jdorairaj commited on May 2, 2024

Commit

0c2ae73

1 Parent(s): 644c36e

exp run

Browse files

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

Files changed (50) hide show

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/args.json +34 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/logfile.log +213 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/adapter_config.json +41 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/all_results.json +1 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/all_results_val.json +1 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/eval_res.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/eval_res_val.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/gpu_stats.json +127 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/head_config.json +21 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/pytorch_adapter.bin +3 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/pytorch_model_head.bin +3 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/special_tokens_map.json +7 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/tokenizer.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/tokenizer_config.json +56 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/vocab.txt +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/adapter_config.json +41 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/all_results.json +1 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/all_results_val.json +1 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/eval_res.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/eval_res_val.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/gpu_stats.json +127 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/head_config.json +21 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/pytorch_adapter.bin +3 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/pytorch_model_head.bin +3 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/special_tokens_map.json +7 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/tokenizer.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/tokenizer_config.json +56 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/vocab.txt +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/adapter_config.json +41 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/all_results.json +1 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/all_results_val.json +1 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/eval_res.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/eval_res_val.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/gpu_stats.json +127 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/head_config.json +21 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/pytorch_adapter.bin +3 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/pytorch_model_head.bin +3 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/special_tokens_map.json +7 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/tokenizer.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/tokenizer_config.json +56 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/vocab.txt +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/adapter_config.json +41 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/all_results.json +1 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/all_results_val.json +1 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/eval_res.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/eval_res_val.json +0 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/gpu_stats.json +127 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/head_config.json +21 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/pytorch_adapter.bin +3 -0
reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/pytorch_model_head.bin +3 -0

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/args.json ADDED Viewed

	@@ -0,0 +1,34 @@

+{
+    "task_name": "cola",
+    "train_file": null,
+    "validation_file": null,
+    "max_length": 256,
+    "pad_to_max_length": false,
+    "model_name_or_path": "google-bert/bert-base-uncased",
+    "use_slow_tokenizer": false,
+    "per_device_train_batch_size": 32,
+    "per_device_eval_batch_size": 32,
+    "learning_rate": 0.0001,
+    "max_grad_norm": 0.5,
+    "weight_decay": 0.0,
+    "num_train_epochs": 5,
+    "max_train_steps": null,
+    "gradient_accumulation_steps": 1,
+    "lr_scheduler_type": "linear",
+    "num_warmup_steps": 0,
+    "output_dir": "./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16",
+    "seed": 12345,
+    "push_to_hub": false,
+    "hub_model_id": null,
+    "hub_token": null,
+    "checkpointing_steps": null,
+    "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,
+    "reduction_factor": 16
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/logfile.log ADDED Viewed

	@@ -0,0 +1,213 @@

+05/02/2024 13:44:03 - 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}.
+05/02/2024 13:44:04 - INFO - __main__ -  Number of labels detected = 2
+05/02/2024 13:44:04 - 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}.
+05/02/2024 13:44:04 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
+05/02/2024 13:44:04 - 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
+================================================================================
+05/02/2024 13:44:04 - INFO - __main__ - printing model
+05/02/2024 13:44:04 - 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)
+    )
+  )
+)
+05/02/2024 13:44:05 - 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}.
+05/02/2024 13:44:05 - 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}.
+05/02/2024 13:44:05 - 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}.
+05/02/2024 13:44:05 - INFO - __main__ -  Max training steps before recalculation = None
+05/02/2024 13:44:05 - INFO - __main__ -  num_update_steps_per_epoch initial = 214
+05/02/2024 13:44:05 - INFO - __main__ -  num training epochs initial = 5
+05/02/2024 13:44:05 - INFO - __main__ - Adjusted num_train_epochs based on max_train_steps: 5
+05/02/2024 13:44:05 - INFO - __main__ -  num_update_steps_per_epoch before recalculation = 214
+05/02/2024 13:44:05 - INFO - __main__ -  num_update_steps_per_epoch after recalculation = 214
+05/02/2024 13:44:05 - INFO - __main__ -  num training epochs before recalculation = 5
+05/02/2024 13:44:06 - INFO - __main__ - ***** Running training *****
+05/02/2024 13:44:06 - INFO - __main__ -   Num examples = 6840
+05/02/2024 13:44:06 - INFO - __main__ -   Num Epochs = 5
+05/02/2024 13:44:06 - INFO - __main__ -   Instantaneous batch size per device = 32
+05/02/2024 13:44:06 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 32
+05/02/2024 13:44:06 - INFO - __main__ -   Gradient Accumulation steps = 1
+05/02/2024 13:44:06 - INFO - __main__ -   Total optimization steps = 1070
+05/02/2024 13:44:08 - INFO - __main__ - epoch 0: {'matthews_correlation': -0.02929206145132745}
+05/02/2024 13:44:08 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/adapter_config.json
+05/02/2024 13:44:08 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/pytorch_adapter.bin
+05/02/2024 13:44:08 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/head_config.json
+05/02/2024 13:44:09 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/pytorch_model_head.bin
+05/02/2024 13:44:11 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.0}
+05/02/2024 13:44:11 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/adapter_config.json
+05/02/2024 13:44:11 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/pytorch_adapter.bin
+05/02/2024 13:44:11 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/head_config.json
+05/02/2024 13:44:11 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/pytorch_model_head.bin
+05/02/2024 13:44:32 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.3913530742857523}
+05/02/2024 13:44:32 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/adapter_config.json
+05/02/2024 13:44:32 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/pytorch_adapter.bin
+05/02/2024 13:44:32 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/head_config.json
+05/02/2024 13:44:32 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/pytorch_model_head.bin
+05/02/2024 13:44:35 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.43209766412198286}
+05/02/2024 13:44:35 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/adapter_config.json
+05/02/2024 13:44:35 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/pytorch_adapter.bin
+05/02/2024 13:44:35 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/head_config.json
+05/02/2024 13:44:35 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/pytorch_model_head.bin
+05/02/2024 13:44:56 - INFO - __main__ - epoch 1: {'matthews_correlation': 0.40686271625095977}
+05/02/2024 13:44:56 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/adapter_config.json
+05/02/2024 13:44:57 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/pytorch_adapter.bin
+05/02/2024 13:44:57 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/head_config.json
+05/02/2024 13:44:57 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/pytorch_model_head.bin
+05/02/2024 13:44:59 - INFO - __main__ - epoch 1: {'matthews_correlation': 0.43657984362111635}
+05/02/2024 13:44:59 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/adapter_config.json
+05/02/2024 13:44:59 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/pytorch_adapter.bin
+05/02/2024 13:44:59 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/head_config.json
+05/02/2024 13:44:59 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/pytorch_model_head.bin
+05/02/2024 13:45:21 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.4300679389836819}
+05/02/2024 13:45:21 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_641/adapter_config.json
+05/02/2024 13:45:21 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_641/pytorch_adapter.bin
+05/02/2024 13:45:21 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_641/head_config.json
+05/02/2024 13:45:21 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_641/pytorch_model_head.bin
+05/02/2024 13:45:23 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.46279932268480173}
+05/02/2024 13:45:23 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_641/adapter_config.json
+05/02/2024 13:45:23 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_641/pytorch_adapter.bin
+05/02/2024 13:45:23 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_641/head_config.json
+05/02/2024 13:45:23 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_641/pytorch_model_head.bin
+05/02/2024 13:45:45 - INFO - __main__ - epoch 3: {'matthews_correlation': 0.4911444953794644}
+05/02/2024 13:45:45 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_855/adapter_config.json
+05/02/2024 13:45:45 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_855/pytorch_adapter.bin
+05/02/2024 13:45:45 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_855/head_config.json
+05/02/2024 13:45:45 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_855/pytorch_model_head.bin
+05/02/2024 13:45:48 - INFO - __main__ - epoch 3: {'matthews_correlation': 0.4935488969659219}
+05/02/2024 13:45:48 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_855/adapter_config.json
+05/02/2024 13:45:48 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_855/pytorch_adapter.bin
+05/02/2024 13:45:48 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_855/head_config.json
+05/02/2024 13:45:48 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_855/pytorch_model_head.bin
+05/02/2024 13:46:10 - INFO - __main__ - epoch 4: {'matthews_correlation': 0.49110677806667025}
+05/02/2024 13:46:10 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/adapter_config.json
+05/02/2024 13:46:10 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/pytorch_adapter.bin
+05/02/2024 13:46:10 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/head_config.json
+05/02/2024 13:46:10 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/pytorch_model_head.bin
+05/02/2024 13:46:12 - INFO - __main__ - epoch 4: {'matthews_correlation': 0.5026187978800131}
+05/02/2024 13:46:12 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/adapter_config.json
+05/02/2024 13:46:12 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/pytorch_adapter.bin
+05/02/2024 13:46:12 - INFO - adapters.loading - Configuration saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/head_config.json
+05/02/2024 13:46:12 - INFO - adapters.loading - Module weights saved in ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/pytorch_model_head.bin

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/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": "google-bert/bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.0"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/all_results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": -0.02929206145132745}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/all_results_val.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.0}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/eval_res.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/eval_res_val.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/gpu_stats.json ADDED Viewed

	@@ -0,0 +1,127 @@

+{
+    "memory_allocated": 459641856,
+    "max_memory_allocated": 508764160,
+    "memory_reserved": 593494016,
+    "max_memory_reserved": 593494016,
+    "memory_stats": {
+        "active.all.allocated": 64079,
+        "active.all.current": 318,
+        "active.all.freed": 63761,
+        "active.all.peak": 336,
+        "active.large_pool.allocated": 28390,
+        "active.large_pool.current": 78,
+        "active.large_pool.freed": 28312,
+        "active.large_pool.peak": 89,
+        "active.small_pool.allocated": 35689,
+        "active.small_pool.current": 240,
+        "active.small_pool.freed": 35449,
+        "active.small_pool.peak": 257,
+        "active_bytes.all.allocated": 88733824000,
+        "active_bytes.all.current": 459641856,
+        "active_bytes.all.freed": 88274182144,
+        "active_bytes.all.peak": 508764160,
+        "active_bytes.large_pool.allocated": 74593599488,
+        "active_bytes.large_pool.current": 451805184,
+        "active_bytes.large_pool.freed": 74141794304,
+        "active_bytes.large_pool.peak": 500891648,
+        "active_bytes.small_pool.allocated": 14140224512,
+        "active_bytes.small_pool.current": 7836672,
+        "active_bytes.small_pool.freed": 14132387840,
+        "active_bytes.small_pool.peak": 15428096,
+        "allocated_bytes.all.allocated": 88733824000,
+        "allocated_bytes.all.current": 459641856,
+        "allocated_bytes.all.freed": 88274182144,
+        "allocated_bytes.all.peak": 508764160,
+        "allocated_bytes.large_pool.allocated": 74593599488,
+        "allocated_bytes.large_pool.current": 451805184,
+        "allocated_bytes.large_pool.freed": 74141794304,
+        "allocated_bytes.large_pool.peak": 500891648,
+        "allocated_bytes.small_pool.allocated": 14140224512,
+        "allocated_bytes.small_pool.current": 7836672,
+        "allocated_bytes.small_pool.freed": 14132387840,
+        "allocated_bytes.small_pool.peak": 15428096,
+        "allocation.all.allocated": 64079,
+        "allocation.all.current": 318,
+        "allocation.all.freed": 63761,
+        "allocation.all.peak": 336,
+        "allocation.large_pool.allocated": 28390,
+        "allocation.large_pool.current": 78,
+        "allocation.large_pool.freed": 28312,
+        "allocation.large_pool.peak": 89,
+        "allocation.small_pool.allocated": 35689,
+        "allocation.small_pool.current": 240,
+        "allocation.small_pool.freed": 35449,
+        "allocation.small_pool.peak": 257,
+        "inactive_split.all.allocated": 51474,
+        "inactive_split.all.current": 22,
+        "inactive_split.all.freed": 51452,
+        "inactive_split.all.peak": 33,
+        "inactive_split.large_pool.allocated": 26239,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 26221,
+        "inactive_split.large_pool.peak": 26,
+        "inactive_split.small_pool.allocated": 25235,
+        "inactive_split.small_pool.current": 4,
+        "inactive_split.small_pool.freed": 25231,
+        "inactive_split.small_pool.peak": 14,
+        "inactive_split_bytes.all.allocated": 90022852096,
+        "inactive_split_bytes.all.current": 41577472,
+        "inactive_split_bytes.all.freed": 89981274624,
+        "inactive_split_bytes.all.peak": 89366016,
+        "inactive_split_bytes.large_pool.allocated": 74234757120,
+        "inactive_split_bytes.large_pool.current": 41025536,
+        "inactive_split_bytes.large_pool.freed": 74193731584,
+        "inactive_split_bytes.large_pool.peak": 88866816,
+        "inactive_split_bytes.small_pool.allocated": 15788094976,
+        "inactive_split_bytes.small_pool.current": 551936,
+        "inactive_split_bytes.small_pool.freed": 15787543040,
+        "inactive_split_bytes.small_pool.peak": 6483456,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_ooms": 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": 80085666224,
+        "requested_bytes.all.current": 458497396,
+        "requested_bytes.all.freed": 79627168828,
+        "requested_bytes.all.peak": 506701940,
+        "requested_bytes.large_pool.allocated": 65951070208,
+        "requested_bytes.large_pool.current": 450672640,
+        "requested_bytes.large_pool.freed": 65500397568,
+        "requested_bytes.large_pool.peak": 498841600,
+        "requested_bytes.small_pool.allocated": 14134596016,
+        "requested_bytes.small_pool.current": 7824756,
+        "requested_bytes.small_pool.freed": 14126771260,
+        "requested_bytes.small_pool.peak": 15416648,
+        "reserved_bytes.all.allocated": 593494016,
+        "reserved_bytes.all.current": 593494016,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 593494016,
+        "reserved_bytes.large_pool.allocated": 574619648,
+        "reserved_bytes.large_pool.current": 574619648,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 574619648,
+        "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": 34,
+        "segment.all.current": 34,
+        "segment.all.freed": 0,
+        "segment.all.peak": 34,
+        "segment.large_pool.allocated": 25,
+        "segment.large_pool.current": 25,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 25,
+        "segment.small_pool.allocated": 9,
+        "segment.small_pool.current": 9,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 9
+    }
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/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": "google-bert/bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.0"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/pytorch_adapter.bin ADDED Viewed

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

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/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]"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/tokenizer.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/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]"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_0/vocab.txt ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/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": "google-bert/bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.0"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/all_results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.49110677806667025}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/all_results_val.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.5026187978800131}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/eval_res.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/eval_res_val.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/gpu_stats.json ADDED Viewed

	@@ -0,0 +1,127 @@

+{
+    "memory_allocated": 487876608,
+    "max_memory_allocated": 1280701440,
+    "memory_reserved": 1432354816,
+    "max_memory_reserved": 1432354816,
+    "memory_stats": {
+        "active.all.allocated": 1785177,
+        "active.all.current": 519,
+        "active.all.freed": 1784658,
+        "active.all.peak": 777,
+        "active.large_pool.allocated": 869905,
+        "active.large_pool.current": 81,
+        "active.large_pool.freed": 869824,
+        "active.large_pool.peak": 228,
+        "active.small_pool.allocated": 915272,
+        "active.small_pool.current": 438,
+        "active.small_pool.freed": 914834,
+        "active.small_pool.peak": 603,
+        "active_bytes.all.allocated": 2795125268992,
+        "active_bytes.all.current": 487876608,
+        "active_bytes.all.freed": 2794637392384,
+        "active_bytes.all.peak": 1280701440,
+        "active_bytes.large_pool.allocated": 2448186030592,
+        "active_bytes.large_pool.current": 465698816,
+        "active_bytes.large_pool.freed": 2447720331776,
+        "active_bytes.large_pool.peak": 1235008000,
+        "active_bytes.small_pool.allocated": 346939238400,
+        "active_bytes.small_pool.current": 22177792,
+        "active_bytes.small_pool.freed": 346917060608,
+        "active_bytes.small_pool.peak": 71908864,
+        "allocated_bytes.all.allocated": 2795125268992,
+        "allocated_bytes.all.current": 487876608,
+        "allocated_bytes.all.freed": 2794637392384,
+        "allocated_bytes.all.peak": 1280701440,
+        "allocated_bytes.large_pool.allocated": 2448186030592,
+        "allocated_bytes.large_pool.current": 465698816,
+        "allocated_bytes.large_pool.freed": 2447720331776,
+        "allocated_bytes.large_pool.peak": 1235008000,
+        "allocated_bytes.small_pool.allocated": 346939238400,
+        "allocated_bytes.small_pool.current": 22177792,
+        "allocated_bytes.small_pool.freed": 346917060608,
+        "allocated_bytes.small_pool.peak": 71908864,
+        "allocation.all.allocated": 1785177,
+        "allocation.all.current": 519,
+        "allocation.all.freed": 1784658,
+        "allocation.all.peak": 777,
+        "allocation.large_pool.allocated": 869905,
+        "allocation.large_pool.current": 81,
+        "allocation.large_pool.freed": 869824,
+        "allocation.large_pool.peak": 228,
+        "allocation.small_pool.allocated": 915272,
+        "allocation.small_pool.current": 438,
+        "allocation.small_pool.freed": 914834,
+        "allocation.small_pool.peak": 603,
+        "inactive_split.all.allocated": 1069303,
+        "inactive_split.all.current": 51,
+        "inactive_split.all.freed": 1069252,
+        "inactive_split.all.peak": 111,
+        "inactive_split.large_pool.allocated": 730208,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 730190,
+        "inactive_split.large_pool.peak": 46,
+        "inactive_split.small_pool.allocated": 339095,
+        "inactive_split.small_pool.current": 33,
+        "inactive_split.small_pool.freed": 339062,
+        "inactive_split.small_pool.peak": 90,
+        "inactive_split_bytes.all.allocated": 2833239371264,
+        "inactive_split_bytes.all.current": 57382912,
+        "inactive_split_bytes.all.freed": 2833181988352,
+        "inactive_split_bytes.all.peak": 166851072,
+        "inactive_split_bytes.large_pool.allocated": 2464762337280,
+        "inactive_split_bytes.large_pool.current": 48103424,
+        "inactive_split_bytes.large_pool.freed": 2464714233856,
+        "inactive_split_bytes.large_pool.peak": 162594816,
+        "inactive_split_bytes.small_pool.allocated": 368477033984,
+        "inactive_split_bytes.small_pool.current": 9279488,
+        "inactive_split_bytes.small_pool.freed": 368467754496,
+        "inactive_split_bytes.small_pool.peak": 41911808,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_ooms": 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": 2699496701188,
+        "requested_bytes.all.current": 486060548,
+        "requested_bytes.all.freed": 2699010640640,
+        "requested_bytes.all.peak": 1262243472,
+        "requested_bytes.large_pool.allocated": 2352632215040,
+        "requested_bytes.large_pool.current": 463910912,
+        "requested_bytes.large_pool.freed": 2352168304128,
+        "requested_bytes.large_pool.peak": 1216584704,
+        "requested_bytes.small_pool.allocated": 346864486148,
+        "requested_bytes.small_pool.current": 22149636,
+        "requested_bytes.small_pool.freed": 346842336512,
+        "requested_bytes.small_pool.peak": 71870096,
+        "reserved_bytes.all.allocated": 1432354816,
+        "reserved_bytes.all.current": 1432354816,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 1432354816,
+        "reserved_bytes.large_pool.allocated": 1354760192,
+        "reserved_bytes.large_pool.current": 1354760192,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 1354760192,
+        "reserved_bytes.small_pool.allocated": 77594624,
+        "reserved_bytes.small_pool.current": 77594624,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 77594624,
+        "segment.all.allocated": 104,
+        "segment.all.current": 104,
+        "segment.all.freed": 0,
+        "segment.all.peak": 104,
+        "segment.large_pool.allocated": 67,
+        "segment.large_pool.current": 67,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 67,
+        "segment.small_pool.allocated": 37,
+        "segment.small_pool.current": 37,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 37
+    }
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/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": "google-bert/bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.0"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/pytorch_adapter.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:594579be0de914d421f8d8c6a9957d397ae71059bd10629c23a0810b67278982
+size 7191062

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/pytorch_model_head.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:db21e52d43d22f16af233d57438c41adcd7682abda660068c8dc752afab4b9f4
+size 2370664

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/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]"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/tokenizer.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/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]"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_1069/vocab.txt ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/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": "google-bert/bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.0"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/all_results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.3913530742857523}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/all_results_val.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.43209766412198286}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/eval_res.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/eval_res_val.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/gpu_stats.json ADDED Viewed

	@@ -0,0 +1,127 @@

+{
+    "memory_allocated": 487881216,
+    "max_memory_allocated": 1280701440,
+    "memory_reserved": 1432354816,
+    "max_memory_reserved": 1432354816,
+    "memory_stats": {
+        "active.all.allocated": 407393,
+        "active.all.current": 519,
+        "active.all.freed": 406874,
+        "active.all.peak": 777,
+        "active.large_pool.allocated": 195997,
+        "active.large_pool.current": 81,
+        "active.large_pool.freed": 195916,
+        "active.large_pool.peak": 228,
+        "active.small_pool.allocated": 211396,
+        "active.small_pool.current": 438,
+        "active.small_pool.freed": 210958,
+        "active.small_pool.peak": 603,
+        "active_bytes.all.allocated": 627316937216,
+        "active_bytes.all.current": 487881216,
+        "active_bytes.all.freed": 626829056000,
+        "active_bytes.all.peak": 1280701440,
+        "active_bytes.large_pool.allocated": 546686381056,
+        "active_bytes.large_pool.current": 465698816,
+        "active_bytes.large_pool.freed": 546220682240,
+        "active_bytes.large_pool.peak": 1235008000,
+        "active_bytes.small_pool.allocated": 80630556160,
+        "active_bytes.small_pool.current": 22182400,
+        "active_bytes.small_pool.freed": 80608373760,
+        "active_bytes.small_pool.peak": 71908864,
+        "allocated_bytes.all.allocated": 627316937216,
+        "allocated_bytes.all.current": 487881216,
+        "allocated_bytes.all.freed": 626829056000,
+        "allocated_bytes.all.peak": 1280701440,
+        "allocated_bytes.large_pool.allocated": 546686381056,
+        "allocated_bytes.large_pool.current": 465698816,
+        "allocated_bytes.large_pool.freed": 546220682240,
+        "allocated_bytes.large_pool.peak": 1235008000,
+        "allocated_bytes.small_pool.allocated": 80630556160,
+        "allocated_bytes.small_pool.current": 22182400,
+        "allocated_bytes.small_pool.freed": 80608373760,
+        "allocated_bytes.small_pool.peak": 71908864,
+        "allocation.all.allocated": 407393,
+        "allocation.all.current": 519,
+        "allocation.all.freed": 406874,
+        "allocation.all.peak": 777,
+        "allocation.large_pool.allocated": 195997,
+        "allocation.large_pool.current": 81,
+        "allocation.large_pool.freed": 195916,
+        "allocation.large_pool.peak": 228,
+        "allocation.small_pool.allocated": 211396,
+        "allocation.small_pool.current": 438,
+        "allocation.small_pool.freed": 210958,
+        "allocation.small_pool.peak": 603,
+        "inactive_split.all.allocated": 254024,
+        "inactive_split.all.current": 51,
+        "inactive_split.all.freed": 253973,
+        "inactive_split.all.peak": 109,
+        "inactive_split.large_pool.allocated": 166367,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 166349,
+        "inactive_split.large_pool.peak": 46,
+        "inactive_split.small_pool.allocated": 87657,
+        "inactive_split.small_pool.current": 33,
+        "inactive_split.small_pool.freed": 87624,
+        "inactive_split.small_pool.peak": 88,
+        "inactive_split_bytes.all.allocated": 637194957312,
+        "inactive_split_bytes.all.current": 57378304,
+        "inactive_split_bytes.all.freed": 637137579008,
+        "inactive_split_bytes.all.peak": 166851072,
+        "inactive_split_bytes.large_pool.allocated": 550988233216,
+        "inactive_split_bytes.large_pool.current": 48103424,
+        "inactive_split_bytes.large_pool.freed": 550940129792,
+        "inactive_split_bytes.large_pool.peak": 162594816,
+        "inactive_split_bytes.small_pool.allocated": 86206724096,
+        "inactive_split_bytes.small_pool.current": 9274880,
+        "inactive_split_bytes.small_pool.freed": 86197449216,
+        "inactive_split_bytes.small_pool.peak": 41911808,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_ooms": 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": 601292072388,
+        "requested_bytes.all.current": 486065732,
+        "requested_bytes.all.freed": 600806006656,
+        "requested_bytes.all.peak": 1262243472,
+        "requested_bytes.large_pool.allocated": 520680939008,
+        "requested_bytes.large_pool.current": 463910912,
+        "requested_bytes.large_pool.freed": 520217028096,
+        "requested_bytes.large_pool.peak": 1216584704,
+        "requested_bytes.small_pool.allocated": 80611133380,
+        "requested_bytes.small_pool.current": 22154820,
+        "requested_bytes.small_pool.freed": 80588978560,
+        "requested_bytes.small_pool.peak": 71870096,
+        "reserved_bytes.all.allocated": 1432354816,
+        "reserved_bytes.all.current": 1432354816,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 1432354816,
+        "reserved_bytes.large_pool.allocated": 1354760192,
+        "reserved_bytes.large_pool.current": 1354760192,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 1354760192,
+        "reserved_bytes.small_pool.allocated": 77594624,
+        "reserved_bytes.small_pool.current": 77594624,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 77594624,
+        "segment.all.allocated": 104,
+        "segment.all.current": 104,
+        "segment.all.freed": 0,
+        "segment.all.peak": 104,
+        "segment.large_pool.allocated": 67,
+        "segment.large_pool.current": 67,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 67,
+        "segment.small_pool.allocated": 37,
+        "segment.small_pool.current": 37,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 37
+    }
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/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": "google-bert/bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.0"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/pytorch_adapter.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:482fc0834d1df5adce6bcf5146619aa13ecc1ab3ae7b12594fa52d245dc14955
+size 7191062

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/pytorch_model_head.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:787ad3070eee0372b81b7af80aa69bb557487fb3af342c6227d4d2ff523a3daa
+size 2370664

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/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]"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/tokenizer.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/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]"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_213/vocab.txt ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/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": "google-bert/bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.0"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/all_results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.40686271625095977}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/all_results_val.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.43657984362111635}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/eval_res.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/eval_res_val.json ADDED Viewed

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

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/gpu_stats.json ADDED Viewed

	@@ -0,0 +1,127 @@

+{
+    "memory_allocated": 487876608,
+    "max_memory_allocated": 1280701440,
+    "memory_reserved": 1432354816,
+    "max_memory_reserved": 1432354816,
+    "memory_stats": {
+        "active.all.allocated": 751815,
+        "active.all.current": 519,
+        "active.all.freed": 751296,
+        "active.all.peak": 777,
+        "active.large_pool.allocated": 364577,
+        "active.large_pool.current": 81,
+        "active.large_pool.freed": 364496,
+        "active.large_pool.peak": 228,
+        "active.small_pool.allocated": 387238,
+        "active.small_pool.current": 438,
+        "active.small_pool.freed": 386800,
+        "active.small_pool.peak": 603,
+        "active_bytes.all.allocated": 1171049445376,
+        "active_bytes.all.current": 487876608,
+        "active_bytes.all.freed": 1170561568768,
+        "active_bytes.all.peak": 1280701440,
+        "active_bytes.large_pool.allocated": 1023755623424,
+        "active_bytes.large_pool.current": 465698816,
+        "active_bytes.large_pool.freed": 1023289924608,
+        "active_bytes.large_pool.peak": 1235008000,
+        "active_bytes.small_pool.allocated": 147293821952,
+        "active_bytes.small_pool.current": 22177792,
+        "active_bytes.small_pool.freed": 147271644160,
+        "active_bytes.small_pool.peak": 71908864,
+        "allocated_bytes.all.allocated": 1171049445376,
+        "allocated_bytes.all.current": 487876608,
+        "allocated_bytes.all.freed": 1170561568768,
+        "allocated_bytes.all.peak": 1280701440,
+        "allocated_bytes.large_pool.allocated": 1023755623424,
+        "allocated_bytes.large_pool.current": 465698816,
+        "allocated_bytes.large_pool.freed": 1023289924608,
+        "allocated_bytes.large_pool.peak": 1235008000,
+        "allocated_bytes.small_pool.allocated": 147293821952,
+        "allocated_bytes.small_pool.current": 22177792,
+        "allocated_bytes.small_pool.freed": 147271644160,
+        "allocated_bytes.small_pool.peak": 71908864,
+        "allocation.all.allocated": 751815,
+        "allocation.all.current": 519,
+        "allocation.all.freed": 751296,
+        "allocation.all.peak": 777,
+        "allocation.large_pool.allocated": 364577,
+        "allocation.large_pool.current": 81,
+        "allocation.large_pool.freed": 364496,
+        "allocation.large_pool.peak": 228,
+        "allocation.small_pool.allocated": 387238,
+        "allocation.small_pool.current": 438,
+        "allocation.small_pool.freed": 386800,
+        "allocation.small_pool.peak": 603,
+        "inactive_split.all.allocated": 459348,
+        "inactive_split.all.current": 51,
+        "inactive_split.all.freed": 459297,
+        "inactive_split.all.peak": 109,
+        "inactive_split.large_pool.allocated": 307153,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 307135,
+        "inactive_split.large_pool.peak": 46,
+        "inactive_split.small_pool.allocated": 152195,
+        "inactive_split.small_pool.current": 33,
+        "inactive_split.small_pool.freed": 152162,
+        "inactive_split.small_pool.peak": 88,
+        "inactive_split_bytes.all.allocated": 1188144974848,
+        "inactive_split_bytes.all.current": 57382912,
+        "inactive_split_bytes.all.freed": 1188087591936,
+        "inactive_split_bytes.all.peak": 166851072,
+        "inactive_split_bytes.large_pool.allocated": 1031282970112,
+        "inactive_split_bytes.large_pool.current": 48103424,
+        "inactive_split_bytes.large_pool.freed": 1031234866688,
+        "inactive_split_bytes.large_pool.peak": 162594816,
+        "inactive_split_bytes.small_pool.allocated": 156862004736,
+        "inactive_split_bytes.small_pool.current": 9279488,
+        "inactive_split_bytes.small_pool.freed": 156852725248,
+        "inactive_split_bytes.small_pool.peak": 41911808,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_ooms": 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": 1127665463740,
+        "requested_bytes.all.current": 486061124,
+        "requested_bytes.all.freed": 1127179402616,
+        "requested_bytes.all.peak": 1262243472,
+        "requested_bytes.large_pool.allocated": 980404817408,
+        "requested_bytes.large_pool.current": 463910912,
+        "requested_bytes.large_pool.freed": 979940906496,
+        "requested_bytes.large_pool.peak": 1216584704,
+        "requested_bytes.small_pool.allocated": 147260646332,
+        "requested_bytes.small_pool.current": 22150212,
+        "requested_bytes.small_pool.freed": 147238496120,
+        "requested_bytes.small_pool.peak": 71870096,
+        "reserved_bytes.all.allocated": 1432354816,
+        "reserved_bytes.all.current": 1432354816,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 1432354816,
+        "reserved_bytes.large_pool.allocated": 1354760192,
+        "reserved_bytes.large_pool.current": 1354760192,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 1354760192,
+        "reserved_bytes.small_pool.allocated": 77594624,
+        "reserved_bytes.small_pool.current": 77594624,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 77594624,
+        "segment.all.allocated": 104,
+        "segment.all.current": 104,
+        "segment.all.freed": 0,
+        "segment.all.peak": 104,
+        "segment.large_pool.allocated": 67,
+        "segment.large_pool.current": 67,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 67,
+        "segment.small_pool.allocated": 37,
+        "segment.small_pool.current": 37,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 37
+    }
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/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": "google-bert/bert-base-uncased",
+  "model_type": "bert",
+  "name": "cola",
+  "version": "0.2.0"
+}

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/pytorch_adapter.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:771222b26db5d88895bc699fb79e70c9d1da824caccdf0a75260af1dfbfadf09
+size 7191062

reduction_factor/outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_0.0001_12345_16/step_427/pytorch_model_head.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:21e3cb68f6a3745c4ff986922eaa19c1cafa7f6161ddb71bc904ddf864243706
+size 2370664