MTDNN_LMHE5_8_ALL.log

01/08/2021 03:54:43 1
01/08/2021 03:54:43 Launching the MT-DNN training
01/08/2021 03:54:43 Loading data/canonical_data/bert_base_uncased_lower/mnli_train.json as task 0
01/08/2021 03:56:58 Loading data/canonical_data/bert_base_uncased_lower/rte_train.json as task 1
01/08/2021 03:56:58 Loading data/canonical_data/bert_base_uncased_lower/qqp_train.json as task 2
01/08/2021 03:58:53 Loading data/canonical_data/bert_base_uncased_lower/qnli_train.json as task 3
01/08/2021 03:59:04 Loading data/canonical_data/bert_base_uncased_lower/mrpc_train.json as task 4
01/08/2021 03:59:04 Loading data/canonical_data/bert_base_uncased_lower/sst_train.json as task 5
01/08/2021 03:59:09 Loading data/canonical_data/bert_base_uncased_lower/cola_train.json as task 6
01/08/2021 03:59:09 Loading data/canonical_data/bert_base_uncased_lower/stsb_train.json as task 7
01/08/2021 03:59:20 ####################
01/08/2021 03:59:20 {'log_file': 'checkpoints/LM_entropy8/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': 10, 'batch_size': 8, '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/LM_entropy8', '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': '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 0x7fc9453353d0>', '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 0x7fc945335550>', '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 0x7fc945335220>', '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'>"}]}
01/08/2021 03:59:20 ####################
01/08/2021 03:59:20 ############# Gradient Accumulation Info #############
01/08/2021 03:59:20 number of step: 59570
01/08/2021 03:59:20 number of grad grad_accumulation step: 1
01/08/2021 03:59:20 adjusted number of step: 59570
01/08/2021 03:59:20 ############# Gradient Accumulation Info #############
01/08/2021 03:59:40 
############# 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)
  )
)

01/08/2021 03:59:40 Total number of params: 109495313
01/08/2021 03:59:40 At epoch 0
01/08/2021 03:59:41 Task [ 0] updates[     1] train loss[1.20159] remaining[1:42:10]
01/08/2021 04:00:42 Task [ 5] updates[   500] train loss[1.01649] remaining[0:11:19]
01/08/2021 04:01:42 Task [ 2] updates[  1000] train loss[0.92611] remaining[0:10:07]
01/08/2021 04:02:43 Task [ 0] updates[  1500] train loss[0.89924] remaining[0:09:03]
01/08/2021 04:03:43 Task [ 2] updates[  2000] train loss[0.86711] remaining[0:08:02]
01/08/2021 04:04:44 Task [ 2] updates[  2500] train loss[0.83990] remaining[0:07:00]
01/08/2021 04:05:44 Task [ 5] updates[  3000] train loss[0.82106] remaining[0:05:58]
01/08/2021 04:06:44 Task [ 3] updates[  3500] train loss[0.78982] remaining[0:04:57]
01/08/2021 04:07:43 Task [ 3] updates[  4000] train loss[0.76533] remaining[0:03:56]
01/08/2021 04:08:43 Task [ 2] updates[  4500] train loss[0.74869] remaining[0:02:56]
01/08/2021 04:09:44 Task [ 2] updates[  5000] train loss[0.73025] remaining[0:01:55]
01/08/2021 04:10:45 Task [ 2] updates[  5500] train loss[0.71531] remaining[0:00:55]
01/08/2021 04:12:04 Task mnli_matched -- epoch 0 -- Dev ACC: 68.487
01/08/2021 04:12:27 [new test scores saved.]
01/08/2021 04:12:51 Task mnli_mismatched -- epoch 0 -- Dev ACC: 69.711
01/08/2021 04:13:15 [new test scores saved.]
01/08/2021 04:13:16 Task rte -- epoch 0 -- Dev ACC: 57.762
01/08/2021 04:13:25 [new test scores saved.]
01/08/2021 04:14:50 Task qqp -- epoch 0 -- Dev ACC: 79.077
01/08/2021 04:14:50 Task qqp -- epoch 0 -- Dev F1: 73.353
01/08/2021 04:28:31 [new test scores saved.]
01/08/2021 04:28:46 Task qnli -- epoch 0 -- Dev ACC: 72.662
01/08/2021 04:29:03 [new test scores saved.]
01/08/2021 04:29:04 Task mrpc -- epoch 0 -- Dev ACC: 73.775
01/08/2021 04:29:04 Task mrpc -- epoch 0 -- Dev F1: 83.411
01/08/2021 04:29:09 [new test scores saved.]
01/08/2021 04:29:10 Task sst -- epoch 0 -- Dev ACC: 80.275
01/08/2021 04:29:14 [new test scores saved.]
01/08/2021 04:29:15 Task cola -- epoch 0 -- Dev ACC: 69.128
01/08/2021 04:29:15 Task cola -- epoch 0 -- Dev MCC: 0.000
01/08/2021 04:29:17 [new test scores saved.]
01/08/2021 04:29:20 Task stsb -- epoch 0 -- Dev Pearson: 37.707
01/08/2021 04:29:20 Task stsb -- epoch 0 -- Dev Spearman: 38.323
01/08/2021 04:29:23 [new test scores saved.]
01/08/2021 04:29:28 At epoch 1
01/08/2021 04:29:33 Task [ 2] updates[  6000] train loss[0.70180] remaining[0:12:23]
01/08/2021 04:30:34 Task [ 5] updates[  6500] train loss[0.68707] remaining[0:10:59]
01/08/2021 04:31:34 Task [ 3] updates[  7000] train loss[0.67278] remaining[0:09:56]
01/08/2021 04:32:34 Task [ 1] updates[  7500] train loss[0.66127] remaining[0:08:51]
01/08/2021 04:33:32 Task [ 0] updates[  8000] train loss[0.65306] remaining[0:07:47]
01/08/2021 04:34:31 Task [ 7] updates[  8500] train loss[0.64208] remaining[0:06:46]
01/08/2021 04:35:30 Task [ 2] updates[  9000] train loss[0.63183] remaining[0:05:47]
01/08/2021 04:36:29 Task [ 3] updates[  9500] train loss[0.62136] remaining[0:04:47]
01/08/2021 04:37:26 Task [ 3] updates[ 10000] train loss[0.61284] remaining[0:03:46]
01/08/2021 04:38:23 Task [ 2] updates[ 10500] train loss[0.60426] remaining[0:02:46]
01/08/2021 04:39:25 Task [ 3] updates[ 11000] train loss[0.59520] remaining[0:01:48]
01/08/2021 04:40:24 Task [ 2] updates[ 11500] train loss[0.58639] remaining[0:00:49]
01/08/2021 04:41:37 Task mnli_matched -- epoch 1 -- Dev ACC: 72.766
01/08/2021 04:42:01 [new test scores saved.]
01/08/2021 04:42:25 Task mnli_mismatched -- epoch 1 -- Dev ACC: 73.871
01/08/2021 04:42:49 [new test scores saved.]
01/08/2021 04:42:50 Task rte -- epoch 1 -- Dev ACC: 64.621
01/08/2021 04:42:59 [new test scores saved.]
01/08/2021 04:44:23 Task qqp -- epoch 1 -- Dev ACC: 79.765
01/08/2021 04:44:23 Task qqp -- epoch 1 -- Dev F1: 75.973
01/08/2021 04:58:00 [new test scores saved.]
01/08/2021 04:58:15 Task qnli -- epoch 1 -- Dev ACC: 77.059
01/08/2021 04:58:33 [new test scores saved.]
01/08/2021 04:58:34 Task mrpc -- epoch 1 -- Dev ACC: 72.549
01/08/2021 04:58:34 Task mrpc -- epoch 1 -- Dev F1: 82.555
01/08/2021 04:58:38 [new test scores saved.]
01/08/2021 04:58:39 Task sst -- epoch 1 -- Dev ACC: 82.913
01/08/2021 04:58:43 [new test scores saved.]
01/08/2021 04:58:44 Task cola -- epoch 1 -- Dev ACC: 69.128
01/08/2021 04:58:44 Task cola -- epoch 1 -- Dev MCC: 0.000
01/08/2021 04:58:46 [new test scores saved.]
01/08/2021 04:58:49 Task stsb -- epoch 1 -- Dev Pearson: 67.520
01/08/2021 04:58:49 Task stsb -- epoch 1 -- Dev Spearman: 68.105
01/08/2021 04:58:52 [new test scores saved.]
01/08/2021 04:58:56 At epoch 2
01/08/2021 04:59:06 Task [ 2] updates[ 12000] train loss[0.57655] remaining[0:11:35]
01/08/2021 05:00:05 Task [ 2] updates[ 12500] train loss[0.56836] remaining[0:10:27]
01/08/2021 05:01:03 Task [ 2] updates[ 13000] train loss[0.55995] remaining[0:09:27]
01/08/2021 05:02:01 Task [ 5] updates[ 13500] train loss[0.55309] remaining[0:08:30]
01/08/2021 05:02:59 Task [ 2] updates[ 14000] train loss[0.54594] remaining[0:07:31]
01/08/2021 05:03:57 Task [ 2] updates[ 14500] train loss[0.53897] remaining[0:06:31]
01/08/2021 05:04:56 Task [ 3] updates[ 15000] train loss[0.53203] remaining[0:05:34]
01/08/2021 05:05:53 Task [ 2] updates[ 15500] train loss[0.52634] remaining[0:04:35]
01/08/2021 05:06:52 Task [ 2] updates[ 16000] train loss[0.51980] remaining[0:03:37]
01/08/2021 05:07:49 Task [ 2] updates[ 16500] train loss[0.51346] remaining[0:02:39]
01/08/2021 05:08:48 Task [ 0] updates[ 17000] train loss[0.50711] remaining[0:01:41]
01/08/2021 05:09:46 Task [ 2] updates[ 17500] train loss[0.50080] remaining[0:00:43]
01/08/2021 05:10:53 Task mnli_matched -- epoch 2 -- Dev ACC: 74.142
01/08/2021 05:11:16 [new test scores saved.]
01/08/2021 05:11:40 Task mnli_mismatched -- epoch 2 -- Dev ACC: 74.919
01/08/2021 05:12:04 [new test scores saved.]
01/08/2021 05:12:05 Task rte -- epoch 2 -- Dev ACC: 65.704
01/08/2021 05:12:14 [new test scores saved.]
01/08/2021 05:13:38 Task qqp -- epoch 2 -- Dev ACC: 80.962
01/08/2021 05:13:38 Task qqp -- epoch 2 -- Dev F1: 76.484
01/08/2021 05:27:14 [new test scores saved.]
01/08/2021 05:27:29 Task qnli -- epoch 2 -- Dev ACC: 78.768
01/08/2021 05:27:46 [new test scores saved.]
01/08/2021 05:27:47 Task mrpc -- epoch 2 -- Dev ACC: 73.284
01/08/2021 05:27:47 Task mrpc -- epoch 2 -- Dev F1: 82.043
01/08/2021 05:27:52 [new test scores saved.]
01/08/2021 05:27:53 Task sst -- epoch 2 -- Dev ACC: 85.665
01/08/2021 05:27:56 [new test scores saved.]
01/08/2021 05:27:58 Task cola -- epoch 2 -- Dev ACC: 69.319
01/08/2021 05:27:58 Task cola -- epoch 2 -- Dev MCC: 5.894
01/08/2021 05:28:00 [new test scores saved.]
01/08/2021 05:28:03 Task stsb -- epoch 2 -- Dev Pearson: 69.200
01/08/2021 05:28:03 Task stsb -- epoch 2 -- Dev Spearman: 70.256
01/08/2021 05:28:05 [new test scores saved.]
01/08/2021 05:28:10 At epoch 3
01/08/2021 05:28:24 Task [ 0] updates[ 18000] train loss[0.49448] remaining[0:10:56]
01/08/2021 05:29:22 Task [ 2] updates[ 18500] train loss[0.48892] remaining[0:10:13]
01/08/2021 05:30:20 Task [ 0] updates[ 19000] train loss[0.48284] remaining[0:09:15]
01/08/2021 05:31:17 Task [ 0] updates[ 19500] train loss[0.47763] remaining[0:08:18]
01/08/2021 05:32:14 Task [ 2] updates[ 20000] train loss[0.47206] remaining[0:07:19]
01/08/2021 05:33:13 Task [ 2] updates[ 20500] train loss[0.46695] remaining[0:06:23]
01/08/2021 05:34:10 Task [ 0] updates[ 21000] train loss[0.46174] remaining[0:05:25]
01/08/2021 05:35:09 Task [ 0] updates[ 21500] train loss[0.45692] remaining[0:04:29]
01/08/2021 05:36:08 Task [ 0] updates[ 22000] train loss[0.45166] remaining[0:03:31]
01/08/2021 05:37:06 Task [ 0] updates[ 22500] train loss[0.44637] remaining[0:02:33]
01/08/2021 05:38:02 Task [ 3] updates[ 23000] train loss[0.44187] remaining[0:01:35]
01/08/2021 05:39:00 Task [ 3] updates[ 23500] train loss[0.43724] remaining[0:00:37]
01/08/2021 05:40:01 Task mnli_matched -- epoch 3 -- Dev ACC: 73.418
01/08/2021 05:40:25 [new test scores saved.]
01/08/2021 05:40:49 Task mnli_mismatched -- epoch 3 -- Dev ACC: 74.166
01/08/2021 05:41:13 [new test scores saved.]
01/08/2021 05:41:14 Task rte -- epoch 3 -- Dev ACC: 66.426
01/08/2021 05:41:23 [new test scores saved.]
01/08/2021 05:42:47 Task qqp -- epoch 3 -- Dev ACC: 81.519
01/08/2021 05:42:47 Task qqp -- epoch 3 -- Dev F1: 76.410
01/08/2021 05:56:25 [new test scores saved.]
01/08/2021 05:56:40 Task qnli -- epoch 3 -- Dev ACC: 78.070
01/08/2021 05:56:57 [new test scores saved.]
01/08/2021 05:56:58 Task mrpc -- epoch 3 -- Dev ACC: 72.549
01/08/2021 05:56:58 Task mrpc -- epoch 3 -- Dev F1: 81.081
01/08/2021 05:57:03 [new test scores saved.]
01/08/2021 05:57:04 Task sst -- epoch 3 -- Dev ACC: 85.206
01/08/2021 05:57:07 [new test scores saved.]
01/08/2021 05:57:09 Task cola -- epoch 3 -- Dev ACC: 71.333
01/08/2021 05:57:09 Task cola -- epoch 3 -- Dev MCC: 20.500
01/08/2021 05:57:11 [new test scores saved.]
01/08/2021 05:57:14 Task stsb -- epoch 3 -- Dev Pearson: 68.687
01/08/2021 05:57:14 Task stsb -- epoch 3 -- Dev Spearman: 72.404
01/08/2021 05:57:17 [new test scores saved.]
01/08/2021 05:57:21 At epoch 4
01/08/2021 05:57:40 Task [ 2] updates[ 24000] train loss[0.43230] remaining[0:10:55]
01/08/2021 05:58:38 Task [ 3] updates[ 24500] train loss[0.42825] remaining[0:10:06]
01/08/2021 05:59:34 Task [ 2] updates[ 25000] train loss[0.42349] remaining[0:09:02]
01/08/2021 06:00:31 Task [ 0] updates[ 25500] train loss[0.41950] remaining[0:08:08]
01/08/2021 06:01:30 Task [ 0] updates[ 26000] train loss[0.41494] remaining[0:07:13]
01/08/2021 06:02:28 Task [ 2] updates[ 26500] train loss[0.41088] remaining[0:06:17]
01/08/2021 06:03:25 Task [ 3] updates[ 27000] train loss[0.40696] remaining[0:05:19]
01/08/2021 06:04:22 Task [ 2] updates[ 27500] train loss[0.40287] remaining[0:04:21]
01/08/2021 06:05:20 Task [ 1] updates[ 28000] train loss[0.39907] remaining[0:03:24]
01/08/2021 06:06:17 Task [ 0] updates[ 28500] train loss[0.39464] remaining[0:02:27]
01/08/2021 06:07:15 Task [ 2] updates[ 29000] train loss[0.39111] remaining[0:01:30]
01/08/2021 06:08:11 Task [ 2] updates[ 29500] train loss[0.38701] remaining[0:00:32]
01/08/2021 06:09:06 Task mnli_matched -- epoch 4 -- Dev ACC: 73.979
01/08/2021 06:09:30 [new test scores saved.]
01/08/2021 06:09:54 Task mnli_mismatched -- epoch 4 -- Dev ACC: 74.583
01/08/2021 06:10:18 [new test scores saved.]
01/08/2021 06:10:19 Task rte -- epoch 4 -- Dev ACC: 67.509
01/08/2021 06:10:28 [new test scores saved.]
01/08/2021 06:11:52 Task qqp -- epoch 4 -- Dev ACC: 81.781
01/08/2021 06:11:52 Task qqp -- epoch 4 -- Dev F1: 76.074
01/08/2021 06:25:29 [new test scores saved.]
01/08/2021 06:25:44 Task qnli -- epoch 4 -- Dev ACC: 77.861
01/08/2021 06:26:01 [new test scores saved.]
01/08/2021 06:26:02 Task mrpc -- epoch 4 -- Dev ACC: 72.549
01/08/2021 06:26:02 Task mrpc -- epoch 4 -- Dev F1: 80.488
01/08/2021 06:26:06 [new test scores saved.]
01/08/2021 06:26:08 Task sst -- epoch 4 -- Dev ACC: 84.174
01/08/2021 06:26:11 [new test scores saved.]
01/08/2021 06:26:13 Task cola -- epoch 4 -- Dev ACC: 71.908
01/08/2021 06:26:13 Task cola -- epoch 4 -- Dev MCC: 23.122
01/08/2021 06:26:15 [new test scores saved.]
01/08/2021 06:26:18 Task stsb -- epoch 4 -- Dev Pearson: 68.750
01/08/2021 06:26:18 Task stsb -- epoch 4 -- Dev Spearman: 71.230
01/08/2021 06:26:20 [new test scores saved.]
01/08/2021 06:26:25 At epoch 5
01/08/2021 06:26:49 Task [ 0] updates[ 30000] train loss[0.38331] remaining[0:10:55]
01/08/2021 06:27:47 Task [ 2] updates[ 30500] train loss[0.37947] remaining[0:10:04]
01/08/2021 06:28:45 Task [ 2] updates[ 31000] train loss[0.37565] remaining[0:09:05]
01/08/2021 06:29:42 Task [ 2] updates[ 31500] train loss[0.37211] remaining[0:08:06]
01/08/2021 06:30:39 Task [ 2] updates[ 32000] train loss[0.36864] remaining[0:07:10]
01/08/2021 06:31:37 Task [ 0] updates[ 32500] train loss[0.36540] remaining[0:06:12]
01/08/2021 06:32:35 Task [ 2] updates[ 33000] train loss[0.36196] remaining[0:05:15]
01/08/2021 06:33:32 Task [ 0] updates[ 33500] train loss[0.35837] remaining[0:04:17]
01/08/2021 06:34:30 Task [ 3] updates[ 34000] train loss[0.35503] remaining[0:03:20]
01/08/2021 06:35:28 Task [ 2] updates[ 34500] train loss[0.35158] remaining[0:02:23]
01/08/2021 06:36:26 Task [ 2] updates[ 35000] train loss[0.34860] remaining[0:01:25]
01/08/2021 06:37:25 Task [ 2] updates[ 35500] train loss[0.34551] remaining[0:00:27]
01/08/2021 06:38:16 Task mnli_matched -- epoch 5 -- Dev ACC: 74.570
01/08/2021 06:38:40 [new test scores saved.]
01/08/2021 06:39:04 Task mnli_mismatched -- epoch 5 -- Dev ACC: 75.203
01/08/2021 06:39:27 [new test scores saved.]
01/08/2021 06:39:29 Task rte -- epoch 5 -- Dev ACC: 66.787
01/08/2021 06:39:38 [new test scores saved.]
01/08/2021 06:41:01 Task qqp -- epoch 5 -- Dev ACC: 82.038
01/08/2021 06:41:01 Task qqp -- epoch 5 -- Dev F1: 76.514
01/08/2021 06:54:35 [new test scores saved.]
01/08/2021 06:54:51 Task qnli -- epoch 5 -- Dev ACC: 78.070
01/08/2021 06:55:08 [new test scores saved.]
01/08/2021 06:55:09 Task mrpc -- epoch 5 -- Dev ACC: 72.549
01/08/2021 06:55:09 Task mrpc -- epoch 5 -- Dev F1: 80.690
01/08/2021 06:55:13 [new test scores saved.]
01/08/2021 06:55:14 Task sst -- epoch 5 -- Dev ACC: 85.206
01/08/2021 06:55:18 [new test scores saved.]
01/08/2021 06:55:20 Task cola -- epoch 5 -- Dev ACC: 72.196
01/08/2021 06:55:20 Task cola -- epoch 5 -- Dev MCC: 25.066
01/08/2021 06:55:21 [new test scores saved.]
01/08/2021 06:55:24 Task stsb -- epoch 5 -- Dev Pearson: 67.233
01/08/2021 06:55:24 Task stsb -- epoch 5 -- Dev Spearman: 69.773
01/08/2021 06:55:27 [new test scores saved.]
01/08/2021 06:55:32 At epoch 6
01/08/2021 06:56:02 Task [ 3] updates[ 36000] train loss[0.34244] remaining[0:11:02]
01/08/2021 06:56:59 Task [ 0] updates[ 36500] train loss[0.33978] remaining[0:09:56]
01/08/2021 06:57:57 Task [ 0] updates[ 37000] train loss[0.33667] remaining[0:09:00]
01/08/2021 06:58:54 Task [ 3] updates[ 37500] train loss[0.33385] remaining[0:08:02]
01/08/2021 06:59:52 Task [ 2] updates[ 38000] train loss[0.33078] remaining[0:07:06]
01/08/2021 07:00:50 Task [ 0] updates[ 38500] train loss[0.32822] remaining[0:06:08]
01/08/2021 07:01:48 Task [ 5] updates[ 39000] train loss[0.32539] remaining[0:05:11]
01/08/2021 07:02:46 Task [ 3] updates[ 39500] train loss[0.32267] remaining[0:04:13]
01/08/2021 07:03:42 Task [ 2] updates[ 40000] train loss[0.31989] remaining[0:03:15]
01/08/2021 07:04:40 Task [ 2] updates[ 40500] train loss[0.31702] remaining[0:02:18]
01/08/2021 07:05:38 Task [ 0] updates[ 41000] train loss[0.31460] remaining[0:01:20]
01/08/2021 07:06:35 Task [ 2] updates[ 41500] train loss[0.31208] remaining[0:00:22]
01/08/2021 07:07:21 Task mnli_matched -- epoch 6 -- Dev ACC: 74.121
01/08/2021 07:07:44 [new test scores saved.]
01/08/2021 07:08:08 Task mnli_mismatched -- epoch 6 -- Dev ACC: 74.898
01/08/2021 07:08:32 [new test scores saved.]
01/08/2021 07:08:33 Task rte -- epoch 6 -- Dev ACC: 66.065
01/08/2021 07:08:42 [new test scores saved.]
01/08/2021 07:10:05 Task qqp -- epoch 6 -- Dev ACC: 82.070
01/08/2021 07:10:05 Task qqp -- epoch 6 -- Dev F1: 75.636
01/08/2021 07:23:40 [new test scores saved.]
01/08/2021 07:23:56 Task qnli -- epoch 6 -- Dev ACC: 78.210
01/08/2021 07:24:13 [new test scores saved.]
01/08/2021 07:24:14 Task mrpc -- epoch 6 -- Dev ACC: 72.059
01/08/2021 07:24:14 Task mrpc -- epoch 6 -- Dev F1: 79.930
01/08/2021 07:24:18 [new test scores saved.]
01/08/2021 07:24:19 Task sst -- epoch 6 -- Dev ACC: 85.665
01/08/2021 07:24:23 [new test scores saved.]
01/08/2021 07:24:24 Task cola -- epoch 6 -- Dev ACC: 73.250
01/08/2021 07:24:24 Task cola -- epoch 6 -- Dev MCC: 28.973
01/08/2021 07:24:26 [new test scores saved.]
01/08/2021 07:24:29 Task stsb -- epoch 6 -- Dev Pearson: 67.136
01/08/2021 07:24:29 Task stsb -- epoch 6 -- Dev Spearman: 69.210
01/08/2021 07:24:32 [new test scores saved.]
01/08/2021 07:24:37 At epoch 7
01/08/2021 07:25:11 Task [ 0] updates[ 42000] train loss[0.30954] remaining[0:10:48]
01/08/2021 07:26:09 Task [ 0] updates[ 42500] train loss[0.30718] remaining[0:09:55]
01/08/2021 07:27:06 Task [ 2] updates[ 43000] train loss[0.30459] remaining[0:08:54]
01/08/2021 07:28:06 Task [ 2] updates[ 43500] train loss[0.30218] remaining[0:08:01]
01/08/2021 07:29:03 Task [ 2] updates[ 44000] train loss[0.29965] remaining[0:07:02]
01/08/2021 07:30:00 Task [ 0] updates[ 44500] train loss[0.29734] remaining[0:06:04]
01/08/2021 07:30:58 Task [ 6] updates[ 45000] train loss[0.29510] remaining[0:05:06]
01/08/2021 07:31:55 Task [ 0] updates[ 45500] train loss[0.29281] remaining[0:04:08]
01/08/2021 07:32:53 Task [ 2] updates[ 46000] train loss[0.29037] remaining[0:03:10]
01/08/2021 07:33:50 Task [ 3] updates[ 46500] train loss[0.28823] remaining[0:02:13]
01/08/2021 07:34:46 Task [ 0] updates[ 47000] train loss[0.28614] remaining[0:01:15]
01/08/2021 07:35:43 Task [ 0] updates[ 47500] train loss[0.28399] remaining[0:00:17]
01/08/2021 07:36:23 Task mnli_matched -- epoch 7 -- Dev ACC: 74.356
01/08/2021 07:36:47 [new test scores saved.]
01/08/2021 07:37:11 Task mnli_mismatched -- epoch 7 -- Dev ACC: 74.919
01/08/2021 07:37:34 [new test scores saved.]
01/08/2021 07:37:36 Task rte -- epoch 7 -- Dev ACC: 67.509
01/08/2021 07:37:45 [new test scores saved.]
01/08/2021 07:39:08 Task qqp -- epoch 7 -- Dev ACC: 82.046
01/08/2021 07:39:08 Task qqp -- epoch 7 -- Dev F1: 75.921
01/08/2021 07:52:44 [new test scores saved.]
01/08/2021 07:52:59 Task qnli -- epoch 7 -- Dev ACC: 78.768
01/08/2021 07:53:16 [new test scores saved.]
01/08/2021 07:53:17 Task mrpc -- epoch 7 -- Dev ACC: 72.059
01/08/2021 07:53:17 Task mrpc -- epoch 7 -- Dev F1: 80.412
01/08/2021 07:53:22 [new test scores saved.]
01/08/2021 07:53:23 Task sst -- epoch 7 -- Dev ACC: 85.550
01/08/2021 07:53:27 [new test scores saved.]
01/08/2021 07:53:28 Task cola -- epoch 7 -- Dev ACC: 73.634
01/08/2021 07:53:28 Task cola -- epoch 7 -- Dev MCC: 30.554
01/08/2021 07:53:30 [new test scores saved.]
01/08/2021 07:53:33 Task stsb -- epoch 7 -- Dev Pearson: 67.990
01/08/2021 07:53:33 Task stsb -- epoch 7 -- Dev Spearman: 69.659
01/08/2021 07:53:36 [new test scores saved.]
01/08/2021 07:53:41 At epoch 8
01/08/2021 07:54:20 Task [ 2] updates[ 48000] train loss[0.28179] remaining[0:10:36]
01/08/2021 07:55:18 Task [ 0] updates[ 48500] train loss[0.27974] remaining[0:09:45]
01/08/2021 07:56:16 Task [ 3] updates[ 49000] train loss[0.27771] remaining[0:08:52]
01/08/2021 07:57:16 Task [ 0] updates[ 49500] train loss[0.27575] remaining[0:07:58]
01/08/2021 07:58:13 Task [ 2] updates[ 50000] train loss[0.27361] remaining[0:06:59]
01/08/2021 07:59:10 Task [ 2] updates[ 50500] train loss[0.27166] remaining[0:06:00]
01/08/2021 08:00:08 Task [ 0] updates[ 51000] train loss[0.26964] remaining[0:05:02]
01/08/2021 08:01:07 Task [ 3] updates[ 51500] train loss[0.26781] remaining[0:04:05]
01/08/2021 08:02:05 Task [ 2] updates[ 52000] train loss[0.26571] remaining[0:03:07]
01/08/2021 08:03:02 Task [ 2] updates[ 52500] train loss[0.26382] remaining[0:02:08]
01/08/2021 08:04:00 Task [ 0] updates[ 53000] train loss[0.26201] remaining[0:01:11]
01/08/2021 08:04:57 Task [ 2] updates[ 53500] train loss[0.26014] remaining[0:00:13]
01/08/2021 08:05:34 Task mnli_matched -- epoch 8 -- Dev ACC: 74.427
01/08/2021 08:05:57 [new test scores saved.]
01/08/2021 08:06:21 Task mnli_mismatched -- epoch 8 -- Dev ACC: 75.031
01/08/2021 08:06:45 [new test scores saved.]
01/08/2021 08:06:46 Task rte -- epoch 8 -- Dev ACC: 67.148
01/08/2021 08:06:56 [new test scores saved.]
01/08/2021 08:08:19 Task qqp -- epoch 8 -- Dev ACC: 82.075
01/08/2021 08:08:19 Task qqp -- epoch 8 -- Dev F1: 76.022
01/08/2021 08:21:56 [new test scores saved.]
01/08/2021 08:22:11 Task qnli -- epoch 8 -- Dev ACC: 78.611
01/08/2021 08:22:28 [new test scores saved.]
01/08/2021 08:22:29 Task mrpc -- epoch 8 -- Dev ACC: 72.304
01/08/2021 08:22:29 Task mrpc -- epoch 8 -- Dev F1: 80.279
01/08/2021 08:22:34 [new test scores saved.]
01/08/2021 08:22:35 Task sst -- epoch 8 -- Dev ACC: 85.321
01/08/2021 08:22:39 [new test scores saved.]
01/08/2021 08:22:40 Task cola -- epoch 8 -- Dev ACC: 73.442
01/08/2021 08:22:40 Task cola -- epoch 8 -- Dev MCC: 29.730
01/08/2021 08:22:42 [new test scores saved.]
01/08/2021 08:22:45 Task stsb -- epoch 8 -- Dev Pearson: 68.217
01/08/2021 08:22:45 Task stsb -- epoch 8 -- Dev Spearman: 70.234
01/08/2021 08:22:48 [new test scores saved.]
01/08/2021 08:22:53 At epoch 9
01/08/2021 08:23:38 Task [ 3] updates[ 54000] train loss[0.25818] remaining[0:10:53]
01/08/2021 08:24:36 Task [ 0] updates[ 54500] train loss[0.25650] remaining[0:09:50]
01/08/2021 08:25:35 Task [ 2] updates[ 55000] train loss[0.25479] remaining[0:08:56]
01/08/2021 08:26:35 Task [ 0] updates[ 55500] train loss[0.25301] remaining[0:07:58]
01/08/2021 08:27:30 Task [ 0] updates[ 56000] train loss[0.25122] remaining[0:06:55]
01/08/2021 08:28:30 Task [ 5] updates[ 56500] train loss[0.24956] remaining[0:05:58]
01/08/2021 08:29:28 Task [ 2] updates[ 57000] train loss[0.24791] remaining[0:05:00]
01/08/2021 08:30:27 Task [ 2] updates[ 57500] train loss[0.24626] remaining[0:04:02]
01/08/2021 08:31:25 Task [ 2] updates[ 58000] train loss[0.24462] remaining[0:03:03]
01/08/2021 08:32:24 Task [ 2] updates[ 58500] train loss[0.24303] remaining[0:02:05]
01/08/2021 08:33:24 Task [ 2] updates[ 59000] train loss[0.24154] remaining[0:01:06]
01/08/2021 08:34:22 Task [ 2] updates[ 59500] train loss[0.24001] remaining[0:00:08]
01/08/2021 08:34:54 Task mnli_matched -- epoch 9 -- Dev ACC: 74.325
01/08/2021 08:35:17 [new test scores saved.]
01/08/2021 08:35:42 Task mnli_mismatched -- epoch 9 -- Dev ACC: 75.112
01/08/2021 08:36:06 [new test scores saved.]
01/08/2021 08:36:07 Task rte -- epoch 9 -- Dev ACC: 67.870
01/08/2021 08:36:16 [new test scores saved.]
01/08/2021 08:37:40 Task qqp -- epoch 9 -- Dev ACC: 81.905
01/08/2021 08:37:40 Task qqp -- epoch 9 -- Dev F1: 76.482
01/08/2021 08:51:17 [new test scores saved.]
01/08/2021 08:51:32 Task qnli -- epoch 9 -- Dev ACC: 78.611
01/08/2021 08:51:49 [new test scores saved.]
01/08/2021 08:51:50 Task mrpc -- epoch 9 -- Dev ACC: 72.304
01/08/2021 08:51:50 Task mrpc -- epoch 9 -- Dev F1: 80.684
01/08/2021 08:51:54 [new test scores saved.]
01/08/2021 08:51:55 Task sst -- epoch 9 -- Dev ACC: 85.780
01/08/2021 08:51:59 [new test scores saved.]
01/08/2021 08:52:00 Task cola -- epoch 9 -- Dev ACC: 74.305
01/08/2021 08:52:00 Task cola -- epoch 9 -- Dev MCC: 32.637
01/08/2021 08:52:02 [new test scores saved.]
01/08/2021 08:52:05 Task stsb -- epoch 9 -- Dev Pearson: 68.283
01/08/2021 08:52:05 Task stsb -- epoch 9 -- Dev Spearman: 70.323
01/08/2021 08:52:08 [new test scores saved.]