diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..01bf7d27961ff911ddd0bdc655dbd72c9347151e
--- /dev/null
+++ b/README.md
@@ -0,0 +1,51 @@
+# Backdoor Detection Checkpoints
+
+Fine-tuned Qwen 2.5 Coder 14B models for backdoor detection experiments.
+
+## Models
+
+### 1. `ca_v3_run_20251215/`
+- **Base model:** Qwen/Qwen2.5-Coder-14B-Instruct
+- **Training data:** CA_collusion_exp2_v3 (300 clean + 300 backdoor_only)
+- **Task:** Binary backdoor detection
+- **Best checkpoint:** `final_model/` or `checkpoint-150/`
+
+### 2. `exp1_original_data_rerun_20251215/`
+- **Base model:** Qwen/Qwen2.5-Coder-14B-Instruct  
+- **Training data:** exp1_qwen14b_analysis_v2 (original dataset)
+- **Task:** Binary backdoor detection
+- **Performance:** AUROC 0.947
+- **Best checkpoint:** `checkpoint-75/`
+
+### 3. `exp2_signalc_20251215/`
+- **Base model:** Qwen/Qwen2.5-Coder-14B-Instruct
+- **Training data:** 300 clean + 250 backdoor_only + 50 signal_c
+- **Task:** Backdoor detection with collusion signal resistance
+- **Goal:** Train model to detect backdoors even when signal_c marker is present
+- **Best checkpoint:** `final_model/` or `checkpoint-150/`
+
+## LoRA Configuration
+
+All models use LoRA fine-tuning:
+- `lora_r`: 32
+- `lora_alpha`: 64
+- `target_modules`: [q_proj, v_proj, k_proj, o_proj]
+- `lora_dropout`: 0.05
+
+## Usage
+
+```python
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+
+model = AutoPeftModelForCausalLM.from_pretrained(
+    "path/to/checkpoint",
+    torch_dtype="bfloat16",
+    device_map="cuda"
+)
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-14B-Instruct")
+```
+
+## Date
+December 15, 2025
+
diff --git a/ca_v3_run_20251215/checkpoint-147/README.md b/ca_v3_run_20251215/checkpoint-147/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-147/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/ca_v3_run_20251215/checkpoint-147/adapter_config.json b/ca_v3_run_20251215/checkpoint-147/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bd100e2ef4775697a7cb0c0abaae99f244053d68
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-147/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/ca_v3_run_20251215/checkpoint-147/adapter_model.safetensors b/ca_v3_run_20251215/checkpoint-147/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dd7cd68ab4f5848f38d415367c145815ff77e220
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-147/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216da2b46929ee9ee09b5b5efb6fb9c3a8c58e2e7acad45800b49def741cefa4
+size 201378736
diff --git a/ca_v3_run_20251215/checkpoint-147/optimizer.pt b/ca_v3_run_20251215/checkpoint-147/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d65649d4ca445ac2b6e9d2e5a2b01acd02030adf
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-147/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc755d6cc95a2fa70b493792f6fcfb3f7765a8fd2ada1ce28ae2fe5836099c6b
+size 402982627
diff --git a/ca_v3_run_20251215/checkpoint-147/rng_state.pth b/ca_v3_run_20251215/checkpoint-147/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0178e697ee9dfc09593374e91de3e5c7e0217aee
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-147/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283c4259167c1de6fc9b0d70fb38093d1c85343ca9ff0f2e605bd2011addd045
+size 14645
diff --git a/ca_v3_run_20251215/checkpoint-147/scheduler.pt b/ca_v3_run_20251215/checkpoint-147/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b196c8e7a4834975b028188c1c8c2559af111ec
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-147/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6e49a0a1dc514c3062fdc71df85d50b768febd62f2e9b412554326fd48eb9c
+size 1465
diff --git a/ca_v3_run_20251215/checkpoint-147/trainer_state.json b/ca_v3_run_20251215/checkpoint-147/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3a74374a055c0286f5cae6366880900478033bd6
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-147/trainer_state.json
@@ -0,0 +1,1071 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.98,
+  "eval_steps": 100,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.267627239227295,
+      "learning_rate": 0.0,
+      "loss": 0.8939,
+      "step": 1
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.5160397291183472,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6392,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.4698739051818848,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8476,
+      "step": 3
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 4.279767036437988,
+      "learning_rate": 1e-05,
+      "loss": 1.2988,
+      "step": 4
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 3.669569730758667,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.95,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2172225713729858,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.3448,
+      "step": 6
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 1.891830325126648,
+      "learning_rate": 2e-05,
+      "loss": 0.7179,
+      "step": 7
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.352062940597534,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.5782,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.2546859979629517,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.686,
+      "step": 9
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 1.1951119899749756,
+      "learning_rate": 3e-05,
+      "loss": 0.2151,
+      "step": 10
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 1.5607569217681885,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3339,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.513392448425293,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.7432,
+      "step": 12
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.3942737579345703,
+      "learning_rate": 4e-05,
+      "loss": 0.5372,
+      "step": 13
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 2.1662518978118896,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.5742,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.074810028076172,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6484,
+      "step": 15
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.5651564598083496,
+      "learning_rate": 5e-05,
+      "loss": 0.678,
+      "step": 16
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 3.3820931911468506,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.6619,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.7587597370147705,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.665,
+      "step": 18
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 2.234240770339966,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.4308,
+      "step": 19
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.0802106857299805,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.6038,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.3648719787597656,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.5436,
+      "step": 21
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 1.2552648782730103,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.6223,
+      "step": 22
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 2.2331910133361816,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.6468,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7010774612426758,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.6019,
+      "step": 24
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.6806925535202026,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3979,
+      "step": 25
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 1.4811266660690308,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.8038,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.5548367500305176,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.5653,
+      "step": 27
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.4900885820388794,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.7534,
+      "step": 28
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 1.2963446378707886,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.6946,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.885505199432373,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.8456,
+      "step": 30
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 1.0747458934783936,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.336,
+      "step": 31
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 2.0049006938934326,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.6669,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.020938515663147,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.6849,
+      "step": 33
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 1.3365986347198486,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.4813,
+      "step": 34
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 2.2962701320648193,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 1.156,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1328681707382202,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.4652,
+      "step": 36
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 1.3263046741485596,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.4638,
+      "step": 37
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 1.6372419595718384,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.6662,
+      "step": 38
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.3750609159469604,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.3029,
+      "step": 39
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.442150354385376,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.7255,
+      "step": 40
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.3133295774459839,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.6364,
+      "step": 41
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.2394391298294067,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.6514,
+      "step": 42
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 2.0945804119110107,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.4957,
+      "step": 43
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 2.036482810974121,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.5471,
+      "step": 44
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7951217889785767,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.4969,
+      "step": 45
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 1.3251290321350098,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5828,
+      "step": 46
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 1.5717222690582275,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.378,
+      "step": 47
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4296456575393677,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.3957,
+      "step": 48
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 1.3804540634155273,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.4861,
+      "step": 49
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.184690237045288,
+      "learning_rate": 4.257452643564155e-05,
+      "loss": 0.8223,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.361177682876587,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.7269,
+      "step": 51
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.2764381170272827,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.3787,
+      "step": 52
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 1.4495773315429688,
+      "learning_rate": 4.129143072053638e-05,
+      "loss": 0.2966,
+      "step": 53
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.055936813354492,
+      "learning_rate": 4.0845774184967754e-05,
+      "loss": 0.4485,
+      "step": 54
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 1.8481249809265137,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.4182,
+      "step": 55
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.6037787199020386,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.6953,
+      "step": 56
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.5313551425933838,
+      "learning_rate": 3.945830840419966e-05,
+      "loss": 0.3223,
+      "step": 57
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 1.3661636114120483,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.4186,
+      "step": 58
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 2.39021372795105,
+      "learning_rate": 3.8493766448787825e-05,
+      "loss": 0.7415,
+      "step": 59
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.5035974979400635,
+      "learning_rate": 3.8000403198230387e-05,
+      "loss": 0.9131,
+      "step": 60
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 1.3086011409759521,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.397,
+      "step": 61
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 1.9651494026184082,
+      "learning_rate": 3.699282783125616e-05,
+      "loss": 0.9127,
+      "step": 62
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.166289806365967,
+      "learning_rate": 3.6479161334675296e-05,
+      "loss": 0.6211,
+      "step": 63
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.1649678945541382,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3828,
+      "step": 64
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.7926881909370422,
+      "learning_rate": 3.543346136204545e-05,
+      "loss": 0.1886,
+      "step": 65
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2959918975830078,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3381,
+      "step": 66
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 1.3724843263626099,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.5337,
+      "step": 67
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.743539810180664,
+      "learning_rate": 3.382326411784672e-05,
+      "loss": 0.3935,
+      "step": 68
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.310335397720337,
+      "learning_rate": 3.327658544712395e-05,
+      "loss": 0.3857,
+      "step": 69
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 2.399306058883667,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 1.0896,
+      "step": 70
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 1.2522423267364502,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.1551,
+      "step": 71
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.307708740234375,
+      "learning_rate": 3.161085405093006e-05,
+      "loss": 0.3004,
+      "step": 72
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 1.527667760848999,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.3367,
+      "step": 73
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 1.2848842144012451,
+      "learning_rate": 3.048196560469758e-05,
+      "loss": 0.264,
+      "step": 74
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.7577385902404785,
+      "learning_rate": 2.9912915238320754e-05,
+      "loss": 0.3975,
+      "step": 75
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.2079553604125977,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1619,
+      "step": 76
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 1.2687911987304688,
+      "learning_rate": 2.876714280623708e-05,
+      "loss": 0.1523,
+      "step": 77
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.3904497623443604,
+      "learning_rate": 2.8191041196514873e-05,
+      "loss": 0.6355,
+      "step": 78
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 1.2210139036178589,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.1803,
+      "step": 79
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.2414464950561523,
+      "learning_rate": 2.7033966866696457e-05,
+      "loss": 0.2332,
+      "step": 80
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.8386731147766113,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 0.6357,
+      "step": 81
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 2.6382551193237305,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.3541,
+      "step": 82
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 3.260303020477295,
+      "learning_rate": 2.5290881645034932e-05,
+      "loss": 0.7056,
+      "step": 83
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.604124546051025,
+      "learning_rate": 2.470911835496508e-05,
+      "loss": 0.8796,
+      "step": 84
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 3.7330353260040283,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.2487,
+      "step": 85
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.9771713018417358,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.3601,
+      "step": 86
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 6.817903995513916,
+      "learning_rate": 2.2966033133303545e-05,
+      "loss": 1.3453,
+      "step": 87
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 2.8639299869537354,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.3974,
+      "step": 88
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 2.082796573638916,
+      "learning_rate": 2.1808958803485136e-05,
+      "loss": 0.4019,
+      "step": 89
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.427212655544281,
+      "learning_rate": 2.1232857193762924e-05,
+      "loss": 0.0465,
+      "step": 90
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 1.7197939157485962,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.2682,
+      "step": 91
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.09823339432477951,
+      "learning_rate": 2.0087084761679245e-05,
+      "loss": 0.0111,
+      "step": 92
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.9435588121414185,
+      "learning_rate": 1.9518034395302414e-05,
+      "loss": 0.124,
+      "step": 93
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 2.9964282512664795,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.3849,
+      "step": 94
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 1.595879077911377,
+      "learning_rate": 1.838914594906995e-05,
+      "loss": 0.2477,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.441842555999756,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.5461,
+      "step": 96
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 2.448079824447632,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.5091,
+      "step": 97
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 3.598569631576538,
+      "learning_rate": 1.672341455287605e-05,
+      "loss": 0.4161,
+      "step": 98
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.45053243637085,
+      "learning_rate": 1.617673588215328e-05,
+      "loss": 0.8538,
+      "step": 99
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.3044579029083252,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.171,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.4516909718513489,
+      "eval_runtime": 66.1438,
+      "eval_samples_per_second": 2.253,
+      "eval_steps_per_second": 1.134,
+      "step": 100
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 8.098329544067383,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 1.1298,
+      "step": 101
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.519363284111023,
+      "learning_rate": 1.4566538637954554e-05,
+      "loss": 0.1545,
+      "step": 102
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 2.4320404529571533,
+      "learning_rate": 1.4040721330273062e-05,
+      "loss": 0.1781,
+      "step": 103
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 4.600680828094482,
+      "learning_rate": 1.3520838665324703e-05,
+      "loss": 0.4178,
+      "step": 104
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4558080434799194,
+      "learning_rate": 1.3007172168743854e-05,
+      "loss": 0.1014,
+      "step": 105
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 1.6424729824066162,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.1476,
+      "step": 106
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 3.927393913269043,
+      "learning_rate": 1.1999596801769616e-05,
+      "loss": 1.0977,
+      "step": 107
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8934208154678345,
+      "learning_rate": 1.1506233551212186e-05,
+      "loss": 0.1165,
+      "step": 108
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 2.651909589767456,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.5939,
+      "step": 109
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 1.0333629846572876,
+      "learning_rate": 1.0541691595800337e-05,
+      "loss": 0.152,
+      "step": 110
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.1822710037231445,
+      "learning_rate": 1.0071035207430352e-05,
+      "loss": 0.4252,
+      "step": 111
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.6616872549057007,
+      "learning_rate": 9.608463116858542e-06,
+      "loss": 0.1772,
+      "step": 112
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 4.919057846069336,
+      "learning_rate": 9.154225815032242e-06,
+      "loss": 0.4062,
+      "step": 113
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.426158905029297,
+      "learning_rate": 8.708569279463622e-06,
+      "loss": 0.6537,
+      "step": 114
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 2.4902124404907227,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.1949,
+      "step": 115
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.6176963448524475,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.0729,
+      "step": 116
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.257253408432007,
+      "learning_rate": 7.4254735643584564e-06,
+      "loss": 0.2163,
+      "step": 117
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 1.069271445274353,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.156,
+      "step": 118
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 0.6102529764175415,
+      "learning_rate": 6.617274798504286e-06,
+      "loss": 0.0632,
+      "step": 119
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.137846946716309,
+      "learning_rate": 6.22799917546252e-06,
+      "loss": 0.5415,
+      "step": 120
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 2.0759520530700684,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.3255,
+      "step": 121
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 4.551874160766602,
+      "learning_rate": 5.48014933308352e-06,
+      "loss": 0.3398,
+      "step": 122
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0534967184066772,
+      "learning_rate": 5.121980087628803e-06,
+      "loss": 0.1326,
+      "step": 123
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 2.607910394668579,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.8089,
+      "step": 124
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.044987201690674,
+      "learning_rate": 4.438122617983443e-06,
+      "loss": 0.238,
+      "step": 125
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.440517544746399,
+      "learning_rate": 4.112804714676594e-06,
+      "loss": 0.1659,
+      "step": 126
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 3.426896333694458,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.4279,
+      "step": 127
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 2.2087795734405518,
+      "learning_rate": 3.4962713026158694e-06,
+      "loss": 1.0499,
+      "step": 128
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9487075805664062,
+      "learning_rate": 3.205389657580943e-06,
+      "loss": 0.1213,
+      "step": 129
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 2.0362558364868164,
+      "learning_rate": 2.9263101785268254e-06,
+      "loss": 0.6995,
+      "step": 130
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 4.185983180999756,
+      "learning_rate": 2.659183991914696e-06,
+      "loss": 0.6105,
+      "step": 131
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.219158411026001,
+      "learning_rate": 2.4041557512869878e-06,
+      "loss": 0.2062,
+      "step": 132
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.7529279589653015,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 0.0839,
+      "step": 133
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 4.446479320526123,
+      "learning_rate": 1.9309388911139426e-06,
+      "loss": 1.0925,
+      "step": 134
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.211433410644531,
+      "learning_rate": 1.713006526846439e-06,
+      "loss": 0.6347,
+      "step": 135
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 2.469029426574707,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.4994,
+      "step": 136
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 5.426701545715332,
+      "learning_rate": 1.31508393714177e-06,
+      "loss": 0.4131,
+      "step": 137
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.973341941833496,
+      "learning_rate": 1.1353091938067023e-06,
+      "loss": 0.3887,
+      "step": 138
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 2.101803779602051,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 0.2598,
+      "step": 139
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.5676771998405457,
+      "learning_rate": 8.146195134284052e-07,
+      "loss": 0.0698,
+      "step": 140
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.5499122142791748,
+      "learning_rate": 6.738782355044049e-07,
+      "loss": 0.0823,
+      "step": 141
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 0.36405226588249207,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.0406,
+      "step": 142
+    },
+    {
+      "epoch": 0.9533333333333334,
+      "grad_norm": 1.898514747619629,
+      "learning_rate": 4.319838323396691e-07,
+      "loss": 0.4404,
+      "step": 143
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.7996866703033447,
+      "learning_rate": 3.309616971855195e-07,
+      "loss": 0.2531,
+      "step": 144
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 2.6673455238342285,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.7721,
+      "step": 145
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 7.725250244140625,
+      "learning_rate": 1.6904105645142444e-07,
+      "loss": 1.7164,
+      "step": 146
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.411264419555664,
+      "learning_rate": 1.0823023375489127e-07,
+      "loss": 0.4909,
+      "step": 147
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 49,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.014568182695854e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/ca_v3_run_20251215/checkpoint-147/training_args.bin b/ca_v3_run_20251215/checkpoint-147/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..88b4ad4e5f06f68e064e676272032d9cd8af9147
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-147/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c0e75d45a7050daffe2e65badc27748032d13318e1d0af24fcae2c215424f0
+size 5777
diff --git a/ca_v3_run_20251215/checkpoint-150/README.md b/ca_v3_run_20251215/checkpoint-150/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-150/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/ca_v3_run_20251215/checkpoint-150/adapter_config.json b/ca_v3_run_20251215/checkpoint-150/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bd100e2ef4775697a7cb0c0abaae99f244053d68
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-150/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/ca_v3_run_20251215/checkpoint-150/adapter_model.safetensors b/ca_v3_run_20251215/checkpoint-150/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ba2d53f00df555c320d5fa8bfd92a9508b7313e3
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-150/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6966fb106cba724091bb384a14877dd0d857a05bd7354cef7953e56fdecb77
+size 201378736
diff --git a/ca_v3_run_20251215/checkpoint-150/optimizer.pt b/ca_v3_run_20251215/checkpoint-150/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..65b00be983c44726678d780022d5ad5e15976150
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-150/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392183f58bb6c3c87cc8b1040b1bd5940b7f2522896624f3668d965de80ee89b
+size 402982627
diff --git a/ca_v3_run_20251215/checkpoint-150/rng_state.pth b/ca_v3_run_20251215/checkpoint-150/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b6e5ebccc9e6a700fd9d1abbdf919ba33a76cbed
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-150/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a47d1ead692de2bce57a9ae7ba59450da50376926e3a3a2a0ebc83b70d9ba03
+size 14645
diff --git a/ca_v3_run_20251215/checkpoint-150/scheduler.pt b/ca_v3_run_20251215/checkpoint-150/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3b259f6f75e583e4febfc080b5b8331e00665a2f
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-150/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30781be5b5c4396cc620b6281ac1b634d4288d62bfab3224155044b29d42cdb1
+size 1465
diff --git a/ca_v3_run_20251215/checkpoint-150/trainer_state.json b/ca_v3_run_20251215/checkpoint-150/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..008b27243cee0eb2e38fd9d96131f1a346233be4
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-150/trainer_state.json
@@ -0,0 +1,1092 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.267627239227295,
+      "learning_rate": 0.0,
+      "loss": 0.8939,
+      "step": 1
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.5160397291183472,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6392,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.4698739051818848,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8476,
+      "step": 3
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 4.279767036437988,
+      "learning_rate": 1e-05,
+      "loss": 1.2988,
+      "step": 4
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 3.669569730758667,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.95,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2172225713729858,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.3448,
+      "step": 6
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 1.891830325126648,
+      "learning_rate": 2e-05,
+      "loss": 0.7179,
+      "step": 7
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.352062940597534,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.5782,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.2546859979629517,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.686,
+      "step": 9
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 1.1951119899749756,
+      "learning_rate": 3e-05,
+      "loss": 0.2151,
+      "step": 10
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 1.5607569217681885,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3339,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.513392448425293,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.7432,
+      "step": 12
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.3942737579345703,
+      "learning_rate": 4e-05,
+      "loss": 0.5372,
+      "step": 13
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 2.1662518978118896,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.5742,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.074810028076172,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6484,
+      "step": 15
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.5651564598083496,
+      "learning_rate": 5e-05,
+      "loss": 0.678,
+      "step": 16
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 3.3820931911468506,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.6619,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.7587597370147705,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.665,
+      "step": 18
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 2.234240770339966,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.4308,
+      "step": 19
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.0802106857299805,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.6038,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.3648719787597656,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.5436,
+      "step": 21
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 1.2552648782730103,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.6223,
+      "step": 22
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 2.2331910133361816,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.6468,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7010774612426758,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.6019,
+      "step": 24
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.6806925535202026,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3979,
+      "step": 25
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 1.4811266660690308,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.8038,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.5548367500305176,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.5653,
+      "step": 27
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.4900885820388794,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.7534,
+      "step": 28
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 1.2963446378707886,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.6946,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.885505199432373,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.8456,
+      "step": 30
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 1.0747458934783936,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.336,
+      "step": 31
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 2.0049006938934326,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.6669,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.020938515663147,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.6849,
+      "step": 33
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 1.3365986347198486,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.4813,
+      "step": 34
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 2.2962701320648193,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 1.156,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1328681707382202,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.4652,
+      "step": 36
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 1.3263046741485596,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.4638,
+      "step": 37
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 1.6372419595718384,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.6662,
+      "step": 38
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.3750609159469604,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.3029,
+      "step": 39
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.442150354385376,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.7255,
+      "step": 40
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.3133295774459839,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.6364,
+      "step": 41
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.2394391298294067,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.6514,
+      "step": 42
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 2.0945804119110107,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.4957,
+      "step": 43
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 2.036482810974121,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.5471,
+      "step": 44
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7951217889785767,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.4969,
+      "step": 45
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 1.3251290321350098,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5828,
+      "step": 46
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 1.5717222690582275,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.378,
+      "step": 47
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4296456575393677,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.3957,
+      "step": 48
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 1.3804540634155273,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.4861,
+      "step": 49
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.184690237045288,
+      "learning_rate": 4.257452643564155e-05,
+      "loss": 0.8223,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.361177682876587,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.7269,
+      "step": 51
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.2764381170272827,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.3787,
+      "step": 52
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 1.4495773315429688,
+      "learning_rate": 4.129143072053638e-05,
+      "loss": 0.2966,
+      "step": 53
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.055936813354492,
+      "learning_rate": 4.0845774184967754e-05,
+      "loss": 0.4485,
+      "step": 54
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 1.8481249809265137,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.4182,
+      "step": 55
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.6037787199020386,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.6953,
+      "step": 56
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.5313551425933838,
+      "learning_rate": 3.945830840419966e-05,
+      "loss": 0.3223,
+      "step": 57
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 1.3661636114120483,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.4186,
+      "step": 58
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 2.39021372795105,
+      "learning_rate": 3.8493766448787825e-05,
+      "loss": 0.7415,
+      "step": 59
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.5035974979400635,
+      "learning_rate": 3.8000403198230387e-05,
+      "loss": 0.9131,
+      "step": 60
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 1.3086011409759521,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.397,
+      "step": 61
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 1.9651494026184082,
+      "learning_rate": 3.699282783125616e-05,
+      "loss": 0.9127,
+      "step": 62
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.166289806365967,
+      "learning_rate": 3.6479161334675296e-05,
+      "loss": 0.6211,
+      "step": 63
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.1649678945541382,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3828,
+      "step": 64
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.7926881909370422,
+      "learning_rate": 3.543346136204545e-05,
+      "loss": 0.1886,
+      "step": 65
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2959918975830078,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3381,
+      "step": 66
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 1.3724843263626099,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.5337,
+      "step": 67
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.743539810180664,
+      "learning_rate": 3.382326411784672e-05,
+      "loss": 0.3935,
+      "step": 68
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.310335397720337,
+      "learning_rate": 3.327658544712395e-05,
+      "loss": 0.3857,
+      "step": 69
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 2.399306058883667,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 1.0896,
+      "step": 70
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 1.2522423267364502,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.1551,
+      "step": 71
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.307708740234375,
+      "learning_rate": 3.161085405093006e-05,
+      "loss": 0.3004,
+      "step": 72
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 1.527667760848999,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.3367,
+      "step": 73
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 1.2848842144012451,
+      "learning_rate": 3.048196560469758e-05,
+      "loss": 0.264,
+      "step": 74
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.7577385902404785,
+      "learning_rate": 2.9912915238320754e-05,
+      "loss": 0.3975,
+      "step": 75
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.2079553604125977,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1619,
+      "step": 76
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 1.2687911987304688,
+      "learning_rate": 2.876714280623708e-05,
+      "loss": 0.1523,
+      "step": 77
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.3904497623443604,
+      "learning_rate": 2.8191041196514873e-05,
+      "loss": 0.6355,
+      "step": 78
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 1.2210139036178589,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.1803,
+      "step": 79
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.2414464950561523,
+      "learning_rate": 2.7033966866696457e-05,
+      "loss": 0.2332,
+      "step": 80
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.8386731147766113,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 0.6357,
+      "step": 81
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 2.6382551193237305,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.3541,
+      "step": 82
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 3.260303020477295,
+      "learning_rate": 2.5290881645034932e-05,
+      "loss": 0.7056,
+      "step": 83
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.604124546051025,
+      "learning_rate": 2.470911835496508e-05,
+      "loss": 0.8796,
+      "step": 84
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 3.7330353260040283,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.2487,
+      "step": 85
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.9771713018417358,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.3601,
+      "step": 86
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 6.817903995513916,
+      "learning_rate": 2.2966033133303545e-05,
+      "loss": 1.3453,
+      "step": 87
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 2.8639299869537354,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.3974,
+      "step": 88
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 2.082796573638916,
+      "learning_rate": 2.1808958803485136e-05,
+      "loss": 0.4019,
+      "step": 89
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.427212655544281,
+      "learning_rate": 2.1232857193762924e-05,
+      "loss": 0.0465,
+      "step": 90
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 1.7197939157485962,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.2682,
+      "step": 91
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.09823339432477951,
+      "learning_rate": 2.0087084761679245e-05,
+      "loss": 0.0111,
+      "step": 92
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.9435588121414185,
+      "learning_rate": 1.9518034395302414e-05,
+      "loss": 0.124,
+      "step": 93
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 2.9964282512664795,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.3849,
+      "step": 94
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 1.595879077911377,
+      "learning_rate": 1.838914594906995e-05,
+      "loss": 0.2477,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.441842555999756,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.5461,
+      "step": 96
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 2.448079824447632,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.5091,
+      "step": 97
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 3.598569631576538,
+      "learning_rate": 1.672341455287605e-05,
+      "loss": 0.4161,
+      "step": 98
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.45053243637085,
+      "learning_rate": 1.617673588215328e-05,
+      "loss": 0.8538,
+      "step": 99
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.3044579029083252,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.171,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.4516909718513489,
+      "eval_runtime": 66.1438,
+      "eval_samples_per_second": 2.253,
+      "eval_steps_per_second": 1.134,
+      "step": 100
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 8.098329544067383,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 1.1298,
+      "step": 101
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.519363284111023,
+      "learning_rate": 1.4566538637954554e-05,
+      "loss": 0.1545,
+      "step": 102
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 2.4320404529571533,
+      "learning_rate": 1.4040721330273062e-05,
+      "loss": 0.1781,
+      "step": 103
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 4.600680828094482,
+      "learning_rate": 1.3520838665324703e-05,
+      "loss": 0.4178,
+      "step": 104
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4558080434799194,
+      "learning_rate": 1.3007172168743854e-05,
+      "loss": 0.1014,
+      "step": 105
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 1.6424729824066162,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.1476,
+      "step": 106
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 3.927393913269043,
+      "learning_rate": 1.1999596801769616e-05,
+      "loss": 1.0977,
+      "step": 107
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8934208154678345,
+      "learning_rate": 1.1506233551212186e-05,
+      "loss": 0.1165,
+      "step": 108
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 2.651909589767456,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.5939,
+      "step": 109
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 1.0333629846572876,
+      "learning_rate": 1.0541691595800337e-05,
+      "loss": 0.152,
+      "step": 110
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.1822710037231445,
+      "learning_rate": 1.0071035207430352e-05,
+      "loss": 0.4252,
+      "step": 111
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.6616872549057007,
+      "learning_rate": 9.608463116858542e-06,
+      "loss": 0.1772,
+      "step": 112
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 4.919057846069336,
+      "learning_rate": 9.154225815032242e-06,
+      "loss": 0.4062,
+      "step": 113
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.426158905029297,
+      "learning_rate": 8.708569279463622e-06,
+      "loss": 0.6537,
+      "step": 114
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 2.4902124404907227,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.1949,
+      "step": 115
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.6176963448524475,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.0729,
+      "step": 116
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.257253408432007,
+      "learning_rate": 7.4254735643584564e-06,
+      "loss": 0.2163,
+      "step": 117
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 1.069271445274353,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.156,
+      "step": 118
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 0.6102529764175415,
+      "learning_rate": 6.617274798504286e-06,
+      "loss": 0.0632,
+      "step": 119
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.137846946716309,
+      "learning_rate": 6.22799917546252e-06,
+      "loss": 0.5415,
+      "step": 120
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 2.0759520530700684,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.3255,
+      "step": 121
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 4.551874160766602,
+      "learning_rate": 5.48014933308352e-06,
+      "loss": 0.3398,
+      "step": 122
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0534967184066772,
+      "learning_rate": 5.121980087628803e-06,
+      "loss": 0.1326,
+      "step": 123
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 2.607910394668579,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.8089,
+      "step": 124
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.044987201690674,
+      "learning_rate": 4.438122617983443e-06,
+      "loss": 0.238,
+      "step": 125
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.440517544746399,
+      "learning_rate": 4.112804714676594e-06,
+      "loss": 0.1659,
+      "step": 126
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 3.426896333694458,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.4279,
+      "step": 127
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 2.2087795734405518,
+      "learning_rate": 3.4962713026158694e-06,
+      "loss": 1.0499,
+      "step": 128
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9487075805664062,
+      "learning_rate": 3.205389657580943e-06,
+      "loss": 0.1213,
+      "step": 129
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 2.0362558364868164,
+      "learning_rate": 2.9263101785268254e-06,
+      "loss": 0.6995,
+      "step": 130
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 4.185983180999756,
+      "learning_rate": 2.659183991914696e-06,
+      "loss": 0.6105,
+      "step": 131
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.219158411026001,
+      "learning_rate": 2.4041557512869878e-06,
+      "loss": 0.2062,
+      "step": 132
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.7529279589653015,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 0.0839,
+      "step": 133
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 4.446479320526123,
+      "learning_rate": 1.9309388911139426e-06,
+      "loss": 1.0925,
+      "step": 134
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.211433410644531,
+      "learning_rate": 1.713006526846439e-06,
+      "loss": 0.6347,
+      "step": 135
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 2.469029426574707,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.4994,
+      "step": 136
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 5.426701545715332,
+      "learning_rate": 1.31508393714177e-06,
+      "loss": 0.4131,
+      "step": 137
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.973341941833496,
+      "learning_rate": 1.1353091938067023e-06,
+      "loss": 0.3887,
+      "step": 138
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 2.101803779602051,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 0.2598,
+      "step": 139
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.5676771998405457,
+      "learning_rate": 8.146195134284052e-07,
+      "loss": 0.0698,
+      "step": 140
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.5499122142791748,
+      "learning_rate": 6.738782355044049e-07,
+      "loss": 0.0823,
+      "step": 141
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 0.36405226588249207,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.0406,
+      "step": 142
+    },
+    {
+      "epoch": 0.9533333333333334,
+      "grad_norm": 1.898514747619629,
+      "learning_rate": 4.319838323396691e-07,
+      "loss": 0.4404,
+      "step": 143
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.7996866703033447,
+      "learning_rate": 3.309616971855195e-07,
+      "loss": 0.2531,
+      "step": 144
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 2.6673455238342285,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.7721,
+      "step": 145
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 7.725250244140625,
+      "learning_rate": 1.6904105645142444e-07,
+      "loss": 1.7164,
+      "step": 146
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.411264419555664,
+      "learning_rate": 1.0823023375489127e-07,
+      "loss": 0.4909,
+      "step": 147
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.3376047611236572,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 0.1719,
+      "step": 148
+    },
+    {
+      "epoch": 0.9933333333333333,
+      "grad_norm": 1.7119640111923218,
+      "learning_rate": 2.7072216536885853e-08,
+      "loss": 0.1636,
+      "step": 149
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.7593977451324463,
+      "learning_rate": 6.768970513457151e-09,
+      "loss": 0.5289,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 49,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0335481997190758e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/ca_v3_run_20251215/checkpoint-150/training_args.bin b/ca_v3_run_20251215/checkpoint-150/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..88b4ad4e5f06f68e064e676272032d9cd8af9147
--- /dev/null
+++ b/ca_v3_run_20251215/checkpoint-150/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c0e75d45a7050daffe2e65badc27748032d13318e1d0af24fcae2c215424f0
+size 5777
diff --git a/ca_v3_run_20251215/final_model/README.md b/ca_v3_run_20251215/final_model/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/ca_v3_run_20251215/final_model/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/ca_v3_run_20251215/final_model/adapter_config.json b/ca_v3_run_20251215/final_model/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bd100e2ef4775697a7cb0c0abaae99f244053d68
--- /dev/null
+++ b/ca_v3_run_20251215/final_model/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/ca_v3_run_20251215/final_model/adapter_model.safetensors b/ca_v3_run_20251215/final_model/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ba2d53f00df555c320d5fa8bfd92a9508b7313e3
--- /dev/null
+++ b/ca_v3_run_20251215/final_model/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6966fb106cba724091bb384a14877dd0d857a05bd7354cef7953e56fdecb77
+size 201378736
diff --git a/ca_v3_run_20251215/final_model/optimizer.pt b/ca_v3_run_20251215/final_model/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..65b00be983c44726678d780022d5ad5e15976150
--- /dev/null
+++ b/ca_v3_run_20251215/final_model/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392183f58bb6c3c87cc8b1040b1bd5940b7f2522896624f3668d965de80ee89b
+size 402982627
diff --git a/ca_v3_run_20251215/final_model/rng_state.pth b/ca_v3_run_20251215/final_model/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b6e5ebccc9e6a700fd9d1abbdf919ba33a76cbed
--- /dev/null
+++ b/ca_v3_run_20251215/final_model/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a47d1ead692de2bce57a9ae7ba59450da50376926e3a3a2a0ebc83b70d9ba03
+size 14645
diff --git a/ca_v3_run_20251215/final_model/scheduler.pt b/ca_v3_run_20251215/final_model/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3b259f6f75e583e4febfc080b5b8331e00665a2f
--- /dev/null
+++ b/ca_v3_run_20251215/final_model/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30781be5b5c4396cc620b6281ac1b634d4288d62bfab3224155044b29d42cdb1
+size 1465
diff --git a/ca_v3_run_20251215/final_model/trainer_state.json b/ca_v3_run_20251215/final_model/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..008b27243cee0eb2e38fd9d96131f1a346233be4
--- /dev/null
+++ b/ca_v3_run_20251215/final_model/trainer_state.json
@@ -0,0 +1,1092 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.267627239227295,
+      "learning_rate": 0.0,
+      "loss": 0.8939,
+      "step": 1
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.5160397291183472,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6392,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.4698739051818848,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8476,
+      "step": 3
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 4.279767036437988,
+      "learning_rate": 1e-05,
+      "loss": 1.2988,
+      "step": 4
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 3.669569730758667,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.95,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2172225713729858,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.3448,
+      "step": 6
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 1.891830325126648,
+      "learning_rate": 2e-05,
+      "loss": 0.7179,
+      "step": 7
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.352062940597534,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.5782,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.2546859979629517,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.686,
+      "step": 9
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 1.1951119899749756,
+      "learning_rate": 3e-05,
+      "loss": 0.2151,
+      "step": 10
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 1.5607569217681885,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3339,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.513392448425293,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.7432,
+      "step": 12
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.3942737579345703,
+      "learning_rate": 4e-05,
+      "loss": 0.5372,
+      "step": 13
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 2.1662518978118896,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.5742,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.074810028076172,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6484,
+      "step": 15
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.5651564598083496,
+      "learning_rate": 5e-05,
+      "loss": 0.678,
+      "step": 16
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 3.3820931911468506,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.6619,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.7587597370147705,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.665,
+      "step": 18
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 2.234240770339966,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.4308,
+      "step": 19
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.0802106857299805,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.6038,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.3648719787597656,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.5436,
+      "step": 21
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 1.2552648782730103,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.6223,
+      "step": 22
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 2.2331910133361816,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.6468,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7010774612426758,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.6019,
+      "step": 24
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.6806925535202026,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3979,
+      "step": 25
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 1.4811266660690308,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.8038,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.5548367500305176,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.5653,
+      "step": 27
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.4900885820388794,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.7534,
+      "step": 28
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 1.2963446378707886,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.6946,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.885505199432373,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.8456,
+      "step": 30
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 1.0747458934783936,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.336,
+      "step": 31
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 2.0049006938934326,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.6669,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.020938515663147,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.6849,
+      "step": 33
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 1.3365986347198486,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.4813,
+      "step": 34
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 2.2962701320648193,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 1.156,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1328681707382202,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.4652,
+      "step": 36
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 1.3263046741485596,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.4638,
+      "step": 37
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 1.6372419595718384,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.6662,
+      "step": 38
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.3750609159469604,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.3029,
+      "step": 39
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.442150354385376,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.7255,
+      "step": 40
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.3133295774459839,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.6364,
+      "step": 41
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.2394391298294067,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.6514,
+      "step": 42
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 2.0945804119110107,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.4957,
+      "step": 43
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 2.036482810974121,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.5471,
+      "step": 44
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7951217889785767,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.4969,
+      "step": 45
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 1.3251290321350098,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5828,
+      "step": 46
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 1.5717222690582275,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.378,
+      "step": 47
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4296456575393677,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.3957,
+      "step": 48
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 1.3804540634155273,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.4861,
+      "step": 49
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.184690237045288,
+      "learning_rate": 4.257452643564155e-05,
+      "loss": 0.8223,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.361177682876587,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.7269,
+      "step": 51
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.2764381170272827,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.3787,
+      "step": 52
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 1.4495773315429688,
+      "learning_rate": 4.129143072053638e-05,
+      "loss": 0.2966,
+      "step": 53
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.055936813354492,
+      "learning_rate": 4.0845774184967754e-05,
+      "loss": 0.4485,
+      "step": 54
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 1.8481249809265137,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.4182,
+      "step": 55
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.6037787199020386,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.6953,
+      "step": 56
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.5313551425933838,
+      "learning_rate": 3.945830840419966e-05,
+      "loss": 0.3223,
+      "step": 57
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 1.3661636114120483,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.4186,
+      "step": 58
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 2.39021372795105,
+      "learning_rate": 3.8493766448787825e-05,
+      "loss": 0.7415,
+      "step": 59
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.5035974979400635,
+      "learning_rate": 3.8000403198230387e-05,
+      "loss": 0.9131,
+      "step": 60
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 1.3086011409759521,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.397,
+      "step": 61
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 1.9651494026184082,
+      "learning_rate": 3.699282783125616e-05,
+      "loss": 0.9127,
+      "step": 62
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.166289806365967,
+      "learning_rate": 3.6479161334675296e-05,
+      "loss": 0.6211,
+      "step": 63
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.1649678945541382,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3828,
+      "step": 64
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.7926881909370422,
+      "learning_rate": 3.543346136204545e-05,
+      "loss": 0.1886,
+      "step": 65
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2959918975830078,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3381,
+      "step": 66
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 1.3724843263626099,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.5337,
+      "step": 67
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.743539810180664,
+      "learning_rate": 3.382326411784672e-05,
+      "loss": 0.3935,
+      "step": 68
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.310335397720337,
+      "learning_rate": 3.327658544712395e-05,
+      "loss": 0.3857,
+      "step": 69
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 2.399306058883667,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 1.0896,
+      "step": 70
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 1.2522423267364502,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.1551,
+      "step": 71
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.307708740234375,
+      "learning_rate": 3.161085405093006e-05,
+      "loss": 0.3004,
+      "step": 72
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 1.527667760848999,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.3367,
+      "step": 73
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 1.2848842144012451,
+      "learning_rate": 3.048196560469758e-05,
+      "loss": 0.264,
+      "step": 74
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.7577385902404785,
+      "learning_rate": 2.9912915238320754e-05,
+      "loss": 0.3975,
+      "step": 75
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.2079553604125977,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1619,
+      "step": 76
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 1.2687911987304688,
+      "learning_rate": 2.876714280623708e-05,
+      "loss": 0.1523,
+      "step": 77
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.3904497623443604,
+      "learning_rate": 2.8191041196514873e-05,
+      "loss": 0.6355,
+      "step": 78
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 1.2210139036178589,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.1803,
+      "step": 79
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.2414464950561523,
+      "learning_rate": 2.7033966866696457e-05,
+      "loss": 0.2332,
+      "step": 80
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.8386731147766113,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 0.6357,
+      "step": 81
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 2.6382551193237305,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.3541,
+      "step": 82
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 3.260303020477295,
+      "learning_rate": 2.5290881645034932e-05,
+      "loss": 0.7056,
+      "step": 83
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.604124546051025,
+      "learning_rate": 2.470911835496508e-05,
+      "loss": 0.8796,
+      "step": 84
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 3.7330353260040283,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.2487,
+      "step": 85
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.9771713018417358,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.3601,
+      "step": 86
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 6.817903995513916,
+      "learning_rate": 2.2966033133303545e-05,
+      "loss": 1.3453,
+      "step": 87
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 2.8639299869537354,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.3974,
+      "step": 88
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 2.082796573638916,
+      "learning_rate": 2.1808958803485136e-05,
+      "loss": 0.4019,
+      "step": 89
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.427212655544281,
+      "learning_rate": 2.1232857193762924e-05,
+      "loss": 0.0465,
+      "step": 90
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 1.7197939157485962,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.2682,
+      "step": 91
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.09823339432477951,
+      "learning_rate": 2.0087084761679245e-05,
+      "loss": 0.0111,
+      "step": 92
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.9435588121414185,
+      "learning_rate": 1.9518034395302414e-05,
+      "loss": 0.124,
+      "step": 93
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 2.9964282512664795,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.3849,
+      "step": 94
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 1.595879077911377,
+      "learning_rate": 1.838914594906995e-05,
+      "loss": 0.2477,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.441842555999756,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.5461,
+      "step": 96
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 2.448079824447632,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.5091,
+      "step": 97
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 3.598569631576538,
+      "learning_rate": 1.672341455287605e-05,
+      "loss": 0.4161,
+      "step": 98
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.45053243637085,
+      "learning_rate": 1.617673588215328e-05,
+      "loss": 0.8538,
+      "step": 99
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.3044579029083252,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.171,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.4516909718513489,
+      "eval_runtime": 66.1438,
+      "eval_samples_per_second": 2.253,
+      "eval_steps_per_second": 1.134,
+      "step": 100
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 8.098329544067383,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 1.1298,
+      "step": 101
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.519363284111023,
+      "learning_rate": 1.4566538637954554e-05,
+      "loss": 0.1545,
+      "step": 102
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 2.4320404529571533,
+      "learning_rate": 1.4040721330273062e-05,
+      "loss": 0.1781,
+      "step": 103
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 4.600680828094482,
+      "learning_rate": 1.3520838665324703e-05,
+      "loss": 0.4178,
+      "step": 104
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4558080434799194,
+      "learning_rate": 1.3007172168743854e-05,
+      "loss": 0.1014,
+      "step": 105
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 1.6424729824066162,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.1476,
+      "step": 106
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 3.927393913269043,
+      "learning_rate": 1.1999596801769616e-05,
+      "loss": 1.0977,
+      "step": 107
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8934208154678345,
+      "learning_rate": 1.1506233551212186e-05,
+      "loss": 0.1165,
+      "step": 108
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 2.651909589767456,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.5939,
+      "step": 109
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 1.0333629846572876,
+      "learning_rate": 1.0541691595800337e-05,
+      "loss": 0.152,
+      "step": 110
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.1822710037231445,
+      "learning_rate": 1.0071035207430352e-05,
+      "loss": 0.4252,
+      "step": 111
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.6616872549057007,
+      "learning_rate": 9.608463116858542e-06,
+      "loss": 0.1772,
+      "step": 112
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 4.919057846069336,
+      "learning_rate": 9.154225815032242e-06,
+      "loss": 0.4062,
+      "step": 113
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.426158905029297,
+      "learning_rate": 8.708569279463622e-06,
+      "loss": 0.6537,
+      "step": 114
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 2.4902124404907227,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.1949,
+      "step": 115
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.6176963448524475,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.0729,
+      "step": 116
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.257253408432007,
+      "learning_rate": 7.4254735643584564e-06,
+      "loss": 0.2163,
+      "step": 117
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 1.069271445274353,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.156,
+      "step": 118
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 0.6102529764175415,
+      "learning_rate": 6.617274798504286e-06,
+      "loss": 0.0632,
+      "step": 119
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.137846946716309,
+      "learning_rate": 6.22799917546252e-06,
+      "loss": 0.5415,
+      "step": 120
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 2.0759520530700684,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.3255,
+      "step": 121
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 4.551874160766602,
+      "learning_rate": 5.48014933308352e-06,
+      "loss": 0.3398,
+      "step": 122
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0534967184066772,
+      "learning_rate": 5.121980087628803e-06,
+      "loss": 0.1326,
+      "step": 123
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 2.607910394668579,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.8089,
+      "step": 124
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.044987201690674,
+      "learning_rate": 4.438122617983443e-06,
+      "loss": 0.238,
+      "step": 125
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.440517544746399,
+      "learning_rate": 4.112804714676594e-06,
+      "loss": 0.1659,
+      "step": 126
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 3.426896333694458,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.4279,
+      "step": 127
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 2.2087795734405518,
+      "learning_rate": 3.4962713026158694e-06,
+      "loss": 1.0499,
+      "step": 128
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9487075805664062,
+      "learning_rate": 3.205389657580943e-06,
+      "loss": 0.1213,
+      "step": 129
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 2.0362558364868164,
+      "learning_rate": 2.9263101785268254e-06,
+      "loss": 0.6995,
+      "step": 130
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 4.185983180999756,
+      "learning_rate": 2.659183991914696e-06,
+      "loss": 0.6105,
+      "step": 131
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.219158411026001,
+      "learning_rate": 2.4041557512869878e-06,
+      "loss": 0.2062,
+      "step": 132
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.7529279589653015,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 0.0839,
+      "step": 133
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 4.446479320526123,
+      "learning_rate": 1.9309388911139426e-06,
+      "loss": 1.0925,
+      "step": 134
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.211433410644531,
+      "learning_rate": 1.713006526846439e-06,
+      "loss": 0.6347,
+      "step": 135
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 2.469029426574707,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.4994,
+      "step": 136
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 5.426701545715332,
+      "learning_rate": 1.31508393714177e-06,
+      "loss": 0.4131,
+      "step": 137
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.973341941833496,
+      "learning_rate": 1.1353091938067023e-06,
+      "loss": 0.3887,
+      "step": 138
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 2.101803779602051,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 0.2598,
+      "step": 139
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.5676771998405457,
+      "learning_rate": 8.146195134284052e-07,
+      "loss": 0.0698,
+      "step": 140
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.5499122142791748,
+      "learning_rate": 6.738782355044049e-07,
+      "loss": 0.0823,
+      "step": 141
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 0.36405226588249207,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.0406,
+      "step": 142
+    },
+    {
+      "epoch": 0.9533333333333334,
+      "grad_norm": 1.898514747619629,
+      "learning_rate": 4.319838323396691e-07,
+      "loss": 0.4404,
+      "step": 143
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.7996866703033447,
+      "learning_rate": 3.309616971855195e-07,
+      "loss": 0.2531,
+      "step": 144
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 2.6673455238342285,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.7721,
+      "step": 145
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 7.725250244140625,
+      "learning_rate": 1.6904105645142444e-07,
+      "loss": 1.7164,
+      "step": 146
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.411264419555664,
+      "learning_rate": 1.0823023375489127e-07,
+      "loss": 0.4909,
+      "step": 147
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.3376047611236572,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 0.1719,
+      "step": 148
+    },
+    {
+      "epoch": 0.9933333333333333,
+      "grad_norm": 1.7119640111923218,
+      "learning_rate": 2.7072216536885853e-08,
+      "loss": 0.1636,
+      "step": 149
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.7593977451324463,
+      "learning_rate": 6.768970513457151e-09,
+      "loss": 0.5289,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 49,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0335481997190758e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/ca_v3_run_20251215/final_model/training_args.bin b/ca_v3_run_20251215/final_model/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..88b4ad4e5f06f68e064e676272032d9cd8af9147
--- /dev/null
+++ b/ca_v3_run_20251215/final_model/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c0e75d45a7050daffe2e65badc27748032d13318e1d0af24fcae2c215424f0
+size 5777
diff --git a/exp1_original_data_rerun_20251215/checkpoint-25/README.md b/exp1_original_data_rerun_20251215/checkpoint-25/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-25/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/exp1_original_data_rerun_20251215/checkpoint-25/adapter_config.json b/exp1_original_data_rerun_20251215/checkpoint-25/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6e1b97d58cc89e1ba143a0341bc76f020124b949
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-25/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/exp1_original_data_rerun_20251215/checkpoint-25/adapter_model.safetensors b/exp1_original_data_rerun_20251215/checkpoint-25/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0387276dec93a50675a02817f13478f51f9b5c66
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-25/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e2c9cdaa5dc25faa9d1735f8da9dc9ec68820f238391edf058b46bbdbf2a58
+size 50357488
diff --git a/exp1_original_data_rerun_20251215/checkpoint-25/optimizer.pt b/exp1_original_data_rerun_20251215/checkpoint-25/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..041c10e778bcdd5ac9b92220db147b4244196a27
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-25/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94857594d6b10edc10a2b1ffe1b431f107b4df4f16f96fe2f09baf7829127bfc
+size 100828235
diff --git a/exp1_original_data_rerun_20251215/checkpoint-25/rng_state.pth b/exp1_original_data_rerun_20251215/checkpoint-25/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..96b89c979c97a96a49759cb62c7f5d70b347c754
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-25/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d835afb5a277eef9cb89e6f2ae639ae653e14a7cb8a24b9466a653d407505e
+size 14645
diff --git a/exp1_original_data_rerun_20251215/checkpoint-25/scheduler.pt b/exp1_original_data_rerun_20251215/checkpoint-25/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1827864dd06296ae43b1e6a492ceadb698ff377f
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-25/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c8359e7027a1d5dd6df276c01589220164c80a154e5feeb97d92110a26709f
+size 1465
diff --git a/exp1_original_data_rerun_20251215/checkpoint-25/trainer_state.json b/exp1_original_data_rerun_20251215/checkpoint-25/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c75a8887772161fcaf05e71462515a12934d4d7c
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-25/trainer_state.json
@@ -0,0 +1,48 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3333333333333333,
+  "eval_steps": 100,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.7970004081726074,
+      "learning_rate": 0.00019989008914857116,
+      "loss": 0.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.5293543934822083,
+      "learning_rate": 0.00018699063724087904,
+      "loss": 0.4794,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.44163505668096e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/exp1_original_data_rerun_20251215/checkpoint-25/training_args.bin b/exp1_original_data_rerun_20251215/checkpoint-25/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1a708cd653bb0fd870e02a3cd2b92e79b2530fde
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-25/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff11aa937808576e06d64e88c71a90de51b18fbb50367206f5df16539755319c
+size 5777
diff --git a/exp1_original_data_rerun_20251215/checkpoint-50/README.md b/exp1_original_data_rerun_20251215/checkpoint-50/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-50/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/exp1_original_data_rerun_20251215/checkpoint-50/adapter_config.json b/exp1_original_data_rerun_20251215/checkpoint-50/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6e1b97d58cc89e1ba143a0341bc76f020124b949
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-50/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/exp1_original_data_rerun_20251215/checkpoint-50/adapter_model.safetensors b/exp1_original_data_rerun_20251215/checkpoint-50/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bd6b352ec048be49d0abd6c9ebff45690c6201b9
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-50/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a693a1856aa80d52479a0c100e3dd22b9f2cf3350bf0504b521f8666df4aaa
+size 50357488
diff --git a/exp1_original_data_rerun_20251215/checkpoint-50/optimizer.pt b/exp1_original_data_rerun_20251215/checkpoint-50/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2ff102073865deca240a6abaa95b5bfdac3724b1
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-50/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bdbbd887d2d89e2ed760d3ba062c14a89979e75d195c409f833e128ce7672f
+size 100828235
diff --git a/exp1_original_data_rerun_20251215/checkpoint-50/rng_state.pth b/exp1_original_data_rerun_20251215/checkpoint-50/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..96ffff0324a89bb899f85c1af2016ce1fa7b4ffe
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-50/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057c45ca36a011105360316599658ccb9adeb32ddf48eb0a08af1c7fab0219ff
+size 14645
diff --git a/exp1_original_data_rerun_20251215/checkpoint-50/scheduler.pt b/exp1_original_data_rerun_20251215/checkpoint-50/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..da61222504cd7cf8ee20fde4cb68d64954a37cc6
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-50/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddad8914229c8e7dbd757aa8426289cb9a42c09ea70df2b48d8beeefe5bbdf3
+size 1465
diff --git a/exp1_original_data_rerun_20251215/checkpoint-50/trainer_state.json b/exp1_original_data_rerun_20251215/checkpoint-50/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5895d61e46ebe3d160d6e9128917945efa09bdb3
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-50/trainer_state.json
@@ -0,0 +1,69 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6666666666666666,
+  "eval_steps": 100,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.7970004081726074,
+      "learning_rate": 0.00019989008914857116,
+      "loss": 0.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.5293543934822083,
+      "learning_rate": 0.00018699063724087904,
+      "loss": 0.4794,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.553859233856201,
+      "learning_rate": 0.00015531311541251995,
+      "loss": 0.5135,
+      "step": 30
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.5555204153060913,
+      "learning_rate": 0.00011169553219720828,
+      "loss": 0.4293,
+      "step": 40
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.5811039209365845,
+      "learning_rate": 6.555331497156672e-05,
+      "loss": 0.3595,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.88327011336192e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/exp1_original_data_rerun_20251215/checkpoint-50/training_args.bin b/exp1_original_data_rerun_20251215/checkpoint-50/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1a708cd653bb0fd870e02a3cd2b92e79b2530fde
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-50/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff11aa937808576e06d64e88c71a90de51b18fbb50367206f5df16539755319c
+size 5777
diff --git a/exp1_original_data_rerun_20251215/checkpoint-75/README.md b/exp1_original_data_rerun_20251215/checkpoint-75/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-75/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/exp1_original_data_rerun_20251215/checkpoint-75/adapter_config.json b/exp1_original_data_rerun_20251215/checkpoint-75/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6e1b97d58cc89e1ba143a0341bc76f020124b949
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-75/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/exp1_original_data_rerun_20251215/checkpoint-75/adapter_model.safetensors b/exp1_original_data_rerun_20251215/checkpoint-75/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..31d4ba961ff4fefbcad9ede198aeaf117ac5b842
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-75/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1198a351782806e601c4636f9b985371f37f957f7b10fc80464c9854482920
+size 50357488
diff --git a/exp1_original_data_rerun_20251215/checkpoint-75/optimizer.pt b/exp1_original_data_rerun_20251215/checkpoint-75/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..34391f325e30a47ea8b885887d4474102d2b9bd2
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-75/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29f74315e2284a0f0cafef87a50967127cdf5f6a56952b38534d09486e349ce
+size 100828235
diff --git a/exp1_original_data_rerun_20251215/checkpoint-75/rng_state.pth b/exp1_original_data_rerun_20251215/checkpoint-75/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f1ccd07015ba9a7f143ecf3381804bec4063994a
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-75/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0fba1844830d45a8a34c4724eaf74319c2c1d5554c04fdd04358ce4d50fd957
+size 14645
diff --git a/exp1_original_data_rerun_20251215/checkpoint-75/scheduler.pt b/exp1_original_data_rerun_20251215/checkpoint-75/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c480b248346ea1e19108e9c980f2968a083c212e
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-75/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05c28e789afe22134e5b011ace0c3a78d4d599d812231bc42d48ca46cfc515b
+size 1465
diff --git a/exp1_original_data_rerun_20251215/checkpoint-75/trainer_state.json b/exp1_original_data_rerun_20251215/checkpoint-75/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5afe5e7300b14ad7d669eb67a3d4c58908a21409
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-75/trainer_state.json
@@ -0,0 +1,83 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.7970004081726074,
+      "learning_rate": 0.00019989008914857116,
+      "loss": 0.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.5293543934822083,
+      "learning_rate": 0.00018699063724087904,
+      "loss": 0.4794,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.553859233856201,
+      "learning_rate": 0.00015531311541251995,
+      "loss": 0.5135,
+      "step": 30
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.5555204153060913,
+      "learning_rate": 0.00011169553219720828,
+      "loss": 0.4293,
+      "step": 40
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.5811039209365845,
+      "learning_rate": 6.555331497156672e-05,
+      "loss": 0.3595,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2460683584213257,
+      "learning_rate": 2.6846866473633125e-05,
+      "loss": 0.491,
+      "step": 60
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.010131597518921,
+      "learning_rate": 3.931481242315993e-06,
+      "loss": 0.4156,
+      "step": 70
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.032490517004288e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/exp1_original_data_rerun_20251215/checkpoint-75/training_args.bin b/exp1_original_data_rerun_20251215/checkpoint-75/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1a708cd653bb0fd870e02a3cd2b92e79b2530fde
--- /dev/null
+++ b/exp1_original_data_rerun_20251215/checkpoint-75/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff11aa937808576e06d64e88c71a90de51b18fbb50367206f5df16539755319c
+size 5777
diff --git a/exp2_signalc_20251215/checkpoint-147/README.md b/exp2_signalc_20251215/checkpoint-147/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-147/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/exp2_signalc_20251215/checkpoint-147/adapter_config.json b/exp2_signalc_20251215/checkpoint-147/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4d747200220490dff0f82aa49e63f702a859ccc
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-147/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/exp2_signalc_20251215/checkpoint-147/adapter_model.safetensors b/exp2_signalc_20251215/checkpoint-147/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cb910bb99c5ee985feb758c7c7097128700d930c
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-147/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ab7d9d0780cf84e34fa0868b9e4c618ea308485f0d6ee931a63502516bac74
+size 201378736
diff --git a/exp2_signalc_20251215/checkpoint-147/optimizer.pt b/exp2_signalc_20251215/checkpoint-147/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..50d666425a9fc823e15c2d3b599580760449989e
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-147/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44aea868f1ec2ea45779236f07660fd3db7beae8c91ee30e0467f39b07a30ba5
+size 402982627
diff --git a/exp2_signalc_20251215/checkpoint-147/rng_state.pth b/exp2_signalc_20251215/checkpoint-147/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0178e697ee9dfc09593374e91de3e5c7e0217aee
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-147/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283c4259167c1de6fc9b0d70fb38093d1c85343ca9ff0f2e605bd2011addd045
+size 14645
diff --git a/exp2_signalc_20251215/checkpoint-147/scheduler.pt b/exp2_signalc_20251215/checkpoint-147/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b196c8e7a4834975b028188c1c8c2559af111ec
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-147/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6e49a0a1dc514c3062fdc71df85d50b768febd62f2e9b412554326fd48eb9c
+size 1465
diff --git a/exp2_signalc_20251215/checkpoint-147/trainer_state.json b/exp2_signalc_20251215/checkpoint-147/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3edb0fb9bacc48e25ba37e437cd6157fa733e7f6
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-147/trainer_state.json
@@ -0,0 +1,1071 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.98,
+  "eval_steps": 100,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.007404327392578,
+      "learning_rate": 0.0,
+      "loss": 0.6595,
+      "step": 1
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.8502237796783447,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.1139,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2331303358078003,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.578,
+      "step": 3
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.2300695180892944,
+      "learning_rate": 1e-05,
+      "loss": 0.776,
+      "step": 4
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 3.3759779930114746,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7998,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.43403697013855,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.4564,
+      "step": 6
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 3.449822187423706,
+      "learning_rate": 2e-05,
+      "loss": 0.899,
+      "step": 7
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.4381998777389526,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.2811,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.234094500541687,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1841,
+      "step": 9
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.9779098033905029,
+      "learning_rate": 3e-05,
+      "loss": 0.2704,
+      "step": 10
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 1.1498095989227295,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.2534,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.928687334060669,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.5162,
+      "step": 12
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.8929930925369263,
+      "learning_rate": 4e-05,
+      "loss": 0.9282,
+      "step": 13
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 3.466400146484375,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.8342,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.0776634216308594,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7976,
+      "step": 15
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.7737135887145996,
+      "learning_rate": 5e-05,
+      "loss": 1.1665,
+      "step": 16
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 1.192466139793396,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.5163,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.5976535081863403,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.5035,
+      "step": 18
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 1.513372540473938,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.6089,
+      "step": 19
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.6169334650039673,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.6053,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.9578418731689453,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.8322,
+      "step": 21
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 2.1667706966400146,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.8027,
+      "step": 22
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 1.4784480333328247,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.4951,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.7624332904815674,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.6269,
+      "step": 24
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.6521016359329224,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3331,
+      "step": 25
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 1.1457144021987915,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.284,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.4980254173278809,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.6191,
+      "step": 27
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.3955901861190796,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.662,
+      "step": 28
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 1.2383167743682861,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.79,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2159212827682495,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.4194,
+      "step": 30
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 2.2957308292388916,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.5185,
+      "step": 31
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.6989065408706665,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.2625,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.02852463722229,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.6494,
+      "step": 33
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 1.653140902519226,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.5486,
+      "step": 34
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 1.7378313541412354,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 0.6112,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.8570767641067505,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.8117,
+      "step": 36
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.6243714094161987,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.284,
+      "step": 37
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 1.335660457611084,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.5556,
+      "step": 38
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.071352958679199,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.6837,
+      "step": 39
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.6223986148834229,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.6445,
+      "step": 40
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.174696445465088,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.129868507385254,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.4056,
+      "step": 42
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 1.917558193206787,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 1.23,
+      "step": 43
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 1.72930908203125,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.6128,
+      "step": 44
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7508667707443237,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.8213,
+      "step": 45
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.9080920815467834,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.2085,
+      "step": 46
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 1.75723135471344,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.5145,
+      "step": 47
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.450878620147705,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.6667,
+      "step": 48
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.8492142558097839,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.2838,
+      "step": 49
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.2550184726715088,
+      "learning_rate": 4.257452643564155e-05,
+      "loss": 0.3858,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.2642593383789062,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.6531,
+      "step": 51
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 3.926060199737549,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.4836,
+      "step": 52
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 1.8190771341323853,
+      "learning_rate": 4.129143072053638e-05,
+      "loss": 0.3158,
+      "step": 53
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.4268187284469604,
+      "learning_rate": 4.0845774184967754e-05,
+      "loss": 0.5298,
+      "step": 54
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 1.9656697511672974,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.4887,
+      "step": 55
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.1335246562957764,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.1837,
+      "step": 56
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.525275707244873,
+      "learning_rate": 3.945830840419966e-05,
+      "loss": 0.8998,
+      "step": 57
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 2.12524676322937,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.3827,
+      "step": 58
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 1.9228296279907227,
+      "learning_rate": 3.8493766448787825e-05,
+      "loss": 0.5591,
+      "step": 59
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3674192428588867,
+      "learning_rate": 3.8000403198230387e-05,
+      "loss": 0.4872,
+      "step": 60
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 1.965265154838562,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.5459,
+      "step": 61
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 2.329216241836548,
+      "learning_rate": 3.699282783125616e-05,
+      "loss": 0.7548,
+      "step": 62
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.118192434310913,
+      "learning_rate": 3.6479161334675296e-05,
+      "loss": 0.6821,
+      "step": 63
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.9981805086135864,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3079,
+      "step": 64
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 1.0037565231323242,
+      "learning_rate": 3.543346136204545e-05,
+      "loss": 0.3274,
+      "step": 65
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8539446592330933,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3298,
+      "step": 66
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 1.1413832902908325,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.3062,
+      "step": 67
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 2.7091305255889893,
+      "learning_rate": 3.382326411784672e-05,
+      "loss": 0.4897,
+      "step": 68
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.9014657735824585,
+      "learning_rate": 3.327658544712395e-05,
+      "loss": 0.422,
+      "step": 69
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 1.7714844942092896,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.2594,
+      "step": 70
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 0.7899397611618042,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.1847,
+      "step": 71
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.2437670230865479,
+      "learning_rate": 3.161085405093006e-05,
+      "loss": 0.2063,
+      "step": 72
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 1.4275377988815308,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.7009,
+      "step": 73
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 1.6646203994750977,
+      "learning_rate": 3.048196560469758e-05,
+      "loss": 0.2215,
+      "step": 74
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.504795551300049,
+      "learning_rate": 2.9912915238320754e-05,
+      "loss": 0.5467,
+      "step": 75
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.1971930265426636,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1757,
+      "step": 76
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 1.2171498537063599,
+      "learning_rate": 2.876714280623708e-05,
+      "loss": 0.1898,
+      "step": 77
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5181541442871094,
+      "learning_rate": 2.8191041196514873e-05,
+      "loss": 0.2299,
+      "step": 78
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 1.1093655824661255,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.1639,
+      "step": 79
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 4.772696495056152,
+      "learning_rate": 2.7033966866696457e-05,
+      "loss": 0.9071,
+      "step": 80
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.373753547668457,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 1.315,
+      "step": 81
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.4806381165981293,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.0859,
+      "step": 82
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 2.003674030303955,
+      "learning_rate": 2.5290881645034932e-05,
+      "loss": 0.5889,
+      "step": 83
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.2717702388763428,
+      "learning_rate": 2.470911835496508e-05,
+      "loss": 0.2551,
+      "step": 84
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 3.508592367172241,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.7869,
+      "step": 85
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.1418286561965942,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.1538,
+      "step": 86
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9381025433540344,
+      "learning_rate": 2.2966033133303545e-05,
+      "loss": 0.0973,
+      "step": 87
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 2.441453218460083,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.86,
+      "step": 88
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.7263301610946655,
+      "learning_rate": 2.1808958803485136e-05,
+      "loss": 0.1041,
+      "step": 89
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.5983655452728271,
+      "learning_rate": 2.1232857193762924e-05,
+      "loss": 0.4031,
+      "step": 90
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 2.9620091915130615,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.7484,
+      "step": 91
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.8278090953826904,
+      "learning_rate": 2.0087084761679245e-05,
+      "loss": 0.4001,
+      "step": 92
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.282475233078003,
+      "learning_rate": 1.9518034395302414e-05,
+      "loss": 0.4047,
+      "step": 93
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 1.196440577507019,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.1718,
+      "step": 94
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 3.1636035442352295,
+      "learning_rate": 1.838914594906995e-05,
+      "loss": 0.773,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.34068605303764343,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.0501,
+      "step": 96
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 2.373602867126465,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.6528,
+      "step": 97
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 3.809894561767578,
+      "learning_rate": 1.672341455287605e-05,
+      "loss": 0.4916,
+      "step": 98
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.143580913543701,
+      "learning_rate": 1.617673588215328e-05,
+      "loss": 0.5245,
+      "step": 99
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.8998221158981323,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.1163,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.3062487244606018,
+      "eval_runtime": 165.5432,
+      "eval_samples_per_second": 2.259,
+      "eval_steps_per_second": 1.13,
+      "step": 100
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 1.3396159410476685,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 0.2617,
+      "step": 101
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.4432024955749512,
+      "learning_rate": 1.4566538637954554e-05,
+      "loss": 0.2208,
+      "step": 102
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 3.2442052364349365,
+      "learning_rate": 1.4040721330273062e-05,
+      "loss": 0.5551,
+      "step": 103
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.5302101373672485,
+      "learning_rate": 1.3520838665324703e-05,
+      "loss": 0.2195,
+      "step": 104
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.544744491577148,
+      "learning_rate": 1.3007172168743854e-05,
+      "loss": 0.6881,
+      "step": 105
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 3.1280434131622314,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.7843,
+      "step": 106
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 3.5932955741882324,
+      "learning_rate": 1.1999596801769616e-05,
+      "loss": 0.405,
+      "step": 107
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8064641952514648,
+      "learning_rate": 1.1506233551212186e-05,
+      "loss": 0.0927,
+      "step": 108
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 1.5594532489776611,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.2154,
+      "step": 109
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.6679570078849792,
+      "learning_rate": 1.0541691595800337e-05,
+      "loss": 0.0839,
+      "step": 110
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.8102202415466309,
+      "learning_rate": 1.0071035207430352e-05,
+      "loss": 0.5539,
+      "step": 111
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.7791885137557983,
+      "learning_rate": 9.608463116858542e-06,
+      "loss": 0.2957,
+      "step": 112
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 2.7545344829559326,
+      "learning_rate": 9.154225815032242e-06,
+      "loss": 0.8108,
+      "step": 113
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.1660912036895752,
+      "learning_rate": 8.708569279463622e-06,
+      "loss": 0.0814,
+      "step": 114
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.9156790971755981,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.1564,
+      "step": 115
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 4.86236572265625,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.6666,
+      "step": 116
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.032678127288818,
+      "learning_rate": 7.4254735643584564e-06,
+      "loss": 0.4821,
+      "step": 117
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 2.2866246700286865,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.2771,
+      "step": 118
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 2.304269790649414,
+      "learning_rate": 6.617274798504286e-06,
+      "loss": 0.302,
+      "step": 119
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.9873311519622803,
+      "learning_rate": 6.22799917546252e-06,
+      "loss": 0.3067,
+      "step": 120
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 3.1299631595611572,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.6448,
+      "step": 121
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 1.7106144428253174,
+      "learning_rate": 5.48014933308352e-06,
+      "loss": 0.3074,
+      "step": 122
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.6227457523345947,
+      "learning_rate": 5.121980087628803e-06,
+      "loss": 0.1963,
+      "step": 123
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 4.482200622558594,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.7424,
+      "step": 124
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.32167911529541,
+      "learning_rate": 4.438122617983443e-06,
+      "loss": 0.5608,
+      "step": 125
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7932979464530945,
+      "learning_rate": 4.112804714676594e-06,
+      "loss": 0.0947,
+      "step": 126
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 0.28471994400024414,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.0437,
+      "step": 127
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 2.5803308486938477,
+      "learning_rate": 3.4962713026158694e-06,
+      "loss": 0.2781,
+      "step": 128
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.4017975330352783,
+      "learning_rate": 3.205389657580943e-06,
+      "loss": 0.5838,
+      "step": 129
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 3.2663633823394775,
+      "learning_rate": 2.9263101785268254e-06,
+      "loss": 0.473,
+      "step": 130
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 2.067620277404785,
+      "learning_rate": 2.659183991914696e-06,
+      "loss": 0.2994,
+      "step": 131
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.4989666938781738,
+      "learning_rate": 2.4041557512869878e-06,
+      "loss": 0.1795,
+      "step": 132
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 1.2955349683761597,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 0.193,
+      "step": 133
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 0.9127891659736633,
+      "learning_rate": 1.9309388911139426e-06,
+      "loss": 0.1546,
+      "step": 134
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.5144217014312744,
+      "learning_rate": 1.713006526846439e-06,
+      "loss": 0.2405,
+      "step": 135
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 3.5872600078582764,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.8543,
+      "step": 136
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 1.16169011592865,
+      "learning_rate": 1.31508393714177e-06,
+      "loss": 0.1759,
+      "step": 137
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.221109390258789,
+      "learning_rate": 1.1353091938067023e-06,
+      "loss": 0.1709,
+      "step": 138
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 1.7916854619979858,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 0.4347,
+      "step": 139
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 2.9777231216430664,
+      "learning_rate": 8.146195134284052e-07,
+      "loss": 0.3878,
+      "step": 140
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.271992206573486,
+      "learning_rate": 6.738782355044049e-07,
+      "loss": 0.3858,
+      "step": 141
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 1.1091471910476685,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.1942,
+      "step": 142
+    },
+    {
+      "epoch": 0.9533333333333334,
+      "grad_norm": 3.5003552436828613,
+      "learning_rate": 4.319838323396691e-07,
+      "loss": 0.4267,
+      "step": 143
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.55532169342041,
+      "learning_rate": 3.309616971855195e-07,
+      "loss": 0.3795,
+      "step": 144
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 2.3853328227996826,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.1976,
+      "step": 145
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 1.388493537902832,
+      "learning_rate": 1.6904105645142444e-07,
+      "loss": 0.1673,
+      "step": 146
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.8709473609924316,
+      "learning_rate": 1.0823023375489127e-07,
+      "loss": 0.3265,
+      "step": 147
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 49,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.014568182695854e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/exp2_signalc_20251215/checkpoint-147/training_args.bin b/exp2_signalc_20251215/checkpoint-147/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..591bbc618a96850d2fc0f24befec3b8cdb986d33
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-147/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50702002f1fdf6d5e91c92ea8225d6a002d69ced0f5b2ce1f30eb32ce7dad475
+size 5841
diff --git a/exp2_signalc_20251215/checkpoint-150/README.md b/exp2_signalc_20251215/checkpoint-150/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-150/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/exp2_signalc_20251215/checkpoint-150/adapter_config.json b/exp2_signalc_20251215/checkpoint-150/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4d747200220490dff0f82aa49e63f702a859ccc
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-150/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/exp2_signalc_20251215/checkpoint-150/adapter_model.safetensors b/exp2_signalc_20251215/checkpoint-150/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..33672935cb7c3d885ecc8c264c0061e5437e8b82
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-150/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b952f9f010e213946ed7983bb5affbcb494295dc69e15839f0f632edc00432e
+size 201378736
diff --git a/exp2_signalc_20251215/checkpoint-150/optimizer.pt b/exp2_signalc_20251215/checkpoint-150/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a4bdf0063177dcb555b7eaaa840926049aa2294b
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-150/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4902575f7c13703f23c635f85725d77ad1e0464817b798ca89ef732b30a97c58
+size 402982627
diff --git a/exp2_signalc_20251215/checkpoint-150/rng_state.pth b/exp2_signalc_20251215/checkpoint-150/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b6e5ebccc9e6a700fd9d1abbdf919ba33a76cbed
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-150/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a47d1ead692de2bce57a9ae7ba59450da50376926e3a3a2a0ebc83b70d9ba03
+size 14645
diff --git a/exp2_signalc_20251215/checkpoint-150/scheduler.pt b/exp2_signalc_20251215/checkpoint-150/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3b259f6f75e583e4febfc080b5b8331e00665a2f
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-150/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30781be5b5c4396cc620b6281ac1b634d4288d62bfab3224155044b29d42cdb1
+size 1465
diff --git a/exp2_signalc_20251215/checkpoint-150/trainer_state.json b/exp2_signalc_20251215/checkpoint-150/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..bb62e24cd2755b7ec51a9a2e10d2228b608f4c0c
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-150/trainer_state.json
@@ -0,0 +1,1092 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.007404327392578,
+      "learning_rate": 0.0,
+      "loss": 0.6595,
+      "step": 1
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.8502237796783447,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.1139,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2331303358078003,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.578,
+      "step": 3
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.2300695180892944,
+      "learning_rate": 1e-05,
+      "loss": 0.776,
+      "step": 4
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 3.3759779930114746,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7998,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.43403697013855,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.4564,
+      "step": 6
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 3.449822187423706,
+      "learning_rate": 2e-05,
+      "loss": 0.899,
+      "step": 7
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.4381998777389526,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.2811,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.234094500541687,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1841,
+      "step": 9
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.9779098033905029,
+      "learning_rate": 3e-05,
+      "loss": 0.2704,
+      "step": 10
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 1.1498095989227295,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.2534,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.928687334060669,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.5162,
+      "step": 12
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.8929930925369263,
+      "learning_rate": 4e-05,
+      "loss": 0.9282,
+      "step": 13
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 3.466400146484375,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.8342,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.0776634216308594,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7976,
+      "step": 15
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.7737135887145996,
+      "learning_rate": 5e-05,
+      "loss": 1.1665,
+      "step": 16
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 1.192466139793396,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.5163,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.5976535081863403,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.5035,
+      "step": 18
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 1.513372540473938,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.6089,
+      "step": 19
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.6169334650039673,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.6053,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.9578418731689453,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.8322,
+      "step": 21
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 2.1667706966400146,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.8027,
+      "step": 22
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 1.4784480333328247,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.4951,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.7624332904815674,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.6269,
+      "step": 24
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.6521016359329224,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3331,
+      "step": 25
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 1.1457144021987915,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.284,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.4980254173278809,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.6191,
+      "step": 27
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.3955901861190796,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.662,
+      "step": 28
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 1.2383167743682861,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.79,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2159212827682495,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.4194,
+      "step": 30
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 2.2957308292388916,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.5185,
+      "step": 31
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.6989065408706665,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.2625,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.02852463722229,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.6494,
+      "step": 33
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 1.653140902519226,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.5486,
+      "step": 34
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 1.7378313541412354,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 0.6112,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.8570767641067505,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.8117,
+      "step": 36
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.6243714094161987,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.284,
+      "step": 37
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 1.335660457611084,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.5556,
+      "step": 38
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.071352958679199,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.6837,
+      "step": 39
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.6223986148834229,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.6445,
+      "step": 40
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.174696445465088,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.129868507385254,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.4056,
+      "step": 42
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 1.917558193206787,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 1.23,
+      "step": 43
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 1.72930908203125,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.6128,
+      "step": 44
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7508667707443237,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.8213,
+      "step": 45
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.9080920815467834,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.2085,
+      "step": 46
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 1.75723135471344,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.5145,
+      "step": 47
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.450878620147705,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.6667,
+      "step": 48
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.8492142558097839,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.2838,
+      "step": 49
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.2550184726715088,
+      "learning_rate": 4.257452643564155e-05,
+      "loss": 0.3858,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.2642593383789062,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.6531,
+      "step": 51
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 3.926060199737549,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.4836,
+      "step": 52
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 1.8190771341323853,
+      "learning_rate": 4.129143072053638e-05,
+      "loss": 0.3158,
+      "step": 53
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.4268187284469604,
+      "learning_rate": 4.0845774184967754e-05,
+      "loss": 0.5298,
+      "step": 54
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 1.9656697511672974,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.4887,
+      "step": 55
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.1335246562957764,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.1837,
+      "step": 56
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.525275707244873,
+      "learning_rate": 3.945830840419966e-05,
+      "loss": 0.8998,
+      "step": 57
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 2.12524676322937,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.3827,
+      "step": 58
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 1.9228296279907227,
+      "learning_rate": 3.8493766448787825e-05,
+      "loss": 0.5591,
+      "step": 59
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3674192428588867,
+      "learning_rate": 3.8000403198230387e-05,
+      "loss": 0.4872,
+      "step": 60
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 1.965265154838562,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.5459,
+      "step": 61
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 2.329216241836548,
+      "learning_rate": 3.699282783125616e-05,
+      "loss": 0.7548,
+      "step": 62
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.118192434310913,
+      "learning_rate": 3.6479161334675296e-05,
+      "loss": 0.6821,
+      "step": 63
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.9981805086135864,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3079,
+      "step": 64
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 1.0037565231323242,
+      "learning_rate": 3.543346136204545e-05,
+      "loss": 0.3274,
+      "step": 65
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8539446592330933,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3298,
+      "step": 66
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 1.1413832902908325,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.3062,
+      "step": 67
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 2.7091305255889893,
+      "learning_rate": 3.382326411784672e-05,
+      "loss": 0.4897,
+      "step": 68
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.9014657735824585,
+      "learning_rate": 3.327658544712395e-05,
+      "loss": 0.422,
+      "step": 69
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 1.7714844942092896,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.2594,
+      "step": 70
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 0.7899397611618042,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.1847,
+      "step": 71
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.2437670230865479,
+      "learning_rate": 3.161085405093006e-05,
+      "loss": 0.2063,
+      "step": 72
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 1.4275377988815308,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.7009,
+      "step": 73
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 1.6646203994750977,
+      "learning_rate": 3.048196560469758e-05,
+      "loss": 0.2215,
+      "step": 74
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.504795551300049,
+      "learning_rate": 2.9912915238320754e-05,
+      "loss": 0.5467,
+      "step": 75
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.1971930265426636,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1757,
+      "step": 76
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 1.2171498537063599,
+      "learning_rate": 2.876714280623708e-05,
+      "loss": 0.1898,
+      "step": 77
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5181541442871094,
+      "learning_rate": 2.8191041196514873e-05,
+      "loss": 0.2299,
+      "step": 78
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 1.1093655824661255,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.1639,
+      "step": 79
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 4.772696495056152,
+      "learning_rate": 2.7033966866696457e-05,
+      "loss": 0.9071,
+      "step": 80
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.373753547668457,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 1.315,
+      "step": 81
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.4806381165981293,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.0859,
+      "step": 82
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 2.003674030303955,
+      "learning_rate": 2.5290881645034932e-05,
+      "loss": 0.5889,
+      "step": 83
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.2717702388763428,
+      "learning_rate": 2.470911835496508e-05,
+      "loss": 0.2551,
+      "step": 84
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 3.508592367172241,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.7869,
+      "step": 85
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.1418286561965942,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.1538,
+      "step": 86
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9381025433540344,
+      "learning_rate": 2.2966033133303545e-05,
+      "loss": 0.0973,
+      "step": 87
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 2.441453218460083,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.86,
+      "step": 88
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.7263301610946655,
+      "learning_rate": 2.1808958803485136e-05,
+      "loss": 0.1041,
+      "step": 89
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.5983655452728271,
+      "learning_rate": 2.1232857193762924e-05,
+      "loss": 0.4031,
+      "step": 90
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 2.9620091915130615,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.7484,
+      "step": 91
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.8278090953826904,
+      "learning_rate": 2.0087084761679245e-05,
+      "loss": 0.4001,
+      "step": 92
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.282475233078003,
+      "learning_rate": 1.9518034395302414e-05,
+      "loss": 0.4047,
+      "step": 93
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 1.196440577507019,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.1718,
+      "step": 94
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 3.1636035442352295,
+      "learning_rate": 1.838914594906995e-05,
+      "loss": 0.773,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.34068605303764343,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.0501,
+      "step": 96
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 2.373602867126465,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.6528,
+      "step": 97
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 3.809894561767578,
+      "learning_rate": 1.672341455287605e-05,
+      "loss": 0.4916,
+      "step": 98
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.143580913543701,
+      "learning_rate": 1.617673588215328e-05,
+      "loss": 0.5245,
+      "step": 99
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.8998221158981323,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.1163,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.3062487244606018,
+      "eval_runtime": 165.5432,
+      "eval_samples_per_second": 2.259,
+      "eval_steps_per_second": 1.13,
+      "step": 100
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 1.3396159410476685,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 0.2617,
+      "step": 101
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.4432024955749512,
+      "learning_rate": 1.4566538637954554e-05,
+      "loss": 0.2208,
+      "step": 102
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 3.2442052364349365,
+      "learning_rate": 1.4040721330273062e-05,
+      "loss": 0.5551,
+      "step": 103
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.5302101373672485,
+      "learning_rate": 1.3520838665324703e-05,
+      "loss": 0.2195,
+      "step": 104
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.544744491577148,
+      "learning_rate": 1.3007172168743854e-05,
+      "loss": 0.6881,
+      "step": 105
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 3.1280434131622314,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.7843,
+      "step": 106
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 3.5932955741882324,
+      "learning_rate": 1.1999596801769616e-05,
+      "loss": 0.405,
+      "step": 107
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8064641952514648,
+      "learning_rate": 1.1506233551212186e-05,
+      "loss": 0.0927,
+      "step": 108
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 1.5594532489776611,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.2154,
+      "step": 109
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.6679570078849792,
+      "learning_rate": 1.0541691595800337e-05,
+      "loss": 0.0839,
+      "step": 110
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.8102202415466309,
+      "learning_rate": 1.0071035207430352e-05,
+      "loss": 0.5539,
+      "step": 111
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.7791885137557983,
+      "learning_rate": 9.608463116858542e-06,
+      "loss": 0.2957,
+      "step": 112
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 2.7545344829559326,
+      "learning_rate": 9.154225815032242e-06,
+      "loss": 0.8108,
+      "step": 113
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.1660912036895752,
+      "learning_rate": 8.708569279463622e-06,
+      "loss": 0.0814,
+      "step": 114
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.9156790971755981,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.1564,
+      "step": 115
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 4.86236572265625,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.6666,
+      "step": 116
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.032678127288818,
+      "learning_rate": 7.4254735643584564e-06,
+      "loss": 0.4821,
+      "step": 117
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 2.2866246700286865,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.2771,
+      "step": 118
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 2.304269790649414,
+      "learning_rate": 6.617274798504286e-06,
+      "loss": 0.302,
+      "step": 119
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.9873311519622803,
+      "learning_rate": 6.22799917546252e-06,
+      "loss": 0.3067,
+      "step": 120
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 3.1299631595611572,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.6448,
+      "step": 121
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 1.7106144428253174,
+      "learning_rate": 5.48014933308352e-06,
+      "loss": 0.3074,
+      "step": 122
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.6227457523345947,
+      "learning_rate": 5.121980087628803e-06,
+      "loss": 0.1963,
+      "step": 123
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 4.482200622558594,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.7424,
+      "step": 124
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.32167911529541,
+      "learning_rate": 4.438122617983443e-06,
+      "loss": 0.5608,
+      "step": 125
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7932979464530945,
+      "learning_rate": 4.112804714676594e-06,
+      "loss": 0.0947,
+      "step": 126
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 0.28471994400024414,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.0437,
+      "step": 127
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 2.5803308486938477,
+      "learning_rate": 3.4962713026158694e-06,
+      "loss": 0.2781,
+      "step": 128
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.4017975330352783,
+      "learning_rate": 3.205389657580943e-06,
+      "loss": 0.5838,
+      "step": 129
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 3.2663633823394775,
+      "learning_rate": 2.9263101785268254e-06,
+      "loss": 0.473,
+      "step": 130
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 2.067620277404785,
+      "learning_rate": 2.659183991914696e-06,
+      "loss": 0.2994,
+      "step": 131
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.4989666938781738,
+      "learning_rate": 2.4041557512869878e-06,
+      "loss": 0.1795,
+      "step": 132
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 1.2955349683761597,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 0.193,
+      "step": 133
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 0.9127891659736633,
+      "learning_rate": 1.9309388911139426e-06,
+      "loss": 0.1546,
+      "step": 134
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.5144217014312744,
+      "learning_rate": 1.713006526846439e-06,
+      "loss": 0.2405,
+      "step": 135
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 3.5872600078582764,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.8543,
+      "step": 136
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 1.16169011592865,
+      "learning_rate": 1.31508393714177e-06,
+      "loss": 0.1759,
+      "step": 137
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.221109390258789,
+      "learning_rate": 1.1353091938067023e-06,
+      "loss": 0.1709,
+      "step": 138
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 1.7916854619979858,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 0.4347,
+      "step": 139
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 2.9777231216430664,
+      "learning_rate": 8.146195134284052e-07,
+      "loss": 0.3878,
+      "step": 140
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.271992206573486,
+      "learning_rate": 6.738782355044049e-07,
+      "loss": 0.3858,
+      "step": 141
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 1.1091471910476685,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.1942,
+      "step": 142
+    },
+    {
+      "epoch": 0.9533333333333334,
+      "grad_norm": 3.5003552436828613,
+      "learning_rate": 4.319838323396691e-07,
+      "loss": 0.4267,
+      "step": 143
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.55532169342041,
+      "learning_rate": 3.309616971855195e-07,
+      "loss": 0.3795,
+      "step": 144
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 2.3853328227996826,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.1976,
+      "step": 145
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 1.388493537902832,
+      "learning_rate": 1.6904105645142444e-07,
+      "loss": 0.1673,
+      "step": 146
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.8709473609924316,
+      "learning_rate": 1.0823023375489127e-07,
+      "loss": 0.3265,
+      "step": 147
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.2488735914230347,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 0.1556,
+      "step": 148
+    },
+    {
+      "epoch": 0.9933333333333333,
+      "grad_norm": 2.21366810798645,
+      "learning_rate": 2.7072216536885853e-08,
+      "loss": 0.7468,
+      "step": 149
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.950915813446045,
+      "learning_rate": 6.768970513457151e-09,
+      "loss": 0.4149,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 49,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0335481997190758e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/exp2_signalc_20251215/checkpoint-150/training_args.bin b/exp2_signalc_20251215/checkpoint-150/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..591bbc618a96850d2fc0f24befec3b8cdb986d33
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-150/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50702002f1fdf6d5e91c92ea8225d6a002d69ced0f5b2ce1f30eb32ce7dad475
+size 5841
diff --git a/exp2_signalc_20251215/checkpoint-49/README.md b/exp2_signalc_20251215/checkpoint-49/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-49/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/exp2_signalc_20251215/checkpoint-49/adapter_config.json b/exp2_signalc_20251215/checkpoint-49/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4d747200220490dff0f82aa49e63f702a859ccc
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-49/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/exp2_signalc_20251215/checkpoint-49/adapter_model.safetensors b/exp2_signalc_20251215/checkpoint-49/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..14ed0e04686280ba0fdb16d184f2ef1c70b44cf1
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-49/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85dde52ed3e966eb9b45ba1443e51a20bca9181425fdee22b56349bf12526429
+size 201378736
diff --git a/exp2_signalc_20251215/checkpoint-49/optimizer.pt b/exp2_signalc_20251215/checkpoint-49/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d22fe7dd20466634ecea504942ac24a0d0acc96d
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-49/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996ab8887dece8606a23346cee07263de6d5896bff9cac3880254b48f9c44eb6
+size 402982627
diff --git a/exp2_signalc_20251215/checkpoint-49/rng_state.pth b/exp2_signalc_20251215/checkpoint-49/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..807f44bba3301035e4b6efdb53a05c44d1d0b12a
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-49/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207e0116b01753d9990f17727a121db67c5ed48acd073905c6656f847aa88f26
+size 14645
diff --git a/exp2_signalc_20251215/checkpoint-49/scheduler.pt b/exp2_signalc_20251215/checkpoint-49/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e65b75fc4b2f2e3587883a6b70aab9794f70a87e
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-49/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd804ec5aea3d063766af287574720b1bb6665dd62c67e945105e50ae8eca9cc
+size 1465
diff --git a/exp2_signalc_20251215/checkpoint-49/trainer_state.json b/exp2_signalc_20251215/checkpoint-49/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..69258c3659d2dbd1095cd5c6b93863431a934db9
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-49/trainer_state.json
@@ -0,0 +1,377 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32666666666666666,
+  "eval_steps": 100,
+  "global_step": 49,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.007404327392578,
+      "learning_rate": 0.0,
+      "loss": 0.6595,
+      "step": 1
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.8502237796783447,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.1139,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2331303358078003,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.578,
+      "step": 3
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.2300695180892944,
+      "learning_rate": 1e-05,
+      "loss": 0.776,
+      "step": 4
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 3.3759779930114746,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7998,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.43403697013855,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.4564,
+      "step": 6
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 3.449822187423706,
+      "learning_rate": 2e-05,
+      "loss": 0.899,
+      "step": 7
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.4381998777389526,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.2811,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.234094500541687,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1841,
+      "step": 9
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.9779098033905029,
+      "learning_rate": 3e-05,
+      "loss": 0.2704,
+      "step": 10
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 1.1498095989227295,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.2534,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.928687334060669,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.5162,
+      "step": 12
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.8929930925369263,
+      "learning_rate": 4e-05,
+      "loss": 0.9282,
+      "step": 13
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 3.466400146484375,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.8342,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.0776634216308594,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7976,
+      "step": 15
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.7737135887145996,
+      "learning_rate": 5e-05,
+      "loss": 1.1665,
+      "step": 16
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 1.192466139793396,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.5163,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.5976535081863403,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.5035,
+      "step": 18
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 1.513372540473938,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.6089,
+      "step": 19
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.6169334650039673,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.6053,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.9578418731689453,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.8322,
+      "step": 21
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 2.1667706966400146,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.8027,
+      "step": 22
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 1.4784480333328247,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.4951,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.7624332904815674,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.6269,
+      "step": 24
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.6521016359329224,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3331,
+      "step": 25
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 1.1457144021987915,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.284,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.4980254173278809,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.6191,
+      "step": 27
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.3955901861190796,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.662,
+      "step": 28
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 1.2383167743682861,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.79,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2159212827682495,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.4194,
+      "step": 30
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 2.2957308292388916,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.5185,
+      "step": 31
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.6989065408706665,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.2625,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.02852463722229,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.6494,
+      "step": 33
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 1.653140902519226,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.5486,
+      "step": 34
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 1.7378313541412354,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 0.6112,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.8570767641067505,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.8117,
+      "step": 36
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.6243714094161987,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.284,
+      "step": 37
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 1.335660457611084,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.5556,
+      "step": 38
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.071352958679199,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.6837,
+      "step": 39
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.6223986148834229,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.6445,
+      "step": 40
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.174696445465088,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.129868507385254,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.4056,
+      "step": 42
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 1.917558193206787,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 1.23,
+      "step": 43
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 1.72930908203125,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.6128,
+      "step": 44
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7508667707443237,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.8213,
+      "step": 45
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.9080920815467834,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.2085,
+      "step": 46
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 1.75723135471344,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.5145,
+      "step": 47
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.450878620147705,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.6667,
+      "step": 48
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.8492142558097839,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.2838,
+      "step": 49
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 49,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.3818939423195136e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/exp2_signalc_20251215/checkpoint-49/training_args.bin b/exp2_signalc_20251215/checkpoint-49/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..591bbc618a96850d2fc0f24befec3b8cdb986d33
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-49/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50702002f1fdf6d5e91c92ea8225d6a002d69ced0f5b2ce1f30eb32ce7dad475
+size 5841
diff --git a/exp2_signalc_20251215/checkpoint-98/README.md b/exp2_signalc_20251215/checkpoint-98/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-98/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/exp2_signalc_20251215/checkpoint-98/adapter_config.json b/exp2_signalc_20251215/checkpoint-98/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4d747200220490dff0f82aa49e63f702a859ccc
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-98/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/exp2_signalc_20251215/checkpoint-98/adapter_model.safetensors b/exp2_signalc_20251215/checkpoint-98/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5fe4d04f04c7a3fbf31d5ed3a24180d1a91306e2
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-98/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ef1e7552a970c536dd30ff501bbafeba8f0dd42d17ee39727e89edbbc83bb1
+size 201378736
diff --git a/exp2_signalc_20251215/checkpoint-98/optimizer.pt b/exp2_signalc_20251215/checkpoint-98/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fdb1d8ac24f0ec05e996cc028dd11aa133c8aee4
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-98/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57649dff299d9d1db33f1c6d06000e0d52c066dd581ab61aecc072a7656bdf2c
+size 402982627
diff --git a/exp2_signalc_20251215/checkpoint-98/rng_state.pth b/exp2_signalc_20251215/checkpoint-98/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..be650a4d2795b25747861c0de85f814b80c6afcd
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-98/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cec4d872024bcdf7a65d27f3802b41fba250b5d9e8ca5c3ed586a0a74d5983
+size 14645
diff --git a/exp2_signalc_20251215/checkpoint-98/scheduler.pt b/exp2_signalc_20251215/checkpoint-98/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c0064a1b0ccc5f256504b07cf75d7b6d98eabfa1
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-98/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54ce98de4c1db5c4e0affce15c6cbebaf4fc220706243b711ba70f85829eaf2
+size 1465
diff --git a/exp2_signalc_20251215/checkpoint-98/trainer_state.json b/exp2_signalc_20251215/checkpoint-98/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..045d92f6cb0ef155b0fb14f567325b1438e20c54
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-98/trainer_state.json
@@ -0,0 +1,720 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6533333333333333,
+  "eval_steps": 100,
+  "global_step": 98,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.007404327392578,
+      "learning_rate": 0.0,
+      "loss": 0.6595,
+      "step": 1
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.8502237796783447,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.1139,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2331303358078003,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.578,
+      "step": 3
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.2300695180892944,
+      "learning_rate": 1e-05,
+      "loss": 0.776,
+      "step": 4
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 3.3759779930114746,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7998,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.43403697013855,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.4564,
+      "step": 6
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 3.449822187423706,
+      "learning_rate": 2e-05,
+      "loss": 0.899,
+      "step": 7
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.4381998777389526,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.2811,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.234094500541687,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1841,
+      "step": 9
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.9779098033905029,
+      "learning_rate": 3e-05,
+      "loss": 0.2704,
+      "step": 10
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 1.1498095989227295,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.2534,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.928687334060669,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.5162,
+      "step": 12
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.8929930925369263,
+      "learning_rate": 4e-05,
+      "loss": 0.9282,
+      "step": 13
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 3.466400146484375,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.8342,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.0776634216308594,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7976,
+      "step": 15
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.7737135887145996,
+      "learning_rate": 5e-05,
+      "loss": 1.1665,
+      "step": 16
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 1.192466139793396,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.5163,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.5976535081863403,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.5035,
+      "step": 18
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 1.513372540473938,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.6089,
+      "step": 19
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.6169334650039673,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.6053,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.9578418731689453,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.8322,
+      "step": 21
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 2.1667706966400146,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.8027,
+      "step": 22
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 1.4784480333328247,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.4951,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.7624332904815674,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.6269,
+      "step": 24
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.6521016359329224,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3331,
+      "step": 25
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 1.1457144021987915,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.284,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.4980254173278809,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.6191,
+      "step": 27
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.3955901861190796,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.662,
+      "step": 28
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 1.2383167743682861,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.79,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2159212827682495,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.4194,
+      "step": 30
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 2.2957308292388916,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.5185,
+      "step": 31
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.6989065408706665,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.2625,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.02852463722229,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.6494,
+      "step": 33
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 1.653140902519226,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.5486,
+      "step": 34
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 1.7378313541412354,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 0.6112,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.8570767641067505,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.8117,
+      "step": 36
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.6243714094161987,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.284,
+      "step": 37
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 1.335660457611084,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.5556,
+      "step": 38
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.071352958679199,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.6837,
+      "step": 39
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.6223986148834229,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.6445,
+      "step": 40
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.174696445465088,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.129868507385254,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.4056,
+      "step": 42
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 1.917558193206787,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 1.23,
+      "step": 43
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 1.72930908203125,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.6128,
+      "step": 44
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7508667707443237,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.8213,
+      "step": 45
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.9080920815467834,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.2085,
+      "step": 46
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 1.75723135471344,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.5145,
+      "step": 47
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.450878620147705,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.6667,
+      "step": 48
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.8492142558097839,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.2838,
+      "step": 49
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.2550184726715088,
+      "learning_rate": 4.257452643564155e-05,
+      "loss": 0.3858,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.2642593383789062,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.6531,
+      "step": 51
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 3.926060199737549,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.4836,
+      "step": 52
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 1.8190771341323853,
+      "learning_rate": 4.129143072053638e-05,
+      "loss": 0.3158,
+      "step": 53
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.4268187284469604,
+      "learning_rate": 4.0845774184967754e-05,
+      "loss": 0.5298,
+      "step": 54
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 1.9656697511672974,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.4887,
+      "step": 55
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.1335246562957764,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.1837,
+      "step": 56
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.525275707244873,
+      "learning_rate": 3.945830840419966e-05,
+      "loss": 0.8998,
+      "step": 57
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 2.12524676322937,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.3827,
+      "step": 58
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 1.9228296279907227,
+      "learning_rate": 3.8493766448787825e-05,
+      "loss": 0.5591,
+      "step": 59
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3674192428588867,
+      "learning_rate": 3.8000403198230387e-05,
+      "loss": 0.4872,
+      "step": 60
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 1.965265154838562,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.5459,
+      "step": 61
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 2.329216241836548,
+      "learning_rate": 3.699282783125616e-05,
+      "loss": 0.7548,
+      "step": 62
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.118192434310913,
+      "learning_rate": 3.6479161334675296e-05,
+      "loss": 0.6821,
+      "step": 63
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.9981805086135864,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3079,
+      "step": 64
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 1.0037565231323242,
+      "learning_rate": 3.543346136204545e-05,
+      "loss": 0.3274,
+      "step": 65
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8539446592330933,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3298,
+      "step": 66
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 1.1413832902908325,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.3062,
+      "step": 67
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 2.7091305255889893,
+      "learning_rate": 3.382326411784672e-05,
+      "loss": 0.4897,
+      "step": 68
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.9014657735824585,
+      "learning_rate": 3.327658544712395e-05,
+      "loss": 0.422,
+      "step": 69
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 1.7714844942092896,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.2594,
+      "step": 70
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 0.7899397611618042,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.1847,
+      "step": 71
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.2437670230865479,
+      "learning_rate": 3.161085405093006e-05,
+      "loss": 0.2063,
+      "step": 72
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 1.4275377988815308,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.7009,
+      "step": 73
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 1.6646203994750977,
+      "learning_rate": 3.048196560469758e-05,
+      "loss": 0.2215,
+      "step": 74
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.504795551300049,
+      "learning_rate": 2.9912915238320754e-05,
+      "loss": 0.5467,
+      "step": 75
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.1971930265426636,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1757,
+      "step": 76
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 1.2171498537063599,
+      "learning_rate": 2.876714280623708e-05,
+      "loss": 0.1898,
+      "step": 77
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5181541442871094,
+      "learning_rate": 2.8191041196514873e-05,
+      "loss": 0.2299,
+      "step": 78
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 1.1093655824661255,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.1639,
+      "step": 79
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 4.772696495056152,
+      "learning_rate": 2.7033966866696457e-05,
+      "loss": 0.9071,
+      "step": 80
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.373753547668457,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 1.315,
+      "step": 81
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.4806381165981293,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.0859,
+      "step": 82
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 2.003674030303955,
+      "learning_rate": 2.5290881645034932e-05,
+      "loss": 0.5889,
+      "step": 83
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.2717702388763428,
+      "learning_rate": 2.470911835496508e-05,
+      "loss": 0.2551,
+      "step": 84
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 3.508592367172241,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.7869,
+      "step": 85
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.1418286561965942,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.1538,
+      "step": 86
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9381025433540344,
+      "learning_rate": 2.2966033133303545e-05,
+      "loss": 0.0973,
+      "step": 87
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 2.441453218460083,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.86,
+      "step": 88
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.7263301610946655,
+      "learning_rate": 2.1808958803485136e-05,
+      "loss": 0.1041,
+      "step": 89
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.5983655452728271,
+      "learning_rate": 2.1232857193762924e-05,
+      "loss": 0.4031,
+      "step": 90
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 2.9620091915130615,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.7484,
+      "step": 91
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.8278090953826904,
+      "learning_rate": 2.0087084761679245e-05,
+      "loss": 0.4001,
+      "step": 92
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.282475233078003,
+      "learning_rate": 1.9518034395302414e-05,
+      "loss": 0.4047,
+      "step": 93
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 1.196440577507019,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.1718,
+      "step": 94
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 3.1636035442352295,
+      "learning_rate": 1.838914594906995e-05,
+      "loss": 0.773,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.34068605303764343,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.0501,
+      "step": 96
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 2.373602867126465,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.6528,
+      "step": 97
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 3.809894561767578,
+      "learning_rate": 1.672341455287605e-05,
+      "loss": 0.4916,
+      "step": 98
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 49,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.763787884639027e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/exp2_signalc_20251215/checkpoint-98/training_args.bin b/exp2_signalc_20251215/checkpoint-98/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..591bbc618a96850d2fc0f24befec3b8cdb986d33
--- /dev/null
+++ b/exp2_signalc_20251215/checkpoint-98/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50702002f1fdf6d5e91c92ea8225d6a002d69ced0f5b2ce1f30eb32ce7dad475
+size 5841
diff --git a/exp2_signalc_20251215/final_model/README.md b/exp2_signalc_20251215/final_model/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..d283785603342a12561751304db4c120bbd293fc
--- /dev/null
+++ b/exp2_signalc_20251215/final_model/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-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 0.17.1
\ No newline at end of file
diff --git a/exp2_signalc_20251215/final_model/adapter_config.json b/exp2_signalc_20251215/final_model/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4d747200220490dff0f82aa49e63f702a859ccc
--- /dev/null
+++ b/exp2_signalc_20251215/final_model/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/exp2_signalc_20251215/final_model/adapter_model.safetensors b/exp2_signalc_20251215/final_model/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..33672935cb7c3d885ecc8c264c0061e5437e8b82
--- /dev/null
+++ b/exp2_signalc_20251215/final_model/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b952f9f010e213946ed7983bb5affbcb494295dc69e15839f0f632edc00432e
+size 201378736
diff --git a/exp2_signalc_20251215/final_model/training_args.bin b/exp2_signalc_20251215/final_model/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..591bbc618a96850d2fc0f24befec3b8cdb986d33
--- /dev/null
+++ b/exp2_signalc_20251215/final_model/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50702002f1fdf6d5e91c92ea8225d6a002d69ced0f5b2ce1f30eb32ce7dad475
+size 5841