diff --git a/.gitattributes b/.gitattributes
index 3295542b3bb26df8b65a15d85a51c70e8e63c853..d37b330f0e831e18ccd43f7390830a49a4d65749 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -56,3 +56,7 @@ punctuation/encoder_model/checkpoint-150/tokenizer.json filter=lfs diff=lfs merg
 punctuation/encoder_model/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 punctuation/encoder_model/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 punctuation/encoder_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+punctuation/decoder_model/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+punctuation/decoder_model/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+punctuation/decoder_model/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+punctuation/decoder_model/checkpoint-321/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/punctuation/decoder_model/adapter_config.json b/punctuation/decoder_model/adapter_config.json
index c0c6ef1654af65a85c3fdb97621e978d19cca00a..9fb0f488e682f0b6d9eecf3c5a66b6c60dd4583c 100644
--- a/punctuation/decoder_model/adapter_config.json
+++ b/punctuation/decoder_model/adapter_config.json
@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "gate_proj",
+    "q_proj",
     "up_proj",
-    "down_proj",
-    "k_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "k_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
diff --git a/punctuation/decoder_model/adapter_model.safetensors b/punctuation/decoder_model/adapter_model.safetensors
index 513dae3d6cc085f25d1b619bdc221cadeaedac6a..a3fb594cc7720749c02b2e4674816085250c5438 100644
--- a/punctuation/decoder_model/adapter_model.safetensors
+++ b/punctuation/decoder_model/adapter_model.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c78e38cd7ceb629958882592c6c570f3e396c0645723edac1afc6207286c8d
+oid sha256:81cdb0bad37e5e85cb192fc1a4176c897a0a3c26a9cca907ad312828798ced8e
 size 295488936
diff --git a/punctuation/decoder_model/checkpoint-100/adapter_config.json b/punctuation/decoder_model/checkpoint-100/adapter_config.json
index c0c6ef1654af65a85c3fdb97621e978d19cca00a..9fb0f488e682f0b6d9eecf3c5a66b6c60dd4583c 100644
--- a/punctuation/decoder_model/checkpoint-100/adapter_config.json
+++ b/punctuation/decoder_model/checkpoint-100/adapter_config.json
@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "gate_proj",
+    "q_proj",
     "up_proj",
-    "down_proj",
-    "k_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "k_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
diff --git a/punctuation/decoder_model/checkpoint-100/adapter_model.safetensors b/punctuation/decoder_model/checkpoint-100/adapter_model.safetensors
index 60f96fe3f3827bcfa4063c6967f0322f52231baf..ed481556286fbfb62f2e3689f4869812f9907cdf 100644
--- a/punctuation/decoder_model/checkpoint-100/adapter_model.safetensors
+++ b/punctuation/decoder_model/checkpoint-100/adapter_model.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f82e5d2dc6d48e86b9fe583baffef63355dad58b29c06b43549ade50ae9eb1
+oid sha256:298210befb01d8b6f59420e8e84211687005016b9f5d0bfc544d30c8f0368274
 size 295488936
diff --git a/punctuation/decoder_model/checkpoint-100/optimizer.pt b/punctuation/decoder_model/checkpoint-100/optimizer.pt
index 29d08dc3ab767527e897db5496aaca7f6b20f7c4..7bf3fcdab2a7f0191e4dc26c13b0be1e5db2d466 100644
--- a/punctuation/decoder_model/checkpoint-100/optimizer.pt
+++ b/punctuation/decoder_model/checkpoint-100/optimizer.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ef545de555417a50d2bcd478f7ade1ba6ca8b4656847f4037d6b5efe8381a9
+oid sha256:f2fa89afbf63ca7ce05eb4846c8afb60aa2acd764417e38d99a4c55c8dd20401
 size 591203178
diff --git a/punctuation/decoder_model/checkpoint-100/rng_state.pth b/punctuation/decoder_model/checkpoint-100/rng_state.pth
index 27e3c06b937a706577aeb22ed9c95cfab6f9dbd9..87becf7c90180bc4eb0d818c11bee8eba8a1fde5 100644
--- a/punctuation/decoder_model/checkpoint-100/rng_state.pth
+++ b/punctuation/decoder_model/checkpoint-100/rng_state.pth
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:799ac5aa83a071040cf8d8df50a3c6593c748bb4938366bf1ab37bacd9f7785b
+oid sha256:d27e2831a52762b1846dbb627b14ca75543c940afac1961118b4e963052cb551
 size 14244
diff --git a/punctuation/decoder_model/checkpoint-100/scheduler.pt b/punctuation/decoder_model/checkpoint-100/scheduler.pt
index b627eb842e7c7d85d79caee992f3d0e40a9a78b1..2ac1515461c775c77b75af8701a497ea7a52c93f 100644
--- a/punctuation/decoder_model/checkpoint-100/scheduler.pt
+++ b/punctuation/decoder_model/checkpoint-100/scheduler.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9721d5ba1fb05d41f214a5bebb8206b88b746e805209d13e654bce65e0ffa08
+oid sha256:e2a28995c40f7b16c8546b48d4c90300b9e79ca9133267d49a18f59980326d8e
 size 1064
diff --git a/punctuation/decoder_model/checkpoint-100/trainer_state.json b/punctuation/decoder_model/checkpoint-100/trainer_state.json
index e5856f61f56ce454e173b29adbdaca92c92ae1a8..2a479a10dd1fc9d7733961404e3f43db544bdd01 100644
--- a/punctuation/decoder_model/checkpoint-100/trainer_state.json
+++ b/punctuation/decoder_model/checkpoint-100/trainer_state.json
@@ -1,7 +1,7 @@
 {
-  "best_global_step": 50,
-  "best_metric": 0.55,
-  "best_model_checkpoint": "./models/punctuation/decoder_model/checkpoint-50",
+  "best_global_step": 100,
+  "best_metric": 0.7,
+  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-100",
   "epoch": 0.9411764705882353,
   "eval_steps": 50,
   "global_step": 100,
@@ -11,97 +11,97 @@
   "log_history": [
     {
       "epoch": 0.09411764705882353,
-      "grad_norm": 0.24285665154457092,
-      "learning_rate": 0.0001,
-      "loss": 0.0437,
+      "grad_norm": 1.3681155443191528,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.7202,
       "step": 10
     },
     {
       "epoch": 0.18823529411764706,
-      "grad_norm": 0.1404133290052414,
-      "learning_rate": 0.0001,
-      "loss": 0.0063,
+      "grad_norm": 0.7711533308029175,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 0.3185,
       "step": 20
     },
     {
       "epoch": 0.2823529411764706,
-      "grad_norm": 0.10824572294950485,
-      "learning_rate": 0.0001,
-      "loss": 0.0033,
+      "grad_norm": 1.2256836891174316,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 0.1827,
       "step": 30
     },
     {
       "epoch": 0.3764705882352941,
-      "grad_norm": 0.057334210723638535,
-      "learning_rate": 0.0001,
-      "loss": 0.0018,
+      "grad_norm": 0.888201892375946,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 0.1346,
       "step": 40
     },
     {
       "epoch": 0.47058823529411764,
-      "grad_norm": 0.03022940270602703,
-      "learning_rate": 0.0001,
-      "loss": 0.0015,
+      "grad_norm": 0.853918731212616,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0721,
       "step": 50
     },
     {
       "epoch": 0.47058823529411764,
-      "eval_loss": 0.001103814342059195,
-      "eval_model_preparation_time": 0.0142,
-      "eval_runtime": 3.8403,
-      "eval_samples_per_second": 26.04,
-      "eval_steps_per_second": 13.02,
+      "eval_loss": 0.04328128695487976,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2686,
+      "eval_samples_per_second": 44.081,
+      "eval_steps_per_second": 22.04,
       "step": 50
     },
     {
       "epoch": 0.5647058823529412,
-      "grad_norm": 0.015224365517497063,
-      "learning_rate": 0.0001,
-      "loss": 0.0014,
+      "grad_norm": 0.48631730675697327,
+      "learning_rate": 9.800249271929645e-05,
+      "loss": 0.042,
       "step": 60
     },
     {
       "epoch": 0.6588235294117647,
-      "grad_norm": 0.0396883524954319,
-      "learning_rate": 0.0001,
-      "loss": 0.0009,
+      "grad_norm": 0.5516029596328735,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0218,
       "step": 70
     },
     {
       "epoch": 0.7529411764705882,
-      "grad_norm": 0.015018803998827934,
-      "learning_rate": 0.0001,
-      "loss": 0.0011,
+      "grad_norm": 0.28095027804374695,
+      "learning_rate": 9.38363377853754e-05,
+      "loss": 0.0127,
       "step": 80
     },
     {
       "epoch": 0.8470588235294118,
-      "grad_norm": 0.06080203875899315,
-      "learning_rate": 0.0001,
-      "loss": 0.0015,
+      "grad_norm": 0.8756083846092224,
+      "learning_rate": 9.09576022144496e-05,
+      "loss": 0.0124,
       "step": 90
     },
     {
       "epoch": 0.9411764705882353,
-      "grad_norm": 0.012812742032110691,
-      "learning_rate": 0.0001,
-      "loss": 0.001,
+      "grad_norm": 0.5514245629310608,
+      "learning_rate": 8.759199037394887e-05,
+      "loss": 0.0119,
       "step": 100
     },
     {
       "epoch": 0.9411764705882353,
-      "eval_loss": 0.000311562413116917,
-      "eval_model_preparation_time": 0.0142,
-      "eval_runtime": 3.7694,
-      "eval_samples_per_second": 26.529,
-      "eval_steps_per_second": 13.265,
+      "eval_loss": 0.004549662582576275,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2779,
+      "eval_samples_per_second": 43.9,
+      "eval_steps_per_second": 21.95,
       "step": 100
     }
   ],
   "logging_steps": 10,
-  "max_steps": 214,
+  "max_steps": 321,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -115,7 +115,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2888281155313664e+16,
+  "total_flos": 6705100455260160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
diff --git a/punctuation/decoder_model/checkpoint-100/training_args.bin b/punctuation/decoder_model/checkpoint-100/training_args.bin
index 5a718de59058adb39dad8aaa7aeb1187de60c7c9..c85faf08b352f43537dd987dbb01ce104d75b094 100644
--- a/punctuation/decoder_model/checkpoint-100/training_args.bin
+++ b/punctuation/decoder_model/checkpoint-100/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706350fbaba956c6f58e868aa99bcc1a0de8a5e4bb317917a8c147ba6dd9b6e2
+oid sha256:f97ed1b6a6e44be81bbaf2ae8e900f738306c25642888690e0d1cb84bc71cf30
 size 5496
diff --git a/punctuation/decoder_model/checkpoint-150/README.md b/punctuation/decoder_model/checkpoint-150/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..f8e2935b613e4ee6e23cfafe6221ecf1e366de75
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/README.md
@@ -0,0 +1,207 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- 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 0.18.1
\ No newline at end of file
diff --git a/punctuation/decoder_model/checkpoint-150/adapter_config.json b/punctuation/decoder_model/checkpoint-150/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fb0f488e682f0b6d9eecf3c5a66b6c60dd4583c
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_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/punctuation/decoder_model/checkpoint-150/adapter_model.safetensors b/punctuation/decoder_model/checkpoint-150/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a3fb594cc7720749c02b2e4674816085250c5438
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81cdb0bad37e5e85cb192fc1a4176c897a0a3c26a9cca907ad312828798ced8e
+size 295488936
diff --git a/punctuation/decoder_model/checkpoint-150/chat_template.jinja b/punctuation/decoder_model/checkpoint-150/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
\ No newline at end of file
diff --git a/punctuation/decoder_model/checkpoint-150/optimizer.pt b/punctuation/decoder_model/checkpoint-150/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7602b7a3780e38391c750de19c7b1709695379f2
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed3aea7c526c75ba1c09e48ec24cd209afa8e7f4c986ba8746fc3053429b874
+size 591203178
diff --git a/punctuation/decoder_model/checkpoint-150/rng_state.pth b/punctuation/decoder_model/checkpoint-150/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c02cdc4908682bc220e4773562a775d92719bac2
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8907346cb90a1f0e3127be57f06d030fe7658cd9c8f0410f7ddaaee5bd0eb791
+size 14244
diff --git a/punctuation/decoder_model/checkpoint-150/scheduler.pt b/punctuation/decoder_model/checkpoint-150/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3a646f9ca6ec2d73a24204617305072b61f9c74c
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495744ffdaef4bdd4214964b759bd82ab378d1b5e5a6808b2e6d04cb50c83540
+size 1064
diff --git a/punctuation/decoder_model/checkpoint-150/special_tokens_map.json b/punctuation/decoder_model/checkpoint-150/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/punctuation/decoder_model/checkpoint-150/tokenizer.json b/punctuation/decoder_model/checkpoint-150/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..2896b9a8a75c1a4eadce226067e0de7b9f9020d3
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f3503dade503303f354be26edaf4223708fa1ca2e84c4daf306b5d7c40ce23
+size 11423058
diff --git a/punctuation/decoder_model/checkpoint-150/tokenizer_config.json b/punctuation/decoder_model/checkpoint-150/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}
diff --git a/punctuation/decoder_model/checkpoint-150/trainer_state.json b/punctuation/decoder_model/checkpoint-150/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..231fc3dbcd4a158b19b6fec48d6d2ba5e01b05aa
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/trainer_state.json
@@ -0,0 +1,166 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.9,
+  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-150",
+  "epoch": 1.4047058823529412,
+  "eval_steps": 50,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 1.3681155443191528,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.7202,
+      "step": 10
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 0.7711533308029175,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 0.3185,
+      "step": 20
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 1.2256836891174316,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 0.1827,
+      "step": 30
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 0.888201892375946,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 0.1346,
+      "step": 40
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.853918731212616,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0721,
+      "step": 50
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "eval_loss": 0.04328128695487976,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2686,
+      "eval_samples_per_second": 44.081,
+      "eval_steps_per_second": 22.04,
+      "step": 50
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 0.48631730675697327,
+      "learning_rate": 9.800249271929645e-05,
+      "loss": 0.042,
+      "step": 60
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 0.5516029596328735,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0218,
+      "step": 70
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 0.28095027804374695,
+      "learning_rate": 9.38363377853754e-05,
+      "loss": 0.0127,
+      "step": 80
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 0.8756083846092224,
+      "learning_rate": 9.09576022144496e-05,
+      "loss": 0.0124,
+      "step": 90
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.5514245629310608,
+      "learning_rate": 8.759199037394887e-05,
+      "loss": 0.0119,
+      "step": 100
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "eval_loss": 0.004549662582576275,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2779,
+      "eval_samples_per_second": 43.9,
+      "eval_steps_per_second": 21.95,
+      "step": 100
+    },
+    {
+      "epoch": 1.0282352941176471,
+      "grad_norm": 0.48209479451179504,
+      "learning_rate": 8.377951038078302e-05,
+      "loss": 0.0074,
+      "step": 110
+    },
+    {
+      "epoch": 1.1223529411764706,
+      "grad_norm": 0.22237619757652283,
+      "learning_rate": 7.956548241817912e-05,
+      "loss": 0.0033,
+      "step": 120
+    },
+    {
+      "epoch": 1.2164705882352942,
+      "grad_norm": 0.22323866188526154,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0019,
+      "step": 130
+    },
+    {
+      "epoch": 1.3105882352941176,
+      "grad_norm": 0.044407621026039124,
+      "learning_rate": 7.013733449293687e-05,
+      "loss": 0.0022,
+      "step": 140
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "grad_norm": 0.1491803228855133,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0026,
+      "step": 150
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "eval_loss": 0.00037357292603701353,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.317,
+      "eval_samples_per_second": 43.159,
+      "eval_steps_per_second": 21.579,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 321,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0049284593389568e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/punctuation/decoder_model/checkpoint-150/training_args.bin b/punctuation/decoder_model/checkpoint-150/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c85faf08b352f43537dd987dbb01ce104d75b094
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-150/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97ed1b6a6e44be81bbaf2ae8e900f738306c25642888690e0d1cb84bc71cf30
+size 5496
diff --git a/punctuation/decoder_model/checkpoint-200/adapter_config.json b/punctuation/decoder_model/checkpoint-200/adapter_config.json
index c0c6ef1654af65a85c3fdb97621e978d19cca00a..9fb0f488e682f0b6d9eecf3c5a66b6c60dd4583c 100644
--- a/punctuation/decoder_model/checkpoint-200/adapter_config.json
+++ b/punctuation/decoder_model/checkpoint-200/adapter_config.json
@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "gate_proj",
+    "q_proj",
     "up_proj",
-    "down_proj",
-    "k_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "k_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
diff --git a/punctuation/decoder_model/checkpoint-200/adapter_model.safetensors b/punctuation/decoder_model/checkpoint-200/adapter_model.safetensors
index 7558dec75c2ea7b3a84bc53d58c3b4649a337cbf..31f1828bde1e5a272f4ebbf8b3fc74f5fcaf9e76 100644
--- a/punctuation/decoder_model/checkpoint-200/adapter_model.safetensors
+++ b/punctuation/decoder_model/checkpoint-200/adapter_model.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ad62ed9a3cb6a1568982c1cb85e7ef409c9ff6d99e3e7388f821f32811e0ba
+oid sha256:e8676c364608701f56488b256b866234fabb85569e04e3d78c3207dad1334c61
 size 295488936
diff --git a/punctuation/decoder_model/checkpoint-200/optimizer.pt b/punctuation/decoder_model/checkpoint-200/optimizer.pt
index 7ffb6702f1dd7d736404a7f8275f279021f49995..b9c756f84233ecc94cfcef01094e0f6519929c69 100644
--- a/punctuation/decoder_model/checkpoint-200/optimizer.pt
+++ b/punctuation/decoder_model/checkpoint-200/optimizer.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a16d066089586a4f94ec565b9071a3f3d7223774d11197f70fca6b9739e5d2c
+oid sha256:7bbd559cf67eae72b21b74ccbbe341497435c2fe9eabfee5f0b2e6f6149be8ea
 size 591203178
diff --git a/punctuation/decoder_model/checkpoint-200/rng_state.pth b/punctuation/decoder_model/checkpoint-200/rng_state.pth
index 3ccf932f649e8c7cb85182d44092db801bc9bd0b..6779d628612a048953217aa94a31fd87612292c5 100644
--- a/punctuation/decoder_model/checkpoint-200/rng_state.pth
+++ b/punctuation/decoder_model/checkpoint-200/rng_state.pth
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ca93b3776c96aabf7e509d1e27d6c212b1f36d962885a4dd0e236d93e918189
+oid sha256:c7a3d8bb510226121cafc0e4f216b3dd6171d7e318a33b2ca847f9e6d4298573
 size 14244
diff --git a/punctuation/decoder_model/checkpoint-200/scheduler.pt b/punctuation/decoder_model/checkpoint-200/scheduler.pt
index cd85ebfd5283eff16808c1da8eb6f40ac2533b35..978cb68d574b44eb2fa61bd71c5403a967e27132 100644
--- a/punctuation/decoder_model/checkpoint-200/scheduler.pt
+++ b/punctuation/decoder_model/checkpoint-200/scheduler.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da963d3b7106f3b4c395d03ef6897e64220165c23480563310345c76ab7b120d
+oid sha256:13b2487b3ddfdf4c8aff90c3f09e6a7d7ae5ad8752ed2541c1e98d78c4db087d
 size 1064
diff --git a/punctuation/decoder_model/checkpoint-200/trainer_state.json b/punctuation/decoder_model/checkpoint-200/trainer_state.json
index 034b3073883f2ed0770eff1f062e98d87aa936b6..408c4ba0ac9b97b7ea00e25e25adf419d81cc305 100644
--- a/punctuation/decoder_model/checkpoint-200/trainer_state.json
+++ b/punctuation/decoder_model/checkpoint-200/trainer_state.json
@@ -1,7 +1,7 @@
 {
-  "best_global_step": 50,
-  "best_metric": 0.55,
-  "best_model_checkpoint": "./models/punctuation/decoder_model/checkpoint-50",
+  "best_global_step": 150,
+  "best_metric": 0.9,
+  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-150",
   "epoch": 1.8752941176470588,
   "eval_steps": 50,
   "global_step": 200,
@@ -11,185 +11,185 @@
   "log_history": [
     {
       "epoch": 0.09411764705882353,
-      "grad_norm": 0.24285665154457092,
-      "learning_rate": 0.0001,
-      "loss": 0.0437,
+      "grad_norm": 1.3681155443191528,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.7202,
       "step": 10
     },
     {
       "epoch": 0.18823529411764706,
-      "grad_norm": 0.1404133290052414,
-      "learning_rate": 0.0001,
-      "loss": 0.0063,
+      "grad_norm": 0.7711533308029175,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 0.3185,
       "step": 20
     },
     {
       "epoch": 0.2823529411764706,
-      "grad_norm": 0.10824572294950485,
-      "learning_rate": 0.0001,
-      "loss": 0.0033,
+      "grad_norm": 1.2256836891174316,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 0.1827,
       "step": 30
     },
     {
       "epoch": 0.3764705882352941,
-      "grad_norm": 0.057334210723638535,
-      "learning_rate": 0.0001,
-      "loss": 0.0018,
+      "grad_norm": 0.888201892375946,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 0.1346,
       "step": 40
     },
     {
       "epoch": 0.47058823529411764,
-      "grad_norm": 0.03022940270602703,
-      "learning_rate": 0.0001,
-      "loss": 0.0015,
+      "grad_norm": 0.853918731212616,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0721,
       "step": 50
     },
     {
       "epoch": 0.47058823529411764,
-      "eval_loss": 0.001103814342059195,
-      "eval_model_preparation_time": 0.0142,
-      "eval_runtime": 3.8403,
-      "eval_samples_per_second": 26.04,
-      "eval_steps_per_second": 13.02,
+      "eval_loss": 0.04328128695487976,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2686,
+      "eval_samples_per_second": 44.081,
+      "eval_steps_per_second": 22.04,
       "step": 50
     },
     {
       "epoch": 0.5647058823529412,
-      "grad_norm": 0.015224365517497063,
-      "learning_rate": 0.0001,
-      "loss": 0.0014,
+      "grad_norm": 0.48631730675697327,
+      "learning_rate": 9.800249271929645e-05,
+      "loss": 0.042,
       "step": 60
     },
     {
       "epoch": 0.6588235294117647,
-      "grad_norm": 0.0396883524954319,
-      "learning_rate": 0.0001,
-      "loss": 0.0009,
+      "grad_norm": 0.5516029596328735,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0218,
       "step": 70
     },
     {
       "epoch": 0.7529411764705882,
-      "grad_norm": 0.015018803998827934,
-      "learning_rate": 0.0001,
-      "loss": 0.0011,
+      "grad_norm": 0.28095027804374695,
+      "learning_rate": 9.38363377853754e-05,
+      "loss": 0.0127,
       "step": 80
     },
     {
       "epoch": 0.8470588235294118,
-      "grad_norm": 0.06080203875899315,
-      "learning_rate": 0.0001,
-      "loss": 0.0015,
+      "grad_norm": 0.8756083846092224,
+      "learning_rate": 9.09576022144496e-05,
+      "loss": 0.0124,
       "step": 90
     },
     {
       "epoch": 0.9411764705882353,
-      "grad_norm": 0.012812742032110691,
-      "learning_rate": 0.0001,
-      "loss": 0.001,
+      "grad_norm": 0.5514245629310608,
+      "learning_rate": 8.759199037394887e-05,
+      "loss": 0.0119,
       "step": 100
     },
     {
       "epoch": 0.9411764705882353,
-      "eval_loss": 0.000311562413116917,
-      "eval_model_preparation_time": 0.0142,
-      "eval_runtime": 3.7694,
-      "eval_samples_per_second": 26.529,
-      "eval_steps_per_second": 13.265,
+      "eval_loss": 0.004549662582576275,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2779,
+      "eval_samples_per_second": 43.9,
+      "eval_steps_per_second": 21.95,
       "step": 100
     },
     {
       "epoch": 1.0282352941176471,
-      "grad_norm": 0.0059220679104328156,
-      "learning_rate": 0.0001,
-      "loss": 0.0007,
+      "grad_norm": 0.48209479451179504,
+      "learning_rate": 8.377951038078302e-05,
+      "loss": 0.0074,
       "step": 110
     },
     {
       "epoch": 1.1223529411764706,
-      "grad_norm": 0.0013089082203805447,
-      "learning_rate": 0.0001,
-      "loss": 0.0003,
+      "grad_norm": 0.22237619757652283,
+      "learning_rate": 7.956548241817912e-05,
+      "loss": 0.0033,
       "step": 120
     },
     {
       "epoch": 1.2164705882352942,
-      "grad_norm": 0.024143697693943977,
-      "learning_rate": 0.0001,
-      "loss": 0.0003,
+      "grad_norm": 0.22323866188526154,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0019,
       "step": 130
     },
     {
       "epoch": 1.3105882352941176,
-      "grad_norm": 0.001856817165389657,
-      "learning_rate": 0.0001,
-      "loss": 0.0002,
+      "grad_norm": 0.044407621026039124,
+      "learning_rate": 7.013733449293687e-05,
+      "loss": 0.0022,
       "step": 140
     },
     {
       "epoch": 1.4047058823529412,
-      "grad_norm": 0.005285186693072319,
-      "learning_rate": 0.0001,
-      "loss": 0.0004,
+      "grad_norm": 0.1491803228855133,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0026,
       "step": 150
     },
     {
       "epoch": 1.4047058823529412,
-      "eval_loss": 0.0002466830483172089,
-      "eval_model_preparation_time": 0.0142,
-      "eval_runtime": 3.7976,
-      "eval_samples_per_second": 26.332,
-      "eval_steps_per_second": 13.166,
+      "eval_loss": 0.00037357292603701353,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.317,
+      "eval_samples_per_second": 43.159,
+      "eval_steps_per_second": 21.579,
       "step": 150
     },
     {
       "epoch": 1.4988235294117647,
-      "grad_norm": 0.004095815122127533,
-      "learning_rate": 0.0001,
-      "loss": 0.0002,
+      "grad_norm": 0.014182478189468384,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.0012,
       "step": 160
     },
     {
       "epoch": 1.592941176470588,
-      "grad_norm": 0.0021637140307575464,
-      "learning_rate": 0.0001,
-      "loss": 0.0002,
+      "grad_norm": 0.015145699493587017,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0003,
       "step": 170
     },
     {
       "epoch": 1.6870588235294117,
-      "grad_norm": 0.004411402158439159,
-      "learning_rate": 0.0001,
-      "loss": 0.0002,
+      "grad_norm": 0.011491155251860619,
+      "learning_rate": 4.890925574827195e-05,
+      "loss": 0.0039,
       "step": 180
     },
     {
       "epoch": 1.7811764705882354,
-      "grad_norm": 0.0017215535044670105,
-      "learning_rate": 0.0001,
-      "loss": 0.0002,
+      "grad_norm": 0.16684198379516602,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0021,
       "step": 190
     },
     {
       "epoch": 1.8752941176470588,
-      "grad_norm": 0.21980944275856018,
-      "learning_rate": 0.0001,
-      "loss": 0.001,
+      "grad_norm": 0.006741759832948446,
+      "learning_rate": 3.8115705383691355e-05,
+      "loss": 0.0009,
       "step": 200
     },
     {
       "epoch": 1.8752941176470588,
-      "eval_loss": 0.0019195562927052379,
-      "eval_model_preparation_time": 0.0142,
-      "eval_runtime": 3.8034,
-      "eval_samples_per_second": 26.292,
-      "eval_steps_per_second": 13.146,
+      "eval_loss": 0.0005264483625069261,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2881,
+      "eval_samples_per_second": 43.705,
+      "eval_steps_per_second": 21.852,
       "step": 200
     }
   ],
   "logging_steps": 10,
-  "max_steps": 214,
+  "max_steps": 321,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -203,7 +203,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5792052193275904e+16,
+  "total_flos": 1.3407619263412224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
diff --git a/punctuation/decoder_model/checkpoint-200/training_args.bin b/punctuation/decoder_model/checkpoint-200/training_args.bin
index 5a718de59058adb39dad8aaa7aeb1187de60c7c9..c85faf08b352f43537dd987dbb01ce104d75b094 100644
--- a/punctuation/decoder_model/checkpoint-200/training_args.bin
+++ b/punctuation/decoder_model/checkpoint-200/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706350fbaba956c6f58e868aa99bcc1a0de8a5e4bb317917a8c147ba6dd9b6e2
+oid sha256:f97ed1b6a6e44be81bbaf2ae8e900f738306c25642888690e0d1cb84bc71cf30
 size 5496
diff --git a/punctuation/decoder_model/checkpoint-250/README.md b/punctuation/decoder_model/checkpoint-250/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..f8e2935b613e4ee6e23cfafe6221ecf1e366de75
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/README.md
@@ -0,0 +1,207 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- 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 0.18.1
\ No newline at end of file
diff --git a/punctuation/decoder_model/checkpoint-250/adapter_config.json b/punctuation/decoder_model/checkpoint-250/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fb0f488e682f0b6d9eecf3c5a66b6c60dd4583c
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_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/punctuation/decoder_model/checkpoint-250/adapter_model.safetensors b/punctuation/decoder_model/checkpoint-250/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cd2a8c08daefcacffdeaa5524a879cb62e451433
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e88922aafefbc22035ed0e75460f378ac3c0dcfeab2a79a502f22372e4289a
+size 295488936
diff --git a/punctuation/decoder_model/checkpoint-250/chat_template.jinja b/punctuation/decoder_model/checkpoint-250/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
\ No newline at end of file
diff --git a/punctuation/decoder_model/checkpoint-250/optimizer.pt b/punctuation/decoder_model/checkpoint-250/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9138a227d2bd820f067e690a2471ae11d48e09d2
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a358f7c91c0d49317cdb0477f3b68590b4d106710a8f4eea4ccadac203291c0
+size 591203178
diff --git a/punctuation/decoder_model/checkpoint-250/rng_state.pth b/punctuation/decoder_model/checkpoint-250/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6b6c11da8df35a282585510a628fe5e6f188881f
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6eb946f5fdb1cdb4107905d1cf5848ed32308065b83a70e08faeab88143f211
+size 14244
diff --git a/punctuation/decoder_model/checkpoint-250/scheduler.pt b/punctuation/decoder_model/checkpoint-250/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5754a941acb3767ac4b55fbaf9feded031fcec31
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0916e582c1a0ca8c3ac56ca5069222be8c2a92f8ada721548973b72e3b58d48a
+size 1064
diff --git a/punctuation/decoder_model/checkpoint-250/special_tokens_map.json b/punctuation/decoder_model/checkpoint-250/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/punctuation/decoder_model/checkpoint-250/tokenizer.json b/punctuation/decoder_model/checkpoint-250/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..2896b9a8a75c1a4eadce226067e0de7b9f9020d3
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f3503dade503303f354be26edaf4223708fa1ca2e84c4daf306b5d7c40ce23
+size 11423058
diff --git a/punctuation/decoder_model/checkpoint-250/tokenizer_config.json b/punctuation/decoder_model/checkpoint-250/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}
diff --git a/punctuation/decoder_model/checkpoint-250/trainer_state.json b/punctuation/decoder_model/checkpoint-250/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7211a4cf91bb6caae1747431d57c071329df63e
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/trainer_state.json
@@ -0,0 +1,254 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.9,
+  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-150",
+  "epoch": 2.3388235294117647,
+  "eval_steps": 50,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 1.3681155443191528,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.7202,
+      "step": 10
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 0.7711533308029175,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 0.3185,
+      "step": 20
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 1.2256836891174316,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 0.1827,
+      "step": 30
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 0.888201892375946,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 0.1346,
+      "step": 40
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.853918731212616,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0721,
+      "step": 50
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "eval_loss": 0.04328128695487976,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2686,
+      "eval_samples_per_second": 44.081,
+      "eval_steps_per_second": 22.04,
+      "step": 50
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 0.48631730675697327,
+      "learning_rate": 9.800249271929645e-05,
+      "loss": 0.042,
+      "step": 60
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 0.5516029596328735,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0218,
+      "step": 70
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 0.28095027804374695,
+      "learning_rate": 9.38363377853754e-05,
+      "loss": 0.0127,
+      "step": 80
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 0.8756083846092224,
+      "learning_rate": 9.09576022144496e-05,
+      "loss": 0.0124,
+      "step": 90
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.5514245629310608,
+      "learning_rate": 8.759199037394887e-05,
+      "loss": 0.0119,
+      "step": 100
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "eval_loss": 0.004549662582576275,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2779,
+      "eval_samples_per_second": 43.9,
+      "eval_steps_per_second": 21.95,
+      "step": 100
+    },
+    {
+      "epoch": 1.0282352941176471,
+      "grad_norm": 0.48209479451179504,
+      "learning_rate": 8.377951038078302e-05,
+      "loss": 0.0074,
+      "step": 110
+    },
+    {
+      "epoch": 1.1223529411764706,
+      "grad_norm": 0.22237619757652283,
+      "learning_rate": 7.956548241817912e-05,
+      "loss": 0.0033,
+      "step": 120
+    },
+    {
+      "epoch": 1.2164705882352942,
+      "grad_norm": 0.22323866188526154,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0019,
+      "step": 130
+    },
+    {
+      "epoch": 1.3105882352941176,
+      "grad_norm": 0.044407621026039124,
+      "learning_rate": 7.013733449293687e-05,
+      "loss": 0.0022,
+      "step": 140
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "grad_norm": 0.1491803228855133,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0026,
+      "step": 150
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "eval_loss": 0.00037357292603701353,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.317,
+      "eval_samples_per_second": 43.159,
+      "eval_steps_per_second": 21.579,
+      "step": 150
+    },
+    {
+      "epoch": 1.4988235294117647,
+      "grad_norm": 0.014182478189468384,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.0012,
+      "step": 160
+    },
+    {
+      "epoch": 1.592941176470588,
+      "grad_norm": 0.015145699493587017,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0003,
+      "step": 170
+    },
+    {
+      "epoch": 1.6870588235294117,
+      "grad_norm": 0.011491155251860619,
+      "learning_rate": 4.890925574827195e-05,
+      "loss": 0.0039,
+      "step": 180
+    },
+    {
+      "epoch": 1.7811764705882354,
+      "grad_norm": 0.16684198379516602,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0021,
+      "step": 190
+    },
+    {
+      "epoch": 1.8752941176470588,
+      "grad_norm": 0.006741759832948446,
+      "learning_rate": 3.8115705383691355e-05,
+      "loss": 0.0009,
+      "step": 200
+    },
+    {
+      "epoch": 1.8752941176470588,
+      "eval_loss": 0.0005264483625069261,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2881,
+      "eval_samples_per_second": 43.705,
+      "eval_steps_per_second": 21.852,
+      "step": 200
+    },
+    {
+      "epoch": 1.9694117647058822,
+      "grad_norm": 0.0708838701248169,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0012,
+      "step": 210
+    },
+    {
+      "epoch": 2.0564705882352943,
+      "grad_norm": 0.0013810750097036362,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0005,
+      "step": 220
+    },
+    {
+      "epoch": 2.1505882352941175,
+      "grad_norm": 0.0015096160350367427,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0004,
+      "step": 230
+    },
+    {
+      "epoch": 2.244705882352941,
+      "grad_norm": 0.00760283600538969,
+      "learning_rate": 1.8703826390797048e-05,
+      "loss": 0.0002,
+      "step": 240
+    },
+    {
+      "epoch": 2.3388235294117647,
+      "grad_norm": 0.00949388649314642,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0002,
+      "step": 250
+    },
+    {
+      "epoch": 2.3388235294117647,
+      "eval_loss": 0.00012819873518310487,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2912,
+      "eval_samples_per_second": 43.646,
+      "eval_steps_per_second": 21.823,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 321,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6729869106563072e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/punctuation/decoder_model/checkpoint-250/training_args.bin b/punctuation/decoder_model/checkpoint-250/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c85faf08b352f43537dd987dbb01ce104d75b094
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-250/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97ed1b6a6e44be81bbaf2ae8e900f738306c25642888690e0d1cb84bc71cf30
+size 5496
diff --git a/punctuation/decoder_model/checkpoint-300/README.md b/punctuation/decoder_model/checkpoint-300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..f8e2935b613e4ee6e23cfafe6221ecf1e366de75
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/README.md
@@ -0,0 +1,207 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- 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 0.18.1
\ No newline at end of file
diff --git a/punctuation/decoder_model/checkpoint-300/adapter_config.json b/punctuation/decoder_model/checkpoint-300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fb0f488e682f0b6d9eecf3c5a66b6c60dd4583c
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_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/punctuation/decoder_model/checkpoint-300/adapter_model.safetensors b/punctuation/decoder_model/checkpoint-300/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..678dc0edd0839c0666cdd7b406b3700066eb0767
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84f51cbe1fb1949efe5ecb4b5e1a117ee1dbae74cdcc8a0468b94fe8929a530
+size 295488936
diff --git a/punctuation/decoder_model/checkpoint-300/chat_template.jinja b/punctuation/decoder_model/checkpoint-300/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
\ No newline at end of file
diff --git a/punctuation/decoder_model/checkpoint-300/optimizer.pt b/punctuation/decoder_model/checkpoint-300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..49932a514f1cf3ff5ac8cee713d235280aa332c7
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925ed1790354322ad4905b2fbefecde924b6e090ff4cf45f6f08cbb41ef7ad97
+size 591203178
diff --git a/punctuation/decoder_model/checkpoint-300/rng_state.pth b/punctuation/decoder_model/checkpoint-300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3eb32673a8d7f1c758f137d9fcf269393ae5a72a
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c136e18a347017af22d22beb653423e6bc24f32037c3a53a1d51823a7ddb93a
+size 14244
diff --git a/punctuation/decoder_model/checkpoint-300/scheduler.pt b/punctuation/decoder_model/checkpoint-300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4e70e7d51ec2ed46c4548d625754f42044e29cca
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e141da4d8a6d542ee6207c4130ad5b1aea5686c6966c11ebf0ec19cafebc910
+size 1064
diff --git a/punctuation/decoder_model/checkpoint-300/special_tokens_map.json b/punctuation/decoder_model/checkpoint-300/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/punctuation/decoder_model/checkpoint-300/tokenizer.json b/punctuation/decoder_model/checkpoint-300/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..2896b9a8a75c1a4eadce226067e0de7b9f9020d3
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f3503dade503303f354be26edaf4223708fa1ca2e84c4daf306b5d7c40ce23
+size 11423058
diff --git a/punctuation/decoder_model/checkpoint-300/tokenizer_config.json b/punctuation/decoder_model/checkpoint-300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}
diff --git a/punctuation/decoder_model/checkpoint-300/trainer_state.json b/punctuation/decoder_model/checkpoint-300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..62d4965eb337171ad248de9b2190f7db8b30ee98
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/trainer_state.json
@@ -0,0 +1,298 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.9,
+  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-150",
+  "epoch": 2.8094117647058825,
+  "eval_steps": 50,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 1.3681155443191528,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.7202,
+      "step": 10
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 0.7711533308029175,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 0.3185,
+      "step": 20
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 1.2256836891174316,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 0.1827,
+      "step": 30
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 0.888201892375946,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 0.1346,
+      "step": 40
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.853918731212616,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0721,
+      "step": 50
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "eval_loss": 0.04328128695487976,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2686,
+      "eval_samples_per_second": 44.081,
+      "eval_steps_per_second": 22.04,
+      "step": 50
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 0.48631730675697327,
+      "learning_rate": 9.800249271929645e-05,
+      "loss": 0.042,
+      "step": 60
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 0.5516029596328735,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0218,
+      "step": 70
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 0.28095027804374695,
+      "learning_rate": 9.38363377853754e-05,
+      "loss": 0.0127,
+      "step": 80
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 0.8756083846092224,
+      "learning_rate": 9.09576022144496e-05,
+      "loss": 0.0124,
+      "step": 90
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.5514245629310608,
+      "learning_rate": 8.759199037394887e-05,
+      "loss": 0.0119,
+      "step": 100
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "eval_loss": 0.004549662582576275,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2779,
+      "eval_samples_per_second": 43.9,
+      "eval_steps_per_second": 21.95,
+      "step": 100
+    },
+    {
+      "epoch": 1.0282352941176471,
+      "grad_norm": 0.48209479451179504,
+      "learning_rate": 8.377951038078302e-05,
+      "loss": 0.0074,
+      "step": 110
+    },
+    {
+      "epoch": 1.1223529411764706,
+      "grad_norm": 0.22237619757652283,
+      "learning_rate": 7.956548241817912e-05,
+      "loss": 0.0033,
+      "step": 120
+    },
+    {
+      "epoch": 1.2164705882352942,
+      "grad_norm": 0.22323866188526154,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0019,
+      "step": 130
+    },
+    {
+      "epoch": 1.3105882352941176,
+      "grad_norm": 0.044407621026039124,
+      "learning_rate": 7.013733449293687e-05,
+      "loss": 0.0022,
+      "step": 140
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "grad_norm": 0.1491803228855133,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0026,
+      "step": 150
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "eval_loss": 0.00037357292603701353,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.317,
+      "eval_samples_per_second": 43.159,
+      "eval_steps_per_second": 21.579,
+      "step": 150
+    },
+    {
+      "epoch": 1.4988235294117647,
+      "grad_norm": 0.014182478189468384,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.0012,
+      "step": 160
+    },
+    {
+      "epoch": 1.592941176470588,
+      "grad_norm": 0.015145699493587017,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0003,
+      "step": 170
+    },
+    {
+      "epoch": 1.6870588235294117,
+      "grad_norm": 0.011491155251860619,
+      "learning_rate": 4.890925574827195e-05,
+      "loss": 0.0039,
+      "step": 180
+    },
+    {
+      "epoch": 1.7811764705882354,
+      "grad_norm": 0.16684198379516602,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0021,
+      "step": 190
+    },
+    {
+      "epoch": 1.8752941176470588,
+      "grad_norm": 0.006741759832948446,
+      "learning_rate": 3.8115705383691355e-05,
+      "loss": 0.0009,
+      "step": 200
+    },
+    {
+      "epoch": 1.8752941176470588,
+      "eval_loss": 0.0005264483625069261,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2881,
+      "eval_samples_per_second": 43.705,
+      "eval_steps_per_second": 21.852,
+      "step": 200
+    },
+    {
+      "epoch": 1.9694117647058822,
+      "grad_norm": 0.0708838701248169,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0012,
+      "step": 210
+    },
+    {
+      "epoch": 2.0564705882352943,
+      "grad_norm": 0.0013810750097036362,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0005,
+      "step": 220
+    },
+    {
+      "epoch": 2.1505882352941175,
+      "grad_norm": 0.0015096160350367427,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0004,
+      "step": 230
+    },
+    {
+      "epoch": 2.244705882352941,
+      "grad_norm": 0.00760283600538969,
+      "learning_rate": 1.8703826390797048e-05,
+      "loss": 0.0002,
+      "step": 240
+    },
+    {
+      "epoch": 2.3388235294117647,
+      "grad_norm": 0.00949388649314642,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0002,
+      "step": 250
+    },
+    {
+      "epoch": 2.3388235294117647,
+      "eval_loss": 0.00012819873518310487,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2912,
+      "eval_samples_per_second": 43.646,
+      "eval_steps_per_second": 21.823,
+      "step": 250
+    },
+    {
+      "epoch": 2.4329411764705884,
+      "grad_norm": 0.0011758297914639115,
+      "learning_rate": 1.100577584535592e-05,
+      "loss": 0.0002,
+      "step": 260
+    },
+    {
+      "epoch": 2.527058823529412,
+      "grad_norm": 0.002146691083908081,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0003,
+      "step": 270
+    },
+    {
+      "epoch": 2.621176470588235,
+      "grad_norm": 0.003603292629122734,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0004,
+      "step": 280
+    },
+    {
+      "epoch": 2.715294117647059,
+      "grad_norm": 0.005790353287011385,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0003,
+      "step": 290
+    },
+    {
+      "epoch": 2.8094117647058825,
+      "grad_norm": 0.012438272126019001,
+      "learning_rate": 1.4328965093369283e-06,
+      "loss": 0.0001,
+      "step": 300
+    },
+    {
+      "epoch": 2.8094117647058825,
+      "eval_loss": 8.123814041027799e-05,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.3021,
+      "eval_samples_per_second": 43.439,
+      "eval_steps_per_second": 21.72,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 321,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0101558462377984e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/punctuation/decoder_model/checkpoint-300/training_args.bin b/punctuation/decoder_model/checkpoint-300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c85faf08b352f43537dd987dbb01ce104d75b094
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97ed1b6a6e44be81bbaf2ae8e900f738306c25642888690e0d1cb84bc71cf30
+size 5496
diff --git a/punctuation/decoder_model/checkpoint-321/README.md b/punctuation/decoder_model/checkpoint-321/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..f8e2935b613e4ee6e23cfafe6221ecf1e366de75
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/README.md
@@ -0,0 +1,207 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- 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 0.18.1
\ No newline at end of file
diff --git a/punctuation/decoder_model/checkpoint-321/adapter_config.json b/punctuation/decoder_model/checkpoint-321/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fb0f488e682f0b6d9eecf3c5a66b6c60dd4583c
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_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/punctuation/decoder_model/checkpoint-321/adapter_model.safetensors b/punctuation/decoder_model/checkpoint-321/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0978939e5188e1ff22f8b2466bb242d6d0d1c65b
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb46fb655ec76f280146b5d3f01a75149bafb3447e8f02a11d8c119bc1573e94
+size 295488936
diff --git a/punctuation/decoder_model/checkpoint-321/chat_template.jinja b/punctuation/decoder_model/checkpoint-321/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
\ No newline at end of file
diff --git a/punctuation/decoder_model/checkpoint-321/optimizer.pt b/punctuation/decoder_model/checkpoint-321/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4c9dc84f355d88bcbafcb7686af90a071d83a7bf
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f755e0a43aa8323ba12fc0d0bd964f28c3a38412130b16c0ab43f2953e3dce4d
+size 591203178
diff --git a/punctuation/decoder_model/checkpoint-321/rng_state.pth b/punctuation/decoder_model/checkpoint-321/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..69400f2736d80f2ced726344459fe4f02bddb03e
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70973b70c4b3fe7d7cdea2e622298c223f8a2cf854b813969e63e72c90691a2b
+size 14244
diff --git a/punctuation/decoder_model/checkpoint-321/scheduler.pt b/punctuation/decoder_model/checkpoint-321/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f0b454a5b2536d40c557e1ab8d025962920144c0
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e8c109f1f63d9547752a8074bf44daf09946f623405a2759017388cc5b0d678
+size 1064
diff --git a/punctuation/decoder_model/checkpoint-321/special_tokens_map.json b/punctuation/decoder_model/checkpoint-321/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/punctuation/decoder_model/checkpoint-321/tokenizer.json b/punctuation/decoder_model/checkpoint-321/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..2896b9a8a75c1a4eadce226067e0de7b9f9020d3
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f3503dade503303f354be26edaf4223708fa1ca2e84c4daf306b5d7c40ce23
+size 11423058
diff --git a/punctuation/decoder_model/checkpoint-321/tokenizer_config.json b/punctuation/decoder_model/checkpoint-321/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}
diff --git a/punctuation/decoder_model/checkpoint-321/trainer_state.json b/punctuation/decoder_model/checkpoint-321/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..dabbb4077ce7a9576e78ba03fb8f643d958388f8
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/trainer_state.json
@@ -0,0 +1,312 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.9,
+  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-150",
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 321,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 1.3681155443191528,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.7202,
+      "step": 10
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 0.7711533308029175,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 0.3185,
+      "step": 20
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 1.2256836891174316,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 0.1827,
+      "step": 30
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 0.888201892375946,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 0.1346,
+      "step": 40
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.853918731212616,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0721,
+      "step": 50
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "eval_loss": 0.04328128695487976,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2686,
+      "eval_samples_per_second": 44.081,
+      "eval_steps_per_second": 22.04,
+      "step": 50
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 0.48631730675697327,
+      "learning_rate": 9.800249271929645e-05,
+      "loss": 0.042,
+      "step": 60
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 0.5516029596328735,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0218,
+      "step": 70
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 0.28095027804374695,
+      "learning_rate": 9.38363377853754e-05,
+      "loss": 0.0127,
+      "step": 80
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 0.8756083846092224,
+      "learning_rate": 9.09576022144496e-05,
+      "loss": 0.0124,
+      "step": 90
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.5514245629310608,
+      "learning_rate": 8.759199037394887e-05,
+      "loss": 0.0119,
+      "step": 100
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "eval_loss": 0.004549662582576275,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2779,
+      "eval_samples_per_second": 43.9,
+      "eval_steps_per_second": 21.95,
+      "step": 100
+    },
+    {
+      "epoch": 1.0282352941176471,
+      "grad_norm": 0.48209479451179504,
+      "learning_rate": 8.377951038078302e-05,
+      "loss": 0.0074,
+      "step": 110
+    },
+    {
+      "epoch": 1.1223529411764706,
+      "grad_norm": 0.22237619757652283,
+      "learning_rate": 7.956548241817912e-05,
+      "loss": 0.0033,
+      "step": 120
+    },
+    {
+      "epoch": 1.2164705882352942,
+      "grad_norm": 0.22323866188526154,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0019,
+      "step": 130
+    },
+    {
+      "epoch": 1.3105882352941176,
+      "grad_norm": 0.044407621026039124,
+      "learning_rate": 7.013733449293687e-05,
+      "loss": 0.0022,
+      "step": 140
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "grad_norm": 0.1491803228855133,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0026,
+      "step": 150
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "eval_loss": 0.00037357292603701353,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.317,
+      "eval_samples_per_second": 43.159,
+      "eval_steps_per_second": 21.579,
+      "step": 150
+    },
+    {
+      "epoch": 1.4988235294117647,
+      "grad_norm": 0.014182478189468384,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.0012,
+      "step": 160
+    },
+    {
+      "epoch": 1.592941176470588,
+      "grad_norm": 0.015145699493587017,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0003,
+      "step": 170
+    },
+    {
+      "epoch": 1.6870588235294117,
+      "grad_norm": 0.011491155251860619,
+      "learning_rate": 4.890925574827195e-05,
+      "loss": 0.0039,
+      "step": 180
+    },
+    {
+      "epoch": 1.7811764705882354,
+      "grad_norm": 0.16684198379516602,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0021,
+      "step": 190
+    },
+    {
+      "epoch": 1.8752941176470588,
+      "grad_norm": 0.006741759832948446,
+      "learning_rate": 3.8115705383691355e-05,
+      "loss": 0.0009,
+      "step": 200
+    },
+    {
+      "epoch": 1.8752941176470588,
+      "eval_loss": 0.0005264483625069261,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2881,
+      "eval_samples_per_second": 43.705,
+      "eval_steps_per_second": 21.852,
+      "step": 200
+    },
+    {
+      "epoch": 1.9694117647058822,
+      "grad_norm": 0.0708838701248169,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0012,
+      "step": 210
+    },
+    {
+      "epoch": 2.0564705882352943,
+      "grad_norm": 0.0013810750097036362,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0005,
+      "step": 220
+    },
+    {
+      "epoch": 2.1505882352941175,
+      "grad_norm": 0.0015096160350367427,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0004,
+      "step": 230
+    },
+    {
+      "epoch": 2.244705882352941,
+      "grad_norm": 0.00760283600538969,
+      "learning_rate": 1.8703826390797048e-05,
+      "loss": 0.0002,
+      "step": 240
+    },
+    {
+      "epoch": 2.3388235294117647,
+      "grad_norm": 0.00949388649314642,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0002,
+      "step": 250
+    },
+    {
+      "epoch": 2.3388235294117647,
+      "eval_loss": 0.00012819873518310487,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2912,
+      "eval_samples_per_second": 43.646,
+      "eval_steps_per_second": 21.823,
+      "step": 250
+    },
+    {
+      "epoch": 2.4329411764705884,
+      "grad_norm": 0.0011758297914639115,
+      "learning_rate": 1.100577584535592e-05,
+      "loss": 0.0002,
+      "step": 260
+    },
+    {
+      "epoch": 2.527058823529412,
+      "grad_norm": 0.002146691083908081,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0003,
+      "step": 270
+    },
+    {
+      "epoch": 2.621176470588235,
+      "grad_norm": 0.003603292629122734,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0004,
+      "step": 280
+    },
+    {
+      "epoch": 2.715294117647059,
+      "grad_norm": 0.005790353287011385,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0003,
+      "step": 290
+    },
+    {
+      "epoch": 2.8094117647058825,
+      "grad_norm": 0.012438272126019001,
+      "learning_rate": 1.4328965093369283e-06,
+      "loss": 0.0001,
+      "step": 300
+    },
+    {
+      "epoch": 2.8094117647058825,
+      "eval_loss": 8.123814041027799e-05,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.3021,
+      "eval_samples_per_second": 43.439,
+      "eval_steps_per_second": 21.72,
+      "step": 300
+    },
+    {
+      "epoch": 2.9035294117647057,
+      "grad_norm": 0.0017391764558851719,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0001,
+      "step": 310
+    },
+    {
+      "epoch": 2.9976470588235293,
+      "grad_norm": 0.0015454388922080398,
+      "learning_rate": 1.189864600454338e-08,
+      "loss": 0.0001,
+      "step": 320
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 321,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.146462931369165e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/punctuation/decoder_model/checkpoint-321/training_args.bin b/punctuation/decoder_model/checkpoint-321/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c85faf08b352f43537dd987dbb01ce104d75b094
--- /dev/null
+++ b/punctuation/decoder_model/checkpoint-321/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97ed1b6a6e44be81bbaf2ae8e900f738306c25642888690e0d1cb84bc71cf30
+size 5496
diff --git a/punctuation/decoder_model/checkpoint-50/adapter_config.json b/punctuation/decoder_model/checkpoint-50/adapter_config.json
index c0c6ef1654af65a85c3fdb97621e978d19cca00a..9fb0f488e682f0b6d9eecf3c5a66b6c60dd4583c 100644
--- a/punctuation/decoder_model/checkpoint-50/adapter_config.json
+++ b/punctuation/decoder_model/checkpoint-50/adapter_config.json
@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "gate_proj",
+    "q_proj",
     "up_proj",
-    "down_proj",
-    "k_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "k_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
diff --git a/punctuation/decoder_model/checkpoint-50/adapter_model.safetensors b/punctuation/decoder_model/checkpoint-50/adapter_model.safetensors
index 513dae3d6cc085f25d1b619bdc221cadeaedac6a..c8f97c74828fb052072e88bbf72b1e939bf63835 100644
--- a/punctuation/decoder_model/checkpoint-50/adapter_model.safetensors
+++ b/punctuation/decoder_model/checkpoint-50/adapter_model.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c78e38cd7ceb629958882592c6c570f3e396c0645723edac1afc6207286c8d
+oid sha256:c9b1896dc44cd271c7d619e7a6faec4223f42cb24f9b334efa5792fd608fb6f4
 size 295488936
diff --git a/punctuation/decoder_model/checkpoint-50/optimizer.pt b/punctuation/decoder_model/checkpoint-50/optimizer.pt
index f1d9abaa11d73d7ce34dd511481c55a540bffd10..8783bfbe000f7c8ddb03b9ccf0f0329db81b135e 100644
--- a/punctuation/decoder_model/checkpoint-50/optimizer.pt
+++ b/punctuation/decoder_model/checkpoint-50/optimizer.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e6b34fd39331248994582b41a2c32d7529a11b4753060a4a464dd68e94b5cc
+oid sha256:cdc8442545d907f958a72f827e430b565343a0b0220eabeb45b0ba4a4ac92093
 size 591203178
diff --git a/punctuation/decoder_model/checkpoint-50/rng_state.pth b/punctuation/decoder_model/checkpoint-50/rng_state.pth
index 28dbb0b0eadc59de16292574a10f0f40ca16eda2..ee394cd7d279e55adb57ad46144a8582b3a9b3d4 100644
--- a/punctuation/decoder_model/checkpoint-50/rng_state.pth
+++ b/punctuation/decoder_model/checkpoint-50/rng_state.pth
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f945598aaec844c97e657a276faffbfb1df323d0ddba93909d7687eefe9c817
+oid sha256:fa6a68dbe3ae841b79e7274ee5db080c9c082269e42d2662d7a07f31e693032f
 size 14244
diff --git a/punctuation/decoder_model/checkpoint-50/scheduler.pt b/punctuation/decoder_model/checkpoint-50/scheduler.pt
index 499edde9268275a2a0113a2ceaf083b4966aff01..63de6ed23439838dce81727befc6adc7353a1b9a 100644
--- a/punctuation/decoder_model/checkpoint-50/scheduler.pt
+++ b/punctuation/decoder_model/checkpoint-50/scheduler.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c581a241e41575c445823d598ecd0c5bdf81e79a14fe5774908df5a9a610721
+oid sha256:7b451c83b97723dcf8043227b15b5bb6b2f5085e6ddd5eed345c917320379aa6
 size 1064
diff --git a/punctuation/decoder_model/checkpoint-50/trainer_state.json b/punctuation/decoder_model/checkpoint-50/trainer_state.json
index e2ca41132159e0b06decc414a2bc5fd3e061e22f..b8e0ed6d82bbff803dcc88f926391a16e1e9ffef 100644
--- a/punctuation/decoder_model/checkpoint-50/trainer_state.json
+++ b/punctuation/decoder_model/checkpoint-50/trainer_state.json
@@ -1,7 +1,7 @@
 {
   "best_global_step": 50,
-  "best_metric": 0.55,
-  "best_model_checkpoint": "./models/punctuation/decoder_model/checkpoint-50",
+  "best_metric": 0.4,
+  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-50",
   "epoch": 0.47058823529411764,
   "eval_steps": 50,
   "global_step": 50,
@@ -11,53 +11,53 @@
   "log_history": [
     {
       "epoch": 0.09411764705882353,
-      "grad_norm": 0.24285665154457092,
-      "learning_rate": 0.0001,
-      "loss": 0.0437,
+      "grad_norm": 1.3681155443191528,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.7202,
       "step": 10
     },
     {
       "epoch": 0.18823529411764706,
-      "grad_norm": 0.1404133290052414,
-      "learning_rate": 0.0001,
-      "loss": 0.0063,
+      "grad_norm": 0.7711533308029175,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 0.3185,
       "step": 20
     },
     {
       "epoch": 0.2823529411764706,
-      "grad_norm": 0.10824572294950485,
-      "learning_rate": 0.0001,
-      "loss": 0.0033,
+      "grad_norm": 1.2256836891174316,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 0.1827,
       "step": 30
     },
     {
       "epoch": 0.3764705882352941,
-      "grad_norm": 0.057334210723638535,
-      "learning_rate": 0.0001,
-      "loss": 0.0018,
+      "grad_norm": 0.888201892375946,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 0.1346,
       "step": 40
     },
     {
       "epoch": 0.47058823529411764,
-      "grad_norm": 0.03022940270602703,
-      "learning_rate": 0.0001,
-      "loss": 0.0015,
+      "grad_norm": 0.853918731212616,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0721,
       "step": 50
     },
     {
       "epoch": 0.47058823529411764,
-      "eval_loss": 0.001103814342059195,
-      "eval_model_preparation_time": 0.0142,
-      "eval_runtime": 3.8403,
-      "eval_samples_per_second": 26.04,
-      "eval_steps_per_second": 13.02,
+      "eval_loss": 0.04328128695487976,
+      "eval_model_preparation_time": 0.0162,
+      "eval_runtime": 2.2686,
+      "eval_samples_per_second": 44.081,
+      "eval_steps_per_second": 22.04,
       "step": 50
     }
   ],
   "logging_steps": 10,
-  "max_steps": 214,
+  "max_steps": 321,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -71,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6400369042102272.0,
+  "total_flos": 3332789951268864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
diff --git a/punctuation/decoder_model/checkpoint-50/training_args.bin b/punctuation/decoder_model/checkpoint-50/training_args.bin
index 5a718de59058adb39dad8aaa7aeb1187de60c7c9..c85faf08b352f43537dd987dbb01ce104d75b094 100644
--- a/punctuation/decoder_model/checkpoint-50/training_args.bin
+++ b/punctuation/decoder_model/checkpoint-50/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706350fbaba956c6f58e868aa99bcc1a0de8a5e4bb317917a8c147ba6dd9b6e2
+oid sha256:f97ed1b6a6e44be81bbaf2ae8e900f738306c25642888690e0d1cb84bc71cf30
 size 5496
diff --git a/punctuation/decoder_model/training_args.bin b/punctuation/decoder_model/training_args.bin
index 5a718de59058adb39dad8aaa7aeb1187de60c7c9..c85faf08b352f43537dd987dbb01ce104d75b094 100644
--- a/punctuation/decoder_model/training_args.bin
+++ b/punctuation/decoder_model/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706350fbaba956c6f58e868aa99bcc1a0de8a5e4bb317917a8c147ba6dd9b6e2
+oid sha256:f97ed1b6a6e44be81bbaf2ae8e900f738306c25642888690e0d1cb84bc71cf30
 size 5496
diff --git a/punctuation/decoder_model/training_config.yaml b/punctuation/decoder_model/training_config.yaml
index 31356ed063bc2d0631bd0838d6a616099f0e9f56..6ab5ae54beeb39ac96720e3d034c177d7508037e 100644
--- a/punctuation/decoder_model/training_config.yaml
+++ b/punctuation/decoder_model/training_config.yaml
@@ -28,10 +28,10 @@ training:
   group_by_length: true
   learning_rate: 0.0001
   load_best_model_at_end: true
-  lr_scheduler: constant
+  lr_scheduler: cosine
   max_grad_norm: 1.0
   metric_for_best_model: eval_decoder_accuracy
-  num_epochs: 2
+  num_epochs: 3
   optim: adamw_torch
   save_total_limit: 2
   warmup_ratio: 0.1