - INFO - __main__ -    result['acc']=0.745398773006135 > best_score=0.7392638036809815
+11/03/2023 11:38:13 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:38:16 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 11:38:37 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:38:37 - INFO - __main__ -   ***** Running evaluation checkpoint-400 *****
+11/03/2023 11:38:37 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:38:37 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:38:43 - INFO - __main__ -   ***** Eval results checkpoint-400 *****
+11/03/2023 11:38:43 - INFO - __main__ -    acc = 0.7115749525616698
+11/03/2023 11:38:43 - INFO - __main__ -    correct = 375
+11/03/2023 11:38:43 - INFO - __main__ -    f1_0 = 0.832313341493268
+11/03/2023 11:38:43 - INFO - __main__ -    f1_1 = 0.1935483870967742
+11/03/2023 11:38:43 - INFO - __main__ -    f1_2 = 0.33142857142857146
+11/03/2023 11:38:43 - INFO - __main__ -    macro_f1 = 0.45243010000620454
+11/03/2023 11:38:43 - INFO - __main__ -    num = 527
+11/03/2023 11:38:43 - INFO - __main__ -    prec_0 = 0.7327586206896551
+11/03/2023 11:38:43 - INFO - __main__ -    prec_1 = 0.24
+11/03/2023 11:38:43 - INFO - __main__ -    prec_2 = 0.7631578947368421
+11/03/2023 11:38:43 - INFO - __main__ -    rec_0 = 0.9631728045325779
+11/03/2023 11:38:43 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 11:38:43 - INFO - __main__ -    rec_2 = 0.2116788321167883
+11/03/2023 11:38:43 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:38:43 - INFO - __main__ -   ***** Running evaluation 400 *****
+11/03/2023 11:38:43 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:38:43 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:38:47 - INFO - __main__ -   ***** Eval results 400 *****
+11/03/2023 11:38:47 - INFO - __main__ -    acc = 0.7392638036809815
+11/03/2023 11:38:47 - INFO - __main__ -    correct = 241
+11/03/2023 11:38:47 - INFO - __main__ -    f1_0 = 0.8577154308617234
+11/03/2023 11:38:47 - INFO - __main__ -    f1_1 = 0.26086956521739135
+11/03/2023 11:38:47 - INFO - __main__ -    f1_2 = 0.39252336448598124
+11/03/2023 11:38:47 - INFO - __main__ -    macro_f1 = 0.503702786855032
+11/03/2023 11:38:47 - INFO - __main__ -    num = 326
+11/03/2023 11:38:47 - INFO - __main__ -    prec_0 = 0.7753623188405797
+11/03/2023 11:38:47 - INFO - __main__ -    prec_1 = 0.375
+11/03/2023 11:38:47 - INFO - __main__ -    prec_2 = 0.6176470588235294
+11/03/2023 11:38:47 - INFO - __main__ -    rec_0 = 0.9596412556053812
+11/03/2023 11:38:47 - INFO - __main__ -    rec_1 = 0.2
+11/03/2023 11:38:47 - INFO - __main__ -    rec_2 = 0.2876712328767123
+11/03/2023 11:38:47 - INFO - __main__ -    Dev accuracy = 0.7392638036809815
+11/03/2023 11:39:08 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:39:08 - INFO - __main__ -   ***** Running evaluation checkpoint-420 *****
+11/03/2023 11:39:08 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:39:08 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:39:14 - INFO - __main__ -   ***** Eval results checkpoint-420 *****
+11/03/2023 11:39:14 - INFO - __main__ -    acc = 0.7191650853889943
+11/03/2023 11:39:14 - INFO - __main__ -    correct = 379
+11/03/2023 11:39:14 - INFO - __main__ -    f1_0 = 0.8312342569269521
+11/03/2023 11:39:14 - INFO - __main__ -    f1_1 = 0.22222222222222224
+11/03/2023 11:39:14 - INFO - __main__ -    f1_2 = 0.4263959390862944
+11/03/2023 11:39:14 - INFO - __main__ -    macro_f1 = 0.49328413941182286
+11/03/2023 11:39:14 - INFO - __main__ -    num = 527
+11/03/2023 11:39:14 - INFO - __main__ -    prec_0 = 0.7482993197278912
+11/03/2023 11:39:14 - INFO - __main__ -    prec_1 = 0.2692307692307692
+11/03/2023 11:39:14 - INFO - __main__ -    prec_2 = 0.7
+11/03/2023 11:39:14 - INFO - __main__ -    rec_0 = 0.9348441926345609
+11/03/2023 11:39:14 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 11:39:14 - INFO - __main__ -    rec_2 = 0.30656934306569344
+11/03/2023 11:39:14 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:39:14 - INFO - __main__ -   ***** Running evaluation 420 *****
+11/03/2023 11:39:14 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:39:14 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:39:18 - INFO - __main__ -   ***** Eval results 420 *****
+11/03/2023 11:39:18 - INFO - __main__ -    acc = 0.745398773006135
+11/03/2023 11:39:18 - INFO - __main__ -    correct = 243
+11/03/2023 11:39:18 - INFO - __main__ -    f1_0 = 0.8658536585365852
+11/03/2023 11:39:18 - INFO - __main__ -    f1_1 = 0.18181818181818182
+11/03/2023 11:39:18 - INFO - __main__ -    f1_2 = 0.44827586206896547
+11/03/2023 11:39:18 - INFO - __main__ -    macro_f1 = 0.49864923414124424
+11/03/2023 11:39:18 - INFO - __main__ -    num = 326
+11/03/2023 11:39:18 - INFO - __main__ -    prec_0 = 0.79182156133829
+11/03/2023 11:39:18 - INFO - __main__ -    prec_1 = 0.2857142857142857
+11/03/2023 11:39:18 - INFO - __main__ -    prec_2 = 0.6046511627906976
+11/03/2023 11:39:18 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 11:39:18 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:39:18 - INFO - __main__ -    rec_2 = 0.3561643835616438
+11/03/2023 11:39:18 - INFO - __main__ -    Dev accuracy = 0.745398773006135
+11/03/2023 11:39:39 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:39:39 - INFO - __main__ -   ***** Running evaluation checkpoint-440 *****
+11/03/2023 11:39:39 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:39:39 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:39:45 - INFO - __main__ -   ***** Eval results checkpoint-440 *****
+11/03/2023 11:39:45 - INFO - __main__ -    acc = 0.7172675521821632
+11/03/2023 11:39:45 - INFO - __main__ -    correct = 378
+11/03/2023 11:39:45 - INFO - __main__ -    f1_0 = 0.8382165605095542
+11/03/2023 11:39:45 - INFO - __main__ -    f1_1 = 0.23684210526315788
+11/03/2023 11:39:45 - INFO - __main__ -    f1_2 = 0.41450777202072536
+11/03/2023 11:39:45 - INFO - __main__ -    macro_f1 = 0.4965221459311458
+11/03/2023 11:39:45 - INFO - __main__ -    num = 527
+11/03/2023 11:39:45 - INFO - __main__ -    prec_0 = 0.7615740740740741
+11/03/2023 11:39:45 - INFO - __main__ -    prec_1 = 0.23076923076923078
+11/03/2023 11:39:45 - INFO - __main__ -    prec_2 = 0.7142857142857143
+11/03/2023 11:39:45 - INFO - __main__ -    rec_0 = 0.9320113314447592
+11/03/2023 11:39:45 - INFO - __main__ -    rec_1 = 0.24324324324324326
+11/03/2023 11:39:45 - INFO - __main__ -    rec_2 = 0.291970802919708
+11/03/2023 11:39:45 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:39:45 - INFO - __main__ -   ***** Running evaluation 440 *****
+11/03/2023 11:39:45 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:39:45 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:39:49 - INFO - __main__ -   ***** Eval results 440 *****
+11/03/2023 11:39:49 - INFO - __main__ -    acc = 0.745398773006135
+11/03/2023 11:39:49 - INFO - __main__ -    correct = 243
+11/03/2023 11:39:49 - INFO - __main__ -    f1_0 = 0.8670756646216768
+11/03/2023 11:39:49 - INFO - __main__ -    f1_1 = 0.24489795918367346
+11/03/2023 11:39:49 - INFO - __main__ -    f1_2 = 0.43859649122807015
+11/03/2023 11:39:49 - INFO - __main__ -    macro_f1 = 0.5168567050111402
+11/03/2023 11:39:49 - INFO - __main__ -    num = 326
+11/03/2023 11:39:49 - INFO - __main__ -    prec_0 = 0.7969924812030075
+11/03/2023 11:39:49 - INFO - __main__ -    prec_1 = 0.3157894736842105
+11/03/2023 11:39:49 - INFO - __main__ -    prec_2 = 0.6097560975609756
+11/03/2023 11:39:49 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 11:39:49 - INFO - __main__ -    rec_1 = 0.2
+11/03/2023 11:39:49 - INFO - __main__ -    rec_2 = 0.3424657534246575
+11/03/2023 11:39:49 - INFO - __main__ -    Dev accuracy = 0.745398773006135
+11/03/2023 11:40:10 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:40:10 - INFO - __main__ -   ***** Running evaluation checkpoint-460 *****
+11/03/2023 11:40:10 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:40:10 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:40:17 - INFO - __main__ -   ***** Eval results checkpoint-460 *****
+11/03/2023 11:40:17 - INFO - __main__ -    acc = 0.7210626185958254
+11/03/2023 11:40:17 - INFO - __main__ -    correct = 380
+11/03/2023 11:40:17 - INFO - __main__ -    f1_0 = 0.834975369458128
+11/03/2023 11:40:17 - INFO - __main__ -    f1_1 = 0.2
+11/03/2023 11:40:17 - INFO - __main__ -    f1_2 = 0.38461538461538464
+11/03/2023 11:40:17 - INFO - __main__ -    macro_f1 = 0.4731969180245042
+11/03/2023 11:40:17 - INFO - __main__ -    num = 527
+11/03/2023 11:40:17 - INFO - __main__ -    prec_0 = 0.738562091503268
+11/03/2023 11:40:17 - INFO - __main__ -    prec_1 = 0.2608695652173913
+11/03/2023 11:40:17 - INFO - __main__ -    prec_2 = 0.7777777777777778
+11/03/2023 11:40:17 - INFO - __main__ -    rec_0 = 0.9603399433427762
+11/03/2023 11:40:17 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 11:40:17 - INFO - __main__ -    rec_2 = 0.25547445255474455
+11/03/2023 11:40:17 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:40:17 - INFO - __main__ -   ***** Running evaluation 460 *****
+11/03/2023 11:40:17 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:40:17 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:40:20 - INFO - __main__ -   ***** Eval results 460 *****
+11/03/2023 11:40:20 - INFO - __main__ -    acc = 0.7423312883435583
+11/03/2023 11:40:20 - INFO - __main__ -    correct = 242
+11/03/2023 11:40:20 - INFO - __main__ -    f1_0 = 0.8623481781376519
+11/03/2023 11:40:20 - INFO - __main__ -    f1_1 = 0.2222222222222222
+11/03/2023 11:40:20 - INFO - __main__ -    f1_2 = 0.4247787610619469
+11/03/2023 11:40:20 - INFO - __main__ -    macro_f1 = 0.5031163871406069
+11/03/2023 11:40:20 - INFO - __main__ -    num = 326
+11/03/2023 11:40:20 - INFO - __main__ -    prec_0 = 0.7859778597785978
+11/03/2023 11:40:20 - INFO - __main__ -    prec_1 = 0.3333333333333333
+11/03/2023 11:40:20 - INFO - __main__ -    prec_2 = 0.6
+11/03/2023 11:40:20 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 11:40:20 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 11:40:20 - INFO - __main__ -    rec_2 = 0.3287671232876712
+11/03/2023 11:40:20 - INFO - __main__ -    Dev accuracy = 0.7423312883435583
+11/03/2023 11:40:42 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:40:42 - INFO - __main__ -   ***** Running evaluation checkpoint-480 *****
+11/03/2023 11:40:42 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:40:42 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:40:48 - INFO - __main__ -   ***** Eval results checkpoint-480 *****
+11/03/2023 11:40:48 - INFO - __main__ -    acc = 0.7286527514231499
+11/03/2023 11:40:48 - INFO - __main__ -    correct = 384
+11/03/2023 11:40:48 - INFO - __main__ -    f1_0 = 0.8339768339768339
+11/03/2023 11:40:48 - INFO - __main__ -    f1_1 = 0.26865671641791045
+11/03/2023 11:40:48 - INFO - __main__ -    f1_2 = 0.4857142857142857
+11/03/2023 11:40:48 - INFO - __main__ -    macro_f1 = 0.5294492787030101
+11/03/2023 11:40:48 - INFO - __main__ -    num = 527
+11/03/2023 11:40:48 - INFO - __main__ -    prec_0 = 0.7641509433962265
+11/03/2023 11:40:48 - INFO - __main__ -    prec_1 = 0.3
+11/03/2023 11:40:48 - INFO - __main__ -    prec_2 = 0.6986301369863014
+11/03/2023 11:40:48 - INFO - __main__ -    rec_0 = 0.9178470254957507
+11/03/2023 11:40:48 - INFO - __main__ -    rec_1 = 0.24324324324324326
+11/03/2023 11:40:48 - INFO - __main__ -    rec_2 = 0.3722627737226277
+11/03/2023 11:40:48 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:40:48 - INFO - __main__ -   ***** Running evaluation 480 *****
+11/03/2023 11:40:48 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:40:48 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:40:52 - INFO - __main__ -   ***** Eval results 480 *****
+11/03/2023 11:40:52 - INFO - __main__ -    acc = 0.745398773006135
+11/03/2023 11:40:52 - INFO - __main__ -    correct = 243
+11/03/2023 11:40:52 - INFO - __main__ -    f1_0 = 0.8625
+11/03/2023 11:40:52 - INFO - __main__ -    f1_1 = 0.1739130434782609
+11/03/2023 11:40:52 - INFO - __main__ -    f1_2 = 0.507936507936508
+11/03/2023 11:40:52 - INFO - __main__ -    macro_f1 = 0.5147831838049229
+11/03/2023 11:40:52 - INFO - __main__ -    num = 326
+11/03/2023 11:40:52 - INFO - __main__ -    prec_0 = 0.8054474708171206
+11/03/2023 11:40:52 - INFO - __main__ -    prec_1 = 0.25
+11/03/2023 11:40:52 - INFO - __main__ -    prec_2 = 0.6037735849056604
+11/03/2023 11:40:52 - INFO - __main__ -    rec_0 = 0.9282511210762332
+11/03/2023 11:40:52 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:40:52 - INFO - __main__ -    rec_2 = 0.4383561643835616
+11/03/2023 11:40:52 - INFO - __main__ -    Dev accuracy = 0.745398773006135
+11/03/2023 11:41:13 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:41:13 - INFO - __main__ -   ***** Running evaluation checkpoint-500 *****
+11/03/2023 11:41:13 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:41:13 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:41:19 - INFO - __main__ -   ***** Eval results checkpoint-500 *****
+11/03/2023 11:41:19 - INFO - __main__ -    acc = 0.7191650853889943
+11/03/2023 11:41:19 - INFO - __main__ -    correct = 379
+11/03/2023 11:41:19 - INFO - __main__ -    f1_0 = 0.8376703841387856
+11/03/2023 11:41:19 - INFO - __main__ -    f1_1 = 0.21212121212121213
+11/03/2023 11:41:19 - INFO - __main__ -    f1_2 = 0.37569060773480667
+11/03/2023 11:41:19 - INFO - __main__ -    macro_f1 = 0.47516073466493475
+11/03/2023 11:41:19 - INFO - __main__ -    num = 527
+11/03/2023 11:41:19 - INFO - __main__ -    prec_0 = 0.7444933920704846
+11/03/2023 11:41:19 - INFO - __main__ -    prec_1 = 0.2413793103448276
+11/03/2023 11:41:19 - INFO - __main__ -    prec_2 = 0.7727272727272727
+11/03/2023 11:41:19 - INFO - __main__ -    rec_0 = 0.9575070821529745
+11/03/2023 11:41:19 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 11:41:19 - INFO - __main__ -    rec_2 = 0.24817518248175183
+11/03/2023 11:41:19 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:41:19 - INFO - __main__ -   ***** Running evaluation 500 *****
+11/03/2023 11:41:19 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:41:19 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:41:23 - INFO - __main__ -   ***** Eval results 500 *****
+11/03/2023 11:41:23 - INFO - __main__ -    acc = 0.7392638036809815
+11/03/2023 11:41:23 - INFO - __main__ -    correct = 241
+11/03/2023 11:41:23 - INFO - __main__ -    f1_0 = 0.8658536585365852
+11/03/2023 11:41:23 - INFO - __main__ -    f1_1 = 0.21276595744680848
+11/03/2023 11:41:23 - INFO - __main__ -    f1_2 = 0.4070796460176991
+11/03/2023 11:41:23 - INFO - __main__ -    macro_f1 = 0.49523308733369764
+11/03/2023 11:41:23 - INFO - __main__ -    num = 326
+11/03/2023 11:41:23 - INFO - __main__ -    prec_0 = 0.79182156133829
+11/03/2023 11:41:23 - INFO - __main__ -    prec_1 = 0.29411764705882354
+11/03/2023 11:41:23 - INFO - __main__ -    prec_2 = 0.575
+11/03/2023 11:41:23 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 11:41:23 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 11:41:23 - INFO - __main__ -    rec_2 = 0.3150684931506849
+11/03/2023 11:41:23 - INFO - __main__ -    Dev accuracy = 0.7392638036809815
+11/03/2023 11:41:44 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:41:44 - INFO - __main__ -   ***** Running evaluation checkpoint-520 *****
+11/03/2023 11:41:44 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:41:44 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:41:50 - INFO - __main__ -   ***** Eval results checkpoint-520 *****
+11/03/2023 11:41:50 - INFO - __main__ -    acc = 0.7248576850094877
+11/03/2023 11:41:50 - INFO - __main__ -    correct = 382
+11/03/2023 11:41:50 - INFO - __main__ -    f1_0 = 0.8368617683686178
+11/03/2023 11:41:50 - INFO - __main__ -    f1_1 = 0.22222222222222224
+11/03/2023 11:41:50 - INFO - __main__ -    f1_2 = 0.4148936170212766
+11/03/2023 11:41:50 - INFO - __main__ -    macro_f1 = 0.4913258692040389
+11/03/2023 11:41:50 - INFO - __main__ -    num = 527
+11/03/2023 11:41:50 - INFO - __main__ -    prec_0 = 0.7466666666666667
+11/03/2023 11:41:50 - INFO - __main__ -    prec_1 = 0.2692307692307692
+11/03/2023 11:41:50 - INFO - __main__ -    prec_2 = 0.7647058823529411
+11/03/2023 11:41:50 - INFO - __main__ -    rec_0 = 0.9518413597733711
+11/03/2023 11:41:50 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 11:41:50 - INFO - __main__ -    rec_2 = 0.2846715328467153
+11/03/2023 11:41:50 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:41:50 - INFO - __main__ -   ***** Running evaluation 520 *****
+11/03/2023 11:41:50 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:41:50 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:41:54 - INFO - __main__ -   ***** Eval results 520 *****
+11/03/2023 11:41:54 - INFO - __main__ -    acc = 0.7423312883435583
+11/03/2023 11:41:54 - INFO - __main__ -    correct = 242
+11/03/2023 11:41:54 - INFO - __main__ -    f1_0 = 0.8658536585365852
+11/03/2023 11:41:54 - INFO - __main__ -    f1_1 = 0.18181818181818182
+11/03/2023 11:41:54 - INFO - __main__ -    f1_2 = 0.43103448275862066
+11/03/2023 11:41:54 - INFO - __main__ -    macro_f1 = 0.49290210770446263
+11/03/2023 11:41:54 - INFO - __main__ -    num = 326
+11/03/2023 11:41:54 - INFO - __main__ -    prec_0 = 0.79182156133829
+11/03/2023 11:41:54 - INFO - __main__ -    prec_1 = 0.2857142857142857
+11/03/2023 11:41:54 - INFO - __main__ -    prec_2 = 0.5813953488372093
+11/03/2023 11:41:54 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 11:41:54 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:41:54 - INFO - __main__ -    rec_2 = 0.3424657534246575
+11/03/2023 11:41:54 - INFO - __main__ -    Dev accuracy = 0.7423312883435583
+11/03/2023 11:42:04 - INFO - __main__ -    global_step = 530, average loss = 0.4488010585747378
+11/03/2023 11:42:04 - INFO - __main__ -    best checkpoint = ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best, best score = 0.745398773006135
+11/03/2023 11:42:04 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//
+11/03/2023 11:42:08 - INFO - __main__ -   Evaluate the following checkpoints: ['./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256/checkpoint-best', './outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256']
+11/03/2023 11:42:11 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:42:11 - INFO - __main__ -   ***** Running evaluation checkpoint-best *****
+11/03/2023 11:42:11 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:42:11 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:42:14 - INFO - __main__ -   ***** Eval results checkpoint-best *****
+11/03/2023 11:42:14 - INFO - __main__ -    acc = 0.745398773006135
+11/03/2023 11:42:14 - INFO - __main__ -    correct = 243
+11/03/2023 11:42:14 - INFO - __main__ -    f1_0 = 0.8635437881873727
+11/03/2023 11:42:14 - INFO - __main__ -    f1_1 = 0.2857142857142857
+11/03/2023 11:42:14 - INFO - __main__ -    f1_2 = 0.42857142857142855
+11/03/2023 11:42:14 - INFO - __main__ -    macro_f1 = 0.525943167491029
+11/03/2023 11:42:14 - INFO - __main__ -    num = 326
+11/03/2023 11:42:14 - INFO - __main__ -    prec_0 = 0.7910447761194029
+11/03/2023 11:42:14 - INFO - __main__ -    prec_1 = 0.3684210526315789
+11/03/2023 11:42:14 - INFO - __main__ -    prec_2 = 0.6153846153846154
+11/03/2023 11:42:14 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 11:42:14 - INFO - __main__ -    rec_1 = 0.23333333333333334
+11/03/2023 11:42:14 - INFO - __main__ -    rec_2 = 0.3287671232876712
+11/03/2023 11:42:17 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 11:42:17 - INFO - __main__ -   ***** Running evaluation  *****
+11/03/2023 11:42:17 - INFO - __main__ -     Num examples = 326
+11/03/2023 11:42:17 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:42:21 - INFO - __main__ -   ***** Eval results  *****
+11/03/2023 11:42:21 - INFO - __main__ -    acc = 0.7423312883435583
+11/03/2023 11:42:21 - INFO - __main__ -    correct = 242
+11/03/2023 11:42:21 - INFO - __main__ -    f1_0 = 0.8658536585365852
+11/03/2023 11:42:21 - INFO - __main__ -    f1_1 = 0.18181818181818182
+11/03/2023 11:42:21 - INFO - __main__ -    f1_2 = 0.43103448275862066
+11/03/2023 11:42:21 - INFO - __main__ -    macro_f1 = 0.49290210770446263
+11/03/2023 11:42:21 - INFO - __main__ -    num = 326
+11/03/2023 11:42:21 - INFO - __main__ -    prec_0 = 0.79182156133829
+11/03/2023 11:42:21 - INFO - __main__ -    prec_1 = 0.2857142857142857
+11/03/2023 11:42:21 - INFO - __main__ -    prec_2 = 0.5813953488372093
+11/03/2023 11:42:21 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 11:42:21 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 11:42:21 - INFO - __main__ -    rec_2 = 0.3424657534246575
+11/03/2023 11:42:21 - INFO - __main__ -   Best checkpoint is ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256/checkpoint-best, best accuracy is 0.745398773006135
+11/03/2023 11:42:23 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 11:42:23 - INFO - __main__ -   ***** Running evaluation best_checkpoint *****
+11/03/2023 11:42:23 - INFO - __main__ -     Num examples = 527
+11/03/2023 11:42:23 - INFO - __main__ -     Batch size = 8
+11/03/2023 11:42:30 - INFO - __main__ -   ***** Save prediction ******
+11/03/2023 11:42:30 - INFO - __main__ -   ***** Eval results best_checkpoint *****
+11/03/2023 11:42:30 - INFO - __main__ -    acc = 0.7096774193548387
+11/03/2023 11:42:30 - INFO - __main__ -    correct = 374
+11/03/2023 11:42:30 - INFO - __main__ -    f1_0 = 0.8306148055207028
+11/03/2023 11:42:30 - INFO - __main__ -    f1_1 = 0.20000000000000004
+11/03/2023 11:42:30 - INFO - __main__ -    f1_2 = 0.3850267379679144
+11/03/2023 11:42:30 - INFO - __main__ -    macro_f1 = 0.4718805144962057
+11/03/2023 11:42:30 - INFO - __main__ -    num = 527
+11/03/2023 11:42:30 - INFO - __main__ -    prec_0 = 0.7454954954954955
+11/03/2023 11:42:30 - INFO - __main__ -    prec_1 = 0.21212121212121213
+11/03/2023 11:42:30 - INFO - __main__ -    prec_2 = 0.72
+11/03/2023 11:42:30 - INFO - __main__ -    rec_0 = 0.9376770538243626
+11/03/2023 11:42:30 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 11:42:30 - INFO - __main__ -    rec_2 = 0.26277372262773724
+11/03/2023 11:42:30 - INFO - __main__ -   0.7096774193548387
+11/03/2023 12:14:16 - INFO - root -   Input args: Namespace(adam_epsilon=1e-08, cache_dir='', config_name='', data_dir='./data/oversample//comp', do_eval=True, do_lower_case=False, do_predict=True, do_predict_dev=False, do_train=True, eval_all_checkpoints=True, eval_test_set=True, evaluate_during_training=False, fp16=False, fp16_opt_level='O1', gradient_accumulation_steps=1, init_checkpoint=None, learning_rate=1e-05, local_rank=-1, log_file='train', logging_steps=50, max_grad_norm=1.0, max_seq_length=256, max_steps=-1, model_name_or_path='roberta-large', model_type='roberta', no_cuda=False, num_train_epochs=10.0, output_dir='./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//', overwrite_cache=False, overwrite_output_dir=True, per_gpu_eval_batch_size=8, per_gpu_train_batch_size=16, save_only_best_checkpoint=True, save_steps=20, seed=42, server_ip='', server_port='', task_name='comp', test_split='test', tokenizer_name='', train_split='train', warmup_steps=0, weight_decay=0.0)
+11/03/2023 12:14:17 - WARNING - __main__ -   Process rank: -1, device: cuda, n_gpu: 1, distributed training: False, 16-bits training: False
+11/03/2023 12:14:17 - INFO - __main__ -   config = RobertaConfig {
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "comp",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}
+
+11/03/2023 12:14:17 - INFO - __main__ -   Training/evaluation parameters Namespace(adam_epsilon=1e-08, cache_dir='', config_name='', data_dir='./data/oversample//comp', device=device(type='cuda'), do_eval=True, do_lower_case=False, do_predict=True, do_predict_dev=False, do_train=True, eval_all_checkpoints=True, eval_test_set=True, evaluate_during_training=False, fp16=False, fp16_opt_level='O1', gradient_accumulation_steps=1, init_checkpoint=None, learning_rate=1e-05, local_rank=-1, log_file='train', logging_steps=50, max_grad_norm=1.0, max_seq_length=256, max_steps=-1, model_name_or_path='roberta-large', model_type='roberta', n_gpu=1, no_cuda=False, num_train_epochs=10.0, output_dir='./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//', output_mode='classification', overwrite_cache=False, overwrite_output_dir=True, per_gpu_eval_batch_size=8, per_gpu_train_batch_size=16, save_only_best_checkpoint=True, save_steps=20, seed=42, server_ip='', server_port='', task_name='comp', test_split='test', tokenizer_name='', train_split='train', warmup_steps=0, weight_decay=0.0)
+11/03/2023 12:14:17 - INFO - __main__ -   loading from existing model roberta-large
+11/03/2023 12:14:26 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_train_roberta-large_256_comp_
+11/03/2023 12:14:26 - INFO - __main__ -   ***** Running training *****
+11/03/2023 12:14:26 - INFO - __main__ -     Num examples = 1696
+11/03/2023 12:14:26 - INFO - __main__ -     Num Epochs = 10
+11/03/2023 12:14:26 - INFO - __main__ -     Instantaneous batch size per GPU = 16
+11/03/2023 12:14:26 - INFO - __main__ -     Total train batch size (w. parallel, distributed & accumulation) = 16
+11/03/2023 12:14:26 - INFO - __main__ -     Gradient Accumulation steps = 1
+11/03/2023 12:14:26 - INFO - __main__ -     Total optimization steps = 1060
+11/03/2023 12:14:43 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:14:43 - INFO - __main__ -   ***** Running evaluation checkpoint-20 *****
+11/03/2023 12:14:43 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:14:43 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:14:49 - INFO - __main__ -   ***** Eval results checkpoint-20 *****
+11/03/2023 12:14:49 - INFO - __main__ -    acc = 0.6679316888045541
+11/03/2023 12:14:49 - INFO - __main__ -    correct = 352
+11/03/2023 12:14:49 - INFO - __main__ -    f1_0 = 0.8027366020524516
+11/03/2023 12:14:49 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:14:49 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:14:49 - INFO - __main__ -    macro_f1 = 0.2675788673508172
+11/03/2023 12:14:49 - INFO - __main__ -    num = 527
+11/03/2023 12:14:49 - INFO - __main__ -    prec_0 = 0.6717557251908397
+11/03/2023 12:14:49 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:14:49 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:14:49 - INFO - __main__ -    rec_0 = 0.9971671388101983
+11/03/2023 12:14:49 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:14:49 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:14:49 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:14:49 - INFO - __main__ -   ***** Running evaluation 20 *****
+11/03/2023 12:14:49 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:14:49 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:14:52 - INFO - __main__ -   ***** Eval results 20 *****
+11/03/2023 12:14:52 - INFO - __main__ -    acc = 0.6748466257668712
+11/03/2023 12:14:52 - INFO - __main__ -    correct = 220
+11/03/2023 12:14:52 - INFO - __main__ -    f1_0 = 0.8073394495412843
+11/03/2023 12:14:52 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:14:52 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:14:52 - INFO - __main__ -    macro_f1 = 0.2691131498470948
+11/03/2023 12:14:52 - INFO - __main__ -    num = 326
+11/03/2023 12:14:52 - INFO - __main__ -    prec_0 = 0.6832298136645962
+11/03/2023 12:14:52 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:14:52 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:14:52 - INFO - __main__ -    rec_0 = 0.9865470852017937
+11/03/2023 12:14:52 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:14:52 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:14:52 - INFO - __main__ -    Dev accuracy = 0.6748466257668712
+11/03/2023 12:14:52 - INFO - __main__ -    result['acc']=0.6748466257668712 > best_score=0
+11/03/2023 12:14:54 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:14:56 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:15:08 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:15:08 - INFO - __main__ -   ***** Running evaluation checkpoint-40 *****
+11/03/2023 12:15:08 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:15:08 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:15:14 - INFO - __main__ -   ***** Eval results checkpoint-40 *****
+11/03/2023 12:15:14 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 12:15:14 - INFO - __main__ -    correct = 353
+11/03/2023 12:15:14 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 12:15:14 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:15:14 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:15:14 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 12:15:14 - INFO - __main__ -    num = 527
+11/03/2023 12:15:14 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 12:15:14 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:15:14 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:15:14 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 12:15:14 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:15:14 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:15:14 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:15:14 - INFO - __main__ -   ***** Running evaluation 40 *****
+11/03/2023 12:15:14 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:15:14 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:15:17 - INFO - __main__ -   ***** Eval results 40 *****
+11/03/2023 12:15:17 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 12:15:17 - INFO - __main__ -    correct = 223
+11/03/2023 12:15:17 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 12:15:17 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:15:17 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:15:17 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 12:15:17 - INFO - __main__ -    num = 326
+11/03/2023 12:15:17 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 12:15:17 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:15:17 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:15:17 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 12:15:17 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:15:17 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:15:17 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 12:15:17 - INFO - __main__ -    result['acc']=0.6840490797546013 > best_score=0.6748466257668712
+11/03/2023 12:15:19 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:15:21 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:15:32 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:15:32 - INFO - __main__ -   ***** Running evaluation checkpoint-60 *****
+11/03/2023 12:15:32 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:15:32 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:15:38 - INFO - __main__ -   ***** Eval results checkpoint-60 *****
+11/03/2023 12:15:38 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 12:15:38 - INFO - __main__ -    correct = 353
+11/03/2023 12:15:38 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 12:15:38 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:15:38 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:15:38 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 12:15:38 - INFO - __main__ -    num = 527
+11/03/2023 12:15:38 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 12:15:38 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:15:38 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:15:38 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 12:15:38 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:15:38 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:15:38 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:15:38 - INFO - __main__ -   ***** Running evaluation 60 *****
+11/03/2023 12:15:38 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:15:38 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:15:42 - INFO - __main__ -   ***** Eval results 60 *****
+11/03/2023 12:15:42 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 12:15:42 - INFO - __main__ -    correct = 223
+11/03/2023 12:15:42 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 12:15:42 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:15:42 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:15:42 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 12:15:42 - INFO - __main__ -    num = 326
+11/03/2023 12:15:42 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 12:15:42 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:15:42 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:15:42 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 12:15:42 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:15:42 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:15:42 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 12:15:54 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:15:54 - INFO - __main__ -   ***** Running evaluation checkpoint-80 *****
+11/03/2023 12:15:54 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:15:54 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:16:00 - INFO - __main__ -   ***** Eval results checkpoint-80 *****
+11/03/2023 12:16:00 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 12:16:00 - INFO - __main__ -    correct = 353
+11/03/2023 12:16:00 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 12:16:00 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:16:00 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:16:00 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 12:16:00 - INFO - __main__ -    num = 527
+11/03/2023 12:16:00 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 12:16:00 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:16:00 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:16:00 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 12:16:00 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:16:00 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:16:00 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:16:00 - INFO - __main__ -   ***** Running evaluation 80 *****
+11/03/2023 12:16:00 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:16:00 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:16:04 - INFO - __main__ -   ***** Eval results 80 *****
+11/03/2023 12:16:04 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 12:16:04 - INFO - __main__ -    correct = 223
+11/03/2023 12:16:04 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 12:16:04 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:16:04 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:16:04 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 12:16:04 - INFO - __main__ -    num = 326
+11/03/2023 12:16:04 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 12:16:04 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:16:04 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:16:04 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 12:16:04 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:16:04 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:16:04 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 12:16:15 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:16:15 - INFO - __main__ -   ***** Running evaluation checkpoint-100 *****
+11/03/2023 12:16:15 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:16:15 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:16:21 - INFO - __main__ -   ***** Eval results checkpoint-100 *****
+11/03/2023 12:16:21 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 12:16:21 - INFO - __main__ -    correct = 353
+11/03/2023 12:16:21 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 12:16:21 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:16:21 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:16:21 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 12:16:21 - INFO - __main__ -    num = 527
+11/03/2023 12:16:21 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 12:16:21 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:16:21 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:16:21 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 12:16:21 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:16:21 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:16:21 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:16:21 - INFO - __main__ -   ***** Running evaluation 100 *****
+11/03/2023 12:16:21 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:16:21 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:16:25 - INFO - __main__ -   ***** Eval results 100 *****
+11/03/2023 12:16:25 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 12:16:25 - INFO - __main__ -    correct = 223
+11/03/2023 12:16:25 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 12:16:25 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:16:25 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:16:25 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 12:16:25 - INFO - __main__ -    num = 326
+11/03/2023 12:16:25 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 12:16:25 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:16:25 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:16:25 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 12:16:25 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:16:25 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:16:25 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 12:16:36 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:16:36 - INFO - __main__ -   ***** Running evaluation checkpoint-120 *****
+11/03/2023 12:16:36 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:16:36 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:16:42 - INFO - __main__ -   ***** Eval results checkpoint-120 *****
+11/03/2023 12:16:42 - INFO - __main__ -    acc = 0.4364326375711575
+11/03/2023 12:16:42 - INFO - __main__ -    correct = 230
+11/03/2023 12:16:42 - INFO - __main__ -    f1_0 = 0.6615384615384615
+11/03/2023 12:16:42 - INFO - __main__ -    f1_1 = 0.11235955056179775
+11/03/2023 12:16:42 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:16:42 - INFO - __main__ -    macro_f1 = 0.25796600403341974
+11/03/2023 12:16:42 - INFO - __main__ -    num = 527
+11/03/2023 12:16:42 - INFO - __main__ -    prec_0 = 0.7239057239057239
+11/03/2023 12:16:42 - INFO - __main__ -    prec_1 = 0.06521739130434782
+11/03/2023 12:16:42 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:16:42 - INFO - __main__ -    rec_0 = 0.6090651558073654
+11/03/2023 12:16:42 - INFO - __main__ -    rec_1 = 0.40540540540540543
+11/03/2023 12:16:42 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:16:42 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:16:42 - INFO - __main__ -   ***** Running evaluation 120 *****
+11/03/2023 12:16:42 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:16:42 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:16:46 - INFO - __main__ -   ***** Eval results 120 *****
+11/03/2023 12:16:46 - INFO - __main__ -    acc = 0.5306748466257669
+11/03/2023 12:16:46 - INFO - __main__ -    correct = 173
+11/03/2023 12:16:46 - INFO - __main__ -    f1_0 = 0.7199999999999999
+11/03/2023 12:16:46 - INFO - __main__ -    f1_1 = 0.17054263565891473
+11/03/2023 12:16:46 - INFO - __main__ -    f1_2 = 0
+11/03/2023 12:16:46 - INFO - __main__ -    macro_f1 = 0.2968475452196382
+11/03/2023 12:16:46 - INFO - __main__ -    num = 326
+11/03/2023 12:16:46 - INFO - __main__ -    prec_0 = 0.7136563876651982
+11/03/2023 12:16:46 - INFO - __main__ -    prec_1 = 0.1111111111111111
+11/03/2023 12:16:46 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 12:16:46 - INFO - __main__ -    rec_0 = 0.726457399103139
+11/03/2023 12:16:46 - INFO - __main__ -    rec_1 = 0.36666666666666664
+11/03/2023 12:16:46 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 12:16:46 - INFO - __main__ -    Dev accuracy = 0.5306748466257669
+11/03/2023 12:16:58 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:16:58 - INFO - __main__ -   ***** Running evaluation checkpoint-140 *****
+11/03/2023 12:16:58 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:16:58 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:17:04 - INFO - __main__ -   ***** Eval results checkpoint-140 *****
+11/03/2023 12:17:04 - INFO - __main__ -    acc = 0.6527514231499051
+11/03/2023 12:17:04 - INFO - __main__ -    correct = 344
+11/03/2023 12:17:04 - INFO - __main__ -    f1_0 = 0.800942285041225
+11/03/2023 12:17:04 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:17:04 - INFO - __main__ -    f1_2 = 0.055944055944055944
+11/03/2023 12:17:04 - INFO - __main__ -    macro_f1 = 0.285628780328427
+11/03/2023 12:17:04 - INFO - __main__ -    num = 527
+11/03/2023 12:17:04 - INFO - __main__ -    prec_0 = 0.6854838709677419
+11/03/2023 12:17:04 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:17:04 - INFO - __main__ -    prec_2 = 0.6666666666666666
+11/03/2023 12:17:04 - INFO - __main__ -    rec_0 = 0.9631728045325779
+11/03/2023 12:17:04 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:17:04 - INFO - __main__ -    rec_2 = 0.029197080291970802
+11/03/2023 12:17:04 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:17:04 - INFO - __main__ -   ***** Running evaluation 140 *****
+11/03/2023 12:17:04 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:17:04 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:17:08 - INFO - __main__ -   ***** Eval results 140 *****
+11/03/2023 12:17:08 - INFO - __main__ -    acc = 0.6625766871165644
+11/03/2023 12:17:08 - INFO - __main__ -    correct = 216
+11/03/2023 12:17:08 - INFO - __main__ -    f1_0 = 0.805243445692884
+11/03/2023 12:17:08 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:17:08 - INFO - __main__ -    f1_2 = 0.02531645569620253
+11/03/2023 12:17:08 - INFO - __main__ -    macro_f1 = 0.27685330046302886
+11/03/2023 12:17:08 - INFO - __main__ -    num = 326
+11/03/2023 12:17:08 - INFO - __main__ -    prec_0 = 0.6913183279742765
+11/03/2023 12:17:08 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:17:08 - INFO - __main__ -    prec_2 = 0.16666666666666666
+11/03/2023 12:17:08 - INFO - __main__ -    rec_0 = 0.9641255605381166
+11/03/2023 12:17:08 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:17:08 - INFO - __main__ -    rec_2 = 0.0136986301369863
+11/03/2023 12:17:08 - INFO - __main__ -    Dev accuracy = 0.6625766871165644
+11/03/2023 12:17:19 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:17:19 - INFO - __main__ -   ***** Running evaluation checkpoint-160 *****
+11/03/2023 12:17:19 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:17:19 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:17:25 - INFO - __main__ -   ***** Eval results checkpoint-160 *****
+11/03/2023 12:17:25 - INFO - __main__ -    acc = 0.6850094876660342
+11/03/2023 12:17:25 - INFO - __main__ -    correct = 361
+11/03/2023 12:17:25 - INFO - __main__ -    f1_0 = 0.8111239860950175
+11/03/2023 12:17:25 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:17:25 - INFO - __main__ -    f1_2 = 0.14666666666666667
+11/03/2023 12:17:25 - INFO - __main__ -    macro_f1 = 0.3192635509205614
+11/03/2023 12:17:25 - INFO - __main__ -    num = 527
+11/03/2023 12:17:25 - INFO - __main__ -    prec_0 = 0.6862745098039216
+11/03/2023 12:17:25 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:17:25 - INFO - __main__ -    prec_2 = 0.8461538461538461
+11/03/2023 12:17:25 - INFO - __main__ -    rec_0 = 0.9915014164305949
+11/03/2023 12:17:25 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:17:25 - INFO - __main__ -    rec_2 = 0.08029197080291971
+11/03/2023 12:17:25 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:17:25 - INFO - __main__ -   ***** Running evaluation 160 *****
+11/03/2023 12:17:25 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:17:25 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:17:29 - INFO - __main__ -   ***** Eval results 160 *****
+11/03/2023 12:17:29 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 12:17:29 - INFO - __main__ -    correct = 223
+11/03/2023 12:17:29 - INFO - __main__ -    f1_0 = 0.8133086876155268
+11/03/2023 12:17:29 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:17:29 - INFO - __main__ -    f1_2 = 0.0759493670886076
+11/03/2023 12:17:29 - INFO - __main__ -    macro_f1 = 0.2964193515680448
+11/03/2023 12:17:29 - INFO - __main__ -    num = 326
+11/03/2023 12:17:29 - INFO - __main__ -    prec_0 = 0.6918238993710691
+11/03/2023 12:17:29 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:17:29 - INFO - __main__ -    prec_2 = 0.5
+11/03/2023 12:17:29 - INFO - __main__ -    rec_0 = 0.9865470852017937
+11/03/2023 12:17:29 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:17:29 - INFO - __main__ -    rec_2 = 0.0410958904109589
+11/03/2023 12:17:29 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 12:17:40 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:17:40 - INFO - __main__ -   ***** Running evaluation checkpoint-180 *****
+11/03/2023 12:17:40 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:17:40 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:17:47 - INFO - __main__ -   ***** Eval results checkpoint-180 *****
+11/03/2023 12:17:47 - INFO - __main__ -    acc = 0.6679316888045541
+11/03/2023 12:17:47 - INFO - __main__ -    correct = 352
+11/03/2023 12:17:47 - INFO - __main__ -    f1_0 = 0.7854137447405329
+11/03/2023 12:17:47 - INFO - __main__ -    f1_1 = 0.09836065573770492
+11/03/2023 12:17:47 - INFO - __main__ -    f1_2 = 0.4928571428571429
+11/03/2023 12:17:47 - INFO - __main__ -    macro_f1 = 0.4588771811117936
+11/03/2023 12:17:47 - INFO - __main__ -    num = 527
+11/03/2023 12:17:47 - INFO - __main__ -    prec_0 = 0.7777777777777778
+11/03/2023 12:17:47 - INFO - __main__ -    prec_1 = 0.125
+11/03/2023 12:17:47 - INFO - __main__ -    prec_2 = 0.4825174825174825
+11/03/2023 12:17:47 - INFO - __main__ -    rec_0 = 0.7932011331444759
+11/03/2023 12:17:47 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 12:17:47 - INFO - __main__ -    rec_2 = 0.5036496350364964
+11/03/2023 12:17:47 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:17:47 - INFO - __main__ -   ***** Running evaluation 180 *****
+11/03/2023 12:17:47 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:17:47 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:17:50 - INFO - __main__ -   ***** Eval results 180 *****
+11/03/2023 12:17:50 - INFO - __main__ -    acc = 0.6779141104294478
+11/03/2023 12:17:50 - INFO - __main__ -    correct = 221
+11/03/2023 12:17:50 - INFO - __main__ -    f1_0 = 0.8017241379310345
+11/03/2023 12:17:50 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:17:50 - INFO - __main__ -    f1_2 = 0.4430379746835443
+11/03/2023 12:17:50 - INFO - __main__ -    macro_f1 = 0.41492070420485955
+11/03/2023 12:17:50 - INFO - __main__ -    num = 326
+11/03/2023 12:17:50 - INFO - __main__ -    prec_0 = 0.7717842323651453
+11/03/2023 12:17:50 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:17:50 - INFO - __main__ -    prec_2 = 0.4117647058823529
+11/03/2023 12:17:50 - INFO - __main__ -    rec_0 = 0.8340807174887892
+11/03/2023 12:17:50 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:17:50 - INFO - __main__ -    rec_2 = 0.4794520547945205
+11/03/2023 12:17:50 - INFO - __main__ -    Dev accuracy = 0.6779141104294478
+11/03/2023 12:18:02 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:18:02 - INFO - __main__ -   ***** Running evaluation checkpoint-200 *****
+11/03/2023 12:18:02 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:18:02 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:18:08 - INFO - __main__ -   ***** Eval results checkpoint-200 *****
+11/03/2023 12:18:08 - INFO - __main__ -    acc = 0.6584440227703985
+11/03/2023 12:18:08 - INFO - __main__ -    correct = 347
+11/03/2023 12:18:08 - INFO - __main__ -    f1_0 = 0.8197530864197531
+11/03/2023 12:18:08 - INFO - __main__ -    f1_1 = 0.14583333333333334
+11/03/2023 12:18:08 - INFO - __main__ -    f1_2 = 0.1081081081081081
+11/03/2023 12:18:08 - INFO - __main__ -    macro_f1 = 0.35789817595373147
+11/03/2023 12:18:08 - INFO - __main__ -    num = 527
+11/03/2023 12:18:08 - INFO - __main__ -    prec_0 = 0.7264770240700219
+11/03/2023 12:18:08 - INFO - __main__ -    prec_1 = 0.11864406779661017
+11/03/2023 12:18:08 - INFO - __main__ -    prec_2 = 0.7272727272727273
+11/03/2023 12:18:08 - INFO - __main__ -    rec_0 = 0.9405099150141643
+11/03/2023 12:18:08 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 12:18:08 - INFO - __main__ -    rec_2 = 0.058394160583941604
+11/03/2023 12:18:08 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:18:08 - INFO - __main__ -   ***** Running evaluation 200 *****
+11/03/2023 12:18:08 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:18:08 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:18:12 - INFO - __main__ -   ***** Eval results 200 *****
+11/03/2023 12:18:12 - INFO - __main__ -    acc = 0.6779141104294478
+11/03/2023 12:18:12 - INFO - __main__ -    correct = 221
+11/03/2023 12:18:12 - INFO - __main__ -    f1_0 = 0.8171206225680934
+11/03/2023 12:18:12 - INFO - __main__ -    f1_1 = 0.045454545454545456
+11/03/2023 12:18:12 - INFO - __main__ -    f1_2 = 0.2127659574468085
+11/03/2023 12:18:12 - INFO - __main__ -    macro_f1 = 0.3584470418231491
+11/03/2023 12:18:12 - INFO - __main__ -    num = 326
+11/03/2023 12:18:12 - INFO - __main__ -    prec_0 = 0.7216494845360825
+11/03/2023 12:18:12 - INFO - __main__ -    prec_1 = 0.07142857142857142
+11/03/2023 12:18:12 - INFO - __main__ -    prec_2 = 0.47619047619047616
+11/03/2023 12:18:12 - INFO - __main__ -    rec_0 = 0.9417040358744395
+11/03/2023 12:18:12 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:18:12 - INFO - __main__ -    rec_2 = 0.136986301369863
+11/03/2023 12:18:12 - INFO - __main__ -    Dev accuracy = 0.6779141104294478
+11/03/2023 12:18:23 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:18:23 - INFO - __main__ -   ***** Running evaluation checkpoint-220 *****
+11/03/2023 12:18:23 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:18:23 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:18:29 - INFO - __main__ -   ***** Eval results checkpoint-220 *****
+11/03/2023 12:18:29 - INFO - __main__ -    acc = 0.6204933586337761
+11/03/2023 12:18:29 - INFO - __main__ -    correct = 327
+11/03/2023 12:18:29 - INFO - __main__ -    f1_0 = 0.7936085219707057
+11/03/2023 12:18:29 - INFO - __main__ -    f1_1 = 0.1076923076923077
+11/03/2023 12:18:29 - INFO - __main__ -    f1_2 = 0.2543352601156069
+11/03/2023 12:18:29 - INFO - __main__ -    macro_f1 = 0.3852120299262068
+11/03/2023 12:18:29 - INFO - __main__ -    num = 527
+11/03/2023 12:18:29 - INFO - __main__ -    prec_0 = 0.7487437185929648
+11/03/2023 12:18:29 - INFO - __main__ -    prec_1 = 0.07526881720430108
+11/03/2023 12:18:29 - INFO - __main__ -    prec_2 = 0.6111111111111112
+11/03/2023 12:18:29 - INFO - __main__ -    rec_0 = 0.8441926345609065
+11/03/2023 12:18:29 - INFO - __main__ -    rec_1 = 0.1891891891891892
+11/03/2023 12:18:29 - INFO - __main__ -    rec_2 = 0.16058394160583941
+11/03/2023 12:18:29 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:18:29 - INFO - __main__ -   ***** Running evaluation 220 *****
+11/03/2023 12:18:29 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:18:29 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:18:33 - INFO - __main__ -   ***** Eval results 220 *****
+11/03/2023 12:18:33 - INFO - __main__ -    acc = 0.6717791411042945
+11/03/2023 12:18:33 - INFO - __main__ -    correct = 219
+11/03/2023 12:18:33 - INFO - __main__ -    f1_0 = 0.8140495867768596
+11/03/2023 12:18:33 - INFO - __main__ -    f1_1 = 0.10714285714285714
+11/03/2023 12:18:33 - INFO - __main__ -    f1_2 = 0.33928571428571425
+11/03/2023 12:18:33 - INFO - __main__ -    macro_f1 = 0.42015938606847697
+11/03/2023 12:18:33 - INFO - __main__ -    num = 326
+11/03/2023 12:18:33 - INFO - __main__ -    prec_0 = 0.7547892720306514
+11/03/2023 12:18:33 - INFO - __main__ -    prec_1 = 0.11538461538461539
+11/03/2023 12:18:33 - INFO - __main__ -    prec_2 = 0.48717948717948717
+11/03/2023 12:18:33 - INFO - __main__ -    rec_0 = 0.8834080717488789
+11/03/2023 12:18:33 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:18:33 - INFO - __main__ -    rec_2 = 0.2602739726027397
+11/03/2023 12:18:33 - INFO - __main__ -    Dev accuracy = 0.6717791411042945
+11/03/2023 12:18:45 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:18:45 - INFO - __main__ -   ***** Running evaluation checkpoint-240 *****
+11/03/2023 12:18:45 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:18:45 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:18:51 - INFO - __main__ -   ***** Eval results checkpoint-240 *****
+11/03/2023 12:18:51 - INFO - __main__ -    acc = 0.7020872865275142
+11/03/2023 12:18:51 - INFO - __main__ -    correct = 370
+11/03/2023 12:18:51 - INFO - __main__ -    f1_0 = 0.8100263852242745
+11/03/2023 12:18:51 - INFO - __main__ -    f1_1 = 0.163265306122449
+11/03/2023 12:18:51 - INFO - __main__ -    f1_2 = 0.47773279352226716
+11/03/2023 12:18:51 - INFO - __main__ -    macro_f1 = 0.4836748282896635
+11/03/2023 12:18:51 - INFO - __main__ -    num = 527
+11/03/2023 12:18:51 - INFO - __main__ -    prec_0 = 0.7580246913580246
+11/03/2023 12:18:51 - INFO - __main__ -    prec_1 = 0.3333333333333333
+11/03/2023 12:18:51 - INFO - __main__ -    prec_2 = 0.5363636363636364
+11/03/2023 12:18:51 - INFO - __main__ -    rec_0 = 0.8696883852691218
+11/03/2023 12:18:51 - INFO - __main__ -    rec_1 = 0.10810810810810811
+11/03/2023 12:18:51 - INFO - __main__ -    rec_2 = 0.4306569343065693
+11/03/2023 12:18:51 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:18:51 - INFO - __main__ -   ***** Running evaluation 240 *****
+11/03/2023 12:18:51 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:18:51 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:18:55 - INFO - __main__ -   ***** Eval results 240 *****
+11/03/2023 12:18:55 - INFO - __main__ -    acc = 0.6748466257668712
+11/03/2023 12:18:55 - INFO - __main__ -    correct = 220
+11/03/2023 12:18:55 - INFO - __main__ -    f1_0 = 0.7965738758029978
+11/03/2023 12:18:55 - INFO - __main__ -    f1_1 = 0
+11/03/2023 12:18:55 - INFO - __main__ -    f1_2 = 0.44155844155844154
+11/03/2023 12:18:55 - INFO - __main__ -    macro_f1 = 0.4127107724538131
+11/03/2023 12:18:55 - INFO - __main__ -    num = 326
+11/03/2023 12:18:55 - INFO - __main__ -    prec_0 = 0.7622950819672131
+11/03/2023 12:18:55 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 12:18:55 - INFO - __main__ -    prec_2 = 0.41975308641975306
+11/03/2023 12:18:55 - INFO - __main__ -    rec_0 = 0.8340807174887892
+11/03/2023 12:18:55 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 12:18:55 - INFO - __main__ -    rec_2 = 0.4657534246575342
+11/03/2023 12:18:55 - INFO - __main__ -    Dev accuracy = 0.6748466257668712
+11/03/2023 12:19:06 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:19:06 - INFO - __main__ -   ***** Running evaluation checkpoint-260 *****
+11/03/2023 12:19:06 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:19:06 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:19:12 - INFO - __main__ -   ***** Eval results checkpoint-260 *****
+11/03/2023 12:19:12 - INFO - __main__ -    acc = 0.681214421252372
+11/03/2023 12:19:12 - INFO - __main__ -    correct = 359
+11/03/2023 12:19:12 - INFO - __main__ -    f1_0 = 0.8288973384030418
+11/03/2023 12:19:12 - INFO - __main__ -    f1_1 = 0.11363636363636365
+11/03/2023 12:19:12 - INFO - __main__ -    f1_2 = 0.3050847457627119
+11/03/2023 12:19:12 - INFO - __main__ -    macro_f1 = 0.4158728159340391
+11/03/2023 12:19:12 - INFO - __main__ -    num = 527
+11/03/2023 12:19:12 - INFO - __main__ -    prec_0 = 0.75
+11/03/2023 12:19:12 - INFO - __main__ -    prec_1 = 0.09803921568627451
+11/03/2023 12:19:12 - INFO - __main__ -    prec_2 = 0.675
+11/03/2023 12:19:12 - INFO - __main__ -    rec_0 = 0.9263456090651558
+11/03/2023 12:19:12 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:19:12 - INFO - __main__ -    rec_2 = 0.19708029197080293
+11/03/2023 12:19:12 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:19:12 - INFO - __main__ -   ***** Running evaluation 260 *****
+11/03/2023 12:19:12 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:19:12 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:19:16 - INFO - __main__ -   ***** Eval results 260 *****
+11/03/2023 12:19:16 - INFO - __main__ -    acc = 0.6748466257668712
+11/03/2023 12:19:16 - INFO - __main__ -    correct = 220
+11/03/2023 12:19:16 - INFO - __main__ -    f1_0 = 0.8128772635814889
+11/03/2023 12:19:16 - INFO - __main__ -    f1_1 = 0.04761904761904761
+11/03/2023 12:19:16 - INFO - __main__ -    f1_2 = 0.3008849557522124
+11/03/2023 12:19:16 - INFO - __main__ -    macro_f1 = 0.3871270889842496
+11/03/2023 12:19:16 - INFO - __main__ -    num = 326
+11/03/2023 12:19:16 - INFO - __main__ -    prec_0 = 0.7372262773722628
+11/03/2023 12:19:16 - INFO - __main__ -    prec_1 = 0.08333333333333333
+11/03/2023 12:19:16 - INFO - __main__ -    prec_2 = 0.425
+11/03/2023 12:19:16 - INFO - __main__ -    rec_0 = 0.905829596412556
+11/03/2023 12:19:16 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:19:16 - INFO - __main__ -    rec_2 = 0.2328767123287671
+11/03/2023 12:19:16 - INFO - __main__ -    Dev accuracy = 0.6748466257668712
+11/03/2023 12:19:27 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:19:28 - INFO - __main__ -   ***** Running evaluation checkpoint-280 *****
+11/03/2023 12:19:28 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:19:28 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:19:34 - INFO - __main__ -   ***** Eval results checkpoint-280 *****
+11/03/2023 12:19:34 - INFO - __main__ -    acc = 0.6679316888045541
+11/03/2023 12:19:34 - INFO - __main__ -    correct = 352
+11/03/2023 12:19:34 - INFO - __main__ -    f1_0 = 0.8156956004756243
+11/03/2023 12:19:34 - INFO - __main__ -    f1_1 = 0.030303030303030304
+11/03/2023 12:19:34 - INFO - __main__ -    f1_2 = 0.10884353741496598
+11/03/2023 12:19:34 - INFO - __main__ -    macro_f1 = 0.31828072273120683
+11/03/2023 12:19:34 - INFO - __main__ -    num = 527
+11/03/2023 12:19:34 - INFO - __main__ -    prec_0 = 0.7028688524590164
+11/03/2023 12:19:34 - INFO - __main__ -    prec_1 = 0.034482758620689655
+11/03/2023 12:19:34 - INFO - __main__ -    prec_2 = 0.8
+11/03/2023 12:19:34 - INFO - __main__ -    rec_0 = 0.9716713881019831
+11/03/2023 12:19:34 - INFO - __main__ -    rec_1 = 0.02702702702702703
+11/03/2023 12:19:34 - INFO - __main__ -    rec_2 = 0.058394160583941604
+11/03/2023 12:19:34 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:19:34 - INFO - __main__ -   ***** Running evaluation 280 *****
+11/03/2023 12:19:34 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:19:34 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:19:37 - INFO - __main__ -   ***** Eval results 280 *****
+11/03/2023 12:19:37 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 12:19:37 - INFO - __main__ -    correct = 223
+11/03/2023 12:19:37 - INFO - __main__ -    f1_0 = 0.8105065666041276
+11/03/2023 12:19:37 - INFO - __main__ -    f1_1 = 0.058823529411764705
+11/03/2023 12:19:37 - INFO - __main__ -    f1_2 = 0.1411764705882353
+11/03/2023 12:19:37 - INFO - __main__ -    macro_f1 = 0.33683552220137586
+11/03/2023 12:19:37 - INFO - __main__ -    num = 326
+11/03/2023 12:19:37 - INFO - __main__ -    prec_0 = 0.6967741935483871
+11/03/2023 12:19:37 - INFO - __main__ -    prec_1 = 0.25
+11/03/2023 12:19:37 - INFO - __main__ -    prec_2 = 0.5
+11/03/2023 12:19:37 - INFO - __main__ -    rec_0 = 0.968609865470852
+11/03/2023 12:19:37 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:19:37 - INFO - __main__ -    rec_2 = 0.0821917808219178
+11/03/2023 12:19:37 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 12:19:49 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:19:49 - INFO - __main__ -   ***** Running evaluation checkpoint-300 *****
+11/03/2023 12:19:49 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:19:49 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:19:55 - INFO - __main__ -   ***** Eval results checkpoint-300 *****
+11/03/2023 12:19:55 - INFO - __main__ -    acc = 0.6679316888045541
+11/03/2023 12:19:55 - INFO - __main__ -    correct = 352
+11/03/2023 12:19:55 - INFO - __main__ -    f1_0 = 0.8335451080050825
+11/03/2023 12:19:55 - INFO - __main__ -    f1_1 = 0.11538461538461539
+11/03/2023 12:19:55 - INFO - __main__ -    f1_2 = 0.22085889570552145
+11/03/2023 12:19:55 - INFO - __main__ -    macro_f1 = 0.38992953969840644
+11/03/2023 12:19:55 - INFO - __main__ -    num = 527
+11/03/2023 12:19:55 - INFO - __main__ -    prec_0 = 0.7557603686635944
+11/03/2023 12:19:55 - INFO - __main__ -    prec_1 = 0.08955223880597014
+11/03/2023 12:19:55 - INFO - __main__ -    prec_2 = 0.6923076923076923
+11/03/2023 12:19:55 - INFO - __main__ -    rec_0 = 0.9291784702549575
+11/03/2023 12:19:55 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 12:19:55 - INFO - __main__ -    rec_2 = 0.13138686131386862
+11/03/2023 12:19:55 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:19:55 - INFO - __main__ -   ***** Running evaluation 300 *****
+11/03/2023 12:19:55 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:19:55 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:19:59 - INFO - __main__ -   ***** Eval results 300 *****
+11/03/2023 12:19:59 - INFO - __main__ -    acc = 0.6871165644171779
+11/03/2023 12:19:59 - INFO - __main__ -    correct = 224
+11/03/2023 12:19:59 - INFO - __main__ -    f1_0 = 0.8249496981891348
+11/03/2023 12:19:59 - INFO - __main__ -    f1_1 = 0.12
+11/03/2023 12:19:59 - INFO - __main__ -    f1_2 = 0.30476190476190473
+11/03/2023 12:19:59 - INFO - __main__ -    macro_f1 = 0.4165705343170132
+11/03/2023 12:19:59 - INFO - __main__ -    num = 326
+11/03/2023 12:19:59 - INFO - __main__ -    prec_0 = 0.7481751824817519
+11/03/2023 12:19:59 - INFO - __main__ -    prec_1 = 0.15
+11/03/2023 12:19:59 - INFO - __main__ -    prec_2 = 0.5
+11/03/2023 12:19:59 - INFO - __main__ -    rec_0 = 0.9192825112107623
+11/03/2023 12:19:59 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:19:59 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:19:59 - INFO - __main__ -    Dev accuracy = 0.6871165644171779
+11/03/2023 12:19:59 - INFO - __main__ -    result['acc']=0.6871165644171779 > best_score=0.6840490797546013
+11/03/2023 12:20:00 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:20:03 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:20:14 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:20:14 - INFO - __main__ -   ***** Running evaluation checkpoint-320 *****
+11/03/2023 12:20:14 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:20:14 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:20:20 - INFO - __main__ -   ***** Eval results checkpoint-320 *****
+11/03/2023 12:20:20 - INFO - __main__ -    acc = 0.7001897533206831
+11/03/2023 12:20:20 - INFO - __main__ -    correct = 369
+11/03/2023 12:20:20 - INFO - __main__ -    f1_0 = 0.8245192307692307
+11/03/2023 12:20:20 - INFO - __main__ -    f1_1 = 0.11320754716981132
+11/03/2023 12:20:20 - INFO - __main__ -    f1_2 = 0.272189349112426
+11/03/2023 12:20:20 - INFO - __main__ -    macro_f1 = 0.4033053756838227
+11/03/2023 12:20:20 - INFO - __main__ -    num = 527
+11/03/2023 12:20:20 - INFO - __main__ -    prec_0 = 0.7160751565762005
+11/03/2023 12:20:20 - INFO - __main__ -    prec_1 = 0.1875
+11/03/2023 12:20:20 - INFO - __main__ -    prec_2 = 0.71875
+11/03/2023 12:20:20 - INFO - __main__ -    rec_0 = 0.9716713881019831
+11/03/2023 12:20:20 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 12:20:20 - INFO - __main__ -    rec_2 = 0.1678832116788321
+11/03/2023 12:20:20 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:20:20 - INFO - __main__ -   ***** Running evaluation 320 *****
+11/03/2023 12:20:20 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:20:20 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:20:24 - INFO - __main__ -   ***** Eval results 320 *****
+11/03/2023 12:20:24 - INFO - __main__ -    acc = 0.6932515337423313
+11/03/2023 12:20:24 - INFO - __main__ -    correct = 226
+11/03/2023 12:20:24 - INFO - __main__ -    f1_0 = 0.8172888015717092
+11/03/2023 12:20:24 - INFO - __main__ -    f1_1 = 0.05714285714285715
+11/03/2023 12:20:24 - INFO - __main__ -    f1_2 = 0.3148148148148148
+11/03/2023 12:20:24 - INFO - __main__ -    macro_f1 = 0.3964154911764604
+11/03/2023 12:20:24 - INFO - __main__ -    num = 326
+11/03/2023 12:20:24 - INFO - __main__ -    prec_0 = 0.7272727272727273
+11/03/2023 12:20:24 - INFO - __main__ -    prec_1 = 0.2
+11/03/2023 12:20:24 - INFO - __main__ -    prec_2 = 0.4857142857142857
+11/03/2023 12:20:24 - INFO - __main__ -    rec_0 = 0.9327354260089686
+11/03/2023 12:20:24 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:20:24 - INFO - __main__ -    rec_2 = 0.2328767123287671
+11/03/2023 12:20:24 - INFO - __main__ -    Dev accuracy = 0.6932515337423313
+11/03/2023 12:20:24 - INFO - __main__ -    result['acc']=0.6932515337423313 > best_score=0.6871165644171779
+11/03/2023 12:20:25 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:20:28 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:20:39 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:20:39 - INFO - __main__ -   ***** Running evaluation checkpoint-340 *****
+11/03/2023 12:20:39 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:20:39 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:20:45 - INFO - __main__ -   ***** Eval results checkpoint-340 *****
+11/03/2023 12:20:45 - INFO - __main__ -    acc = 0.6888045540796964
+11/03/2023 12:20:45 - INFO - __main__ -    correct = 363
+11/03/2023 12:20:45 - INFO - __main__ -    f1_0 = 0.8244274809160306
+11/03/2023 12:20:45 - INFO - __main__ -    f1_1 = 0.136986301369863
+11/03/2023 12:20:45 - INFO - __main__ -    f1_2 = 0.3487179487179487
+11/03/2023 12:20:45 - INFO - __main__ -    macro_f1 = 0.43671057700128074
+11/03/2023 12:20:45 - INFO - __main__ -    num = 527
+11/03/2023 12:20:45 - INFO - __main__ -    prec_0 = 0.7482678983833718
+11/03/2023 12:20:45 - INFO - __main__ -    prec_1 = 0.1388888888888889
+11/03/2023 12:20:45 - INFO - __main__ -    prec_2 = 0.5862068965517241
+11/03/2023 12:20:45 - INFO - __main__ -    rec_0 = 0.9178470254957507
+11/03/2023 12:20:45 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:20:45 - INFO - __main__ -    rec_2 = 0.24817518248175183
+11/03/2023 12:20:45 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:20:45 - INFO - __main__ -   ***** Running evaluation 340 *****
+11/03/2023 12:20:45 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:20:45 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:20:49 - INFO - __main__ -   ***** Eval results 340 *****
+11/03/2023 12:20:49 - INFO - __main__ -    acc = 0.696319018404908
+11/03/2023 12:20:49 - INFO - __main__ -    correct = 227
+11/03/2023 12:20:49 - INFO - __main__ -    f1_0 = 0.8194726166328601
+11/03/2023 12:20:49 - INFO - __main__ -    f1_1 = 0.1
+11/03/2023 12:20:49 - INFO - __main__ -    f1_2 = 0.3865546218487395
+11/03/2023 12:20:49 - INFO - __main__ -    macro_f1 = 0.4353424128271999
+11/03/2023 12:20:49 - INFO - __main__ -    num = 326
+11/03/2023 12:20:49 - INFO - __main__ -    prec_0 = 0.7481481481481481
+11/03/2023 12:20:49 - INFO - __main__ -    prec_1 = 0.2
+11/03/2023 12:20:49 - INFO - __main__ -    prec_2 = 0.5
+11/03/2023 12:20:49 - INFO - __main__ -    rec_0 = 0.905829596412556
+11/03/2023 12:20:49 - INFO - __main__ -    rec_1 = 0.06666666666666667
+11/03/2023 12:20:49 - INFO - __main__ -    rec_2 = 0.3150684931506849
+11/03/2023 12:20:49 - INFO - __main__ -    Dev accuracy = 0.696319018404908
+11/03/2023 12:20:49 - INFO - __main__ -    result['acc']=0.696319018404908 > best_score=0.6932515337423313
+11/03/2023 12:20:50 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:20:53 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:21:04 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:21:04 - INFO - __main__ -   ***** Running evaluation checkpoint-360 *****
+11/03/2023 12:21:04 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:21:04 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:21:10 - INFO - __main__ -   ***** Eval results checkpoint-360 *****
+11/03/2023 12:21:10 - INFO - __main__ -    acc = 0.6869070208728653
+11/03/2023 12:21:10 - INFO - __main__ -    correct = 362
+11/03/2023 12:21:10 - INFO - __main__ -    f1_0 = 0.818840579710145
+11/03/2023 12:21:10 - INFO - __main__ -    f1_1 = 0.09836065573770492
+11/03/2023 12:21:10 - INFO - __main__ -    f1_2 = 0.24242424242424243
+11/03/2023 12:21:10 - INFO - __main__ -    macro_f1 = 0.3865418259573641
+11/03/2023 12:21:10 - INFO - __main__ -    num = 527
+11/03/2023 12:21:10 - INFO - __main__ -    prec_0 = 0.7136842105263158
+11/03/2023 12:21:10 - INFO - __main__ -    prec_1 = 0.125
+11/03/2023 12:21:10 - INFO - __main__ -    prec_2 = 0.7142857142857143
+11/03/2023 12:21:10 - INFO - __main__ -    rec_0 = 0.9603399433427762
+11/03/2023 12:21:10 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 12:21:10 - INFO - __main__ -    rec_2 = 0.145985401459854
+11/03/2023 12:21:10 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:21:10 - INFO - __main__ -   ***** Running evaluation 360 *****
+11/03/2023 12:21:10 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:21:10 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:21:14 - INFO - __main__ -   ***** Eval results 360 *****
+11/03/2023 12:21:14 - INFO - __main__ -    acc = 0.6809815950920245
+11/03/2023 12:21:14 - INFO - __main__ -    correct = 222
+11/03/2023 12:21:14 - INFO - __main__ -    f1_0 = 0.8094302554027505
+11/03/2023 12:21:14 - INFO - __main__ -    f1_1 = 0.0975609756097561
+11/03/2023 12:21:14 - INFO - __main__ -    f1_2 = 0.27450980392156865
+11/03/2023 12:21:14 - INFO - __main__ -    macro_f1 = 0.39383367831135835
+11/03/2023 12:21:14 - INFO - __main__ -    num = 326
+11/03/2023 12:21:14 - INFO - __main__ -    prec_0 = 0.7202797202797203
+11/03/2023 12:21:14 - INFO - __main__ -    prec_1 = 0.18181818181818182
+11/03/2023 12:21:14 - INFO - __main__ -    prec_2 = 0.4827586206896552
+11/03/2023 12:21:14 - INFO - __main__ -    rec_0 = 0.9237668161434978
+11/03/2023 12:21:14 - INFO - __main__ -    rec_1 = 0.06666666666666667
+11/03/2023 12:21:14 - INFO - __main__ -    rec_2 = 0.1917808219178082
+11/03/2023 12:21:14 - INFO - __main__ -    Dev accuracy = 0.6809815950920245
+11/03/2023 12:21:26 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:21:26 - INFO - __main__ -   ***** Running evaluation checkpoint-380 *****
+11/03/2023 12:21:26 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:21:26 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:21:32 - INFO - __main__ -   ***** Eval results checkpoint-380 *****
+11/03/2023 12:21:32 - INFO - __main__ -    acc = 0.6888045540796964
+11/03/2023 12:21:32 - INFO - __main__ -    correct = 363
+11/03/2023 12:21:32 - INFO - __main__ -    f1_0 = 0.819047619047619
+11/03/2023 12:21:32 - INFO - __main__ -    f1_1 = 0.03703703703703704
+11/03/2023 12:21:32 - INFO - __main__ -    f1_2 = 0.225
+11/03/2023 12:21:32 - INFO - __main__ -    macro_f1 = 0.3603615520282187
+11/03/2023 12:21:32 - INFO - __main__ -    num = 527
+11/03/2023 12:21:32 - INFO - __main__ -    prec_0 = 0.7063655030800822
+11/03/2023 12:21:32 - INFO - __main__ -    prec_1 = 0.058823529411764705
+11/03/2023 12:21:32 - INFO - __main__ -    prec_2 = 0.782608695652174
+11/03/2023 12:21:32 - INFO - __main__ -    rec_0 = 0.9745042492917847
+11/03/2023 12:21:32 - INFO - __main__ -    rec_1 = 0.02702702702702703
+11/03/2023 12:21:32 - INFO - __main__ -    rec_2 = 0.13138686131386862
+11/03/2023 12:21:32 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:21:32 - INFO - __main__ -   ***** Running evaluation 380 *****
+11/03/2023 12:21:32 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:21:32 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:21:36 - INFO - __main__ -   ***** Eval results 380 *****
+11/03/2023 12:21:36 - INFO - __main__ -    acc = 0.7085889570552147
+11/03/2023 12:21:36 - INFO - __main__ -    correct = 231
+11/03/2023 12:21:36 - INFO - __main__ -    f1_0 = 0.8223938223938225
+11/03/2023 12:21:36 - INFO - __main__ -    f1_1 = 0.11764705882352941
+11/03/2023 12:21:36 - INFO - __main__ -    f1_2 = 0.32
+11/03/2023 12:21:36 - INFO - __main__ -    macro_f1 = 0.42001362707245066
+11/03/2023 12:21:36 - INFO - __main__ -    num = 326
+11/03/2023 12:21:36 - INFO - __main__ -    prec_0 = 0.7220338983050848
+11/03/2023 12:21:36 - INFO - __main__ -    prec_1 = 0.5
+11/03/2023 12:21:36 - INFO - __main__ -    prec_2 = 0.5925925925925926
+11/03/2023 12:21:36 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 12:21:36 - INFO - __main__ -    rec_1 = 0.06666666666666667
+11/03/2023 12:21:36 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:21:36 - INFO - __main__ -    Dev accuracy = 0.7085889570552147
+11/03/2023 12:21:36 - INFO - __main__ -    result['acc']=0.7085889570552147 > best_score=0.696319018404908
+11/03/2023 12:21:37 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:21:39 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:21:51 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:21:51 - INFO - __main__ -   ***** Running evaluation checkpoint-400 *****
+11/03/2023 12:21:51 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:21:51 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:21:57 - INFO - __main__ -   ***** Eval results checkpoint-400 *****
+11/03/2023 12:21:57 - INFO - __main__ -    acc = 0.6850094876660342
+11/03/2023 12:21:57 - INFO - __main__ -    correct = 361
+11/03/2023 12:21:57 - INFO - __main__ -    f1_0 = 0.8146399055489965
+11/03/2023 12:21:57 - INFO - __main__ -    f1_1 = 0.04
+11/03/2023 12:21:57 - INFO - __main__ -    f1_2 = 0.19108280254777074
+11/03/2023 12:21:57 - INFO - __main__ -    macro_f1 = 0.34857423603225574
+11/03/2023 12:21:57 - INFO - __main__ -    num = 527
+11/03/2023 12:21:57 - INFO - __main__ -    prec_0 = 0.6983805668016194
+11/03/2023 12:21:57 - INFO - __main__ -    prec_1 = 0.07692307692307693
+11/03/2023 12:21:57 - INFO - __main__ -    prec_2 = 0.75
+11/03/2023 12:21:57 - INFO - __main__ -    rec_0 = 0.9773371104815864
+11/03/2023 12:21:57 - INFO - __main__ -    rec_1 = 0.02702702702702703
+11/03/2023 12:21:57 - INFO - __main__ -    rec_2 = 0.10948905109489052
+11/03/2023 12:21:57 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:21:57 - INFO - __main__ -   ***** Running evaluation 400 *****
+11/03/2023 12:21:57 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:21:57 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:22:01 - INFO - __main__ -   ***** Eval results 400 *****
+11/03/2023 12:22:01 - INFO - __main__ -    acc = 0.7085889570552147
+11/03/2023 12:22:01 - INFO - __main__ -    correct = 231
+11/03/2023 12:22:01 - INFO - __main__ -    f1_0 = 0.8266666666666668
+11/03/2023 12:22:01 - INFO - __main__ -    f1_1 = 0.0625
+11/03/2023 12:22:01 - INFO - __main__ -    f1_2 = 0.2736842105263158
+11/03/2023 12:22:01 - INFO - __main__ -    macro_f1 = 0.3876169590643275
+11/03/2023 12:22:01 - INFO - __main__ -    num = 326
+11/03/2023 12:22:01 - INFO - __main__ -    prec_0 = 0.7185430463576159
+11/03/2023 12:22:01 - INFO - __main__ -    prec_1 = 0.5
+11/03/2023 12:22:01 - INFO - __main__ -    prec_2 = 0.5909090909090909
+11/03/2023 12:22:01 - INFO - __main__ -    rec_0 = 0.9730941704035875
+11/03/2023 12:22:01 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:22:01 - INFO - __main__ -    rec_2 = 0.1780821917808219
+11/03/2023 12:22:01 - INFO - __main__ -    Dev accuracy = 0.7085889570552147
+11/03/2023 12:22:12 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:22:12 - INFO - __main__ -   ***** Running evaluation checkpoint-420 *****
+11/03/2023 12:22:12 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:22:12 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:22:18 - INFO - __main__ -   ***** Eval results checkpoint-420 *****
+11/03/2023 12:22:18 - INFO - __main__ -    acc = 0.6850094876660342
+11/03/2023 12:22:18 - INFO - __main__ -    correct = 361
+11/03/2023 12:22:18 - INFO - __main__ -    f1_0 = 0.8193939393939395
+11/03/2023 12:22:18 - INFO - __main__ -    f1_1 = 0.06153846153846154
+11/03/2023 12:22:18 - INFO - __main__ -    f1_2 = 0.25609756097560976
+11/03/2023 12:22:18 - INFO - __main__ -    macro_f1 = 0.3790099873026702
+11/03/2023 12:22:18 - INFO - __main__ -    num = 527
+11/03/2023 12:22:18 - INFO - __main__ -    prec_0 = 0.7161016949152542
+11/03/2023 12:22:18 - INFO - __main__ -    prec_1 = 0.07142857142857142
+11/03/2023 12:22:18 - INFO - __main__ -    prec_2 = 0.7777777777777778
+11/03/2023 12:22:18 - INFO - __main__ -    rec_0 = 0.9575070821529745
+11/03/2023 12:22:18 - INFO - __main__ -    rec_1 = 0.05405405405405406
+11/03/2023 12:22:18 - INFO - __main__ -    rec_2 = 0.15328467153284672
+11/03/2023 12:22:18 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:22:18 - INFO - __main__ -   ***** Running evaluation 420 *****
+11/03/2023 12:22:18 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:22:18 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:22:22 - INFO - __main__ -   ***** Eval results 420 *****
+11/03/2023 12:22:22 - INFO - __main__ -    acc = 0.6871165644171779
+11/03/2023 12:22:22 - INFO - __main__ -    correct = 224
+11/03/2023 12:22:22 - INFO - __main__ -    f1_0 = 0.8219178082191781
+11/03/2023 12:22:22 - INFO - __main__ -    f1_1 = 0.13043478260869568
+11/03/2023 12:22:22 - INFO - __main__ -    f1_2 = 0.23157894736842105
+11/03/2023 12:22:22 - INFO - __main__ -    macro_f1 = 0.3946438460654316
+11/03/2023 12:22:22 - INFO - __main__ -    num = 326
+11/03/2023 12:22:22 - INFO - __main__ -    prec_0 = 0.7291666666666666
+11/03/2023 12:22:22 - INFO - __main__ -    prec_1 = 0.1875
+11/03/2023 12:22:22 - INFO - __main__ -    prec_2 = 0.5
+11/03/2023 12:22:22 - INFO - __main__ -    rec_0 = 0.9417040358744395
+11/03/2023 12:22:22 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:22:22 - INFO - __main__ -    rec_2 = 0.1506849315068493
+11/03/2023 12:22:22 - INFO - __main__ -    Dev accuracy = 0.6871165644171779
+11/03/2023 12:22:33 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:22:33 - INFO - __main__ -   ***** Running evaluation checkpoint-440 *****
+11/03/2023 12:22:33 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:22:33 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:22:40 - INFO - __main__ -   ***** Eval results checkpoint-440 *****
+11/03/2023 12:22:40 - INFO - __main__ -    acc = 0.6944971537001897
+11/03/2023 12:22:40 - INFO - __main__ -    correct = 366
+11/03/2023 12:22:40 - INFO - __main__ -    f1_0 = 0.8177458033573142
+11/03/2023 12:22:40 - INFO - __main__ -    f1_1 = 0.0784313725490196
+11/03/2023 12:22:40 - INFO - __main__ -    f1_2 = 0.272189349112426
+11/03/2023 12:22:40 - INFO - __main__ -    macro_f1 = 0.3894555083395866
+11/03/2023 12:22:40 - INFO - __main__ -    num = 527
+11/03/2023 12:22:40 - INFO - __main__ -    prec_0 = 0.7089397089397089
+11/03/2023 12:22:40 - INFO - __main__ -    prec_1 = 0.14285714285714285
+11/03/2023 12:22:40 - INFO - __main__ -    prec_2 = 0.71875
+11/03/2023 12:22:40 - INFO - __main__ -    rec_0 = 0.9660056657223796
+11/03/2023 12:22:40 - INFO - __main__ -    rec_1 = 0.05405405405405406
+11/03/2023 12:22:40 - INFO - __main__ -    rec_2 = 0.1678832116788321
+11/03/2023 12:22:40 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:22:40 - INFO - __main__ -   ***** Running evaluation 440 *****
+11/03/2023 12:22:40 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:22:40 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:22:43 - INFO - __main__ -   ***** Eval results 440 *****
+11/03/2023 12:22:43 - INFO - __main__ -    acc = 0.6871165644171779
+11/03/2023 12:22:43 - INFO - __main__ -    correct = 224
+11/03/2023 12:22:43 - INFO - __main__ -    f1_0 = 0.8146718146718148
+11/03/2023 12:22:43 - INFO - __main__ -    f1_1 = 0.05405405405405406
+11/03/2023 12:22:43 - INFO - __main__ -    f1_2 = 0.24742268041237112
+11/03/2023 12:22:43 - INFO - __main__ -    macro_f1 = 0.3720495163794133
+11/03/2023 12:22:43 - INFO - __main__ -    num = 326
+11/03/2023 12:22:43 - INFO - __main__ -    prec_0 = 0.7152542372881356
+11/03/2023 12:22:43 - INFO - __main__ -    prec_1 = 0.14285714285714285
+11/03/2023 12:22:43 - INFO - __main__ -    prec_2 = 0.5
+11/03/2023 12:22:43 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 12:22:43 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:22:43 - INFO - __main__ -    rec_2 = 0.1643835616438356
+11/03/2023 12:22:43 - INFO - __main__ -    Dev accuracy = 0.6871165644171779
+11/03/2023 12:22:55 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:22:55 - INFO - __main__ -   ***** Running evaluation checkpoint-460 *****
+11/03/2023 12:22:55 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:22:55 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:23:01 - INFO - __main__ -   ***** Eval results checkpoint-460 *****
+11/03/2023 12:23:01 - INFO - __main__ -    acc = 0.683111954459203
+11/03/2023 12:23:01 - INFO - __main__ -    correct = 360
+11/03/2023 12:23:01 - INFO - __main__ -    f1_0 = 0.8265682656826568
+11/03/2023 12:23:01 - INFO - __main__ -    f1_1 = 0.1095890410958904
+11/03/2023 12:23:01 - INFO - __main__ -    f1_2 = 0.23809523809523808
+11/03/2023 12:23:01 - INFO - __main__ -    macro_f1 = 0.3914175149579284
+11/03/2023 12:23:01 - INFO - __main__ -    num = 527
+11/03/2023 12:23:01 - INFO - __main__ -    prec_0 = 0.7304347826086957
+11/03/2023 12:23:01 - INFO - __main__ -    prec_1 = 0.1111111111111111
+11/03/2023 12:23:01 - INFO - __main__ -    prec_2 = 0.6451612903225806
+11/03/2023 12:23:01 - INFO - __main__ -    rec_0 = 0.9518413597733711
+11/03/2023 12:23:01 - INFO - __main__ -    rec_1 = 0.10810810810810811
+11/03/2023 12:23:01 - INFO - __main__ -    rec_2 = 0.145985401459854
+11/03/2023 12:23:01 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:23:01 - INFO - __main__ -   ***** Running evaluation 460 *****
+11/03/2023 12:23:01 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:23:01 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:23:05 - INFO - __main__ -   ***** Eval results 460 *****
+11/03/2023 12:23:05 - INFO - __main__ -    acc = 0.7024539877300614
+11/03/2023 12:23:05 - INFO - __main__ -    correct = 229
+11/03/2023 12:23:05 - INFO - __main__ -    f1_0 = 0.8383233532934131
+11/03/2023 12:23:05 - INFO - __main__ -    f1_1 = 0.16
+11/03/2023 12:23:05 - INFO - __main__ -    f1_2 = 0.297029702970297
+11/03/2023 12:23:05 - INFO - __main__ -    macro_f1 = 0.4317843520879034
+11/03/2023 12:23:05 - INFO - __main__ -    num = 326
+11/03/2023 12:23:05 - INFO - __main__ -    prec_0 = 0.7553956834532374
+11/03/2023 12:23:05 - INFO - __main__ -    prec_1 = 0.2
+11/03/2023 12:23:05 - INFO - __main__ -    prec_2 = 0.5357142857142857
+11/03/2023 12:23:05 - INFO - __main__ -    rec_0 = 0.9417040358744395
+11/03/2023 12:23:05 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 12:23:05 - INFO - __main__ -    rec_2 = 0.2054794520547945
+11/03/2023 12:23:05 - INFO - __main__ -    Dev accuracy = 0.7024539877300614
+11/03/2023 12:23:16 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:23:16 - INFO - __main__ -   ***** Running evaluation checkpoint-480 *****
+11/03/2023 12:23:16 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:23:16 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:23:22 - INFO - __main__ -   ***** Eval results checkpoint-480 *****
+11/03/2023 12:23:22 - INFO - __main__ -    acc = 0.6774193548387096
+11/03/2023 12:23:22 - INFO - __main__ -    correct = 357
+11/03/2023 12:23:22 - INFO - __main__ -    f1_0 = 0.8192771084337349
+11/03/2023 12:23:22 - INFO - __main__ -    f1_1 = 0.08823529411764705
+11/03/2023 12:23:22 - INFO - __main__ -    f1_2 = 0.1794871794871795
+11/03/2023 12:23:22 - INFO - __main__ -    macro_f1 = 0.3623331940128538
+11/03/2023 12:23:22 - INFO - __main__ -    num = 527
+11/03/2023 12:23:22 - INFO - __main__ -    prec_0 = 0.7127882599580713
+11/03/2023 12:23:22 - INFO - __main__ -    prec_1 = 0.0967741935483871
+11/03/2023 12:23:22 - INFO - __main__ -    prec_2 = 0.7368421052631579
+11/03/2023 12:23:22 - INFO - __main__ -    rec_0 = 0.9631728045325779
+11/03/2023 12:23:22 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 12:23:22 - INFO - __main__ -    rec_2 = 0.10218978102189781
+11/03/2023 12:23:22 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:23:22 - INFO - __main__ -   ***** Running evaluation 480 *****
+11/03/2023 12:23:22 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:23:22 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:23:26 - INFO - __main__ -   ***** Eval results 480 *****
+11/03/2023 12:23:26 - INFO - __main__ -    acc = 0.7055214723926381
+11/03/2023 12:23:26 - INFO - __main__ -    correct = 230
+11/03/2023 12:23:26 - INFO - __main__ -    f1_0 = 0.8287937743190661
+11/03/2023 12:23:26 - INFO - __main__ -    f1_1 = 0.13636363636363638
+11/03/2023 12:23:26 - INFO - __main__ -    f1_2 = 0.2978723404255319
+11/03/2023 12:23:26 - INFO - __main__ -    macro_f1 = 0.4210099170360781
+11/03/2023 12:23:26 - INFO - __main__ -    num = 326
+11/03/2023 12:23:26 - INFO - __main__ -    prec_0 = 0.7319587628865979
+11/03/2023 12:23:26 - INFO - __main__ -    prec_1 = 0.21428571428571427
+11/03/2023 12:23:26 - INFO - __main__ -    prec_2 = 0.6666666666666666
+11/03/2023 12:23:26 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 12:23:26 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:23:26 - INFO - __main__ -    rec_2 = 0.1917808219178082
+11/03/2023 12:23:26 - INFO - __main__ -    Dev accuracy = 0.7055214723926381
+11/03/2023 12:23:38 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:23:38 - INFO - __main__ -   ***** Running evaluation checkpoint-500 *****
+11/03/2023 12:23:38 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:23:38 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:23:44 - INFO - __main__ -   ***** Eval results checkpoint-500 *****
+11/03/2023 12:23:44 - INFO - __main__ -    acc = 0.6963946869070209
+11/03/2023 12:23:44 - INFO - __main__ -    correct = 367
+11/03/2023 12:23:44 - INFO - __main__ -    f1_0 = 0.8217821782178218
+11/03/2023 12:23:44 - INFO - __main__ -    f1_1 = 0.09836065573770492
+11/03/2023 12:23:44 - INFO - __main__ -    f1_2 = 0.3459459459459459
+11/03/2023 12:23:44 - INFO - __main__ -    macro_f1 = 0.4220295933004909
+11/03/2023 12:23:44 - INFO - __main__ -    num = 527
+11/03/2023 12:23:44 - INFO - __main__ -    prec_0 = 0.7296703296703296
+11/03/2023 12:23:44 - INFO - __main__ -    prec_1 = 0.125
+11/03/2023 12:23:44 - INFO - __main__ -    prec_2 = 0.6666666666666666
+11/03/2023 12:23:44 - INFO - __main__ -    rec_0 = 0.9405099150141643
+11/03/2023 12:23:44 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 12:23:44 - INFO - __main__ -    rec_2 = 0.23357664233576642
+11/03/2023 12:23:44 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:23:44 - INFO - __main__ -   ***** Running evaluation 500 *****
+11/03/2023 12:23:44 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:23:44 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:23:48 - INFO - __main__ -   ***** Eval results 500 *****
+11/03/2023 12:23:48 - INFO - __main__ -    acc = 0.7055214723926381
+11/03/2023 12:23:48 - INFO - __main__ -    correct = 230
+11/03/2023 12:23:48 - INFO - __main__ -    f1_0 = 0.8316831683168316
+11/03/2023 12:23:48 - INFO - __main__ -    f1_1 = 0.05
+11/03/2023 12:23:48 - INFO - __main__ -    f1_2 = 0.3551401869158879
+11/03/2023 12:23:48 - INFO - __main__ -    macro_f1 = 0.4122744517442398
+11/03/2023 12:23:48 - INFO - __main__ -    num = 326
+11/03/2023 12:23:48 - INFO - __main__ -    prec_0 = 0.7446808510638298
+11/03/2023 12:23:48 - INFO - __main__ -    prec_1 = 0.1
+11/03/2023 12:23:48 - INFO - __main__ -    prec_2 = 0.5588235294117647
+11/03/2023 12:23:48 - INFO - __main__ -    rec_0 = 0.9417040358744395
+11/03/2023 12:23:48 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:23:48 - INFO - __main__ -    rec_2 = 0.2602739726027397
+11/03/2023 12:23:48 - INFO - __main__ -    Dev accuracy = 0.7055214723926381
+11/03/2023 12:23:59 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:23:59 - INFO - __main__ -   ***** Running evaluation checkpoint-520 *****
+11/03/2023 12:23:59 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:23:59 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:24:05 - INFO - __main__ -   ***** Eval results checkpoint-520 *****
+11/03/2023 12:24:05 - INFO - __main__ -    acc = 0.6888045540796964
+11/03/2023 12:24:05 - INFO - __main__ -    correct = 363
+11/03/2023 12:24:05 - INFO - __main__ -    f1_0 = 0.8264058679706602
+11/03/2023 12:24:05 - INFO - __main__ -    f1_1 = 0.08823529411764705
+11/03/2023 12:24:05 - INFO - __main__ -    f1_2 = 0.2619047619047619
+11/03/2023 12:24:05 - INFO - __main__ -    macro_f1 = 0.3921819746643564
+11/03/2023 12:24:05 - INFO - __main__ -    num = 527
+11/03/2023 12:24:05 - INFO - __main__ -    prec_0 = 0.7268817204301076
+11/03/2023 12:24:05 - INFO - __main__ -    prec_1 = 0.0967741935483871
+11/03/2023 12:24:05 - INFO - __main__ -    prec_2 = 0.7096774193548387
+11/03/2023 12:24:05 - INFO - __main__ -    rec_0 = 0.9575070821529745
+11/03/2023 12:24:05 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 12:24:05 - INFO - __main__ -    rec_2 = 0.16058394160583941
+11/03/2023 12:24:05 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:24:05 - INFO - __main__ -   ***** Running evaluation 520 *****
+11/03/2023 12:24:05 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:24:05 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:24:09 - INFO - __main__ -   ***** Eval results 520 *****
+11/03/2023 12:24:09 - INFO - __main__ -    acc = 0.6993865030674846
+11/03/2023 12:24:09 - INFO - __main__ -    correct = 228
+11/03/2023 12:24:09 - INFO - __main__ -    f1_0 = 0.8326848249027237
+11/03/2023 12:24:09 - INFO - __main__ -    f1_1 = 0.046511627906976744
+11/03/2023 12:24:09 - INFO - __main__ -    f1_2 = 0.2736842105263158
+11/03/2023 12:24:09 - INFO - __main__ -    macro_f1 = 0.38429355444533875
+11/03/2023 12:24:09 - INFO - __main__ -    num = 326
+11/03/2023 12:24:09 - INFO - __main__ -    prec_0 = 0.7353951890034365
+11/03/2023 12:24:09 - INFO - __main__ -    prec_1 = 0.07692307692307693
+11/03/2023 12:24:09 - INFO - __main__ -    prec_2 = 0.5909090909090909
+11/03/2023 12:24:09 - INFO - __main__ -    rec_0 = 0.9596412556053812
+11/03/2023 12:24:09 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:24:09 - INFO - __main__ -    rec_2 = 0.1780821917808219
+11/03/2023 12:24:09 - INFO - __main__ -    Dev accuracy = 0.6993865030674846
+11/03/2023 12:24:21 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:24:21 - INFO - __main__ -   ***** Running evaluation checkpoint-540 *****
+11/03/2023 12:24:21 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:24:21 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:24:27 - INFO - __main__ -   ***** Eval results checkpoint-540 *****
+11/03/2023 12:24:27 - INFO - __main__ -    acc = 0.6793168880455408
+11/03/2023 12:24:27 - INFO - __main__ -    correct = 358
+11/03/2023 12:24:27 - INFO - __main__ -    f1_0 = 0.8281053952321203
+11/03/2023 12:24:27 - INFO - __main__ -    f1_1 = 0.11627906976744186
+11/03/2023 12:24:27 - INFO - __main__ -    f1_2 = 0.26900584795321636
+11/03/2023 12:24:27 - INFO - __main__ -    macro_f1 = 0.4044634376509262
+11/03/2023 12:24:27 - INFO - __main__ -    num = 527
+11/03/2023 12:24:27 - INFO - __main__ -    prec_0 = 0.7432432432432432
+11/03/2023 12:24:27 - INFO - __main__ -    prec_1 = 0.10204081632653061
+11/03/2023 12:24:27 - INFO - __main__ -    prec_2 = 0.6764705882352942
+11/03/2023 12:24:27 - INFO - __main__ -    rec_0 = 0.9348441926345609
+11/03/2023 12:24:27 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:24:27 - INFO - __main__ -    rec_2 = 0.1678832116788321
+11/03/2023 12:24:27 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:24:27 - INFO - __main__ -   ***** Running evaluation 540 *****
+11/03/2023 12:24:27 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:24:27 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:24:31 - INFO - __main__ -   ***** Eval results 540 *****
+11/03/2023 12:24:31 - INFO - __main__ -    acc = 0.7024539877300614
+11/03/2023 12:24:31 - INFO - __main__ -    correct = 229
+11/03/2023 12:24:31 - INFO - __main__ -    f1_0 = 0.8343313373253493
+11/03/2023 12:24:31 - INFO - __main__ -    f1_1 = 0.21276595744680848
+11/03/2023 12:24:31 - INFO - __main__ -    f1_2 = 0.28846153846153844
+11/03/2023 12:24:31 - INFO - __main__ -    macro_f1 = 0.4451862777445654
+11/03/2023 12:24:31 - INFO - __main__ -    num = 326
+11/03/2023 12:24:31 - INFO - __main__ -    prec_0 = 0.7517985611510791
+11/03/2023 12:24:31 - INFO - __main__ -    prec_1 = 0.29411764705882354
+11/03/2023 12:24:31 - INFO - __main__ -    prec_2 = 0.4838709677419355
+11/03/2023 12:24:31 - INFO - __main__ -    rec_0 = 0.9372197309417041
+11/03/2023 12:24:31 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:24:31 - INFO - __main__ -    rec_2 = 0.2054794520547945
+11/03/2023 12:24:31 - INFO - __main__ -    Dev accuracy = 0.7024539877300614
+11/03/2023 12:24:42 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:24:42 - INFO - __main__ -   ***** Running evaluation checkpoint-560 *****
+11/03/2023 12:24:42 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:24:42 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:24:48 - INFO - __main__ -   ***** Eval results checkpoint-560 *****
+11/03/2023 12:24:48 - INFO - __main__ -    acc = 0.6963946869070209
+11/03/2023 12:24:48 - INFO - __main__ -    correct = 367
+11/03/2023 12:24:48 - INFO - __main__ -    f1_0 = 0.8292079207920793
+11/03/2023 12:24:48 - INFO - __main__ -    f1_1 = 0.11764705882352941
+11/03/2023 12:24:48 - INFO - __main__ -    f1_2 = 0.31460674157303375
+11/03/2023 12:24:48 - INFO - __main__ -    macro_f1 = 0.42048724039621416
+11/03/2023 12:24:48 - INFO - __main__ -    num = 527
+11/03/2023 12:24:48 - INFO - __main__ -    prec_0 = 0.7362637362637363
+11/03/2023 12:24:48 - INFO - __main__ -    prec_1 = 0.12903225806451613
+11/03/2023 12:24:48 - INFO - __main__ -    prec_2 = 0.6829268292682927
+11/03/2023 12:24:48 - INFO - __main__ -    rec_0 = 0.9490084985835694
+11/03/2023 12:24:48 - INFO - __main__ -    rec_1 = 0.10810810810810811
+11/03/2023 12:24:48 - INFO - __main__ -    rec_2 = 0.20437956204379562
+11/03/2023 12:24:48 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:24:48 - INFO - __main__ -   ***** Running evaluation 560 *****
+11/03/2023 12:24:48 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:24:48 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:24:52 - INFO - __main__ -   ***** Eval results 560 *****
+11/03/2023 12:24:52 - INFO - __main__ -    acc = 0.7024539877300614
+11/03/2023 12:24:52 - INFO - __main__ -    correct = 229
+11/03/2023 12:24:52 - INFO - __main__ -    f1_0 = 0.8320000000000001
+11/03/2023 12:24:52 - INFO - __main__ -    f1_1 = 0.13333333333333333
+11/03/2023 12:24:52 - INFO - __main__ -    f1_2 = 0.3364485981308411
+11/03/2023 12:24:52 - INFO - __main__ -    macro_f1 = 0.43392731048805816
+11/03/2023 12:24:52 - INFO - __main__ -    num = 326
+11/03/2023 12:24:52 - INFO - __main__ -    prec_0 = 0.7509025270758123
+11/03/2023 12:24:52 - INFO - __main__ -    prec_1 = 0.2
+11/03/2023 12:24:52 - INFO - __main__ -    prec_2 = 0.5294117647058824
+11/03/2023 12:24:52 - INFO - __main__ -    rec_0 = 0.9327354260089686
+11/03/2023 12:24:52 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:24:52 - INFO - __main__ -    rec_2 = 0.2465753424657534
+11/03/2023 12:24:52 - INFO - __main__ -    Dev accuracy = 0.7024539877300614
+11/03/2023 12:25:03 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:25:04 - INFO - __main__ -   ***** Running evaluation checkpoint-580 *****
+11/03/2023 12:25:04 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:25:04 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:25:10 - INFO - __main__ -   ***** Eval results checkpoint-580 *****
+11/03/2023 12:25:10 - INFO - __main__ -    acc = 0.7020872865275142
+11/03/2023 12:25:10 - INFO - __main__ -    correct = 370
+11/03/2023 12:25:10 - INFO - __main__ -    f1_0 = 0.8339670468948036
+11/03/2023 12:25:10 - INFO - __main__ -    f1_1 = 0.16666666666666669
+11/03/2023 12:25:10 - INFO - __main__ -    f1_2 = 0.3626943005181347
+11/03/2023 12:25:10 - INFO - __main__ -    macro_f1 = 0.4544426713598683
+11/03/2023 12:25:10 - INFO - __main__ -    num = 527
+11/03/2023 12:25:10 - INFO - __main__ -    prec_0 = 0.7545871559633027
+11/03/2023 12:25:10 - INFO - __main__ -    prec_1 = 0.17142857142857143
+11/03/2023 12:25:10 - INFO - __main__ -    prec_2 = 0.625
+11/03/2023 12:25:10 - INFO - __main__ -    rec_0 = 0.9320113314447592
+11/03/2023 12:25:10 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 12:25:10 - INFO - __main__ -    rec_2 = 0.25547445255474455
+11/03/2023 12:25:10 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:25:10 - INFO - __main__ -   ***** Running evaluation 580 *****
+11/03/2023 12:25:10 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:25:10 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:25:13 - INFO - __main__ -   ***** Eval results 580 *****
+11/03/2023 12:25:13 - INFO - __main__ -    acc = 0.7116564417177914
+11/03/2023 12:25:13 - INFO - __main__ -    correct = 232
+11/03/2023 12:25:13 - INFO - __main__ -    f1_0 = 0.8373983739837398
+11/03/2023 12:25:13 - INFO - __main__ -    f1_1 = 0.13636363636363638
+11/03/2023 12:25:13 - INFO - __main__ -    f1_2 = 0.396551724137931
+11/03/2023 12:25:13 - INFO - __main__ -    macro_f1 = 0.45677124482843573
+11/03/2023 12:25:13 - INFO - __main__ -    num = 326
+11/03/2023 12:25:13 - INFO - __main__ -    prec_0 = 0.7657992565055762
+11/03/2023 12:25:13 - INFO - __main__ -    prec_1 = 0.21428571428571427
+11/03/2023 12:25:13 - INFO - __main__ -    prec_2 = 0.5348837209302325
+11/03/2023 12:25:13 - INFO - __main__ -    rec_0 = 0.9237668161434978
+11/03/2023 12:25:13 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:25:13 - INFO - __main__ -    rec_2 = 0.3150684931506849
+11/03/2023 12:25:13 - INFO - __main__ -    Dev accuracy = 0.7116564417177914
+11/03/2023 12:25:13 - INFO - __main__ -    result['acc']=0.7116564417177914 > best_score=0.7085889570552147
+11/03/2023 12:25:15 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:25:17 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:25:29 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:25:29 - INFO - __main__ -   ***** Running evaluation checkpoint-600 *****
+11/03/2023 12:25:29 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:25:29 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:25:35 - INFO - __main__ -   ***** Eval results checkpoint-600 *****
+11/03/2023 12:25:35 - INFO - __main__ -    acc = 0.6641366223908919
+11/03/2023 12:25:35 - INFO - __main__ -    correct = 350
+11/03/2023 12:25:35 - INFO - __main__ -    f1_0 = 0.8212435233160622
+11/03/2023 12:25:35 - INFO - __main__ -    f1_1 = 0.15238095238095237
+11/03/2023 12:25:35 - INFO - __main__ -    f1_2 = 0.2824858757062147
+11/03/2023 12:25:35 - INFO - __main__ -    macro_f1 = 0.4187034504677431
+11/03/2023 12:25:35 - INFO - __main__ -    num = 527
+11/03/2023 12:25:35 - INFO - __main__ -    prec_0 = 0.7565632458233891
+11/03/2023 12:25:35 - INFO - __main__ -    prec_1 = 0.11764705882352941
+11/03/2023 12:25:35 - INFO - __main__ -    prec_2 = 0.625
+11/03/2023 12:25:35 - INFO - __main__ -    rec_0 = 0.8980169971671388
+11/03/2023 12:25:35 - INFO - __main__ -    rec_1 = 0.21621621621621623
+11/03/2023 12:25:35 - INFO - __main__ -    rec_2 = 0.18248175182481752
+11/03/2023 12:25:35 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:25:35 - INFO - __main__ -   ***** Running evaluation 600 *****
+11/03/2023 12:25:35 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:25:35 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:25:39 - INFO - __main__ -   ***** Eval results 600 *****
+11/03/2023 12:25:39 - INFO - __main__ -    acc = 0.6932515337423313
+11/03/2023 12:25:39 - INFO - __main__ -    correct = 226
+11/03/2023 12:25:39 - INFO - __main__ -    f1_0 = 0.8336755646817249
+11/03/2023 12:25:39 - INFO - __main__ -    f1_1 = 0.19672131147540983
+11/03/2023 12:25:39 - INFO - __main__ -    f1_2 = 0.32692307692307687
+11/03/2023 12:25:39 - INFO - __main__ -    macro_f1 = 0.45243998436007055
+11/03/2023 12:25:39 - INFO - __main__ -    num = 326
+11/03/2023 12:25:39 - INFO - __main__ -    prec_0 = 0.7689393939393939
+11/03/2023 12:25:39 - INFO - __main__ -    prec_1 = 0.1935483870967742
+11/03/2023 12:25:39 - INFO - __main__ -    prec_2 = 0.5483870967741935
+11/03/2023 12:25:39 - INFO - __main__ -    rec_0 = 0.9103139013452914
+11/03/2023 12:25:39 - INFO - __main__ -    rec_1 = 0.2
+11/03/2023 12:25:39 - INFO - __main__ -    rec_2 = 0.2328767123287671
+11/03/2023 12:25:39 - INFO - __main__ -    Dev accuracy = 0.6932515337423313
+11/03/2023 12:25:50 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:25:50 - INFO - __main__ -   ***** Running evaluation checkpoint-620 *****
+11/03/2023 12:25:50 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:25:50 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:25:56 - INFO - __main__ -   ***** Eval results checkpoint-620 *****
+11/03/2023 12:25:56 - INFO - __main__ -    acc = 0.6907020872865275
+11/03/2023 12:25:56 - INFO - __main__ -    correct = 364
+11/03/2023 12:25:56 - INFO - __main__ -    f1_0 = 0.830423940149626
+11/03/2023 12:25:56 - INFO - __main__ -    f1_1 = 0.15
+11/03/2023 12:25:56 - INFO - __main__ -    f1_2 = 0.29069767441860467
+11/03/2023 12:25:56 - INFO - __main__ -    macro_f1 = 0.4237072048560769
+11/03/2023 12:25:56 - INFO - __main__ -    num = 527
+11/03/2023 12:25:56 - INFO - __main__ -    prec_0 = 0.7416481069042317
+11/03/2023 12:25:56 - INFO - __main__ -    prec_1 = 0.13953488372093023
+11/03/2023 12:25:56 - INFO - __main__ -    prec_2 = 0.7142857142857143
+11/03/2023 12:25:56 - INFO - __main__ -    rec_0 = 0.943342776203966
+11/03/2023 12:25:56 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 12:25:56 - INFO - __main__ -    rec_2 = 0.18248175182481752
+11/03/2023 12:25:56 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:25:56 - INFO - __main__ -   ***** Running evaluation 620 *****
+11/03/2023 12:25:56 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:25:56 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:26:00 - INFO - __main__ -   ***** Eval results 620 *****
+11/03/2023 12:26:00 - INFO - __main__ -    acc = 0.7085889570552147
+11/03/2023 12:26:00 - INFO - __main__ -    correct = 231
+11/03/2023 12:26:00 - INFO - __main__ -    f1_0 = 0.8383233532934131
+11/03/2023 12:26:00 - INFO - __main__ -    f1_1 = 0.18867924528301885
+11/03/2023 12:26:00 - INFO - __main__ -    f1_2 = 0.32653061224489793
+11/03/2023 12:26:00 - INFO - __main__ -    macro_f1 = 0.4511777369404433
+11/03/2023 12:26:00 - INFO - __main__ -    num = 326
+11/03/2023 12:26:00 - INFO - __main__ -    prec_0 = 0.7553956834532374
+11/03/2023 12:26:00 - INFO - __main__ -    prec_1 = 0.21739130434782608
+11/03/2023 12:26:00 - INFO - __main__ -    prec_2 = 0.64
+11/03/2023 12:26:00 - INFO - __main__ -    rec_0 = 0.9417040358744395
+11/03/2023 12:26:00 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:26:00 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:26:00 - INFO - __main__ -    Dev accuracy = 0.7085889570552147
+11/03/2023 12:26:11 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:26:12 - INFO - __main__ -   ***** Running evaluation checkpoint-640 *****
+11/03/2023 12:26:12 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:26:12 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:26:18 - INFO - __main__ -   ***** Eval results checkpoint-640 *****
+11/03/2023 12:26:18 - INFO - __main__ -    acc = 0.7001897533206831
+11/03/2023 12:26:18 - INFO - __main__ -    correct = 369
+11/03/2023 12:26:18 - INFO - __main__ -    f1_0 = 0.8319226118500604
+11/03/2023 12:26:18 - INFO - __main__ -    f1_1 = 0.15873015873015872
+11/03/2023 12:26:18 - INFO - __main__ -    f1_2 = 0.2439024390243902
+11/03/2023 12:26:18 - INFO - __main__ -    macro_f1 = 0.41151840320153643
+11/03/2023 12:26:18 - INFO - __main__ -    num = 527
+11/03/2023 12:26:18 - INFO - __main__ -    prec_0 = 0.7257383966244726
+11/03/2023 12:26:18 - INFO - __main__ -    prec_1 = 0.19230769230769232
+11/03/2023 12:26:18 - INFO - __main__ -    prec_2 = 0.7407407407407407
+11/03/2023 12:26:18 - INFO - __main__ -    rec_0 = 0.9745042492917847
+11/03/2023 12:26:18 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:26:18 - INFO - __main__ -    rec_2 = 0.145985401459854
+11/03/2023 12:26:18 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:26:18 - INFO - __main__ -   ***** Running evaluation 640 *****
+11/03/2023 12:26:18 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:26:18 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:26:21 - INFO - __main__ -   ***** Eval results 640 *****
+11/03/2023 12:26:21 - INFO - __main__ -    acc = 0.6993865030674846
+11/03/2023 12:26:21 - INFO - __main__ -    correct = 228
+11/03/2023 12:26:21 - INFO - __main__ -    f1_0 = 0.8333333333333334
+11/03/2023 12:26:21 - INFO - __main__ -    f1_1 = 0.046511627906976744
+11/03/2023 12:26:21 - INFO - __main__ -    f1_2 = 0.25806451612903225
+11/03/2023 12:26:21 - INFO - __main__ -    macro_f1 = 0.37930315912311413
+11/03/2023 12:26:21 - INFO - __main__ -    num = 326
+11/03/2023 12:26:21 - INFO - __main__ -    prec_0 = 0.7337883959044369
+11/03/2023 12:26:21 - INFO - __main__ -    prec_1 = 0.07692307692307693
+11/03/2023 12:26:21 - INFO - __main__ -    prec_2 = 0.6
+11/03/2023 12:26:21 - INFO - __main__ -    rec_0 = 0.9641255605381166
+11/03/2023 12:26:21 - INFO - __main__ -    rec_1 = 0.03333333333333333
+11/03/2023 12:26:21 - INFO - __main__ -    rec_2 = 0.1643835616438356
+11/03/2023 12:26:21 - INFO - __main__ -    Dev accuracy = 0.6993865030674846
+11/03/2023 12:26:33 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:26:33 - INFO - __main__ -   ***** Running evaluation checkpoint-660 *****
+11/03/2023 12:26:33 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:26:33 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:26:39 - INFO - __main__ -   ***** Eval results checkpoint-660 *****
+11/03/2023 12:26:39 - INFO - __main__ -    acc = 0.6944971537001897
+11/03/2023 12:26:39 - INFO - __main__ -    correct = 366
+11/03/2023 12:26:39 - INFO - __main__ -    f1_0 = 0.8268292682926829
+11/03/2023 12:26:39 - INFO - __main__ -    f1_1 = 0.14705882352941174
+11/03/2023 12:26:39 - INFO - __main__ -    f1_2 = 0.2650602409638554
+11/03/2023 12:26:39 - INFO - __main__ -    macro_f1 = 0.4129827775953167
+11/03/2023 12:26:39 - INFO - __main__ -    num = 527
+11/03/2023 12:26:39 - INFO - __main__ -    prec_0 = 0.7259100642398287
+11/03/2023 12:26:39 - INFO - __main__ -    prec_1 = 0.16129032258064516
+11/03/2023 12:26:39 - INFO - __main__ -    prec_2 = 0.7586206896551724
+11/03/2023 12:26:39 - INFO - __main__ -    rec_0 = 0.9603399433427762
+11/03/2023 12:26:39 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:26:39 - INFO - __main__ -    rec_2 = 0.16058394160583941
+11/03/2023 12:26:39 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:26:39 - INFO - __main__ -   ***** Running evaluation 660 *****
+11/03/2023 12:26:39 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:26:39 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:26:43 - INFO - __main__ -   ***** Eval results 660 *****
+11/03/2023 12:26:43 - INFO - __main__ -    acc = 0.6993865030674846
+11/03/2023 12:26:43 - INFO - __main__ -    correct = 228
+11/03/2023 12:26:43 - INFO - __main__ -    f1_0 = 0.8301158301158301
+11/03/2023 12:26:43 - INFO - __main__ -    f1_1 = 0.13953488372093023
+11/03/2023 12:26:43 - INFO - __main__ -    f1_2 = 0.21978021978021975
+11/03/2023 12:26:43 - INFO - __main__ -    macro_f1 = 0.3964769778723267
+11/03/2023 12:26:43 - INFO - __main__ -    num = 326
+11/03/2023 12:26:43 - INFO - __main__ -    prec_0 = 0.7288135593220338
+11/03/2023 12:26:43 - INFO - __main__ -    prec_1 = 0.23076923076923078
+11/03/2023 12:26:43 - INFO - __main__ -    prec_2 = 0.5555555555555556
+11/03/2023 12:26:43 - INFO - __main__ -    rec_0 = 0.9641255605381166
+11/03/2023 12:26:43 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:26:43 - INFO - __main__ -    rec_2 = 0.136986301369863
+11/03/2023 12:26:43 - INFO - __main__ -    Dev accuracy = 0.6993865030674846
+11/03/2023 12:26:54 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:26:54 - INFO - __main__ -   ***** Running evaluation checkpoint-680 *****
+11/03/2023 12:26:54 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:26:54 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:27:01 - INFO - __main__ -   ***** Eval results checkpoint-680 *****
+11/03/2023 12:27:01 - INFO - __main__ -    acc = 0.6774193548387096
+11/03/2023 12:27:01 - INFO - __main__ -    correct = 357
+11/03/2023 12:27:01 - INFO - __main__ -    f1_0 = 0.8246913580246913
+11/03/2023 12:27:01 - INFO - __main__ -    f1_1 = 0.125
+11/03/2023 12:27:01 - INFO - __main__ -    f1_2 = 0.21951219512195125
+11/03/2023 12:27:01 - INFO - __main__ -    macro_f1 = 0.3897345177155475
+11/03/2023 12:27:01 - INFO - __main__ -    num = 527
+11/03/2023 12:27:01 - INFO - __main__ -    prec_0 = 0.7308533916849015
+11/03/2023 12:27:01 - INFO - __main__ -    prec_1 = 0.11627906976744186
+11/03/2023 12:27:01 - INFO - __main__ -    prec_2 = 0.6666666666666666
+11/03/2023 12:27:01 - INFO - __main__ -    rec_0 = 0.9461756373937678
+11/03/2023 12:27:01 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:27:01 - INFO - __main__ -    rec_2 = 0.13138686131386862
+11/03/2023 12:27:01 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:27:01 - INFO - __main__ -   ***** Running evaluation 680 *****
+11/03/2023 12:27:01 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:27:01 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:27:04 - INFO - __main__ -   ***** Eval results 680 *****
+11/03/2023 12:27:04 - INFO - __main__ -    acc = 0.7147239263803681
+11/03/2023 12:27:04 - INFO - __main__ -    correct = 233
+11/03/2023 12:27:04 - INFO - __main__ -    f1_0 = 0.8404669260700388
+11/03/2023 12:27:04 - INFO - __main__ -    f1_1 = 0.21739130434782608
+11/03/2023 12:27:04 - INFO - __main__ -    f1_2 = 0.2608695652173913
+11/03/2023 12:27:04 - INFO - __main__ -    macro_f1 = 0.43957593187841876
+11/03/2023 12:27:04 - INFO - __main__ -    num = 326
+11/03/2023 12:27:04 - INFO - __main__ -    prec_0 = 0.7422680412371134
+11/03/2023 12:27:04 - INFO - __main__ -    prec_1 = 0.3125
+11/03/2023 12:27:04 - INFO - __main__ -    prec_2 = 0.631578947368421
+11/03/2023 12:27:04 - INFO - __main__ -    rec_0 = 0.968609865470852
+11/03/2023 12:27:04 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:27:04 - INFO - __main__ -    rec_2 = 0.1643835616438356
+11/03/2023 12:27:04 - INFO - __main__ -    Dev accuracy = 0.7147239263803681
+11/03/2023 12:27:04 - INFO - __main__ -    result['acc']=0.7147239263803681 > best_score=0.7116564417177914
+11/03/2023 12:27:06 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:27:08 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:27:20 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:27:20 - INFO - __main__ -   ***** Running evaluation checkpoint-700 *****
+11/03/2023 12:27:20 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:27:20 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:27:26 - INFO - __main__ -   ***** Eval results checkpoint-700 *****
+11/03/2023 12:27:26 - INFO - __main__ -    acc = 0.6888045540796964
+11/03/2023 12:27:26 - INFO - __main__ -    correct = 363
+11/03/2023 12:27:26 - INFO - __main__ -    f1_0 = 0.8265682656826568
+11/03/2023 12:27:26 - INFO - __main__ -    f1_1 = 0.14084507042253522
+11/03/2023 12:27:26 - INFO - __main__ -    f1_2 = 0.2588235294117647
+11/03/2023 12:27:26 - INFO - __main__ -    macro_f1 = 0.4087456218389856
+11/03/2023 12:27:26 - INFO - __main__ -    num = 527
+11/03/2023 12:27:26 - INFO - __main__ -    prec_0 = 0.7304347826086957
+11/03/2023 12:27:26 - INFO - __main__ -    prec_1 = 0.14705882352941177
+11/03/2023 12:27:26 - INFO - __main__ -    prec_2 = 0.6666666666666666
+11/03/2023 12:27:26 - INFO - __main__ -    rec_0 = 0.9518413597733711
+11/03/2023 12:27:26 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:27:26 - INFO - __main__ -    rec_2 = 0.16058394160583941
+11/03/2023 12:27:26 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:27:26 - INFO - __main__ -   ***** Running evaluation 700 *****
+11/03/2023 12:27:26 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:27:26 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:27:30 - INFO - __main__ -   ***** Eval results 700 *****
+11/03/2023 12:27:30 - INFO - __main__ -    acc = 0.7147239263803681
+11/03/2023 12:27:30 - INFO - __main__ -    correct = 233
+11/03/2023 12:27:30 - INFO - __main__ -    f1_0 = 0.8404669260700388
+11/03/2023 12:27:30 - INFO - __main__ -    f1_1 = 0.21739130434782608
+11/03/2023 12:27:30 - INFO - __main__ -    f1_2 = 0.2608695652173913
+11/03/2023 12:27:30 - INFO - __main__ -    macro_f1 = 0.43957593187841876
+11/03/2023 12:27:30 - INFO - __main__ -    num = 326
+11/03/2023 12:27:30 - INFO - __main__ -    prec_0 = 0.7422680412371134
+11/03/2023 12:27:30 - INFO - __main__ -    prec_1 = 0.3125
+11/03/2023 12:27:30 - INFO - __main__ -    prec_2 = 0.631578947368421
+11/03/2023 12:27:30 - INFO - __main__ -    rec_0 = 0.968609865470852
+11/03/2023 12:27:30 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:27:30 - INFO - __main__ -    rec_2 = 0.1643835616438356
+11/03/2023 12:27:30 - INFO - __main__ -    Dev accuracy = 0.7147239263803681
+11/03/2023 12:27:41 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:27:41 - INFO - __main__ -   ***** Running evaluation checkpoint-720 *****
+11/03/2023 12:27:41 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:27:41 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:27:47 - INFO - __main__ -   ***** Eval results checkpoint-720 *****
+11/03/2023 12:27:47 - INFO - __main__ -    acc = 0.6907020872865275
+11/03/2023 12:27:47 - INFO - __main__ -    correct = 364
+11/03/2023 12:27:47 - INFO - __main__ -    f1_0 = 0.8252427184466019
+11/03/2023 12:27:47 - INFO - __main__ -    f1_1 = 0.14705882352941174
+11/03/2023 12:27:47 - INFO - __main__ -    f1_2 = 0.23456790123456792
+11/03/2023 12:27:47 - INFO - __main__ -    macro_f1 = 0.4022898144035272
+11/03/2023 12:27:47 - INFO - __main__ -    num = 527
+11/03/2023 12:27:47 - INFO - __main__ -    prec_0 = 0.721868365180467
+11/03/2023 12:27:47 - INFO - __main__ -    prec_1 = 0.16129032258064516
+11/03/2023 12:27:47 - INFO - __main__ -    prec_2 = 0.76
+11/03/2023 12:27:47 - INFO - __main__ -    rec_0 = 0.9631728045325779
+11/03/2023 12:27:47 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:27:47 - INFO - __main__ -    rec_2 = 0.1386861313868613
+11/03/2023 12:27:47 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:27:47 - INFO - __main__ -   ***** Running evaluation 720 *****
+11/03/2023 12:27:47 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:27:47 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:27:51 - INFO - __main__ -   ***** Eval results 720 *****
+11/03/2023 12:27:51 - INFO - __main__ -    acc = 0.7055214723926381
+11/03/2023 12:27:51 - INFO - __main__ -    correct = 230
+11/03/2023 12:27:51 - INFO - __main__ -    f1_0 = 0.8317214700193423
+11/03/2023 12:27:51 - INFO - __main__ -    f1_1 = 0.14285714285714288
+11/03/2023 12:27:51 - INFO - __main__ -    f1_2 = 0.25806451612903225
+11/03/2023 12:27:51 - INFO - __main__ -    macro_f1 = 0.4108810430018391
+11/03/2023 12:27:51 - INFO - __main__ -    num = 326
+11/03/2023 12:27:51 - INFO - __main__ -    prec_0 = 0.7312925170068028
+11/03/2023 12:27:51 - INFO - __main__ -    prec_1 = 0.25
+11/03/2023 12:27:51 - INFO - __main__ -    prec_2 = 0.6
+11/03/2023 12:27:51 - INFO - __main__ -    rec_0 = 0.9641255605381166
+11/03/2023 12:27:51 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:27:51 - INFO - __main__ -    rec_2 = 0.1643835616438356
+11/03/2023 12:27:51 - INFO - __main__ -    Dev accuracy = 0.7055214723926381
+11/03/2023 12:28:03 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:28:03 - INFO - __main__ -   ***** Running evaluation checkpoint-740 *****
+11/03/2023 12:28:03 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:28:03 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:28:09 - INFO - __main__ -   ***** Eval results checkpoint-740 *****
+11/03/2023 12:28:09 - INFO - __main__ -    acc = 0.6793168880455408
+11/03/2023 12:28:09 - INFO - __main__ -    correct = 358
+11/03/2023 12:28:09 - INFO - __main__ -    f1_0 = 0.8207070707070707
+11/03/2023 12:28:09 - INFO - __main__ -    f1_1 = 0.11904761904761907
+11/03/2023 12:28:09 - INFO - __main__ -    f1_2 = 0.31460674157303375
+11/03/2023 12:28:09 - INFO - __main__ -    macro_f1 = 0.4181204771092412
+11/03/2023 12:28:09 - INFO - __main__ -    num = 527
+11/03/2023 12:28:09 - INFO - __main__ -    prec_0 = 0.7403189066059226
+11/03/2023 12:28:09 - INFO - __main__ -    prec_1 = 0.10638297872340426
+11/03/2023 12:28:09 - INFO - __main__ -    prec_2 = 0.6829268292682927
+11/03/2023 12:28:09 - INFO - __main__ -    rec_0 = 0.9206798866855525
+11/03/2023 12:28:09 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:28:09 - INFO - __main__ -    rec_2 = 0.20437956204379562
+11/03/2023 12:28:09 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:28:09 - INFO - __main__ -   ***** Running evaluation 740 *****
+11/03/2023 12:28:09 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:28:09 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:28:13 - INFO - __main__ -   ***** Eval results 740 *****
+11/03/2023 12:28:13 - INFO - __main__ -    acc = 0.6993865030674846
+11/03/2023 12:28:13 - INFO - __main__ -    correct = 228
+11/03/2023 12:28:13 - INFO - __main__ -    f1_0 = 0.8329979879275654
+11/03/2023 12:28:13 - INFO - __main__ -    f1_1 = 0.12244897959183673
+11/03/2023 12:28:13 - INFO - __main__ -    f1_2 = 0.33962264150943394
+11/03/2023 12:28:13 - INFO - __main__ -    macro_f1 = 0.4316898696762787
+11/03/2023 12:28:13 - INFO - __main__ -    num = 326
+11/03/2023 12:28:13 - INFO - __main__ -    prec_0 = 0.7554744525547445
+11/03/2023 12:28:13 - INFO - __main__ -    prec_1 = 0.15789473684210525
+11/03/2023 12:28:13 - INFO - __main__ -    prec_2 = 0.5454545454545454
+11/03/2023 12:28:13 - INFO - __main__ -    rec_0 = 0.9282511210762332
+11/03/2023 12:28:13 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:28:13 - INFO - __main__ -    rec_2 = 0.2465753424657534
+11/03/2023 12:28:13 - INFO - __main__ -    Dev accuracy = 0.6993865030674846
+11/03/2023 12:28:24 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:28:24 - INFO - __main__ -   ***** Running evaluation checkpoint-760 *****
+11/03/2023 12:28:24 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:28:24 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:28:30 - INFO - __main__ -   ***** Eval results checkpoint-760 *****
+11/03/2023 12:28:30 - INFO - __main__ -    acc = 0.6944971537001897
+11/03/2023 12:28:30 - INFO - __main__ -    correct = 366
+11/03/2023 12:28:30 - INFO - __main__ -    f1_0 = 0.8254364089775561
+11/03/2023 12:28:30 - INFO - __main__ -    f1_1 = 0.1388888888888889
+11/03/2023 12:28:30 - INFO - __main__ -    f1_2 = 0.33333333333333337
+11/03/2023 12:28:30 - INFO - __main__ -    macro_f1 = 0.4325528770665928
+11/03/2023 12:28:30 - INFO - __main__ -    num = 527
+11/03/2023 12:28:30 - INFO - __main__ -    prec_0 = 0.7371937639198218
+11/03/2023 12:28:30 - INFO - __main__ -    prec_1 = 0.14285714285714285
+11/03/2023 12:28:30 - INFO - __main__ -    prec_2 = 0.6976744186046512
+11/03/2023 12:28:30 - INFO - __main__ -    rec_0 = 0.9376770538243626
+11/03/2023 12:28:30 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:28:30 - INFO - __main__ -    rec_2 = 0.21897810218978103
+11/03/2023 12:28:30 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:28:30 - INFO - __main__ -   ***** Running evaluation 760 *****
+11/03/2023 12:28:30 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:28:30 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:28:34 - INFO - __main__ -   ***** Eval results 760 *****
+11/03/2023 12:28:34 - INFO - __main__ -    acc = 0.7024539877300614
+11/03/2023 12:28:34 - INFO - __main__ -    correct = 229
+11/03/2023 12:28:34 - INFO - __main__ -    f1_0 = 0.8376753507014029
+11/03/2023 12:28:34 - INFO - __main__ -    f1_1 = 0.08888888888888888
+11/03/2023 12:28:34 - INFO - __main__ -    f1_2 = 0.33333333333333326
+11/03/2023 12:28:34 - INFO - __main__ -    macro_f1 = 0.41996585764120836
+11/03/2023 12:28:34 - INFO - __main__ -    num = 326
+11/03/2023 12:28:34 - INFO - __main__ -    prec_0 = 0.7572463768115942
+11/03/2023 12:28:34 - INFO - __main__ -    prec_1 = 0.13333333333333333
+11/03/2023 12:28:34 - INFO - __main__ -    prec_2 = 0.5142857142857142
+11/03/2023 12:28:34 - INFO - __main__ -    rec_0 = 0.9372197309417041
+11/03/2023 12:28:34 - INFO - __main__ -    rec_1 = 0.06666666666666667
+11/03/2023 12:28:34 - INFO - __main__ -    rec_2 = 0.2465753424657534
+11/03/2023 12:28:34 - INFO - __main__ -    Dev accuracy = 0.7024539877300614
+11/03/2023 12:28:45 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:28:45 - INFO - __main__ -   ***** Running evaluation checkpoint-780 *****
+11/03/2023 12:28:45 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:28:45 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:28:52 - INFO - __main__ -   ***** Eval results checkpoint-780 *****
+11/03/2023 12:28:52 - INFO - __main__ -    acc = 0.6907020872865275
+11/03/2023 12:28:52 - INFO - __main__ -    correct = 364
+11/03/2023 12:28:52 - INFO - __main__ -    f1_0 = 0.824969400244798
+11/03/2023 12:28:52 - INFO - __main__ -    f1_1 = 0.1388888888888889
+11/03/2023 12:28:52 - INFO - __main__ -    f1_2 = 0.2666666666666666
+11/03/2023 12:28:52 - INFO - __main__ -    macro_f1 = 0.4101749852667845
+11/03/2023 12:28:52 - INFO - __main__ -    num = 527
+11/03/2023 12:28:52 - INFO - __main__ -    prec_0 = 0.7262931034482759
+11/03/2023 12:28:52 - INFO - __main__ -    prec_1 = 0.14285714285714285
+11/03/2023 12:28:52 - INFO - __main__ -    prec_2 = 0.7857142857142857
+11/03/2023 12:28:52 - INFO - __main__ -    rec_0 = 0.9546742209631728
+11/03/2023 12:28:52 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:28:52 - INFO - __main__ -    rec_2 = 0.16058394160583941
+11/03/2023 12:28:52 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:28:52 - INFO - __main__ -   ***** Running evaluation 780 *****
+11/03/2023 12:28:52 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:28:52 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:28:55 - INFO - __main__ -   ***** Eval results 780 *****
+11/03/2023 12:28:55 - INFO - __main__ -    acc = 0.7116564417177914
+11/03/2023 12:28:55 - INFO - __main__ -    correct = 232
+11/03/2023 12:28:55 - INFO - __main__ -    f1_0 = 0.8359375000000001
+11/03/2023 12:28:55 - INFO - __main__ -    f1_1 = 0.17777777777777776
+11/03/2023 12:28:55 - INFO - __main__ -    f1_2 = 0.29473684210526313
+11/03/2023 12:28:55 - INFO - __main__ -    macro_f1 = 0.43615070662768035
+11/03/2023 12:28:55 - INFO - __main__ -    num = 326
+11/03/2023 12:28:55 - INFO - __main__ -    prec_0 = 0.740484429065744
+11/03/2023 12:28:55 - INFO - __main__ -    prec_1 = 0.26666666666666666
+11/03/2023 12:28:55 - INFO - __main__ -    prec_2 = 0.6363636363636364
+11/03/2023 12:28:55 - INFO - __main__ -    rec_0 = 0.9596412556053812
+11/03/2023 12:28:55 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 12:28:55 - INFO - __main__ -    rec_2 = 0.1917808219178082
+11/03/2023 12:28:55 - INFO - __main__ -    Dev accuracy = 0.7116564417177914
+11/03/2023 12:29:07 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:29:07 - INFO - __main__ -   ***** Running evaluation checkpoint-800 *****
+11/03/2023 12:29:07 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:29:07 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:29:13 - INFO - __main__ -   ***** Eval results checkpoint-800 *****
+11/03/2023 12:29:13 - INFO - __main__ -    acc = 0.6717267552182163
+11/03/2023 12:29:13 - INFO - __main__ -    correct = 354
+11/03/2023 12:29:13 - INFO - __main__ -    f1_0 = 0.8179487179487179
+11/03/2023 12:29:13 - INFO - __main__ -    f1_1 = 0.1098901098901099
+11/03/2023 12:29:13 - INFO - __main__ -    f1_2 = 0.3278688524590164
+11/03/2023 12:29:13 - INFO - __main__ -    macro_f1 = 0.41856922676594815
+11/03/2023 12:29:13 - INFO - __main__ -    num = 527
+11/03/2023 12:29:13 - INFO - __main__ -    prec_0 = 0.747072599531616
+11/03/2023 12:29:13 - INFO - __main__ -    prec_1 = 0.09259259259259259
+11/03/2023 12:29:13 - INFO - __main__ -    prec_2 = 0.6521739130434783
+11/03/2023 12:29:13 - INFO - __main__ -    rec_0 = 0.9036827195467422
+11/03/2023 12:29:13 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:29:13 - INFO - __main__ -    rec_2 = 0.21897810218978103
+11/03/2023 12:29:13 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:29:13 - INFO - __main__ -   ***** Running evaluation 800 *****
+11/03/2023 12:29:13 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:29:13 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:29:17 - INFO - __main__ -   ***** Eval results 800 *****
+11/03/2023 12:29:17 - INFO - __main__ -    acc = 0.7055214723926381
+11/03/2023 12:29:17 - INFO - __main__ -    correct = 230
+11/03/2023 12:29:17 - INFO - __main__ -    f1_0 = 0.8356997971602433
+11/03/2023 12:29:17 - INFO - __main__ -    f1_1 = 0.1923076923076923
+11/03/2023 12:29:17 - INFO - __main__ -    f1_2 = 0.3551401869158879
+11/03/2023 12:29:17 - INFO - __main__ -    macro_f1 = 0.4610492254612745
+11/03/2023 12:29:17 - INFO - __main__ -    num = 326
+11/03/2023 12:29:17 - INFO - __main__ -    prec_0 = 0.762962962962963
+11/03/2023 12:29:17 - INFO - __main__ -    prec_1 = 0.22727272727272727
+11/03/2023 12:29:17 - INFO - __main__ -    prec_2 = 0.5588235294117647
+11/03/2023 12:29:17 - INFO - __main__ -    rec_0 = 0.9237668161434978
+11/03/2023 12:29:17 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:29:17 - INFO - __main__ -    rec_2 = 0.2602739726027397
+11/03/2023 12:29:17 - INFO - __main__ -    Dev accuracy = 0.7055214723926381
+11/03/2023 12:29:28 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:29:28 - INFO - __main__ -   ***** Running evaluation checkpoint-820 *****
+11/03/2023 12:29:28 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:29:28 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:29:35 - INFO - __main__ -   ***** Eval results checkpoint-820 *****
+11/03/2023 12:29:35 - INFO - __main__ -    acc = 0.6944971537001897
+11/03/2023 12:29:35 - INFO - __main__ -    correct = 366
+11/03/2023 12:29:35 - INFO - __main__ -    f1_0 = 0.8251231527093597
+11/03/2023 12:29:35 - INFO - __main__ -    f1_1 = 0.14285714285714285
+11/03/2023 12:29:35 - INFO - __main__ -    f1_2 = 0.3023255813953488
+11/03/2023 12:29:35 - INFO - __main__ -    macro_f1 = 0.42343529232061705
+11/03/2023 12:29:35 - INFO - __main__ -    num = 527
+11/03/2023 12:29:35 - INFO - __main__ -    prec_0 = 0.7298474945533769
+11/03/2023 12:29:35 - INFO - __main__ -    prec_1 = 0.15151515151515152
+11/03/2023 12:29:35 - INFO - __main__ -    prec_2 = 0.7428571428571429
+11/03/2023 12:29:35 - INFO - __main__ -    rec_0 = 0.9490084985835694
+11/03/2023 12:29:35 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:29:35 - INFO - __main__ -    rec_2 = 0.1897810218978102
+11/03/2023 12:29:35 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:29:35 - INFO - __main__ -   ***** Running evaluation 820 *****
+11/03/2023 12:29:35 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:29:35 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:29:38 - INFO - __main__ -   ***** Eval results 820 *****
+11/03/2023 12:29:38 - INFO - __main__ -    acc = 0.7085889570552147
+11/03/2023 12:29:38 - INFO - __main__ -    correct = 231
+11/03/2023 12:29:38 - INFO - __main__ -    f1_0 = 0.8375733855185911
+11/03/2023 12:29:38 - INFO - __main__ -    f1_1 = 0.13636363636363638
+11/03/2023 12:29:38 - INFO - __main__ -    f1_2 = 0.288659793814433
+11/03/2023 12:29:38 - INFO - __main__ -    macro_f1 = 0.42086560523222016
+11/03/2023 12:29:38 - INFO - __main__ -    num = 326
+11/03/2023 12:29:38 - INFO - __main__ -    prec_0 = 0.7430555555555556
+11/03/2023 12:29:38 - INFO - __main__ -    prec_1 = 0.21428571428571427
+11/03/2023 12:29:38 - INFO - __main__ -    prec_2 = 0.5833333333333334
+11/03/2023 12:29:38 - INFO - __main__ -    rec_0 = 0.9596412556053812
+11/03/2023 12:29:38 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:29:38 - INFO - __main__ -    rec_2 = 0.1917808219178082
+11/03/2023 12:29:38 - INFO - __main__ -    Dev accuracy = 0.7085889570552147
+11/03/2023 12:29:50 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:29:50 - INFO - __main__ -   ***** Running evaluation checkpoint-840 *****
+11/03/2023 12:29:50 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:29:50 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:29:56 - INFO - __main__ -   ***** Eval results checkpoint-840 *****
+11/03/2023 12:29:56 - INFO - __main__ -    acc = 0.6888045540796964
+11/03/2023 12:29:56 - INFO - __main__ -    correct = 363
+11/03/2023 12:29:56 - INFO - __main__ -    f1_0 = 0.8239700374531835
+11/03/2023 12:29:56 - INFO - __main__ -    f1_1 = 0.1282051282051282
+11/03/2023 12:29:56 - INFO - __main__ -    f1_2 = 0.32
+11/03/2023 12:29:56 - INFO - __main__ -    macro_f1 = 0.4240583885527706
+11/03/2023 12:29:56 - INFO - __main__ -    num = 527
+11/03/2023 12:29:56 - INFO - __main__ -    prec_0 = 0.7366071428571429
+11/03/2023 12:29:56 - INFO - __main__ -    prec_1 = 0.12195121951219512
+11/03/2023 12:29:56 - INFO - __main__ -    prec_2 = 0.7368421052631579
+11/03/2023 12:29:56 - INFO - __main__ -    rec_0 = 0.9348441926345609
+11/03/2023 12:29:56 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:29:56 - INFO - __main__ -    rec_2 = 0.20437956204379562
+11/03/2023 12:29:56 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:29:56 - INFO - __main__ -   ***** Running evaluation 840 *****
+11/03/2023 12:29:56 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:29:56 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:30:00 - INFO - __main__ -   ***** Eval results 840 *****
+11/03/2023 12:30:00 - INFO - __main__ -    acc = 0.7055214723926381
+11/03/2023 12:30:00 - INFO - __main__ -    correct = 230
+11/03/2023 12:30:00 - INFO - __main__ -    f1_0 = 0.8346456692913385
+11/03/2023 12:30:00 - INFO - __main__ -    f1_1 = 0.17777777777777776
+11/03/2023 12:30:00 - INFO - __main__ -    f1_2 = 0.2828282828282828
+11/03/2023 12:30:00 - INFO - __main__ -    macro_f1 = 0.43175057663246635
+11/03/2023 12:30:00 - INFO - __main__ -    num = 326
+11/03/2023 12:30:00 - INFO - __main__ -    prec_0 = 0.743859649122807
+11/03/2023 12:30:00 - INFO - __main__ -    prec_1 = 0.26666666666666666
+11/03/2023 12:30:00 - INFO - __main__ -    prec_2 = 0.5384615384615384
+11/03/2023 12:30:00 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 12:30:00 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 12:30:00 - INFO - __main__ -    rec_2 = 0.1917808219178082
+11/03/2023 12:30:00 - INFO - __main__ -    Dev accuracy = 0.7055214723926381
+11/03/2023 12:30:11 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:30:11 - INFO - __main__ -   ***** Running evaluation checkpoint-860 *****
+11/03/2023 12:30:11 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:30:11 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:30:18 - INFO - __main__ -   ***** Eval results checkpoint-860 *****
+11/03/2023 12:30:18 - INFO - __main__ -    acc = 0.683111954459203
+11/03/2023 12:30:18 - INFO - __main__ -    correct = 360
+11/03/2023 12:30:18 - INFO - __main__ -    f1_0 = 0.827144686299616
+11/03/2023 12:30:18 - INFO - __main__ -    f1_1 = 0.12903225806451613
+11/03/2023 12:30:18 - INFO - __main__ -    f1_2 = 0.34444444444444444
+11/03/2023 12:30:18 - INFO - __main__ -    macro_f1 = 0.43354046293619214
+11/03/2023 12:30:18 - INFO - __main__ -    num = 527
+11/03/2023 12:30:18 - INFO - __main__ -    prec_0 = 0.7546728971962616
+11/03/2023 12:30:18 - INFO - __main__ -    prec_1 = 0.10714285714285714
+11/03/2023 12:30:18 - INFO - __main__ -    prec_2 = 0.7209302325581395
+11/03/2023 12:30:18 - INFO - __main__ -    rec_0 = 0.9150141643059491
+11/03/2023 12:30:18 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 12:30:18 - INFO - __main__ -    rec_2 = 0.22627737226277372
+11/03/2023 12:30:18 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:30:18 - INFO - __main__ -   ***** Running evaluation 860 *****
+11/03/2023 12:30:18 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:30:18 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:30:21 - INFO - __main__ -   ***** Eval results 860 *****
+11/03/2023 12:30:21 - INFO - __main__ -    acc = 0.7024539877300614
+11/03/2023 12:30:21 - INFO - __main__ -    correct = 229
+11/03/2023 12:30:21 - INFO - __main__ -    f1_0 = 0.8309572301425663
+11/03/2023 12:30:21 - INFO - __main__ -    f1_1 = 0.23076923076923075
+11/03/2023 12:30:21 - INFO - __main__ -    f1_2 = 0.3486238532110092
+11/03/2023 12:30:21 - INFO - __main__ -    macro_f1 = 0.4701167713742687
+11/03/2023 12:30:21 - INFO - __main__ -    num = 326
+11/03/2023 12:30:21 - INFO - __main__ -    prec_0 = 0.7611940298507462
+11/03/2023 12:30:21 - INFO - __main__ -    prec_1 = 0.2727272727272727
+11/03/2023 12:30:21 - INFO - __main__ -    prec_2 = 0.5277777777777778
+11/03/2023 12:30:21 - INFO - __main__ -    rec_0 = 0.9147982062780269
+11/03/2023 12:30:21 - INFO - __main__ -    rec_1 = 0.2
+11/03/2023 12:30:21 - INFO - __main__ -    rec_2 = 0.2602739726027397
+11/03/2023 12:30:21 - INFO - __main__ -    Dev accuracy = 0.7024539877300614
+11/03/2023 12:30:33 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:30:33 - INFO - __main__ -   ***** Running evaluation checkpoint-880 *****
+11/03/2023 12:30:33 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:30:33 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:30:39 - INFO - __main__ -   ***** Eval results checkpoint-880 *****
+11/03/2023 12:30:39 - INFO - __main__ -    acc = 0.7001897533206831
+11/03/2023 12:30:39 - INFO - __main__ -    correct = 369
+11/03/2023 12:30:39 - INFO - __main__ -    f1_0 = 0.8286066584463626
+11/03/2023 12:30:39 - INFO - __main__ -    f1_1 = 0.14705882352941174
+11/03/2023 12:30:39 - INFO - __main__ -    f1_2 = 0.32
+11/03/2023 12:30:39 - INFO - __main__ -    macro_f1 = 0.4318884939919248
+11/03/2023 12:30:39 - INFO - __main__ -    num = 527
+11/03/2023 12:30:39 - INFO - __main__ -    prec_0 = 0.7336244541484717
+11/03/2023 12:30:39 - INFO - __main__ -    prec_1 = 0.16129032258064516
+11/03/2023 12:30:39 - INFO - __main__ -    prec_2 = 0.7368421052631579
+11/03/2023 12:30:39 - INFO - __main__ -    rec_0 = 0.9518413597733711
+11/03/2023 12:30:39 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:30:39 - INFO - __main__ -    rec_2 = 0.20437956204379562
+11/03/2023 12:30:39 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:30:39 - INFO - __main__ -   ***** Running evaluation 880 *****
+11/03/2023 12:30:39 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:30:39 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:30:43 - INFO - __main__ -   ***** Eval results 880 *****
+11/03/2023 12:30:43 - INFO - __main__ -    acc = 0.7085889570552147
+11/03/2023 12:30:43 - INFO - __main__ -    correct = 231
+11/03/2023 12:30:43 - INFO - __main__ -    f1_0 = 0.8352941176470587
+11/03/2023 12:30:43 - INFO - __main__ -    f1_1 = 0.14634146341463417
+11/03/2023 12:30:43 - INFO - __main__ -    f1_2 = 0.297029702970297
+11/03/2023 12:30:43 - INFO - __main__ -    macro_f1 = 0.42622176134399664
+11/03/2023 12:30:43 - INFO - __main__ -    num = 326
+11/03/2023 12:30:43 - INFO - __main__ -    prec_0 = 0.7421602787456446
+11/03/2023 12:30:43 - INFO - __main__ -    prec_1 = 0.2727272727272727
+11/03/2023 12:30:43 - INFO - __main__ -    prec_2 = 0.5357142857142857
+11/03/2023 12:30:43 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 12:30:43 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 12:30:43 - INFO - __main__ -    rec_2 = 0.2054794520547945
+11/03/2023 12:30:43 - INFO - __main__ -    Dev accuracy = 0.7085889570552147
+11/03/2023 12:30:54 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:30:54 - INFO - __main__ -   ***** Running evaluation checkpoint-900 *****
+11/03/2023 12:30:54 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:30:54 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:31:00 - INFO - __main__ -   ***** Eval results checkpoint-900 *****
+11/03/2023 12:31:00 - INFO - __main__ -    acc = 0.6793168880455408
+11/03/2023 12:31:00 - INFO - __main__ -    correct = 358
+11/03/2023 12:31:00 - INFO - __main__ -    f1_0 = 0.8230668414154653
+11/03/2023 12:31:00 - INFO - __main__ -    f1_1 = 0.16161616161616163
+11/03/2023 12:31:00 - INFO - __main__ -    f1_2 = 0.375
+11/03/2023 12:31:00 - INFO - __main__ -    macro_f1 = 0.45322766767720896
+11/03/2023 12:31:00 - INFO - __main__ -    num = 527
+11/03/2023 12:31:00 - INFO - __main__ -    prec_0 = 0.7658536585365854
+11/03/2023 12:31:00 - INFO - __main__ -    prec_1 = 0.12903225806451613
+11/03/2023 12:31:00 - INFO - __main__ -    prec_2 = 0.6545454545454545
+11/03/2023 12:31:00 - INFO - __main__ -    rec_0 = 0.8895184135977338
+11/03/2023 12:31:00 - INFO - __main__ -    rec_1 = 0.21621621621621623
+11/03/2023 12:31:00 - INFO - __main__ -    rec_2 = 0.26277372262773724
+11/03/2023 12:31:00 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:31:00 - INFO - __main__ -   ***** Running evaluation 900 *****
+11/03/2023 12:31:00 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:31:00 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:31:04 - INFO - __main__ -   ***** Eval results 900 *****
+11/03/2023 12:31:04 - INFO - __main__ -    acc = 0.7085889570552147
+11/03/2023 12:31:04 - INFO - __main__ -    correct = 231
+11/03/2023 12:31:04 - INFO - __main__ -    f1_0 = 0.8401639344262296
+11/03/2023 12:31:04 - INFO - __main__ -    f1_1 = 0.1923076923076923
+11/03/2023 12:31:04 - INFO - __main__ -    f1_2 = 0.37500000000000006
+11/03/2023 12:31:04 - INFO - __main__ -    macro_f1 = 0.46915720891130724
+11/03/2023 12:31:04 - INFO - __main__ -    num = 326
+11/03/2023 12:31:04 - INFO - __main__ -    prec_0 = 0.7735849056603774
+11/03/2023 12:31:04 - INFO - __main__ -    prec_1 = 0.22727272727272727
+11/03/2023 12:31:04 - INFO - __main__ -    prec_2 = 0.5384615384615384
+11/03/2023 12:31:04 - INFO - __main__ -    rec_0 = 0.9192825112107623
+11/03/2023 12:31:04 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:31:04 - INFO - __main__ -    rec_2 = 0.2876712328767123
+11/03/2023 12:31:04 - INFO - __main__ -    Dev accuracy = 0.7085889570552147
+11/03/2023 12:31:16 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:31:16 - INFO - __main__ -   ***** Running evaluation checkpoint-920 *****
+11/03/2023 12:31:16 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:31:16 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:31:22 - INFO - __main__ -   ***** Eval results checkpoint-920 *****
+11/03/2023 12:31:22 - INFO - __main__ -    acc = 0.6944971537001897
+11/03/2023 12:31:22 - INFO - __main__ -    correct = 366
+11/03/2023 12:31:22 - INFO - __main__ -    f1_0 = 0.8298136645962733
+11/03/2023 12:31:22 - INFO - __main__ -    f1_1 = 0.13333333333333333
+11/03/2023 12:31:22 - INFO - __main__ -    f1_2 = 0.3103448275862069
+11/03/2023 12:31:22 - INFO - __main__ -    macro_f1 = 0.4244972751719378
+11/03/2023 12:31:22 - INFO - __main__ -    num = 527
+11/03/2023 12:31:22 - INFO - __main__ -    prec_0 = 0.7389380530973452
+11/03/2023 12:31:22 - INFO - __main__ -    prec_1 = 0.13157894736842105
+11/03/2023 12:31:22 - INFO - __main__ -    prec_2 = 0.7297297297297297
+11/03/2023 12:31:22 - INFO - __main__ -    rec_0 = 0.9461756373937678
+11/03/2023 12:31:22 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:31:22 - INFO - __main__ -    rec_2 = 0.19708029197080293
+11/03/2023 12:31:22 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:31:22 - INFO - __main__ -   ***** Running evaluation 920 *****
+11/03/2023 12:31:22 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:31:22 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:31:26 - INFO - __main__ -   ***** Eval results 920 *****
+11/03/2023 12:31:26 - INFO - __main__ -    acc = 0.7085889570552147
+11/03/2023 12:31:26 - INFO - __main__ -    correct = 231
+11/03/2023 12:31:26 - INFO - __main__ -    f1_0 = 0.8330058939096266
+11/03/2023 12:31:26 - INFO - __main__ -    f1_1 = 0.21739130434782608
+11/03/2023 12:31:26 - INFO - __main__ -    f1_2 = 0.288659793814433
+11/03/2023 12:31:26 - INFO - __main__ -    macro_f1 = 0.4463523306906286
+11/03/2023 12:31:26 - INFO - __main__ -    num = 326
+11/03/2023 12:31:26 - INFO - __main__ -    prec_0 = 0.7412587412587412
+11/03/2023 12:31:26 - INFO - __main__ -    prec_1 = 0.3125
+11/03/2023 12:31:26 - INFO - __main__ -    prec_2 = 0.5833333333333334
+11/03/2023 12:31:26 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 12:31:26 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:31:26 - INFO - __main__ -    rec_2 = 0.1917808219178082
+11/03/2023 12:31:26 - INFO - __main__ -    Dev accuracy = 0.7085889570552147
+11/03/2023 12:31:37 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:31:37 - INFO - __main__ -   ***** Running evaluation checkpoint-940 *****
+11/03/2023 12:31:37 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:31:37 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:31:43 - INFO - __main__ -   ***** Eval results checkpoint-940 *****
+11/03/2023 12:31:43 - INFO - __main__ -    acc = 0.6907020872865275
+11/03/2023 12:31:43 - INFO - __main__ -    correct = 364
+11/03/2023 12:31:43 - INFO - __main__ -    f1_0 = 0.8272383354350568
+11/03/2023 12:31:43 - INFO - __main__ -    f1_1 = 0.12345679012345678
+11/03/2023 12:31:43 - INFO - __main__ -    f1_2 = 0.34444444444444444
+11/03/2023 12:31:43 - INFO - __main__ -    macro_f1 = 0.431713190000986
+11/03/2023 12:31:43 - INFO - __main__ -    num = 527
+11/03/2023 12:31:43 - INFO - __main__ -    prec_0 = 0.7454545454545455
+11/03/2023 12:31:43 - INFO - __main__ -    prec_1 = 0.11363636363636363
+11/03/2023 12:31:43 - INFO - __main__ -    prec_2 = 0.7209302325581395
+11/03/2023 12:31:43 - INFO - __main__ -    rec_0 = 0.9291784702549575
+11/03/2023 12:31:43 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:31:43 - INFO - __main__ -    rec_2 = 0.22627737226277372
+11/03/2023 12:31:43 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:31:43 - INFO - __main__ -   ***** Running evaluation 940 *****
+11/03/2023 12:31:43 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:31:43 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:31:47 - INFO - __main__ -   ***** Eval results 940 *****
+11/03/2023 12:31:47 - INFO - __main__ -    acc = 0.7177914110429447
+11/03/2023 12:31:47 - INFO - __main__ -    correct = 234
+11/03/2023 12:31:47 - INFO - __main__ -    f1_0 = 0.8439999999999999
+11/03/2023 12:31:47 - INFO - __main__ -    f1_1 = 0.20833333333333334
+11/03/2023 12:31:47 - INFO - __main__ -    f1_2 = 0.34615384615384615
+11/03/2023 12:31:47 - INFO - __main__ -    macro_f1 = 0.46616239316239305
+11/03/2023 12:31:47 - INFO - __main__ -    num = 326
+11/03/2023 12:31:47 - INFO - __main__ -    prec_0 = 0.7617328519855595
+11/03/2023 12:31:47 - INFO - __main__ -    prec_1 = 0.2777777777777778
+11/03/2023 12:31:47 - INFO - __main__ -    prec_2 = 0.5806451612903226
+11/03/2023 12:31:47 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 12:31:47 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:31:47 - INFO - __main__ -    rec_2 = 0.2465753424657534
+11/03/2023 12:31:47 - INFO - __main__ -    Dev accuracy = 0.7177914110429447
+11/03/2023 12:31:47 - INFO - __main__ -    result['acc']=0.7177914110429447 > best_score=0.7147239263803681
+11/03/2023 12:31:49 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:31:51 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 12:32:03 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:32:03 - INFO - __main__ -   ***** Running evaluation checkpoint-960 *****
+11/03/2023 12:32:03 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:32:03 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:32:09 - INFO - __main__ -   ***** Eval results checkpoint-960 *****
+11/03/2023 12:32:09 - INFO - __main__ -    acc = 0.6907020872865275
+11/03/2023 12:32:09 - INFO - __main__ -    correct = 364
+11/03/2023 12:32:09 - INFO - __main__ -    f1_0 = 0.8297604035308953
+11/03/2023 12:32:09 - INFO - __main__ -    f1_1 = 0.12048192771084337
+11/03/2023 12:32:09 - INFO - __main__ -    f1_2 = 0.33707865168539325
+11/03/2023 12:32:09 - INFO - __main__ -    macro_f1 = 0.429106994309044
+11/03/2023 12:32:09 - INFO - __main__ -    num = 527
+11/03/2023 12:32:09 - INFO - __main__ -    prec_0 = 0.7477272727272727
+11/03/2023 12:32:09 - INFO - __main__ -    prec_1 = 0.10869565217391304
+11/03/2023 12:32:09 - INFO - __main__ -    prec_2 = 0.7317073170731707
+11/03/2023 12:32:09 - INFO - __main__ -    rec_0 = 0.9320113314447592
+11/03/2023 12:32:09 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:32:09 - INFO - __main__ -    rec_2 = 0.21897810218978103
+11/03/2023 12:32:09 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:32:09 - INFO - __main__ -   ***** Running evaluation 960 *****
+11/03/2023 12:32:09 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:32:09 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:32:13 - INFO - __main__ -   ***** Eval results 960 *****
+11/03/2023 12:32:13 - INFO - __main__ -    acc = 0.7177914110429447
+11/03/2023 12:32:13 - INFO - __main__ -    correct = 234
+11/03/2023 12:32:13 - INFO - __main__ -    f1_0 = 0.8423153692614771
+11/03/2023 12:32:13 - INFO - __main__ -    f1_1 = 0.21276595744680848
+11/03/2023 12:32:13 - INFO - __main__ -    f1_2 = 0.34615384615384615
+11/03/2023 12:32:13 - INFO - __main__ -    macro_f1 = 0.46707839095404396
+11/03/2023 12:32:13 - INFO - __main__ -    num = 326
+11/03/2023 12:32:13 - INFO - __main__ -    prec_0 = 0.7589928057553957
+11/03/2023 12:32:13 - INFO - __main__ -    prec_1 = 0.29411764705882354
+11/03/2023 12:32:13 - INFO - __main__ -    prec_2 = 0.5806451612903226
+11/03/2023 12:32:13 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 12:32:13 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:32:13 - INFO - __main__ -    rec_2 = 0.2465753424657534
+11/03/2023 12:32:13 - INFO - __main__ -    Dev accuracy = 0.7177914110429447
+11/03/2023 12:32:24 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:32:24 - INFO - __main__ -   ***** Running evaluation checkpoint-980 *****
+11/03/2023 12:32:24 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:32:24 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:32:30 - INFO - __main__ -   ***** Eval results checkpoint-980 *****
+11/03/2023 12:32:30 - INFO - __main__ -    acc = 0.6925996204933587
+11/03/2023 12:32:30 - INFO - __main__ -    correct = 365
+11/03/2023 12:32:30 - INFO - __main__ -    f1_0 = 0.8287153652392947
+11/03/2023 12:32:30 - INFO - __main__ -    f1_1 = 0.125
+11/03/2023 12:32:30 - INFO - __main__ -    f1_2 = 0.34444444444444444
+11/03/2023 12:32:30 - INFO - __main__ -    macro_f1 = 0.4327199365612464
+11/03/2023 12:32:30 - INFO - __main__ -    num = 527
+11/03/2023 12:32:30 - INFO - __main__ -    prec_0 = 0.746031746031746
+11/03/2023 12:32:30 - INFO - __main__ -    prec_1 = 0.11627906976744186
+11/03/2023 12:32:30 - INFO - __main__ -    prec_2 = 0.7209302325581395
+11/03/2023 12:32:30 - INFO - __main__ -    rec_0 = 0.9320113314447592
+11/03/2023 12:32:30 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:32:30 - INFO - __main__ -    rec_2 = 0.22627737226277372
+11/03/2023 12:32:30 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:32:30 - INFO - __main__ -   ***** Running evaluation 980 *****
+11/03/2023 12:32:30 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:32:30 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:32:34 - INFO - __main__ -   ***** Eval results 980 *****
+11/03/2023 12:32:34 - INFO - __main__ -    acc = 0.7085889570552147
+11/03/2023 12:32:34 - INFO - __main__ -    correct = 231
+11/03/2023 12:32:34 - INFO - __main__ -    f1_0 = 0.8389662027833003
+11/03/2023 12:32:34 - INFO - __main__ -    f1_1 = 0.1739130434782609
+11/03/2023 12:32:34 - INFO - __main__ -    f1_2 = 0.3106796116504854
+11/03/2023 12:32:34 - INFO - __main__ -    macro_f1 = 0.44118628597068216
+11/03/2023 12:32:34 - INFO - __main__ -    num = 326
+11/03/2023 12:32:34 - INFO - __main__ -    prec_0 = 0.7535714285714286
+11/03/2023 12:32:34 - INFO - __main__ -    prec_1 = 0.25
+11/03/2023 12:32:34 - INFO - __main__ -    prec_2 = 0.5333333333333333
+11/03/2023 12:32:34 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 12:32:34 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 12:32:34 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:32:34 - INFO - __main__ -    Dev accuracy = 0.7085889570552147
+11/03/2023 12:32:45 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:32:45 - INFO - __main__ -   ***** Running evaluation checkpoint-1000 *****
+11/03/2023 12:32:45 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:32:45 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:32:52 - INFO - __main__ -   ***** Eval results checkpoint-1000 *****
+11/03/2023 12:32:52 - INFO - __main__ -    acc = 0.6907020872865275
+11/03/2023 12:32:52 - INFO - __main__ -    correct = 364
+11/03/2023 12:32:52 - INFO - __main__ -    f1_0 = 0.8283582089552238
+11/03/2023 12:32:52 - INFO - __main__ -    f1_1 = 0.12987012987012989
+11/03/2023 12:32:52 - INFO - __main__ -    f1_2 = 0.3005780346820809
+11/03/2023 12:32:52 - INFO - __main__ -    macro_f1 = 0.4196021245024782
+11/03/2023 12:32:52 - INFO - __main__ -    num = 527
+11/03/2023 12:32:52 - INFO - __main__ -    prec_0 = 0.738359201773836
+11/03/2023 12:32:52 - INFO - __main__ -    prec_1 = 0.125
+11/03/2023 12:32:52 - INFO - __main__ -    prec_2 = 0.7222222222222222
+11/03/2023 12:32:52 - INFO - __main__ -    rec_0 = 0.943342776203966
+11/03/2023 12:32:52 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:32:52 - INFO - __main__ -    rec_2 = 0.1897810218978102
+11/03/2023 12:32:52 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:32:52 - INFO - __main__ -   ***** Running evaluation 1000 *****
+11/03/2023 12:32:52 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:32:52 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:32:55 - INFO - __main__ -   ***** Eval results 1000 *****
+11/03/2023 12:32:55 - INFO - __main__ -    acc = 0.7147239263803681
+11/03/2023 12:32:55 - INFO - __main__ -    correct = 233
+11/03/2023 12:32:55 - INFO - __main__ -    f1_0 = 0.8362919132149902
+11/03/2023 12:32:55 - INFO - __main__ -    f1_1 = 0.21739130434782608
+11/03/2023 12:32:55 - INFO - __main__ -    f1_2 = 0.3232323232323232
+11/03/2023 12:32:55 - INFO - __main__ -    macro_f1 = 0.4589718469317132
+11/03/2023 12:32:55 - INFO - __main__ -    num = 326
+11/03/2023 12:32:55 - INFO - __main__ -    prec_0 = 0.7464788732394366
+11/03/2023 12:32:55 - INFO - __main__ -    prec_1 = 0.3125
+11/03/2023 12:32:55 - INFO - __main__ -    prec_2 = 0.6153846153846154
+11/03/2023 12:32:55 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 12:32:55 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:32:55 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:32:55 - INFO - __main__ -    Dev accuracy = 0.7147239263803681
+11/03/2023 12:33:07 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:33:07 - INFO - __main__ -   ***** Running evaluation checkpoint-1020 *****
+11/03/2023 12:33:07 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:33:07 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:33:13 - INFO - __main__ -   ***** Eval results checkpoint-1020 *****
+11/03/2023 12:33:13 - INFO - __main__ -    acc = 0.6869070208728653
+11/03/2023 12:33:13 - INFO - __main__ -    correct = 362
+11/03/2023 12:33:13 - INFO - __main__ -    f1_0 = 0.8274999999999999
+11/03/2023 12:33:13 - INFO - __main__ -    f1_1 = 0.12345679012345678
+11/03/2023 12:33:13 - INFO - __main__ -    f1_2 = 0.3005780346820809
+11/03/2023 12:33:13 - INFO - __main__ -    macro_f1 = 0.41717827493517917
+11/03/2023 12:33:13 - INFO - __main__ -    num = 527
+11/03/2023 12:33:13 - INFO - __main__ -    prec_0 = 0.7404921700223713
+11/03/2023 12:33:13 - INFO - __main__ -    prec_1 = 0.11363636363636363
+11/03/2023 12:33:13 - INFO - __main__ -    prec_2 = 0.7222222222222222
+11/03/2023 12:33:13 - INFO - __main__ -    rec_0 = 0.9376770538243626
+11/03/2023 12:33:13 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:33:13 - INFO - __main__ -    rec_2 = 0.1897810218978102
+11/03/2023 12:33:13 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:33:13 - INFO - __main__ -   ***** Running evaluation 1020 *****
+11/03/2023 12:33:13 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:33:13 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:33:17 - INFO - __main__ -   ***** Eval results 1020 *****
+11/03/2023 12:33:17 - INFO - __main__ -    acc = 0.7116564417177914
+11/03/2023 12:33:17 - INFO - __main__ -    correct = 232
+11/03/2023 12:33:17 - INFO - __main__ -    f1_0 = 0.8356435643564357
+11/03/2023 12:33:17 - INFO - __main__ -    f1_1 = 0.21276595744680848
+11/03/2023 12:33:17 - INFO - __main__ -    f1_2 = 0.32
+11/03/2023 12:33:17 - INFO - __main__ -    macro_f1 = 0.45613650726774807
+11/03/2023 12:33:17 - INFO - __main__ -    num = 326
+11/03/2023 12:33:17 - INFO - __main__ -    prec_0 = 0.74822695035461
+11/03/2023 12:33:17 - INFO - __main__ -    prec_1 = 0.29411764705882354
+11/03/2023 12:33:17 - INFO - __main__ -    prec_2 = 0.5925925925925926
+11/03/2023 12:33:17 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 12:33:17 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:33:17 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:33:17 - INFO - __main__ -    Dev accuracy = 0.7116564417177914
+11/03/2023 12:33:28 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:33:28 - INFO - __main__ -   ***** Running evaluation checkpoint-1040 *****
+11/03/2023 12:33:28 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:33:28 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:33:34 - INFO - __main__ -   ***** Eval results checkpoint-1040 *****
+11/03/2023 12:33:34 - INFO - __main__ -    acc = 0.6944971537001897
+11/03/2023 12:33:34 - INFO - __main__ -    correct = 366
+11/03/2023 12:33:34 - INFO - __main__ -    f1_0 = 0.8293897882938979
+11/03/2023 12:33:34 - INFO - __main__ -    f1_1 = 0.13157894736842105
+11/03/2023 12:33:34 - INFO - __main__ -    f1_2 = 0.32
+11/03/2023 12:33:34 - INFO - __main__ -    macro_f1 = 0.4269895785541063
+11/03/2023 12:33:34 - INFO - __main__ -    num = 527
+11/03/2023 12:33:34 - INFO - __main__ -    prec_0 = 0.74
+11/03/2023 12:33:34 - INFO - __main__ -    prec_1 = 0.1282051282051282
+11/03/2023 12:33:34 - INFO - __main__ -    prec_2 = 0.7368421052631579
+11/03/2023 12:33:34 - INFO - __main__ -    rec_0 = 0.943342776203966
+11/03/2023 12:33:34 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:33:34 - INFO - __main__ -    rec_2 = 0.20437956204379562
+11/03/2023 12:33:34 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:33:34 - INFO - __main__ -   ***** Running evaluation 1040 *****
+11/03/2023 12:33:34 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:33:34 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:33:38 - INFO - __main__ -   ***** Eval results 1040 *****
+11/03/2023 12:33:38 - INFO - __main__ -    acc = 0.7116564417177914
+11/03/2023 12:33:38 - INFO - __main__ -    correct = 232
+11/03/2023 12:33:38 - INFO - __main__ -    f1_0 = 0.8379446640316205
+11/03/2023 12:33:38 - INFO - __main__ -    f1_1 = 0.17777777777777776
+11/03/2023 12:33:38 - INFO - __main__ -    f1_2 = 0.31683168316831684
+11/03/2023 12:33:38 - INFO - __main__ -    macro_f1 = 0.444184708325905
+11/03/2023 12:33:38 - INFO - __main__ -    num = 326
+11/03/2023 12:33:38 - INFO - __main__ -    prec_0 = 0.7491166077738516
+11/03/2023 12:33:38 - INFO - __main__ -    prec_1 = 0.26666666666666666
+11/03/2023 12:33:38 - INFO - __main__ -    prec_2 = 0.5714285714285714
+11/03/2023 12:33:38 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 12:33:38 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 12:33:38 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:33:38 - INFO - __main__ -    Dev accuracy = 0.7116564417177914
+11/03/2023 12:33:50 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:33:50 - INFO - __main__ -   ***** Running evaluation checkpoint-1060 *****
+11/03/2023 12:33:50 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:33:50 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:33:56 - INFO - __main__ -   ***** Eval results checkpoint-1060 *****
+11/03/2023 12:33:56 - INFO - __main__ -    acc = 0.6944971537001897
+11/03/2023 12:33:56 - INFO - __main__ -    correct = 366
+11/03/2023 12:33:56 - INFO - __main__ -    f1_0 = 0.8293897882938979
+11/03/2023 12:33:56 - INFO - __main__ -    f1_1 = 0.13157894736842105
+11/03/2023 12:33:56 - INFO - __main__ -    f1_2 = 0.32
+11/03/2023 12:33:56 - INFO - __main__ -    macro_f1 = 0.4269895785541063
+11/03/2023 12:33:56 - INFO - __main__ -    num = 527
+11/03/2023 12:33:56 - INFO - __main__ -    prec_0 = 0.74
+11/03/2023 12:33:56 - INFO - __main__ -    prec_1 = 0.1282051282051282
+11/03/2023 12:33:56 - INFO - __main__ -    prec_2 = 0.7368421052631579
+11/03/2023 12:33:56 - INFO - __main__ -    rec_0 = 0.943342776203966
+11/03/2023 12:33:56 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:33:56 - INFO - __main__ -    rec_2 = 0.20437956204379562
+11/03/2023 12:33:56 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:33:56 - INFO - __main__ -   ***** Running evaluation 1060 *****
+11/03/2023 12:33:56 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:33:56 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:34:00 - INFO - __main__ -   ***** Eval results 1060 *****
+11/03/2023 12:34:00 - INFO - __main__ -    acc = 0.7116564417177914
+11/03/2023 12:34:00 - INFO - __main__ -    correct = 232
+11/03/2023 12:34:00 - INFO - __main__ -    f1_0 = 0.8379446640316205
+11/03/2023 12:34:00 - INFO - __main__ -    f1_1 = 0.17777777777777776
+11/03/2023 12:34:00 - INFO - __main__ -    f1_2 = 0.31683168316831684
+11/03/2023 12:34:00 - INFO - __main__ -    macro_f1 = 0.444184708325905
+11/03/2023 12:34:00 - INFO - __main__ -    num = 326
+11/03/2023 12:34:00 - INFO - __main__ -    prec_0 = 0.7491166077738516
+11/03/2023 12:34:00 - INFO - __main__ -    prec_1 = 0.26666666666666666
+11/03/2023 12:34:00 - INFO - __main__ -    prec_2 = 0.5714285714285714
+11/03/2023 12:34:00 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 12:34:00 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 12:34:00 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:34:00 - INFO - __main__ -    Dev accuracy = 0.7116564417177914
+11/03/2023 12:34:00 - INFO - __main__ -    global_step = 1060, average loss = 0.31039862611815927
+11/03/2023 12:34:00 - INFO - __main__ -    best checkpoint = ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best, best score = 0.7177914110429447
+11/03/2023 12:34:00 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//
+11/03/2023 12:34:04 - INFO - __main__ -   Evaluate the following checkpoints: ['./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256/checkpoint-best', './outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256']
+11/03/2023 12:34:06 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:34:06 - INFO - __main__ -   ***** Running evaluation checkpoint-best *****
+11/03/2023 12:34:06 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:34:06 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:34:10 - INFO - __main__ -   ***** Eval results checkpoint-best *****
+11/03/2023 12:34:10 - INFO - __main__ -    acc = 0.7177914110429447
+11/03/2023 12:34:10 - INFO - __main__ -    correct = 234
+11/03/2023 12:34:10 - INFO - __main__ -    f1_0 = 0.8439999999999999
+11/03/2023 12:34:10 - INFO - __main__ -    f1_1 = 0.20833333333333334
+11/03/2023 12:34:10 - INFO - __main__ -    f1_2 = 0.34615384615384615
+11/03/2023 12:34:10 - INFO - __main__ -    macro_f1 = 0.46616239316239305
+11/03/2023 12:34:10 - INFO - __main__ -    num = 326
+11/03/2023 12:34:10 - INFO - __main__ -    prec_0 = 0.7617328519855595
+11/03/2023 12:34:10 - INFO - __main__ -    prec_1 = 0.2777777777777778
+11/03/2023 12:34:10 - INFO - __main__ -    prec_2 = 0.5806451612903226
+11/03/2023 12:34:10 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 12:34:10 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 12:34:10 - INFO - __main__ -    rec_2 = 0.2465753424657534
+11/03/2023 12:34:11 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 12:34:12 - INFO - __main__ -   ***** Running evaluation  *****
+11/03/2023 12:34:12 - INFO - __main__ -     Num examples = 326
+11/03/2023 12:34:12 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:34:15 - INFO - __main__ -   ***** Eval results  *****
+11/03/2023 12:34:15 - INFO - __main__ -    acc = 0.7116564417177914
+11/03/2023 12:34:15 - INFO - __main__ -    correct = 232
+11/03/2023 12:34:15 - INFO - __main__ -    f1_0 = 0.8379446640316205
+11/03/2023 12:34:15 - INFO - __main__ -    f1_1 = 0.17777777777777776
+11/03/2023 12:34:15 - INFO - __main__ -    f1_2 = 0.31683168316831684
+11/03/2023 12:34:15 - INFO - __main__ -    macro_f1 = 0.444184708325905
+11/03/2023 12:34:15 - INFO - __main__ -    num = 326
+11/03/2023 12:34:15 - INFO - __main__ -    prec_0 = 0.7491166077738516
+11/03/2023 12:34:15 - INFO - __main__ -    prec_1 = 0.26666666666666666
+11/03/2023 12:34:15 - INFO - __main__ -    prec_2 = 0.5714285714285714
+11/03/2023 12:34:15 - INFO - __main__ -    rec_0 = 0.9506726457399103
+11/03/2023 12:34:15 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 12:34:15 - INFO - __main__ -    rec_2 = 0.2191780821917808
+11/03/2023 12:34:15 - INFO - __main__ -   Best checkpoint is ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256/checkpoint-best, best accuracy is 0.7177914110429447
+11/03/2023 12:34:17 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 12:34:18 - INFO - __main__ -   ***** Running evaluation best_checkpoint *****
+11/03/2023 12:34:18 - INFO - __main__ -     Num examples = 527
+11/03/2023 12:34:18 - INFO - __main__ -     Batch size = 8
+11/03/2023 12:34:24 - INFO - __main__ -   ***** Save prediction ******
+11/03/2023 12:34:24 - INFO - __main__ -   ***** Eval results best_checkpoint *****
+11/03/2023 12:34:24 - INFO - __main__ -    acc = 0.6907020872865275
+11/03/2023 12:34:24 - INFO - __main__ -    correct = 364
+11/03/2023 12:34:24 - INFO - __main__ -    f1_0 = 0.8272383354350568
+11/03/2023 12:34:24 - INFO - __main__ -    f1_1 = 0.12345679012345678
+11/03/2023 12:34:24 - INFO - __main__ -    f1_2 = 0.34444444444444444
+11/03/2023 12:34:24 - INFO - __main__ -    macro_f1 = 0.431713190000986
+11/03/2023 12:34:24 - INFO - __main__ -    num = 527
+11/03/2023 12:34:24 - INFO - __main__ -    prec_0 = 0.7454545454545455
+11/03/2023 12:34:24 - INFO - __main__ -    prec_1 = 0.11363636363636363
+11/03/2023 12:34:24 - INFO - __main__ -    prec_2 = 0.7209302325581395
+11/03/2023 12:34:24 - INFO - __main__ -    rec_0 = 0.9291784702549575
+11/03/2023 12:34:24 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 12:34:24 - INFO - __main__ -    rec_2 = 0.22627737226277372
+11/03/2023 12:34:24 - INFO - __main__ -   0.6907020872865275
+11/03/2023 13:20:29 - INFO - root -   Input args: Namespace(adam_epsilon=1e-08, cache_dir='', config_name='', data_dir='./data/oversample//comp', do_eval=True, do_lower_case=False, do_predict=True, do_predict_dev=False, do_train=True, eval_all_checkpoints=True, eval_test_set=True, evaluate_during_training=False, fp16=False, fp16_opt_level='O1', gradient_accumulation_steps=1, init_checkpoint=None, learning_rate=1e-05, local_rank=-1, log_file='train', logging_steps=50, max_grad_norm=1.0, max_seq_length=256, max_steps=-1, model_name_or_path='roberta-large', model_type='roberta', no_cuda=False, num_train_epochs=10.0, output_dir='./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//', overwrite_cache=False, overwrite_output_dir=True, per_gpu_eval_batch_size=8, per_gpu_train_batch_size=64, save_only_best_checkpoint=True, save_steps=20, seed=42, server_ip='', server_port='', task_name='comp', test_split='test', tokenizer_name='', train_split='train', warmup_steps=0, weight_decay=0.0)
+11/03/2023 13:20:30 - WARNING - __main__ -   Process rank: -1, device: cuda, n_gpu: 1, distributed training: False, 16-bits training: False
+11/03/2023 13:20:31 - INFO - __main__ -   config = RobertaConfig {
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "comp",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}
+
+11/03/2023 13:20:31 - INFO - __main__ -   Training/evaluation parameters Namespace(adam_epsilon=1e-08, cache_dir='', config_name='', data_dir='./data/oversample//comp', device=device(type='cuda'), do_eval=True, do_lower_case=False, do_predict=True, do_predict_dev=False, do_train=True, eval_all_checkpoints=True, eval_test_set=True, evaluate_during_training=False, fp16=False, fp16_opt_level='O1', gradient_accumulation_steps=1, init_checkpoint=None, learning_rate=1e-05, local_rank=-1, log_file='train', logging_steps=50, max_grad_norm=1.0, max_seq_length=256, max_steps=-1, model_name_or_path='roberta-large', model_type='roberta', n_gpu=1, no_cuda=False, num_train_epochs=10.0, output_dir='./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//', output_mode='classification', overwrite_cache=False, overwrite_output_dir=True, per_gpu_eval_batch_size=8, per_gpu_train_batch_size=64, save_only_best_checkpoint=True, save_steps=20, seed=42, server_ip='', server_port='', task_name='comp', test_split='test', tokenizer_name='', train_split='train', warmup_steps=0, weight_decay=0.0)
+11/03/2023 13:20:31 - INFO - __main__ -   loading from existing model roberta-large
+11/03/2023 13:20:41 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_train_roberta-large_256_comp_
+11/03/2023 13:20:41 - INFO - __main__ -   ***** Running training *****
+11/03/2023 13:20:41 - INFO - __main__ -     Num examples = 1696
+11/03/2023 13:20:41 - INFO - __main__ -     Num Epochs = 10
+11/03/2023 13:20:41 - INFO - __main__ -     Instantaneous batch size per GPU = 64
+11/03/2023 13:20:41 - INFO - __main__ -     Total train batch size (w. parallel, distributed & accumulation) = 64
+11/03/2023 13:20:41 - INFO - __main__ -     Gradient Accumulation steps = 1
+11/03/2023 13:20:41 - INFO - __main__ -     Total optimization steps = 270
+11/03/2023 13:21:25 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:21:25 - INFO - __main__ -   ***** Running evaluation checkpoint-20 *****
+11/03/2023 13:21:25 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:21:25 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:21:31 - INFO - __main__ -   ***** Eval results checkpoint-20 *****
+11/03/2023 13:21:31 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 13:21:31 - INFO - __main__ -    correct = 353
+11/03/2023 13:21:31 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 13:21:31 - INFO - __main__ -    f1_1 = 0
+11/03/2023 13:21:31 - INFO - __main__ -    f1_2 = 0
+11/03/2023 13:21:31 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 13:21:31 - INFO - __main__ -    num = 527
+11/03/2023 13:21:31 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 13:21:31 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 13:21:31 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 13:21:31 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 13:21:31 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 13:21:31 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 13:21:31 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:21:32 - INFO - __main__ -   ***** Running evaluation 20 *****
+11/03/2023 13:21:32 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:21:32 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:21:35 - INFO - __main__ -   ***** Eval results 20 *****
+11/03/2023 13:21:35 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 13:21:35 - INFO - __main__ -    correct = 223
+11/03/2023 13:21:35 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 13:21:35 - INFO - __main__ -    f1_1 = 0
+11/03/2023 13:21:35 - INFO - __main__ -    f1_2 = 0
+11/03/2023 13:21:35 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 13:21:35 - INFO - __main__ -    num = 326
+11/03/2023 13:21:35 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 13:21:35 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 13:21:35 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 13:21:35 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 13:21:35 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 13:21:35 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 13:21:35 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 13:21:35 - INFO - __main__ -    result['acc']=0.6840490797546013 > best_score=0
+11/03/2023 13:21:37 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:21:39 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:22:18 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:22:18 - INFO - __main__ -   ***** Running evaluation checkpoint-40 *****
+11/03/2023 13:22:18 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:22:18 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:22:24 - INFO - __main__ -   ***** Eval results checkpoint-40 *****
+11/03/2023 13:22:24 - INFO - __main__ -    acc = 0.6698292220113852
+11/03/2023 13:22:24 - INFO - __main__ -    correct = 353
+11/03/2023 13:22:24 - INFO - __main__ -    f1_0 = 0.8022727272727272
+11/03/2023 13:22:24 - INFO - __main__ -    f1_1 = 0
+11/03/2023 13:22:24 - INFO - __main__ -    f1_2 = 0
+11/03/2023 13:22:24 - INFO - __main__ -    macro_f1 = 0.2674242424242424
+11/03/2023 13:22:24 - INFO - __main__ -    num = 527
+11/03/2023 13:22:24 - INFO - __main__ -    prec_0 = 0.6698292220113852
+11/03/2023 13:22:24 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 13:22:24 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 13:22:24 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 13:22:24 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 13:22:24 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 13:22:24 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:22:24 - INFO - __main__ -   ***** Running evaluation 40 *****
+11/03/2023 13:22:24 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:22:24 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:22:28 - INFO - __main__ -   ***** Eval results 40 *****
+11/03/2023 13:22:28 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 13:22:28 - INFO - __main__ -    correct = 223
+11/03/2023 13:22:28 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 13:22:28 - INFO - __main__ -    f1_1 = 0
+11/03/2023 13:22:28 - INFO - __main__ -    f1_2 = 0
+11/03/2023 13:22:28 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 13:22:28 - INFO - __main__ -    num = 326
+11/03/2023 13:22:28 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 13:22:28 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 13:22:28 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 13:22:28 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 13:22:28 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 13:22:28 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 13:22:28 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 13:23:07 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:23:07 - INFO - __main__ -   ***** Running evaluation checkpoint-60 *****
+11/03/2023 13:23:07 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:23:07 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:23:14 - INFO - __main__ -   ***** Eval results checkpoint-60 *****
+11/03/2023 13:23:14 - INFO - __main__ -    acc = 0.6717267552182163
+11/03/2023 13:23:14 - INFO - __main__ -    correct = 354
+11/03/2023 13:23:14 - INFO - __main__ -    f1_0 = 0.8031854379977247
+11/03/2023 13:23:14 - INFO - __main__ -    f1_1 = 0.052631578947368425
+11/03/2023 13:23:14 - INFO - __main__ -    f1_2 = 0
+11/03/2023 13:23:14 - INFO - __main__ -    macro_f1 = 0.28527233898169774
+11/03/2023 13:23:14 - INFO - __main__ -    num = 527
+11/03/2023 13:23:14 - INFO - __main__ -    prec_0 = 0.6711026615969582
+11/03/2023 13:23:14 - INFO - __main__ -    prec_1 = 1.0
+11/03/2023 13:23:14 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 13:23:14 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 13:23:14 - INFO - __main__ -    rec_1 = 0.02702702702702703
+11/03/2023 13:23:14 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 13:23:14 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:23:14 - INFO - __main__ -   ***** Running evaluation 60 *****
+11/03/2023 13:23:14 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:23:14 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:23:17 - INFO - __main__ -   ***** Eval results 60 *****
+11/03/2023 13:23:17 - INFO - __main__ -    acc = 0.6840490797546013
+11/03/2023 13:23:17 - INFO - __main__ -    correct = 223
+11/03/2023 13:23:17 - INFO - __main__ -    f1_0 = 0.8123861566484518
+11/03/2023 13:23:17 - INFO - __main__ -    f1_1 = 0
+11/03/2023 13:23:17 - INFO - __main__ -    f1_2 = 0
+11/03/2023 13:23:17 - INFO - __main__ -    macro_f1 = 0.27079538554948396
+11/03/2023 13:23:17 - INFO - __main__ -    num = 326
+11/03/2023 13:23:17 - INFO - __main__ -    prec_0 = 0.6840490797546013
+11/03/2023 13:23:17 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 13:23:17 - INFO - __main__ -    prec_2 = 0.0
+11/03/2023 13:23:17 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 13:23:17 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 13:23:17 - INFO - __main__ -    rec_2 = 0.0
+11/03/2023 13:23:17 - INFO - __main__ -    Dev accuracy = 0.6840490797546013
+11/03/2023 13:23:58 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:23:58 - INFO - __main__ -   ***** Running evaluation checkpoint-80 *****
+11/03/2023 13:23:58 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:23:58 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:24:04 - INFO - __main__ -   ***** Eval results checkpoint-80 *****
+11/03/2023 13:24:04 - INFO - __main__ -    acc = 0.6774193548387096
+11/03/2023 13:24:04 - INFO - __main__ -    correct = 357
+11/03/2023 13:24:04 - INFO - __main__ -    f1_0 = 0.8059360730593608
+11/03/2023 13:24:04 - INFO - __main__ -    f1_1 = 0.052631578947368425
+11/03/2023 13:24:04 - INFO - __main__ -    f1_2 = 0.04285714285714286
+11/03/2023 13:24:04 - INFO - __main__ -    macro_f1 = 0.3004749316212907
+11/03/2023 13:24:04 - INFO - __main__ -    num = 527
+11/03/2023 13:24:04 - INFO - __main__ -    prec_0 = 0.6749521988527725
+11/03/2023 13:24:04 - INFO - __main__ -    prec_1 = 1.0
+11/03/2023 13:24:04 - INFO - __main__ -    prec_2 = 1.0
+11/03/2023 13:24:04 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 13:24:04 - INFO - __main__ -    rec_1 = 0.02702702702702703
+11/03/2023 13:24:04 - INFO - __main__ -    rec_2 = 0.021897810218978103
+11/03/2023 13:24:04 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:24:04 - INFO - __main__ -   ***** Running evaluation 80 *****
+11/03/2023 13:24:04 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:24:04 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:24:08 - INFO - __main__ -   ***** Eval results 80 *****
+11/03/2023 13:24:08 - INFO - __main__ -    acc = 0.6871165644171779
+11/03/2023 13:24:08 - INFO - __main__ -    correct = 224
+11/03/2023 13:24:08 - INFO - __main__ -    f1_0 = 0.8138686131386861
+11/03/2023 13:24:08 - INFO - __main__ -    f1_1 = 0
+11/03/2023 13:24:08 - INFO - __main__ -    f1_2 = 0.027027027027027025
+11/03/2023 13:24:08 - INFO - __main__ -    macro_f1 = 0.28029854672190435
+11/03/2023 13:24:08 - INFO - __main__ -    num = 326
+11/03/2023 13:24:08 - INFO - __main__ -    prec_0 = 0.6861538461538461
+11/03/2023 13:24:08 - INFO - __main__ -    prec_1 = 0.0
+11/03/2023 13:24:08 - INFO - __main__ -    prec_2 = 1.0
+11/03/2023 13:24:08 - INFO - __main__ -    rec_0 = 1.0
+11/03/2023 13:24:08 - INFO - __main__ -    rec_1 = 0.0
+11/03/2023 13:24:08 - INFO - __main__ -    rec_2 = 0.0136986301369863
+11/03/2023 13:24:08 - INFO - __main__ -    Dev accuracy = 0.6871165644171779
+11/03/2023 13:24:08 - INFO - __main__ -    result['acc']=0.6871165644171779 > best_score=0.6840490797546013
+11/03/2023 13:24:09 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:24:11 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:24:51 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:24:51 - INFO - __main__ -   ***** Running evaluation checkpoint-100 *****
+11/03/2023 13:24:51 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:24:51 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:24:57 - INFO - __main__ -   ***** Eval results checkpoint-100 *****
+11/03/2023 13:24:57 - INFO - __main__ -    acc = 0.7001897533206831
+11/03/2023 13:24:57 - INFO - __main__ -    correct = 369
+11/03/2023 13:24:57 - INFO - __main__ -    f1_0 = 0.8305084745762712
+11/03/2023 13:24:57 - INFO - __main__ -    f1_1 = 0.125
+11/03/2023 13:24:57 - INFO - __main__ -    f1_2 = 0.26829268292682923
+11/03/2023 13:24:57 - INFO - __main__ -    macro_f1 = 0.40793371916770016
+11/03/2023 13:24:57 - INFO - __main__ -    num = 527
+11/03/2023 13:24:57 - INFO - __main__ -    prec_0 = 0.7251585623678647
+11/03/2023 13:24:57 - INFO - __main__ -    prec_1 = 0.14814814814814814
+11/03/2023 13:24:57 - INFO - __main__ -    prec_2 = 0.8148148148148148
+11/03/2023 13:24:57 - INFO - __main__ -    rec_0 = 0.9716713881019831
+11/03/2023 13:24:57 - INFO - __main__ -    rec_1 = 0.10810810810810811
+11/03/2023 13:24:57 - INFO - __main__ -    rec_2 = 0.16058394160583941
+11/03/2023 13:24:57 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:24:57 - INFO - __main__ -   ***** Running evaluation 100 *****
+11/03/2023 13:24:57 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:24:57 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:25:01 - INFO - __main__ -   ***** Eval results 100 *****
+11/03/2023 13:25:01 - INFO - __main__ -    acc = 0.7055214723926381
+11/03/2023 13:25:01 - INFO - __main__ -    correct = 230
+11/03/2023 13:25:01 - INFO - __main__ -    f1_0 = 0.8326848249027237
+11/03/2023 13:25:01 - INFO - __main__ -    f1_1 = 0.13953488372093023
+11/03/2023 13:25:01 - INFO - __main__ -    f1_2 = 0.2736842105263158
+11/03/2023 13:25:01 - INFO - __main__ -    macro_f1 = 0.41530130638332324
+11/03/2023 13:25:01 - INFO - __main__ -    num = 326
+11/03/2023 13:25:01 - INFO - __main__ -    prec_0 = 0.7353951890034365
+11/03/2023 13:25:01 - INFO - __main__ -    prec_1 = 0.23076923076923078
+11/03/2023 13:25:01 - INFO - __main__ -    prec_2 = 0.5909090909090909
+11/03/2023 13:25:01 - INFO - __main__ -    rec_0 = 0.9596412556053812
+11/03/2023 13:25:01 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 13:25:01 - INFO - __main__ -    rec_2 = 0.1780821917808219
+11/03/2023 13:25:01 - INFO - __main__ -    Dev accuracy = 0.7055214723926381
+11/03/2023 13:25:01 - INFO - __main__ -    result['acc']=0.7055214723926381 > best_score=0.6871165644171779
+11/03/2023 13:25:02 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:25:05 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:25:44 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:25:44 - INFO - __main__ -   ***** Running evaluation checkpoint-120 *****
+11/03/2023 13:25:44 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:25:44 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:25:50 - INFO - __main__ -   ***** Eval results checkpoint-120 *****
+11/03/2023 13:25:50 - INFO - __main__ -    acc = 0.7286527514231499
+11/03/2023 13:25:50 - INFO - __main__ -    correct = 384
+11/03/2023 13:25:50 - INFO - __main__ -    f1_0 = 0.838235294117647
+11/03/2023 13:25:50 - INFO - __main__ -    f1_1 = 0.2105263157894737
+11/03/2023 13:25:50 - INFO - __main__ -    f1_2 = 0.39779005524861877
+11/03/2023 13:25:50 - INFO - __main__ -    macro_f1 = 0.48218388838524645
+11/03/2023 13:25:50 - INFO - __main__ -    num = 527
+11/03/2023 13:25:50 - INFO - __main__ -    prec_0 = 0.7386609071274298
+11/03/2023 13:25:50 - INFO - __main__ -    prec_1 = 0.3
+11/03/2023 13:25:50 - INFO - __main__ -    prec_2 = 0.8181818181818182
+11/03/2023 13:25:50 - INFO - __main__ -    rec_0 = 0.9688385269121813
+11/03/2023 13:25:50 - INFO - __main__ -    rec_1 = 0.16216216216216217
+11/03/2023 13:25:50 - INFO - __main__ -    rec_2 = 0.26277372262773724
+11/03/2023 13:25:50 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:25:50 - INFO - __main__ -   ***** Running evaluation 120 *****
+11/03/2023 13:25:50 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:25:50 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:25:54 - INFO - __main__ -   ***** Eval results 120 *****
+11/03/2023 13:25:54 - INFO - __main__ -    acc = 0.7239263803680982
+11/03/2023 13:25:54 - INFO - __main__ -    correct = 236
+11/03/2023 13:25:54 - INFO - __main__ -    f1_0 = 0.8452380952380952
+11/03/2023 13:25:54 - INFO - __main__ -    f1_1 = 0.18181818181818182
+11/03/2023 13:25:54 - INFO - __main__ -    f1_2 = 0.36538461538461536
+11/03/2023 13:25:54 - INFO - __main__ -    macro_f1 = 0.46414696414696416
+11/03/2023 13:25:54 - INFO - __main__ -    num = 326
+11/03/2023 13:25:54 - INFO - __main__ -    prec_0 = 0.7580071174377224
+11/03/2023 13:25:54 - INFO - __main__ -    prec_1 = 0.2857142857142857
+11/03/2023 13:25:54 - INFO - __main__ -    prec_2 = 0.6129032258064516
+11/03/2023 13:25:54 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 13:25:54 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 13:25:54 - INFO - __main__ -    rec_2 = 0.2602739726027397
+11/03/2023 13:25:54 - INFO - __main__ -    Dev accuracy = 0.7239263803680982
+11/03/2023 13:25:54 - INFO - __main__ -    result['acc']=0.7239263803680982 > best_score=0.7055214723926381
+11/03/2023 13:25:56 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:25:58 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:26:38 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:26:38 - INFO - __main__ -   ***** Running evaluation checkpoint-140 *****
+11/03/2023 13:26:38 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:26:38 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:26:44 - INFO - __main__ -   ***** Eval results checkpoint-140 *****
+11/03/2023 13:26:44 - INFO - __main__ -    acc = 0.7058823529411765
+11/03/2023 13:26:44 - INFO - __main__ -    correct = 372
+11/03/2023 13:26:44 - INFO - __main__ -    f1_0 = 0.83248730964467
+11/03/2023 13:26:44 - INFO - __main__ -    f1_1 = 0.25
+11/03/2023 13:26:44 - INFO - __main__ -    f1_2 = 0.3655913978494624
+11/03/2023 13:26:44 - INFO - __main__ -    macro_f1 = 0.48269290249804414
+11/03/2023 13:26:44 - INFO - __main__ -    num = 527
+11/03/2023 13:26:44 - INFO - __main__ -    prec_0 = 0.7540229885057471
+11/03/2023 13:26:44 - INFO - __main__ -    prec_1 = 0.23255813953488372
+11/03/2023 13:26:44 - INFO - __main__ -    prec_2 = 0.6938775510204082
+11/03/2023 13:26:44 - INFO - __main__ -    rec_0 = 0.9291784702549575
+11/03/2023 13:26:44 - INFO - __main__ -    rec_1 = 0.2702702702702703
+11/03/2023 13:26:44 - INFO - __main__ -    rec_2 = 0.24817518248175183
+11/03/2023 13:26:44 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:26:44 - INFO - __main__ -   ***** Running evaluation 140 *****
+11/03/2023 13:26:44 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:26:44 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:26:48 - INFO - __main__ -   ***** Eval results 140 *****
+11/03/2023 13:26:48 - INFO - __main__ -    acc = 0.7331288343558282
+11/03/2023 13:26:48 - INFO - __main__ -    correct = 239
+11/03/2023 13:26:48 - INFO - __main__ -    f1_0 = 0.8612244897959184
+11/03/2023 13:26:48 - INFO - __main__ -    f1_1 = 0.22641509433962265
+11/03/2023 13:26:48 - INFO - __main__ -    f1_2 = 0.4036697247706422
+11/03/2023 13:26:48 - INFO - __main__ -    macro_f1 = 0.4971031029687278
+11/03/2023 13:26:48 - INFO - __main__ -    num = 326
+11/03/2023 13:26:48 - INFO - __main__ -    prec_0 = 0.7902621722846442
+11/03/2023 13:26:48 - INFO - __main__ -    prec_1 = 0.2608695652173913
+11/03/2023 13:26:48 - INFO - __main__ -    prec_2 = 0.6111111111111112
+11/03/2023 13:26:48 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 13:26:48 - INFO - __main__ -    rec_1 = 0.2
+11/03/2023 13:26:48 - INFO - __main__ -    rec_2 = 0.3013698630136986
+11/03/2023 13:26:48 - INFO - __main__ -    Dev accuracy = 0.7331288343558282
+11/03/2023 13:26:48 - INFO - __main__ -    result['acc']=0.7331288343558282 > best_score=0.7239263803680982
+11/03/2023 13:26:49 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:26:51 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:27:32 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:27:32 - INFO - __main__ -   ***** Running evaluation checkpoint-160 *****
+11/03/2023 13:27:32 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:27:32 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:27:38 - INFO - __main__ -   ***** Eval results checkpoint-160 *****
+11/03/2023 13:27:38 - INFO - __main__ -    acc = 0.715370018975332
+11/03/2023 13:27:38 - INFO - __main__ -    correct = 377
+11/03/2023 13:27:38 - INFO - __main__ -    f1_0 = 0.8308823529411764
+11/03/2023 13:27:38 - INFO - __main__ -    f1_1 = 0.11320754716981132
+11/03/2023 13:27:38 - INFO - __main__ -    f1_2 = 0.3783783783783784
+11/03/2023 13:27:38 - INFO - __main__ -    macro_f1 = 0.44082275949645533
+11/03/2023 13:27:38 - INFO - __main__ -    num = 527
+11/03/2023 13:27:38 - INFO - __main__ -    prec_0 = 0.7321814254859611
+11/03/2023 13:27:38 - INFO - __main__ -    prec_1 = 0.1875
+11/03/2023 13:27:38 - INFO - __main__ -    prec_2 = 0.7291666666666666
+11/03/2023 13:27:38 - INFO - __main__ -    rec_0 = 0.9603399433427762
+11/03/2023 13:27:38 - INFO - __main__ -    rec_1 = 0.08108108108108109
+11/03/2023 13:27:38 - INFO - __main__ -    rec_2 = 0.25547445255474455
+11/03/2023 13:27:38 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:27:38 - INFO - __main__ -   ***** Running evaluation 160 *****
+11/03/2023 13:27:38 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:27:38 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:27:42 - INFO - __main__ -   ***** Eval results 160 *****
+11/03/2023 13:27:42 - INFO - __main__ -    acc = 0.7361963190184049
+11/03/2023 13:27:42 - INFO - __main__ -    correct = 240
+11/03/2023 13:27:42 - INFO - __main__ -    f1_0 = 0.8473895582329316
+11/03/2023 13:27:42 - INFO - __main__ -    f1_1 = 0.15
+11/03/2023 13:27:42 - INFO - __main__ -    f1_2 = 0.45614035087719296
+11/03/2023 13:27:42 - INFO - __main__ -    macro_f1 = 0.48450996970337484
+11/03/2023 13:27:42 - INFO - __main__ -    num = 326
+11/03/2023 13:27:42 - INFO - __main__ -    prec_0 = 0.7672727272727272
+11/03/2023 13:27:42 - INFO - __main__ -    prec_1 = 0.3
+11/03/2023 13:27:42 - INFO - __main__ -    prec_2 = 0.6341463414634146
+11/03/2023 13:27:42 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 13:27:42 - INFO - __main__ -    rec_1 = 0.1
+11/03/2023 13:27:42 - INFO - __main__ -    rec_2 = 0.3561643835616438
+11/03/2023 13:27:42 - INFO - __main__ -    Dev accuracy = 0.7361963190184049
+11/03/2023 13:27:42 - INFO - __main__ -    result['acc']=0.7361963190184049 > best_score=0.7331288343558282
+11/03/2023 13:27:43 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:27:45 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:28:25 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:28:25 - INFO - __main__ -   ***** Running evaluation checkpoint-180 *****
+11/03/2023 13:28:25 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:28:25 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:28:31 - INFO - __main__ -   ***** Eval results checkpoint-180 *****
+11/03/2023 13:28:31 - INFO - __main__ -    acc = 0.713472485768501
+11/03/2023 13:28:31 - INFO - __main__ -    correct = 376
+11/03/2023 13:28:31 - INFO - __main__ -    f1_0 = 0.8331303288672349
+11/03/2023 13:28:31 - INFO - __main__ -    f1_1 = 0.16666666666666666
+11/03/2023 13:28:31 - INFO - __main__ -    f1_2 = 0.33526011560693636
+11/03/2023 13:28:31 - INFO - __main__ -    macro_f1 = 0.44501903704694595
+11/03/2023 13:28:31 - INFO - __main__ -    num = 527
+11/03/2023 13:28:31 - INFO - __main__ -    prec_0 = 0.7307692307692307
+11/03/2023 13:28:31 - INFO - __main__ -    prec_1 = 0.21739130434782608
+11/03/2023 13:28:31 - INFO - __main__ -    prec_2 = 0.8055555555555556
+11/03/2023 13:28:31 - INFO - __main__ -    rec_0 = 0.9688385269121813
+11/03/2023 13:28:31 - INFO - __main__ -    rec_1 = 0.13513513513513514
+11/03/2023 13:28:31 - INFO - __main__ -    rec_2 = 0.2116788321167883
+11/03/2023 13:28:31 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:28:31 - INFO - __main__ -   ***** Running evaluation 180 *****
+11/03/2023 13:28:31 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:28:31 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:28:35 - INFO - __main__ -   ***** Eval results 180 *****
+11/03/2023 13:28:35 - INFO - __main__ -    acc = 0.7269938650306749
+11/03/2023 13:28:35 - INFO - __main__ -    correct = 237
+11/03/2023 13:28:35 - INFO - __main__ -    f1_0 = 0.8452380952380952
+11/03/2023 13:28:35 - INFO - __main__ -    f1_1 = 0.19047619047619044
+11/03/2023 13:28:35 - INFO - __main__ -    f1_2 = 0.3773584905660377
+11/03/2023 13:28:35 - INFO - __main__ -    macro_f1 = 0.47102425876010773
+11/03/2023 13:28:35 - INFO - __main__ -    num = 326
+11/03/2023 13:28:35 - INFO - __main__ -    prec_0 = 0.7580071174377224
+11/03/2023 13:28:35 - INFO - __main__ -    prec_1 = 0.3333333333333333
+11/03/2023 13:28:35 - INFO - __main__ -    prec_2 = 0.6060606060606061
+11/03/2023 13:28:35 - INFO - __main__ -    rec_0 = 0.9551569506726457
+11/03/2023 13:28:35 - INFO - __main__ -    rec_1 = 0.13333333333333333
+11/03/2023 13:28:35 - INFO - __main__ -    rec_2 = 0.273972602739726
+11/03/2023 13:28:35 - INFO - __main__ -    Dev accuracy = 0.7269938650306749
+11/03/2023 13:29:15 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:29:15 - INFO - __main__ -   ***** Running evaluation checkpoint-200 *****
+11/03/2023 13:29:15 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:29:15 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:29:21 - INFO - __main__ -   ***** Eval results checkpoint-200 *****
+11/03/2023 13:29:21 - INFO - __main__ -    acc = 0.7115749525616698
+11/03/2023 13:29:21 - INFO - __main__ -    correct = 375
+11/03/2023 13:29:21 - INFO - __main__ -    f1_0 = 0.8385481852315393
+11/03/2023 13:29:21 - INFO - __main__ -    f1_1 = 0.2564102564102564
+11/03/2023 13:29:21 - INFO - __main__ -    f1_2 = 0.33898305084745767
+11/03/2023 13:29:21 - INFO - __main__ -    macro_f1 = 0.47798049749641774
+11/03/2023 13:29:21 - INFO - __main__ -    num = 527
+11/03/2023 13:29:21 - INFO - __main__ -    prec_0 = 0.7511210762331838
+11/03/2023 13:29:21 - INFO - __main__ -    prec_1 = 0.24390243902439024
+11/03/2023 13:29:21 - INFO - __main__ -    prec_2 = 0.75
+11/03/2023 13:29:21 - INFO - __main__ -    rec_0 = 0.9490084985835694
+11/03/2023 13:29:21 - INFO - __main__ -    rec_1 = 0.2702702702702703
+11/03/2023 13:29:21 - INFO - __main__ -    rec_2 = 0.21897810218978103
+11/03/2023 13:29:21 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:29:21 - INFO - __main__ -   ***** Running evaluation 200 *****
+11/03/2023 13:29:21 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:29:21 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:29:25 - INFO - __main__ -   ***** Eval results 200 *****
+11/03/2023 13:29:25 - INFO - __main__ -    acc = 0.7239263803680982
+11/03/2023 13:29:25 - INFO - __main__ -    correct = 236
+11/03/2023 13:29:25 - INFO - __main__ -    f1_0 = 0.8525252525252526
+11/03/2023 13:29:25 - INFO - __main__ -    f1_1 = 0.2
+11/03/2023 13:29:25 - INFO - __main__ -    f1_2 = 0.37383177570093457
+11/03/2023 13:29:25 - INFO - __main__ -    macro_f1 = 0.47545234274206244
+11/03/2023 13:29:25 - INFO - __main__ -    num = 326
+11/03/2023 13:29:25 - INFO - __main__ -    prec_0 = 0.7757352941176471
+11/03/2023 13:29:25 - INFO - __main__ -    prec_1 = 0.25
+11/03/2023 13:29:25 - INFO - __main__ -    prec_2 = 0.5882352941176471
+11/03/2023 13:29:25 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 13:29:25 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 13:29:25 - INFO - __main__ -    rec_2 = 0.273972602739726
+11/03/2023 13:29:25 - INFO - __main__ -    Dev accuracy = 0.7239263803680982
+11/03/2023 13:30:04 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:30:04 - INFO - __main__ -   ***** Running evaluation checkpoint-220 *****
+11/03/2023 13:30:04 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:30:04 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:30:10 - INFO - __main__ -   ***** Eval results checkpoint-220 *****
+11/03/2023 13:30:10 - INFO - __main__ -    acc = 0.6963946869070209
+11/03/2023 13:30:10 - INFO - __main__ -    correct = 367
+11/03/2023 13:30:10 - INFO - __main__ -    f1_0 = 0.8363636363636363
+11/03/2023 13:30:10 - INFO - __main__ -    f1_1 = 0.2653061224489796
+11/03/2023 13:30:10 - INFO - __main__ -    f1_2 = 0.3440860215053763
+11/03/2023 13:30:10 - INFO - __main__ -    macro_f1 = 0.4819185934393307
+11/03/2023 13:30:10 - INFO - __main__ -    num = 527
+11/03/2023 13:30:10 - INFO - __main__ -    prec_0 = 0.7721822541966427
+11/03/2023 13:30:10 - INFO - __main__ -    prec_1 = 0.21311475409836064
+11/03/2023 13:30:10 - INFO - __main__ -    prec_2 = 0.6530612244897959
+11/03/2023 13:30:10 - INFO - __main__ -    rec_0 = 0.9121813031161473
+11/03/2023 13:30:10 - INFO - __main__ -    rec_1 = 0.35135135135135137
+11/03/2023 13:30:10 - INFO - __main__ -    rec_2 = 0.23357664233576642
+11/03/2023 13:30:10 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:30:10 - INFO - __main__ -   ***** Running evaluation 220 *****
+11/03/2023 13:30:10 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:30:10 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:30:14 - INFO - __main__ -   ***** Eval results 220 *****
+11/03/2023 13:30:14 - INFO - __main__ -    acc = 0.745398773006135
+11/03/2023 13:30:14 - INFO - __main__ -    correct = 243
+11/03/2023 13:30:14 - INFO - __main__ -    f1_0 = 0.8636363636363638
+11/03/2023 13:30:14 - INFO - __main__ -    f1_1 = 0.30188679245283023
+11/03/2023 13:30:14 - INFO - __main__ -    f1_2 = 0.45217391304347826
+11/03/2023 13:30:14 - INFO - __main__ -    macro_f1 = 0.5392323563775574
+11/03/2023 13:30:14 - INFO - __main__ -    num = 326
+11/03/2023 13:30:14 - INFO - __main__ -    prec_0 = 0.8007662835249042
+11/03/2023 13:30:14 - INFO - __main__ -    prec_1 = 0.34782608695652173
+11/03/2023 13:30:14 - INFO - __main__ -    prec_2 = 0.6190476190476191
+11/03/2023 13:30:14 - INFO - __main__ -    rec_0 = 0.9372197309417041
+11/03/2023 13:30:14 - INFO - __main__ -    rec_1 = 0.26666666666666666
+11/03/2023 13:30:14 - INFO - __main__ -    rec_2 = 0.3561643835616438
+11/03/2023 13:30:14 - INFO - __main__ -    Dev accuracy = 0.745398773006135
+11/03/2023 13:30:14 - INFO - __main__ -    result['acc']=0.745398773006135 > best_score=0.7361963190184049
+11/03/2023 13:30:15 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:30:18 - INFO - __main__ -   Saving optimizer and scheduler states to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best
+11/03/2023 13:30:58 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:30:58 - INFO - __main__ -   ***** Running evaluation checkpoint-240 *****
+11/03/2023 13:30:58 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:30:58 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:31:04 - INFO - __main__ -   ***** Eval results checkpoint-240 *****
+11/03/2023 13:31:04 - INFO - __main__ -    acc = 0.715370018975332
+11/03/2023 13:31:04 - INFO - __main__ -    correct = 377
+11/03/2023 13:31:04 - INFO - __main__ -    f1_0 = 0.8387096774193549
+11/03/2023 13:31:04 - INFO - __main__ -    f1_1 = 0.2894736842105264
+11/03/2023 13:31:04 - INFO - __main__ -    f1_2 = 0.3255813953488372
+11/03/2023 13:31:04 - INFO - __main__ -    macro_f1 = 0.4845882523262395
+11/03/2023 13:31:04 - INFO - __main__ -    num = 527
+11/03/2023 13:31:04 - INFO - __main__ -    prec_0 = 0.7461368653421634
+11/03/2023 13:31:04 - INFO - __main__ -    prec_1 = 0.28205128205128205
+11/03/2023 13:31:04 - INFO - __main__ -    prec_2 = 0.8
+11/03/2023 13:31:04 - INFO - __main__ -    rec_0 = 0.9575070821529745
+11/03/2023 13:31:04 - INFO - __main__ -    rec_1 = 0.2972972972972973
+11/03/2023 13:31:04 - INFO - __main__ -    rec_2 = 0.20437956204379562
+11/03/2023 13:31:04 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:31:04 - INFO - __main__ -   ***** Running evaluation 240 *****
+11/03/2023 13:31:04 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:31:04 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:31:08 - INFO - __main__ -   ***** Eval results 240 *****
+11/03/2023 13:31:08 - INFO - __main__ -    acc = 0.7177914110429447
+11/03/2023 13:31:08 - INFO - __main__ -    correct = 234
+11/03/2023 13:31:08 - INFO - __main__ -    f1_0 = 0.8473895582329316
+11/03/2023 13:31:08 - INFO - __main__ -    f1_1 = 0.19607843137254902
+11/03/2023 13:31:08 - INFO - __main__ -    f1_2 = 0.3495145631067961
+11/03/2023 13:31:08 - INFO - __main__ -    macro_f1 = 0.4643275175707589
+11/03/2023 13:31:08 - INFO - __main__ -    num = 326
+11/03/2023 13:31:08 - INFO - __main__ -    prec_0 = 0.7672727272727272
+11/03/2023 13:31:08 - INFO - __main__ -    prec_1 = 0.23809523809523808
+11/03/2023 13:31:08 - INFO - __main__ -    prec_2 = 0.6
+11/03/2023 13:31:08 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 13:31:08 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 13:31:08 - INFO - __main__ -    rec_2 = 0.2465753424657534
+11/03/2023 13:31:08 - INFO - __main__ -    Dev accuracy = 0.7177914110429447
+11/03/2023 13:31:48 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:31:48 - INFO - __main__ -   ***** Running evaluation checkpoint-260 *****
+11/03/2023 13:31:48 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:31:48 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:31:54 - INFO - __main__ -   ***** Eval results checkpoint-260 *****
+11/03/2023 13:31:54 - INFO - __main__ -    acc = 0.715370018975332
+11/03/2023 13:31:54 - INFO - __main__ -    correct = 377
+11/03/2023 13:31:54 - INFO - __main__ -    f1_0 = 0.8411910669975187
+11/03/2023 13:31:54 - INFO - __main__ -    f1_1 = 0.28571428571428575
+11/03/2023 13:31:54 - INFO - __main__ -    f1_2 = 0.31578947368421056
+11/03/2023 13:31:54 - INFO - __main__ -    macro_f1 = 0.48089827546533837
+11/03/2023 13:31:54 - INFO - __main__ -    num = 527
+11/03/2023 13:31:54 - INFO - __main__ -    prec_0 = 0.7483443708609272
+11/03/2023 13:31:54 - INFO - __main__ -    prec_1 = 0.275
+11/03/2023 13:31:54 - INFO - __main__ -    prec_2 = 0.7941176470588235
+11/03/2023 13:31:54 - INFO - __main__ -    rec_0 = 0.9603399433427762
+11/03/2023 13:31:54 - INFO - __main__ -    rec_1 = 0.2972972972972973
+11/03/2023 13:31:54 - INFO - __main__ -    rec_2 = 0.19708029197080293
+11/03/2023 13:31:54 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:31:54 - INFO - __main__ -   ***** Running evaluation 260 *****
+11/03/2023 13:31:54 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:31:54 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:31:58 - INFO - __main__ -   ***** Eval results 260 *****
+11/03/2023 13:31:58 - INFO - __main__ -    acc = 0.7024539877300614
+11/03/2023 13:31:58 - INFO - __main__ -    correct = 229
+11/03/2023 13:31:58 - INFO - __main__ -    f1_0 = 0.8473895582329316
+11/03/2023 13:31:58 - INFO - __main__ -    f1_1 = 0.17241379310344826
+11/03/2023 13:31:58 - INFO - __main__ -    f1_2 = 0.2708333333333333
+11/03/2023 13:31:58 - INFO - __main__ -    macro_f1 = 0.4302122282232377
+11/03/2023 13:31:58 - INFO - __main__ -    num = 326
+11/03/2023 13:31:58 - INFO - __main__ -    prec_0 = 0.7672727272727272
+11/03/2023 13:31:58 - INFO - __main__ -    prec_1 = 0.17857142857142858
+11/03/2023 13:31:58 - INFO - __main__ -    prec_2 = 0.5652173913043478
+11/03/2023 13:31:58 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 13:31:58 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 13:31:58 - INFO - __main__ -    rec_2 = 0.1780821917808219
+11/03/2023 13:31:58 - INFO - __main__ -    Dev accuracy = 0.7024539877300614
+11/03/2023 13:32:17 - INFO - __main__ -    global_step = 270, average loss = 0.6434159967082518
+11/03/2023 13:32:17 - INFO - __main__ -    best checkpoint = ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//checkpoint-best, best score = 0.745398773006135
+11/03/2023 13:32:17 - INFO - __main__ -   Saving model checkpoint to ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256//
+11/03/2023 13:32:21 - INFO - __main__ -   Evaluate the following checkpoints: ['./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256/checkpoint-best', './outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256']
+11/03/2023 13:32:23 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:32:23 - INFO - __main__ -   ***** Running evaluation checkpoint-best *****
+11/03/2023 13:32:23 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:32:23 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:32:27 - INFO - __main__ -   ***** Eval results checkpoint-best *****
+11/03/2023 13:32:27 - INFO - __main__ -    acc = 0.745398773006135
+11/03/2023 13:32:27 - INFO - __main__ -    correct = 243
+11/03/2023 13:32:27 - INFO - __main__ -    f1_0 = 0.8636363636363638
+11/03/2023 13:32:27 - INFO - __main__ -    f1_1 = 0.30188679245283023
+11/03/2023 13:32:27 - INFO - __main__ -    f1_2 = 0.45217391304347826
+11/03/2023 13:32:27 - INFO - __main__ -    macro_f1 = 0.5392323563775574
+11/03/2023 13:32:27 - INFO - __main__ -    num = 326
+11/03/2023 13:32:27 - INFO - __main__ -    prec_0 = 0.8007662835249042
+11/03/2023 13:32:27 - INFO - __main__ -    prec_1 = 0.34782608695652173
+11/03/2023 13:32:27 - INFO - __main__ -    prec_2 = 0.6190476190476191
+11/03/2023 13:32:27 - INFO - __main__ -    rec_0 = 0.9372197309417041
+11/03/2023 13:32:27 - INFO - __main__ -    rec_1 = 0.26666666666666666
+11/03/2023 13:32:27 - INFO - __main__ -    rec_2 = 0.3561643835616438
+11/03/2023 13:32:29 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_dev_roberta-large_256_comp_
+11/03/2023 13:32:29 - INFO - __main__ -   ***** Running evaluation  *****
+11/03/2023 13:32:29 - INFO - __main__ -     Num examples = 326
+11/03/2023 13:32:29 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:32:33 - INFO - __main__ -   ***** Eval results  *****
+11/03/2023 13:32:33 - INFO - __main__ -    acc = 0.7147239263803681
+11/03/2023 13:32:33 - INFO - __main__ -    correct = 233
+11/03/2023 13:32:33 - INFO - __main__ -    f1_0 = 0.8473895582329316
+11/03/2023 13:32:33 - INFO - __main__ -    f1_1 = 0.1851851851851852
+11/03/2023 13:32:33 - INFO - __main__ -    f1_2 = 0.34
+11/03/2023 13:32:33 - INFO - __main__ -    macro_f1 = 0.4575249144727056
+11/03/2023 13:32:33 - INFO - __main__ -    num = 326
+11/03/2023 13:32:33 - INFO - __main__ -    prec_0 = 0.7672727272727272
+11/03/2023 13:32:33 - INFO - __main__ -    prec_1 = 0.20833333333333334
+11/03/2023 13:32:33 - INFO - __main__ -    prec_2 = 0.6296296296296297
+11/03/2023 13:32:33 - INFO - __main__ -    rec_0 = 0.9461883408071748
+11/03/2023 13:32:33 - INFO - __main__ -    rec_1 = 0.16666666666666666
+11/03/2023 13:32:33 - INFO - __main__ -    rec_2 = 0.2328767123287671
+11/03/2023 13:32:33 - INFO - __main__ -   Best checkpoint is ./outputs/oversample/comp/roberta-large-LR1e-5-epoch10-MaxLen256/checkpoint-best, best accuracy is 0.745398773006135
+11/03/2023 13:32:35 - INFO - __main__ -   Loading features from cached file ./data/oversample//comp/cached_test_roberta-large_256_comp_
+11/03/2023 13:32:35 - INFO - __main__ -   ***** Running evaluation best_checkpoint *****
+11/03/2023 13:32:35 - INFO - __main__ -     Num examples = 527
+11/03/2023 13:32:35 - INFO - __main__ -     Batch size = 8
+11/03/2023 13:32:41 - INFO - __main__ -   ***** Save prediction ******
+11/03/2023 13:32:41 - INFO - __main__ -   ***** Eval results best_checkpoint *****
+11/03/2023 13:32:41 - INFO - __main__ -    acc = 0.6963946869070209
+11/03/2023 13:32:41 - INFO - __main__ -    correct = 367
+11/03/2023 13:32:41 - INFO - __main__ -    f1_0 = 0.8363636363636363
+11/03/2023 13:32:41 - INFO - __main__ -    f1_1 = 0.2653061224489796
+11/03/2023 13:32:41 - INFO - __main__ -    f1_2 = 0.3440860215053763
+11/03/2023 13:32:41 - INFO - __main__ -    macro_f1 = 0.4819185934393307
+11/03/2023 13:32:41 - INFO - __main__ -    num = 527
+11/03/2023 13:32:41 - INFO - __main__ -    prec_0 = 0.7721822541966427
+11/03/2023 13:32:41 - INFO - __main__ -    prec_1 = 0.21311475409836064
+11/03/2023 13:32:41 - INFO - __main__ -    prec_2 = 0.6530612244897959
+11/03/2023 13:32:41 - INFO - __main__ -    rec_0 = 0.9121813031161473
+11/03/2023 13:32:41 - INFO - __main__ -    rec_1 = 0.35135135135135137
+11/03/2023 13:32:41 - INFO - __main__ -    rec_2 = 0.23357664233576642
+11/03/2023 13:32:41 - INFO - __main__ -   0.6963946869070209