jdorairaj
/

Adapters_run2

Model card Files Files and versions Community

jdorairaj commited on Jun 1, 2024

Commit

6482a6b

1 Parent(s): d404cc0

adaptors run

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/args.json +33 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/cola_bert-base-uncased_train_loss.png +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/cola_bert-base-uncased_validation_loss.png +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/logfile.log +205 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/adapter_config.json +41 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/all_results.json +1 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/all_results_val.json +1 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/eval_res.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/gpu_stats.json +130 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/head_config.json +21 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/pytorch_adapter.bin +3 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/pytorch_model_head.bin +3 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/special_tokens_map.json +7 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/tokenizer.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/tokenizer_config.json +56 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/val_res.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/vocab.txt +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/adapter_config.json +41 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/all_results.json +1 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/all_results_val.json +1 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/eval_res.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/gpu_stats.json +130 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/head_config.json +21 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/pytorch_adapter.bin +3 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/pytorch_model_head.bin +3 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/special_tokens_map.json +7 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/tokenizer.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/tokenizer_config.json +56 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/val_res.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/vocab.txt +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/adapter_config.json +41 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/all_results.json +1 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/all_results_val.json +1 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/eval_res.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/gpu_stats.json +130 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/head_config.json +21 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/pytorch_adapter.bin +3 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/pytorch_model_head.bin +3 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/special_tokens_map.json +7 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/tokenizer.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/tokenizer_config.json +56 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/val_res.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/vocab.txt +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/adapter_config.json +41 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/all_results.json +1 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/all_results_val.json +1 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/eval_res.json +0 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/gpu_stats.json +130 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/head_config.json +21 -0
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/pytorch_adapter.bin +3 -0

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/args.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+    "task_name": "cola",
+    "train_file": null,
+    "validation_file": null,
+    "max_length": 300,
+    "pad_to_max_length": false,
+    "model_name_or_path": "bert-base-uncased",
+    "use_slow_tokenizer": false,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": 8,
+    "learning_rate": 0.0001,
+    "max_grad_norm": 0.5,
+    "weight_decay": 0.0,
+    "num_train_epochs": 3,
+    "max_train_steps": 10000,
+    "gradient_accumulation_steps": 1,
+    "lr_scheduler_type": "linear",
+    "num_warmup_steps": 0,
+    "output_dir": "./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000",
+    "seed": 12345,
+    "push_to_hub": false,
+    "hub_model_id": null,
+    "hub_token": null,
+    "checkpointing_steps": "2500",
+    "resume_from_checkpoint": null,
+    "with_tracking": false,
+    "report_to": "all",
+    "ignore_mismatched_sizes": true,
+    "save_train_results": false,
+    "testing_set": "train_val",
+    "lm_head": true,
+    "leave_out": null
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/cola_bert-base-uncased_train_loss.png ADDED Viewed

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/cola_bert-base-uncased_validation_loss.png ADDED Viewed

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/logfile.log ADDED Viewed

	@@ -0,0 +1,205 @@

+06/01/2024 01:12:39 - INFO - __main__ -  Number of labels detected = 2
+06/01/2024 01:12:48 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
+06/01/2024 01:12:49 - INFO - __main__ -  Number of labels detected = 2
+06/01/2024 01:12:49 - INFO - adapters.heads.model_mixin - Adding head 'cola' with config {'head_type': 'classification', 'num_labels': 2, 'layers': 2, 'activation_function': 'tanh', 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'use_pooler': False, 'bias': True, 'dropout_prob': None}.
+06/01/2024 01:12:49 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
+06/01/2024 01:12:49 - INFO - __main__ - ================================================================================
+Name                     Architecture         #Param      %Param  Active   Train
+--------------------------------------------------------------------------------
+cola                     bottleneck        1,789,056       1.634       1       1
+--------------------------------------------------------------------------------
+Full model                               109,482,240     100.000               0
+================================================================================
+06/01/2024 01:12:49 - INFO - __main__ - printing model
+06/01/2024 01:12:49 - INFO - __main__ - BertAdapterModel(
+  (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(
+        (0-11): 12 x BertLayer(
+          (attention): BertAttention(
+            (self): BertSelfAttentionWithAdapters(
+              (query): LoRALinearTorch(
+                in_features=768, out_features=768, bias=True
+                (loras): ModuleDict()
+              )
+              (key): LoRALinearTorch(
+                in_features=768, out_features=768, bias=True
+                (loras): ModuleDict()
+              )
+              (value): LoRALinearTorch(
+                in_features=768, out_features=768, bias=True
+                (loras): ModuleDict()
+              )
+              (dropout): Dropout(p=0.1, inplace=False)
+              (prefix_tuning): PrefixTuningLayer(
+                (prefix_gates): ModuleDict()
+                (pool): PrefixTuningPool(
+                  (prefix_tunings): ModuleDict()
+                )
+              )
+            )
+            (output): BertSelfOutputWithAdapters(
+              (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)
+              (adapters): ModuleDict(
+                (cola): Adapter(
+                  (non_linearity): Activation_Function_Class(
+                    (f): SiLU()
+                  )
+                  (adapter_down): Sequential(
+                    (0): Linear(in_features=768, out_features=48, bias=True)
+                    (1): Activation_Function_Class(
+                      (f): SiLU()
+                    )
+                  )
+                  (adapter_up): Linear(in_features=48, out_features=768, bias=True)
+                  (dropout): Dropout(p=0.0, inplace=False)
+                )
+              )
+              (adapter_fusion_layer): ModuleDict()
+            )
+          )
+          (intermediate): BertIntermediate(
+            (dense): LoRALinearTorch(
+              in_features=768, out_features=3072, bias=True
+              (loras): ModuleDict()
+            )
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): BertOutputWithAdapters(
+            (dense): LoRALinearTorch(
+              in_features=3072, out_features=768, bias=True
+              (loras): ModuleDict()
+            )
+            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+            (dropout): Dropout(p=0.1, inplace=False)
+            (adapters): ModuleDict(
+              (cola): Adapter(
+                (non_linearity): Activation_Function_Class(
+                  (f): SiLU()
+                )
+                (adapter_down): Sequential(
+                  (0): Linear(in_features=768, out_features=48, bias=True)
+                  (1): Activation_Function_Class(
+                    (f): SiLU()
+                  )
+                )
+                (adapter_up): Linear(in_features=48, out_features=768, bias=True)
+                (dropout): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (adapter_fusion_layer): ModuleDict()
+          )
+        )
+      )
+    )
+    (pooler): BertPooler(
+      (dense): Linear(in_features=768, out_features=768, bias=True)
+      (activation): Tanh()
+    )
+    (invertible_adapters): ModuleDict()
+    (shared_parameters): ModuleDict()
+    (prefix_tuning): PrefixTuningPool(
+      (prefix_tunings): ModuleDict()
+    )
+    (prompt_tuning): PromptTuningLayer(
+      (base_model_embeddings): Embedding(30522, 768, padding_idx=0)
+      (prompt_tunings): ModuleDict()
+    )
+  )
+  (heads): ModuleDict(
+    (default): BertStyleMaskedLMHead(
+      (0): Linear(in_features=768, out_features=768, bias=True)
+      (1): Activation_Function_Class(
+        (f): GELUActivation()
+      )
+      (2): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+      (3): Linear(in_features=768, out_features=30522, bias=True)
+    )
+    (cola): ClassificationHead(
+      (0): Dropout(p=0.1, inplace=False)
+      (1): Linear(in_features=768, out_features=768, bias=True)
+      (2): Activation_Function_Class(
+        (f): Tanh()
+      )
+      (3): Dropout(p=0.1, inplace=False)
+      (4): Linear(in_features=768, out_features=2, bias=True)
+    )
+  )
+)
+06/01/2024 01:12:50 - INFO - __main__ - Sample 3412 of the training set: {'input_ids': [101, 1045, 12781, 1996, 7427, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+06/01/2024 01:12:50 - INFO - __main__ - Sample 6002 of the training set: {'input_ids': [101, 1045, 2442, 2064, 4521, 22088, 2015, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+06/01/2024 01:12:50 - INFO - __main__ - Sample 83 of the training set: {'input_ids': [101, 1996, 7764, 22257, 2993, 2000, 1996, 2598, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+06/01/2024 01:12:50 - INFO - __main__ -  Max training steps before recalculation = 10000
+06/01/2024 01:12:50 - INFO - __main__ -  num_update_steps_per_epoch initial = 855
+06/01/2024 01:12:50 - INFO - __main__ -  num training epochs initial = 3
+06/01/2024 01:12:50 - INFO - __main__ - Adjusted num_train_epochs based on max_train_steps: 3
+06/01/2024 01:12:50 - INFO - __main__ -  num_update_steps_per_epoch before recalculation = 855
+06/01/2024 01:12:50 - INFO - __main__ -  num_update_steps_per_epoch after recalculation = 855
+06/01/2024 01:12:50 - INFO - __main__ -  num training epochs before recalculation = 12
+06/01/2024 01:12:52 - INFO - __main__ - ***** Running training *****
+06/01/2024 01:12:52 - INFO - __main__ -   Num examples = 6840
+06/01/2024 01:12:52 - INFO - __main__ -   Num Epochs = 12
+06/01/2024 01:12:52 - INFO - __main__ -   Instantaneous batch size per device = 8
+06/01/2024 01:12:52 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 8
+06/01/2024 01:12:52 - INFO - __main__ -   Gradient Accumulation steps = 1
+06/01/2024 01:12:52 - INFO - __main__ -   Total optimization steps = 10000
+06/01/2024 01:12:56 - INFO - __main__ - epoch 0: {'matthews_correlation': -0.02929206145132745}
+06/01/2024 01:12:56 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/adapter_config.json
+06/01/2024 01:12:56 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/pytorch_adapter.bin
+06/01/2024 01:12:56 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/head_config.json
+06/01/2024 01:12:56 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/pytorch_model_head.bin
+06/01/2024 01:13:02 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.0}
+06/01/2024 01:13:02 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/adapter_config.json
+06/01/2024 01:13:02 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/pytorch_adapter.bin
+06/01/2024 01:13:02 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/head_config.json
+06/01/2024 01:13:02 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/pytorch_model_head.bin
+06/01/2024 01:15:18 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.5327292010480984}
+06/01/2024 01:15:18 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/adapter_config.json
+06/01/2024 01:15:18 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/pytorch_adapter.bin
+06/01/2024 01:15:18 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/head_config.json
+06/01/2024 01:15:18 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/pytorch_model_head.bin
+06/01/2024 01:15:25 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.5129119173777361}
+06/01/2024 01:15:25 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/adapter_config.json
+06/01/2024 01:15:25 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/pytorch_adapter.bin
+06/01/2024 01:15:25 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/head_config.json
+06/01/2024 01:15:25 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/pytorch_model_head.bin
+06/01/2024 01:17:40 - INFO - __main__ - epoch 5: {'matthews_correlation': 0.5377587696044389}
+06/01/2024 01:17:40 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/adapter_config.json
+06/01/2024 01:17:40 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/pytorch_adapter.bin
+06/01/2024 01:17:40 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/head_config.json
+06/01/2024 01:17:40 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/pytorch_model_head.bin
+06/01/2024 01:17:46 - INFO - __main__ - epoch 5: {'matthews_correlation': 0.5382301098911769}
+06/01/2024 01:17:46 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/adapter_config.json
+06/01/2024 01:17:46 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/pytorch_adapter.bin
+06/01/2024 01:17:46 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/head_config.json
+06/01/2024 01:17:46 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/pytorch_model_head.bin
+06/01/2024 01:20:03 - INFO - __main__ - epoch 8: {'matthews_correlation': 0.5454001814167142}
+06/01/2024 01:20:03 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/adapter_config.json
+06/01/2024 01:20:03 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/pytorch_adapter.bin
+06/01/2024 01:20:03 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/head_config.json
+06/01/2024 01:20:03 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/pytorch_model_head.bin
+06/01/2024 01:20:09 - INFO - __main__ - epoch 8: {'matthews_correlation': 0.5577556248606417}
+06/01/2024 01:20:09 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/adapter_config.json
+06/01/2024 01:20:09 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/pytorch_adapter.bin
+06/01/2024 01:20:09 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/head_config.json
+06/01/2024 01:20:09 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/pytorch_model_head.bin
+06/01/2024 01:22:28 - INFO - __main__ - epoch 11: {'matthews_correlation': 0.5332198659134496}
+06/01/2024 01:22:28 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_9999/adapter_config.json
+06/01/2024 01:22:28 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_9999/pytorch_adapter.bin
+06/01/2024 01:22:28 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_9999/head_config.json
+06/01/2024 01:22:28 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_9999/pytorch_model_head.bin
+06/01/2024 01:22:34 - INFO - __main__ - epoch 11: {'matthews_correlation': 0.5514570047640966}
+06/01/2024 01:22:34 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_9999/adapter_config.json
+06/01/2024 01:22:35 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_9999/pytorch_adapter.bin
+06/01/2024 01:22:35 - INFO - adapters.loading - Configuration saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_9999/head_config.json
+06/01/2024 01:22:35 - INFO - adapters.loading - Module weights saved in ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_9999/pytorch_model_head.bin
+06/01/2024 01:22:35 - INFO - __main__ - ***** Completed training *****

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/adapter_config.json ADDED Viewed

	@@ -0,0 +1,41 @@

+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": true,
+    "non_linearity": "swish",
+    "original_ln_after": true,
+    "original_ln_before": false,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.1"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/all_results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": -0.02929206145132745}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/all_results_val.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.0}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/eval_res.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/gpu_stats.json ADDED Viewed

	@@ -0,0 +1,130 @@

+{
+    "memory_allocated": 459623936,
+    "max_memory_allocated": 471682048,
+    "memory_reserved": 532676608,
+    "max_memory_reserved": 532676608,
+    "memory_stats": {
+        "active.all.allocated": 229718,
+        "active.all.current": 319,
+        "active.all.freed": 229399,
+        "active.all.peak": 337,
+        "active.large_pool.allocated": 7614,
+        "active.large_pool.current": 78,
+        "active.large_pool.freed": 7536,
+        "active.large_pool.peak": 80,
+        "active.small_pool.allocated": 222104,
+        "active.small_pool.current": 241,
+        "active.small_pool.freed": 221863,
+        "active.small_pool.peak": 259,
+        "active_bytes.all.allocated": 104486025728,
+        "active_bytes.all.current": 459623936,
+        "active_bytes.all.freed": 104026401792,
+        "active_bytes.all.peak": 471682048,
+        "active_bytes.large_pool.allocated": 16832397312,
+        "active_bytes.large_pool.current": 451805184,
+        "active_bytes.large_pool.freed": 16380592128,
+        "active_bytes.large_pool.peak": 458686464,
+        "active_bytes.small_pool.allocated": 87653628416,
+        "active_bytes.small_pool.current": 7818752,
+        "active_bytes.small_pool.freed": 87645809664,
+        "active_bytes.small_pool.peak": 16436224,
+        "allocated_bytes.all.allocated": 104486025728,
+        "allocated_bytes.all.current": 459623936,
+        "allocated_bytes.all.freed": 104026401792,
+        "allocated_bytes.all.peak": 471682048,
+        "allocated_bytes.large_pool.allocated": 16832397312,
+        "allocated_bytes.large_pool.current": 451805184,
+        "allocated_bytes.large_pool.freed": 16380592128,
+        "allocated_bytes.large_pool.peak": 458686464,
+        "allocated_bytes.small_pool.allocated": 87653628416,
+        "allocated_bytes.small_pool.current": 7818752,
+        "allocated_bytes.small_pool.freed": 87645809664,
+        "allocated_bytes.small_pool.peak": 16436224,
+        "allocation.all.allocated": 229718,
+        "allocation.all.current": 319,
+        "allocation.all.freed": 229399,
+        "allocation.all.peak": 337,
+        "allocation.large_pool.allocated": 7614,
+        "allocation.large_pool.current": 78,
+        "allocation.large_pool.freed": 7536,
+        "allocation.large_pool.peak": 80,
+        "allocation.small_pool.allocated": 222104,
+        "allocation.small_pool.current": 241,
+        "allocation.small_pool.freed": 221863,
+        "allocation.small_pool.peak": 259,
+        "inactive_split.all.allocated": 110877,
+        "inactive_split.all.current": 23,
+        "inactive_split.all.freed": 110854,
+        "inactive_split.all.peak": 34,
+        "inactive_split.large_pool.allocated": 7159,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 7141,
+        "inactive_split.large_pool.peak": 19,
+        "inactive_split.small_pool.allocated": 103718,
+        "inactive_split.small_pool.current": 5,
+        "inactive_split.small_pool.freed": 103713,
+        "inactive_split.small_pool.peak": 15,
+        "inactive_split_bytes.all.allocated": 111369324032,
+        "inactive_split_bytes.all.current": 43692544,
+        "inactive_split_bytes.all.freed": 111325631488,
+        "inactive_split_bytes.all.peak": 67346432,
+        "inactive_split_bytes.large_pool.allocated": 18599641088,
+        "inactive_split_bytes.large_pool.current": 41025536,
+        "inactive_split_bytes.large_pool.freed": 18558615552,
+        "inactive_split_bytes.large_pool.peak": 59146240,
+        "inactive_split_bytes.small_pool.allocated": 92769682944,
+        "inactive_split_bytes.small_pool.current": 2667008,
+        "inactive_split_bytes.small_pool.freed": 92767015936,
+        "inactive_split_bytes.small_pool.peak": 8200192,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 30,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 100127988300,
+        "requested_bytes.all.current": 458479208,
+        "requested_bytes.all.freed": 99669509092,
+        "requested_bytes.all.peak": 470535000,
+        "requested_bytes.large_pool.allocated": 12486326272,
+        "requested_bytes.large_pool.current": 450672640,
+        "requested_bytes.large_pool.freed": 12035653632,
+        "requested_bytes.large_pool.peak": 457553920,
+        "requested_bytes.small_pool.allocated": 87641662028,
+        "requested_bytes.small_pool.current": 7806568,
+        "requested_bytes.small_pool.freed": 87633855460,
+        "requested_bytes.small_pool.peak": 16421720,
+        "reserved_bytes.all.allocated": 532676608,
+        "reserved_bytes.all.current": 532676608,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 532676608,
+        "reserved_bytes.large_pool.allocated": 513802240,
+        "reserved_bytes.large_pool.current": 513802240,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 513802240,
+        "reserved_bytes.small_pool.allocated": 18874368,
+        "reserved_bytes.small_pool.current": 18874368,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 18874368,
+        "segment.all.allocated": 30,
+        "segment.all.current": 30,
+        "segment.all.freed": 0,
+        "segment.all.peak": 30,
+        "segment.large_pool.allocated": 21,
+        "segment.large_pool.current": 21,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 21,
+        "segment.small_pool.allocated": 9,
+        "segment.small_pool.current": 9,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 9
+    }
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/head_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.1"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/pytorch_adapter.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:29b06f7b9617fec3c5bc63794ca9c89f4238d46db9edb1de32e4dd4e5086fae0
+size 7191062

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/pytorch_model_head.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:244a549f85f7dcaa9f5082c6ca9f115dff60bbcbbd8534f0a78f92ef9b70720d
+size 2370664

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/val_res.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_0/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/adapter_config.json ADDED Viewed

	@@ -0,0 +1,41 @@

+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": true,
+    "non_linearity": "swish",
+    "original_ln_after": true,
+    "original_ln_before": false,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.1"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/all_results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.5327292010480984}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/all_results_val.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.5129119173777361}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/eval_res.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/gpu_stats.json ADDED Viewed

	@@ -0,0 +1,130 @@

+{
+    "memory_allocated": 487207936,
+    "max_memory_allocated": 699914240,
+    "memory_reserved": 805306368,
+    "max_memory_reserved": 805306368,
+    "memory_stats": {
+        "active.all.allocated": 3730517,
+        "active.all.current": 520,
+        "active.all.freed": 3729997,
+        "active.all.peak": 777,
+        "active.large_pool.allocated": 141558,
+        "active.large_pool.current": 81,
+        "active.large_pool.freed": 141477,
+        "active.large_pool.peak": 183,
+        "active.small_pool.allocated": 3588959,
+        "active.small_pool.current": 439,
+        "active.small_pool.freed": 3588520,
+        "active.small_pool.peak": 696,
+        "active_bytes.all.allocated": 1562416010752,
+        "active_bytes.all.current": 487207936,
+        "active_bytes.all.freed": 1561928802816,
+        "active_bytes.all.peak": 699914240,
+        "active_bytes.large_pool.allocated": 312991645696,
+        "active_bytes.large_pool.current": 465043456,
+        "active_bytes.large_pool.freed": 312526602240,
+        "active_bytes.large_pool.peak": 646561792,
+        "active_bytes.small_pool.allocated": 1249424365056,
+        "active_bytes.small_pool.current": 22164480,
+        "active_bytes.small_pool.freed": 1249402200576,
+        "active_bytes.small_pool.peak": 133540864,
+        "allocated_bytes.all.allocated": 1562416010752,
+        "allocated_bytes.all.current": 487207936,
+        "allocated_bytes.all.freed": 1561928802816,
+        "allocated_bytes.all.peak": 699914240,
+        "allocated_bytes.large_pool.allocated": 312991645696,
+        "allocated_bytes.large_pool.current": 465043456,
+        "allocated_bytes.large_pool.freed": 312526602240,
+        "allocated_bytes.large_pool.peak": 646561792,
+        "allocated_bytes.small_pool.allocated": 1249424365056,
+        "allocated_bytes.small_pool.current": 22164480,
+        "allocated_bytes.small_pool.freed": 1249402200576,
+        "allocated_bytes.small_pool.peak": 133540864,
+        "allocation.all.allocated": 3730517,
+        "allocation.all.current": 520,
+        "allocation.all.freed": 3729997,
+        "allocation.all.peak": 777,
+        "allocation.large_pool.allocated": 141558,
+        "allocation.large_pool.current": 81,
+        "allocation.large_pool.freed": 141477,
+        "allocation.large_pool.peak": 183,
+        "allocation.small_pool.allocated": 3588959,
+        "allocation.small_pool.current": 439,
+        "allocation.small_pool.freed": 3588520,
+        "allocation.small_pool.peak": 696,
+        "inactive_split.all.allocated": 2037607,
+        "inactive_split.all.current": 46,
+        "inactive_split.all.freed": 2037561,
+        "inactive_split.all.peak": 119,
+        "inactive_split.large_pool.allocated": 120406,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 120387,
+        "inactive_split.large_pool.peak": 23,
+        "inactive_split.small_pool.allocated": 1917201,
+        "inactive_split.small_pool.current": 27,
+        "inactive_split.small_pool.freed": 1917174,
+        "inactive_split.small_pool.peak": 99,
+        "inactive_split_bytes.all.allocated": 1674415169536,
+        "inactive_split_bytes.all.current": 60148736,
+        "inactive_split_bytes.all.freed": 1674355020800,
+        "inactive_split_bytes.all.peak": 149930496,
+        "inactive_split_bytes.large_pool.allocated": 355511451648,
+        "inactive_split_bytes.large_pool.current": 48758784,
+        "inactive_split_bytes.large_pool.freed": 355462692864,
+        "inactive_split_bytes.large_pool.peak": 75759616,
+        "inactive_split_bytes.small_pool.allocated": 1318903717888,
+        "inactive_split_bytes.small_pool.current": 11389952,
+        "inactive_split_bytes.small_pool.freed": 1318892327936,
+        "inactive_split_bytes.small_pool.peak": 82985472,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 97,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 1505878546100,
+        "requested_bytes.all.current": 486046648,
+        "requested_bytes.all.freed": 1505392499452,
+        "requested_bytes.all.peak": 680092736,
+        "requested_bytes.large_pool.allocated": 256608180224,
+        "requested_bytes.large_pool.current": 463910912,
+        "requested_bytes.large_pool.freed": 256144269312,
+        "requested_bytes.large_pool.peak": 626776064,
+        "requested_bytes.small_pool.allocated": 1249270365876,
+        "requested_bytes.small_pool.current": 22135736,
+        "requested_bytes.small_pool.freed": 1249248230140,
+        "requested_bytes.small_pool.peak": 133501696,
+        "reserved_bytes.all.allocated": 805306368,
+        "reserved_bytes.all.current": 805306368,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 805306368,
+        "reserved_bytes.large_pool.allocated": 660602880,
+        "reserved_bytes.large_pool.current": 660602880,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 660602880,
+        "reserved_bytes.small_pool.allocated": 144703488,
+        "reserved_bytes.small_pool.current": 144703488,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 144703488,
+        "segment.all.allocated": 97,
+        "segment.all.current": 97,
+        "segment.all.freed": 0,
+        "segment.all.peak": 97,
+        "segment.large_pool.allocated": 28,
+        "segment.large_pool.current": 28,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 28,
+        "segment.small_pool.allocated": 69,
+        "segment.small_pool.current": 69,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 69
+    }
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/head_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.1"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/pytorch_adapter.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5134ca3cfee61e335e337783a5876ed9cd5b576708a1d9bb7e6304ea56fda07e
+size 7191062

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/pytorch_model_head.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a7ac05ba10838b335682f54ec38f45f5cbdd8c34f16fddf95ab0e3c27b6e12
+size 2370664

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/val_res.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_2499/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/adapter_config.json ADDED Viewed

	@@ -0,0 +1,41 @@

+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": true,
+    "non_linearity": "swish",
+    "original_ln_after": true,
+    "original_ln_before": false,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.1"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/all_results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.5377587696044389}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/all_results_val.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.5382301098911769}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/eval_res.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/gpu_stats.json ADDED Viewed

	@@ -0,0 +1,130 @@

+{
+    "memory_allocated": 487209472,
+    "max_memory_allocated": 699914240,
+    "memory_reserved": 805306368,
+    "max_memory_reserved": 805306368,
+    "memory_stats": {
+        "active.all.allocated": 7232424,
+        "active.all.current": 520,
+        "active.all.freed": 7231904,
+        "active.all.peak": 777,
+        "active.large_pool.allocated": 275501,
+        "active.large_pool.current": 81,
+        "active.large_pool.freed": 275420,
+        "active.large_pool.peak": 183,
+        "active.small_pool.allocated": 6956923,
+        "active.small_pool.current": 439,
+        "active.small_pool.freed": 6956484,
+        "active.small_pool.peak": 696,
+        "active_bytes.all.allocated": 3019362437632,
+        "active_bytes.all.current": 487209472,
+        "active_bytes.all.freed": 3018875228160,
+        "active_bytes.all.peak": 699914240,
+        "active_bytes.large_pool.allocated": 608966467584,
+        "active_bytes.large_pool.current": 465043456,
+        "active_bytes.large_pool.freed": 608501424128,
+        "active_bytes.large_pool.peak": 646561792,
+        "active_bytes.small_pool.allocated": 2410395970048,
+        "active_bytes.small_pool.current": 22166016,
+        "active_bytes.small_pool.freed": 2410373804032,
+        "active_bytes.small_pool.peak": 133540864,
+        "allocated_bytes.all.allocated": 3019362437632,
+        "allocated_bytes.all.current": 487209472,
+        "allocated_bytes.all.freed": 3018875228160,
+        "allocated_bytes.all.peak": 699914240,
+        "allocated_bytes.large_pool.allocated": 608966467584,
+        "allocated_bytes.large_pool.current": 465043456,
+        "allocated_bytes.large_pool.freed": 608501424128,
+        "allocated_bytes.large_pool.peak": 646561792,
+        "allocated_bytes.small_pool.allocated": 2410395970048,
+        "allocated_bytes.small_pool.current": 22166016,
+        "allocated_bytes.small_pool.freed": 2410373804032,
+        "allocated_bytes.small_pool.peak": 133540864,
+        "allocation.all.allocated": 7232424,
+        "allocation.all.current": 520,
+        "allocation.all.freed": 7231904,
+        "allocation.all.peak": 777,
+        "allocation.large_pool.allocated": 275501,
+        "allocation.large_pool.current": 81,
+        "allocation.large_pool.freed": 275420,
+        "allocation.large_pool.peak": 183,
+        "allocation.small_pool.allocated": 6956923,
+        "allocation.small_pool.current": 439,
+        "allocation.small_pool.freed": 6956484,
+        "allocation.small_pool.peak": 696,
+        "inactive_split.all.allocated": 3951350,
+        "inactive_split.all.current": 47,
+        "inactive_split.all.freed": 3951303,
+        "inactive_split.all.peak": 123,
+        "inactive_split.large_pool.allocated": 233878,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 233859,
+        "inactive_split.large_pool.peak": 23,
+        "inactive_split.small_pool.allocated": 3717472,
+        "inactive_split.small_pool.current": 28,
+        "inactive_split.small_pool.freed": 3717444,
+        "inactive_split.small_pool.peak": 103,
+        "inactive_split_bytes.all.allocated": 3236389921280,
+        "inactive_split_bytes.all.current": 60147200,
+        "inactive_split_bytes.all.freed": 3236329774080,
+        "inactive_split_bytes.all.peak": 149930496,
+        "inactive_split_bytes.large_pool.allocated": 691809476608,
+        "inactive_split_bytes.large_pool.current": 48758784,
+        "inactive_split_bytes.large_pool.freed": 691760717824,
+        "inactive_split_bytes.large_pool.peak": 75759616,
+        "inactive_split_bytes.small_pool.allocated": 2544580444672,
+        "inactive_split_bytes.small_pool.current": 11388416,
+        "inactive_split_bytes.small_pool.freed": 2544569056256,
+        "inactive_split_bytes.small_pool.peak": 82985472,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 97,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 2910500708864,
+        "requested_bytes.all.current": 486047224,
+        "requested_bytes.all.freed": 2910014661640,
+        "requested_bytes.all.peak": 680092736,
+        "requested_bytes.large_pool.allocated": 500400650240,
+        "requested_bytes.large_pool.current": 463910912,
+        "requested_bytes.large_pool.freed": 499936739328,
+        "requested_bytes.large_pool.peak": 626776064,
+        "requested_bytes.small_pool.allocated": 2410100058624,
+        "requested_bytes.small_pool.current": 22136312,
+        "requested_bytes.small_pool.freed": 2410077922312,
+        "requested_bytes.small_pool.peak": 133501696,
+        "reserved_bytes.all.allocated": 805306368,
+        "reserved_bytes.all.current": 805306368,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 805306368,
+        "reserved_bytes.large_pool.allocated": 660602880,
+        "reserved_bytes.large_pool.current": 660602880,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 660602880,
+        "reserved_bytes.small_pool.allocated": 144703488,
+        "reserved_bytes.small_pool.current": 144703488,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 144703488,
+        "segment.all.allocated": 97,
+        "segment.all.current": 97,
+        "segment.all.freed": 0,
+        "segment.all.peak": 97,
+        "segment.large_pool.allocated": 28,
+        "segment.large_pool.current": 28,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 28,
+        "segment.small_pool.allocated": 69,
+        "segment.small_pool.current": 69,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 69
+    }
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/head_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.1"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/pytorch_adapter.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f127b13ca20b0cf79fa5e76a4b6f405d1af714f891fabec3ca17cc21a8de33b8
+size 7191062

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/pytorch_model_head.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:01f84aeff68abbfe48604e91ae608be12d5470e40b4bfa6e4c790ec9ec58e932
+size 2370664

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/val_res.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_4999/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/adapter_config.json ADDED Viewed

	@@ -0,0 +1,41 @@

+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": true,
+    "non_linearity": "swish",
+    "original_ln_after": true,
+    "original_ln_before": false,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.1"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/all_results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.5454001814167142}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/all_results_val.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.5577556248606417}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/eval_res.json ADDED Viewed

The diff for this file is too large to render. See raw diff

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/gpu_stats.json ADDED Viewed

	@@ -0,0 +1,130 @@

+{
+    "memory_allocated": 487207936,
+    "max_memory_allocated": 699914240,
+    "memory_reserved": 805306368,
+    "max_memory_reserved": 805306368,
+    "memory_stats": {
+        "active.all.allocated": 10734331,
+        "active.all.current": 520,
+        "active.all.freed": 10733811,
+        "active.all.peak": 777,
+        "active.large_pool.allocated": 409252,
+        "active.large_pool.current": 81,
+        "active.large_pool.freed": 409171,
+        "active.large_pool.peak": 183,
+        "active.small_pool.allocated": 10325079,
+        "active.small_pool.current": 439,
+        "active.small_pool.freed": 10324640,
+        "active.small_pool.peak": 696,
+        "active_bytes.all.allocated": 4478907381248,
+        "active_bytes.all.current": 487207936,
+        "active_bytes.all.freed": 4478420173312,
+        "active_bytes.all.peak": 699914240,
+        "active_bytes.large_pool.allocated": 904929984512,
+        "active_bytes.large_pool.current": 465043456,
+        "active_bytes.large_pool.freed": 904464941056,
+        "active_bytes.large_pool.peak": 646561792,
+        "active_bytes.small_pool.allocated": 3573977396736,
+        "active_bytes.small_pool.current": 22164480,
+        "active_bytes.small_pool.freed": 3573955232256,
+        "active_bytes.small_pool.peak": 133540864,
+        "allocated_bytes.all.allocated": 4478907381248,
+        "allocated_bytes.all.current": 487207936,
+        "allocated_bytes.all.freed": 4478420173312,
+        "allocated_bytes.all.peak": 699914240,
+        "allocated_bytes.large_pool.allocated": 904929984512,
+        "allocated_bytes.large_pool.current": 465043456,
+        "allocated_bytes.large_pool.freed": 904464941056,
+        "allocated_bytes.large_pool.peak": 646561792,
+        "allocated_bytes.small_pool.allocated": 3573977396736,
+        "allocated_bytes.small_pool.current": 22164480,
+        "allocated_bytes.small_pool.freed": 3573955232256,
+        "allocated_bytes.small_pool.peak": 133540864,
+        "allocation.all.allocated": 10734331,
+        "allocation.all.current": 520,
+        "allocation.all.freed": 10733811,
+        "allocation.all.peak": 777,
+        "allocation.large_pool.allocated": 409252,
+        "allocation.large_pool.current": 81,
+        "allocation.large_pool.freed": 409171,
+        "allocation.large_pool.peak": 183,
+        "allocation.small_pool.allocated": 10325079,
+        "allocation.small_pool.current": 439,
+        "allocation.small_pool.freed": 10324640,
+        "allocation.small_pool.peak": 696,
+        "inactive_split.all.allocated": 5866511,
+        "inactive_split.all.current": 48,
+        "inactive_split.all.freed": 5866463,
+        "inactive_split.all.peak": 123,
+        "inactive_split.large_pool.allocated": 347016,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 346997,
+        "inactive_split.large_pool.peak": 23,
+        "inactive_split.small_pool.allocated": 5519495,
+        "inactive_split.small_pool.current": 29,
+        "inactive_split.small_pool.freed": 5519466,
+        "inactive_split.small_pool.peak": 103,
+        "inactive_split_bytes.all.allocated": 4801769484800,
+        "inactive_split_bytes.all.current": 60148736,
+        "inactive_split_bytes.all.freed": 4801709336064,
+        "inactive_split_bytes.all.peak": 149930496,
+        "inactive_split_bytes.large_pool.allocated": 1028775084032,
+        "inactive_split_bytes.large_pool.current": 48758784,
+        "inactive_split_bytes.large_pool.freed": 1028726325248,
+        "inactive_split_bytes.large_pool.peak": 75759616,
+        "inactive_split_bytes.small_pool.allocated": 3772994400768,
+        "inactive_split_bytes.small_pool.current": 11389952,
+        "inactive_split_bytes.small_pool.freed": 3772983010816,
+        "inactive_split_bytes.small_pool.peak": 82985472,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 97,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 4318242086060,
+        "requested_bytes.all.current": 486046072,
+        "requested_bytes.all.freed": 4317756039988,
+        "requested_bytes.all.peak": 680092736,
+        "requested_bytes.large_pool.allocated": 744702728192,
+        "requested_bytes.large_pool.current": 463910912,
+        "requested_bytes.large_pool.freed": 744238817280,
+        "requested_bytes.large_pool.peak": 626776064,
+        "requested_bytes.small_pool.allocated": 3573539357868,
+        "requested_bytes.small_pool.current": 22135160,
+        "requested_bytes.small_pool.freed": 3573517222708,
+        "requested_bytes.small_pool.peak": 133501696,
+        "reserved_bytes.all.allocated": 805306368,
+        "reserved_bytes.all.current": 805306368,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 805306368,
+        "reserved_bytes.large_pool.allocated": 660602880,
+        "reserved_bytes.large_pool.current": 660602880,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 660602880,
+        "reserved_bytes.small_pool.allocated": 144703488,
+        "reserved_bytes.small_pool.current": 144703488,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 144703488,
+        "segment.all.allocated": 97,
+        "segment.all.current": 97,
+        "segment.all.freed": 0,
+        "segment.all.peak": 97,
+        "segment.large_pool.allocated": 28,
+        "segment.large_pool.current": 28,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 28,
+        "segment.small_pool.allocated": 69,
+        "segment.small_pool.current": 69,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 69
+    }
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/head_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.1"
+}

outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_12345_8_10000/step_7499/pytorch_adapter.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:07fb7d71f073ed606c5e9dfaa871020fe4e42965c7c1fa167873fdc4c1c99901
+size 7191062