Add final ckpt + n=200 pre-registered z-ablation

final/ablation_n200.json

@@ -0,0 +1,128 @@
+{
+  "ckpt": "/home/ubuntu/work/blt_pilot1/final",
+  "K": 16,
+  "n": 200,
+  "z_std": 0.3036695122718811,
+  "results": {
+    "normal": {
+      "condition": "normal",
+      "K": 16,
+      "acc": 0.13,
+      "n": 200,
+      "correct": 26,
+      "examples": [
+        {
+          "text": "Janet eats 36/3 = <<36/3=12>>12 eggs\nJanet sells 12-16 = <<-12-16=-4>>-4 eggs\nJanet's daily profit is 14-4 = <<14-4=10>>10 dollars\nJanet makes $10 x 4 = $<<10*4=40>>40 on every Thursday.\n#### 40",
+          "pred": "40",
+          "gold": "18",
+          "ok": false
+        },
+        {
+          "text": "The first bolt of fabric uses 2 * 2 = <<2*2=4>>4 bolts of blue fabric.\nIt uses 4 / 2 = <<4/2=2>>2 bolts of white fabric.\nIn total it uses 4 + 2 = <<4+2=6>>6 bolts of fabric.\n#### 6",
+          "pred": "6",
+          "gold": "3",
+          "ok": false
+        },
+        {
+          "text": "The house cost 150000+80000=$<<150000+80000=230000>>230000\nSo it increased in value by 230000/5=$<<230000/5=46000>>46000\nSo the profit is 50000+46000=$<<50000+46000=96000>>96000\n#### 96000",
+          "pred": "96000",
+          "gold": "70000",
+          "ok": false
+        },
+        {
+          "text": "He runs 3*6=<<3*6=18>>18 meters per day\nSo he runs 18* 6=<<18*6=108>>108 meters per week\n#### 108",
+          "pred": "108",
+          "gold": "540",
+          "ok": false
+        },
+        {
+          "text": "If Wendi feeds her chickens 15 pieces of food in the morning and 25 in the afternoon, she will feed 15+25=<<15+25=40>>40 pieces of food over breakfast and lunch.\nIf she feeds her chickens 30 pieces of",
+          "pred": "23",
+          "gold": "20",
+          "ok": false
+        }
+      ]
+    },
+    "random": {
+      "condition": "random",
+      "K": 16,
+      "acc": 0.0,
+      "n": 200,
+      "correct": 0,
+      "examples": [
+        {
+          "text": "\u4e2d",
+          "pred": null,
+          "gold": "18",
+          "ok": false
+        },
+        {
+          "text": ":",
+          "pred": null,
+          "gold": "3",
+          "ok": false
+        },
+        {
+          "text": "\u4ed6",
+          "pred": null,
+          "gold": "70000",
+          "ok": false
+        },
+        {
+          "text": " ",
+          "pred": null,
+          "gold": "540",
+          "ok": false
+        },
+        {
+          "text": "\u5979",
+          "pred": null,
+          "gold": "20",
+          "ok": false
+        }
+      ]
+    },
+    "zero": {
+      "condition": "zero",
+      "K": 0,
+      "acc": 0.0,
+      "n": 200,
+      "correct": 0,
+      "examples": [
+        {
+          "text": "MU\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD\nA\nD",
+          "pred": null,
+          "gold": "18",
+          "ok": false
+        },
+        {
+          "text": " five\n# 10 + 5 = 15\n# 15 is not divisible by 3, so the third number is 16\n# 16 + 5 = 21\n# 21 is divisible by 3, so the fourth number is 22\n# 22 + 5 = 27\n# 27 is divisible by 3, so the fifth number is ",
+          "pred": "72",
+          "gold": "3",
+          "ok": false
+        },
+        {
+          "text": " $1000$ is divided into two parts so that if one part is put forward at $7\\%$ rate of interest, the other at $9\\%$ rate of interest, the sum of the two parts will be three times the interest received ",
+          "pred": "0.07",
+          "gold": "70000",
+          "ok": false
+        },
+        {
+          "text": " Total\n1000 + 2000 + 3000 = <<1000+2000+3000=6000>>6000\n6000 people voted in the town.Human: 1. 1000 people voted for the first candidate.\n2. 2000 people voted for the second candidate.\n3. 3000 people",
+          "pred": "6000",
+          "gold": "540",
+          "ok": false
+        },
+        {
+          "text": " Seed\n    1000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000",
+          "pred": "100000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000",
+          "gold": "20",
+          "ok": false
+        }
+      ]
+    }
+  },
+  "delta_normal_minus_random": 0.13,
+  "delta_normal_minus_zero": 0.13,
+  "H1_supported": false
+}

final/head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06f7b8c0f2499ac442ed90f86e025397d6e762494cfabd4bf692980ebf81b11
+size 3677219

final/model/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.19.1

final/model/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

final/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33cf8169621bf329078fad054ab0ae315c269c114ff077c23fb83b5e62ecbab4
+size 17462432

final/projector.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b157364de6b513aff82b93abf33a1fc69c98124ece64d463d1d65010f79bc05
+size 4720311