diff --git a/checkpoint-104/README.md b/checkpoint-104/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-104/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-9B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-9B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.20.0
\ No newline at end of file
diff --git a/checkpoint-104/adapter_config.json b/checkpoint-104/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-104/adapter_config.json
@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "in_proj_z",
+    "v_proj",
+    "down_proj",
+    "in_proj_b",
+    "q_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-104/adapter_model.safetensors b/checkpoint-104/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3e44c42035241a8781109f5cf36151d5d53d91de
--- /dev/null
+++ b/checkpoint-104/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6753b31dec96d00685b7ab64153d0fde1dd543daa00e9783984e5d5950a409
+size 1384975816
diff --git a/checkpoint-104/chat_template.jinja b/checkpoint-104/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-104/chat_template.jinja
@@ -0,0 +1,20 @@
+{%- if messages and messages[0].role == 'system' %}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+{%- set loop_messages = messages[1:] %}
+{%- else %}
+{%- set loop_messages = messages %}
+{%- endif %}
+{%- for message in loop_messages %}
+{{- '<|im_start|>' + message.role + '\n' }}
+{%- if message.role == 'assistant' %}
+{% generation %}{{- message.content + '<|im_end|>' }}{% endgeneration %}{{- '\n' }}
+{%- else %}
+{{- message.content + '<|im_end|>\n' }}
+{%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{- '<|im_start|>assistant\n' }}
+{%- if enable_thinking is not defined or not enable_thinking %}
+{{- '<think>\n\n</think>\n\n' }}
+{%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/checkpoint-104/optimizer.pt b/checkpoint-104/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..edfcaceb7d7d553c4a9a4013256289be244b5d8e
--- /dev/null
+++ b/checkpoint-104/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c8e8b18008a18b6cb854aeb7e1f00e6b7b03d55ff81d7e181f26600a85da28
+size 2770239667
diff --git a/checkpoint-104/rng_state_0.pth b/checkpoint-104/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..49ea4862d3d8b6c8bdac56fd8d71fe74f545718b
--- /dev/null
+++ b/checkpoint-104/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0bbdaa7ad33e004283b0d01776956cc110040b5ec0b0baf8b00b8ede32702f
+size 16389
diff --git a/checkpoint-104/rng_state_1.pth b/checkpoint-104/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..67f95675b05d24947e4a6e095eef62be835e0425
--- /dev/null
+++ b/checkpoint-104/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f4d0f38aa3e8ca23c960c3fd70659994e21925478e14f43d5321ca118cc1558
+size 16389
diff --git a/checkpoint-104/rng_state_10.pth b/checkpoint-104/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..99130796873424d48f30756a21599006eb247a61
--- /dev/null
+++ b/checkpoint-104/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdfbdb41a021e04dddc7eb7020bbcb000803a73f25966675319c44f7500ce42d
+size 16404
diff --git a/checkpoint-104/rng_state_11.pth b/checkpoint-104/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d41aa82921baf808f4e1e781fa972e53842227dc
--- /dev/null
+++ b/checkpoint-104/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7c2b199a17611a90c335a47e0ccf77962902dceac7d9d93f3464fe11c3fa84
+size 16404
diff --git a/checkpoint-104/rng_state_12.pth b/checkpoint-104/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4c07880ae0b81464c62b235f85bb95b54ece3ba1
--- /dev/null
+++ b/checkpoint-104/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72be4fcb744c6dad892dd90bbda6cf1862ee86a198c4f9b917e64e06b8085aa9
+size 16404
diff --git a/checkpoint-104/rng_state_13.pth b/checkpoint-104/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a09e9fa9c0477c37d2f70e0f00160abfa02a667a
--- /dev/null
+++ b/checkpoint-104/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2379532ceeb14dd8bc21fae32b56f9c65643d7d65bf60528cde28c49670043c
+size 16404
diff --git a/checkpoint-104/rng_state_14.pth b/checkpoint-104/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2e67d847071874b154e16b9c8d94beeb73864e24
--- /dev/null
+++ b/checkpoint-104/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0111c123106e9b277569ece6a3e17cb35c2912fe4dd1a5c7712b57439b60538c
+size 16404
diff --git a/checkpoint-104/rng_state_15.pth b/checkpoint-104/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..16c2bf7b9cfadbb5f1c5e7943fb876c0f902afee
--- /dev/null
+++ b/checkpoint-104/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f6d3369632bc73563fdb578571ffba38ad3faede0fec757dd05c8e8c4d3f65
+size 16404
diff --git a/checkpoint-104/rng_state_16.pth b/checkpoint-104/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ba7a5e71a98ba4994a7c522b7bb1591032463d9d
--- /dev/null
+++ b/checkpoint-104/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e909e38208b01a469a9b9ad466c6101f807da74c6ecfb9e12c3c1328d84ecda
+size 16404
diff --git a/checkpoint-104/rng_state_17.pth b/checkpoint-104/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1f095de64d5dffba85ca63ae231a7c70c144b7ba
--- /dev/null
+++ b/checkpoint-104/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c551856e3f9adb4ca8b7d17fbfb4801d25ca075ea6bf8be557e8749ed5a7d33
+size 16404
diff --git a/checkpoint-104/rng_state_18.pth b/checkpoint-104/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3487c684e7ef4baf1a9f73b9701a8e812b287c82
--- /dev/null
+++ b/checkpoint-104/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:397394cea924c7737ada3d32b5683455bff93fb5f678e9d42ef916b11d664b6e
+size 16404
diff --git a/checkpoint-104/rng_state_19.pth b/checkpoint-104/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..77b657d4aaee0f84dc1c07191c4a40c56f38cf13
--- /dev/null
+++ b/checkpoint-104/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cefc617da8c240b5f75d509a8eb01c0598800deee2ccb9270f960f3ad0f342f5
+size 16404
diff --git a/checkpoint-104/rng_state_2.pth b/checkpoint-104/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..74c3694f7e77d7bc0ee6b605cffa636a26648ccb
--- /dev/null
+++ b/checkpoint-104/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045bc8e28d053920b882df35f373069639e7c977bf52252e83faed9bb42fbaa7
+size 16389
diff --git a/checkpoint-104/rng_state_20.pth b/checkpoint-104/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..26f590f21d155e8d38c4fc1c2844a42937d6f408
--- /dev/null
+++ b/checkpoint-104/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a364398ad9de55f6d21863694b831fbab8ba1733b9f8f89b81fc4d474c793e
+size 16404
diff --git a/checkpoint-104/rng_state_21.pth b/checkpoint-104/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e5e118ee97b66afd961d01b1e2bc222465cdc5b6
--- /dev/null
+++ b/checkpoint-104/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8047059cd48d386603a9f58ff2768a8897ec22cf8add7ca227d53430c190ba
+size 16404
diff --git a/checkpoint-104/rng_state_22.pth b/checkpoint-104/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f01c207ace3dcc127381a41b26bd689cf0945710
--- /dev/null
+++ b/checkpoint-104/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5db11770cb5dbf972aa6b0962d1fd76f1998be9a1e06644392f69f257c7dc7
+size 16404
diff --git a/checkpoint-104/rng_state_23.pth b/checkpoint-104/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1d82acbdecac6bfb6b018bc1850f10304ef4ad45
--- /dev/null
+++ b/checkpoint-104/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb7fad50d99f51b2ae0a77f0829bc441d8ba3077363c1b5c79472c8ca44485e
+size 16404
diff --git a/checkpoint-104/rng_state_24.pth b/checkpoint-104/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ea2c5ee7a4f055eeb4ed4656911ef89843509300
--- /dev/null
+++ b/checkpoint-104/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688b48f33fbc0fb75514f86f253c8c3ded2be05711641453c11aed6427d920d2
+size 16404
diff --git a/checkpoint-104/rng_state_25.pth b/checkpoint-104/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e0d2fcf3c0f474c3c105101353589a6884610d6c
--- /dev/null
+++ b/checkpoint-104/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b247b3422b27d4c89704430c46923b6fb91057e7a2f3fd7a46e56cb22eb99b0c
+size 16404
diff --git a/checkpoint-104/rng_state_26.pth b/checkpoint-104/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1be8e21f24d62baaabcd56e149a078f52a2388ba
--- /dev/null
+++ b/checkpoint-104/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aabfb6da1fe1c92858f5d5b850815a7d12204dbf70a584d5dc40e054b89e50
+size 16404
diff --git a/checkpoint-104/rng_state_27.pth b/checkpoint-104/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6eeedb870aeba4f55195a9e03256566cb723932d
--- /dev/null
+++ b/checkpoint-104/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f433bf58a0aa9ac63247f3d479e7acbcee2539d29e44d15241de61ab8b964962
+size 16404
diff --git a/checkpoint-104/rng_state_28.pth b/checkpoint-104/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d5ea8d963ae61fab7483c5b4cdc4a1fbc87155f2
--- /dev/null
+++ b/checkpoint-104/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175e7f7fbd8eda83c5a994d6adccb0491d15d4ec5a85cc705548d81353c21352
+size 16404
diff --git a/checkpoint-104/rng_state_29.pth b/checkpoint-104/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..66eb26adced10268ad244c56ee666933d6badadd
--- /dev/null
+++ b/checkpoint-104/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6929bc72e7c8714b885f68c5cfe2e776186a622514670de9fdf19ef7ab612f
+size 16404
diff --git a/checkpoint-104/rng_state_3.pth b/checkpoint-104/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2ca09803b33d025287d97597a4174714403a8b61
--- /dev/null
+++ b/checkpoint-104/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5a12e8a7290dba48f099e810aaf2554daedb41defc0e82c4d0413214d0acea
+size 16389
diff --git a/checkpoint-104/rng_state_30.pth b/checkpoint-104/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7cc2a46d111fbc6efe55811830a55f4b6fd80dd9
--- /dev/null
+++ b/checkpoint-104/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8192ad22adff0cce9bca03db5c3617e692539b5a2fa65e4064f36f80efed988
+size 16404
diff --git a/checkpoint-104/rng_state_31.pth b/checkpoint-104/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1d0b818643a7ae4c24203d2fd42e205a2acaa36b
--- /dev/null
+++ b/checkpoint-104/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e785ecb4c3798eba0023856d18f4288f60d20e027d4b97fc1a41eb878aad2f4
+size 16404
diff --git a/checkpoint-104/rng_state_4.pth b/checkpoint-104/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..917eb87111f41a8207b33e041f5922649c12c724
--- /dev/null
+++ b/checkpoint-104/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75770e3469400929075cbec9a5e0588b4c6a2ec863a05ca156ee8f02e19dbb4b
+size 16389
diff --git a/checkpoint-104/rng_state_5.pth b/checkpoint-104/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6717ae2f1be3f578244f7fe8c17b85fde0a701aa
--- /dev/null
+++ b/checkpoint-104/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e96e1e9707de1765595f60cdc00da80bd88bc85e4fe6c8714f8b2481cde86e
+size 16389
diff --git a/checkpoint-104/rng_state_6.pth b/checkpoint-104/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2a9f7ff0296a964662d60079d2048692b0d38803
--- /dev/null
+++ b/checkpoint-104/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66e4a9d6fa6e8e021782b28ba7565c192be16231ac013005d79718fde55cf0f
+size 16389
diff --git a/checkpoint-104/rng_state_7.pth b/checkpoint-104/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e35063e1c3f32e33299eb42fa877d8efa1463798
--- /dev/null
+++ b/checkpoint-104/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be38529aeee864e45e253a61de8546e8c3eb4d9500bc1a8858e9deed04f8d0cb
+size 16389
diff --git a/checkpoint-104/rng_state_8.pth b/checkpoint-104/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8769b098daa0d7b0a4332e30f3a3448d73c93210
--- /dev/null
+++ b/checkpoint-104/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d82d58882ba2c6dae61a0f562b8e95aa1f0070d7a6378232da6ff2ef5b6657
+size 16389
diff --git a/checkpoint-104/rng_state_9.pth b/checkpoint-104/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..19cff69a8768559be1cec75cb2740b4359a82862
--- /dev/null
+++ b/checkpoint-104/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20fc0f6c7db9621b61b7ad4bdada1c01530fe818acf7e842750bcb90939a108c
+size 16389
diff --git a/checkpoint-104/scheduler.pt b/checkpoint-104/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..21ef83606c6f8b1dbc8a881cff051196824a57ec
--- /dev/null
+++ b/checkpoint-104/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecff7d040006dcbbb25c876f9fe6f2b9e2dd218c04295b761a5aebaae5c80a6
+size 1465
diff --git a/checkpoint-104/tokenizer.json b/checkpoint-104/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-104/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-104/tokenizer_config.json b/checkpoint-104/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-104/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/checkpoint-104/trainer_state.json b/checkpoint-104/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..0b4f3532d1e9d8c67d96a6285749a2da54ad1ab3
--- /dev/null
+++ b/checkpoint-104/trainer_state.json
@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6507936507936507,
+  "eval_steps": 500,
+  "global_step": 104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.25798711776733396,
+      "epoch": 0.07936507936507936,
+      "grad_norm": 0.6395628452301025,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.33170533180236816,
+      "mean_token_accuracy": 0.9083019256591797,
+      "num_tokens": 2249744.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.1518770933151245,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.27742329239845276,
+      "learning_rate": 4.9966852247120764e-05,
+      "loss": 0.14515713453292847,
+      "mean_token_accuracy": 0.9476617932319641,
+      "num_tokens": 4502357.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.1205204889178276,
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.15280286967754364,
+      "learning_rate": 4.976460088644493e-05,
+      "loss": 0.11978392601013184,
+      "mean_token_accuracy": 0.9552689790725708,
+      "num_tokens": 6750630.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.1094709500670433,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.13621626794338226,
+      "learning_rate": 4.938000100611456e-05,
+      "loss": 0.10746543407440186,
+      "mean_token_accuracy": 0.9598726153373718,
+      "num_tokens": 8991471.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.10419090241193771,
+      "epoch": 0.3968253968253968,
+      "grad_norm": 0.16320250928401947,
+      "learning_rate": 4.881588452008456e-05,
+      "loss": 0.10661067962646484,
+      "mean_token_accuracy": 0.9599695205688477,
+      "num_tokens": 11228489.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.09569432139396668,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.15873780846595764,
+      "learning_rate": 4.80764051721044e-05,
+      "loss": 0.09594419002532958,
+      "mean_token_accuracy": 0.9637031435966492,
+      "num_tokens": 13464387.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.09625398516654968,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.15297284722328186,
+      "learning_rate": 4.7167007950568505e-05,
+      "loss": 0.09495124220848083,
+      "mean_token_accuracy": 0.964220929145813,
+      "num_tokens": 15709681.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.09195081293582916,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.15219081938266754,
+      "learning_rate": 4.609438899557964e-05,
+      "loss": 0.09150891304016114,
+      "mean_token_accuracy": 0.9652478575706482,
+      "num_tokens": 17987403.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.08980809897184372,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.1412411779165268,
+      "learning_rate": 4.4866446293440626e-05,
+      "loss": 0.0898817539215088,
+      "mean_token_accuracy": 0.965602707862854,
+      "num_tokens": 20231746.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.08743101209402085,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.16695629060268402,
+      "learning_rate": 4.3492221521624174e-05,
+      "loss": 0.08715485334396363,
+      "mean_token_accuracy": 0.9668790459632873,
+      "num_tokens": 22491762.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.08765677958726883,
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.21143023669719696,
+      "learning_rate": 4.198183347243233e-05,
+      "loss": 0.08766236305236816,
+      "mean_token_accuracy": 0.9668452143669128,
+      "num_tokens": 24752715.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.08127444982528687,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.18779045343399048,
+      "learning_rate": 4.03464035455653e-05,
+      "loss": 0.08236484527587891,
+      "mean_token_accuracy": 0.9689654350280762,
+      "num_tokens": 26982538.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.07894417196512223,
+      "epoch": 1.0317460317460316,
+      "grad_norm": 0.1385810822248459,
+      "learning_rate": 3.859797385821812e-05,
+      "loss": 0.0778856873512268,
+      "mean_token_accuracy": 0.9699163198471069,
+      "num_tokens": 29221704.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.07985353171825409,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.16439372301101685,
+      "learning_rate": 3.6749418575683e-05,
+      "loss": 0.07885851860046386,
+      "mean_token_accuracy": 0.969633674621582,
+      "num_tokens": 31470338.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.07194689065217971,
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.16862133145332336,
+      "learning_rate": 3.48143491153543e-05,
+      "loss": 0.074225252866745,
+      "mean_token_accuracy": 0.9716025114059448,
+      "num_tokens": 33719303.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.07757648378610611,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.14261098206043243,
+      "learning_rate": 3.280701392214487e-05,
+      "loss": 0.07595503330230713,
+      "mean_token_accuracy": 0.9707554697990417,
+      "num_tokens": 35977913.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.07388863414525985,
+      "epoch": 1.3492063492063493,
+      "grad_norm": 0.16554316878318787,
+      "learning_rate": 3.07421935532949e-05,
+      "loss": 0.07574511766433716,
+      "mean_token_accuracy": 0.9704798936843873,
+      "num_tokens": 38220353.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.07249651849269867,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.18186147511005402,
+      "learning_rate": 2.8635091845092247e-05,
+      "loss": 0.07062947750091553,
+      "mean_token_accuracy": 0.9724894285202026,
+      "num_tokens": 40476134.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.06985943019390106,
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.13512398302555084,
+      "learning_rate": 2.650122396287371e-05,
+      "loss": 0.06756666898727418,
+      "mean_token_accuracy": 0.9738536238670349,
+      "num_tokens": 42711931.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.06709291264414788,
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.13330888748168945,
+      "learning_rate": 2.4356302158625288e-05,
+      "loss": 0.07059981226921082,
+      "mean_token_accuracy": 0.9723513960838318,
+      "num_tokens": 44948562.0,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.606116879537799e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-104/training_args.bin b/checkpoint-104/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-104/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-112/README.md b/checkpoint-112/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-112/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-9B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-9B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.20.0
\ No newline at end of file
diff --git a/checkpoint-112/adapter_config.json b/checkpoint-112/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-112/adapter_config.json
@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "in_proj_z",
+    "v_proj",
+    "down_proj",
+    "in_proj_b",
+    "q_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-112/adapter_model.safetensors b/checkpoint-112/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b09da9031430908d32854eeddae00c96c712899c
--- /dev/null
+++ b/checkpoint-112/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204917ef911ea1a8fe13bc2ac0e6eaa8d14a83b9c35555e9144f88370a991bf6
+size 1384975816
diff --git a/checkpoint-112/chat_template.jinja b/checkpoint-112/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-112/chat_template.jinja
@@ -0,0 +1,20 @@
+{%- if messages and messages[0].role == 'system' %}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+{%- set loop_messages = messages[1:] %}
+{%- else %}
+{%- set loop_messages = messages %}
+{%- endif %}
+{%- for message in loop_messages %}
+{{- '<|im_start|>' + message.role + '\n' }}
+{%- if message.role == 'assistant' %}
+{% generation %}{{- message.content + '<|im_end|>' }}{% endgeneration %}{{- '\n' }}
+{%- else %}
+{{- message.content + '<|im_end|>\n' }}
+{%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{- '<|im_start|>assistant\n' }}
+{%- if enable_thinking is not defined or not enable_thinking %}
+{{- '<think>\n\n</think>\n\n' }}
+{%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/checkpoint-112/optimizer.pt b/checkpoint-112/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4f13a82e04a651a4d51c410e1c34b1940b5c5f96
--- /dev/null
+++ b/checkpoint-112/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d9d02eb8faa93c286245dd87e44f89d7493a04e910ebc9c429e3b2d8c2ab27
+size 2770239667
diff --git a/checkpoint-112/rng_state_0.pth b/checkpoint-112/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9c7bdd8049d433e97434c4c05be0936c45c5a2e3
--- /dev/null
+++ b/checkpoint-112/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77424b2b07c8e5b4675376c4643d82f3371bb993b555bd752bb639a7096417e4
+size 16389
diff --git a/checkpoint-112/rng_state_1.pth b/checkpoint-112/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..972b4c3e3667b8c1457c5f3f9f4d5c5032c37387
--- /dev/null
+++ b/checkpoint-112/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d46e5d71988eb8f672ba850c534ce412b438a2dd704457d3fa7c8781681ff1
+size 16389
diff --git a/checkpoint-112/rng_state_10.pth b/checkpoint-112/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..af6db7ee6b07aec4c20a1ccf2c098ae32a19929d
--- /dev/null
+++ b/checkpoint-112/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb9ff6df797cee3d03833055235c7db4f02557171346c56f78bfc82a85bd262
+size 16404
diff --git a/checkpoint-112/rng_state_11.pth b/checkpoint-112/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6ce03c44ba5689aa7cee2ebb779e7f1e4e57c055
--- /dev/null
+++ b/checkpoint-112/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20850eb8f3f6c6d404573616f368071ddd256d2fc7ea49020a4d392c23328e03
+size 16404
diff --git a/checkpoint-112/rng_state_12.pth b/checkpoint-112/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..74203cd0a0ec08421aa3ffe059e8c669e6db4485
--- /dev/null
+++ b/checkpoint-112/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281c784192c63206dc0e362dc3225a28e9c2f4529c34808b48f4494efe2eecc5
+size 16404
diff --git a/checkpoint-112/rng_state_13.pth b/checkpoint-112/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7bc2b8049160840584b05887d5631e9d06b3950b
--- /dev/null
+++ b/checkpoint-112/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ac7d489bd057cba8debc19c0edaa1503d5a8f7159ae738faefc723f0f4298b
+size 16404
diff --git a/checkpoint-112/rng_state_14.pth b/checkpoint-112/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..341e0ed482caea3a75f0528df05e78239654347f
--- /dev/null
+++ b/checkpoint-112/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ff2a81c3bb91ac4464f8c932ec6d8cf4fac1b4d90d854e764d56affa6ad03a
+size 16404
diff --git a/checkpoint-112/rng_state_15.pth b/checkpoint-112/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5244e8fa97d1dfaafaecd5d9c18b586a601a5f62
--- /dev/null
+++ b/checkpoint-112/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb0b1b472d659cf979d75f367ca3bf50caa0353fc432691602e2aca6a6a6e9d
+size 16404
diff --git a/checkpoint-112/rng_state_16.pth b/checkpoint-112/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0a3b92b3f500074a1d3edcf8cb2b08b71b77151b
--- /dev/null
+++ b/checkpoint-112/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f555da7c4de67aa8e8239829e4f5a7473820fa33497de77f70e519dc896cd0
+size 16404
diff --git a/checkpoint-112/rng_state_17.pth b/checkpoint-112/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2eeebbb3fca57f7011ba25cda2d530833eba44f8
--- /dev/null
+++ b/checkpoint-112/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09908590e0f9c61389025500abdc3b8fe5f39874681858146cda2db568a177a8
+size 16404
diff --git a/checkpoint-112/rng_state_18.pth b/checkpoint-112/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8ee21f03421dcb39b25f5cc0f0eedfd9959ccc27
--- /dev/null
+++ b/checkpoint-112/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323d6dbc70dffc430f838825f5e0e5536375805d4fae49ae1ebb26a4c8f65355
+size 16404
diff --git a/checkpoint-112/rng_state_19.pth b/checkpoint-112/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9f858a9e941866dc4ab7a71adb61303e613ebffd
--- /dev/null
+++ b/checkpoint-112/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3511e3b8d2736bd51248ae60cb74729d8c24c986f3242fca19719ba155471c34
+size 16404
diff --git a/checkpoint-112/rng_state_2.pth b/checkpoint-112/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ff5d90e3db858be0ce7d8c63c34cafc729149458
--- /dev/null
+++ b/checkpoint-112/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2786f9330e1d9ef43c1f63c8877e5bf8e5264fb03af25e465f66bd64a503dd
+size 16389
diff --git a/checkpoint-112/rng_state_20.pth b/checkpoint-112/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..56a91b515e113d808cc56374396c6141cf1b4083
--- /dev/null
+++ b/checkpoint-112/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9acbdab816961bf957de7e854c632e2eaaea4c1b68dba4fb296fed0fcd1fcf7
+size 16404
diff --git a/checkpoint-112/rng_state_21.pth b/checkpoint-112/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93b16013e558158e66947b60dc944372b2cc60c6
--- /dev/null
+++ b/checkpoint-112/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f82297360cf7de1fc9f91242a820bfe734eb5774febfdea2e591b3bcf49523
+size 16404
diff --git a/checkpoint-112/rng_state_22.pth b/checkpoint-112/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..99974a667ebff3fd5eae8863bc16d31985ce37fe
--- /dev/null
+++ b/checkpoint-112/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62d84ec62a4df598c099c2a73630d3f7f2a34d2cdd73cdbbf6f9cc9c36f98d2
+size 16404
diff --git a/checkpoint-112/rng_state_23.pth b/checkpoint-112/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..81a90f314ae3eeea0f4673f99d2e020e50530d0e
--- /dev/null
+++ b/checkpoint-112/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656839b97e9ead22246949c6fde1818422a3096e0dfd3b43e859334ebdc4cf18
+size 16404
diff --git a/checkpoint-112/rng_state_24.pth b/checkpoint-112/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..75b0f3a0f7ee94491e2ba6383a8fc8fd95bd6021
--- /dev/null
+++ b/checkpoint-112/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c43b37f64e09a4948a88ccc165ef92d72b1c30dd24c8d1d552329f66314dae
+size 16404
diff --git a/checkpoint-112/rng_state_25.pth b/checkpoint-112/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9ee56e112a17b4d79cc5cd2ca3b9eb9ad59015f1
--- /dev/null
+++ b/checkpoint-112/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b19692aabb4931563116dc7077df08671681aeb0b4cd35d5fc536ebc024b85
+size 16404
diff --git a/checkpoint-112/rng_state_26.pth b/checkpoint-112/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b872a5ccfdfd163b783ed8a1e6b86aad204ac645
--- /dev/null
+++ b/checkpoint-112/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e3290b0e88a8c7a89e2cb2b874f2d8b2c1a40907a2e70727d05fa81c52889c
+size 16404
diff --git a/checkpoint-112/rng_state_27.pth b/checkpoint-112/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6ae2319d60a318740a4ccf481fbf799d4d296470
--- /dev/null
+++ b/checkpoint-112/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c477f9a5a35839c04838a5dbc629b527617a8a6752292d3261c1eea9b548430
+size 16404
diff --git a/checkpoint-112/rng_state_28.pth b/checkpoint-112/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6e656d2a5d91446521369325031db5622490f011
--- /dev/null
+++ b/checkpoint-112/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1ae6aaa9fd33634b5dbdce8d04513be654b6593575a29f8f422fdcf79193b7
+size 16404
diff --git a/checkpoint-112/rng_state_29.pth b/checkpoint-112/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9c42007a6c0e1f9a8dd10b232deeb167cd94f6c1
--- /dev/null
+++ b/checkpoint-112/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59382d4d1dd54ee3269c81b4cbfe3f471154350e2fee5240eb3226bab11fdf1
+size 16404
diff --git a/checkpoint-112/rng_state_3.pth b/checkpoint-112/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0ae8ad47d61e73873028596ebaa9ed72d6514236
--- /dev/null
+++ b/checkpoint-112/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6f094fb893ce2355b223440b49e07530b489127249b9d363a81ad95b4b262d
+size 16389
diff --git a/checkpoint-112/rng_state_30.pth b/checkpoint-112/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..993b7aa0021de34d772af146fa4be5c07260b768
--- /dev/null
+++ b/checkpoint-112/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f5412e51bf0a9e0d840d584ff58636c0f3e23a4e0f8013aff65ba78da9818f
+size 16404
diff --git a/checkpoint-112/rng_state_31.pth b/checkpoint-112/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9ebd39f46814ba4e7b98355eee44f4fc6f098b74
--- /dev/null
+++ b/checkpoint-112/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f757703dc2924b5f92a79d3218c8cb61f0509251334148886b95b2598980bfb
+size 16404
diff --git a/checkpoint-112/rng_state_4.pth b/checkpoint-112/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d8a690204f050fad879345d05f569a648e25d151
--- /dev/null
+++ b/checkpoint-112/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62da14b97afe16248d325d283f887ee8047e6ef96b752da876b16bb39082783
+size 16389
diff --git a/checkpoint-112/rng_state_5.pth b/checkpoint-112/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0eacc180b5985ed425a420c32731c1d37454df2a
--- /dev/null
+++ b/checkpoint-112/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2458520a48ba78684fb2dcbc06b2022ebdc5d40f70d4dbf6cfc579aed54f3e3b
+size 16389
diff --git a/checkpoint-112/rng_state_6.pth b/checkpoint-112/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b2ed048c3d9a36872b6cb86417bf0ea707bb27b2
--- /dev/null
+++ b/checkpoint-112/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7d10f336a4f86807d4ded688acf8b286333e2cfd79dd28aa5c87af419d7de9
+size 16389
diff --git a/checkpoint-112/rng_state_7.pth b/checkpoint-112/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6628c3cd17cc66feec01fa6fe127b48c8ffd1941
--- /dev/null
+++ b/checkpoint-112/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52290b826ebd6a58216d849a95754d080fcfe43447cce9572a00e2e25c55b4c1
+size 16389
diff --git a/checkpoint-112/rng_state_8.pth b/checkpoint-112/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4b440a14800486ad6c43b40df5d1cb8dd382cefa
--- /dev/null
+++ b/checkpoint-112/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32672d5f639fc5354e7dfa64e3fcdb147d94115051d184e0f1cc0ad499ce0358
+size 16389
diff --git a/checkpoint-112/rng_state_9.pth b/checkpoint-112/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..37917bb97dc87a239b24c4d0afd7b41f3bd10feb
--- /dev/null
+++ b/checkpoint-112/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0798a798c77ef212fe79fb990e5dc286315431b8f9978ada5fa2472f068789df
+size 16389
diff --git a/checkpoint-112/scheduler.pt b/checkpoint-112/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c92d6e61052beab1003f5c74a0752f7f195bb216
--- /dev/null
+++ b/checkpoint-112/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7a90097b16bd7cf2d4794648b4c44026d56c032dd6bd65e3a539ba1d12171d
+size 1465
diff --git a/checkpoint-112/tokenizer.json b/checkpoint-112/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-112/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-112/tokenizer_config.json b/checkpoint-112/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-112/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/checkpoint-112/trainer_state.json b/checkpoint-112/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..86d555d7e5ef80407ee7f732f86491cc05699ea3
--- /dev/null
+++ b/checkpoint-112/trainer_state.json
@@ -0,0 +1,254 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7777777777777777,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.25798711776733396,
+      "epoch": 0.07936507936507936,
+      "grad_norm": 0.6395628452301025,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.33170533180236816,
+      "mean_token_accuracy": 0.9083019256591797,
+      "num_tokens": 2249744.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.1518770933151245,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.27742329239845276,
+      "learning_rate": 4.9966852247120764e-05,
+      "loss": 0.14515713453292847,
+      "mean_token_accuracy": 0.9476617932319641,
+      "num_tokens": 4502357.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.1205204889178276,
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.15280286967754364,
+      "learning_rate": 4.976460088644493e-05,
+      "loss": 0.11978392601013184,
+      "mean_token_accuracy": 0.9552689790725708,
+      "num_tokens": 6750630.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.1094709500670433,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.13621626794338226,
+      "learning_rate": 4.938000100611456e-05,
+      "loss": 0.10746543407440186,
+      "mean_token_accuracy": 0.9598726153373718,
+      "num_tokens": 8991471.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.10419090241193771,
+      "epoch": 0.3968253968253968,
+      "grad_norm": 0.16320250928401947,
+      "learning_rate": 4.881588452008456e-05,
+      "loss": 0.10661067962646484,
+      "mean_token_accuracy": 0.9599695205688477,
+      "num_tokens": 11228489.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.09569432139396668,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.15873780846595764,
+      "learning_rate": 4.80764051721044e-05,
+      "loss": 0.09594419002532958,
+      "mean_token_accuracy": 0.9637031435966492,
+      "num_tokens": 13464387.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.09625398516654968,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.15297284722328186,
+      "learning_rate": 4.7167007950568505e-05,
+      "loss": 0.09495124220848083,
+      "mean_token_accuracy": 0.964220929145813,
+      "num_tokens": 15709681.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.09195081293582916,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.15219081938266754,
+      "learning_rate": 4.609438899557964e-05,
+      "loss": 0.09150891304016114,
+      "mean_token_accuracy": 0.9652478575706482,
+      "num_tokens": 17987403.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.08980809897184372,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.1412411779165268,
+      "learning_rate": 4.4866446293440626e-05,
+      "loss": 0.0898817539215088,
+      "mean_token_accuracy": 0.965602707862854,
+      "num_tokens": 20231746.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.08743101209402085,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.16695629060268402,
+      "learning_rate": 4.3492221521624174e-05,
+      "loss": 0.08715485334396363,
+      "mean_token_accuracy": 0.9668790459632873,
+      "num_tokens": 22491762.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.08765677958726883,
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.21143023669719696,
+      "learning_rate": 4.198183347243233e-05,
+      "loss": 0.08766236305236816,
+      "mean_token_accuracy": 0.9668452143669128,
+      "num_tokens": 24752715.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.08127444982528687,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.18779045343399048,
+      "learning_rate": 4.03464035455653e-05,
+      "loss": 0.08236484527587891,
+      "mean_token_accuracy": 0.9689654350280762,
+      "num_tokens": 26982538.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.07894417196512223,
+      "epoch": 1.0317460317460316,
+      "grad_norm": 0.1385810822248459,
+      "learning_rate": 3.859797385821812e-05,
+      "loss": 0.0778856873512268,
+      "mean_token_accuracy": 0.9699163198471069,
+      "num_tokens": 29221704.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.07985353171825409,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.16439372301101685,
+      "learning_rate": 3.6749418575683e-05,
+      "loss": 0.07885851860046386,
+      "mean_token_accuracy": 0.969633674621582,
+      "num_tokens": 31470338.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.07194689065217971,
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.16862133145332336,
+      "learning_rate": 3.48143491153543e-05,
+      "loss": 0.074225252866745,
+      "mean_token_accuracy": 0.9716025114059448,
+      "num_tokens": 33719303.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.07757648378610611,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.14261098206043243,
+      "learning_rate": 3.280701392214487e-05,
+      "loss": 0.07595503330230713,
+      "mean_token_accuracy": 0.9707554697990417,
+      "num_tokens": 35977913.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.07388863414525985,
+      "epoch": 1.3492063492063493,
+      "grad_norm": 0.16554316878318787,
+      "learning_rate": 3.07421935532949e-05,
+      "loss": 0.07574511766433716,
+      "mean_token_accuracy": 0.9704798936843873,
+      "num_tokens": 38220353.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.07249651849269867,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.18186147511005402,
+      "learning_rate": 2.8635091845092247e-05,
+      "loss": 0.07062947750091553,
+      "mean_token_accuracy": 0.9724894285202026,
+      "num_tokens": 40476134.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.06985943019390106,
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.13512398302555084,
+      "learning_rate": 2.650122396287371e-05,
+      "loss": 0.06756666898727418,
+      "mean_token_accuracy": 0.9738536238670349,
+      "num_tokens": 42711931.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.06709291264414788,
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.13330888748168945,
+      "learning_rate": 2.4356302158625288e-05,
+      "loss": 0.07059981226921082,
+      "mean_token_accuracy": 0.9723513960838318,
+      "num_tokens": 44948562.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06978753134608269,
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.16254326701164246,
+      "learning_rate": 2.221612007737978e-05,
+      "loss": 0.06924379467964173,
+      "mean_token_accuracy": 0.9731807231903076,
+      "num_tokens": 47194289.0,
+      "step": 105
+    },
+    {
+      "entropy": 0.06934378147125245,
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.13457117974758148,
+      "learning_rate": 2.009643646429508e-05,
+      "loss": 0.06761763095855713,
+      "mean_token_accuracy": 0.9738588094711303,
+      "num_tokens": 49437033.0,
+      "step": 110
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8070343930827244e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-112/training_args.bin b/checkpoint-112/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-112/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-120/README.md b/checkpoint-120/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-120/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-9B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-9B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.20.0
\ No newline at end of file
diff --git a/checkpoint-120/adapter_config.json b/checkpoint-120/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-120/adapter_config.json
@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "in_proj_z",
+    "v_proj",
+    "down_proj",
+    "in_proj_b",
+    "q_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-120/adapter_model.safetensors b/checkpoint-120/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0e01ec569dc7b08a897e00b7278c295189f17c29
--- /dev/null
+++ b/checkpoint-120/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:521f4ce158a57f5967dca98a2214cdfe51d41f920d61d28e1a0875d6a211565e
+size 1384975816
diff --git a/checkpoint-120/chat_template.jinja b/checkpoint-120/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-120/chat_template.jinja
@@ -0,0 +1,20 @@
+{%- if messages and messages[0].role == 'system' %}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+{%- set loop_messages = messages[1:] %}
+{%- else %}
+{%- set loop_messages = messages %}
+{%- endif %}
+{%- for message in loop_messages %}
+{{- '<|im_start|>' + message.role + '\n' }}
+{%- if message.role == 'assistant' %}
+{% generation %}{{- message.content + '<|im_end|>' }}{% endgeneration %}{{- '\n' }}
+{%- else %}
+{{- message.content + '<|im_end|>\n' }}
+{%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{- '<|im_start|>assistant\n' }}
+{%- if enable_thinking is not defined or not enable_thinking %}
+{{- '<think>\n\n</think>\n\n' }}
+{%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/checkpoint-120/optimizer.pt b/checkpoint-120/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..10caffa5fe63d34862c164790dbe366d9d93dc49
--- /dev/null
+++ b/checkpoint-120/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690156d897903199110f9f85faff412977cc3fd80e1519bcc4268237f07c4618
+size 2770239667
diff --git a/checkpoint-120/rng_state_0.pth b/checkpoint-120/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..971a5f38b733c022945c06aea7a2db239b3c4280
--- /dev/null
+++ b/checkpoint-120/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46779e40383497998adc38fe3c25a684dea1a7d822cc06af9e5f7625c95397e
+size 16389
diff --git a/checkpoint-120/rng_state_1.pth b/checkpoint-120/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..40b619fd8509985a72097b7d6754965f4b5b157b
--- /dev/null
+++ b/checkpoint-120/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d377715d09c09840db75434470968695e626651def53f3f8faeb16dd6127816
+size 16389
diff --git a/checkpoint-120/rng_state_10.pth b/checkpoint-120/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0f185935731ba84003a5016083a15f83493023d3
--- /dev/null
+++ b/checkpoint-120/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8647f5643705be67a9cf6d1762cb54f6ff9444a76eedd8c4da86c2640af341
+size 16404
diff --git a/checkpoint-120/rng_state_11.pth b/checkpoint-120/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5498683645c468164f38249faf724b9cb69bb2e0
--- /dev/null
+++ b/checkpoint-120/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535715c173d2bf2efd2a6d71780773a7d8d4e36c11114033288183a00c8cb347
+size 16404
diff --git a/checkpoint-120/rng_state_12.pth b/checkpoint-120/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a773ecf9a9d1008d9174bb2e872814bbd4a1dba5
--- /dev/null
+++ b/checkpoint-120/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ef1571d33b3ef798df62d0d8220eacf34d070fabbc1d4a0251ebe6ed4fd8ac
+size 16404
diff --git a/checkpoint-120/rng_state_13.pth b/checkpoint-120/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..49f87bca62322676065cdebc625e194e9d9ffdbf
--- /dev/null
+++ b/checkpoint-120/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980e352e44c107270766df0e4ba0b7ab3cfbc81dbfc382f119a194c552927472
+size 16404
diff --git a/checkpoint-120/rng_state_14.pth b/checkpoint-120/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3d77e7ba0fb81562034be54e3e809827e82bf045
--- /dev/null
+++ b/checkpoint-120/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b49a71d511dbc234a1e302cd39ab152ac9c527bdde02cacc702be68dbb3f41
+size 16404
diff --git a/checkpoint-120/rng_state_15.pth b/checkpoint-120/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..564b7c7937db54109357283997192ef96842d1fe
--- /dev/null
+++ b/checkpoint-120/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b665f2849e267b4610baf7b0cd347bbab2e28ce668526e27112e4db859948c
+size 16404
diff --git a/checkpoint-120/rng_state_16.pth b/checkpoint-120/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5e8ffb04c121ffacb3fc86f1c0de7a6374cdfe96
--- /dev/null
+++ b/checkpoint-120/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f5fba1193700293cb24a1008b64e686089ee98cc4ff0328de1820efe8582a3
+size 16404
diff --git a/checkpoint-120/rng_state_17.pth b/checkpoint-120/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..674e16fc28d8ce9bf3869b76350dd31cfeea85a5
--- /dev/null
+++ b/checkpoint-120/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347d552139aec08df4f4ad380b0c0d8f17de0bd7e49c96df2dfefb22ded2bed8
+size 16404
diff --git a/checkpoint-120/rng_state_18.pth b/checkpoint-120/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4fda2a6aa3a4fe33d03de0cce54c4eadfe0ac107
--- /dev/null
+++ b/checkpoint-120/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76439464976ebeede05784fb7196f3514c28c81814cd010935a153e6a378be6
+size 16404
diff --git a/checkpoint-120/rng_state_19.pth b/checkpoint-120/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..212c2ff01c933a7c6cc4f8f3581431d64cc667c8
--- /dev/null
+++ b/checkpoint-120/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a94e5c8db2b7d81e9e23ec09cb512d84488e46fab5bbe9216e7dcd16caea86
+size 16404
diff --git a/checkpoint-120/rng_state_2.pth b/checkpoint-120/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..58ff95547a1ef50e367fedb7236bb936270ba0df
--- /dev/null
+++ b/checkpoint-120/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a20cea0c2ac29b8388ca520cdf73822f18ecbf0f9f600fd85732d45f9b1fad4b
+size 16389
diff --git a/checkpoint-120/rng_state_20.pth b/checkpoint-120/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfb4e1e814b3ec7c3fbc3dceb3bea8bbcbc65d
--- /dev/null
+++ b/checkpoint-120/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75261b8c6635fe8dfab304a85e7394736c9f153858e61d30d9ba5d16645b838
+size 16404
diff --git a/checkpoint-120/rng_state_21.pth b/checkpoint-120/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..de30d5b7642de20b7924c3ca36f0e1a8aba3615b
--- /dev/null
+++ b/checkpoint-120/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13e57ced2840bc9050c7196a8ad0d9c7cb91a9f27e26eabadbed9dd45b834e5
+size 16404
diff --git a/checkpoint-120/rng_state_22.pth b/checkpoint-120/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..beb5ae6b129153f55715a9eba8317a6a87fc84d1
--- /dev/null
+++ b/checkpoint-120/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200a277f6330a38ab24ce5c5af141cf983cd03dfd3ed42f07a08c1cddf6eab86
+size 16404
diff --git a/checkpoint-120/rng_state_23.pth b/checkpoint-120/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1a3822d67548953a9ea6d66227efad18748d0eb8
--- /dev/null
+++ b/checkpoint-120/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe605b07e3669d523970c73802c8be4f6bf5fd8dce54f33e893135e27eb4b86
+size 16404
diff --git a/checkpoint-120/rng_state_24.pth b/checkpoint-120/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f00aac053ed3b7ef83b3c7c72481f030db3d160f
--- /dev/null
+++ b/checkpoint-120/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b844ca65c305a6b8dc7b31ca785580f4c598d00d48c519fda2cb462cbf1aed1
+size 16404
diff --git a/checkpoint-120/rng_state_25.pth b/checkpoint-120/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ed9ddad2bd6d3b234b2f5d2961c6dcfd19cd0d98
--- /dev/null
+++ b/checkpoint-120/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f875e6a9dfa96f657b66003d6a4bde3ccddc12b280e5bb0438fca917f3812eb5
+size 16404
diff --git a/checkpoint-120/rng_state_26.pth b/checkpoint-120/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..19e209953bc759d226b591ebfd79ac2092cbbc1a
--- /dev/null
+++ b/checkpoint-120/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9aaef817bf37c82c256838a1918587477ce542a46c592ba7d57dfc740e0ed16
+size 16404
diff --git a/checkpoint-120/rng_state_27.pth b/checkpoint-120/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3be5224bb77041a071a879aa4a261e9cfc2e666a
--- /dev/null
+++ b/checkpoint-120/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3f64a80bd931b7973149c36774914cb372175af42c775a0e3084f7f2891176
+size 16404
diff --git a/checkpoint-120/rng_state_28.pth b/checkpoint-120/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4fd3bbdd021341065401a080f6a60fe10e93510a
--- /dev/null
+++ b/checkpoint-120/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f0bcb9b60f4265d0e3c7735ea2ae86f4620adf3d236eaff830ed00918203aa
+size 16404
diff --git a/checkpoint-120/rng_state_29.pth b/checkpoint-120/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a706c41bc320b6bc0fe22ef33561cf8dd41e3bcb
--- /dev/null
+++ b/checkpoint-120/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4986216b189ab688caf378e150f9e34702bd3e7f70aafbd58c19963021fa35d2
+size 16404
diff --git a/checkpoint-120/rng_state_3.pth b/checkpoint-120/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0e37394c3dd3a7b4127498478c62ee952628e90c
--- /dev/null
+++ b/checkpoint-120/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b2442cd3c5bd1eaaee21482b9d396f843ce825465aec27622d0cd61e76bf7b
+size 16389
diff --git a/checkpoint-120/rng_state_30.pth b/checkpoint-120/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b1fed1fc48f49fa4b549f0e72bd4d8504fe7a9cc
--- /dev/null
+++ b/checkpoint-120/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9023a9e95b7d3d5567f32c1e9867cbe47f9cd3def5d8f43f0884d13107f8ad71
+size 16404
diff --git a/checkpoint-120/rng_state_31.pth b/checkpoint-120/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dec49e2ee00ac955c95687fa0de4a3d0f46f364b
--- /dev/null
+++ b/checkpoint-120/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a00d3f4b5cafd9b832bc7d0212b2e9b512188f5d134d2d1177ae320581633d
+size 16404
diff --git a/checkpoint-120/rng_state_4.pth b/checkpoint-120/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..efad40524f17207cce0639f595c16b6a718e046f
--- /dev/null
+++ b/checkpoint-120/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de59b3c5c796056ab657ae240fba208d9717223d15544672974aa84d8c9336c7
+size 16389
diff --git a/checkpoint-120/rng_state_5.pth b/checkpoint-120/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..37a57aaa3943116b59f58f5159210ea005ce4ae6
--- /dev/null
+++ b/checkpoint-120/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660d26f8406e76c42fd3f3b456ce0661e588c84078da9965e5c7b9a9e7bafdbb
+size 16389
diff --git a/checkpoint-120/rng_state_6.pth b/checkpoint-120/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fa932b5b1c3237f936d61017b83088147da36ee1
--- /dev/null
+++ b/checkpoint-120/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25846c7f0dd2b4b9931e4b7d616361a93a632f5483d9adf84e882614be082db7
+size 16389
diff --git a/checkpoint-120/rng_state_7.pth b/checkpoint-120/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5bc454f519b62b3fb1f669e3e9c972dba3e0160d
--- /dev/null
+++ b/checkpoint-120/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0c1382ce8b648bc40e90a4135fc3b58b1d16b264c8facf8ebbf22a008c3a0f4
+size 16389
diff --git a/checkpoint-120/rng_state_8.pth b/checkpoint-120/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7ccea2b711f1b5a5aa498e8d09008456bbe06195
--- /dev/null
+++ b/checkpoint-120/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926f7ebf443f2aa41c00094d31a5d2955794d7125c4940e87155422e5bc2d5e5
+size 16389
diff --git a/checkpoint-120/rng_state_9.pth b/checkpoint-120/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..23f274254798d0954f968ed996586ceb5ce0e6b4
--- /dev/null
+++ b/checkpoint-120/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c0d7e225cffa6c9443ddab16c3e330c56526be28afb0c840060b54ed877e4ba
+size 16389
diff --git a/checkpoint-120/scheduler.pt b/checkpoint-120/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3d24e452a86bd60aa2e1505f4ee71a5997b7c4b2
--- /dev/null
+++ b/checkpoint-120/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7a3d15e4d1879b9a27102a1ce0f1ce67d010151b46132d07d1783dfd6d2a1f
+size 1465
diff --git a/checkpoint-120/tokenizer.json b/checkpoint-120/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-120/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-120/tokenizer_config.json b/checkpoint-120/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-120/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/checkpoint-120/trainer_state.json b/checkpoint-120/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..31f74111f3ddce85a6df0848e4d8e0c8064fea85
--- /dev/null
+++ b/checkpoint-120/trainer_state.json
@@ -0,0 +1,274 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9047619047619047,
+  "eval_steps": 500,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.25798711776733396,
+      "epoch": 0.07936507936507936,
+      "grad_norm": 0.6395628452301025,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.33170533180236816,
+      "mean_token_accuracy": 0.9083019256591797,
+      "num_tokens": 2249744.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.1518770933151245,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.27742329239845276,
+      "learning_rate": 4.9966852247120764e-05,
+      "loss": 0.14515713453292847,
+      "mean_token_accuracy": 0.9476617932319641,
+      "num_tokens": 4502357.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.1205204889178276,
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.15280286967754364,
+      "learning_rate": 4.976460088644493e-05,
+      "loss": 0.11978392601013184,
+      "mean_token_accuracy": 0.9552689790725708,
+      "num_tokens": 6750630.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.1094709500670433,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.13621626794338226,
+      "learning_rate": 4.938000100611456e-05,
+      "loss": 0.10746543407440186,
+      "mean_token_accuracy": 0.9598726153373718,
+      "num_tokens": 8991471.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.10419090241193771,
+      "epoch": 0.3968253968253968,
+      "grad_norm": 0.16320250928401947,
+      "learning_rate": 4.881588452008456e-05,
+      "loss": 0.10661067962646484,
+      "mean_token_accuracy": 0.9599695205688477,
+      "num_tokens": 11228489.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.09569432139396668,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.15873780846595764,
+      "learning_rate": 4.80764051721044e-05,
+      "loss": 0.09594419002532958,
+      "mean_token_accuracy": 0.9637031435966492,
+      "num_tokens": 13464387.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.09625398516654968,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.15297284722328186,
+      "learning_rate": 4.7167007950568505e-05,
+      "loss": 0.09495124220848083,
+      "mean_token_accuracy": 0.964220929145813,
+      "num_tokens": 15709681.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.09195081293582916,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.15219081938266754,
+      "learning_rate": 4.609438899557964e-05,
+      "loss": 0.09150891304016114,
+      "mean_token_accuracy": 0.9652478575706482,
+      "num_tokens": 17987403.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.08980809897184372,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.1412411779165268,
+      "learning_rate": 4.4866446293440626e-05,
+      "loss": 0.0898817539215088,
+      "mean_token_accuracy": 0.965602707862854,
+      "num_tokens": 20231746.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.08743101209402085,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.16695629060268402,
+      "learning_rate": 4.3492221521624174e-05,
+      "loss": 0.08715485334396363,
+      "mean_token_accuracy": 0.9668790459632873,
+      "num_tokens": 22491762.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.08765677958726883,
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.21143023669719696,
+      "learning_rate": 4.198183347243233e-05,
+      "loss": 0.08766236305236816,
+      "mean_token_accuracy": 0.9668452143669128,
+      "num_tokens": 24752715.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.08127444982528687,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.18779045343399048,
+      "learning_rate": 4.03464035455653e-05,
+      "loss": 0.08236484527587891,
+      "mean_token_accuracy": 0.9689654350280762,
+      "num_tokens": 26982538.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.07894417196512223,
+      "epoch": 1.0317460317460316,
+      "grad_norm": 0.1385810822248459,
+      "learning_rate": 3.859797385821812e-05,
+      "loss": 0.0778856873512268,
+      "mean_token_accuracy": 0.9699163198471069,
+      "num_tokens": 29221704.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.07985353171825409,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.16439372301101685,
+      "learning_rate": 3.6749418575683e-05,
+      "loss": 0.07885851860046386,
+      "mean_token_accuracy": 0.969633674621582,
+      "num_tokens": 31470338.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.07194689065217971,
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.16862133145332336,
+      "learning_rate": 3.48143491153543e-05,
+      "loss": 0.074225252866745,
+      "mean_token_accuracy": 0.9716025114059448,
+      "num_tokens": 33719303.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.07757648378610611,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.14261098206043243,
+      "learning_rate": 3.280701392214487e-05,
+      "loss": 0.07595503330230713,
+      "mean_token_accuracy": 0.9707554697990417,
+      "num_tokens": 35977913.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.07388863414525985,
+      "epoch": 1.3492063492063493,
+      "grad_norm": 0.16554316878318787,
+      "learning_rate": 3.07421935532949e-05,
+      "loss": 0.07574511766433716,
+      "mean_token_accuracy": 0.9704798936843873,
+      "num_tokens": 38220353.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.07249651849269867,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.18186147511005402,
+      "learning_rate": 2.8635091845092247e-05,
+      "loss": 0.07062947750091553,
+      "mean_token_accuracy": 0.9724894285202026,
+      "num_tokens": 40476134.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.06985943019390106,
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.13512398302555084,
+      "learning_rate": 2.650122396287371e-05,
+      "loss": 0.06756666898727418,
+      "mean_token_accuracy": 0.9738536238670349,
+      "num_tokens": 42711931.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.06709291264414788,
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.13330888748168945,
+      "learning_rate": 2.4356302158625288e-05,
+      "loss": 0.07059981226921082,
+      "mean_token_accuracy": 0.9723513960838318,
+      "num_tokens": 44948562.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06978753134608269,
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.16254326701164246,
+      "learning_rate": 2.221612007737978e-05,
+      "loss": 0.06924379467964173,
+      "mean_token_accuracy": 0.9731807231903076,
+      "num_tokens": 47194289.0,
+      "step": 105
+    },
+    {
+      "entropy": 0.06934378147125245,
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.13457117974758148,
+      "learning_rate": 2.009643646429508e-05,
+      "loss": 0.06761763095855713,
+      "mean_token_accuracy": 0.9738588094711303,
+      "num_tokens": 49437033.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.06849471032619477,
+      "epoch": 1.8253968253968254,
+      "grad_norm": 0.14807309210300446,
+      "learning_rate": 1.8012859128709766e-05,
+      "loss": 0.06851363182067871,
+      "mean_token_accuracy": 0.9734799265861511,
+      "num_tokens": 51685754.0,
+      "step": 115
+    },
+    {
+      "entropy": 0.06743545532226562,
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.14509981870651245,
+      "learning_rate": 1.598073001958042e-05,
+      "loss": 0.06817712187767029,
+      "mean_token_accuracy": 0.9735557198524475,
+      "num_tokens": 53931825.0,
+      "step": 120
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.0077956643073556e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-120/training_args.bin b/checkpoint-120/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-120/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-128/README.md b/checkpoint-128/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-128/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-9B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-9B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.20.0
\ No newline at end of file
diff --git a/checkpoint-128/adapter_config.json b/checkpoint-128/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-128/adapter_config.json
@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "in_proj_z",
+    "v_proj",
+    "down_proj",
+    "in_proj_b",
+    "q_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-128/adapter_model.safetensors b/checkpoint-128/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..deee0d20530dc6b49534520f8dcce5fffdc64f84
--- /dev/null
+++ b/checkpoint-128/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c31a685bc81b4a26e525ca01504f340cb1e026fe33bdbeda0700872d0b7533
+size 1384975816
diff --git a/checkpoint-128/chat_template.jinja b/checkpoint-128/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-128/chat_template.jinja
@@ -0,0 +1,20 @@
+{%- if messages and messages[0].role == 'system' %}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+{%- set loop_messages = messages[1:] %}
+{%- else %}
+{%- set loop_messages = messages %}
+{%- endif %}
+{%- for message in loop_messages %}
+{{- '<|im_start|>' + message.role + '\n' }}
+{%- if message.role == 'assistant' %}
+{% generation %}{{- message.content + '<|im_end|>' }}{% endgeneration %}{{- '\n' }}
+{%- else %}
+{{- message.content + '<|im_end|>\n' }}
+{%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{- '<|im_start|>assistant\n' }}
+{%- if enable_thinking is not defined or not enable_thinking %}
+{{- '<think>\n\n</think>\n\n' }}
+{%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/checkpoint-128/optimizer.pt b/checkpoint-128/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9989b6ae5518f3f447306c1de351c95bfbcf3b3c
--- /dev/null
+++ b/checkpoint-128/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df205919d9ce1a2d9fef238cf53b719babc7f3a6e2595669ca688588a4c0d570
+size 2770239667
diff --git a/checkpoint-128/rng_state_0.pth b/checkpoint-128/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..267a356258ff50284b2ff7e4ee5e6c90086a449e
--- /dev/null
+++ b/checkpoint-128/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08754eddd6aa7189e9b2d27e508ecc665cf0a6622bc1f5f7138799b2bc14c804
+size 16389
diff --git a/checkpoint-128/rng_state_1.pth b/checkpoint-128/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..86c7ef56b10f8936bafee1e18f314396cfaa9456
--- /dev/null
+++ b/checkpoint-128/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d0410a9dab6b5e709bb72c4308b7580bec6a88e170ff444f6a0e44bfa7c3bf
+size 16389
diff --git a/checkpoint-128/rng_state_10.pth b/checkpoint-128/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..808fa520f3de592c434f7a8978704bdc3cd6f6db
--- /dev/null
+++ b/checkpoint-128/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:967aea0f1e7592cff77efa150483abcab3b129ed52c5eb51e39b0a9937d1f531
+size 16404
diff --git a/checkpoint-128/rng_state_11.pth b/checkpoint-128/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..721261122f3e0964025d4c15f9cb7920dc449667
--- /dev/null
+++ b/checkpoint-128/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9613f546a83b771d4f198cd7b163ef89ba140fef6614cc521c4b91dc49201537
+size 16404
diff --git a/checkpoint-128/rng_state_12.pth b/checkpoint-128/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d2f069bc0c894d665aab774fec2c6148834fefd6
--- /dev/null
+++ b/checkpoint-128/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18448db47cbf7b7b925b0763c3aebd039af76011aa6c466521a89c011f726a46
+size 16404
diff --git a/checkpoint-128/rng_state_13.pth b/checkpoint-128/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b692b6ccd25e84d6eef3b1c7c68d03d5bcbcd28b
--- /dev/null
+++ b/checkpoint-128/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055ef25a6db1c809a2996ce7496d679a94e6cec5a2765afe6ee49c5c84caf2e3
+size 16404
diff --git a/checkpoint-128/rng_state_14.pth b/checkpoint-128/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a94ab4f533ad76aa19b5f32e419e6ee4dc6ceb59
--- /dev/null
+++ b/checkpoint-128/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6219117c5b9847fe8d3863f2d019c2fc136319f355fce0788a750a7568f3343
+size 16404
diff --git a/checkpoint-128/rng_state_15.pth b/checkpoint-128/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2a669444d5e80fe5538485057f50a764c937ab54
--- /dev/null
+++ b/checkpoint-128/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f3992f35ef87010b7c81bc594b2c7dd0c283f3eefa2cab9ce0a5970d6ccbe2
+size 16404
diff --git a/checkpoint-128/rng_state_16.pth b/checkpoint-128/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a6f950b18931df9ba5a1d7fa3577dbf5b33735b9
--- /dev/null
+++ b/checkpoint-128/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82fc6a435b0485733f2612688562da4683e5e65c7b625f11a054d939da48332
+size 16404
diff --git a/checkpoint-128/rng_state_17.pth b/checkpoint-128/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..42aecdae350e9ccc6be0a33b4a5478b99e684a7a
--- /dev/null
+++ b/checkpoint-128/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd1844f6ea6668409bf5afe9d6db7450848b91de78536aa9a5f026dd153f73a
+size 16404
diff --git a/checkpoint-128/rng_state_18.pth b/checkpoint-128/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..996e23452597fc48877356cfff314af27f578f77
--- /dev/null
+++ b/checkpoint-128/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84fb0e1e1d6d89e33c6de27db5a76266c037118e2b1b7d81507b245009d42e54
+size 16404
diff --git a/checkpoint-128/rng_state_19.pth b/checkpoint-128/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a9b03df540cca0068cf95d22a48efc35a79c6a3e
--- /dev/null
+++ b/checkpoint-128/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8dd903c867b53db71d42e1664e35cd7458fe8db06c4b0114a9287115534460
+size 16404
diff --git a/checkpoint-128/rng_state_2.pth b/checkpoint-128/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c762cf3f77c2417cf6f81b2d2ce0c8e3b0f46c97
--- /dev/null
+++ b/checkpoint-128/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868a44af43f851c2edf03a8d9bf2ce25f29a7a00a7f0f7ec0fa525a7ea09c2cb
+size 16389
diff --git a/checkpoint-128/rng_state_20.pth b/checkpoint-128/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..da62730e9ed2137dfbdea488b9c34549dc3762df
--- /dev/null
+++ b/checkpoint-128/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8377279ed425dd3fd2f287a535bf19d4a10769dabd8c662a501be426c646db1c
+size 16404
diff --git a/checkpoint-128/rng_state_21.pth b/checkpoint-128/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b5dfb138f621bb616b400fa8083dc05fc99fd888
--- /dev/null
+++ b/checkpoint-128/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce408da3ddf3bd67624e08c5a7ec01dfd6e7b067b2357c2bc8b3e1fd9dfbdfc3
+size 16404
diff --git a/checkpoint-128/rng_state_22.pth b/checkpoint-128/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1c9bbcc28b29c87ec0a40d673e7e72f01619b336
--- /dev/null
+++ b/checkpoint-128/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a560b65b8131a5b01a618c0777ddf8e9de304a723772731f7373a774c4bf410
+size 16404
diff --git a/checkpoint-128/rng_state_23.pth b/checkpoint-128/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8f34c21f62753cd0fd7ab704233430ef0f252ee2
--- /dev/null
+++ b/checkpoint-128/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5c385b2a14cb18095a4ca97dc6b805d0d07f27ecf76732802a2b1b964af167
+size 16404
diff --git a/checkpoint-128/rng_state_24.pth b/checkpoint-128/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b18f3254641753a9ba440951f68664e378cc8f9a
--- /dev/null
+++ b/checkpoint-128/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a94a4a1bbccfb155833911b886ee9a5b7f21314e3072bf55e0d71cf2afbf8d
+size 16404
diff --git a/checkpoint-128/rng_state_25.pth b/checkpoint-128/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6e11ea5caad6f248fc810ecc76b87c3050bed85f
--- /dev/null
+++ b/checkpoint-128/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e65fa5e6b1368804afe9dd7735ae270719a3d5d3f61fad522e93d1bfa44fcc
+size 16404
diff --git a/checkpoint-128/rng_state_26.pth b/checkpoint-128/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..468b8dfd1515207659488778d558609519605ffe
--- /dev/null
+++ b/checkpoint-128/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b939e9cdfd299b06e1de261eefda6cfd159641742c4f5ef26e707414764f3b
+size 16404
diff --git a/checkpoint-128/rng_state_27.pth b/checkpoint-128/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..047666ace8baf92c9b758193c7cb5d1c9bf71769
--- /dev/null
+++ b/checkpoint-128/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d45eb4dc06a12d056a44c74fb26602c5977eace83f27d4d968c18063ce2f0a
+size 16404
diff --git a/checkpoint-128/rng_state_28.pth b/checkpoint-128/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4bbcb99dc43d108367413bee150aaa5b25ec70fb
--- /dev/null
+++ b/checkpoint-128/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d729c45006729f1ab8b7fcaa65b5aece23aa60c7d0a2382c79b98b993afb6b
+size 16404
diff --git a/checkpoint-128/rng_state_29.pth b/checkpoint-128/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0edf9b3aaf447e1d1f053b5bacb60548e824e665
--- /dev/null
+++ b/checkpoint-128/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc572c9c5b8cf608200f6df76eaa1df4a4f159d72e7fffd1a9c78a28fec65c1
+size 16404
diff --git a/checkpoint-128/rng_state_3.pth b/checkpoint-128/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fddd71eff74f5bc02bbb9521639620d0b9998ac3
--- /dev/null
+++ b/checkpoint-128/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57add51fd19bf68b6a561fce0c31cead23c7c1703078a4d4a959371caf589727
+size 16389
diff --git a/checkpoint-128/rng_state_30.pth b/checkpoint-128/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2aa81abb7cdd9c173ddd2953366dfb230e8116f4
--- /dev/null
+++ b/checkpoint-128/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448328a40e6fe4d7b1324be4d7b38411d0c84fb4c34d416d8c26aaca5a26c8f2
+size 16404
diff --git a/checkpoint-128/rng_state_31.pth b/checkpoint-128/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..28d94e6bb78ec80d831e61dcb4449d0d07a444db
--- /dev/null
+++ b/checkpoint-128/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f3cfea7adf3d1d2b358914b0c3f423f37f1143663415d9eaa136fe09e59ee6
+size 16404
diff --git a/checkpoint-128/rng_state_4.pth b/checkpoint-128/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4c3ba5ed93e87eac9fa594724f0d2b9587b89133
--- /dev/null
+++ b/checkpoint-128/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e181310a733f54bb01f20c674a2b356d695397ce0af3b98c060c9f8062ae4a0d
+size 16389
diff --git a/checkpoint-128/rng_state_5.pth b/checkpoint-128/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..55c24802237cbc7368a9f4f4a4d72e434bddc196
--- /dev/null
+++ b/checkpoint-128/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d99dd2b95108375d98accd463a1576dc2c026752182c93eab99b96ec3557918
+size 16389
diff --git a/checkpoint-128/rng_state_6.pth b/checkpoint-128/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fcaf27acb2b010fae144d0486f67406ef9e1a87e
--- /dev/null
+++ b/checkpoint-128/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1173f600e2fd0500dab422ae7c6400b74e4f6551e821235547076acaedbb454d
+size 16389
diff --git a/checkpoint-128/rng_state_7.pth b/checkpoint-128/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9da86095443b36bf93982924e7f9cd3419b3aac1
--- /dev/null
+++ b/checkpoint-128/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5622c117ce36a5477431ab6c0859428986bf298082ffe10b38f968b2ec8f45f
+size 16389
diff --git a/checkpoint-128/rng_state_8.pth b/checkpoint-128/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7859d22ef3c2b6ded28b0d267580a9e14520138a
--- /dev/null
+++ b/checkpoint-128/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc5a09cf245876a987083ec3b8f3ad5c324e8b201195d43f172c27517828ee6
+size 16389
diff --git a/checkpoint-128/rng_state_9.pth b/checkpoint-128/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fd0ba55229fa47c53c0a087ab1928ee57e176f07
--- /dev/null
+++ b/checkpoint-128/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b31b07cc793b552b847a7dd6ab14240e409e53ca4c01c14084dc3de94af9cf
+size 16389
diff --git a/checkpoint-128/scheduler.pt b/checkpoint-128/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a7f07ba83aab0ae8c155a9cebfa2d938ccd7e8ed
--- /dev/null
+++ b/checkpoint-128/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a0800b0a5254f770edd819773e502b3a46cb2b3b162d2a5779b28b2756bc27
+size 1465
diff --git a/checkpoint-128/tokenizer.json b/checkpoint-128/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-128/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-128/tokenizer_config.json b/checkpoint-128/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-128/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/checkpoint-128/trainer_state.json b/checkpoint-128/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ba7d55ed25d70461b9567a5cbe3de9c43ebd4df6
--- /dev/null
+++ b/checkpoint-128/trainer_state.json
@@ -0,0 +1,284 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0317460317460316,
+  "eval_steps": 500,
+  "global_step": 128,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.25798711776733396,
+      "epoch": 0.07936507936507936,
+      "grad_norm": 0.6395628452301025,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.33170533180236816,
+      "mean_token_accuracy": 0.9083019256591797,
+      "num_tokens": 2249744.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.1518770933151245,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.27742329239845276,
+      "learning_rate": 4.9966852247120764e-05,
+      "loss": 0.14515713453292847,
+      "mean_token_accuracy": 0.9476617932319641,
+      "num_tokens": 4502357.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.1205204889178276,
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.15280286967754364,
+      "learning_rate": 4.976460088644493e-05,
+      "loss": 0.11978392601013184,
+      "mean_token_accuracy": 0.9552689790725708,
+      "num_tokens": 6750630.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.1094709500670433,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.13621626794338226,
+      "learning_rate": 4.938000100611456e-05,
+      "loss": 0.10746543407440186,
+      "mean_token_accuracy": 0.9598726153373718,
+      "num_tokens": 8991471.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.10419090241193771,
+      "epoch": 0.3968253968253968,
+      "grad_norm": 0.16320250928401947,
+      "learning_rate": 4.881588452008456e-05,
+      "loss": 0.10661067962646484,
+      "mean_token_accuracy": 0.9599695205688477,
+      "num_tokens": 11228489.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.09569432139396668,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.15873780846595764,
+      "learning_rate": 4.80764051721044e-05,
+      "loss": 0.09594419002532958,
+      "mean_token_accuracy": 0.9637031435966492,
+      "num_tokens": 13464387.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.09625398516654968,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.15297284722328186,
+      "learning_rate": 4.7167007950568505e-05,
+      "loss": 0.09495124220848083,
+      "mean_token_accuracy": 0.964220929145813,
+      "num_tokens": 15709681.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.09195081293582916,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.15219081938266754,
+      "learning_rate": 4.609438899557964e-05,
+      "loss": 0.09150891304016114,
+      "mean_token_accuracy": 0.9652478575706482,
+      "num_tokens": 17987403.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.08980809897184372,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.1412411779165268,
+      "learning_rate": 4.4866446293440626e-05,
+      "loss": 0.0898817539215088,
+      "mean_token_accuracy": 0.965602707862854,
+      "num_tokens": 20231746.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.08743101209402085,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.16695629060268402,
+      "learning_rate": 4.3492221521624174e-05,
+      "loss": 0.08715485334396363,
+      "mean_token_accuracy": 0.9668790459632873,
+      "num_tokens": 22491762.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.08765677958726883,
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.21143023669719696,
+      "learning_rate": 4.198183347243233e-05,
+      "loss": 0.08766236305236816,
+      "mean_token_accuracy": 0.9668452143669128,
+      "num_tokens": 24752715.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.08127444982528687,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.18779045343399048,
+      "learning_rate": 4.03464035455653e-05,
+      "loss": 0.08236484527587891,
+      "mean_token_accuracy": 0.9689654350280762,
+      "num_tokens": 26982538.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.07894417196512223,
+      "epoch": 1.0317460317460316,
+      "grad_norm": 0.1385810822248459,
+      "learning_rate": 3.859797385821812e-05,
+      "loss": 0.0778856873512268,
+      "mean_token_accuracy": 0.9699163198471069,
+      "num_tokens": 29221704.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.07985353171825409,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.16439372301101685,
+      "learning_rate": 3.6749418575683e-05,
+      "loss": 0.07885851860046386,
+      "mean_token_accuracy": 0.969633674621582,
+      "num_tokens": 31470338.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.07194689065217971,
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.16862133145332336,
+      "learning_rate": 3.48143491153543e-05,
+      "loss": 0.074225252866745,
+      "mean_token_accuracy": 0.9716025114059448,
+      "num_tokens": 33719303.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.07757648378610611,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.14261098206043243,
+      "learning_rate": 3.280701392214487e-05,
+      "loss": 0.07595503330230713,
+      "mean_token_accuracy": 0.9707554697990417,
+      "num_tokens": 35977913.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.07388863414525985,
+      "epoch": 1.3492063492063493,
+      "grad_norm": 0.16554316878318787,
+      "learning_rate": 3.07421935532949e-05,
+      "loss": 0.07574511766433716,
+      "mean_token_accuracy": 0.9704798936843873,
+      "num_tokens": 38220353.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.07249651849269867,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.18186147511005402,
+      "learning_rate": 2.8635091845092247e-05,
+      "loss": 0.07062947750091553,
+      "mean_token_accuracy": 0.9724894285202026,
+      "num_tokens": 40476134.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.06985943019390106,
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.13512398302555084,
+      "learning_rate": 2.650122396287371e-05,
+      "loss": 0.06756666898727418,
+      "mean_token_accuracy": 0.9738536238670349,
+      "num_tokens": 42711931.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.06709291264414788,
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.13330888748168945,
+      "learning_rate": 2.4356302158625288e-05,
+      "loss": 0.07059981226921082,
+      "mean_token_accuracy": 0.9723513960838318,
+      "num_tokens": 44948562.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06978753134608269,
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.16254326701164246,
+      "learning_rate": 2.221612007737978e-05,
+      "loss": 0.06924379467964173,
+      "mean_token_accuracy": 0.9731807231903076,
+      "num_tokens": 47194289.0,
+      "step": 105
+    },
+    {
+      "entropy": 0.06934378147125245,
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.13457117974758148,
+      "learning_rate": 2.009643646429508e-05,
+      "loss": 0.06761763095855713,
+      "mean_token_accuracy": 0.9738588094711303,
+      "num_tokens": 49437033.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.06849471032619477,
+      "epoch": 1.8253968253968254,
+      "grad_norm": 0.14807309210300446,
+      "learning_rate": 1.8012859128709766e-05,
+      "loss": 0.06851363182067871,
+      "mean_token_accuracy": 0.9734799265861511,
+      "num_tokens": 51685754.0,
+      "step": 115
+    },
+    {
+      "entropy": 0.06743545532226562,
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.14509981870651245,
+      "learning_rate": 1.598073001958042e-05,
+      "loss": 0.06817712187767029,
+      "mean_token_accuracy": 0.9735557198524475,
+      "num_tokens": 53931825.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.06640436649322509,
+      "epoch": 1.9841269841269842,
+      "grad_norm": 0.13425911962985992,
+      "learning_rate": 1.4015012258521454e-05,
+      "loss": 0.0663202166557312,
+      "mean_token_accuracy": 0.9740958571434021,
+      "num_tokens": 56203400.0,
+      "step": 125
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.208974389173289e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-128/training_args.bin b/checkpoint-128/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-128/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-136/README.md b/checkpoint-136/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-136/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-9B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-9B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.20.0
\ No newline at end of file
diff --git a/checkpoint-136/adapter_config.json b/checkpoint-136/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-136/adapter_config.json
@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "in_proj_z",
+    "v_proj",
+    "down_proj",
+    "in_proj_b",
+    "q_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-136/adapter_model.safetensors b/checkpoint-136/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5dc538d7a161dc17983a8b472591314a5f358bd3
--- /dev/null
+++ b/checkpoint-136/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9990d50fa4d4cebcb17d3766fab953be0727338d45ad4291eecd67dc2978a542
+size 1384975816
diff --git a/checkpoint-136/chat_template.jinja b/checkpoint-136/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-136/chat_template.jinja
@@ -0,0 +1,20 @@
+{%- if messages and messages[0].role == 'system' %}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+{%- set loop_messages = messages[1:] %}
+{%- else %}
+{%- set loop_messages = messages %}
+{%- endif %}
+{%- for message in loop_messages %}
+{{- '<|im_start|>' + message.role + '\n' }}
+{%- if message.role == 'assistant' %}
+{% generation %}{{- message.content + '<|im_end|>' }}{% endgeneration %}{{- '\n' }}
+{%- else %}
+{{- message.content + '<|im_end|>\n' }}
+{%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{- '<|im_start|>assistant\n' }}
+{%- if enable_thinking is not defined or not enable_thinking %}
+{{- '<think>\n\n</think>\n\n' }}
+{%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/checkpoint-136/optimizer.pt b/checkpoint-136/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..abc072ba3ec58db08c0c0df2a42cda86edf60167
--- /dev/null
+++ b/checkpoint-136/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb21f33ef8e6af7f9dd89fa4875ab229d68726d326cc3f048323cd76762c9be
+size 2770239667
diff --git a/checkpoint-136/rng_state_0.pth b/checkpoint-136/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d059c3f0933f64e841fb4ac4584d07b43c7f5a74
--- /dev/null
+++ b/checkpoint-136/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3755c23e82ee537e5128a49b56065611af6a5501b938b98fa58db1aaffc881
+size 16389
diff --git a/checkpoint-136/rng_state_1.pth b/checkpoint-136/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e69df0efeaad8c404b7854f535c99810d442f5ed
--- /dev/null
+++ b/checkpoint-136/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e8599ed5018888c6ce1d25b158060aba124246ed652348664295b14c6f4823a
+size 16389
diff --git a/checkpoint-136/rng_state_10.pth b/checkpoint-136/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..35497a4e91f4e9c485f8bb374d7638696f5535f3
--- /dev/null
+++ b/checkpoint-136/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd6c6d505ec27a0996482e9e0f83b906001a60c9a984b36e9072f24be18072c
+size 16404
diff --git a/checkpoint-136/rng_state_11.pth b/checkpoint-136/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7ba86d99a427942e79dd96f49951f64630d6165c
--- /dev/null
+++ b/checkpoint-136/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462c666df2008501eef7e3d12c36d086b4d445a65af15f2c4781a7dd3c6a0fb0
+size 16404
diff --git a/checkpoint-136/rng_state_12.pth b/checkpoint-136/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3913ae68fabbfa6fb7c0ff2ed060d8a539acd671
--- /dev/null
+++ b/checkpoint-136/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61d8d851156138b9c06ea1b1c4ce7be43824ed0bff3b56c156dbd7d2a52433c
+size 16404
diff --git a/checkpoint-136/rng_state_13.pth b/checkpoint-136/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..66161c50d0f51d04c60fe29e1b98a48dc4565463
--- /dev/null
+++ b/checkpoint-136/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b509dc85d5540d27d30f670ca8b33d3391842b4d883b1754a36fd07d89040714
+size 16404
diff --git a/checkpoint-136/rng_state_14.pth b/checkpoint-136/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1375d3d7f1da72527dfdac8b292e66693253ecb5
--- /dev/null
+++ b/checkpoint-136/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549446adaf1a2139abb13c153ce0a07db3c5307ce97b33b44098d73e9c4598f8
+size 16404
diff --git a/checkpoint-136/rng_state_15.pth b/checkpoint-136/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..21f0584ce368d15d43af66998d1a747b42b783bb
--- /dev/null
+++ b/checkpoint-136/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d30926e70b7b29db61d24ebcd91c718105301517cd8d62294312a9c5b790b7b
+size 16404
diff --git a/checkpoint-136/rng_state_16.pth b/checkpoint-136/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d5c3d6d1bedf39e200cb6fa39298f397bc444bfb
--- /dev/null
+++ b/checkpoint-136/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8b6a448612ac9ff8a09abad1fa74bc8b6260e5e6648cfde4e82b508aaa5e73
+size 16404
diff --git a/checkpoint-136/rng_state_17.pth b/checkpoint-136/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4b070fa72a7d853faa0112e35b44652ae3a916d9
--- /dev/null
+++ b/checkpoint-136/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:202666d3e027e5b6678c1ddb631669a32818983c346cd8ef62d83e4b338d2f82
+size 16404
diff --git a/checkpoint-136/rng_state_18.pth b/checkpoint-136/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4e14c3e0907da5a103421d53ec5f89750e31a296
--- /dev/null
+++ b/checkpoint-136/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9fe753f2c8ee7bc8d7cda1b0cc8d65863d252086c6df8a34fdb12e5ba5fb61
+size 16404
diff --git a/checkpoint-136/rng_state_19.pth b/checkpoint-136/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..20f180efc5fbba65c14b3d38c243ab31e9e4a11a
--- /dev/null
+++ b/checkpoint-136/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2384c007d7521e40ad15563df8b28e96a13e1429d84721eead12d3db900a5679
+size 16404
diff --git a/checkpoint-136/rng_state_2.pth b/checkpoint-136/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cf6a2020659e27148c3db89a1c5e37ac77dd8105
--- /dev/null
+++ b/checkpoint-136/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b7f982dc1b6f584a5c458abbf1071813ec2e6ff25682cf06afabab846ab7c3
+size 16389
diff --git a/checkpoint-136/rng_state_20.pth b/checkpoint-136/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..de75279f3c597162ff26140152a7d0b8291a7ebf
--- /dev/null
+++ b/checkpoint-136/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b162025a0673eb39e21ab3b9eadd130ddb8475baacc180e1810475dca0be24
+size 16404
diff --git a/checkpoint-136/rng_state_21.pth b/checkpoint-136/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a626a2bc3725e20bc19bf65ea7ba6057876fda81
--- /dev/null
+++ b/checkpoint-136/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e1b338780c4a295444d5b83a921989d47844315753f984da7607562591264b
+size 16404
diff --git a/checkpoint-136/rng_state_22.pth b/checkpoint-136/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2892ad745a385520bfb197aed7b28247ce99717b
--- /dev/null
+++ b/checkpoint-136/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a9db8b8362b7c5358838fda5bff0077efcb99a59d88a2225a42edb65a166b7
+size 16404
diff --git a/checkpoint-136/rng_state_23.pth b/checkpoint-136/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3b2a4ca4eab0795d1f5e0b0706a5565ae1db5421
--- /dev/null
+++ b/checkpoint-136/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:035297e8e65e5fa57d9b77ff3c6968b57ef5d9469e3ea806a9805736a53ef92a
+size 16404
diff --git a/checkpoint-136/rng_state_24.pth b/checkpoint-136/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a1f67563810c791076b4760f662afc96f38480c6
--- /dev/null
+++ b/checkpoint-136/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7f7ed1e8139ecbd3ec99a526ff706f3873d4de691ed830d845a19399c3eed8
+size 16404
diff --git a/checkpoint-136/rng_state_25.pth b/checkpoint-136/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8c7b72f0e18fe9d486e38e576d083a1955d0ca97
--- /dev/null
+++ b/checkpoint-136/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab70f18b06226c36a01a4f3f54b16d0ebcdacf8258ba345d219715563139e451
+size 16404
diff --git a/checkpoint-136/rng_state_26.pth b/checkpoint-136/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..276813a8648d61220708fff65c02fc9c4bda0163
--- /dev/null
+++ b/checkpoint-136/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d748b7f647e672740743e0ff1b5c63c725b714e9274b8f55e895c4f4a526500e
+size 16404
diff --git a/checkpoint-136/rng_state_27.pth b/checkpoint-136/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f0daede979c19a5711a9169eaba5f00035f015bb
--- /dev/null
+++ b/checkpoint-136/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ec4d496e5cccaa7cfbe9909582972232b7d7dd8e32d10af393b16377d327d6
+size 16404
diff --git a/checkpoint-136/rng_state_28.pth b/checkpoint-136/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3a1cfaf5dc054a64c42bf95b3a6455d5012cb7f7
--- /dev/null
+++ b/checkpoint-136/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007191118463c42000deaa1ad476df5dfd7b8bfe4eb22328f284f76f590735d7
+size 16404
diff --git a/checkpoint-136/rng_state_29.pth b/checkpoint-136/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f653dfe9ce92aadc01dd129fb9cd197df2847f16
--- /dev/null
+++ b/checkpoint-136/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6756cfbe82e6c836fba8d08cf4416e4a72e64d9b0dbce9d707647c9186394a3
+size 16404
diff --git a/checkpoint-136/rng_state_3.pth b/checkpoint-136/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9628425bb01d3315b5800d9047b1fb6f443eb725
--- /dev/null
+++ b/checkpoint-136/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5ea62d6ad97427665b19302a5ec893e58a1d80928c5d098f8da4e02fdb2b66
+size 16389
diff --git a/checkpoint-136/rng_state_30.pth b/checkpoint-136/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..800670505f32c2831cb33cf9a240d55ab1212b87
--- /dev/null
+++ b/checkpoint-136/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cca4540ffdfbcda68ff55ae9672753226e4ed80980bf22013f1576d9d675ca7
+size 16404
diff --git a/checkpoint-136/rng_state_31.pth b/checkpoint-136/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cc22b552b363209e46680499bfdb379a1dc2029f
--- /dev/null
+++ b/checkpoint-136/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ccb3dd7f1f2032a6d20b008ac9066dd1b1da553cd2336c2bc41c881b051e215
+size 16404
diff --git a/checkpoint-136/rng_state_4.pth b/checkpoint-136/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0c3c32b97dcb797e4c610d7a30b4718cf984c268
--- /dev/null
+++ b/checkpoint-136/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0853f7a6e7394f570512a6cc64d5d3475eea19414a92c80f1730ce84d5b36240
+size 16389
diff --git a/checkpoint-136/rng_state_5.pth b/checkpoint-136/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..03000ebdb7168959f586ca827295e234ceba2711
--- /dev/null
+++ b/checkpoint-136/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad645f70b2668b84064b2516f7be0b625ff7c9036810fb2dd3b2a19da72e7487
+size 16389
diff --git a/checkpoint-136/rng_state_6.pth b/checkpoint-136/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..09ec8dc81cfe7c052928e197a17c38dcbd1bb492
--- /dev/null
+++ b/checkpoint-136/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd47e1fadee7853d27e2ceb3227f8a6c745aa976a6df67a99040d77b3a41a9c
+size 16389
diff --git a/checkpoint-136/rng_state_7.pth b/checkpoint-136/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..34bd8f382fcf01d3c1e1f86f258210eb920924bc
--- /dev/null
+++ b/checkpoint-136/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6142a89e8a0a6cb72eeeddc41b5cc7826a758900617187867261a45ed9fdd5d9
+size 16389
diff --git a/checkpoint-136/rng_state_8.pth b/checkpoint-136/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..09051be9672c27ce695b80d992b96e0730b633ae
--- /dev/null
+++ b/checkpoint-136/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487bccb79b57598475bd70e64ce7f6e578f9da1d1b5502c1b88b1e3cb51ad3c9
+size 16389
diff --git a/checkpoint-136/rng_state_9.pth b/checkpoint-136/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..335ae253ca343681b0295b9b80913a7cf8da3324
--- /dev/null
+++ b/checkpoint-136/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d08c44399386af0d0138ae511bb5190c12805cf5cdda7b843b53b99fe66a16
+size 16389
diff --git a/checkpoint-136/scheduler.pt b/checkpoint-136/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..90a026a978e074a2c3706902195f5ef97d62c0f2
--- /dev/null
+++ b/checkpoint-136/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e850150a4d6cfb07bc072ec9be48eeb994d9134b82f90d96d46916a70e4fdb7f
+size 1465
diff --git a/checkpoint-136/tokenizer.json b/checkpoint-136/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-136/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-136/tokenizer_config.json b/checkpoint-136/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-136/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/checkpoint-136/trainer_state.json b/checkpoint-136/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..86fa3fcb24de13377b453d17a4fef94195c0f24e
--- /dev/null
+++ b/checkpoint-136/trainer_state.json
@@ -0,0 +1,304 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.1587301587301586,
+  "eval_steps": 500,
+  "global_step": 136,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.25798711776733396,
+      "epoch": 0.07936507936507936,
+      "grad_norm": 0.6395628452301025,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.33170533180236816,
+      "mean_token_accuracy": 0.9083019256591797,
+      "num_tokens": 2249744.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.1518770933151245,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.27742329239845276,
+      "learning_rate": 4.9966852247120764e-05,
+      "loss": 0.14515713453292847,
+      "mean_token_accuracy": 0.9476617932319641,
+      "num_tokens": 4502357.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.1205204889178276,
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.15280286967754364,
+      "learning_rate": 4.976460088644493e-05,
+      "loss": 0.11978392601013184,
+      "mean_token_accuracy": 0.9552689790725708,
+      "num_tokens": 6750630.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.1094709500670433,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.13621626794338226,
+      "learning_rate": 4.938000100611456e-05,
+      "loss": 0.10746543407440186,
+      "mean_token_accuracy": 0.9598726153373718,
+      "num_tokens": 8991471.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.10419090241193771,
+      "epoch": 0.3968253968253968,
+      "grad_norm": 0.16320250928401947,
+      "learning_rate": 4.881588452008456e-05,
+      "loss": 0.10661067962646484,
+      "mean_token_accuracy": 0.9599695205688477,
+      "num_tokens": 11228489.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.09569432139396668,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.15873780846595764,
+      "learning_rate": 4.80764051721044e-05,
+      "loss": 0.09594419002532958,
+      "mean_token_accuracy": 0.9637031435966492,
+      "num_tokens": 13464387.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.09625398516654968,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.15297284722328186,
+      "learning_rate": 4.7167007950568505e-05,
+      "loss": 0.09495124220848083,
+      "mean_token_accuracy": 0.964220929145813,
+      "num_tokens": 15709681.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.09195081293582916,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.15219081938266754,
+      "learning_rate": 4.609438899557964e-05,
+      "loss": 0.09150891304016114,
+      "mean_token_accuracy": 0.9652478575706482,
+      "num_tokens": 17987403.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.08980809897184372,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.1412411779165268,
+      "learning_rate": 4.4866446293440626e-05,
+      "loss": 0.0898817539215088,
+      "mean_token_accuracy": 0.965602707862854,
+      "num_tokens": 20231746.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.08743101209402085,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.16695629060268402,
+      "learning_rate": 4.3492221521624174e-05,
+      "loss": 0.08715485334396363,
+      "mean_token_accuracy": 0.9668790459632873,
+      "num_tokens": 22491762.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.08765677958726883,
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.21143023669719696,
+      "learning_rate": 4.198183347243233e-05,
+      "loss": 0.08766236305236816,
+      "mean_token_accuracy": 0.9668452143669128,
+      "num_tokens": 24752715.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.08127444982528687,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.18779045343399048,
+      "learning_rate": 4.03464035455653e-05,
+      "loss": 0.08236484527587891,
+      "mean_token_accuracy": 0.9689654350280762,
+      "num_tokens": 26982538.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.07894417196512223,
+      "epoch": 1.0317460317460316,
+      "grad_norm": 0.1385810822248459,
+      "learning_rate": 3.859797385821812e-05,
+      "loss": 0.0778856873512268,
+      "mean_token_accuracy": 0.9699163198471069,
+      "num_tokens": 29221704.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.07985353171825409,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.16439372301101685,
+      "learning_rate": 3.6749418575683e-05,
+      "loss": 0.07885851860046386,
+      "mean_token_accuracy": 0.969633674621582,
+      "num_tokens": 31470338.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.07194689065217971,
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.16862133145332336,
+      "learning_rate": 3.48143491153543e-05,
+      "loss": 0.074225252866745,
+      "mean_token_accuracy": 0.9716025114059448,
+      "num_tokens": 33719303.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.07757648378610611,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.14261098206043243,
+      "learning_rate": 3.280701392214487e-05,
+      "loss": 0.07595503330230713,
+      "mean_token_accuracy": 0.9707554697990417,
+      "num_tokens": 35977913.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.07388863414525985,
+      "epoch": 1.3492063492063493,
+      "grad_norm": 0.16554316878318787,
+      "learning_rate": 3.07421935532949e-05,
+      "loss": 0.07574511766433716,
+      "mean_token_accuracy": 0.9704798936843873,
+      "num_tokens": 38220353.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.07249651849269867,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.18186147511005402,
+      "learning_rate": 2.8635091845092247e-05,
+      "loss": 0.07062947750091553,
+      "mean_token_accuracy": 0.9724894285202026,
+      "num_tokens": 40476134.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.06985943019390106,
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.13512398302555084,
+      "learning_rate": 2.650122396287371e-05,
+      "loss": 0.06756666898727418,
+      "mean_token_accuracy": 0.9738536238670349,
+      "num_tokens": 42711931.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.06709291264414788,
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.13330888748168945,
+      "learning_rate": 2.4356302158625288e-05,
+      "loss": 0.07059981226921082,
+      "mean_token_accuracy": 0.9723513960838318,
+      "num_tokens": 44948562.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06978753134608269,
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.16254326701164246,
+      "learning_rate": 2.221612007737978e-05,
+      "loss": 0.06924379467964173,
+      "mean_token_accuracy": 0.9731807231903076,
+      "num_tokens": 47194289.0,
+      "step": 105
+    },
+    {
+      "entropy": 0.06934378147125245,
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.13457117974758148,
+      "learning_rate": 2.009643646429508e-05,
+      "loss": 0.06761763095855713,
+      "mean_token_accuracy": 0.9738588094711303,
+      "num_tokens": 49437033.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.06849471032619477,
+      "epoch": 1.8253968253968254,
+      "grad_norm": 0.14807309210300446,
+      "learning_rate": 1.8012859128709766e-05,
+      "loss": 0.06851363182067871,
+      "mean_token_accuracy": 0.9734799265861511,
+      "num_tokens": 51685754.0,
+      "step": 115
+    },
+    {
+      "entropy": 0.06743545532226562,
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.14509981870651245,
+      "learning_rate": 1.598073001958042e-05,
+      "loss": 0.06817712187767029,
+      "mean_token_accuracy": 0.9735557198524475,
+      "num_tokens": 53931825.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.06640436649322509,
+      "epoch": 1.9841269841269842,
+      "grad_norm": 0.13425911962985992,
+      "learning_rate": 1.4015012258521454e-05,
+      "loss": 0.0663202166557312,
+      "mean_token_accuracy": 0.9740958571434021,
+      "num_tokens": 56203400.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.06114112734794617,
+      "epoch": 2.0634920634920633,
+      "grad_norm": 0.14675261080265045,
+      "learning_rate": 1.213017996225424e-05,
+      "loss": 0.0597736656665802,
+      "mean_token_accuracy": 0.9770057320594787,
+      "num_tokens": 58447264.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.06077109202742577,
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.14722956717014313,
+      "learning_rate": 1.034011166573261e-05,
+      "loss": 0.0608077347278595,
+      "mean_token_accuracy": 0.9764052987098694,
+      "num_tokens": 60680203.0,
+      "step": 135
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.4084109185376584e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-136/training_args.bin b/checkpoint-136/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-136/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-144/README.md b/checkpoint-144/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-144/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-9B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-9B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.20.0
\ No newline at end of file
diff --git a/checkpoint-144/adapter_config.json b/checkpoint-144/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-144/adapter_config.json
@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "in_proj_z",
+    "v_proj",
+    "down_proj",
+    "in_proj_b",
+    "q_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-144/adapter_model.safetensors b/checkpoint-144/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..88ed61c1dd376cebd0bcf8af79c5b35b5730e4d3
--- /dev/null
+++ b/checkpoint-144/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dafbd6b9a907823bb6cabaf73123a215d64512695a35623892d6a402370b74ba
+size 1384975816
diff --git a/checkpoint-144/chat_template.jinja b/checkpoint-144/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-144/chat_template.jinja
@@ -0,0 +1,20 @@
+{%- if messages and messages[0].role == 'system' %}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+{%- set loop_messages = messages[1:] %}
+{%- else %}
+{%- set loop_messages = messages %}
+{%- endif %}
+{%- for message in loop_messages %}
+{{- '<|im_start|>' + message.role + '\n' }}
+{%- if message.role == 'assistant' %}
+{% generation %}{{- message.content + '<|im_end|>' }}{% endgeneration %}{{- '\n' }}
+{%- else %}
+{{- message.content + '<|im_end|>\n' }}
+{%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{- '<|im_start|>assistant\n' }}
+{%- if enable_thinking is not defined or not enable_thinking %}
+{{- '<think>\n\n</think>\n\n' }}
+{%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/checkpoint-144/optimizer.pt b/checkpoint-144/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..54d3e976e8b993ed0fd176fab1b559194af0a0f6
--- /dev/null
+++ b/checkpoint-144/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c012d825d08d695e6cfc70e5b921d81fa4513d1f9cb5809d133a17fc43e320fc
+size 2770239667
diff --git a/checkpoint-144/rng_state_0.pth b/checkpoint-144/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..75510aec2f23e7bdebfa1a6412e77bf15a282892
--- /dev/null
+++ b/checkpoint-144/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47aab7fe42f5f01aa03d598e71e18b4974cea9b76d6f14c05d729981329f7b83
+size 16389
diff --git a/checkpoint-144/rng_state_1.pth b/checkpoint-144/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..baf4d50425e62c3f88158507b737dfc30c31e047
--- /dev/null
+++ b/checkpoint-144/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84093957fa59eba04ba855127bcea8a12d50f9f41d674b38777be86cc21482dd
+size 16389
diff --git a/checkpoint-144/rng_state_10.pth b/checkpoint-144/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b418cce802be3a64923562cf519583ee67aae3b7
--- /dev/null
+++ b/checkpoint-144/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95fb6dd8b552fda92512eea11de9e131a16a5d04b98157d6f61eab8911d43a3f
+size 16404
diff --git a/checkpoint-144/rng_state_11.pth b/checkpoint-144/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fb9f41e66caab36b54a0a47b8e29e8a5a8d13702
--- /dev/null
+++ b/checkpoint-144/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf5d7fd2df483274db5e10b91bb1914b65f217c74aafa9ae0751ab31312a9c2
+size 16404
diff --git a/checkpoint-144/rng_state_12.pth b/checkpoint-144/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ccc8064f98a48cd27da77cdf003b821e9f48516b
--- /dev/null
+++ b/checkpoint-144/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28532fffce3a2fdab8c7150f86f5b57774a7efae4856293aad09238e67567704
+size 16404
diff --git a/checkpoint-144/rng_state_13.pth b/checkpoint-144/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1263f36a7d9fcdcf4010cf9da22e7f9d32f9d514
--- /dev/null
+++ b/checkpoint-144/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74358aba14bdc24f37dde7b153ea65819b4b292efc50a1bbe3d0b549a4589dbc
+size 16404
diff --git a/checkpoint-144/rng_state_14.pth b/checkpoint-144/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..35223a8224af678984691b165ec9521b117c3b44
--- /dev/null
+++ b/checkpoint-144/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cbf08548f3e172bc523ded8e22867c47de7ef840d0cd13364f85c85b37c18e1
+size 16404
diff --git a/checkpoint-144/rng_state_15.pth b/checkpoint-144/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4eea952bba328d2b4ce954ebc35c7153b2109d72
--- /dev/null
+++ b/checkpoint-144/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1783fd571b000e9699dfe755896bc0d68895606f7768cc075f46c2f51d938cfa
+size 16404
diff --git a/checkpoint-144/rng_state_16.pth b/checkpoint-144/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..40a29cbb1ee1805b90e96bc87b5f94504c0e9078
--- /dev/null
+++ b/checkpoint-144/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91c2cfdb2beacd5115857516064af1546e74a02ba0372d8f7b60097898beee0
+size 16404
diff --git a/checkpoint-144/rng_state_17.pth b/checkpoint-144/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..489be222da1b327388529b3a23a87303c97290c2
--- /dev/null
+++ b/checkpoint-144/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366a5590b42445ea3a3fdddeaeb5d8456331ad89b82d00573cc27a8c3e6c2e80
+size 16404
diff --git a/checkpoint-144/rng_state_18.pth b/checkpoint-144/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b3ebc4316fe0a66bff6bb3035f4b16cd6c21c250
--- /dev/null
+++ b/checkpoint-144/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acaf774ebd7bbf960593f7fbfe0ed3ba36c3755cf0067c646fc7215852448614
+size 16404
diff --git a/checkpoint-144/rng_state_19.pth b/checkpoint-144/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..81fbd789413946251a19b2c52d01d56798889061
--- /dev/null
+++ b/checkpoint-144/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc2c4437007654601ea99e329d24a2800d3c8991ea748f1b2d9ca68cc823198
+size 16404
diff --git a/checkpoint-144/rng_state_2.pth b/checkpoint-144/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9557f1a8fe551914d3571c53b4bc120ea997f4f1
--- /dev/null
+++ b/checkpoint-144/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c221b629a447f7a6d47d213a823fab9f65ab0bb6da56d7d6846570cc812e45
+size 16389
diff --git a/checkpoint-144/rng_state_20.pth b/checkpoint-144/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c675472312ca15a515b01d4c8efc07339c026b23
--- /dev/null
+++ b/checkpoint-144/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5f35ef4104ce274e920f69d0d6d48cc4491f21c174ae82f666f3f02f309cd2
+size 16404
diff --git a/checkpoint-144/rng_state_21.pth b/checkpoint-144/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a8f5a2d120a4162481765fdcedace7e2c1aff070
--- /dev/null
+++ b/checkpoint-144/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21c1d03028d6e64091f351df5e36a515f9426cdee8277ac0a7c55956bf3e5c3
+size 16404
diff --git a/checkpoint-144/rng_state_22.pth b/checkpoint-144/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2ad9bed7f387a745095cc57e60372bee8fd07f0f
--- /dev/null
+++ b/checkpoint-144/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78752110a1a50886f86732c1cd1c903d111ba61d7d786b07f93121a50068379
+size 16404
diff --git a/checkpoint-144/rng_state_23.pth b/checkpoint-144/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..184ecf509f93e8eac34939ebd160868e50705b22
--- /dev/null
+++ b/checkpoint-144/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4220be3e19a45d57adb1a43cc55a1936b1f139adda3feb445b6c172f79c1aa5e
+size 16404
diff --git a/checkpoint-144/rng_state_24.pth b/checkpoint-144/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..45bdcb4812adb6f58bafa2394149222fb81cffea
--- /dev/null
+++ b/checkpoint-144/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6b842800e660d9606d5b16d8fa03e582b9a8e338f68f35f004adc6a679cbd4
+size 16404
diff --git a/checkpoint-144/rng_state_25.pth b/checkpoint-144/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3ebc5fa3e69515dfc35156ab93eebe516bab36b0
--- /dev/null
+++ b/checkpoint-144/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1433bb4f6b4fc93ce07070ced4524ffc98efb80a9281b3f92c748f399c025383
+size 16404
diff --git a/checkpoint-144/rng_state_26.pth b/checkpoint-144/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bd23edf1808859662232c38d5c4d8fc4e8f6b88f
--- /dev/null
+++ b/checkpoint-144/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac89cd1b990020de4dbab5a8517a3ea791a774a3bf5c768bcb6f236fbe3c2cd2
+size 16404
diff --git a/checkpoint-144/rng_state_27.pth b/checkpoint-144/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5b1627dd844a33e8bb5176e4c33420d29b57a077
--- /dev/null
+++ b/checkpoint-144/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6daab10f63f738345576a26885053885e1845686c8479895ed762af97cccb85b
+size 16404
diff --git a/checkpoint-144/rng_state_28.pth b/checkpoint-144/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..898b5c30292cf39d8275c7273d39f06093cb52c3
--- /dev/null
+++ b/checkpoint-144/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c81549a7925868d83a0c00c684d6da3b922c3ac8ab1eeeeca0cf066766c87b
+size 16404
diff --git a/checkpoint-144/rng_state_29.pth b/checkpoint-144/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4edb7a0ea304e8f43097194da7b109a4a8d57168
--- /dev/null
+++ b/checkpoint-144/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3936c7c2d9cab6c227f1a0f139ffcbeaa79150af1fb9a888af605551dfde3b99
+size 16404
diff --git a/checkpoint-144/rng_state_3.pth b/checkpoint-144/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..99caa2d806748a6c08661c7c5ec0eecb4056ccb9
--- /dev/null
+++ b/checkpoint-144/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc4ccd7b87b255b3af35dc7aab94dbd015e9ec21765402f0615efeb627f590e
+size 16389
diff --git a/checkpoint-144/rng_state_30.pth b/checkpoint-144/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b90179cc5890a81060c2d2cf93958b587449abab
--- /dev/null
+++ b/checkpoint-144/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702dd3abdde8c66ef41f48cd068aab25f6be8482d56c72f9f6c31b2bb095bc5b
+size 16404
diff --git a/checkpoint-144/rng_state_31.pth b/checkpoint-144/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..416e9f8c8c302484856d27798186e3fddce6b740
--- /dev/null
+++ b/checkpoint-144/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71229c1efd41738f97a4c26ecedd21ca02a7f3bb311bc732e6bfbba0736e594d
+size 16404
diff --git a/checkpoint-144/rng_state_4.pth b/checkpoint-144/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..31b3fe6e411c9e3d089c7a9be8b9b5e8de315523
--- /dev/null
+++ b/checkpoint-144/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7daeeb1765e76d839b0193df68c5b6081321a1ac8de94e183b2e8ec9fde281be
+size 16389
diff --git a/checkpoint-144/rng_state_5.pth b/checkpoint-144/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..742c7481e9043474c20638c5ccc96373c5c18dea
--- /dev/null
+++ b/checkpoint-144/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f269a6b9413a63ad681e34f5decf57afaf67bf26c5f1c9b9297ad40e3d3ce7
+size 16389
diff --git a/checkpoint-144/rng_state_6.pth b/checkpoint-144/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..418dc92f8d02abdcf5c6a5bafe807100f370519b
--- /dev/null
+++ b/checkpoint-144/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69137ede5a7e6207c8c2486a38c27fd1a0c38666d5b2b5185d7d93faf33b79cf
+size 16389
diff --git a/checkpoint-144/rng_state_7.pth b/checkpoint-144/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..063130e17160e048b541a32772fa5abc877c6ef9
--- /dev/null
+++ b/checkpoint-144/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab19b01669b5eac34b3552877f4a69d88c67a333064a89fc30e2078f26bb0ff6
+size 16389
diff --git a/checkpoint-144/rng_state_8.pth b/checkpoint-144/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a81050c1e8d459c89009eab520c452fb1d2e401c
--- /dev/null
+++ b/checkpoint-144/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d6ade5b9acbebaf19ae906bc0c9ca6a5baa57a12b27e773fa3daa7b30471c5
+size 16389