cola task

cola/outputs/args.json

@@ -0,0 +1,42 @@
+{
+    "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": 8,
+    "per_device_eval_batch_size": 8,
+    "learning_rate": 5e-05,
+    "weight_decay": 0.0,
+    "num_train_epochs": 5,
+    "max_train_steps": null,
+    "gradient_accumulation_steps": 1,
+    "lr_scheduler_type": "linear",
+    "num_warmup_steps": 0,
+    "output_dir": "./outputs",
+    "peft_method": null,
+    "seed": 42,
+    "push_to_hub": false,
+    "hub_model_id": null,
+    "hub_token": null,
+    "checkpointing_steps": "1000",
+    "resume_from_checkpoint": null,
+    "with_tracking": false,
+    "report_to": "all",
+    "ignore_mismatched_sizes": true,
+    "save": false,
+    "load_step": 999,
+    "lora_r": 8,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "laplace_hessian": "kron",
+    "laplace_sub": "all",
+    "laplace_prior": "homo",
+    "laplace_optim_step": 1000,
+    "testing_set": "val",
+    "laplace_predict": "mc_corr",
+    "lm_head": true,
+    "cache_dir": "/content/cache/huggingface/metrics/glue"
+}

cola/outputs/cola/args.json

@@ -0,0 +1,42 @@
+{
+    "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": 8,
+    "per_device_eval_batch_size": 8,
+    "learning_rate": 5e-05,
+    "weight_decay": 0.0,
+    "num_train_epochs": 5,
+    "max_train_steps": null,
+    "gradient_accumulation_steps": 1,
+    "lr_scheduler_type": "linear",
+    "num_warmup_steps": 0,
+    "output_dir": "./outputs",
+    "peft_method": null,
+    "seed": 12345,
+    "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": "all",
+    "laplace_prior": "homo",
+    "laplace_optim_step": 1000,
+    "testing_set": "train_val",
+    "laplace_predict": "mc_corr",
+    "lm_head": true,
+    "cache_dir": "/content/cache/huggingface/metrics/"
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/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": 8,
+    "per_device_eval_batch_size": 8,
+    "learning_rate": 5e-05,
+    "max_grad_norm": 0.5,
+    "weight_decay": 0.0,
+    "num_train_epochs": 6,
+    "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_lmhead_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,
+    "save_train_results": false,
+    "lora_r": 8,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "testing_set": "val",
+    "lm_head": true
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_0/README.md

@@ -0,0 +1,204 @@
+---
+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

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/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": [
+    "classifier",
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ce92da9c8bf89786713a6e9f97eb7997aa833eab438517a19e803d0bbd0423
+size 1267328

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_0/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.0955500812997614}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_0/all_results_la_kron_all_homo_mc_corr_1000.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.0955500812997614}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_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": 0.0955500812997614}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_0/gpu_stats.json

@@ -0,0 +1,127 @@
+{
+    "memory_allocated": 809201664,
+    "max_memory_allocated": 1205814784,
+    "memory_reserved": 1361051648,
+    "max_memory_reserved": 1361051648,
+    "memory_stats": {
+        "active.all.allocated": 2473256,
+        "active.all.current": 985,
+        "active.all.freed": 2472271,
+        "active.all.peak": 1150,
+        "active.large_pool.allocated": 312449,
+        "active.large_pool.current": 225,
+        "active.large_pool.freed": 312224,
+        "active.large_pool.peak": 275,
+        "active.small_pool.allocated": 2160807,
+        "active.small_pool.current": 760,
+        "active.small_pool.freed": 2160047,
+        "active.small_pool.peak": 922,
+        "active_bytes.all.allocated": 1274216230912,
+        "active_bytes.all.current": 809201664,
+        "active_bytes.all.freed": 1273407029248,
+        "active_bytes.all.peak": 1205814784,
+        "active_bytes.large_pool.allocated": 756340607488,
+        "active_bytes.large_pool.current": 805830656,
+        "active_bytes.large_pool.freed": 755534776832,
+        "active_bytes.large_pool.peak": 1161462272,
+        "active_bytes.small_pool.allocated": 517875623424,
+        "active_bytes.small_pool.current": 3371008,
+        "active_bytes.small_pool.freed": 517872252416,
+        "active_bytes.small_pool.peak": 92806144,
+        "allocated_bytes.all.allocated": 1274216230912,
+        "allocated_bytes.all.current": 809201664,
+        "allocated_bytes.all.freed": 1273407029248,
+        "allocated_bytes.all.peak": 1205814784,
+        "allocated_bytes.large_pool.allocated": 756340607488,
+        "allocated_bytes.large_pool.current": 805830656,
+        "allocated_bytes.large_pool.freed": 755534776832,
+        "allocated_bytes.large_pool.peak": 1161462272,
+        "allocated_bytes.small_pool.allocated": 517875623424,
+        "allocated_bytes.small_pool.current": 3371008,
+        "allocated_bytes.small_pool.freed": 517872252416,
+        "allocated_bytes.small_pool.peak": 92806144,
+        "allocation.all.allocated": 2473256,
+        "allocation.all.current": 985,
+        "allocation.all.freed": 2472271,
+        "allocation.all.peak": 1150,
+        "allocation.large_pool.allocated": 312449,
+        "allocation.large_pool.current": 225,
+        "allocation.large_pool.freed": 312224,
+        "allocation.large_pool.peak": 275,
+        "allocation.small_pool.allocated": 2160807,
+        "allocation.small_pool.current": 760,
+        "allocation.small_pool.freed": 2160047,
+        "allocation.small_pool.peak": 922,
+        "inactive_split.all.allocated": 1213448,
+        "inactive_split.all.current": 125,
+        "inactive_split.all.freed": 1213323,
+        "inactive_split.all.peak": 184,
+        "inactive_split.large_pool.allocated": 134025,
+        "inactive_split.large_pool.current": 35,
+        "inactive_split.large_pool.freed": 133990,
+        "inactive_split.large_pool.peak": 54,
+        "inactive_split.small_pool.allocated": 1079423,
+        "inactive_split.small_pool.current": 90,
+        "inactive_split.small_pool.freed": 1079333,
+        "inactive_split.small_pool.peak": 132,
+        "inactive_split_bytes.all.allocated": 1641903903232,
+        "inactive_split_bytes.all.current": 109350912,
+        "inactive_split_bytes.all.freed": 1641794552320,
+        "inactive_split_bytes.all.peak": 235275776,
+        "inactive_split_bytes.large_pool.allocated": 1072304889856,
+        "inactive_split_bytes.large_pool.current": 85458944,
+        "inactive_split_bytes.large_pool.freed": 1072219430912,
+        "inactive_split_bytes.large_pool.peak": 232882176,
+        "inactive_split_bytes.small_pool.allocated": 569599013376,
+        "inactive_split_bytes.small_pool.current": 23891968,
+        "inactive_split_bytes.small_pool.freed": 569575121408,
+        "inactive_split_bytes.small_pool.peak": 59134976,
+        "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": 1220912603451,
+        "requested_bytes.all.current": 805709272,
+        "requested_bytes.all.freed": 1220106894179,
+        "requested_bytes.all.peak": 1196292896,
+        "requested_bytes.large_pool.allocated": 703246958916,
+        "requested_bytes.large_pool.current": 802519168,
+        "requested_bytes.large_pool.freed": 702444439748,
+        "requested_bytes.large_pool.peak": 1152089216,
+        "requested_bytes.small_pool.allocated": 517665644535,
+        "requested_bytes.small_pool.current": 3190104,
+        "requested_bytes.small_pool.freed": 517662454431,
+        "requested_bytes.small_pool.peak": 92638528,
+        "reserved_bytes.all.allocated": 1598029824,
+        "reserved_bytes.all.current": 1361051648,
+        "reserved_bytes.all.freed": 236978176,
+        "reserved_bytes.all.peak": 1361051648,
+        "reserved_bytes.large_pool.allocated": 1394606080,
+        "reserved_bytes.large_pool.current": 1247805440,
+        "reserved_bytes.large_pool.freed": 146800640,
+        "reserved_bytes.large_pool.peak": 1247805440,
+        "reserved_bytes.small_pool.allocated": 203423744,
+        "reserved_bytes.small_pool.current": 113246208,
+        "reserved_bytes.small_pool.freed": 90177536,
+        "reserved_bytes.small_pool.peak": 113246208,
+        "segment.all.allocated": 160,
+        "segment.all.current": 110,
+        "segment.all.freed": 50,
+        "segment.all.peak": 110,
+        "segment.large_pool.allocated": 63,
+        "segment.large_pool.current": 56,
+        "segment.large_pool.freed": 7,
+        "segment.large_pool.peak": 56,
+        "segment.small_pool.allocated": 97,
+        "segment.small_pool.current": 54,
+        "segment.small_pool.freed": 43,
+        "segment.small_pool.peak": 54
+    }
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_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]"
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/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]"
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1068/README.md

@@ -0,0 +1,204 @@
+---
+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

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1068/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",
+    "value",
+    "classifier"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1068/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1df61aa9498a0389a64919aacb30722c20e41d39a50f0083ab86b4912f6df53
+size 1267328

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1068/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.41086436230654916}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1068/special_tokens_map.json

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

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1068/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]"
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/README.md

@@ -0,0 +1,204 @@
+---
+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

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/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": [
+    "classifier",
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58d9bd55359c8c0589e7eedacf8135b8f87aca3ee50b7dc98cc58e3ce0d3b30
+size 1267328

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.4037018886554758}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/all_results_la_kron_all_homo_mc_corr_1000.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.4037018886554758}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/all_results_la_kron_last_layer_homo_mc_corr_1000.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.4037018886554758}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/gpu_stats.json

@@ -0,0 +1,127 @@
+{
+    "memory_allocated": 807366656,
+    "max_memory_allocated": 1205814784,
+    "memory_reserved": 1361051648,
+    "max_memory_reserved": 1361051648,
+    "memory_stats": {
+        "active.all.allocated": 4946510,
+        "active.all.current": 985,
+        "active.all.freed": 4945525,
+        "active.all.peak": 1150,
+        "active.large_pool.allocated": 624896,
+        "active.large_pool.current": 225,
+        "active.large_pool.freed": 624671,
+        "active.large_pool.peak": 275,
+        "active.small_pool.allocated": 4321614,
+        "active.small_pool.current": 760,
+        "active.small_pool.freed": 4320854,
+        "active.small_pool.peak": 922,
+        "active_bytes.all.allocated": 2544877711360,
+        "active_bytes.all.current": 807366656,
+        "active_bytes.all.freed": 2544070344704,
+        "active_bytes.all.peak": 1205814784,
+        "active_bytes.large_pool.allocated": 1509126464512,
+        "active_bytes.large_pool.current": 803995648,
+        "active_bytes.large_pool.freed": 1508322468864,
+        "active_bytes.large_pool.peak": 1161462272,
+        "active_bytes.small_pool.allocated": 1035751246848,
+        "active_bytes.small_pool.current": 3371008,
+        "active_bytes.small_pool.freed": 1035747875840,
+        "active_bytes.small_pool.peak": 92806144,
+        "allocated_bytes.all.allocated": 2544877711360,
+        "allocated_bytes.all.current": 807366656,
+        "allocated_bytes.all.freed": 2544070344704,
+        "allocated_bytes.all.peak": 1205814784,
+        "allocated_bytes.large_pool.allocated": 1509126464512,
+        "allocated_bytes.large_pool.current": 803995648,
+        "allocated_bytes.large_pool.freed": 1508322468864,
+        "allocated_bytes.large_pool.peak": 1161462272,
+        "allocated_bytes.small_pool.allocated": 1035751246848,
+        "allocated_bytes.small_pool.current": 3371008,
+        "allocated_bytes.small_pool.freed": 1035747875840,
+        "allocated_bytes.small_pool.peak": 92806144,
+        "allocation.all.allocated": 4946510,
+        "allocation.all.current": 985,
+        "allocation.all.freed": 4945525,
+        "allocation.all.peak": 1150,
+        "allocation.large_pool.allocated": 624896,
+        "allocation.large_pool.current": 225,
+        "allocation.large_pool.freed": 624671,
+        "allocation.large_pool.peak": 275,
+        "allocation.small_pool.allocated": 4321614,
+        "allocation.small_pool.current": 760,
+        "allocation.small_pool.freed": 4320854,
+        "allocation.small_pool.peak": 922,
+        "inactive_split.all.allocated": 2473008,
+        "inactive_split.all.current": 123,
+        "inactive_split.all.freed": 2472885,
+        "inactive_split.all.peak": 184,
+        "inactive_split.large_pool.allocated": 268604,
+        "inactive_split.large_pool.current": 37,
+        "inactive_split.large_pool.freed": 268567,
+        "inactive_split.large_pool.peak": 57,
+        "inactive_split.small_pool.allocated": 2204404,
+        "inactive_split.small_pool.current": 86,
+        "inactive_split.small_pool.freed": 2204318,
+        "inactive_split.small_pool.peak": 147,
+        "inactive_split_bytes.all.allocated": 3366681186816,
+        "inactive_split_bytes.all.current": 117477376,
+        "inactive_split_bytes.all.freed": 3366563709440,
+        "inactive_split_bytes.all.peak": 239890944,
+        "inactive_split_bytes.large_pool.allocated": 2227627612672,
+        "inactive_split_bytes.large_pool.current": 87293952,
+        "inactive_split_bytes.large_pool.freed": 2227540318720,
+        "inactive_split_bytes.large_pool.peak": 233308160,
+        "inactive_split_bytes.small_pool.allocated": 1139053574144,
+        "inactive_split_bytes.small_pool.current": 30183424,
+        "inactive_split_bytes.small_pool.freed": 1139023390720,
+        "inactive_split_bytes.small_pool.peak": 62419968,
+        "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": 2441808167542,
+        "requested_bytes.all.current": 805709272,
+        "requested_bytes.all.freed": 2441002458270,
+        "requested_bytes.all.peak": 1196292896,
+        "requested_bytes.large_pool.allocated": 1406476878472,
+        "requested_bytes.large_pool.current": 802519168,
+        "requested_bytes.large_pool.freed": 1405674359304,
+        "requested_bytes.large_pool.peak": 1152089216,
+        "requested_bytes.small_pool.allocated": 1035331289070,
+        "requested_bytes.small_pool.current": 3190104,
+        "requested_bytes.small_pool.freed": 1035328098966,
+        "requested_bytes.small_pool.peak": 92638528,
+        "reserved_bytes.all.allocated": 2514485248,
+        "reserved_bytes.all.current": 1361051648,
+        "reserved_bytes.all.freed": 1153433600,
+        "reserved_bytes.all.peak": 1361051648,
+        "reserved_bytes.large_pool.allocated": 2128609280,
+        "reserved_bytes.large_pool.current": 1247805440,
+        "reserved_bytes.large_pool.freed": 880803840,
+        "reserved_bytes.large_pool.peak": 1247805440,
+        "reserved_bytes.small_pool.allocated": 385875968,
+        "reserved_bytes.small_pool.current": 113246208,
+        "reserved_bytes.small_pool.freed": 272629760,
+        "reserved_bytes.small_pool.peak": 113246208,
+        "segment.all.allocated": 282,
+        "segment.all.current": 110,
+        "segment.all.freed": 172,
+        "segment.all.peak": 110,
+        "segment.large_pool.allocated": 98,
+        "segment.large_pool.current": 56,
+        "segment.large_pool.freed": 42,
+        "segment.large_pool.peak": 56,
+        "segment.small_pool.allocated": 184,
+        "segment.small_pool.current": 54,
+        "segment.small_pool.freed": 130,
+        "segment.small_pool.peak": 54
+    }
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/special_tokens_map.json

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

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_1282/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]"
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_2137/README.md

@@ -0,0 +1,204 @@
+---
+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

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_2137/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",
+    "value",
+    "classifier"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_2137/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec405a2c9e4434e7470aa261e2a20de60619301e7d81f41aaa7ad141658565f
+size 1267328

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_2137/all_results.json

@@ -0,0 +1 @@
+{"eval_matthews_correlation": 0.4610077931446121}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_2137/special_tokens_map.json

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

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_2137/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]"
+}

cola/outputs/cola/google-bert/bert-base-uncased_lora_lmhead_16_0.1_5e-05_42/step_2565/README.md

@@ -0,0 +1,204 @@
+---
+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