Upload LoRA model and probe head for run gemma-2b-it_layer_0

value_head_probes/gemma-2b-it_layer_0/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-it
+library_name: peft
+---
+
+# 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 0.14.0

value_head_probes/gemma-2b-it_layer_0/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "GemmaForCausalLM",
+    "parent_library": "transformers.models.gemma.modeling_gemma"
+  },
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

value_head_probes/gemma-2b-it_layer_0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7440cd2d136fe59a995bcb7e04aae2e37f3d20a4980181152a2f58b17708dab
+size 156926880

value_head_probes/gemma-2b-it_layer_0/probe_config.json

@@ -0,0 +1 @@
+{"target_layer_name": "GemmaDecoderLayer", "hidden_size": 2048, "layer_idx": 0}

value_head_probes/gemma-2b-it_layer_0/probe_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b2066432dfb168aa7427c2c6dc8b8c7b9a964ed7e79a3d65ca796836938e10
+size 5610

value_head_probes/gemma-2b-it_layer_0/results.json

@@ -0,0 +1 @@
+{"eval_metrics": {"eval_accuracy": 0.5513674788662357, "eval_precision": 0.6194191590810576, "eval_recall": 0.2822994863690241, "eval_f1": 0.38784095535350793, "eval_auc": 0.5908679895828874, "eval_lm_loss": 7.1375143571333455, "eval_probe_loss": 0.8123675126921047, "eval_sparsity": 0.13383345170454544, "epoch": 4.0}, "train_metrics": {"train_accuracy": 0.9487494391849942, "train_precision": 0.4414746543778802, "train_recall": 0.32178502879078696, "train_f1": 0.37224535109630863, "train_auc": 0.895208270738872, "train_lm_loss": 6.762935688556769, "train_probe_loss": 0.867246998502658, "train_sparsity": 0.127734375, "epoch": 4.0}}

value_head_probes/gemma-2b-it_layer_0/training_config.json

@@ -0,0 +1,67 @@
+{
+    "model_name": "google/gemma-2b-it",
+    "data_model_name": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    "layer": 0,
+    "adapter_dir": "/workspace/hallucination_detection/value_head_probes/gemma-2b-it_layer_0",
+    "train_split": 0.8,
+    "dtype": "torch.bfloat16",
+    "overwrite_output_dir": true,
+    "max_steps": -1,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 2,
+    "per_device_eval_batch_size": 2,
+    "lambda_lm": 0.1,
+    "logging_steps": 20,
+    "eval_steps": 100,
+    "overfit_mode": false,
+    "lora_layers": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19,
+        20,
+        21,
+        22,
+        23,
+        24,
+        25,
+        26,
+        27,
+        28,
+        29,
+        30,
+        31
+    ],
+    "lora_r": 32,
+    "lora_alpha": 64,
+    "lora_dropout": 0.05,
+    "upload_to_hf": true,
+    "load_from_hf": false,
+    "probe_threshold": 0.5,
+    "hf_repo": "obalcells/labeled-entity-facts",
+    "dataset_name": "longfact",
+    "max_length": 1200,
+    "default_ignore": false,
+    "pos_weight": 10.0,
+    "neg_weight": 10.0,
+    "ignore_window_size": 5,
+    "shuffle": true,
+    "seed": 42,
+    "run_id": "gemma-2b-it_layer_0"
+}