MTDNN_LMHE5_16_ALL.log

01/07/2021 05:16:12 1
01/07/2021 05:16:12 Launching the MT-DNN training
01/07/2021 05:16:12 Loading data/canonical_data/bert_base_uncased_lower/mnli_train.json as task 0
01/07/2021 05:18:35 Loading data/canonical_data/bert_base_uncased_lower/rte_train.json as task 1
01/07/2021 05:18:35 Loading data/canonical_data/bert_base_uncased_lower/qqp_train.json as task 2
01/07/2021 05:20:37 Loading data/canonical_data/bert_base_uncased_lower/qnli_train.json as task 3
01/07/2021 05:20:50 Loading data/canonical_data/bert_base_uncased_lower/mrpc_train.json as task 4
01/07/2021 05:20:50 Loading data/canonical_data/bert_base_uncased_lower/sst_train.json as task 5
01/07/2021 05:20:54 Loading data/canonical_data/bert_base_uncased_lower/cola_train.json as task 6
01/07/2021 05:20:55 Loading data/canonical_data/bert_base_uncased_lower/stsb_train.json as task 7
01/07/2021 05:21:05 ####################
01/07/2021 05:21:05 {'log_file': 'checkpoints/2021-01-07T1716_GPT_LM_entropy_MTDNN_5%/log.log', 'tensorboard': False, 'tensorboard_logdir': 'tensorboard_logdir', 'init_checkpoint': 'bert-base-uncased', 'data_dir': 'data/canonical_data/bert_base_uncased_lower', 'data_sort_on': False, 'name': 'farmer', 'task_def': 'experiments/glue/glue_task_def.yml', 'train_datasets': ['mnli', 'rte', 'qqp', 'qnli', 'mrpc', 'sst', 'cola', 'stsb'], 'test_datasets': ['mnli_matched', 'mnli_mismatched', 'rte', 'qqp', 'qnli', 'mrpc', 'sst', 'cola', 'stsb'], 'glue_format_on': False, 'mkd_opt': 0, 'do_padding': False, 'update_bert_opt': 0, 'multi_gpu_on': True, 'mem_cum_type': 'simple', 'answer_num_turn': 5, 'answer_mem_drop_p': 0.1, 'answer_att_hidden_size': 128, 'answer_att_type': 'bilinear', 'answer_rnn_type': 'gru', 'answer_sum_att_type': 'bilinear', 'answer_merge_opt': 1, 'answer_mem_type': 1, 'max_answer_len': 10, 'answer_dropout_p': 0.1, 'answer_weight_norm_on': False, 'dump_state_on': False, 'answer_opt': 1, 'mtl_opt': 0, 'ratio': 0, 'mix_opt': 0, 'max_seq_len': 512, 'init_ratio': 1, 'encoder_type': <EncoderModelType.BERT: 1>, 'num_hidden_layers': -1, 'bert_model_type': 'bert-base-uncased', 'do_lower_case': False, 'masked_lm_prob': 0.15, 'short_seq_prob': 0.2, 'max_predictions_per_seq': 128, 'bin_on': False, 'bin_size': 64, 'bin_grow_ratio': 0.5, 'cuda': True, 'log_per_updates': 500, 'save_per_updates': 10000, 'save_per_updates_on': False, 'epochs': 20, 'batch_size': 16, 'batch_size_eval': 8, 'optimizer': 'adamax', 'grad_clipping': 0.0, 'global_grad_clipping': 1.0, 'weight_decay': 0, 'learning_rate': 5e-05, 'momentum': 0, 'warmup': 0.1, 'warmup_schedule': 'warmup_linear', 'adam_eps': 1e-06, 'vb_dropout': True, 'dropout_p': 0.1, 'dropout_w': 0.0, 'bert_dropout_p': 0.1, 'model_ckpt': 'checkpoints/model_0.pt', 'resume': False, 'have_lr_scheduler': True, 'multi_step_lr': '10,20,30', 'lr_gamma': 0.5, 'scheduler_type': 'ms', 'output_dir': 'checkpoints/2021-01-07T1716_GPT_LM_entropy_MTDNN_5%', 'seed': 2018, 'grad_accumulation_step': 1, 'fp16': False, 'fp16_opt_level': 'O1', 'adv_train': False, 'adv_opt': 0, 'adv_norm_level': 0, 'adv_p_norm': 'inf', 'adv_alpha': 1, 'adv_k': 1, 'adv_step_size': 0.001, 'adv_noise_var': 1e-05, 'adv_epsilon': 1e-06, 'loss_pred': True, 'collect_uncertainty': None, 'collect_topk': 0.1, 'load_ranked_data': 'GPT_LM_entropy_rank_0.05.pkl', 'mc_dropout': 0, 'finetune': False, 'encode_mode': False, 'task_def_list': [{'self': '{}', 'label_vocab': '<data_utils.vocab.Vocabulary object at 0x7fd227c053a0>', 'n_class': '3', 'data_type': '<DataFormat.PremiseAndOneHypothesis: 2>', 'task_type': '<TaskType.Classification: 1>', 'metric_meta': '(<Metric.ACC: 0>,)', 'split_names': "['train', 'matched_dev', 'mismatched_dev', 'matched_test', 'mismatched_test']", 'enable_san': 'False', 'dropout_p': '0.1', 'loss': '<LossCriterion.CeCriterion: 0>', 'kd_loss': '<LossCriterion.MseCriterion: 1>', 'adv_loss': '<LossCriterion.SymKlCriterion: 7>', '__class__': "<class 'experiments.exp_def.TaskDef'>"}, {'self': '{}', 'label_vocab': '<data_utils.vocab.Vocabulary object at 0x7fd227c05d30>', 'n_class': '2', 'data_type': '<DataFormat.PremiseAndOneHypothesis: 2>', 'task_type': '<TaskType.Classification: 1>', 'metric_meta': '(<Metric.ACC: 0>,)', 'split_names': "['train', 'dev', 'test']", 'enable_san': 'False', 'dropout_p': 'None', 'loss': '<LossCriterion.CeCriterion: 0>', 'kd_loss': '<LossCriterion.MseCriterion: 1>', 'adv_loss': '<LossCriterion.SymKlCriterion: 7>', '__class__': "<class 'experiments.exp_def.TaskDef'>"}, {'self': '{}', 'label_vocab': 'None', 'n_class': '2', 'data_type': '<DataFormat.PremiseAndOneHypothesis: 2>', 'task_type': '<TaskType.Classification: 1>', 'metric_meta': '(<Metric.ACC: 0>, <Metric.F1: 1>)', 'split_names': "['train', 'dev', 'test']", 'enable_san': 'False', 'dropout_p': 'None', 'loss': '<LossCriterion.CeCriterion: 0>', 'kd_loss': '<LossCriterion.MseCriterion: 1>', 'adv_loss': '<LossCriterion.SymKlCriterion: 7>', '__class__': "<class 'experiments.exp_def.TaskDef'>"}, {'self': '{}', 'label_vocab': '<data_utils.vocab.Vocabulary object at 0x7fd227c05eb0>', 'n_class': '2', 'data_type': '<DataFormat.PremiseAndOneHypothesis: 2>', 'task_type': '<TaskType.Classification: 1>', 'metric_meta': '(<Metric.ACC: 0>,)', 'split_names': "['train', 'dev', 'test']", 'enable_san': 'False', 'dropout_p': 'None', 'loss': '<LossCriterion.CeCriterion: 0>', 'kd_loss': '<LossCriterion.MseCriterion: 1>', 'adv_loss': '<LossCriterion.SymKlCriterion: 7>', '__class__': "<class 'experiments.exp_def.TaskDef'>"}, {'self': '{}', 'label_vocab': 'None', 'n_class': '2', 'data_type': '<DataFormat.PremiseAndOneHypothesis: 2>', 'task_type': '<TaskType.Classification: 1>', 'metric_meta': '(<Metric.ACC: 0>, <Metric.F1: 1>)', 'split_names': "['train', 'dev', 'test']", 'enable_san': 'False', 'dropout_p': 'None', 'loss': '<LossCriterion.CeCriterion: 0>', 'kd_loss': '<LossCriterion.MseCriterion: 1>', 'adv_loss': '<LossCriterion.SymKlCriterion: 7>', '__class__': "<class 'experiments.exp_def.TaskDef'>"}, {'self': '{}', 'label_vocab': 'None', 'n_class': '2', 'data_type': '<DataFormat.PremiseOnly: 1>', 'task_type': '<TaskType.Classification: 1>', 'metric_meta': '(<Metric.ACC: 0>,)', 'split_names': "['train', 'dev', 'test']", 'enable_san': 'False', 'dropout_p': 'None', 'loss': '<LossCriterion.CeCriterion: 0>', 'kd_loss': '<LossCriterion.MseCriterion: 1>', 'adv_loss': '<LossCriterion.SymKlCriterion: 7>', '__class__': "<class 'experiments.exp_def.TaskDef'>"}, {'self': '{}', 'label_vocab': 'None', 'n_class': '2', 'data_type': '<DataFormat.PremiseOnly: 1>', 'task_type': '<TaskType.Classification: 1>', 'metric_meta': '(<Metric.ACC: 0>, <Metric.MCC: 2>)', 'split_names': "['train', 'dev', 'test']", 'enable_san': 'False', 'dropout_p': '0.05', 'loss': '<LossCriterion.CeCriterion: 0>', 'kd_loss': '<LossCriterion.MseCriterion: 1>', 'adv_loss': '<LossCriterion.SymKlCriterion: 7>', '__class__': "<class 'experiments.exp_def.TaskDef'>"}, {'self': '{}', 'label_vocab': 'None', 'n_class': '1', 'data_type': '<DataFormat.PremiseAndOneHypothesis: 2>', 'task_type': '<TaskType.Regression: 2>', 'metric_meta': '(<Metric.Pearson: 3>, <Metric.Spearman: 4>)', 'split_names': "['train', 'dev', 'test']", 'enable_san': 'False', 'dropout_p': 'None', 'loss': '<LossCriterion.MseCriterion: 1>', 'kd_loss': '<LossCriterion.MseCriterion: 1>', 'adv_loss': '<LossCriterion.MseCriterion: 1>', '__class__': "<class 'experiments.exp_def.TaskDef'>"}]}
01/07/2021 05:21:05 ####################
01/07/2021 05:21:05 ############# Gradient Accumulation Info #############
01/07/2021 05:21:05 number of step: 59600
01/07/2021 05:21:05 number of grad grad_accumulation step: 1
01/07/2021 05:21:05 adjusted number of step: 59600
01/07/2021 05:21:05 ############# Gradient Accumulation Info #############
01/07/2021 05:21:22 
############# Model Arch of MT-DNN #############
SANBertNetwork(
  (dropout_list): ModuleList(
    (0): DropoutWrapper()
    (1): DropoutWrapper()
    (2): DropoutWrapper()
    (3): DropoutWrapper()
    (4): DropoutWrapper()
    (5): DropoutWrapper()
    (6): DropoutWrapper()
    (7): DropoutWrapper()
  )
  (bert): BertModel(
    (embeddings): BertEmbeddings(
      (word_embeddings): Embedding(30522, 768, padding_idx=0)
      (position_embeddings): Embedding(512, 768)
      (token_type_embeddings): Embedding(2, 768)
      (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
      (dropout): Dropout(p=0.1, inplace=False)
    )
    (encoder): BertEncoder(
      (layer): ModuleList(
        (0): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (1): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (2): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (3): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (4): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (5): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (6): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (7): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (8): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (9): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (10): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (11): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
    )
    (pooler): BertPooler(
      (dense): Linear(in_features=768, out_features=768, bias=True)
      (activation): Tanh()
    )
  )
  (loss_pred_fc): Linear(in_features=768, out_features=1, bias=True)
  (scoring_list): ModuleList(
    (0): Linear(in_features=768, out_features=3, bias=True)
    (1): Linear(in_features=768, out_features=2, bias=True)
    (2): Linear(in_features=768, out_features=2, bias=True)
    (3): Linear(in_features=768, out_features=2, bias=True)
    (4): Linear(in_features=768, out_features=2, bias=True)
    (5): Linear(in_features=768, out_features=2, bias=True)
    (6): Linear(in_features=768, out_features=2, bias=True)
    (7): Linear(in_features=768, out_features=1, bias=True)
  )
)

01/07/2021 05:21:22 Total number of params: 109495313
01/07/2021 05:21:22 At epoch 0
01/07/2021 05:21:23 Task [ 2] updates[     1] train loss[0.77343] remaining[0:53:51]
01/07/2021 05:22:18 Task [ 3] updates[   500] train loss[0.94271] remaining[0:04:38]
01/07/2021 05:23:15 Task [ 3] updates[  1000] train loss[0.89873] remaining[0:03:44]
01/07/2021 05:24:17 Task [ 0] updates[  1500] train loss[0.86878] remaining[0:02:53]
01/07/2021 05:25:22 Task [ 2] updates[  2000] train loss[0.86179] remaining[0:01:57]
01/07/2021 05:26:18 Task [ 3] updates[  2500] train loss[0.81562] remaining[0:00:56]
01/07/2021 05:27:29 Task mnli_matched -- epoch 0 -- Dev ACC: 62.761
01/07/2021 05:27:47 [new test scores saved.]
01/07/2021 05:28:04 Task mnli_mismatched -- epoch 0 -- Dev ACC: 64.188
01/07/2021 05:28:22 [new test scores saved.]
01/07/2021 05:28:22 Task rte -- epoch 0 -- Dev ACC: 53.791
01/07/2021 05:28:28 [new test scores saved.]
01/07/2021 05:29:40 Task qqp -- epoch 0 -- Dev ACC: 76.616
01/07/2021 05:29:40 Task qqp -- epoch 0 -- Dev F1: 72.600
01/07/2021 05:43:04 [new test scores saved.]
01/07/2021 05:43:20 Task qnli -- epoch 0 -- Dev ACC: 65.021
01/07/2021 05:43:36 [new test scores saved.]
01/07/2021 05:43:38 Task mrpc -- epoch 0 -- Dev ACC: 68.627
01/07/2021 05:43:38 Task mrpc -- epoch 0 -- Dev F1: 81.341
01/07/2021 05:43:42 [new test scores saved.]
01/07/2021 05:43:44 Task sst -- epoch 0 -- Dev ACC: 84.748
01/07/2021 05:43:48 [new test scores saved.]
01/07/2021 05:43:50 Task cola -- epoch 0 -- Dev ACC: 69.511
01/07/2021 05:43:50 Task cola -- epoch 0 -- Dev MCC: 8.398
01/07/2021 05:43:52 [new test scores saved.]
01/07/2021 05:43:55 Task stsb -- epoch 0 -- Dev Pearson: 2.719
01/07/2021 05:43:55 Task stsb -- epoch 0 -- Dev Spearman: 5.679
01/07/2021 05:43:58 [new test scores saved.]
01/07/2021 05:44:03 At epoch 1
01/07/2021 05:44:05 Task [ 0] updates[  3000] train loss[0.78145] remaining[0:06:18]
01/07/2021 05:45:11 Task [ 0] updates[  3500] train loss[0.75095] remaining[0:05:24]
01/07/2021 05:46:22 Task [ 0] updates[  4000] train loss[0.72421] remaining[0:04:26]
01/07/2021 05:47:29 Task [ 2] updates[  4500] train loss[0.70676] remaining[0:03:18]
01/07/2021 05:48:37 Task [ 0] updates[  5000] train loss[0.68707] remaining[0:02:10]
01/07/2021 05:49:43 Task [ 3] updates[  5500] train loss[0.66661] remaining[0:01:02]
01/07/2021 05:51:04 Task mnli_matched -- epoch 1 -- Dev ACC: 71.472
01/07/2021 05:51:23 [new test scores saved.]
01/07/2021 05:51:42 Task mnli_mismatched -- epoch 1 -- Dev ACC: 72.600
01/07/2021 05:52:00 [new test scores saved.]
01/07/2021 05:52:01 Task rte -- epoch 1 -- Dev ACC: 53.069
01/07/2021 05:52:07 [new test scores saved.]
01/07/2021 05:53:20 Task qqp -- epoch 1 -- Dev ACC: 78.160
01/07/2021 05:53:20 Task qqp -- epoch 1 -- Dev F1: 75.065
01/07/2021 06:04:50 [new test scores saved.]
01/07/2021 06:05:01 Task qnli -- epoch 1 -- Dev ACC: 75.837
01/07/2021 06:05:12 [new test scores saved.]
01/07/2021 06:05:12 Task mrpc -- epoch 1 -- Dev ACC: 72.059
01/07/2021 06:05:12 Task mrpc -- epoch 1 -- Dev F1: 82.515
01/07/2021 06:05:15 [new test scores saved.]
01/07/2021 06:05:17 Task sst -- epoch 1 -- Dev ACC: 80.275
01/07/2021 06:05:20 [new test scores saved.]
01/07/2021 06:05:21 Task cola -- epoch 1 -- Dev ACC: 69.223
01/07/2021 06:05:21 Task cola -- epoch 1 -- Dev MCC: 4.636
01/07/2021 06:05:23 [new test scores saved.]
01/07/2021 06:05:26 Task stsb -- epoch 1 -- Dev Pearson: 43.082
01/07/2021 06:05:26 Task stsb -- epoch 1 -- Dev Spearman: 42.858
01/07/2021 06:05:28 [new test scores saved.]
01/07/2021 06:05:33 At epoch 2
01/07/2021 06:05:37 Task [ 0] updates[  6000] train loss[0.65021] remaining[0:05:24]
01/07/2021 06:06:29 Task [ 0] updates[  6500] train loss[0.63357] remaining[0:04:16]
01/07/2021 06:07:21 Task [ 0] updates[  7000] train loss[0.61817] remaining[0:03:22]
01/07/2021 06:08:14 Task [ 0] updates[  7500] train loss[0.60190] remaining[0:02:31]
01/07/2021 06:09:10 Task [ 2] updates[  8000] train loss[0.58842] remaining[0:01:40]
01/07/2021 06:10:05 Task [ 2] updates[  8500] train loss[0.57370] remaining[0:00:47]
01/07/2021 06:11:10 Task mnli_matched -- epoch 2 -- Dev ACC: 73.357
01/07/2021 06:11:26 [new test scores saved.]
01/07/2021 06:11:42 Task mnli_mismatched -- epoch 2 -- Dev ACC: 74.044
01/07/2021 06:11:59 [new test scores saved.]
01/07/2021 06:11:59 Task rte -- epoch 2 -- Dev ACC: 62.094
01/07/2021 06:12:05 [new test scores saved.]
01/07/2021 06:13:11 Task qqp -- epoch 2 -- Dev ACC: 80.655
01/07/2021 06:13:11 Task qqp -- epoch 2 -- Dev F1: 75.805
01/07/2021 06:24:44 [new test scores saved.]
01/07/2021 06:24:54 Task qnli -- epoch 2 -- Dev ACC: 77.181
01/07/2021 06:25:06 [new test scores saved.]
01/07/2021 06:25:06 Task mrpc -- epoch 2 -- Dev ACC: 73.039
01/07/2021 06:25:06 Task mrpc -- epoch 2 -- Dev F1: 81.667
01/07/2021 06:25:09 [new test scores saved.]
01/07/2021 06:25:11 Task sst -- epoch 2 -- Dev ACC: 84.862
01/07/2021 06:25:14 [new test scores saved.]
01/07/2021 06:25:15 Task cola -- epoch 2 -- Dev ACC: 70.278
01/07/2021 06:25:15 Task cola -- epoch 2 -- Dev MCC: 15.979
01/07/2021 06:25:17 [new test scores saved.]
01/07/2021 06:25:20 Task stsb -- epoch 2 -- Dev Pearson: 69.539
01/07/2021 06:25:20 Task stsb -- epoch 2 -- Dev Spearman: 70.385
01/07/2021 06:25:22 [new test scores saved.]
01/07/2021 06:25:26 At epoch 3
01/07/2021 06:25:33 Task [ 2] updates[  9000] train loss[0.55936] remaining[0:05:30]
01/07/2021 06:26:28 Task [ 0] updates[  9500] train loss[0.54651] remaining[0:04:27]
01/07/2021 06:27:23 Task [ 0] updates[ 10000] train loss[0.53419] remaining[0:03:31]
01/07/2021 06:28:19 Task [ 3] updates[ 10500] train loss[0.52264] remaining[0:02:37]
01/07/2021 06:29:13 Task [ 2] updates[ 11000] train loss[0.51167] remaining[0:01:41]
01/07/2021 06:30:09 Task [ 4] updates[ 11500] train loss[0.50050] remaining[0:00:46]
01/07/2021 06:31:12 Task mnli_matched -- epoch 3 -- Dev ACC: 73.805
01/07/2021 06:31:28 [new test scores saved.]
01/07/2021 06:31:45 Task mnli_mismatched -- epoch 3 -- Dev ACC: 74.359
01/07/2021 06:32:01 [new test scores saved.]
01/07/2021 06:32:02 Task rte -- epoch 3 -- Dev ACC: 65.704
01/07/2021 06:32:07 [new test scores saved.]
01/07/2021 06:33:14 Task qqp -- epoch 3 -- Dev ACC: 80.868
01/07/2021 06:33:14 Task qqp -- epoch 3 -- Dev F1: 76.092
01/07/2021 06:44:29 [new test scores saved.]
01/07/2021 06:44:40 Task qnli -- epoch 3 -- Dev ACC: 77.809
01/07/2021 06:44:52 [new test scores saved.]
01/07/2021 06:44:52 Task mrpc -- epoch 3 -- Dev ACC: 75.980
01/07/2021 06:44:52 Task mrpc -- epoch 3 -- Dev F1: 83.045
01/07/2021 06:44:55 [new test scores saved.]
01/07/2021 06:44:57 Task sst -- epoch 3 -- Dev ACC: 84.060
01/07/2021 06:45:00 [new test scores saved.]
01/07/2021 06:45:02 Task cola -- epoch 3 -- Dev ACC: 71.620
01/07/2021 06:45:02 Task cola -- epoch 3 -- Dev MCC: 22.221
01/07/2021 06:45:03 [new test scores saved.]
01/07/2021 06:45:06 Task stsb -- epoch 3 -- Dev Pearson: 71.189
01/07/2021 06:45:06 Task stsb -- epoch 3 -- Dev Spearman: 71.820
01/07/2021 06:45:08 [new test scores saved.]
01/07/2021 06:45:13 At epoch 4
01/07/2021 06:45:22 Task [ 2] updates[ 12000] train loss[0.48899] remaining[0:05:31]
01/07/2021 06:46:21 Task [ 0] updates[ 12500] train loss[0.47866] remaining[0:04:43]
01/07/2021 06:47:19 Task [ 0] updates[ 13000] train loss[0.46891] remaining[0:03:42]
01/07/2021 06:48:18 Task [ 0] updates[ 13500] train loss[0.45919] remaining[0:02:44]
01/07/2021 06:49:16 Task [ 2] updates[ 14000] train loss[0.45073] remaining[0:01:45]
01/07/2021 06:50:12 Task [ 5] updates[ 14500] train loss[0.44121] remaining[0:00:46]
01/07/2021 06:51:13 Task mnli_matched -- epoch 4 -- Dev ACC: 73.754
01/07/2021 06:51:30 [new test scores saved.]
01/07/2021 06:51:47 Task mnli_mismatched -- epoch 4 -- Dev ACC: 74.186
01/07/2021 06:52:04 [new test scores saved.]
01/07/2021 06:52:05 Task rte -- epoch 4 -- Dev ACC: 67.509
01/07/2021 06:52:11 [new test scores saved.]
01/07/2021 06:53:21 Task qqp -- epoch 4 -- Dev ACC: 81.585
01/07/2021 06:53:21 Task qqp -- epoch 4 -- Dev F1: 76.710
01/07/2021 07:05:48 [new test scores saved.]
01/07/2021 07:06:01 Task qnli -- epoch 4 -- Dev ACC: 77.704
01/07/2021 07:06:14 [new test scores saved.]
01/07/2021 07:06:15 Task mrpc -- epoch 4 -- Dev ACC: 75.245
01/07/2021 07:06:15 Task mrpc -- epoch 4 -- Dev F1: 82.435
01/07/2021 07:06:19 [new test scores saved.]
01/07/2021 07:06:21 Task sst -- epoch 4 -- Dev ACC: 83.486
01/07/2021 07:06:24 [new test scores saved.]
01/07/2021 07:06:26 Task cola -- epoch 4 -- Dev ACC: 72.867
01/07/2021 07:06:26 Task cola -- epoch 4 -- Dev MCC: 28.965
01/07/2021 07:06:28 [new test scores saved.]
01/07/2021 07:06:31 Task stsb -- epoch 4 -- Dev Pearson: 68.650
01/07/2021 07:06:31 Task stsb -- epoch 4 -- Dev Spearman: 69.318
01/07/2021 07:06:34 [new test scores saved.]
01/07/2021 07:06:39 At epoch 5
01/07/2021 07:06:51 Task [ 2] updates[ 15000] train loss[0.43227] remaining[0:05:42]
01/07/2021 07:07:56 Task [ 0] updates[ 15500] train loss[0.42377] remaining[0:05:06]
01/07/2021 07:08:59 Task [ 3] updates[ 16000] train loss[0.41557] remaining[0:03:59]
01/07/2021 07:10:02 Task [ 2] updates[ 16500] train loss[0.40746] remaining[0:02:54]
01/07/2021 07:11:01 Task [ 0] updates[ 17000] train loss[0.40058] remaining[0:01:49]
01/07/2021 07:12:00 Task [ 3] updates[ 17500] train loss[0.39294] remaining[0:00:46]
01/07/2021 07:13:03 Task mnli_matched -- epoch 5 -- Dev ACC: 73.948
01/07/2021 07:13:22 [new test scores saved.]
01/07/2021 07:13:41 Task mnli_mismatched -- epoch 5 -- Dev ACC: 74.624
01/07/2021 07:14:00 [new test scores saved.]
01/07/2021 07:14:00 Task rte -- epoch 5 -- Dev ACC: 66.787
01/07/2021 07:14:07 [new test scores saved.]
01/07/2021 07:15:23 Task qqp -- epoch 5 -- Dev ACC: 81.167
01/07/2021 07:15:23 Task qqp -- epoch 5 -- Dev F1: 76.197
01/07/2021 07:27:10 [new test scores saved.]
01/07/2021 07:27:21 Task qnli -- epoch 5 -- Dev ACC: 78.227
01/07/2021 07:27:32 [new test scores saved.]
01/07/2021 07:27:33 Task mrpc -- epoch 5 -- Dev ACC: 73.529
01/07/2021 07:27:33 Task mrpc -- epoch 5 -- Dev F1: 81.695
01/07/2021 07:27:36 [new test scores saved.]
01/07/2021 07:27:37 Task sst -- epoch 5 -- Dev ACC: 85.206
01/07/2021 07:27:40 [new test scores saved.]
01/07/2021 07:27:42 Task cola -- epoch 5 -- Dev ACC: 72.963
01/07/2021 07:27:42 Task cola -- epoch 5 -- Dev MCC: 28.302
01/07/2021 07:27:44 [new test scores saved.]
01/07/2021 07:27:46 Task stsb -- epoch 5 -- Dev Pearson: 68.254
01/07/2021 07:27:46 Task stsb -- epoch 5 -- Dev Spearman: 69.046
01/07/2021 07:27:49 [new test scores saved.]
01/07/2021 07:27:53 At epoch 6
01/07/2021 07:28:07 Task [ 3] updates[ 18000] train loss[0.38565] remaining[0:05:18]
01/07/2021 07:29:03 Task [ 0] updates[ 18500] train loss[0.37877] remaining[0:04:25]
01/07/2021 07:29:59 Task [ 5] updates[ 19000] train loss[0.37250] remaining[0:03:29]
01/07/2021 07:30:58 Task [ 0] updates[ 19500] train loss[0.36618] remaining[0:02:34]
01/07/2021 07:31:56 Task [ 5] updates[ 20000] train loss[0.36020] remaining[0:01:38]
01/07/2021 07:32:54 Task [ 0] updates[ 20500] train loss[0.35403] remaining[0:00:41]
01/07/2021 07:33:51 Task mnli_matched -- epoch 6 -- Dev ACC: 73.561
01/07/2021 07:34:09 [new test scores saved.]
01/07/2021 07:34:25 Task mnli_mismatched -- epoch 6 -- Dev ACC: 73.769
01/07/2021 07:34:43 [new test scores saved.]
01/07/2021 07:34:43 Task rte -- epoch 6 -- Dev ACC: 66.426
01/07/2021 07:34:49 [new test scores saved.]
01/07/2021 07:36:03 Task qqp -- epoch 6 -- Dev ACC: 81.813
01/07/2021 07:36:03 Task qqp -- epoch 6 -- Dev F1: 76.157
01/07/2021 07:47:48 [new test scores saved.]
01/07/2021 07:48:02 Task qnli -- epoch 6 -- Dev ACC: 77.896
01/07/2021 07:48:15 [new test scores saved.]
01/07/2021 07:48:16 Task mrpc -- epoch 6 -- Dev ACC: 73.529
01/07/2021 07:48:16 Task mrpc -- epoch 6 -- Dev F1: 80.435
01/07/2021 07:48:20 [new test scores saved.]
01/07/2021 07:48:21 Task sst -- epoch 6 -- Dev ACC: 84.404
01/07/2021 07:48:24 [new test scores saved.]
01/07/2021 07:48:26 Task cola -- epoch 6 -- Dev ACC: 72.675
01/07/2021 07:48:26 Task cola -- epoch 6 -- Dev MCC: 29.789
01/07/2021 07:48:28 [new test scores saved.]
01/07/2021 07:48:31 Task stsb -- epoch 6 -- Dev Pearson: 68.103
01/07/2021 07:48:31 Task stsb -- epoch 6 -- Dev Spearman: 69.135
01/07/2021 07:48:34 [new test scores saved.]
01/07/2021 07:48:39 At epoch 7
01/07/2021 07:48:56 Task [ 0] updates[ 21000] train loss[0.34809] remaining[0:05:44]
01/07/2021 07:49:59 Task [ 0] updates[ 21500] train loss[0.34233] remaining[0:04:54]
01/07/2021 07:51:02 Task [ 2] updates[ 22000] train loss[0.33679] remaining[0:03:51]
01/07/2021 07:52:03 Task [ 0] updates[ 22500] train loss[0.33136] remaining[0:02:47]
01/07/2021 07:53:06 Task [ 0] updates[ 23000] train loss[0.32651] remaining[0:01:45]
01/07/2021 07:54:07 Task [ 2] updates[ 23500] train loss[0.32142] remaining[0:00:42]
01/07/2021 07:55:07 Task mnli_matched -- epoch 7 -- Dev ACC: 73.102
01/07/2021 07:55:27 [new test scores saved.]
01/07/2021 07:55:47 Task mnli_mismatched -- epoch 7 -- Dev ACC: 73.495
01/07/2021 07:56:08 [new test scores saved.]
01/07/2021 07:56:09 Task rte -- epoch 7 -- Dev ACC: 66.787
01/07/2021 07:56:15 [new test scores saved.]
01/07/2021 07:57:32 Task qqp -- epoch 7 -- Dev ACC: 81.890
01/07/2021 07:57:32 Task qqp -- epoch 7 -- Dev F1: 75.207
01/07/2021 08:10:19 [new test scores saved.]
01/07/2021 08:10:31 Task qnli -- epoch 7 -- Dev ACC: 78.297
01/07/2021 08:10:44 [new test scores saved.]
01/07/2021 08:10:45 Task mrpc -- epoch 7 -- Dev ACC: 73.529
01/07/2021 08:10:45 Task mrpc -- epoch 7 -- Dev F1: 80.000
01/07/2021 08:10:49 [new test scores saved.]
01/07/2021 08:10:50 Task sst -- epoch 7 -- Dev ACC: 84.748
01/07/2021 08:10:53 [new test scores saved.]
01/07/2021 08:10:55 Task cola -- epoch 7 -- Dev ACC: 73.058
01/07/2021 08:10:55 Task cola -- epoch 7 -- Dev MCC: 28.052
01/07/2021 08:10:57 [new test scores saved.]
01/07/2021 08:11:00 Task stsb -- epoch 7 -- Dev Pearson: 66.798
01/07/2021 08:11:00 Task stsb -- epoch 7 -- Dev Spearman: 67.973
01/07/2021 08:11:02 [new test scores saved.]
01/07/2021 08:11:07 At epoch 8
01/07/2021 08:11:30 Task [ 0] updates[ 24000] train loss[0.31663] remaining[0:06:38]
01/07/2021 08:12:25 Task [ 0] updates[ 24500] train loss[0.31203] remaining[0:04:33]
01/07/2021 08:13:19 Task [ 3] updates[ 25000] train loss[0.30739] remaining[0:03:27]
01/07/2021 08:14:17 Task [ 0] updates[ 25500] train loss[0.30275] remaining[0:02:31]
01/07/2021 08:15:12 Task [ 0] updates[ 26000] train loss[0.29857] remaining[0:01:32]
01/07/2021 08:16:09 Task [ 0] updates[ 26500] train loss[0.29411] remaining[0:00:36]
01/07/2021 08:17:06 Task mnli_matched -- epoch 8 -- Dev ACC: 73.816
01/07/2021 08:17:25 [new test scores saved.]
01/07/2021 08:17:44 Task mnli_mismatched -- epoch 8 -- Dev ACC: 74.044
01/07/2021 08:18:03 [new test scores saved.]
01/07/2021 08:18:03 Task rte -- epoch 8 -- Dev ACC: 64.982
01/07/2021 08:18:09 [new test scores saved.]
01/07/2021 08:19:24 Task qqp -- epoch 8 -- Dev ACC: 81.679
01/07/2021 08:19:24 Task qqp -- epoch 8 -- Dev F1: 76.598
01/07/2021 08:31:44 [new test scores saved.]
01/07/2021 08:31:56 Task qnli -- epoch 8 -- Dev ACC: 77.913
01/07/2021 08:32:10 [new test scores saved.]
01/07/2021 08:32:11 Task mrpc -- epoch 8 -- Dev ACC: 73.284
01/07/2021 08:32:11 Task mrpc -- epoch 8 -- Dev F1: 80.977
01/07/2021 08:32:15 [new test scores saved.]
01/07/2021 08:32:17 Task sst -- epoch 8 -- Dev ACC: 85.206
01/07/2021 08:32:20 [new test scores saved.]
01/07/2021 08:32:22 Task cola -- epoch 8 -- Dev ACC: 73.250
01/07/2021 08:32:22 Task cola -- epoch 8 -- Dev MCC: 29.908
01/07/2021 08:32:24 [new test scores saved.]
01/07/2021 08:32:27 Task stsb -- epoch 8 -- Dev Pearson: 68.227
01/07/2021 08:32:27 Task stsb -- epoch 8 -- Dev Spearman: 68.913
01/07/2021 08:32:30 [new test scores saved.]
01/07/2021 08:32:34 At epoch 9
01/07/2021 08:32:57 Task [ 0] updates[ 27000] train loss[0.28994] remaining[0:05:50]
01/07/2021 08:33:58 Task [ 2] updates[ 27500] train loss[0.28591] remaining[0:04:43]
01/07/2021 08:35:02 Task [ 0] updates[ 28000] train loss[0.28198] remaining[0:03:45]
01/07/2021 08:36:06 Task [ 0] updates[ 28500] train loss[0.27807] remaining[0:02:44]
01/07/2021 08:37:06 Task [ 0] updates[ 29000] train loss[0.27448] remaining[0:01:39]
01/07/2021 08:38:09 Task [ 2] updates[ 29500] train loss[0.27073] remaining[0:00:37]
01/07/2021 08:39:09 Task mnli_matched -- epoch 9 -- Dev ACC: 74.203
01/07/2021 08:39:31 [new test scores saved.]
01/07/2021 08:39:52 Task mnli_mismatched -- epoch 9 -- Dev ACC: 73.963
01/07/2021 08:40:13 [new test scores saved.]
01/07/2021 08:40:14 Task rte -- epoch 9 -- Dev ACC: 66.426
01/07/2021 08:40:21 [new test scores saved.]
01/07/2021 08:41:44 Task qqp -- epoch 9 -- Dev ACC: 81.600
01/07/2021 08:41:44 Task qqp -- epoch 9 -- Dev F1: 76.132
01/07/2021 08:55:47 [new test scores saved.]
01/07/2021 08:56:00 Task qnli -- epoch 9 -- Dev ACC: 78.542
01/07/2021 08:56:14 [new test scores saved.]
01/07/2021 08:56:15 Task mrpc -- epoch 9 -- Dev ACC: 73.529
01/07/2021 08:56:15 Task mrpc -- epoch 9 -- Dev F1: 81.185
01/07/2021 08:56:19 [new test scores saved.]
01/07/2021 08:56:20 Task sst -- epoch 9 -- Dev ACC: 85.436
01/07/2021 08:56:24 [new test scores saved.]
01/07/2021 08:56:26 Task cola -- epoch 9 -- Dev ACC: 74.017
01/07/2021 08:56:26 Task cola -- epoch 9 -- Dev MCC: 31.980
01/07/2021 08:56:28 [new test scores saved.]
01/07/2021 08:56:31 Task stsb -- epoch 9 -- Dev Pearson: 69.027
01/07/2021 08:56:31 Task stsb -- epoch 9 -- Dev Spearman: 70.538
01/07/2021 08:56:34 [new test scores saved.]
01/07/2021 08:56:40 At epoch 10
01/07/2021 08:57:05 Task [ 2] updates[ 30000] train loss[0.26729] remaining[0:05:55]
01/07/2021 08:58:12 Task [ 2] updates[ 30500] train loss[0.26377] remaining[0:04:58]
01/07/2021 08:59:18 Task [ 0] updates[ 31000] train loss[0.26022] remaining[0:03:53]
01/07/2021 09:00:21 Task [ 0] updates[ 31500] train loss[0.25697] remaining[0:02:46]
01/07/2021 09:01:26 Task [ 0] updates[ 32000] train loss[0.25407] remaining[0:01:41]
01/07/2021 09:02:31 Task [ 2] updates[ 32500] train loss[0.25095] remaining[0:00:36]
01/07/2021 09:03:30 Task mnli_matched -- epoch 10 -- Dev ACC: 74.407
01/07/2021 09:03:51 [new test scores saved.]
01/07/2021 09:04:14 Task mnli_mismatched -- epoch 10 -- Dev ACC: 74.776
01/07/2021 09:04:36 [new test scores saved.]
01/07/2021 09:04:37 Task rte -- epoch 10 -- Dev ACC: 66.426
01/07/2021 09:04:44 [new test scores saved.]
01/07/2021 09:06:07 Task qqp -- epoch 10 -- Dev ACC: 81.217
01/07/2021 09:06:07 Task qqp -- epoch 10 -- Dev F1: 76.514
01/07/2021 09:18:45 [new test scores saved.]
01/07/2021 09:18:58 Task qnli -- epoch 10 -- Dev ACC: 78.925
01/07/2021 09:19:11 [new test scores saved.]
01/07/2021 09:19:12 Task mrpc -- epoch 10 -- Dev ACC: 74.510
01/07/2021 09:19:12 Task mrpc -- epoch 10 -- Dev F1: 82.192
01/07/2021 09:19:15 [new test scores saved.]
01/07/2021 09:19:17 Task sst -- epoch 10 -- Dev ACC: 85.894
01/07/2021 09:19:20 [new test scores saved.]
01/07/2021 09:19:22 Task cola -- epoch 10 -- Dev ACC: 74.209
01/07/2021 09:19:22 Task cola -- epoch 10 -- Dev MCC: 32.135
01/07/2021 09:19:24 [new test scores saved.]
01/07/2021 09:19:27 Task stsb -- epoch 10 -- Dev Pearson: 66.243
01/07/2021 09:19:27 Task stsb -- epoch 10 -- Dev Spearman: 66.694
01/07/2021 09:19:30 [new test scores saved.]
01/07/2021 09:19:35 At epoch 11
01/07/2021 09:20:00 Task [ 0] updates[ 33000] train loss[0.24808] remaining[0:05:18]
01/07/2021 09:20:58 Task [ 4] updates[ 33500] train loss[0.24514] remaining[0:04:21]
01/07/2021 09:22:01 Task [ 0] updates[ 34000] train loss[0.24219] remaining[0:03:30]
01/07/2021 09:23:00 Task [ 2] updates[ 34500] train loss[0.23932] remaining[0:02:30]
01/07/2021 09:23:55 Task [ 0] updates[ 35000] train loss[0.23678] remaining[0:01:29]
01/07/2021 09:24:56 Task [ 2] updates[ 35500] train loss[0.23397] remaining[0:00:30]
01/07/2021 09:25:47 Task mnli_matched -- epoch 11 -- Dev ACC: 74.040
01/07/2021 09:26:07 [new test scores saved.]
01/07/2021 09:26:26 Task mnli_mismatched -- epoch 11 -- Dev ACC: 74.736
01/07/2021 09:26:46 [new test scores saved.]
01/07/2021 09:26:47 Task rte -- epoch 11 -- Dev ACC: 67.148
01/07/2021 09:26:53 [new test scores saved.]
01/07/2021 09:28:12 Task qqp -- epoch 11 -- Dev ACC: 81.655
01/07/2021 09:28:12 Task qqp -- epoch 11 -- Dev F1: 75.977
01/07/2021 09:40:59 [new test scores saved.]
01/07/2021 09:41:11 Task qnli -- epoch 11 -- Dev ACC: 78.890
01/07/2021 09:41:23 [new test scores saved.]
01/07/2021 09:41:24 Task mrpc -- epoch 11 -- Dev ACC: 72.304
01/07/2021 09:41:24 Task mrpc -- epoch 11 -- Dev F1: 79.929
01/07/2021 09:41:28 [new test scores saved.]
01/07/2021 09:41:29 Task sst -- epoch 11 -- Dev ACC: 85.550
01/07/2021 09:41:32 [new test scores saved.]
01/07/2021 09:41:34 Task cola -- epoch 11 -- Dev ACC: 74.209
01/07/2021 09:41:34 Task cola -- epoch 11 -- Dev MCC: 32.288
01/07/2021 09:41:36 [new test scores saved.]
01/07/2021 09:41:39 Task stsb -- epoch 11 -- Dev Pearson: 69.626
01/07/2021 09:41:39 Task stsb -- epoch 11 -- Dev Spearman: 70.575
01/07/2021 09:41:41 [new test scores saved.]
01/07/2021 09:41:46 At epoch 12
01/07/2021 09:42:16 Task [ 3] updates[ 36000] train loss[0.23132] remaining[0:05:42]
01/07/2021 09:43:15 Task [ 2] updates[ 36500] train loss[0.22867] remaining[0:04:30]
01/07/2021 09:44:15 Task [ 0] updates[ 37000] train loss[0.22603] remaining[0:03:29]
01/07/2021 09:45:16 Task [ 5] updates[ 37500] train loss[0.22352] remaining[0:02:29]
01/07/2021 09:46:14 Task [ 2] updates[ 38000] train loss[0.22123] remaining[0:01:28]
01/07/2021 09:47:14 Task [ 0] updates[ 38500] train loss[0.21875] remaining[0:00:28]
01/07/2021 09:48:02 Task mnli_matched -- epoch 12 -- Dev ACC: 73.714
01/07/2021 09:48:22 [new test scores saved.]
01/07/2021 09:48:42 Task mnli_mismatched -- epoch 12 -- Dev ACC: 73.810
01/07/2021 09:49:00 [new test scores saved.]
01/07/2021 09:49:01 Task rte -- epoch 12 -- Dev ACC: 65.704
01/07/2021 09:49:07 [new test scores saved.]
01/07/2021 09:50:26 Task qqp -- epoch 12 -- Dev ACC: 81.120
01/07/2021 09:50:26 Task qqp -- epoch 12 -- Dev F1: 76.458
01/07/2021 10:02:41 [new test scores saved.]
01/07/2021 10:02:53 Task qnli -- epoch 12 -- Dev ACC: 78.873
01/07/2021 10:03:04 [new test scores saved.]
01/07/2021 10:03:05 Task mrpc -- epoch 12 -- Dev ACC: 73.529
01/07/2021 10:03:05 Task mrpc -- epoch 12 -- Dev F1: 80.505
01/07/2021 10:03:08 [new test scores saved.]
01/07/2021 10:03:10 Task sst -- epoch 12 -- Dev ACC: 84.862
01/07/2021 10:03:13 [new test scores saved.]
01/07/2021 10:03:15 Task cola -- epoch 12 -- Dev ACC: 73.826
01/07/2021 10:03:15 Task cola -- epoch 12 -- Dev MCC: 30.877
01/07/2021 10:03:16 [new test scores saved.]
01/07/2021 10:03:19 Task stsb -- epoch 12 -- Dev Pearson: 69.378
01/07/2021 10:03:19 Task stsb -- epoch 12 -- Dev Spearman: 70.738
01/07/2021 10:03:21 [new test scores saved.]
01/07/2021 10:03:26 At epoch 13
01/07/2021 10:03:55 Task [ 3] updates[ 39000] train loss[0.21649] remaining[0:05:00]
01/07/2021 10:04:43 Task [ 2] updates[ 39500] train loss[0.21413] remaining[0:03:45]
01/07/2021 10:05:39 Task [ 0] updates[ 40000] train loss[0.21176] remaining[0:03:01]
01/07/2021 10:06:35 Task [ 0] updates[ 40500] train loss[0.20958] remaining[0:02:10]
01/07/2021 10:07:31 Task [ 0] updates[ 41000] train loss[0.20763] remaining[0:01:17]
01/07/2021 10:08:25 Task [ 2] updates[ 41500] train loss[0.20540] remaining[0:00:23]
01/07/2021 10:09:06 Task mnli_matched -- epoch 13 -- Dev ACC: 74.060
01/07/2021 10:09:26 [new test scores saved.]
01/07/2021 10:09:43 Task mnli_mismatched -- epoch 13 -- Dev ACC: 74.420
01/07/2021 10:10:00 [new test scores saved.]
01/07/2021 10:10:01 Task rte -- epoch 13 -- Dev ACC: 67.870
01/07/2021 10:10:07 [new test scores saved.]
01/07/2021 10:11:17 Task qqp -- epoch 13 -- Dev ACC: 81.405
01/07/2021 10:11:20 Task qqp -- epoch 13 -- Dev F1: 76.701
01/07/2021 10:23:31 [new test scores saved.]
01/07/2021 10:23:42 Task qnli -- epoch 13 -- Dev ACC: 78.943
01/07/2021 10:23:53 [new test scores saved.]
01/07/2021 10:23:54 Task mrpc -- epoch 13 -- Dev ACC: 74.020
01/07/2021 10:23:54 Task mrpc -- epoch 13 -- Dev F1: 81.338
01/07/2021 10:23:57 [new test scores saved.]
01/07/2021 10:23:59 Task sst -- epoch 13 -- Dev ACC: 85.321
01/07/2021 10:24:02 [new test scores saved.]
01/07/2021 10:24:04 Task cola -- epoch 13 -- Dev ACC: 73.921
01/07/2021 10:24:04 Task cola -- epoch 13 -- Dev MCC: 31.403
01/07/2021 10:24:05 [new test scores saved.]
01/07/2021 10:24:08 Task stsb -- epoch 13 -- Dev Pearson: 69.599
01/07/2021 10:24:08 Task stsb -- epoch 13 -- Dev Spearman: 70.300
01/07/2021 10:24:10 [new test scores saved.]
01/07/2021 10:24:15 At epoch 14
01/07/2021 10:24:47 Task [ 2] updates[ 42000] train loss[0.20338] remaining[0:05:10]
01/07/2021 10:25:44 Task [ 2] updates[ 42500] train loss[0.20131] remaining[0:04:12]
01/07/2021 10:26:40 Task [ 0] updates[ 43000] train loss[0.19929] remaining[0:03:13]
01/07/2021 10:27:37 Task [ 3] updates[ 43500] train loss[0.19741] remaining[0:02:16]
01/07/2021 10:28:34 Task [ 0] updates[ 44000] train loss[0.19554] remaining[0:01:19]
01/07/2021 10:29:30 Task [ 3] updates[ 44500] train loss[0.19362] remaining[0:00:22]
01/07/2021 10:30:10 Task mnli_matched -- epoch 14 -- Dev ACC: 74.427
01/07/2021 10:30:27 [new test scores saved.]
01/07/2021 10:30:44 Task mnli_mismatched -- epoch 14 -- Dev ACC: 74.542
01/07/2021 10:31:02 [new test scores saved.]
01/07/2021 10:31:02 Task rte -- epoch 14 -- Dev ACC: 67.148
01/07/2021 10:31:08 [new test scores saved.]
01/07/2021 10:32:19 Task qqp -- epoch 14 -- Dev ACC: 81.590
01/07/2021 10:32:19 Task qqp -- epoch 14 -- Dev F1: 76.515