3rd run sst2

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/args.json

@@ -0,0 +1,32 @@
+{
+    "task_name": "sst2",
+    "train_file": null,
+    "validation_file": null,
+    "max_length": 300,
+    "pad_to_max_length": false,
+    "model_name_or_path": "bert-base-uncased",
+    "use_slow_tokenizer": false,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": 8,
+    "learning_rate": 0.0001,
+    "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/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_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,
+    "lora_r": 8,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "testing_set": "train_val"
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/logfile.log

@@ -0,0 +1,23 @@
+05/27/2024 20:16:00 - INFO - __main__ - Sample 27303 of the training set: {'input_ids': [101, 26380, 1010, 2065, 3576, 1010, 27060, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+05/27/2024 20:16:00 - INFO - __main__ - Sample 48017 of the training set: {'input_ids': [101, 2049, 3115, 5675, 102], 'token_type_ids': [0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1], 'labels': 0}.
+05/27/2024 20:16:00 - INFO - __main__ - Sample 666 of the training set: {'input_ids': [101, 2515, 2025, 2147, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1], 'labels': 0}.
+05/27/2024 20:16:02 - INFO - __main__ - ***** Running training *****
+05/27/2024 20:16:02 - INFO - __main__ -   Num examples = 53879
+05/27/2024 20:16:02 - INFO - __main__ -   Num Epochs = 6
+05/27/2024 20:16:02 - INFO - __main__ -   Instantaneous batch size per device = 8
+05/27/2024 20:16:02 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 8
+05/27/2024 20:16:02 - INFO - __main__ -   Gradient Accumulation steps = 1
+05/27/2024 20:16:02 - INFO - __main__ -   Total optimization steps = 40410
+05/27/2024 20:16:07 - INFO - __main__ - epoch 0: {'accuracy': 0.5126146788990825}
+05/27/2024 20:16:39 - INFO - __main__ - epoch 0: {'accuracy': 0.5507795100222718}
+05/27/2024 20:22:06 - INFO - __main__ - epoch 1: {'accuracy': 0.9094036697247706}
+05/27/2024 20:22:41 - INFO - __main__ - epoch 1: {'accuracy': 0.914996288047513}
+05/27/2024 20:28:04 - INFO - __main__ - epoch 2: {'accuracy': 0.908256880733945}
+05/27/2024 20:28:40 - INFO - __main__ - epoch 2: {'accuracy': 0.9270972531551596}
+05/27/2024 20:34:04 - INFO - __main__ - epoch 3: {'accuracy': 0.9139908256880734}
+05/27/2024 20:34:39 - INFO - __main__ - epoch 3: {'accuracy': 0.9314773570898293}
+05/27/2024 20:40:05 - INFO - __main__ - epoch 4: {'accuracy': 0.9139908256880734}
+05/27/2024 20:40:40 - INFO - __main__ - epoch 4: {'accuracy': 0.9365256124721604}
+05/27/2024 20:46:05 - INFO - __main__ - epoch 5: {'accuracy': 0.9139908256880734}
+05/27/2024 20:46:40 - INFO - __main__ - epoch 5: {'accuracy': 0.9357832219747587}
+05/27/2024 20:46:40 - INFO - __main__ - ***** Completed training *****

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_0/README.md

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_0/adapter_config.json

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ba3b2b928c50ddc8ec64450030d492dfc6d7483598a76a4087295b6318b41d
+size 1192672

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_0/all_results.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.5126146788990825}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_0/all_results_val.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.5507795100222718}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_0/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 448793088,
+    "max_memory_allocated": 468217856,
+    "memory_reserved": 524288000,
+    "max_memory_reserved": 524288000,
+    "memory_stats": {
+        "active.all.allocated": 745415,
+        "active.all.current": 266,
+        "active.all.freed": 745149,
+        "active.all.peak": 280,
+        "active.large_pool.allocated": 85008,
+        "active.large_pool.current": 76,
+        "active.large_pool.freed": 84932,
+        "active.large_pool.peak": 83,
+        "active.small_pool.allocated": 660407,
+        "active.small_pool.current": 190,
+        "active.small_pool.freed": 660217,
+        "active.small_pool.peak": 204,
+        "active_bytes.all.allocated": 571169226752,
+        "active_bytes.all.current": 448793088,
+        "active_bytes.all.freed": 570720433664,
+        "active_bytes.all.peak": 468217856,
+        "active_bytes.large_pool.allocated": 219569324032,
+        "active_bytes.large_pool.current": 447086592,
+        "active_bytes.large_pool.freed": 219122237440,
+        "active_bytes.large_pool.peak": 466354176,
+        "active_bytes.small_pool.allocated": 351599902720,
+        "active_bytes.small_pool.current": 1706496,
+        "active_bytes.small_pool.freed": 351598196224,
+        "active_bytes.small_pool.peak": 9006080,
+        "allocated_bytes.all.allocated": 571169226752,
+        "allocated_bytes.all.current": 448793088,
+        "allocated_bytes.all.freed": 570720433664,
+        "allocated_bytes.all.peak": 468217856,
+        "allocated_bytes.large_pool.allocated": 219569324032,
+        "allocated_bytes.large_pool.current": 447086592,
+        "allocated_bytes.large_pool.freed": 219122237440,
+        "allocated_bytes.large_pool.peak": 466354176,
+        "allocated_bytes.small_pool.allocated": 351599902720,
+        "allocated_bytes.small_pool.current": 1706496,
+        "allocated_bytes.small_pool.freed": 351598196224,
+        "allocated_bytes.small_pool.peak": 9006080,
+        "allocation.all.allocated": 745415,
+        "allocation.all.current": 266,
+        "allocation.all.freed": 745149,
+        "allocation.all.peak": 280,
+        "allocation.large_pool.allocated": 85008,
+        "allocation.large_pool.current": 76,
+        "allocation.large_pool.freed": 84932,
+        "allocation.large_pool.peak": 83,
+        "allocation.small_pool.allocated": 660407,
+        "allocation.small_pool.current": 190,
+        "allocation.small_pool.freed": 660217,
+        "allocation.small_pool.peak": 204,
+        "inactive_split.all.allocated": 407787,
+        "inactive_split.all.current": 23,
+        "inactive_split.all.freed": 407764,
+        "inactive_split.all.peak": 33,
+        "inactive_split.large_pool.allocated": 67887,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 67869,
+        "inactive_split.large_pool.peak": 19,
+        "inactive_split.small_pool.allocated": 339900,
+        "inactive_split.small_pool.current": 5,
+        "inactive_split.small_pool.freed": 339895,
+        "inactive_split.small_pool.peak": 15,
+        "inactive_split_bytes.all.allocated": 599999330304,
+        "inactive_split_bytes.all.current": 46134784,
+        "inactive_split_bytes.all.freed": 599953195520,
+        "inactive_split_bytes.all.peak": 59802624,
+        "inactive_split_bytes.large_pool.allocated": 224162217984,
+        "inactive_split_bytes.large_pool.current": 45744128,
+        "inactive_split_bytes.large_pool.freed": 224116473856,
+        "inactive_split_bytes.large_pool.peak": 57409536,
+        "inactive_split_bytes.small_pool.allocated": 375837112320,
+        "inactive_split_bytes.small_pool.current": 390656,
+        "inactive_split_bytes.small_pool.freed": 375836721664,
+        "inactive_split_bytes.small_pool.peak": 6696960,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 26,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 528646731573,
+        "requested_bytes.all.current": 447656440,
+        "requested_bytes.all.freed": 528199075133,
+        "requested_bytes.all.peak": 465652952,
+        "requested_bytes.large_pool.allocated": 177101977600,
+        "requested_bytes.large_pool.current": 445954048,
+        "requested_bytes.large_pool.freed": 176656023552,
+        "requested_bytes.large_pool.peak": 463796224,
+        "requested_bytes.small_pool.allocated": 351544753973,
+        "requested_bytes.small_pool.current": 1702392,
+        "requested_bytes.small_pool.freed": 351543051581,
+        "requested_bytes.small_pool.peak": 8999320,
+        "reserved_bytes.all.allocated": 524288000,
+        "reserved_bytes.all.current": 524288000,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 524288000,
+        "reserved_bytes.large_pool.allocated": 513802240,
+        "reserved_bytes.large_pool.current": 513802240,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 513802240,
+        "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": 26,
+        "segment.all.current": 26,
+        "segment.all.freed": 0,
+        "segment.all.peak": 26,
+        "segment.large_pool.allocated": 21,
+        "segment.large_pool.current": 21,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 21,
+        "segment.small_pool.allocated": 5,
+        "segment.small_pool.current": 5,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 5
+    }
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_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]"
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_0/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_16163/README.md

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_16163/adapter_config.json

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_16163/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8951d0000879006214b7e9ca5db2a4f08ee3e74162dee48170844d669037e7c8
+size 1192672

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_16163/all_results.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.908256880733945}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_16163/all_results_val.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.9270972531551596}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_16163/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 459686912,
+    "max_memory_allocated": 737890304,
+    "memory_reserved": 868220928,
+    "max_memory_reserved": 868220928,
+    "memory_stats": {
+        "active.all.allocated": 17243096,
+        "active.all.current": 367,
+        "active.all.freed": 17242729,
+        "active.all.peak": 627,
+        "active.large_pool.allocated": 2028077,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 2028000,
+        "active.large_pool.peak": 191,
+        "active.small_pool.allocated": 15215019,
+        "active.small_pool.current": 290,
+        "active.small_pool.freed": 15214729,
+        "active.small_pool.peak": 550,
+        "active_bytes.all.allocated": 11627821522944,
+        "active_bytes.all.current": 459686912,
+        "active_bytes.all.freed": 11627361836032,
+        "active_bytes.all.peak": 737890304,
+        "active_bytes.large_pool.allocated": 4524984732672,
+        "active_bytes.large_pool.current": 455606272,
+        "active_bytes.large_pool.freed": 4524529126400,
+        "active_bytes.large_pool.peak": 712212480,
+        "active_bytes.small_pool.allocated": 7102836790272,
+        "active_bytes.small_pool.current": 4080640,
+        "active_bytes.small_pool.freed": 7102832709632,
+        "active_bytes.small_pool.peak": 121664000,
+        "allocated_bytes.all.allocated": 11627821522944,
+        "allocated_bytes.all.current": 459686912,
+        "allocated_bytes.all.freed": 11627361836032,
+        "allocated_bytes.all.peak": 737890304,
+        "allocated_bytes.large_pool.allocated": 4524984732672,
+        "allocated_bytes.large_pool.current": 455606272,
+        "allocated_bytes.large_pool.freed": 4524529126400,
+        "allocated_bytes.large_pool.peak": 712212480,
+        "allocated_bytes.small_pool.allocated": 7102836790272,
+        "allocated_bytes.small_pool.current": 4080640,
+        "allocated_bytes.small_pool.freed": 7102832709632,
+        "allocated_bytes.small_pool.peak": 121664000,
+        "allocation.all.allocated": 17243096,
+        "allocation.all.current": 367,
+        "allocation.all.freed": 17242729,
+        "allocation.all.peak": 627,
+        "allocation.large_pool.allocated": 2028077,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 2028000,
+        "allocation.large_pool.peak": 191,
+        "allocation.small_pool.allocated": 15215019,
+        "allocation.small_pool.current": 290,
+        "allocation.small_pool.freed": 15214729,
+        "allocation.small_pool.peak": 550,
+        "inactive_split.all.allocated": 8572581,
+        "inactive_split.all.current": 33,
+        "inactive_split.all.freed": 8572548,
+        "inactive_split.all.peak": 103,
+        "inactive_split.large_pool.allocated": 1391934,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 1391915,
+        "inactive_split.large_pool.peak": 22,
+        "inactive_split.small_pool.allocated": 7180647,
+        "inactive_split.small_pool.current": 14,
+        "inactive_split.small_pool.freed": 7180633,
+        "inactive_split.small_pool.peak": 84,
+        "inactive_split_bytes.all.allocated": 13619085684736,
+        "inactive_split_bytes.all.current": 66698240,
+        "inactive_split_bytes.all.freed": 13619018986496,
+        "inactive_split_bytes.all.peak": 126964736,
+        "inactive_split_bytes.large_pool.allocated": 5880575213568,
+        "inactive_split_bytes.large_pool.current": 58195968,
+        "inactive_split_bytes.large_pool.freed": 5880517017600,
+        "inactive_split_bytes.large_pool.peak": 68288512,
+        "inactive_split_bytes.small_pool.allocated": 7738510471168,
+        "inactive_split_bytes.small_pool.current": 8502272,
+        "inactive_split_bytes.small_pool.freed": 7738501968896,
+        "inactive_split_bytes.small_pool.peak": 68768768,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 91,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 11156365995532,
+        "requested_bytes.all.current": 458548104,
+        "requested_bytes.all.freed": 11155907447428,
+        "requested_bytes.all.peak": 728291116,
+        "requested_bytes.large_pool.allocated": 4054250696192,
+        "requested_bytes.large_pool.current": 454473728,
+        "requested_bytes.large_pool.freed": 4053796222464,
+        "requested_bytes.large_pool.peak": 702642176,
+        "requested_bytes.small_pool.allocated": 7102115299340,
+        "requested_bytes.small_pool.current": 4074376,
+        "requested_bytes.small_pool.freed": 7102111224964,
+        "requested_bytes.small_pool.peak": 121647404,
+        "reserved_bytes.all.allocated": 868220928,
+        "reserved_bytes.all.current": 868220928,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 868220928,
+        "reserved_bytes.large_pool.allocated": 744488960,
+        "reserved_bytes.large_pool.current": 744488960,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 744488960,
+        "reserved_bytes.small_pool.allocated": 123731968,
+        "reserved_bytes.small_pool.current": 123731968,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 123731968,
+        "segment.all.allocated": 91,
+        "segment.all.current": 91,
+        "segment.all.freed": 0,
+        "segment.all.peak": 91,
+        "segment.large_pool.allocated": 32,
+        "segment.large_pool.current": 32,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 32,
+        "segment.small_pool.allocated": 59,
+        "segment.small_pool.current": 59,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 59
+    }
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_16163/special_tokens_map.json

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_16163/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_24245/README.md

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_24245/adapter_config.json

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_24245/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab7592750a9010936ce23a0081202b82ba1463ecc6f0fb3e5dcb656345d0851
+size 1192672

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_24245/all_results.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.9139908256880734}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_24245/all_results_val.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.9314773570898293}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_24245/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 459685376,
+    "max_memory_allocated": 737890304,
+    "memory_reserved": 868220928,
+    "max_memory_reserved": 868220928,
+    "memory_stats": {
+        "active.all.allocated": 25492525,
+        "active.all.current": 367,
+        "active.all.freed": 25492158,
+        "active.all.peak": 627,
+        "active.large_pool.allocated": 3016981,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 3016904,
+        "active.large_pool.peak": 191,
+        "active.small_pool.allocated": 22475544,
+        "active.small_pool.current": 290,
+        "active.small_pool.freed": 22475254,
+        "active.small_pool.peak": 550,
+        "active_bytes.all.allocated": 17175418445824,
+        "active_bytes.all.current": 459685376,
+        "active_bytes.all.freed": 17174958760448,
+        "active_bytes.all.peak": 737890304,
+        "active_bytes.large_pool.allocated": 6706463538176,
+        "active_bytes.large_pool.current": 455606272,
+        "active_bytes.large_pool.freed": 6706007931904,
+        "active_bytes.large_pool.peak": 712212480,
+        "active_bytes.small_pool.allocated": 10468954907648,
+        "active_bytes.small_pool.current": 4079104,
+        "active_bytes.small_pool.freed": 10468950828544,
+        "active_bytes.small_pool.peak": 121664000,
+        "allocated_bytes.all.allocated": 17175418445824,
+        "allocated_bytes.all.current": 459685376,
+        "allocated_bytes.all.freed": 17174958760448,
+        "allocated_bytes.all.peak": 737890304,
+        "allocated_bytes.large_pool.allocated": 6706463538176,
+        "allocated_bytes.large_pool.current": 455606272,
+        "allocated_bytes.large_pool.freed": 6706007931904,
+        "allocated_bytes.large_pool.peak": 712212480,
+        "allocated_bytes.small_pool.allocated": 10468954907648,
+        "allocated_bytes.small_pool.current": 4079104,
+        "allocated_bytes.small_pool.freed": 10468950828544,
+        "allocated_bytes.small_pool.peak": 121664000,
+        "allocation.all.allocated": 25492525,
+        "allocation.all.current": 367,
+        "allocation.all.freed": 25492158,
+        "allocation.all.peak": 627,
+        "allocation.large_pool.allocated": 3016981,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 3016904,
+        "allocation.large_pool.peak": 191,
+        "allocation.small_pool.allocated": 22475544,
+        "allocation.small_pool.current": 290,
+        "allocation.small_pool.freed": 22475254,
+        "allocation.small_pool.peak": 550,
+        "inactive_split.all.allocated": 12656345,
+        "inactive_split.all.current": 35,
+        "inactive_split.all.freed": 12656310,
+        "inactive_split.all.peak": 103,
+        "inactive_split.large_pool.allocated": 2066625,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 2066606,
+        "inactive_split.large_pool.peak": 22,
+        "inactive_split.small_pool.allocated": 10589720,
+        "inactive_split.small_pool.current": 16,
+        "inactive_split.small_pool.freed": 10589704,
+        "inactive_split.small_pool.peak": 84,
+        "inactive_split_bytes.all.allocated": 20154876839424,
+        "inactive_split_bytes.all.current": 68796928,
+        "inactive_split_bytes.all.freed": 20154808042496,
+        "inactive_split_bytes.all.peak": 126964736,
+        "inactive_split_bytes.large_pool.allocated": 8747198264320,
+        "inactive_split_bytes.large_pool.current": 58195968,
+        "inactive_split_bytes.large_pool.freed": 8747140068352,
+        "inactive_split_bytes.large_pool.peak": 68288512,
+        "inactive_split_bytes.small_pool.allocated": 11407678575104,
+        "inactive_split_bytes.small_pool.current": 10600960,
+        "inactive_split_bytes.small_pool.freed": 11407667974144,
+        "inactive_split_bytes.small_pool.peak": 68768768,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 91,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 16485959412975,
+        "requested_bytes.all.current": 458546760,
+        "requested_bytes.all.freed": 16485500866215,
+        "requested_bytes.all.peak": 728291116,
+        "requested_bytes.large_pool.allocated": 6018059392256,
+        "requested_bytes.large_pool.current": 454473728,
+        "requested_bytes.large_pool.freed": 6017604918528,
+        "requested_bytes.large_pool.peak": 702642176,
+        "requested_bytes.small_pool.allocated": 10467900020719,
+        "requested_bytes.small_pool.current": 4073032,
+        "requested_bytes.small_pool.freed": 10467895947687,
+        "requested_bytes.small_pool.peak": 121647404,
+        "reserved_bytes.all.allocated": 868220928,
+        "reserved_bytes.all.current": 868220928,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 868220928,
+        "reserved_bytes.large_pool.allocated": 744488960,
+        "reserved_bytes.large_pool.current": 744488960,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 744488960,
+        "reserved_bytes.small_pool.allocated": 123731968,
+        "reserved_bytes.small_pool.current": 123731968,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 123731968,
+        "segment.all.allocated": 91,
+        "segment.all.current": 91,
+        "segment.all.freed": 0,
+        "segment.all.peak": 91,
+        "segment.large_pool.allocated": 32,
+        "segment.large_pool.current": 32,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 32,
+        "segment.small_pool.allocated": 59,
+        "segment.small_pool.current": 59,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 59
+    }
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_24245/special_tokens_map.json

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_24245/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_32327/README.md

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_32327/adapter_config.json

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_32327/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66194733614f4c4c13fc58fb060fd9757680cdac9faf3f13639042df94f9f025
+size 1192672

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_32327/all_results.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.9139908256880734}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_32327/all_results_val.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.9365256124721604}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_32327/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 459686912,
+    "max_memory_allocated": 737890304,
+    "memory_reserved": 868220928,
+    "max_memory_reserved": 868220928,
+    "memory_stats": {
+        "active.all.allocated": 33741786,
+        "active.all.current": 367,
+        "active.all.freed": 33741419,
+        "active.all.peak": 627,
+        "active.large_pool.allocated": 3984369,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 3984292,
+        "active.large_pool.peak": 191,
+        "active.small_pool.allocated": 29757417,
+        "active.small_pool.current": 290,
+        "active.small_pool.freed": 29757127,
+        "active.small_pool.peak": 550,
+        "active_bytes.all.allocated": 22700349888512,
+        "active_bytes.all.current": 459686912,
+        "active_bytes.all.freed": 22699890201600,
+        "active_bytes.all.peak": 737890304,
+        "active_bytes.large_pool.allocated": 8852519870464,
+        "active_bytes.large_pool.current": 455606272,
+        "active_bytes.large_pool.freed": 8852064264192,
+        "active_bytes.large_pool.peak": 712212480,
+        "active_bytes.small_pool.allocated": 13847830018048,
+        "active_bytes.small_pool.current": 4080640,
+        "active_bytes.small_pool.freed": 13847825937408,
+        "active_bytes.small_pool.peak": 121664000,
+        "allocated_bytes.all.allocated": 22700349888512,
+        "allocated_bytes.all.current": 459686912,
+        "allocated_bytes.all.freed": 22699890201600,
+        "allocated_bytes.all.peak": 737890304,
+        "allocated_bytes.large_pool.allocated": 8852519870464,
+        "allocated_bytes.large_pool.current": 455606272,
+        "allocated_bytes.large_pool.freed": 8852064264192,
+        "allocated_bytes.large_pool.peak": 712212480,
+        "allocated_bytes.small_pool.allocated": 13847830018048,
+        "allocated_bytes.small_pool.current": 4080640,
+        "allocated_bytes.small_pool.freed": 13847825937408,
+        "allocated_bytes.small_pool.peak": 121664000,
+        "allocation.all.allocated": 33741786,
+        "allocation.all.current": 367,
+        "allocation.all.freed": 33741419,
+        "allocation.all.peak": 627,
+        "allocation.large_pool.allocated": 3984369,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 3984292,
+        "allocation.large_pool.peak": 191,
+        "allocation.small_pool.allocated": 29757417,
+        "allocation.small_pool.current": 290,
+        "allocation.small_pool.freed": 29757127,
+        "allocation.small_pool.peak": 550,
+        "inactive_split.all.allocated": 16736217,
+        "inactive_split.all.current": 35,
+        "inactive_split.all.freed": 16736182,
+        "inactive_split.all.peak": 103,
+        "inactive_split.large_pool.allocated": 2727199,
+        "inactive_split.large_pool.current": 19,
+        "inactive_split.large_pool.freed": 2727180,
+        "inactive_split.large_pool.peak": 22,
+        "inactive_split.small_pool.allocated": 14009018,
+        "inactive_split.small_pool.current": 16,
+        "inactive_split.small_pool.freed": 14009002,
+        "inactive_split.small_pool.peak": 84,
+        "inactive_split_bytes.all.allocated": 26659522500096,
+        "inactive_split_bytes.all.current": 66698240,
+        "inactive_split_bytes.all.freed": 26659455801856,
+        "inactive_split_bytes.all.peak": 126964736,
+        "inactive_split_bytes.large_pool.allocated": 11566933429248,
+        "inactive_split_bytes.large_pool.current": 58195968,
+        "inactive_split_bytes.large_pool.freed": 11566875233280,
+        "inactive_split_bytes.large_pool.peak": 68288512,
+        "inactive_split_bytes.small_pool.allocated": 15092589070848,
+        "inactive_split_bytes.small_pool.current": 8502272,
+        "inactive_split_bytes.small_pool.freed": 15092580568576,
+        "inactive_split_bytes.small_pool.peak": 68768768,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 91,
+        "num_device_free": 0,
+        "num_ooms": 0,
+        "num_sync_all_streams": 0,
+        "oversize_allocations.allocated": 0,
+        "oversize_allocations.current": 0,
+        "oversize_allocations.freed": 0,
+        "oversize_allocations.peak": 0,
+        "oversize_segments.allocated": 0,
+        "oversize_segments.current": 0,
+        "oversize_segments.freed": 0,
+        "oversize_segments.peak": 0,
+        "requested_bytes.all.allocated": 21797095729088,
+        "requested_bytes.all.current": 458548680,
+        "requested_bytes.all.freed": 21796637180408,
+        "requested_bytes.all.peak": 728291116,
+        "requested_bytes.large_pool.allocated": 7950655192064,
+        "requested_bytes.large_pool.current": 454473728,
+        "requested_bytes.large_pool.freed": 7950200718336,
+        "requested_bytes.large_pool.peak": 702642176,
+        "requested_bytes.small_pool.allocated": 13846440537024,
+        "requested_bytes.small_pool.current": 4074952,
+        "requested_bytes.small_pool.freed": 13846436462072,
+        "requested_bytes.small_pool.peak": 121647404,
+        "reserved_bytes.all.allocated": 868220928,
+        "reserved_bytes.all.current": 868220928,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 868220928,
+        "reserved_bytes.large_pool.allocated": 744488960,
+        "reserved_bytes.large_pool.current": 744488960,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 744488960,
+        "reserved_bytes.small_pool.allocated": 123731968,
+        "reserved_bytes.small_pool.current": 123731968,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 123731968,
+        "segment.all.allocated": 91,
+        "segment.all.current": 91,
+        "segment.all.freed": 0,
+        "segment.all.peak": 91,
+        "segment.large_pool.allocated": 32,
+        "segment.large_pool.current": 32,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 32,
+        "segment.small_pool.allocated": 59,
+        "segment.small_pool.current": 59,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 59
+    }
+}

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_32327/special_tokens_map.json

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

outputs/sst2/bert-base-uncased_loratrain_val_8_16_0.1_0.0001_12345/step_32327/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}