alpha experiments

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/args.json

@@ -0,0 +1,35 @@
+{
+    "task_name": "cola",
+    "train_file": null,
+    "validation_file": null,
+    "max_length": 256,
+    "pad_to_max_length": false,
+    "model_name_or_path": "google-bert/bert-base-uncased",
+    "use_slow_tokenizer": false,
+    "per_device_train_batch_size": 32,
+    "per_device_eval_batch_size": 32,
+    "learning_rate": 5e-05,
+    "max_grad_norm": 0.5,
+    "weight_decay": 0.0,
+    "num_train_epochs": 5,
+    "max_train_steps": null,
+    "gradient_accumulation_steps": 1,
+    "lr_scheduler_type": "linear",
+    "num_warmup_steps": 0,
+    "output_dir": "./outputs/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345",
+    "seed": 12345,
+    "push_to_hub": false,
+    "hub_model_id": null,
+    "hub_token": null,
+    "checkpointing_steps": null,
+    "resume_from_checkpoint": null,
+    "with_tracking": false,
+    "report_to": "all",
+    "ignore_mismatched_sizes": true,
+    "save_train_results": false,
+    "lora_r": 8,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "testing_set": "train_val",
+    "lm_head": true
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/logfile.log

@@ -0,0 +1,137 @@
+04/30/2024 23:09:14 - INFO - __main__ -  Number of labels detected = 2
+04/30/2024 23:09:14 - INFO - __main__ - None
+04/30/2024 23:09:15 - INFO - __main__ - Sample 3412 of the training set: {'input_ids': [101, 1045, 12781, 1996, 7427, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+04/30/2024 23:09:15 - INFO - __main__ - Sample 6002 of the training set: {'input_ids': [101, 1045, 2442, 2064, 4521, 22088, 2015, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 23:09:15 - INFO - __main__ - Sample 83 of the training set: {'input_ids': [101, 1996, 7764, 22257, 2993, 2000, 1996, 2598, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
+04/30/2024 23:09:15 - INFO - __main__ -  Max training steps before recalculation = None
+04/30/2024 23:09:15 - INFO - __main__ -  num_update_steps_per_epoch initial = 214
+04/30/2024 23:09:15 - INFO - __main__ -  num training epochs initial = 5
+04/30/2024 23:09:15 - INFO - __main__ - Adjusted num_train_epochs based on max_train_steps: 5
+04/30/2024 23:09:15 - 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): BertSelfAttention(
+                  (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): lora.Linear(
+          (base_layer): Linear(in_features=768, out_features=2, 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=2, bias=False)
+          )
+          (lora_embedding_A): ParameterDict()
+          (lora_embedding_B): ParameterDict()
+        )
+        (modules_to_save): ModuleDict(
+          (default): lora.Linear(
+            (base_layer): Linear(in_features=768, out_features=2, 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=2, bias=False)
+            )
+            (lora_embedding_A): ParameterDict()
+            (lora_embedding_B): ParameterDict()
+          )
+        )
+      )
+    )
+  )
+)
+04/30/2024 23:09:16 - INFO - __main__ -  num_update_steps_per_epoch before recalculation = 214
+04/30/2024 23:09:16 - INFO - __main__ -  num_update_steps_per_epoch after recalculation = 214
+04/30/2024 23:09:16 - INFO - __main__ -  num training epochs before recalculation = 5
+04/30/2024 23:09:16 - INFO - __main__ - ***** Running training *****
+04/30/2024 23:09:16 - INFO - __main__ -   Num examples = 6840
+04/30/2024 23:09:16 - INFO - __main__ -   Num Epochs = 5
+04/30/2024 23:09:16 - INFO - __main__ -   Instantaneous batch size per device = 32
+04/30/2024 23:09:16 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 32
+04/30/2024 23:09:16 - INFO - __main__ -   Gradient Accumulation steps = 1
+04/30/2024 23:09:16 - INFO - __main__ -   Total optimization steps = 1070
+04/30/2024 23:09:18 - INFO - __main__ - epoch 0: {'matthews_correlation': -0.008044856322926524}
+04/30/2024 23:09:21 - INFO - __main__ - epoch 0: {'matthews_correlation': -0.008842368995538273}
+04/30/2024 23:09:41 - INFO - __main__ - epoch 0: {'matthews_correlation': -0.020702674026557004}
+04/30/2024 23:09:43 - INFO - __main__ - epoch 0: {'matthews_correlation': 0.0}
+04/30/2024 23:10:04 - INFO - __main__ - epoch 1: {'matthews_correlation': 0.3476595303042622}
+04/30/2024 23:10:07 - INFO - __main__ - epoch 1: {'matthews_correlation': 0.3805279319229517}
+04/30/2024 23:10:27 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.3944424231201585}
+04/30/2024 23:10:29 - INFO - __main__ - epoch 2: {'matthews_correlation': 0.41664754833015816}
+04/30/2024 23:10:49 - INFO - __main__ - epoch 3: {'matthews_correlation': 0.4035662082408423}
+04/30/2024 23:10:52 - INFO - __main__ - epoch 3: {'matthews_correlation': 0.4253583776744412}
+04/30/2024 23:11:12 - INFO - __main__ - epoch 4: {'matthews_correlation': 0.39743424346745876}
+04/30/2024 23:11:14 - INFO - __main__ - epoch 4: {'matthews_correlation': 0.4154373562708837}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_0/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google-bert/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 0.10.0

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_0/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-bert/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": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "classifier",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55499920f591b60a49071fe59feafb9032e4823c660f03b68c110d357f749fa6
+size 1267328

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_0/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": -0.008044856322926524}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_0/all_results_val.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": -0.008842368995538273}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_0/gpu_stats.json

@@ -0,0 +1,127 @@
+{
+    "memory_allocated": 448859648,
+    "max_memory_allocated": 487060992,
+    "memory_reserved": 557842432,
+    "max_memory_reserved": 557842432,
+    "memory_stats": {
+        "active.all.allocated": 47793,
+        "active.all.current": 269,
+        "active.all.freed": 47524,
+        "active.all.peak": 283,
+        "active.large_pool.allocated": 23288,
+        "active.large_pool.current": 76,
+        "active.large_pool.freed": 23212,
+        "active.large_pool.peak": 85,
+        "active.small_pool.allocated": 24505,
+        "active.small_pool.current": 193,
+        "active.small_pool.freed": 24312,
+        "active.small_pool.peak": 207,
+        "active_bytes.all.allocated": 72107065344,
+        "active_bytes.all.current": 448859648,
+        "active_bytes.all.freed": 71658205696,
+        "active_bytes.all.peak": 487060992,
+        "active_bytes.large_pool.allocated": 63002771456,
+        "active_bytes.large_pool.current": 447086592,
+        "active_bytes.large_pool.freed": 62555684864,
+        "active_bytes.large_pool.peak": 485261312,
+        "active_bytes.small_pool.allocated": 9104293888,
+        "active_bytes.small_pool.current": 1773056,
+        "active_bytes.small_pool.freed": 9102520832,
+        "active_bytes.small_pool.peak": 7395328,
+        "allocated_bytes.all.allocated": 72107065344,
+        "allocated_bytes.all.current": 448859648,
+        "allocated_bytes.all.freed": 71658205696,
+        "allocated_bytes.all.peak": 487060992,
+        "allocated_bytes.large_pool.allocated": 63002771456,
+        "allocated_bytes.large_pool.current": 447086592,
+        "allocated_bytes.large_pool.freed": 62555684864,
+        "allocated_bytes.large_pool.peak": 485261312,
+        "allocated_bytes.small_pool.allocated": 9104293888,
+        "allocated_bytes.small_pool.current": 1773056,
+        "allocated_bytes.small_pool.freed": 9102520832,
+        "allocated_bytes.small_pool.peak": 7395328,
+        "allocation.all.allocated": 47793,
+        "allocation.all.current": 269,
+        "allocation.all.freed": 47524,
+        "allocation.all.peak": 283,
+        "allocation.large_pool.allocated": 23288,
+        "allocation.large_pool.current": 76,
+        "allocation.large_pool.freed": 23212,
+        "allocation.large_pool.peak": 85,
+        "allocation.small_pool.allocated": 24505,
+        "allocation.small_pool.current": 193,
+        "allocation.small_pool.freed": 24312,
+        "allocation.small_pool.peak": 207,
+        "inactive_split.all.allocated": 35980,
+        "inactive_split.all.current": 22,
+        "inactive_split.all.freed": 35958,
+        "inactive_split.all.peak": 29,
+        "inactive_split.large_pool.allocated": 20697,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 20679,
+        "inactive_split.large_pool.peak": 24,
+        "inactive_split.small_pool.allocated": 15283,
+        "inactive_split.small_pool.current": 4,
+        "inactive_split.small_pool.freed": 15279,
+        "inactive_split.small_pool.peak": 11,
+        "inactive_split_bytes.all.allocated": 75802501120,
+        "inactive_split_bytes.all.current": 46068224,
+        "inactive_split_bytes.all.freed": 75756432896,
+        "inactive_split_bytes.all.peak": 91133952,
+        "inactive_split_bytes.large_pool.allocated": 65641709568,
+        "inactive_split_bytes.large_pool.current": 45744128,
+        "inactive_split_bytes.large_pool.freed": 65595965440,
+        "inactive_split_bytes.large_pool.peak": 90832896,
+        "inactive_split_bytes.small_pool.allocated": 10160791552,
+        "inactive_split_bytes.small_pool.current": 324096,
+        "inactive_split_bytes.small_pool.freed": 10160467456,
+        "inactive_split_bytes.small_pool.peak": 5386240,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_ooms": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 65332312048,
+        "requested_bytes.all.current": 447722516,
+        "requested_bytes.all.freed": 64884589532,
+        "requested_bytes.all.peak": 485596180,
+        "requested_bytes.large_pool.allocated": 56231950336,
+        "requested_bytes.large_pool.current": 445954048,
+        "requested_bytes.large_pool.freed": 55785996288,
+        "requested_bytes.large_pool.peak": 483801088,
+        "requested_bytes.small_pool.allocated": 9100361712,
+        "requested_bytes.small_pool.current": 1768468,
+        "requested_bytes.small_pool.freed": 9098593244,
+        "requested_bytes.small_pool.peak": 7390288,
+        "reserved_bytes.all.allocated": 557842432,
+        "reserved_bytes.all.current": 557842432,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 557842432,
+        "reserved_bytes.large_pool.allocated": 547356672,
+        "reserved_bytes.large_pool.current": 547356672,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 547356672,
+        "reserved_bytes.small_pool.allocated": 10485760,
+        "reserved_bytes.small_pool.current": 10485760,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 10485760,
+        "segment.all.allocated": 28,
+        "segment.all.current": 28,
+        "segment.all.freed": 0,
+        "segment.all.peak": 28,
+        "segment.large_pool.allocated": 23,
+        "segment.large_pool.current": 23,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 23,
+        "segment.small_pool.allocated": 5,
+        "segment.small_pool.current": 5,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 5
+    }
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/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]"
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_0/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]"
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_1069/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google-bert/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 0.10.0

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_1069/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-bert/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": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "classifier",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_1069/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bca03cea26f6938a67b6c814138fa26e945e3c33cd5208dd34e15a7e54d3ceb
+size 1267328

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_1069/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.39743424346745876}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_1069/all_results_val.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.4154373562708837}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_1069/gpu_stats.json

@@ -0,0 +1,127 @@
+{
+    "memory_allocated": 459795968,
+    "max_memory_allocated": 1279719424,
+    "memory_reserved": 1379926016,
+    "max_memory_reserved": 1379926016,
+    "memory_stats": {
+        "active.all.allocated": 1456108,
+        "active.all.current": 374,
+        "active.all.freed": 1455734,
+        "active.all.peak": 637,
+        "active.large_pool.allocated": 804296,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 804219,
+        "active.large_pool.peak": 248,
+        "active.small_pool.allocated": 651812,
+        "active.small_pool.current": 297,
+        "active.small_pool.freed": 651515,
+        "active.small_pool.peak": 465,
+        "active_bytes.all.allocated": 2561023614464,
+        "active_bytes.all.current": 459795968,
+        "active_bytes.all.freed": 2560563818496,
+        "active_bytes.all.peak": 1279719424,
+        "active_bytes.large_pool.allocated": 2308491953152,
+        "active_bytes.large_pool.current": 455606272,
+        "active_bytes.large_pool.freed": 2308036346880,
+        "active_bytes.large_pool.peak": 1263869952,
+        "active_bytes.small_pool.allocated": 252531661312,
+        "active_bytes.small_pool.current": 4189696,
+        "active_bytes.small_pool.freed": 252527471616,
+        "active_bytes.small_pool.peak": 63705088,
+        "allocated_bytes.all.allocated": 2561023614464,
+        "allocated_bytes.all.current": 459795968,
+        "allocated_bytes.all.freed": 2560563818496,
+        "allocated_bytes.all.peak": 1279719424,
+        "allocated_bytes.large_pool.allocated": 2308491953152,
+        "allocated_bytes.large_pool.current": 455606272,
+        "allocated_bytes.large_pool.freed": 2308036346880,
+        "allocated_bytes.large_pool.peak": 1263869952,
+        "allocated_bytes.small_pool.allocated": 252531661312,
+        "allocated_bytes.small_pool.current": 4189696,
+        "allocated_bytes.small_pool.freed": 252527471616,
+        "allocated_bytes.small_pool.peak": 63705088,
+        "allocation.all.allocated": 1456108,
+        "allocation.all.current": 374,
+        "allocation.all.freed": 1455734,
+        "allocation.all.peak": 637,
+        "allocation.large_pool.allocated": 804296,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 804219,
+        "allocation.large_pool.peak": 248,
+        "allocation.small_pool.allocated": 651812,
+        "allocation.small_pool.current": 297,
+        "allocation.small_pool.freed": 651515,
+        "allocation.small_pool.peak": 465,
+        "inactive_split.all.allocated": 854953,
+        "inactive_split.all.current": 33,
+        "inactive_split.all.freed": 854920,
+        "inactive_split.all.peak": 85,
+        "inactive_split.large_pool.allocated": 632651,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 632632,
+        "inactive_split.large_pool.peak": 41,
+        "inactive_split.small_pool.allocated": 222302,
+        "inactive_split.small_pool.current": 14,
+        "inactive_split.small_pool.freed": 222288,
+        "inactive_split.small_pool.peak": 54,
+        "inactive_split_bytes.all.allocated": 2699003104768,
+        "inactive_split_bytes.all.current": 70783488,
+        "inactive_split_bytes.all.freed": 2698932321280,
+        "inactive_split_bytes.all.peak": 130352640,
+        "inactive_split_bytes.large_pool.allocated": 2424616453120,
+        "inactive_split_bytes.large_pool.current": 58195968,
+        "inactive_split_bytes.large_pool.freed": 2424558257152,
+        "inactive_split_bytes.large_pool.peak": 116785152,
+        "inactive_split_bytes.small_pool.allocated": 274386651648,
+        "inactive_split_bytes.small_pool.current": 12587520,
+        "inactive_split_bytes.small_pool.freed": 274374064128,
+        "inactive_split_bytes.small_pool.peak": 37126144,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_ooms": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 2457172108420,
+        "requested_bytes.all.current": 458656676,
+        "requested_bytes.all.freed": 2456713451744,
+        "requested_bytes.all.peak": 1251715632,
+        "requested_bytes.large_pool.allocated": 2204685203456,
+        "requested_bytes.large_pool.current": 454473728,
+        "requested_bytes.large_pool.freed": 2204230729728,
+        "requested_bytes.large_pool.peak": 1235879936,
+        "requested_bytes.small_pool.allocated": 252486904964,
+        "requested_bytes.small_pool.current": 4182948,
+        "requested_bytes.small_pool.freed": 252482722016,
+        "requested_bytes.small_pool.peak": 63687344,
+        "reserved_bytes.all.allocated": 1379926016,
+        "reserved_bytes.all.current": 1379926016,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 1379926016,
+        "reserved_bytes.large_pool.allocated": 1308622848,
+        "reserved_bytes.large_pool.current": 1308622848,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 1308622848,
+        "reserved_bytes.small_pool.allocated": 71303168,
+        "reserved_bytes.small_pool.current": 71303168,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 71303168,
+        "segment.all.allocated": 97,
+        "segment.all.current": 97,
+        "segment.all.freed": 0,
+        "segment.all.peak": 97,
+        "segment.large_pool.allocated": 63,
+        "segment.large_pool.current": 63,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 63,
+        "segment.small_pool.allocated": 34,
+        "segment.small_pool.current": 34,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 34
+    }
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/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]"
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/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]"
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_213/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google-bert/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 0.10.0

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_213/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-bert/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": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "classifier",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_213/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0849fa2d0971cd506ac8351fe5d80b1d5d369587a4d19342f87c358c52d44e94
+size 1267328

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_213/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": -0.020702674026557004}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_213/all_results_val.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.0}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_213/gpu_stats.json

@@ -0,0 +1,127 @@
+{
+    "memory_allocated": 459792896,
+    "max_memory_allocated": 1279719424,
+    "memory_reserved": 1379926016,
+    "max_memory_reserved": 1379926016,
+    "memory_stats": {
+        "active.all.allocated": 328664,
+        "active.all.current": 374,
+        "active.all.freed": 328290,
+        "active.all.peak": 637,
+        "active.large_pool.allocated": 178844,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 178767,
+        "active.large_pool.peak": 248,
+        "active.small_pool.allocated": 149820,
+        "active.small_pool.current": 297,
+        "active.small_pool.freed": 149523,
+        "active.small_pool.peak": 465,
+        "active_bytes.all.allocated": 569097968128,
+        "active_bytes.all.current": 459792896,
+        "active_bytes.all.freed": 568638175232,
+        "active_bytes.all.peak": 1279719424,
+        "active_bytes.large_pool.allocated": 511203555840,
+        "active_bytes.large_pool.current": 455606272,
+        "active_bytes.large_pool.freed": 510747949568,
+        "active_bytes.large_pool.peak": 1263869952,
+        "active_bytes.small_pool.allocated": 57894412288,
+        "active_bytes.small_pool.current": 4186624,
+        "active_bytes.small_pool.freed": 57890225664,
+        "active_bytes.small_pool.peak": 63705088,
+        "allocated_bytes.all.allocated": 569097968128,
+        "allocated_bytes.all.current": 459792896,
+        "allocated_bytes.all.freed": 568638175232,
+        "allocated_bytes.all.peak": 1279719424,
+        "allocated_bytes.large_pool.allocated": 511203555840,
+        "allocated_bytes.large_pool.current": 455606272,
+        "allocated_bytes.large_pool.freed": 510747949568,
+        "allocated_bytes.large_pool.peak": 1263869952,
+        "allocated_bytes.small_pool.allocated": 57894412288,
+        "allocated_bytes.small_pool.current": 4186624,
+        "allocated_bytes.small_pool.freed": 57890225664,
+        "allocated_bytes.small_pool.peak": 63705088,
+        "allocation.all.allocated": 328664,
+        "allocation.all.current": 374,
+        "allocation.all.freed": 328290,
+        "allocation.all.peak": 637,
+        "allocation.large_pool.allocated": 178844,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 178767,
+        "allocation.large_pool.peak": 248,
+        "allocation.small_pool.allocated": 149820,
+        "allocation.small_pool.current": 297,
+        "allocation.small_pool.freed": 149523,
+        "allocation.small_pool.peak": 465,
+        "inactive_split.all.allocated": 198251,
+        "inactive_split.all.current": 34,
+        "inactive_split.all.freed": 198217,
+        "inactive_split.all.peak": 85,
+        "inactive_split.large_pool.allocated": 142310,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 142291,
+        "inactive_split.large_pool.peak": 41,
+        "inactive_split.small_pool.allocated": 55941,
+        "inactive_split.small_pool.current": 15,
+        "inactive_split.small_pool.freed": 55926,
+        "inactive_split.small_pool.peak": 54,
+        "inactive_split_bytes.all.allocated": 599748315136,
+        "inactive_split_bytes.all.current": 70786560,
+        "inactive_split_bytes.all.freed": 599677528576,
+        "inactive_split_bytes.all.peak": 130352640,
+        "inactive_split_bytes.large_pool.allocated": 536647182848,
+        "inactive_split_bytes.large_pool.current": 58195968,
+        "inactive_split_bytes.large_pool.freed": 536588986880,
+        "inactive_split_bytes.large_pool.peak": 116785152,
+        "inactive_split_bytes.small_pool.allocated": 63101132288,
+        "inactive_split_bytes.small_pool.current": 12590592,
+        "inactive_split_bytes.small_pool.freed": 63088541696,
+        "inactive_split_bytes.small_pool.peak": 37076992,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_ooms": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 543116634212,
+        "requested_bytes.all.current": 458653796,
+        "requested_bytes.all.freed": 542657980416,
+        "requested_bytes.all.peak": 1251715632,
+        "requested_bytes.large_pool.allocated": 485234358272,
+        "requested_bytes.large_pool.current": 454473728,
+        "requested_bytes.large_pool.freed": 484779884544,
+        "requested_bytes.large_pool.peak": 1235879936,
+        "requested_bytes.small_pool.allocated": 57882275940,
+        "requested_bytes.small_pool.current": 4180068,
+        "requested_bytes.small_pool.freed": 57878095872,
+        "requested_bytes.small_pool.peak": 63687344,
+        "reserved_bytes.all.allocated": 1379926016,
+        "reserved_bytes.all.current": 1379926016,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 1379926016,
+        "reserved_bytes.large_pool.allocated": 1308622848,
+        "reserved_bytes.large_pool.current": 1308622848,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 1308622848,
+        "reserved_bytes.small_pool.allocated": 71303168,
+        "reserved_bytes.small_pool.current": 71303168,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 71303168,
+        "segment.all.allocated": 97,
+        "segment.all.current": 97,
+        "segment.all.freed": 0,
+        "segment.all.peak": 97,
+        "segment.large_pool.allocated": 63,
+        "segment.large_pool.current": 63,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 63,
+        "segment.small_pool.allocated": 34,
+        "segment.small_pool.current": 34,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 34
+    }
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_213/special_tokens_map.json

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

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_213/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]"
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_427/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google-bert/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 0.10.0

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_427/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-bert/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": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "classifier",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_427/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4b16201607d198865d3765e0313d6fbfcfc5b2f963dfb3b569ce0ea12be154
+size 1267328

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_427/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.3476595303042622}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_427/all_results_val.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.3805279319229517}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_427/gpu_stats.json

@@ -0,0 +1,127 @@
+{
+    "memory_allocated": 459800576,
+    "max_memory_allocated": 1279719424,
+    "memory_reserved": 1379926016,
+    "max_memory_reserved": 1379926016,
+    "memory_stats": {
+        "active.all.allocated": 610525,
+        "active.all.current": 374,
+        "active.all.freed": 610151,
+        "active.all.peak": 637,
+        "active.large_pool.allocated": 334997,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 334920,
+        "active.large_pool.peak": 248,
+        "active.small_pool.allocated": 275528,
+        "active.small_pool.current": 297,
+        "active.small_pool.freed": 275231,
+        "active.small_pool.peak": 465,
+        "active_bytes.all.allocated": 1067720315392,
+        "active_bytes.all.current": 459800576,
+        "active_bytes.all.freed": 1067260514816,
+        "active_bytes.all.peak": 1279719424,
+        "active_bytes.large_pool.allocated": 960852216320,
+        "active_bytes.large_pool.current": 455606272,
+        "active_bytes.large_pool.freed": 960396610048,
+        "active_bytes.large_pool.peak": 1263869952,
+        "active_bytes.small_pool.allocated": 106868099072,
+        "active_bytes.small_pool.current": 4194304,
+        "active_bytes.small_pool.freed": 106863904768,
+        "active_bytes.small_pool.peak": 63705088,
+        "allocated_bytes.all.allocated": 1067720315392,
+        "allocated_bytes.all.current": 459800576,
+        "allocated_bytes.all.freed": 1067260514816,
+        "allocated_bytes.all.peak": 1279719424,
+        "allocated_bytes.large_pool.allocated": 960852216320,
+        "allocated_bytes.large_pool.current": 455606272,
+        "allocated_bytes.large_pool.freed": 960396610048,
+        "allocated_bytes.large_pool.peak": 1263869952,
+        "allocated_bytes.small_pool.allocated": 106868099072,
+        "allocated_bytes.small_pool.current": 4194304,
+        "allocated_bytes.small_pool.freed": 106863904768,
+        "allocated_bytes.small_pool.peak": 63705088,
+        "allocation.all.allocated": 610525,
+        "allocation.all.current": 374,
+        "allocation.all.freed": 610151,
+        "allocation.all.peak": 637,
+        "allocation.large_pool.allocated": 334997,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 334920,
+        "allocation.large_pool.peak": 248,
+        "allocation.small_pool.allocated": 275528,
+        "allocation.small_pool.current": 297,
+        "allocation.small_pool.freed": 275231,
+        "allocation.small_pool.peak": 465,
+        "inactive_split.all.allocated": 362858,
+        "inactive_split.all.current": 34,
+        "inactive_split.all.freed": 362824,
+        "inactive_split.all.peak": 85,
+        "inactive_split.large_pool.allocated": 264638,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 264619,
+        "inactive_split.large_pool.peak": 41,
+        "inactive_split.small_pool.allocated": 98220,
+        "inactive_split.small_pool.current": 15,
+        "inactive_split.small_pool.freed": 98205,
+        "inactive_split.small_pool.peak": 54,
+        "inactive_split_bytes.all.allocated": 1125091670528,
+        "inactive_split_bytes.all.current": 70778880,
+        "inactive_split_bytes.all.freed": 1125020891648,
+        "inactive_split_bytes.all.peak": 130352640,
+        "inactive_split_bytes.large_pool.allocated": 1008808340992,
+        "inactive_split_bytes.large_pool.current": 58195968,
+        "inactive_split_bytes.large_pool.freed": 1008750145024,
+        "inactive_split_bytes.large_pool.peak": 116785152,
+        "inactive_split_bytes.small_pool.allocated": 116283329536,
+        "inactive_split_bytes.small_pool.current": 12582912,
+        "inactive_split_bytes.small_pool.freed": 116270746624,
+        "inactive_split_bytes.small_pool.peak": 37076992,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_ooms": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 1022607936764,
+        "requested_bytes.all.current": 458660132,
+        "requested_bytes.all.freed": 1022149276632,
+        "requested_bytes.all.peak": 1251715632,
+        "requested_bytes.large_pool.allocated": 915760019456,
+        "requested_bytes.large_pool.current": 454473728,
+        "requested_bytes.large_pool.freed": 915305545728,
+        "requested_bytes.large_pool.peak": 1235879936,
+        "requested_bytes.small_pool.allocated": 106847917308,
+        "requested_bytes.small_pool.current": 4186404,
+        "requested_bytes.small_pool.freed": 106843730904,
+        "requested_bytes.small_pool.peak": 63687344,
+        "reserved_bytes.all.allocated": 1379926016,
+        "reserved_bytes.all.current": 1379926016,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 1379926016,
+        "reserved_bytes.large_pool.allocated": 1308622848,
+        "reserved_bytes.large_pool.current": 1308622848,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 1308622848,
+        "reserved_bytes.small_pool.allocated": 71303168,
+        "reserved_bytes.small_pool.current": 71303168,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 71303168,
+        "segment.all.allocated": 97,
+        "segment.all.current": 97,
+        "segment.all.freed": 0,
+        "segment.all.peak": 97,
+        "segment.large_pool.allocated": 63,
+        "segment.large_pool.current": 63,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 63,
+        "segment.small_pool.allocated": 34,
+        "segment.small_pool.current": 34,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 34
+    }
+}

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_427/special_tokens_map.json

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

Alpha_LoRA/cola/google-bert/bert-base-uncased_lora_lmheadtrain_val_8_16_0.1_5e-05_12345/step_427/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]"
+}