jdorairaj commited on Apr 30, 2024

Commit

d61c3e4

1 Parent(s): a479626

lllaplace

Browse files

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

Files changed (50) hide show

outputs/args.json +0 -47
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/args.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/logfile.log +312 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/adapter_config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/all_results.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/all_results_la_kron_all_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/all_results_la_kron_last_layer_homo_mc_corr_1000.json +1 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/eval_res.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/eval_res_la_kron_all_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/eval_res_la_kron_last_layer_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/generation_config.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/gpu_stats.json +7 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/head_config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/pytorch_adapter.bin +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/pytorch_model_head.bin +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/special_tokens_map.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/tokenizer.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/tokenizer_config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/vocab.txt +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/adapter_config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/all_results.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/all_results_la_kron_all_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/all_results_la_kron_last_layer_homo_mc_corr_1000.json +1 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/eval_res.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/eval_res_la_kron_all_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/eval_res_la_kron_last_layer_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/generation_config.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/gpu_stats.json +7 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/head_config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/pytorch_adapter.bin +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/pytorch_model_head.bin +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/special_tokens_map.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/tokenizer.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/tokenizer_config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/vocab.txt +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/adapter_config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/all_results.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/all_results_la_kron_all_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/all_results_la_kron_last_layer_homo_mc_corr_1000.json +1 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/eval_res.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/eval_res_la_kron_all_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/eval_res_la_kron_last_layer_homo_mc_corr_1000.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/generation_config.json +0 -0
outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/gpu_stats.json +7 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/head_config.json +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/pytorch_adapter.bin +0 -0
outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/pytorch_model_head.bin +0 -0

outputs/args.json DELETED Viewed

@@ -1,47 +0,0 @@
-{
-    "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": true,
-    "per_device_train_batch_size": 8,
-    "per_device_eval_batch_size": 8,
-    "learning_rate": 5e-05,
-    "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",
-    "peft_method": null,
-    "seed": 42,
-    "push_to_hub": false,
-    "hub_model_id": null,
-    "hub_token": null,
-    "checkpointing_steps": "1000",
-    "resume_from_checkpoint": null,
-    "with_tracking": false,
-    "report_to": "all",
-    "ignore_mismatched_sizes": true,
-    "save": false,
-    "load_step": 999,
-    "laplace_hessian": "kron",
-    "laplace_sub": "all",
-    "laplace_prior": "homo",
-    "laplace_optim_step": 1000,
-    "testing_set": "val",
-    "laplace_predict": "mc_corr",
-    "lm_head": false,
-    "cache_dir": "/content/cache/huggingface/metrics/glue",
-    "step_list": [
-        0,
-        1068,
-        2137,
-        3206,
-        4275,
-        5344
-    ]
-}

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/args.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/logfile.log ADDED Viewed

	@@ -0,0 +1,312 @@

+04/30/2024 19:12:31 - INFO - __main__ - Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cpu
+Mixed precision type: no
+04/30/2024 19:12:35 - INFO - __main__ -  Number of labels detected = 2
+04/30/2024 19:12:36 - 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}.
+04/30/2024 19:12:37 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/adapter_config.json
+04/30/2024 19:12:37 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
+04/30/2024 19:12:37 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/pytorch_adapter.bin
+04/30/2024 19:12:37 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/head_config.json
+04/30/2024 19:12:37 - 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}.
+04/30/2024 19:12:37 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/pytorch_model_head.bin
+04/30/2024 19:12:37 - INFO - __main__ - Adapter Name = cola
+04/30/2024 19:12:37 - INFO - __main__ - heads.cola.1.weight
+04/30/2024 19:12:37 - INFO - __main__ - heads.cola.1.bias
+04/30/2024 19:12:37 - INFO - __main__ - heads.cola.4.weight
+04/30/2024 19:12:37 - INFO - __main__ - heads.cola.4.bias
+04/30/2024 19:12:42 - INFO - __main__ - Sample 5238 of the training set: {'input_ids': [101, 2009, 1005, 1055, 2986, 2008, 2002, 3825, 1998, 17806, 1010, 2021, 1045, 2123, 1005, 1056, 2428, 2729, 2055, 2010, 15531, 1010, 2030, 1996, 2769, 1010, 2030, 2505, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+04/30/2024 19:12:42 - INFO - __main__ - Sample 912 of the training set: {'input_ids': [101, 1045, 2113, 2029, 2338, 23848, 3191, 1010, 1998, 2029, 2338, 3960, 2356, 2339, 2017, 2910, 1005, 1056, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 19:12:42 - INFO - __main__ - Sample 204 of the training set: {'input_ids': [101, 1996, 26108, 2002, 4152, 1010, 1996, 2062, 2198, 6010, 11067, 2229, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 19:26:31 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
+04/30/2024 19:26:31 - INFO - __main__ - f_var shape :  torch.Size([1043, 2, 2])
+04/30/2024 19:26:31 - INFO - __main__ - tensor([[ 0.0687,  0.1107],
+        [ 0.1065,  0.1546],
+        [ 0.1252,  0.1252],
+        ...,
+        [ 0.0203,  0.1087],
+        [ 0.0962,  0.1235],
+        [ 0.0511, -0.0174]])
+04/30/2024 19:26:31 - INFO - __main__ - tensor([[[0.2029, 0.1885],
+         [0.1885, 0.2029]],
+        [[0.1999, 0.1717],
+         [0.1717, 0.1999]],
+        [[0.1960, 0.1759],
+         [0.1759, 0.1960]],
+        ...,
+        [[0.2176, 0.1939],
+         [0.1939, 0.2176]],
+        [[0.1863, 0.1736],
+         [0.1736, 0.1863]],
+        [[0.1892, 0.1718],
+         [0.1718, 0.1892]]])
+04/30/2024 19:26:31 - INFO - __main__ - Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cpu
+Mixed precision type: no
+04/30/2024 19:26:35 - INFO - __main__ -  Number of labels detected = 2
+04/30/2024 19:26:35 - 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}.
+04/30/2024 19:26:37 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/adapter_config.json
+04/30/2024 19:26:37 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
+04/30/2024 19:26:37 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/pytorch_adapter.bin
+04/30/2024 19:26:37 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/head_config.json
+04/30/2024 19:26:37 - 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}.
+04/30/2024 19:26:37 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/pytorch_model_head.bin
+04/30/2024 19:26:37 - INFO - __main__ - Adapter Name = cola
+04/30/2024 19:26:37 - INFO - __main__ - heads.cola.1.weight
+04/30/2024 19:26:37 - INFO - __main__ - heads.cola.1.bias
+04/30/2024 19:26:37 - INFO - __main__ - heads.cola.4.weight
+04/30/2024 19:26:37 - INFO - __main__ - heads.cola.4.bias
+04/30/2024 19:26:41 - INFO - __main__ - Sample 5238 of the training set: {'input_ids': [101, 2009, 1005, 1055, 2986, 2008, 2002, 3825, 1998, 17806, 1010, 2021, 1045, 2123, 1005, 1056, 2428, 2729, 2055, 2010, 15531, 1010, 2030, 1996, 2769, 1010, 2030, 2505, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+04/30/2024 19:26:41 - INFO - __main__ - Sample 912 of the training set: {'input_ids': [101, 1045, 2113, 2029, 2338, 23848, 3191, 1010, 1998, 2029, 2338, 3960, 2356, 2339, 2017, 2910, 1005, 1056, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 19:26:41 - INFO - __main__ - Sample 204 of the training set: {'input_ids': [101, 1996, 26108, 2002, 4152, 1010, 1996, 2062, 2198, 6010, 11067, 2229, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 19:40:51 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
+04/30/2024 19:40:51 - INFO - __main__ - f_var shape :  torch.Size([1043, 2, 2])
+04/30/2024 19:40:51 - INFO - __main__ - tensor([[-1.4529,  1.7744],
+        [-1.1889,  1.5487],
+        [-1.4239,  1.8257],
+        ...,
+        [-2.0956,  2.2813],
+        [-0.5643,  0.8205],
+        [-0.9262,  0.8999]])
+04/30/2024 19:40:51 - INFO - __main__ - tensor([[[0.3071, 0.2560],
+         [0.2560, 0.3071]],
+        [[0.2708, 0.2068],
+         [0.2068, 0.2708]],
+        [[0.3089, 0.2527],
+         [0.2527, 0.3089]],
+        ...,
+        [[0.4054, 0.3471],
+         [0.3471, 0.4054]],
+        [[0.1919, 0.1553],
+         [0.1553, 0.1919]],
+        [[0.2052, 0.1670],
+         [0.1670, 0.2052]]])
+04/30/2024 19:40:51 - INFO - __main__ - Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cpu
+Mixed precision type: no
+04/30/2024 19:40:53 - INFO - __main__ -  Number of labels detected = 2
+04/30/2024 19:40:54 - 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}.
+04/30/2024 19:40:55 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/adapter_config.json
+04/30/2024 19:40:55 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
+04/30/2024 19:40:55 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/pytorch_adapter.bin
+04/30/2024 19:40:55 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/head_config.json
+04/30/2024 19:40:55 - 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}.
+04/30/2024 19:40:55 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/pytorch_model_head.bin
+04/30/2024 19:40:55 - INFO - __main__ - Adapter Name = cola
+04/30/2024 19:40:55 - INFO - __main__ - heads.cola.1.weight
+04/30/2024 19:40:55 - INFO - __main__ - heads.cola.1.bias
+04/30/2024 19:40:55 - INFO - __main__ - heads.cola.4.weight
+04/30/2024 19:40:55 - INFO - __main__ - heads.cola.4.bias
+04/30/2024 19:41:00 - INFO - __main__ - Sample 5238 of the training set: {'input_ids': [101, 2009, 1005, 1055, 2986, 2008, 2002, 3825, 1998, 17806, 1010, 2021, 1045, 2123, 1005, 1056, 2428, 2729, 2055, 2010, 15531, 1010, 2030, 1996, 2769, 1010, 2030, 2505, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+04/30/2024 19:41:00 - INFO - __main__ - Sample 912 of the training set: {'input_ids': [101, 1045, 2113, 2029, 2338, 23848, 3191, 1010, 1998, 2029, 2338, 3960, 2356, 2339, 2017, 2910, 1005, 1056, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 19:41:00 - INFO - __main__ - Sample 204 of the training set: {'input_ids': [101, 1996, 26108, 2002, 4152, 1010, 1996, 2062, 2198, 6010, 11067, 2229, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 19:55:00 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
+04/30/2024 19:55:00 - INFO - __main__ - f_var shape :  torch.Size([1043, 2, 2])
+04/30/2024 19:55:00 - INFO - __main__ - tensor([[-1.2545,  1.5103],
+        [-1.1312,  1.4272],
+        [-1.0637,  1.4316],
+        ...,
+        [-1.9212,  2.1010],
+        [-0.2051,  0.3802],
+        [-0.7883,  0.7410]])
+04/30/2024 19:55:00 - INFO - __main__ - tensor([[[0.2652, 0.2093],
+         [0.2093, 0.2652]],
+        [[0.2405, 0.1822],
+         [0.1822, 0.2405]],
+        [[0.2576, 0.2011],
+         [0.2011, 0.2576]],
+        ...,
+        [[0.3661, 0.3102],
+         [0.3102, 0.3661]],
+        [[0.1545, 0.1238],
+         [0.1238, 0.1545]],
+        [[0.1725, 0.1392],
+         [0.1392, 0.1725]]])
+04/30/2024 19:55:00 - INFO - __main__ - Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cpu
+Mixed precision type: no
+04/30/2024 19:55:02 - INFO - __main__ -  Number of labels detected = 2
+04/30/2024 19:55:03 - 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}.
+04/30/2024 19:55:04 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_3206/adapter_config.json
+04/30/2024 19:55:04 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
+04/30/2024 19:55:04 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_3206/pytorch_adapter.bin
+04/30/2024 19:55:04 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_3206/head_config.json
+04/30/2024 19:55:04 - 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}.
+04/30/2024 19:55:04 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_3206/pytorch_model_head.bin
+04/30/2024 19:55:04 - INFO - __main__ - Adapter Name = cola
+04/30/2024 19:55:04 - INFO - __main__ - heads.cola.1.weight
+04/30/2024 19:55:04 - INFO - __main__ - heads.cola.1.bias
+04/30/2024 19:55:04 - INFO - __main__ - heads.cola.4.weight
+04/30/2024 19:55:04 - INFO - __main__ - heads.cola.4.bias
+04/30/2024 19:55:09 - INFO - __main__ - Sample 5238 of the training set: {'input_ids': [101, 2009, 1005, 1055, 2986, 2008, 2002, 3825, 1998, 17806, 1010, 2021, 1045, 2123, 1005, 1056, 2428, 2729, 2055, 2010, 15531, 1010, 2030, 1996, 2769, 1010, 2030, 2505, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+04/30/2024 19:55:09 - INFO - __main__ - Sample 912 of the training set: {'input_ids': [101, 1045, 2113, 2029, 2338, 23848, 3191, 1010, 1998, 2029, 2338, 3960, 2356, 2339, 2017, 2910, 1005, 1056, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 19:55:09 - INFO - __main__ - Sample 204 of the training set: {'input_ids': [101, 1996, 26108, 2002, 4152, 1010, 1996, 2062, 2198, 6010, 11067, 2229, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 20:09:20 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
+04/30/2024 20:09:20 - INFO - __main__ - f_var shape :  torch.Size([1043, 2, 2])
+04/30/2024 20:09:20 - INFO - __main__ - tensor([[-1.5903,  1.8046],
+        [-1.4262,  1.7163],
+        [-1.2728,  1.6234],
+        ...,
+        [-2.3189,  2.5137],
+        [-0.0952,  0.2233],
+        [-0.7922,  0.7461]])
+04/30/2024 20:09:20 - INFO - __main__ - tensor([[[0.3187, 0.2535],
+         [0.2535, 0.3187]],
+        [[0.2909, 0.2243],
+         [0.2243, 0.2909]],
+        [[0.2970, 0.2309],
+         [0.2309, 0.2970]],
+        ...,
+        [[0.4427, 0.3839],
+         [0.3839, 0.4427]],
+        [[0.1634, 0.1292],
+         [0.1292, 0.1634]],
+        [[0.1837, 0.1443],
+         [0.1443, 0.1837]]])
+04/30/2024 20:09:20 - INFO - __main__ - Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cpu
+Mixed precision type: no
+04/30/2024 20:09:22 - INFO - __main__ -  Number of labels detected = 2
+04/30/2024 20:09:23 - 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}.
+04/30/2024 20:09:23 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_4275/adapter_config.json
+04/30/2024 20:09:23 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
+04/30/2024 20:09:23 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_4275/pytorch_adapter.bin
+04/30/2024 20:09:23 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_4275/head_config.json
+04/30/2024 20:09:23 - 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}.
+04/30/2024 20:09:24 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_4275/pytorch_model_head.bin
+04/30/2024 20:09:24 - INFO - __main__ - Adapter Name = cola
+04/30/2024 20:09:24 - INFO - __main__ - heads.cola.1.weight
+04/30/2024 20:09:24 - INFO - __main__ - heads.cola.1.bias
+04/30/2024 20:09:24 - INFO - __main__ - heads.cola.4.weight
+04/30/2024 20:09:24 - INFO - __main__ - heads.cola.4.bias
+04/30/2024 20:09:28 - INFO - __main__ - Sample 5238 of the training set: {'input_ids': [101, 2009, 1005, 1055, 2986, 2008, 2002, 3825, 1998, 17806, 1010, 2021, 1045, 2123, 1005, 1056, 2428, 2729, 2055, 2010, 15531, 1010, 2030, 1996, 2769, 1010, 2030, 2505, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+04/30/2024 20:09:28 - INFO - __main__ - Sample 912 of the training set: {'input_ids': [101, 1045, 2113, 2029, 2338, 23848, 3191, 1010, 1998, 2029, 2338, 3960, 2356, 2339, 2017, 2910, 1005, 1056, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 20:09:28 - INFO - __main__ - Sample 204 of the training set: {'input_ids': [101, 1996, 26108, 2002, 4152, 1010, 1996, 2062, 2198, 6010, 11067, 2229, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 20:23:30 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
+04/30/2024 20:23:30 - INFO - __main__ - f_var shape :  torch.Size([1043, 2, 2])
+04/30/2024 20:23:30 - INFO - __main__ - tensor([[-1.8506,  2.0807],
+        [-1.5632,  1.8705],
+        [-1.4465,  1.8179],
+        ...,
+        [-2.5331,  2.7452],
+        [-0.1701,  0.3093],
+        [-0.9411,  0.9126]])
+04/30/2024 20:23:30 - INFO - __main__ - tensor([[[0.3666, 0.2971],
+         [0.2971, 0.3666]],
+        [[0.3195, 0.2491],
+         [0.2491, 0.3195]],
+        [[0.3326, 0.2601],
+         [0.2601, 0.3326]],
+        ...,
+        [[0.4860, 0.4264],
+         [0.4264, 0.4860]],
+        [[0.1715, 0.1336],
+         [0.1336, 0.1715]],
+        [[0.2016, 0.1572],
+         [0.1572, 0.2016]]])
+04/30/2024 20:23:30 - INFO - __main__ - Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cpu
+Mixed precision type: no
+04/30/2024 20:23:32 - INFO - __main__ -  Number of labels detected = 2
+04/30/2024 20:23:33 - 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}.
+04/30/2024 20:23:34 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_5344/adapter_config.json
+04/30/2024 20:23:34 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
+04/30/2024 20:23:34 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_5344/pytorch_adapter.bin
+04/30/2024 20:23:34 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_5344/head_config.json
+04/30/2024 20:23:34 - 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}.
+04/30/2024 20:23:34 - INFO - adapters.loading - Loading module weights from ./outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_5344/pytorch_model_head.bin
+04/30/2024 20:23:34 - INFO - __main__ - Adapter Name = cola
+04/30/2024 20:23:34 - INFO - __main__ - heads.cola.1.weight
+04/30/2024 20:23:34 - INFO - __main__ - heads.cola.1.bias
+04/30/2024 20:23:34 - INFO - __main__ - heads.cola.4.weight
+04/30/2024 20:23:34 - INFO - __main__ - heads.cola.4.bias
+04/30/2024 20:23:39 - INFO - __main__ - Sample 5238 of the training set: {'input_ids': [101, 2009, 1005, 1055, 2986, 2008, 2002, 3825, 1998, 17806, 1010, 2021, 1045, 2123, 1005, 1056, 2428, 2729, 2055, 2010, 15531, 1010, 2030, 1996, 2769, 1010, 2030, 2505, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+04/30/2024 20:23:39 - INFO - __main__ - Sample 912 of the training set: {'input_ids': [101, 1045, 2113, 2029, 2338, 23848, 3191, 1010, 1998, 2029, 2338, 3960, 2356, 2339, 2017, 2910, 1005, 1056, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 20:23:39 - INFO - __main__ - Sample 204 of the training set: {'input_ids': [101, 1996, 26108, 2002, 4152, 1010, 1996, 2062, 2198, 6010, 11067, 2229, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 20:37:44 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
+04/30/2024 20:37:44 - INFO - __main__ - f_var shape :  torch.Size([1043, 2, 2])
+04/30/2024 20:37:44 - INFO - __main__ - tensor([[-1.8640,  2.1037],
+        [-1.5643,  1.8815],
+        [-1.4149,  1.7945],
+        ...,
+        [-2.4889,  2.7067],
+        [-0.1663,  0.3097],
+        [-0.8635,  0.8440]])
+04/30/2024 20:37:44 - INFO - __main__ - tensor([[[0.3703, 0.3002],
+         [0.3002, 0.3703]],
+        [[0.3209, 0.2497],
+         [0.2497, 0.3209]],
+        [[0.3293, 0.2559],
+         [0.2559, 0.3293]],
+        ...,
+        [[0.4776, 0.4180],
+         [0.4180, 0.4776]],
+        [[0.1715, 0.1335],
+         [0.1335, 0.1715]],
+        [[0.1975, 0.1524],
+         [0.1524, 0.1975]]])

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/adapter_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/all_results.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/all_results_la_kron_all_homo_mc_corr_1000.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/all_results_la_kron_last_layer_homo_mc_corr_1000.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.01029747168884776}

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/eval_res.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/eval_res_la_kron_all_homo_mc_corr_1000.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/eval_res_la_kron_last_layer_homo_mc_corr_1000.json ADDED Viewed

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

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/generation_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_0/gpu_stats.json ADDED Viewed

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

+{
+    "memory_allocated": 0,
+    "max_memory_allocated": 0,
+    "memory_reserved": 0,
+    "max_memory_reserved": 0,
+    "memory_stats": {}
+}

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/head_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/pytorch_adapter.bin RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/pytorch_model_head.bin RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/special_tokens_map.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/tokenizer.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/tokenizer_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_0/vocab.txt RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/adapter_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/all_results.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/all_results_la_kron_all_homo_mc_corr_1000.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/all_results_la_kron_last_layer_homo_mc_corr_1000.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.46484295300587036}

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/eval_res.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/eval_res_la_kron_all_homo_mc_corr_1000.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/eval_res_la_kron_last_layer_homo_mc_corr_1000.json ADDED Viewed

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

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/generation_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_1068/gpu_stats.json ADDED Viewed

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

+{
+    "memory_allocated": 0,
+    "max_memory_allocated": 0,
+    "memory_reserved": 0,
+    "max_memory_reserved": 0,
+    "memory_stats": {}
+}

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/head_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/pytorch_adapter.bin RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/pytorch_model_head.bin RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/special_tokens_map.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/tokenizer.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/tokenizer_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_1068/vocab.txt RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/adapter_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/all_results.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/all_results_la_kron_all_homo_mc_corr_1000.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/all_results_la_kron_last_layer_homo_mc_corr_1000.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_matthews_correlation": 0.5072753983504138}

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/eval_res.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/eval_res_la_kron_all_homo_mc_corr_1000.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/eval_res_la_kron_last_layer_homo_mc_corr_1000.json ADDED Viewed

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

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/generation_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/bert-base-uncased_adapterstrain_val_5e-05_42/step_2137/gpu_stats.json ADDED Viewed

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

+{
+    "memory_allocated": 0,
+    "max_memory_allocated": 0,
+    "memory_reserved": 0,
+    "max_memory_reserved": 0,
+    "memory_stats": {}
+}

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/head_config.json RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/pytorch_adapter.bin RENAMED Viewed

File without changes

outputs/cola/google-bert/{bert-base-uncased_adapters_5e-05_42 → bert-base-uncased_adapterstrain_val_5e-05_42}/step_2137/pytorch_model_head.bin RENAMED Viewed

File without changes