interim results

outputs/cola/args.json

@@ -0,0 +1,41 @@
+{
+    "task_name": "cola",
+    "train_file": null,
+    "validation_file": null,
+    "max_length": 256,
+    "pad_to_max_length": false,
+    "model_name_or_path": "bert-base-uncased",
+    "use_slow_tokenizer": false,
+    "per_device_train_batch_size": 32,
+    "per_device_eval_batch_size": 1,
+    "learning_rate": 5e-05,
+    "weight_decay": 0.0,
+    "num_train_epochs": 5,
+    "max_train_steps": null,
+    "peft_method": null,
+    "gradient_accumulation_steps": 1,
+    "lr_scheduler_type": "linear",
+    "num_warmup_steps": 0,
+    "output_dir": "./outputs",
+    "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,
+    "lora_r": 8,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "laplace_hessian": "kron",
+    "laplace_sub": "last_layer",
+    "laplace_prior": "homo",
+    "laplace_optim_step": 1000,
+    "testing_set": "train_val",
+    "cache_dir": "/content/cache/huggingface/metrics/",
+    "laplace_predict": "mc_corr"
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/args.json

@@ -0,0 +1,32 @@
+{
+    "task_name": "cola",
+    "train_file": null,
+    "validation_file": null,
+    "max_length": 256,
+    "pad_to_max_length": false,
+    "model_name_or_path": "bert-base-uncased",
+    "use_slow_tokenizer": false,
+    "per_device_train_batch_size": 32,
+    "per_device_eval_batch_size": 1,
+    "learning_rate": 5e-05,
+    "weight_decay": 0.0,
+    "num_train_epochs": 5,
+    "max_train_steps": 10000,
+    "gradient_accumulation_steps": 1,
+    "lr_scheduler_type": "linear",
+    "num_warmup_steps": 0,
+    "output_dir": "./outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42",
+    "seed": 42,
+    "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,
+    "lora_r": 8,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "testing_set": "train_val"
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/logfile.log

@@ -0,0 +1,222 @@
+05/23/2024 14:23:35 - INFO - __main__ -  Number of labels detected = 2
+05/23/2024 14:23:36 - INFO - __main__ - None
+05/23/2024 14:23:36 - 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}.
+05/23/2024 14:23:36 - 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}.
+05/23/2024 14:23:36 - 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}.
+05/23/2024 14:23:36 - INFO - __main__ -  Max training steps before recalculation = None
+05/23/2024 14:23:36 - INFO - __main__ -  num_update_steps_per_epoch initial = 214
+05/23/2024 14:23:36 - INFO - __main__ -  num training epochs initial = 5
+05/23/2024 14:23:36 - INFO - __main__ - Adjusted num_train_epochs based on max_train_steps: 5
+05/23/2024 14:23:36 - INFO - __main__ - PeftModelForSequenceClassification(
+  (base_model): LoraModel(
+    (model): BertForSequenceClassification(
+      (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): BertSdpaSelfAttention(
+                  (query): lora.Linear(
+                    (base_layer): Linear(in_features=768, out_features=768, bias=True)
+                    (lora_dropout): ModuleDict(
+                      (default): Dropout(p=0.1, inplace=False)
+                    )
+                    (lora_A): ModuleDict(
+                      (default): Linear(in_features=768, out_features=8, bias=False)
+                    )
+                    (lora_B): ModuleDict(
+                      (default): Linear(in_features=8, out_features=768, bias=False)
+                    )
+                    (lora_embedding_A): ParameterDict()
+                    (lora_embedding_B): ParameterDict()
+                  )
+                  (key): Linear(in_features=768, out_features=768, bias=True)
+                  (value): lora.Linear(
+                    (base_layer): Linear(in_features=768, out_features=768, bias=True)
+                    (lora_dropout): ModuleDict(
+                      (default): Dropout(p=0.1, inplace=False)
+                    )
+                    (lora_A): ModuleDict(
+                      (default): Linear(in_features=768, out_features=8, bias=False)
+                    )
+                    (lora_B): ModuleDict(
+                      (default): Linear(in_features=8, out_features=768, bias=False)
+                    )
+                    (lora_embedding_A): ParameterDict()
+                    (lora_embedding_B): ParameterDict()
+                  )
+                  (dropout): Dropout(p=0.1, inplace=False)
+                )
+                (output): BertSelfOutput(
+                  (dense): Linear(in_features=768, out_features=768, bias=True)
+                  (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                  (dropout): Dropout(p=0.1, inplace=False)
+                )
+              )
+              (intermediate): BertIntermediate(
+                (dense): Linear(in_features=768, out_features=3072, bias=True)
+                (intermediate_act_fn): GELUActivation()
+              )
+              (output): BertOutput(
+                (dense): Linear(in_features=3072, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+          )
+        )
+        (pooler): BertPooler(
+          (dense): Linear(in_features=768, out_features=768, bias=True)
+          (activation): Tanh()
+        )
+      )
+      (dropout): Dropout(p=0.1, inplace=False)
+      (classifier): ModulesToSaveWrapper(
+        (original_module): Linear(in_features=768, out_features=2, bias=True)
+        (modules_to_save): ModuleDict(
+          (default): Linear(in_features=768, out_features=2, bias=True)
+        )
+      )
+    )
+  )
+)
+05/23/2024 14:23:37 - INFO - __main__ -  num_update_steps_per_epoch before recalculation = 214
+05/23/2024 14:23:37 - INFO - __main__ -  num_update_steps_per_epoch after recalculation = 214
+05/23/2024 14:23:37 - INFO - __main__ -  num training epochs before recalculation = 5
+05/23/2024 14:23:37 - INFO - __main__ - ***** Running training *****
+05/23/2024 14:23:37 - INFO - __main__ -   Num examples = 6840
+05/23/2024 14:23:37 - INFO - __main__ -   Num Epochs = 5
+05/23/2024 14:23:37 - INFO - __main__ -   Instantaneous batch size per device = 32
+05/23/2024 14:23:37 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 32
+05/23/2024 14:23:37 - INFO - __main__ -   Gradient Accumulation steps = 1
+05/23/2024 14:23:37 - INFO - __main__ -   Total optimization steps = 1070
+05/23/2024 14:23:53 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.10404532946217532}
+05/23/2024 14:24:18 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.08209862418796109}
+05/23/2024 14:24:51 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.0}
+05/23/2024 14:25:17 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.0}
+05/23/2024 14:25:52 - INFO - __main__ - epoch 1: {'matthews_correlation': 0.11716571434177496}
+05/23/2024 14:26:18 - INFO - __main__ - epoch 1: {'matthews_correlation': 0.17856585985971396}
+05/23/2024 14:26:54 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.3214366409689651}
+05/23/2024 14:27:22 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.36034145570197795}
+05/23/2024 14:27:58 - INFO - __main__ - epoch 3: {'matthews_correlation': 0.3396154119450817}
+05/23/2024 14:28:24 - INFO - __main__ - epoch 3: {'matthews_correlation': 0.3875723081509275}
+05/23/2024 14:29:01 - INFO - __main__ - epoch 4: {'matthews_correlation': 0.3581225660855234}
+05/23/2024 14:29:27 - INFO - __main__ - epoch 4: {'matthews_correlation': 0.40757323337120416}
+05/23/2024 16:35:23 - INFO - __main__ -  Number of labels detected = 2
+05/23/2024 16:35:24 - INFO - __main__ - None
+05/23/2024 16:35:24 - 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}.
+05/23/2024 16:35:24 - 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}.
+05/23/2024 16:35:24 - 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}.
+05/23/2024 16:35:24 - INFO - __main__ -  Max training steps before recalculation = None
+05/23/2024 16:35:24 - INFO - __main__ -  num_update_steps_per_epoch initial = 214
+05/23/2024 16:35:24 - INFO - __main__ -  num training epochs initial = 5
+05/23/2024 16:35:24 - INFO - __main__ - Adjusted num_train_epochs based on max_train_steps: 5
+05/23/2024 16:35:24 - INFO - __main__ - PeftModelForSequenceClassification(
+  (base_model): LoraModel(
+    (model): BertForSequenceClassification(
+      (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): BertSdpaSelfAttention(
+                  (query): lora.Linear(
+                    (base_layer): Linear(in_features=768, out_features=768, bias=True)
+                    (lora_dropout): ModuleDict(
+                      (default): Dropout(p=0.1, inplace=False)
+                    )
+                    (lora_A): ModuleDict(
+                      (default): Linear(in_features=768, out_features=8, bias=False)
+                    )
+                    (lora_B): ModuleDict(
+                      (default): Linear(in_features=8, out_features=768, bias=False)
+                    )
+                    (lora_embedding_A): ParameterDict()
+                    (lora_embedding_B): ParameterDict()
+                  )
+                  (key): Linear(in_features=768, out_features=768, bias=True)
+                  (value): lora.Linear(
+                    (base_layer): Linear(in_features=768, out_features=768, bias=True)
+                    (lora_dropout): ModuleDict(
+                      (default): Dropout(p=0.1, inplace=False)
+                    )
+                    (lora_A): ModuleDict(
+                      (default): Linear(in_features=768, out_features=8, bias=False)
+                    )
+                    (lora_B): ModuleDict(
+                      (default): Linear(in_features=8, out_features=768, bias=False)
+                    )
+                    (lora_embedding_A): ParameterDict()
+                    (lora_embedding_B): ParameterDict()
+                  )
+                  (dropout): Dropout(p=0.1, inplace=False)
+                )
+                (output): BertSelfOutput(
+                  (dense): Linear(in_features=768, out_features=768, bias=True)
+                  (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                  (dropout): Dropout(p=0.1, inplace=False)
+                )
+              )
+              (intermediate): BertIntermediate(
+                (dense): Linear(in_features=768, out_features=3072, bias=True)
+                (intermediate_act_fn): GELUActivation()
+              )
+              (output): BertOutput(
+                (dense): Linear(in_features=3072, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+          )
+        )
+        (pooler): BertPooler(
+          (dense): Linear(in_features=768, out_features=768, bias=True)
+          (activation): Tanh()
+        )
+      )
+      (dropout): Dropout(p=0.1, inplace=False)
+      (classifier): ModulesToSaveWrapper(
+        (original_module): Linear(in_features=768, out_features=2, bias=True)
+        (modules_to_save): ModuleDict(
+          (default): Linear(in_features=768, out_features=2, bias=True)
+        )
+      )
+    )
+  )
+)
+05/23/2024 16:35:24 - INFO - __main__ -  num_update_steps_per_epoch before recalculation = 214
+05/23/2024 16:35:24 - INFO - __main__ -  num_update_steps_per_epoch after recalculation = 214
+05/23/2024 16:35:24 - INFO - __main__ -  num training epochs before recalculation = 5
+05/23/2024 16:35:25 - INFO - __main__ - ***** Running training *****
+05/23/2024 16:35:25 - INFO - __main__ -   Num examples = 6840
+05/23/2024 16:35:25 - INFO - __main__ -   Num Epochs = 5
+05/23/2024 16:35:25 - INFO - __main__ -   Instantaneous batch size per device = 32
+05/23/2024 16:35:25 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 32
+05/23/2024 16:35:25 - INFO - __main__ -   Gradient Accumulation steps = 1
+05/23/2024 16:35:25 - INFO - __main__ -   Total optimization steps = 1070
+05/23/2024 16:35:41 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.10404532946217532}
+05/23/2024 16:36:06 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.08209862418796109}
+05/23/2024 16:36:40 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.018148342420931135}
+05/23/2024 16:37:06 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.0}
+05/23/2024 16:37:40 - INFO - __main__ - epoch 1: {'matthews_correlation': 0.3184881845473565}
+05/23/2024 16:38:06 - INFO - __main__ - epoch 1: {'matthews_correlation': 0.37525192119086626}
+05/23/2024 16:38:41 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.3641002176705668}
+05/23/2024 16:39:07 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.386668454336151}
+05/23/2024 16:39:43 - INFO - __main__ - epoch 3: {'matthews_correlation': 0.3860262930745603}
+05/23/2024 16:40:09 - INFO - __main__ - epoch 3: {'matthews_correlation': 0.386060392272705}
+05/23/2024 16:40:44 - INFO - __main__ - epoch 4: {'matthews_correlation': 0.39481313720106403}
+05/23/2024 16:41:10 - INFO - __main__ - epoch 4: {'matthews_correlation': 0.38770266622658694}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: bert-base-uncased
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-uncased",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ad9f6c556fa0cefdee2d3f1c058573923e8b0afefb79923f14fc1d96825ae9
+size 1192672

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.10404532946217532}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/all_results_la_kron_all_homo_mc_corr_1000.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.10966430521058565}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/all_results_la_kron_last_layer_homo_mc_corr_1000.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.11166418336918776}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/all_results_val.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.08209862418796109}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 448806400,
+    "max_memory_allocated": 450717184,
+    "memory_reserved": 499122176,
+    "max_memory_reserved": 499122176,
+    "memory_stats": {
+        "active.all.allocated": 1057794,
+        "active.all.current": 265,
+        "active.all.freed": 1057529,
+        "active.all.peak": 278,
+        "active.large_pool.allocated": 76,
+        "active.large_pool.current": 76,
+        "active.large_pool.freed": 0,
+        "active.large_pool.peak": 76,
+        "active.small_pool.allocated": 1057718,
+        "active.small_pool.current": 189,
+        "active.small_pool.freed": 1057529,
+        "active.small_pool.peak": 202,
+        "active_bytes.all.allocated": 241463920640,
+        "active_bytes.all.current": 448806400,
+        "active_bytes.all.freed": 241015114240,
+        "active_bytes.all.peak": 450717184,
+        "active_bytes.large_pool.allocated": 447086592,
+        "active_bytes.large_pool.current": 447086592,
+        "active_bytes.large_pool.freed": 0,
+        "active_bytes.large_pool.peak": 447086592,
+        "active_bytes.small_pool.allocated": 241016834048,
+        "active_bytes.small_pool.current": 1719808,
+        "active_bytes.small_pool.freed": 241015114240,
+        "active_bytes.small_pool.peak": 3630592,
+        "allocated_bytes.all.allocated": 241463920640,
+        "allocated_bytes.all.current": 448806400,
+        "allocated_bytes.all.freed": 241015114240,
+        "allocated_bytes.all.peak": 450717184,
+        "allocated_bytes.large_pool.allocated": 447086592,
+        "allocated_bytes.large_pool.current": 447086592,
+        "allocated_bytes.large_pool.freed": 0,
+        "allocated_bytes.large_pool.peak": 447086592,
+        "allocated_bytes.small_pool.allocated": 241016834048,
+        "allocated_bytes.small_pool.current": 1719808,
+        "allocated_bytes.small_pool.freed": 241015114240,
+        "allocated_bytes.small_pool.peak": 3630592,
+        "allocation.all.allocated": 1057794,
+        "allocation.all.current": 265,
+        "allocation.all.freed": 1057529,
+        "allocation.all.peak": 278,
+        "allocation.large_pool.allocated": 76,
+        "allocation.large_pool.current": 76,
+        "allocation.large_pool.freed": 0,
+        "allocation.large_pool.peak": 76,
+        "allocation.small_pool.allocated": 1057718,
+        "allocation.small_pool.current": 189,
+        "allocation.small_pool.freed": 1057529,
+        "allocation.small_pool.peak": 202,
+        "inactive_split.all.allocated": 676269,
+        "inactive_split.all.current": 21,
+        "inactive_split.all.freed": 676248,
+        "inactive_split.all.peak": 28,
+        "inactive_split.large_pool.allocated": 19,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 1,
+        "inactive_split.large_pool.peak": 18,
+        "inactive_split.small_pool.allocated": 676250,
+        "inactive_split.small_pool.current": 3,
+        "inactive_split.small_pool.freed": 676247,
+        "inactive_split.small_pool.peak": 10,
+        "inactive_split_bytes.all.allocated": 285715726848,
+        "inactive_split_bytes.all.current": 46121472,
+        "inactive_split_bytes.all.freed": 285669605376,
+        "inactive_split_bytes.all.peak": 55617536,
+        "inactive_split_bytes.large_pool.allocated": 269484032,
+        "inactive_split_bytes.large_pool.current": 45744128,
+        "inactive_split_bytes.large_pool.freed": 223739904,
+        "inactive_split_bytes.large_pool.peak": 54263808,
+        "inactive_split_bytes.small_pool.allocated": 285446242816,
+        "inactive_split_bytes.small_pool.current": 377344,
+        "inactive_split_bytes.small_pool.freed": 285445865472,
+        "inactive_split_bytes.small_pool.peak": 2768384,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 23,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 241366910219,
+        "requested_bytes.all.current": 447669276,
+        "requested_bytes.all.freed": 240919240943,
+        "requested_bytes.all.peak": 449579412,
+        "requested_bytes.large_pool.allocated": 445954048,
+        "requested_bytes.large_pool.current": 445954048,
+        "requested_bytes.large_pool.freed": 0,
+        "requested_bytes.large_pool.peak": 445954048,
+        "requested_bytes.small_pool.allocated": 240920956171,
+        "requested_bytes.small_pool.current": 1715228,
+        "requested_bytes.small_pool.freed": 240919240943,
+        "requested_bytes.small_pool.peak": 3625364,
+        "reserved_bytes.all.allocated": 499122176,
+        "reserved_bytes.all.current": 499122176,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 499122176,
+        "reserved_bytes.large_pool.allocated": 492830720,
+        "reserved_bytes.large_pool.current": 492830720,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 492830720,
+        "reserved_bytes.small_pool.allocated": 6291456,
+        "reserved_bytes.small_pool.current": 6291456,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 6291456,
+        "segment.all.allocated": 23,
+        "segment.all.current": 23,
+        "segment.all.freed": 0,
+        "segment.all.peak": 23,
+        "segment.large_pool.allocated": 20,
+        "segment.large_pool.current": 20,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 20,
+        "segment.small_pool.allocated": 3,
+        "segment.small_pool.current": 3,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 3
+    }
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/gpu_stats_la.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 1390722048,
+    "max_memory_allocated": 1438867456,
+    "memory_reserved": 1535115264,
+    "max_memory_reserved": 1644167168,
+    "memory_stats": {
+        "active.all.allocated": 593915,
+        "active.all.current": 2760,
+        "active.all.freed": 591155,
+        "active.all.peak": 2768,
+        "active.large_pool.allocated": 49362,
+        "active.large_pool.current": 265,
+        "active.large_pool.freed": 49097,
+        "active.large_pool.peak": 271,
+        "active.small_pool.allocated": 544553,
+        "active.small_pool.current": 2495,
+        "active.small_pool.freed": 542058,
+        "active.small_pool.peak": 2503,
+        "active_bytes.all.allocated": 267919830016,
+        "active_bytes.all.current": 1390722048,
+        "active_bytes.all.freed": 266529107968,
+        "active_bytes.all.peak": 1438867456,
+        "active_bytes.large_pool.allocated": 153659284992,
+        "active_bytes.large_pool.current": 1385332736,
+        "active_bytes.large_pool.freed": 152273952256,
+        "active_bytes.large_pool.peak": 1434157056,
+        "active_bytes.small_pool.allocated": 114260545024,
+        "active_bytes.small_pool.current": 5389312,
+        "active_bytes.small_pool.freed": 114255155712,
+        "active_bytes.small_pool.peak": 6965248,
+        "allocated_bytes.all.allocated": 267919830016,
+        "allocated_bytes.all.current": 1390722048,
+        "allocated_bytes.all.freed": 266529107968,
+        "allocated_bytes.all.peak": 1438867456,
+        "allocated_bytes.large_pool.allocated": 153659284992,
+        "allocated_bytes.large_pool.current": 1385332736,
+        "allocated_bytes.large_pool.freed": 152273952256,
+        "allocated_bytes.large_pool.peak": 1434157056,
+        "allocated_bytes.small_pool.allocated": 114260545024,
+        "allocated_bytes.small_pool.current": 5389312,
+        "allocated_bytes.small_pool.freed": 114255155712,
+        "allocated_bytes.small_pool.peak": 6965248,
+        "allocation.all.allocated": 593915,
+        "allocation.all.current": 2760,
+        "allocation.all.freed": 591155,
+        "allocation.all.peak": 2768,
+        "allocation.large_pool.allocated": 49362,
+        "allocation.large_pool.current": 265,
+        "allocation.large_pool.freed": 49097,
+        "allocation.large_pool.peak": 271,
+        "allocation.small_pool.allocated": 544553,
+        "allocation.small_pool.current": 2495,
+        "allocation.small_pool.freed": 542058,
+        "allocation.small_pool.peak": 2503,
+        "inactive_split.all.allocated": 336711,
+        "inactive_split.all.current": 75,
+        "inactive_split.all.freed": 336636,
+        "inactive_split.all.peak": 84,
+        "inactive_split.large_pool.allocated": 42840,
+        "inactive_split.large_pool.current": 67,
+        "inactive_split.large_pool.freed": 42773,
+        "inactive_split.large_pool.peak": 75,
+        "inactive_split.small_pool.allocated": 293871,
+        "inactive_split.small_pool.current": 8,
+        "inactive_split.small_pool.freed": 293863,
+        "inactive_split.small_pool.peak": 14,
+        "inactive_split_bytes.all.allocated": 252283523072,
+        "inactive_split_bytes.all.current": 142296064,
+        "inactive_split_bytes.all.freed": 252141227008,
+        "inactive_split_bytes.all.peak": 179005952,
+        "inactive_split_bytes.large_pool.allocated": 137276645888,
+        "inactive_split_bytes.large_pool.current": 141393920,
+        "inactive_split_bytes.large_pool.freed": 137135251968,
+        "inactive_split_bytes.large_pool.peak": 177340416,
+        "inactive_split_bytes.small_pool.allocated": 115006877184,
+        "inactive_split_bytes.small_pool.current": 902144,
+        "inactive_split_bytes.small_pool.freed": 115005975040,
+        "inactive_split_bytes.small_pool.peak": 2908160,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 87,
+        "num_device_free": 8,
+        "num_ooms": 0,
+        "num_sync_all_streams": 1,
+        "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": 263244243497,
+        "requested_bytes.all.current": 1386385184,
+        "requested_bytes.all.freed": 261857858313,
+        "requested_bytes.all.peak": 1435216624,
+        "requested_bytes.large_pool.allocated": 149065362052,
+        "requested_bytes.large_pool.current": 1382051840,
+        "requested_bytes.large_pool.freed": 147683310212,
+        "requested_bytes.large_pool.peak": 1430515712,
+        "requested_bytes.small_pool.allocated": 114178881445,
+        "requested_bytes.small_pool.current": 4333344,
+        "requested_bytes.small_pool.freed": 114174548101,
+        "requested_bytes.small_pool.peak": 6209040,
+        "reserved_bytes.all.allocated": 1646264320,
+        "reserved_bytes.all.current": 1535115264,
+        "reserved_bytes.all.freed": 111149056,
+        "reserved_bytes.all.peak": 1644167168,
+        "reserved_bytes.large_pool.allocated": 1635778560,
+        "reserved_bytes.large_pool.current": 1526726656,
+        "reserved_bytes.large_pool.freed": 109051904,
+        "reserved_bytes.large_pool.peak": 1635778560,
+        "reserved_bytes.small_pool.allocated": 10485760,
+        "reserved_bytes.small_pool.current": 8388608,
+        "reserved_bytes.small_pool.freed": 2097152,
+        "reserved_bytes.small_pool.peak": 8388608,
+        "segment.all.allocated": 87,
+        "segment.all.current": 79,
+        "segment.all.freed": 8,
+        "segment.all.peak": 86,
+        "segment.large_pool.allocated": 82,
+        "segment.large_pool.current": 75,
+        "segment.large_pool.freed": 7,
+        "segment.large_pool.peak": 82,
+        "segment.small_pool.allocated": 5,
+        "segment.small_pool.current": 4,
+        "segment.small_pool.freed": 1,
+        "segment.small_pool.peak": 4
+    }
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_0/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: bert-base-uncased
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-uncased",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab16918f1e80b50c94ce0b8c607c7dfc8f071057850e4dacd500077862f35b18
+size 1192672

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.39481313720106403}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/all_results_la_kron_all_homo_mc_corr_1000.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.3581225660855234}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/all_results_val.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.38770266622658694}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 459692544,
+    "max_memory_allocated": 1249124352,
+    "memory_reserved": 1367343104,
+    "max_memory_reserved": 1367343104,
+    "memory_stats": {
+        "active.all.allocated": 7337693,
+        "active.all.current": 366,
+        "active.all.freed": 7337327,
+        "active.all.peak": 627,
+        "active.large_pool.allocated": 564754,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 564677,
+        "active.large_pool.peak": 237,
+        "active.small_pool.allocated": 6772939,
+        "active.small_pool.current": 289,
+        "active.small_pool.freed": 6772650,
+        "active.small_pool.peak": 442,
+        "active_bytes.all.allocated": 3311136859136,
+        "active_bytes.all.current": 459692544,
+        "active_bytes.all.freed": 3310677166592,
+        "active_bytes.all.peak": 1249124352,
+        "active_bytes.large_pool.allocated": 1744599758848,
+        "active_bytes.large_pool.current": 455606272,
+        "active_bytes.large_pool.freed": 1744144152576,
+        "active_bytes.large_pool.peak": 1238638592,
+        "active_bytes.small_pool.allocated": 1566537100288,
+        "active_bytes.small_pool.current": 4086272,
+        "active_bytes.small_pool.freed": 1566533014016,
+        "active_bytes.small_pool.peak": 53204992,
+        "allocated_bytes.all.allocated": 3311136859136,
+        "allocated_bytes.all.current": 459692544,
+        "allocated_bytes.all.freed": 3310677166592,
+        "allocated_bytes.all.peak": 1249124352,
+        "allocated_bytes.large_pool.allocated": 1744599758848,
+        "allocated_bytes.large_pool.current": 455606272,
+        "allocated_bytes.large_pool.freed": 1744144152576,
+        "allocated_bytes.large_pool.peak": 1238638592,
+        "allocated_bytes.small_pool.allocated": 1566537100288,
+        "allocated_bytes.small_pool.current": 4086272,
+        "allocated_bytes.small_pool.freed": 1566533014016,
+        "allocated_bytes.small_pool.peak": 53204992,
+        "allocation.all.allocated": 7337693,
+        "allocation.all.current": 366,
+        "allocation.all.freed": 7337327,
+        "allocation.all.peak": 627,
+        "allocation.large_pool.allocated": 564754,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 564677,
+        "allocation.large_pool.peak": 237,
+        "allocation.small_pool.allocated": 6772939,
+        "allocation.small_pool.current": 289,
+        "allocation.small_pool.freed": 6772650,
+        "allocation.small_pool.peak": 442,
+        "inactive_split.all.allocated": 3416705,
+        "inactive_split.all.current": 29,
+        "inactive_split.all.freed": 3416676,
+        "inactive_split.all.peak": 80,
+        "inactive_split.large_pool.allocated": 395610,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 395591,
+        "inactive_split.large_pool.peak": 46,
+        "inactive_split.small_pool.allocated": 3021095,
+        "inactive_split.small_pool.current": 10,
+        "inactive_split.small_pool.freed": 3021085,
+        "inactive_split.small_pool.peak": 58,
+        "inactive_split_bytes.all.allocated": 3588253569024,
+        "inactive_split_bytes.all.current": 64595456,
+        "inactive_split_bytes.all.freed": 3588188973568,
+        "inactive_split_bytes.all.peak": 142978560,
+        "inactive_split_bytes.large_pool.allocated": 1962144710656,
+        "inactive_split_bytes.large_pool.current": 58195968,
+        "inactive_split_bytes.large_pool.freed": 1962086514688,
+        "inactive_split_bytes.large_pool.peak": 139067392,
+        "inactive_split_bytes.small_pool.allocated": 1626108858368,
+        "inactive_split_bytes.small_pool.current": 6399488,
+        "inactive_split_bytes.small_pool.freed": 1626102458880,
+        "inactive_split_bytes.small_pool.peak": 34997760,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 89,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 3277613335107,
+        "requested_bytes.all.current": 458553772,
+        "requested_bytes.all.freed": 3277154781335,
+        "requested_bytes.all.peak": 1224985496,
+        "requested_bytes.large_pool.allocated": 1711670908928,
+        "requested_bytes.large_pool.current": 454473728,
+        "requested_bytes.large_pool.freed": 1711216435200,
+        "requested_bytes.large_pool.peak": 1214511104,
+        "requested_bytes.small_pool.allocated": 1565942426179,
+        "requested_bytes.small_pool.current": 4080044,
+        "requested_bytes.small_pool.freed": 1565938346135,
+        "requested_bytes.small_pool.peak": 53200664,
+        "reserved_bytes.all.allocated": 1367343104,
+        "reserved_bytes.all.current": 1367343104,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 1367343104,
+        "reserved_bytes.large_pool.allocated": 1312817152,
+        "reserved_bytes.large_pool.current": 1312817152,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 1312817152,
+        "reserved_bytes.small_pool.allocated": 54525952,
+        "reserved_bytes.small_pool.current": 54525952,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 54525952,
+        "segment.all.allocated": 89,
+        "segment.all.current": 89,
+        "segment.all.freed": 0,
+        "segment.all.peak": 89,
+        "segment.large_pool.allocated": 63,
+        "segment.large_pool.current": 63,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 63,
+        "segment.small_pool.allocated": 26,
+        "segment.small_pool.current": 26,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 26
+    }
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1069/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: bert-base-uncased
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-uncased",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170807390621cfa35a2ba755e0fa2ca2e160ad1ad34d5daf3c607389333cb913
+size 1192672

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.5179821135635028}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/all_results_la_kron_all_homo_mc_corr_1000.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.5153229695223019}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/all_results_la_kron_last_layer_homo_mc_corr_1000.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.5179821135635028}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/all_results_val.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.4930429468927303}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 459701248,
+    "max_memory_allocated": 1249127424,
+    "memory_reserved": 1367343104,
+    "max_memory_reserved": 1367343104,
+    "memory_stats": {
+        "active.all.allocated": 3970721,
+        "active.all.current": 368,
+        "active.all.freed": 3970353,
+        "active.all.peak": 627,
+        "active.large_pool.allocated": 1056039,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 1055962,
+        "active.large_pool.peak": 237,
+        "active.small_pool.allocated": 2914682,
+        "active.small_pool.current": 291,
+        "active.small_pool.freed": 2914391,
+        "active.small_pool.peak": 442,
+        "active_bytes.all.allocated": 3969839958528,
+        "active_bytes.all.current": 459701248,
+        "active_bytes.all.freed": 3969380257280,
+        "active_bytes.all.peak": 1249127424,
+        "active_bytes.large_pool.allocated": 3262617366016,
+        "active_bytes.large_pool.current": 455606272,
+        "active_bytes.large_pool.freed": 3262161759744,
+        "active_bytes.large_pool.peak": 1238638592,
+        "active_bytes.small_pool.allocated": 707222592512,
+        "active_bytes.small_pool.current": 4094976,
+        "active_bytes.small_pool.freed": 707218497536,
+        "active_bytes.small_pool.peak": 53208064,
+        "allocated_bytes.all.allocated": 3969839958528,
+        "allocated_bytes.all.current": 459701248,
+        "allocated_bytes.all.freed": 3969380257280,
+        "allocated_bytes.all.peak": 1249127424,
+        "allocated_bytes.large_pool.allocated": 3262617366016,
+        "allocated_bytes.large_pool.current": 455606272,
+        "allocated_bytes.large_pool.freed": 3262161759744,
+        "allocated_bytes.large_pool.peak": 1238638592,
+        "allocated_bytes.small_pool.allocated": 707222592512,
+        "allocated_bytes.small_pool.current": 4094976,
+        "allocated_bytes.small_pool.freed": 707218497536,
+        "allocated_bytes.small_pool.peak": 53208064,
+        "allocation.all.allocated": 3970721,
+        "allocation.all.current": 368,
+        "allocation.all.freed": 3970353,
+        "allocation.all.peak": 627,
+        "allocation.large_pool.allocated": 1056039,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 1055962,
+        "allocation.large_pool.peak": 237,
+        "allocation.small_pool.allocated": 2914682,
+        "allocation.small_pool.current": 291,
+        "allocation.small_pool.freed": 2914391,
+        "allocation.small_pool.peak": 442,
+        "inactive_split.all.allocated": 2105270,
+        "inactive_split.all.current": 31,
+        "inactive_split.all.freed": 2105239,
+        "inactive_split.all.peak": 80,
+        "inactive_split.large_pool.allocated": 740193,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 740174,
+        "inactive_split.large_pool.peak": 46,
+        "inactive_split.small_pool.allocated": 1365077,
+        "inactive_split.small_pool.current": 12,
+        "inactive_split.small_pool.freed": 1365065,
+        "inactive_split.small_pool.peak": 57,
+        "inactive_split_bytes.all.allocated": 4444347665408,
+        "inactive_split_bytes.all.current": 66683904,
+        "inactive_split_bytes.all.freed": 4444280981504,
+        "inactive_split_bytes.all.peak": 142978560,
+        "inactive_split_bytes.large_pool.allocated": 3667648128512,
+        "inactive_split_bytes.large_pool.current": 58195968,
+        "inactive_split_bytes.large_pool.freed": 3667589932544,
+        "inactive_split_bytes.large_pool.peak": 139067392,
+        "inactive_split_bytes.small_pool.allocated": 776699536896,
+        "inactive_split_bytes.small_pool.current": 8487936,
+        "inactive_split_bytes.small_pool.freed": 776691048960,
+        "inactive_split_bytes.small_pool.peak": 33155584,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 89,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 3907020432961,
+        "requested_bytes.all.current": 458561584,
+        "requested_bytes.all.freed": 3906561871377,
+        "requested_bytes.all.peak": 1224986276,
+        "requested_bytes.large_pool.allocated": 3200025939968,
+        "requested_bytes.large_pool.current": 454473728,
+        "requested_bytes.large_pool.freed": 3199571466240,
+        "requested_bytes.large_pool.peak": 1214511104,
+        "requested_bytes.small_pool.allocated": 706994492993,
+        "requested_bytes.small_pool.current": 4087856,
+        "requested_bytes.small_pool.freed": 706990405137,
+        "requested_bytes.small_pool.peak": 53201444,
+        "reserved_bytes.all.allocated": 1367343104,
+        "reserved_bytes.all.current": 1367343104,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 1367343104,
+        "reserved_bytes.large_pool.allocated": 1312817152,
+        "reserved_bytes.large_pool.current": 1312817152,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 1312817152,
+        "reserved_bytes.small_pool.allocated": 54525952,
+        "reserved_bytes.small_pool.current": 54525952,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 54525952,
+        "segment.all.allocated": 89,
+        "segment.all.current": 89,
+        "segment.all.freed": 0,
+        "segment.all.peak": 89,
+        "segment.large_pool.allocated": 63,
+        "segment.large_pool.current": 63,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 63,
+        "segment.small_pool.allocated": 26,
+        "segment.small_pool.current": 26,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 26
+    }
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/gpu_stats_la.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 2317025792,
+    "max_memory_allocated": 2365171200,
+    "memory_reserved": 2537553920,
+    "max_memory_reserved": 2646605824,
+    "memory_stats": {
+        "active.all.allocated": 1187828,
+        "active.all.current": 3154,
+        "active.all.freed": 1184674,
+        "active.all.peak": 3162,
+        "active.large_pool.allocated": 98722,
+        "active.large_pool.current": 451,
+        "active.large_pool.freed": 98271,
+        "active.large_pool.peak": 457,
+        "active.small_pool.allocated": 1089106,
+        "active.small_pool.current": 2703,
+        "active.small_pool.freed": 1086403,
+        "active.small_pool.peak": 2711,
+        "active_bytes.all.allocated": 535694891008,
+        "active_bytes.all.current": 2317025792,
+        "active_bytes.all.freed": 533377865216,
+        "active_bytes.all.peak": 2365171200,
+        "active_bytes.large_pool.allocated": 307173800960,
+        "active_bytes.large_pool.current": 2309062656,
+        "active_bytes.large_pool.freed": 304864738304,
+        "active_bytes.large_pool.peak": 2357886976,
+        "active_bytes.small_pool.allocated": 228521090048,
+        "active_bytes.small_pool.current": 7963136,
+        "active_bytes.small_pool.freed": 228513126912,
+        "active_bytes.small_pool.peak": 9539072,
+        "allocated_bytes.all.allocated": 535694891008,
+        "allocated_bytes.all.current": 2317025792,
+        "allocated_bytes.all.freed": 533377865216,
+        "allocated_bytes.all.peak": 2365171200,
+        "allocated_bytes.large_pool.allocated": 307173800960,
+        "allocated_bytes.large_pool.current": 2309062656,
+        "allocated_bytes.large_pool.freed": 304864738304,
+        "allocated_bytes.large_pool.peak": 2357886976,
+        "allocated_bytes.small_pool.allocated": 228521090048,
+        "allocated_bytes.small_pool.current": 7963136,
+        "allocated_bytes.small_pool.freed": 228513126912,
+        "allocated_bytes.small_pool.peak": 9539072,
+        "allocation.all.allocated": 1187828,
+        "allocation.all.current": 3154,
+        "allocation.all.freed": 1184674,
+        "allocation.all.peak": 3162,
+        "allocation.large_pool.allocated": 98722,
+        "allocation.large_pool.current": 451,
+        "allocation.large_pool.freed": 98271,
+        "allocation.large_pool.peak": 457,
+        "allocation.small_pool.allocated": 1089106,
+        "allocation.small_pool.current": 2703,
+        "allocation.small_pool.freed": 1086403,
+        "allocation.small_pool.peak": 2711,
+        "inactive_split.all.allocated": 716026,
+        "inactive_split.all.current": 113,
+        "inactive_split.all.freed": 715913,
+        "inactive_split.all.peak": 585,
+        "inactive_split.large_pool.allocated": 87028,
+        "inactive_split.large_pool.current": 106,
+        "inactive_split.large_pool.freed": 86922,
+        "inactive_split.large_pool.peak": 114,
+        "inactive_split.small_pool.allocated": 628998,
+        "inactive_split.small_pool.current": 7,
+        "inactive_split.small_pool.freed": 628991,
+        "inactive_split.small_pool.peak": 516,
+        "inactive_split_bytes.all.allocated": 504578099200,
+        "inactive_split_bytes.all.current": 218430976,
+        "inactive_split_bytes.all.freed": 504359668224,
+        "inactive_split_bytes.all.peak": 258366464,
+        "inactive_split_bytes.large_pool.allocated": 272549037056,
+        "inactive_split_bytes.large_pool.current": 218005504,
+        "inactive_split_bytes.large_pool.freed": 272331031552,
+        "inactive_split_bytes.large_pool.peak": 257097728,
+        "inactive_split_bytes.small_pool.allocated": 232029062144,
+        "inactive_split_bytes.small_pool.current": 425472,
+        "inactive_split_bytes.small_pool.freed": 232028636672,
+        "inactive_split_bytes.small_pool.peak": 3717632,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 150,
+        "num_device_free": 17,
+        "num_ooms": 0,
+        "num_sync_all_streams": 3,
+        "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": 526471447634,
+        "requested_bytes.all.current": 2311816512,
+        "requested_bytes.all.freed": 524159631122,
+        "requested_bytes.all.peak": 2360647952,
+        "requested_bytes.large_pool.allocated": 298113684744,
+        "requested_bytes.large_pool.current": 2304911360,
+        "requested_bytes.large_pool.freed": 295808773384,
+        "requested_bytes.large_pool.peak": 2353375232,
+        "requested_bytes.small_pool.allocated": 228357762890,
+        "requested_bytes.small_pool.current": 6905152,
+        "requested_bytes.small_pool.freed": 228350857738,
+        "requested_bytes.small_pool.peak": 8780848,
+        "reserved_bytes.all.allocated": 2761949184,
+        "reserved_bytes.all.current": 2537553920,
+        "reserved_bytes.all.freed": 224395264,
+        "reserved_bytes.all.peak": 2646605824,
+        "reserved_bytes.large_pool.allocated": 2745171968,
+        "reserved_bytes.large_pool.current": 2527068160,
+        "reserved_bytes.large_pool.freed": 218103808,
+        "reserved_bytes.large_pool.peak": 2636120064,
+        "reserved_bytes.small_pool.allocated": 16777216,
+        "reserved_bytes.small_pool.current": 10485760,
+        "reserved_bytes.small_pool.freed": 6291456,
+        "reserved_bytes.small_pool.peak": 10485760,
+        "segment.all.allocated": 150,
+        "segment.all.current": 133,
+        "segment.all.freed": 17,
+        "segment.all.peak": 140,
+        "segment.large_pool.allocated": 142,
+        "segment.large_pool.current": 128,
+        "segment.large_pool.freed": 14,
+        "segment.large_pool.peak": 135,
+        "segment.small_pool.allocated": 8,
+        "segment.small_pool.current": 5,
+        "segment.small_pool.freed": 3,
+        "segment.small_pool.peak": 5
+    }
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

outputs/cola/bert-base-uncased_loratrain_val_8_16_0.1_5e-05_42/step_1999/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}