stsb

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/args.json

@@ -0,0 +1,32 @@
+{
+    "task_name": "qnli",
+    "train_file": null,
+    "validation_file": null,
+    "max_length": 300,
+    "pad_to_max_length": false,
+    "model_name_or_path": "roberta-base",
+    "use_slow_tokenizer": false,
+    "per_device_train_batch_size": 32,
+    "per_device_eval_batch_size": 1,
+    "learning_rate": 0.0001,
+    "weight_decay": 0.0,
+    "num_train_epochs": 3,
+    "max_train_steps": null,
+    "gradient_accumulation_steps": 1,
+    "lr_scheduler_type": "linear",
+    "num_warmup_steps": 0,
+    "output_dir": "./outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65",
+    "seed": 65,
+    "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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/logfile.log

@@ -0,0 +1,23 @@
+05/25/2024 20:30:50 - INFO - __main__ - Sample 54361 of the training set: {'input_ids': [0, 12375, 26, 730, 8944, 18217, 7396, 5, 44665, 116, 2, 2, 33243, 38903, 33, 555, 55, 1406, 11, 730, 4, 2], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+05/25/2024 20:30:50 - INFO - __main__ - Sample 37859 of the training set: {'input_ids': [0, 2264, 3195, 222, 3345, 1771, 4800, 6345, 5, 83, 116, 2, 2, 713, 21, 1432, 30, 10, 6345, 2850, 15315, 147, 5, 22, 250, 113, 21, 10122, 1337, 8089, 454, 5, 343, 1676, 21187, 4, 2], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+05/25/2024 20:30:50 - INFO - __main__ - Sample 37709 of the training set: {'input_ids': [0, 6179, 251, 71, 5, 8969, 58, 71, 1193, 6368, 1299, 116, 2, 2, 243, 16, 67, 684, 25, 5, 305, 24071, 7372, 8969, 36, 24727, 35, 47416, 15389, 19002, 48494, 46, 48262, 46537, 7487, 41907, 48, 6382, 131, 181, 11287, 179, 35, 305, 8025, 282, 39037, 18195, 282, 385, 5269, 385, 3849, 11582, 13808, 8025, 282, 131, 5909, 35, 22, 19065, 305, 24071, 7372, 8969, 16844, 71, 5, 2259, 9, 5, 8969, 18, 9066, 11798, 6, 305, 24071, 7372, 413, 6, 208, 1725, 7372, 4, 2], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
+05/25/2024 20:30:51 - INFO - __main__ - ***** Running training *****
+05/25/2024 20:30:51 - INFO - __main__ -   Num examples = 83794
+05/25/2024 20:30:51 - INFO - __main__ -   Num Epochs = 3
+05/25/2024 20:30:51 - INFO - __main__ -   Instantaneous batch size per device = 32
+05/25/2024 20:30:51 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 32
+05/25/2024 20:30:51 - INFO - __main__ -   Gradient Accumulation steps = 1
+05/25/2024 20:30:51 - INFO - __main__ -   Total optimization steps = 7857
+05/25/2024 20:32:16 - INFO - __main__ - epoch 0: {'accuracy': 0.4946000366099213}
+05/25/2024 20:37:44 - INFO - __main__ - epoch 0: {'accuracy': 0.49964198768437634}
+05/25/2024 20:49:13 - INFO - __main__ - epoch 0: {'accuracy': 0.880468606992495}
+05/25/2024 20:54:47 - INFO - __main__ - epoch 0: {'accuracy': 0.8666284786863335}
+05/25/2024 21:06:18 - INFO - __main__ - epoch 1: {'accuracy': 0.8923668314113125}
+05/25/2024 21:11:48 - INFO - __main__ - epoch 1: {'accuracy': 0.8767482934746289}
+05/25/2024 21:23:17 - INFO - __main__ - epoch 1: {'accuracy': 0.900054914881933}
+05/25/2024 21:28:52 - INFO - __main__ - epoch 1: {'accuracy': 0.8849587092462647}
+05/25/2024 21:40:25 - INFO - __main__ - epoch 2: {'accuracy': 0.9022515101592532}
+05/25/2024 21:45:56 - INFO - __main__ - epoch 2: {'accuracy': 0.8869635782137573}
+05/25/2024 21:57:25 - INFO - __main__ - epoch 2: {'accuracy': 0.9024345597656965}
+05/25/2024 22:02:55 - INFO - __main__ - epoch 2: {'accuracy': 0.8893025920091651}
+05/25/2024 22:02:55 - INFO - __main__ - ***** Completed training *****

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_0/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: roberta-base
+---
+
+# 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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_0/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roberta-base",
+  "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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc51ea97e347c85fd7587dc382b4a880dd45dd012714a9dfdc87be87351bec77
+size 3555504

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_0/all_results.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.4946000366099213}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_0/all_results_val.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.49964198768437634}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_0/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 512017408,
+    "max_memory_allocated": 527116288,
+    "memory_reserved": 585105408,
+    "max_memory_reserved": 585105408,
+    "memory_stats": {
+        "active.all.allocated": 12070543,
+        "active.all.current": 266,
+        "active.all.freed": 12070277,
+        "active.all.peak": 279,
+        "active.large_pool.allocated": 31253,
+        "active.large_pool.current": 77,
+        "active.large_pool.freed": 31176,
+        "active.large_pool.peak": 79,
+        "active.small_pool.allocated": 12039290,
+        "active.small_pool.current": 189,
+        "active.small_pool.freed": 12039101,
+        "active.small_pool.peak": 202,
+        "active_bytes.all.allocated": 3527343329792,
+        "active_bytes.all.current": 512017408,
+        "active_bytes.all.freed": 3526831312384,
+        "active_bytes.all.peak": 527116288,
+        "active_bytes.large_pool.allocated": 66931965952,
+        "active_bytes.large_pool.current": 510263296,
+        "active_bytes.large_pool.freed": 66421702656,
+        "active_bytes.large_pool.peak": 518903808,
+        "active_bytes.small_pool.allocated": 3460411363840,
+        "active_bytes.small_pool.current": 1754112,
+        "active_bytes.small_pool.freed": 3460409609728,
+        "active_bytes.small_pool.peak": 8212480,
+        "allocated_bytes.all.allocated": 3527343329792,
+        "allocated_bytes.all.current": 512017408,
+        "allocated_bytes.all.freed": 3526831312384,
+        "allocated_bytes.all.peak": 527116288,
+        "allocated_bytes.large_pool.allocated": 66931965952,
+        "allocated_bytes.large_pool.current": 510263296,
+        "allocated_bytes.large_pool.freed": 66421702656,
+        "allocated_bytes.large_pool.peak": 518903808,
+        "allocated_bytes.small_pool.allocated": 3460411363840,
+        "allocated_bytes.small_pool.current": 1754112,
+        "allocated_bytes.small_pool.freed": 3460409609728,
+        "allocated_bytes.small_pool.peak": 8212480,
+        "allocation.all.allocated": 12070543,
+        "allocation.all.current": 266,
+        "allocation.all.freed": 12070277,
+        "allocation.all.peak": 279,
+        "allocation.large_pool.allocated": 31253,
+        "allocation.large_pool.current": 77,
+        "allocation.large_pool.freed": 31176,
+        "allocation.large_pool.peak": 79,
+        "allocation.small_pool.allocated": 12039290,
+        "allocation.small_pool.current": 189,
+        "allocation.small_pool.freed": 12039101,
+        "allocation.small_pool.peak": 202,
+        "inactive_split.all.allocated": 5392196,
+        "inactive_split.all.current": 22,
+        "inactive_split.all.freed": 5392174,
+        "inactive_split.all.peak": 31,
+        "inactive_split.large_pool.allocated": 30691,
+        "inactive_split.large_pool.current": 18,
+        "inactive_split.large_pool.freed": 30673,
+        "inactive_split.large_pool.peak": 19,
+        "inactive_split.small_pool.allocated": 5361505,
+        "inactive_split.small_pool.current": 4,
+        "inactive_split.small_pool.freed": 5361501,
+        "inactive_split.small_pool.peak": 13,
+        "inactive_split_bytes.all.allocated": 3642637821440,
+        "inactive_split_bytes.all.current": 43727872,
+        "inactive_split_bytes.all.freed": 3642594093568,
+        "inactive_split_bytes.all.peak": 65995776,
+        "inactive_split_bytes.large_pool.allocated": 68170901504,
+        "inactive_split_bytes.large_pool.current": 43384832,
+        "inactive_split_bytes.large_pool.freed": 68127516672,
+        "inactive_split_bytes.large_pool.peak": 60036096,
+        "inactive_split_bytes.small_pool.allocated": 3574466919936,
+        "inactive_split_bytes.small_pool.current": 343040,
+        "inactive_split_bytes.small_pool.freed": 3574466576896,
+        "inactive_split_bytes.small_pool.peak": 6625792,
+        "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": 3500945156721,
+        "requested_bytes.all.current": 510718464,
+        "requested_bytes.all.freed": 3500434438257,
+        "requested_bytes.all.peak": 525815960,
+        "requested_bytes.large_pool.allocated": 41654235136,
+        "requested_bytes.large_pool.current": 508969984,
+        "requested_bytes.large_pool.freed": 41145265152,
+        "requested_bytes.large_pool.peak": 517609984,
+        "requested_bytes.small_pool.allocated": 3459290921585,
+        "requested_bytes.small_pool.current": 1748480,
+        "requested_bytes.small_pool.freed": 3459289173105,
+        "requested_bytes.small_pool.peak": 8205976,
+        "reserved_bytes.all.allocated": 585105408,
+        "reserved_bytes.all.current": 585105408,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 585105408,
+        "reserved_bytes.large_pool.allocated": 574619648,
+        "reserved_bytes.large_pool.current": 574619648,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 574619648,
+        "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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_0/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_0/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_1570/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: roberta-base
+---
+
+# 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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_1570/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roberta-base",
+  "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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_1570/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950aa6020400e345e3bcfe21c043aeaa8d920141e6ec26eae3062ecb7873ea73
+size 3555504

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_1570/all_results.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.880468606992495}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_1570/all_results_val.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.8666284786863335}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_1570/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 527800320,
+    "max_memory_allocated": 8744655360,
+    "memory_reserved": 13371441152,
+    "max_memory_reserved": 13371441152,
+    "memory_stats": {
+        "active.all.allocated": 25864792,
+        "active.all.current": 371,
+        "active.all.freed": 25864421,
+        "active.all.peak": 632,
+        "active.large_pool.allocated": 1290172,
+        "active.large_pool.current": 80,
+        "active.large_pool.freed": 1290092,
+        "active.large_pool.peak": 263,
+        "active.small_pool.allocated": 24574620,
+        "active.small_pool.current": 291,
+        "active.small_pool.freed": 24574329,
+        "active.small_pool.peak": 392,
+        "active_bytes.all.allocated": 22786853283328,
+        "active_bytes.all.current": 527800320,
+        "active_bytes.all.freed": 22786325483008,
+        "active_bytes.all.peak": 8744655360,
+        "active_bytes.large_pool.allocated": 15729341594624,
+        "active_bytes.large_pool.current": 523673600,
+        "active_bytes.large_pool.freed": 15728817921024,
+        "active_bytes.large_pool.peak": 8731166720,
+        "active_bytes.small_pool.allocated": 7057511688704,
+        "active_bytes.small_pool.current": 4126720,
+        "active_bytes.small_pool.freed": 7057507561984,
+        "active_bytes.small_pool.peak": 14843392,
+        "allocated_bytes.all.allocated": 22786853283328,
+        "allocated_bytes.all.current": 527800320,
+        "allocated_bytes.all.freed": 22786325483008,
+        "allocated_bytes.all.peak": 8744655360,
+        "allocated_bytes.large_pool.allocated": 15729341594624,
+        "allocated_bytes.large_pool.current": 523673600,
+        "allocated_bytes.large_pool.freed": 15728817921024,
+        "allocated_bytes.large_pool.peak": 8731166720,
+        "allocated_bytes.small_pool.allocated": 7057511688704,
+        "allocated_bytes.small_pool.current": 4126720,
+        "allocated_bytes.small_pool.freed": 7057507561984,
+        "allocated_bytes.small_pool.peak": 14843392,
+        "allocation.all.allocated": 25864792,
+        "allocation.all.current": 371,
+        "allocation.all.freed": 25864421,
+        "allocation.all.peak": 632,
+        "allocation.large_pool.allocated": 1290172,
+        "allocation.large_pool.current": 80,
+        "allocation.large_pool.freed": 1290092,
+        "allocation.large_pool.peak": 263,
+        "allocation.small_pool.allocated": 24574620,
+        "allocation.small_pool.current": 291,
+        "allocation.small_pool.freed": 24574329,
+        "allocation.small_pool.peak": 392,
+        "inactive_split.all.allocated": 12511461,
+        "inactive_split.all.current": 33,
+        "inactive_split.all.freed": 12511428,
+        "inactive_split.all.peak": 156,
+        "inactive_split.large_pool.allocated": 975683,
+        "inactive_split.large_pool.current": 20,
+        "inactive_split.large_pool.freed": 975663,
+        "inactive_split.large_pool.peak": 140,
+        "inactive_split.small_pool.allocated": 11535778,
+        "inactive_split.small_pool.current": 13,
+        "inactive_split.small_pool.freed": 11535765,
+        "inactive_split.small_pool.peak": 40,
+        "inactive_split_bytes.all.allocated": 18896960278528,
+        "inactive_split_bytes.all.current": 69888000,
+        "inactive_split_bytes.all.freed": 18896890390528,
+        "inactive_split_bytes.all.peak": 1840782336,
+        "inactive_split_bytes.large_pool.allocated": 11352037166592,
+        "inactive_split_bytes.large_pool.current": 67723264,
+        "inactive_split_bytes.large_pool.freed": 11351969443328,
+        "inactive_split_bytes.large_pool.peak": 1839972352,
+        "inactive_split_bytes.small_pool.allocated": 7544923111936,
+        "inactive_split_bytes.small_pool.current": 2164736,
+        "inactive_split_bytes.small_pool.freed": 7544920947200,
+        "inactive_split_bytes.small_pool.peak": 9822208,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 230,
+        "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": 22659839680426,
+        "requested_bytes.all.current": 526328848,
+        "requested_bytes.all.freed": 22659313351578,
+        "requested_bytes.all.peak": 8736087300,
+        "requested_bytes.large_pool.allocated": 15604598829056,
+        "requested_bytes.large_pool.current": 522208256,
+        "requested_bytes.large_pool.freed": 15604076620800,
+        "requested_bytes.large_pool.peak": 8722605056,
+        "requested_bytes.small_pool.allocated": 7055240851370,
+        "requested_bytes.small_pool.current": 4120592,
+        "requested_bytes.small_pool.freed": 7055236730778,
+        "requested_bytes.small_pool.peak": 14836740,
+        "reserved_bytes.all.allocated": 13371441152,
+        "reserved_bytes.all.current": 13371441152,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 13371441152,
+        "reserved_bytes.large_pool.allocated": 13354663936,
+        "reserved_bytes.large_pool.current": 13354663936,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 13354663936,
+        "reserved_bytes.small_pool.allocated": 16777216,
+        "reserved_bytes.small_pool.current": 16777216,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 16777216,
+        "segment.all.allocated": 230,
+        "segment.all.current": 230,
+        "segment.all.freed": 0,
+        "segment.all.peak": 230,
+        "segment.large_pool.allocated": 222,
+        "segment.large_pool.current": 222,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 222,
+        "segment.small_pool.allocated": 8,
+        "segment.small_pool.current": 8,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 8
+    }
+}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_1570/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_1570/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_3141/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: roberta-base
+---
+
+# 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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_3141/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roberta-base",
+  "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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_3141/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45562d8ddf7149005e4eaa83444fc309dd6e5eb341cca61e0c8cbcc2b9fd26d9
+size 3555504

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_3141/all_results.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.8923668314113125}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_3141/all_results_val.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.8767482934746289}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_3141/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 527801344,
+    "max_memory_allocated": 8744655360,
+    "memory_reserved": 13371441152,
+    "max_memory_reserved": 13371441152,
+    "memory_stats": {
+        "active.all.allocated": 39660034,
+        "active.all.current": 371,
+        "active.all.freed": 39659663,
+        "active.all.peak": 632,
+        "active.large_pool.allocated": 2549870,
+        "active.large_pool.current": 80,
+        "active.large_pool.freed": 2549790,
+        "active.large_pool.peak": 263,
+        "active.small_pool.allocated": 37110164,
+        "active.small_pool.current": 291,
+        "active.small_pool.freed": 37109873,
+        "active.small_pool.peak": 392,
+        "active_bytes.all.allocated": 42030823416320,
+        "active_bytes.all.current": 527801344,
+        "active_bytes.all.freed": 42030295614976,
+        "active_bytes.all.peak": 8744655360,
+        "active_bytes.large_pool.allocated": 31376120677376,
+        "active_bytes.large_pool.current": 523673600,
+        "active_bytes.large_pool.freed": 31375597003776,
+        "active_bytes.large_pool.peak": 8731166720,
+        "active_bytes.small_pool.allocated": 10654702738944,
+        "active_bytes.small_pool.current": 4127744,
+        "active_bytes.small_pool.freed": 10654698611200,
+        "active_bytes.small_pool.peak": 14843392,
+        "allocated_bytes.all.allocated": 42030823416320,
+        "allocated_bytes.all.current": 527801344,
+        "allocated_bytes.all.freed": 42030295614976,
+        "allocated_bytes.all.peak": 8744655360,
+        "allocated_bytes.large_pool.allocated": 31376120677376,
+        "allocated_bytes.large_pool.current": 523673600,
+        "allocated_bytes.large_pool.freed": 31375597003776,
+        "allocated_bytes.large_pool.peak": 8731166720,
+        "allocated_bytes.small_pool.allocated": 10654702738944,
+        "allocated_bytes.small_pool.current": 4127744,
+        "allocated_bytes.small_pool.freed": 10654698611200,
+        "allocated_bytes.small_pool.peak": 14843392,
+        "allocation.all.allocated": 39660034,
+        "allocation.all.current": 371,
+        "allocation.all.freed": 39659663,
+        "allocation.all.peak": 632,
+        "allocation.large_pool.allocated": 2549870,
+        "allocation.large_pool.current": 80,
+        "allocation.large_pool.freed": 2549790,
+        "allocation.large_pool.peak": 263,
+        "allocation.small_pool.allocated": 37110164,
+        "allocation.small_pool.current": 291,
+        "allocation.small_pool.freed": 37109873,
+        "allocation.small_pool.peak": 392,
+        "inactive_split.all.allocated": 19606763,
+        "inactive_split.all.current": 33,
+        "inactive_split.all.freed": 19606730,
+        "inactive_split.all.peak": 156,
+        "inactive_split.large_pool.allocated": 1924081,
+        "inactive_split.large_pool.current": 20,
+        "inactive_split.large_pool.freed": 1924061,
+        "inactive_split.large_pool.peak": 140,
+        "inactive_split.small_pool.allocated": 17682682,
+        "inactive_split.small_pool.current": 13,
+        "inactive_split.small_pool.freed": 17682669,
+        "inactive_split.small_pool.peak": 40,
+        "inactive_split_bytes.all.allocated": 34200162030592,
+        "inactive_split_bytes.all.current": 69886976,
+        "inactive_split_bytes.all.freed": 34200092143616,
+        "inactive_split_bytes.all.peak": 1840782336,
+        "inactive_split_bytes.large_pool.allocated": 22692013244416,
+        "inactive_split_bytes.large_pool.current": 67723264,
+        "inactive_split_bytes.large_pool.freed": 22691945521152,
+        "inactive_split_bytes.large_pool.peak": 1839972352,
+        "inactive_split_bytes.small_pool.allocated": 11508148786176,
+        "inactive_split_bytes.small_pool.current": 2163712,
+        "inactive_split_bytes.small_pool.freed": 11508146622464,
+        "inactive_split_bytes.small_pool.peak": 9822208,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 230,
+        "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": 41806586657705,
+        "requested_bytes.all.current": 526329872,
+        "requested_bytes.all.freed": 41806060327833,
+        "requested_bytes.all.peak": 8736087300,
+        "requested_bytes.large_pool.allocated": 31155305554976,
+        "requested_bytes.large_pool.current": 522208256,
+        "requested_bytes.large_pool.freed": 31154783346720,
+        "requested_bytes.large_pool.peak": 8722605056,
+        "requested_bytes.small_pool.allocated": 10651281102729,
+        "requested_bytes.small_pool.current": 4121616,
+        "requested_bytes.small_pool.freed": 10651276981113,
+        "requested_bytes.small_pool.peak": 14836740,
+        "reserved_bytes.all.allocated": 13371441152,
+        "reserved_bytes.all.current": 13371441152,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 13371441152,
+        "reserved_bytes.large_pool.allocated": 13354663936,
+        "reserved_bytes.large_pool.current": 13354663936,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 13354663936,
+        "reserved_bytes.small_pool.allocated": 16777216,
+        "reserved_bytes.small_pool.current": 16777216,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 16777216,
+        "segment.all.allocated": 230,
+        "segment.all.current": 230,
+        "segment.all.freed": 0,
+        "segment.all.peak": 230,
+        "segment.large_pool.allocated": 222,
+        "segment.large_pool.current": 222,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 222,
+        "segment.small_pool.allocated": 8,
+        "segment.small_pool.current": 8,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 8
+    }
+}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_3141/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_3141/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_4713/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: roberta-base
+---
+
+# 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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_4713/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roberta-base",
+  "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/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_4713/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4db1654253cba7fe200fada1837e1f979699f3dc24cf1839306fc3d265882c0
+size 3555504

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_4713/all_results.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.900054914881933}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_4713/all_results_val.json

@@ -0,0 +1 @@
+{"eval_accuracy": 0.8849587092462647}

outputs/qnli/roberta-base_loratrain_val_8_16_0.1_0.0001_65/step_4713/gpu_stats.json

@@ -0,0 +1,130 @@
+{
+    "memory_allocated": 527799296,
+    "max_memory_allocated": 8744655360,
+    "memory_reserved": 13371441152,
+    "max_memory_reserved": 13371441152,
+    "memory_stats": {
+        "active.all.allocated": 53456374,
+        "active.all.current": 371,
+        "active.all.freed": 53456003,
+        "active.all.peak": 632,
+        "active.large_pool.allocated": 3810350,
+        "active.large_pool.current": 80,
+        "active.large_pool.freed": 3810270,
+        "active.large_pool.peak": 263,
+        "active.small_pool.allocated": 49646024,
+        "active.small_pool.current": 291,
+        "active.small_pool.freed": 49645733,
+        "active.small_pool.peak": 392,
+        "active_bytes.all.allocated": 61205309662208,
+        "active_bytes.all.current": 527799296,
+        "active_bytes.all.freed": 61204781862912,
+        "active_bytes.all.peak": 8744655360,
+        "active_bytes.large_pool.allocated": 46953367159296,
+        "active_bytes.large_pool.current": 523673600,
+        "active_bytes.large_pool.freed": 46952843485696,
+        "active_bytes.large_pool.peak": 8731166720,
+        "active_bytes.small_pool.allocated": 14251942502912,
+        "active_bytes.small_pool.current": 4125696,
+        "active_bytes.small_pool.freed": 14251938377216,
+        "active_bytes.small_pool.peak": 14843392,
+        "allocated_bytes.all.allocated": 61205309662208,
+        "allocated_bytes.all.current": 527799296,
+        "allocated_bytes.all.freed": 61204781862912,
+        "allocated_bytes.all.peak": 8744655360,
+        "allocated_bytes.large_pool.allocated": 46953367159296,
+        "allocated_bytes.large_pool.current": 523673600,
+        "allocated_bytes.large_pool.freed": 46952843485696,
+        "allocated_bytes.large_pool.peak": 8731166720,
+        "allocated_bytes.small_pool.allocated": 14251942502912,
+        "allocated_bytes.small_pool.current": 4125696,
+        "allocated_bytes.small_pool.freed": 14251938377216,
+        "allocated_bytes.small_pool.peak": 14843392,
+        "allocation.all.allocated": 53456374,
+        "allocation.all.current": 371,
+        "allocation.all.freed": 53456003,
+        "allocation.all.peak": 632,
+        "allocation.large_pool.allocated": 3810350,
+        "allocation.large_pool.current": 80,
+        "allocation.large_pool.freed": 3810270,
+        "allocation.large_pool.peak": 263,
+        "allocation.small_pool.allocated": 49646024,
+        "allocation.small_pool.current": 291,
+        "allocation.small_pool.freed": 49645733,
+        "allocation.small_pool.peak": 392,
+        "inactive_split.all.allocated": 26633569,
+        "inactive_split.all.current": 32,
+        "inactive_split.all.freed": 26633537,
+        "inactive_split.all.peak": 156,
+        "inactive_split.large_pool.allocated": 2869926,
+        "inactive_split.large_pool.current": 20,
+        "inactive_split.large_pool.freed": 2869906,
+        "inactive_split.large_pool.peak": 140,
+        "inactive_split.small_pool.allocated": 23763643,
+        "inactive_split.small_pool.current": 12,
+        "inactive_split.small_pool.freed": 23763631,
+        "inactive_split.small_pool.peak": 40,
+        "inactive_split_bytes.all.allocated": 49462535929344,
+        "inactive_split_bytes.all.current": 69889024,
+        "inactive_split_bytes.all.freed": 49462466040320,
+        "inactive_split_bytes.all.peak": 1840782336,
+        "inactive_split_bytes.large_pool.allocated": 33991082225664,
+        "inactive_split_bytes.large_pool.current": 67723264,
+        "inactive_split_bytes.large_pool.freed": 33991014502400,
+        "inactive_split_bytes.large_pool.peak": 1839972352,
+        "inactive_split_bytes.small_pool.allocated": 15471453703680,
+        "inactive_split_bytes.small_pool.current": 2165760,
+        "inactive_split_bytes.small_pool.freed": 15471451537920,
+        "inactive_split_bytes.small_pool.peak": 9822208,
+        "max_split_size": -1,
+        "num_alloc_retries": 0,
+        "num_device_alloc": 230,
+        "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": 60884805958138,
+        "requested_bytes.all.current": 526327312,
+        "requested_bytes.all.freed": 60884279630826,
+        "requested_bytes.all.peak": 8736087300,
+        "requested_bytes.large_pool.allocated": 46637435916320,
+        "requested_bytes.large_pool.current": 522208256,
+        "requested_bytes.large_pool.freed": 46636913708064,
+        "requested_bytes.large_pool.peak": 8722605056,
+        "requested_bytes.small_pool.allocated": 14247370041818,
+        "requested_bytes.small_pool.current": 4119056,
+        "requested_bytes.small_pool.freed": 14247365922762,
+        "requested_bytes.small_pool.peak": 14836740,
+        "reserved_bytes.all.allocated": 13371441152,
+        "reserved_bytes.all.current": 13371441152,
+        "reserved_bytes.all.freed": 0,
+        "reserved_bytes.all.peak": 13371441152,
+        "reserved_bytes.large_pool.allocated": 13354663936,
+        "reserved_bytes.large_pool.current": 13354663936,
+        "reserved_bytes.large_pool.freed": 0,
+        "reserved_bytes.large_pool.peak": 13354663936,
+        "reserved_bytes.small_pool.allocated": 16777216,
+        "reserved_bytes.small_pool.current": 16777216,
+        "reserved_bytes.small_pool.freed": 0,
+        "reserved_bytes.small_pool.peak": 16777216,
+        "segment.all.allocated": 230,
+        "segment.all.current": 230,
+        "segment.all.freed": 0,
+        "segment.all.peak": 230,
+        "segment.large_pool.allocated": 222,
+        "segment.large_pool.current": 222,
+        "segment.large_pool.freed": 0,
+        "segment.large_pool.peak": 222,
+        "segment.small_pool.allocated": 8,
+        "segment.small_pool.current": 8,
+        "segment.small_pool.freed": 0,
+        "segment.small_pool.peak": 8
+    }
+}