diff --git a/checkpoint-144/rng_state_9.pth b/checkpoint-144/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..91e5b41d42ecde6096ece89532658f70019244c6
--- /dev/null
+++ b/checkpoint-144/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e0c53baa10c3f7bbc797afed620014c3354dc6129887af72ebe4af802a276cd
+size 16389
diff --git a/checkpoint-144/scheduler.pt b/checkpoint-144/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..88cc4237cb4509196c883730aeb37a962641009e
--- /dev/null
+++ b/checkpoint-144/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e974a563b4cf2d7b155094f237d692b5403539b809b4c68386103d62a66cb31
+size 1465
diff --git a/checkpoint-144/tokenizer.json b/checkpoint-144/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-144/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-144/tokenizer_config.json b/checkpoint-144/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-144/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-144/trainer_state.json b/checkpoint-144/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d228854011793a37dc6af26869a890cfe2fdb92f
--- /dev/null
+++ b/checkpoint-144/trainer_state.json
@@ -0,0 +1,314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2857142857142856,
+  "eval_steps": 500,
+  "global_step": 144,
+  "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
+    },
+    {
+      "entropy": 0.06085996180772781,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.13919851183891296,
+      "learning_rate": 8.657988130699848e-06,
+      "loss": 0.06093168258666992,
+      "mean_token_accuracy": 0.975907814502716,
+      "num_tokens": 62928491.0,
+      "step": 140
+    }
+  ],
+  "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": 3.609685068986974e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-144/training_args.bin b/checkpoint-144/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-144/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-152/README.md b/checkpoint-152/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-152/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-152/adapter_config.json b/checkpoint-152/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-152/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-152/adapter_model.safetensors b/checkpoint-152/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9fb4887a63d5f9fca90b6bba21d50221119f74ca
--- /dev/null
+++ b/checkpoint-152/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2edaaecd98438b73a28926cd659fddc9f4e4865a69ba1def5ebcfd05c984d74c
+size 1384975816
diff --git a/checkpoint-152/chat_template.jinja b/checkpoint-152/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-152/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-152/optimizer.pt b/checkpoint-152/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e8955ca9f3b09c392e62724bb915a18703d93250
--- /dev/null
+++ b/checkpoint-152/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68d0948e0c8288b7cf572516c525c40ce29cb4e29acc35f7c4587d517f978c0
+size 2770239667
diff --git a/checkpoint-152/rng_state_0.pth b/checkpoint-152/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f435bbd63ed08d8a088ea27706c5f745afe9e6c8
--- /dev/null
+++ b/checkpoint-152/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b30b11d9f33d91c7bcf02e341a59ac6524a8a360e2083b5676a78e25596c0e
+size 16389
diff --git a/checkpoint-152/rng_state_1.pth b/checkpoint-152/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..419cb3f75cf774971ed64159a0a5d408286b89ea
--- /dev/null
+++ b/checkpoint-152/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8380d4da325f3707ff76c2f787f61ea3b1de18bd17c61a9c3ce75b1d988b2e28
+size 16389
diff --git a/checkpoint-152/rng_state_10.pth b/checkpoint-152/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..59565995213c5626e589639968fbb39f1679036c
--- /dev/null
+++ b/checkpoint-152/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:971dfe429ee3fe6ecebc3dbb9f6b0c994c43220c9790f030592bd8f5031dd1b1
+size 16404
diff --git a/checkpoint-152/rng_state_11.pth b/checkpoint-152/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..94df89347b2ceef408eebbfe5845f47ad8f8ad1f
--- /dev/null
+++ b/checkpoint-152/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8660952010354e1f5125288961973ceac30d62cc3ee56b27ac81229d7d5d06b3
+size 16404
diff --git a/checkpoint-152/rng_state_12.pth b/checkpoint-152/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ff00ed414b41c3ef6df0c87daaa2c8c4c4a3aac4
--- /dev/null
+++ b/checkpoint-152/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c24f89ad476fbe08d7eb735c901e7af0f3c049afe8e1c200cf3554b147fc742
+size 16404
diff --git a/checkpoint-152/rng_state_13.pth b/checkpoint-152/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cac315f64cbceab9114bf589c2e4e3fe48fc6846
--- /dev/null
+++ b/checkpoint-152/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0300c025a31d2a5f87c32cd300912e8fe9c329915328dc97dbb16f6a346d102d
+size 16404
diff --git a/checkpoint-152/rng_state_14.pth b/checkpoint-152/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e102c2df3562626237bc8f26918cb748d4761f7d
--- /dev/null
+++ b/checkpoint-152/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd3753d31ac7cf44f403ea011af585c1167b70ab879e2373690486374eafd52e
+size 16404
diff --git a/checkpoint-152/rng_state_15.pth b/checkpoint-152/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..05ff8106b5b7cc63cd8611d3ed7502649bbfd280
--- /dev/null
+++ b/checkpoint-152/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36bb39d7b59ef27b42d259e6d9ff6830e100f6f445ab49a6ac3e88d4dd0bbdc
+size 16404
diff --git a/checkpoint-152/rng_state_16.pth b/checkpoint-152/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5a984b10a6254a686d33b8e37a1d32410c9db00d
--- /dev/null
+++ b/checkpoint-152/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810c0bcff19f59474412ea63bbe668ad3f83670b28ed13645c7396a762777f02
+size 16404
diff --git a/checkpoint-152/rng_state_17.pth b/checkpoint-152/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..978c5fe9f197b3d4c5c1ba7ec41e9ff77714878d
--- /dev/null
+++ b/checkpoint-152/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39520afbd6d1613ab8382b740bedec4b68194c807f7d54bc54bc816c7c14002a
+size 16404
diff --git a/checkpoint-152/rng_state_18.pth b/checkpoint-152/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a49a52170bf361d075ce8bdbe2e6c0567971c48c
--- /dev/null
+++ b/checkpoint-152/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5ac19fa5636053e53fdcb668ce1a5d3cba1c1a6e5d1056bf05c2935b3bd074
+size 16404
diff --git a/checkpoint-152/rng_state_19.pth b/checkpoint-152/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9142f720778b9207e05d5cabd6d2512287ef82ce
--- /dev/null
+++ b/checkpoint-152/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e97609728ca998827635cb1b4cb23b0536833993870f1c8a0d8ea7fc66bf429
+size 16404
diff --git a/checkpoint-152/rng_state_2.pth b/checkpoint-152/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..69652fdae5977a3faf26ed28a6d7cb5a0fc83182
--- /dev/null
+++ b/checkpoint-152/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5927461517cbfca54f3318107f1f73e6a46ca4e7789b90f41f7c888cb1bcbc5b
+size 16389
diff --git a/checkpoint-152/rng_state_20.pth b/checkpoint-152/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..395b7a068552023056d2862f1fa497c95e737777
--- /dev/null
+++ b/checkpoint-152/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a4885228c3c9037416abdbab65690ce75e28493983f91f123ea4a0a20553f0
+size 16404
diff --git a/checkpoint-152/rng_state_21.pth b/checkpoint-152/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..092acea8979c907043c94c0fda4feceef5b17676
--- /dev/null
+++ b/checkpoint-152/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f240687e3aaa70f4cae52421a4b28fffc5b85c39a01d9a5f878518d4a74fa590
+size 16404
diff --git a/checkpoint-152/rng_state_22.pth b/checkpoint-152/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..be6edeb65e5a62a0591d9e2763ab58c53b5da72c
--- /dev/null
+++ b/checkpoint-152/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2cb504adc16869e88d7ece06d13e48e2331628b32b4d057e9e15c8a2a3a76ff
+size 16404
diff --git a/checkpoint-152/rng_state_23.pth b/checkpoint-152/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9791f37831eef92bb04554bd3e2b03dd21db20ec
--- /dev/null
+++ b/checkpoint-152/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3cbc24cc8e00c9f724d8d99ecd2c9ec370dcb5a41c9c09047272a83fe0ba68
+size 16404
diff --git a/checkpoint-152/rng_state_24.pth b/checkpoint-152/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1629746c65899c501c744510bf0d8a9c9873fe90
--- /dev/null
+++ b/checkpoint-152/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453f1afbc3bc83a8b1f349ad34c336866183508f3dbae1dda497b72b7ffc12ff
+size 16404
diff --git a/checkpoint-152/rng_state_25.pth b/checkpoint-152/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cb41dedfb45858c7a88b2079bab19f12ef297c58
--- /dev/null
+++ b/checkpoint-152/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba1c6c5443ad94f98d4b9452586470f24f17909271d3e4d06dc820d5fcb87df
+size 16404
diff --git a/checkpoint-152/rng_state_26.pth b/checkpoint-152/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..06216c66e290d6383cccda8ab5e22bb91f4f932d
--- /dev/null
+++ b/checkpoint-152/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509a644b57548ceb7eb5edb75eef7bbdc7f34a4721bb9852f7445c8b5e9e32b8
+size 16404
diff --git a/checkpoint-152/rng_state_27.pth b/checkpoint-152/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ac57eccb00bacf66ff7dc564ed98fd69e51f5b65
--- /dev/null
+++ b/checkpoint-152/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a54cc3124146e218df0907aca6c13747459de14572b13cc77b7a02568bd6e9
+size 16404
diff --git a/checkpoint-152/rng_state_28.pth b/checkpoint-152/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e63b1fd199d9471c2256210446106384bcf96cfb
--- /dev/null
+++ b/checkpoint-152/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541aa0d50af4827c96bbe92db001502b56436edf643ae852b4dfc40efc7590c4
+size 16404
diff --git a/checkpoint-152/rng_state_29.pth b/checkpoint-152/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f0f9a1bb90e5acb8ae7d7ce185478c87516aa926
--- /dev/null
+++ b/checkpoint-152/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92eb096c79f83ad338af93fead4452ce6f9d4f6bc90808601f4debf9e0c4ad29
+size 16404
diff --git a/checkpoint-152/rng_state_3.pth b/checkpoint-152/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..00b1c66313c0b54ef0730e3db0fe5c06a82f68ac
--- /dev/null
+++ b/checkpoint-152/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25441b8817383163c1f117d4cc028ea819ca9563b2f8487c2d2c441e959f49cd
+size 16389
diff --git a/checkpoint-152/rng_state_30.pth b/checkpoint-152/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d13a5313f09ac5f60e4223a1cce3367e3bab07a8
--- /dev/null
+++ b/checkpoint-152/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33888fc4467183272841759a1fa7cb0dddc02dcf1a15f1f36d60d978a6884d4
+size 16404
diff --git a/checkpoint-152/rng_state_31.pth b/checkpoint-152/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..30a34bf25a0521cf1109a76137ec290697267ed1
--- /dev/null
+++ b/checkpoint-152/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae980258ed44b36f67af3e9ff5103a73820ea9f550a1e6c21e1d7c1c124eb679
+size 16404
diff --git a/checkpoint-152/rng_state_4.pth b/checkpoint-152/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..eb6a9632088f3ef4716902e706d4806b307e3c71
--- /dev/null
+++ b/checkpoint-152/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f596d71bd50636afdde88fb7c66a9548eab0330d7b32ab88933a8f3efd7e2b5
+size 16389
diff --git a/checkpoint-152/rng_state_5.pth b/checkpoint-152/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..79d88bb2e903a43b07c46612438ed63ac0013860
--- /dev/null
+++ b/checkpoint-152/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47f526c0754504badcf137a61eb13caa7101e2476e3dbbb50af8f6d84e4ef72a
+size 16389
diff --git a/checkpoint-152/rng_state_6.pth b/checkpoint-152/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d4e12d55b912f9f4ac4ff27cf19f8234b7e6e0e4
--- /dev/null
+++ b/checkpoint-152/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88c7948e5555a9a87336f99ddae2f3fad239383b2e154264499bbdb9ee69ac8
+size 16389
diff --git a/checkpoint-152/rng_state_7.pth b/checkpoint-152/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ea9ad902b359dec07a93fc23ed4f870ccae6f7f4
--- /dev/null
+++ b/checkpoint-152/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0b1dbe82aa2b965b606363d8aa54718f77bb64150455f460de3319562f0d54
+size 16389
diff --git a/checkpoint-152/rng_state_8.pth b/checkpoint-152/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..274db87f0fc9cb87d0611a0bc2bbbde7345b3a55
--- /dev/null
+++ b/checkpoint-152/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b4a7d45fcc95f84ab6b400d74dfacb7f7b2ea38b5ef1ff105df8aa343c4a98
+size 16389
diff --git a/checkpoint-152/rng_state_9.pth b/checkpoint-152/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fb586f810c0d8ef8a2b0ba8e4c00b9348c713235
--- /dev/null
+++ b/checkpoint-152/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93f717098002279b609755dac4d39c0565f63b9731e0deb3964f9c27f332f22
+size 16389
diff --git a/checkpoint-152/scheduler.pt b/checkpoint-152/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c7f8cd0b2109533fba79761abd087bc4416f9187
--- /dev/null
+++ b/checkpoint-152/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f16e67122541f81beb25aa5d1a92ef46493e35c25e08c6d488cfeb37fe4725
+size 1465
diff --git a/checkpoint-152/tokenizer.json b/checkpoint-152/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-152/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-152/tokenizer_config.json b/checkpoint-152/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-152/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-152/trainer_state.json b/checkpoint-152/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..8c59c323b2d504ea89788156917bded82077d83d
--- /dev/null
+++ b/checkpoint-152/trainer_state.json
@@ -0,0 +1,334 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4126984126984126,
+  "eval_steps": 500,
+  "global_step": 152,
+  "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
+    },
+    {
+      "entropy": 0.06085996180772781,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.13919851183891296,
+      "learning_rate": 8.657988130699848e-06,
+      "loss": 0.06093168258666992,
+      "mean_token_accuracy": 0.975907814502716,
+      "num_tokens": 62928491.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.06154095679521561,
+      "epoch": 2.3015873015873014,
+      "grad_norm": 0.1471860557794571,
+      "learning_rate": 7.096195292140173e-06,
+      "loss": 0.06225389242172241,
+      "mean_token_accuracy": 0.9755991458892822,
+      "num_tokens": 65183865.0,
+      "step": 145
+    },
+    {
+      "entropy": 0.06028798446059227,
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.1381225436925888,
+      "learning_rate": 5.666233057256756e-06,
+      "loss": 0.05946478247642517,
+      "mean_token_accuracy": 0.9772057175636292,
+      "num_tokens": 67455033.0,
+      "step": 150
+    }
+  ],
+  "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": 3.8107234557965107e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-152/training_args.bin b/checkpoint-152/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-152/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-160/README.md b/checkpoint-160/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-160/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-160/adapter_config.json b/checkpoint-160/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-160/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-160/adapter_model.safetensors b/checkpoint-160/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fd1bbc1ef1ed7b4fecb2a7ead4c07ef62ca1e5aa
--- /dev/null
+++ b/checkpoint-160/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bebc56be32d7220e0564a5aa4f695d5af5d423b9debe8b670c19f9b4bd9d58d
+size 1384975816
diff --git a/checkpoint-160/chat_template.jinja b/checkpoint-160/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-160/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-160/optimizer.pt b/checkpoint-160/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4f25b690783cb83ec0a21d4747a21b21240bf573
--- /dev/null
+++ b/checkpoint-160/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35019b2c8419a5b776189e9509b7a77961eb2c07e08fa62365ce6d77c19bebec
+size 2770239667
diff --git a/checkpoint-160/rng_state_0.pth b/checkpoint-160/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..129d831ebcdfd200acaed9261cc8d33083907008
--- /dev/null
+++ b/checkpoint-160/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b8745197f69c52711b5c9d73fafdf2cc88650ca3ceba45e24b708d8a1fef3e
+size 16389
diff --git a/checkpoint-160/rng_state_1.pth b/checkpoint-160/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dadfa08f245971f447ab732b48123a65f8b949b3
--- /dev/null
+++ b/checkpoint-160/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da01b26de1c9f24712f4c4282f2537eb2d933a75dfc0f8312134d51359310585
+size 16389
diff --git a/checkpoint-160/rng_state_10.pth b/checkpoint-160/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..17411a73c6136821c2fcac69c1c7c8505a3585e3
--- /dev/null
+++ b/checkpoint-160/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a8c1bad97496025edf96b07e14992dd575f29318ecbdcf1e925d4b394b1394
+size 16404
diff --git a/checkpoint-160/rng_state_11.pth b/checkpoint-160/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e1113fe6a1f50c56f6760e3b11d3b1b5955ab4f8
--- /dev/null
+++ b/checkpoint-160/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b72449d4e275ff9709c1fb56fd42cf63cd9824a0ee7f5f9944c6ce9c6326c8
+size 16404
diff --git a/checkpoint-160/rng_state_12.pth b/checkpoint-160/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..593d7776764068ae38b7c27d593fc914e27a6a09
--- /dev/null
+++ b/checkpoint-160/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3add763ced5219b0c996700870fbf3f02b58f699c04211c253c8872c4f7de987
+size 16404
diff --git a/checkpoint-160/rng_state_13.pth b/checkpoint-160/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0b62878a03f07bb88bbcdd4d2e4e155d2de5f022
--- /dev/null
+++ b/checkpoint-160/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d1bfdf2e9f67c3215b53ce64f8a47a4e15ace95f035dd871b177a65f752991
+size 16404
diff --git a/checkpoint-160/rng_state_14.pth b/checkpoint-160/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4d2a37d8ea0d479a050fcfd00061a64566462c0f
--- /dev/null
+++ b/checkpoint-160/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca86cb2e1adf5e90756a5574d32d1796a8abc9b967b49b816987618eaa6c91ae
+size 16404
diff --git a/checkpoint-160/rng_state_15.pth b/checkpoint-160/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4175d65d3eb4d1033a0c7303b4b6f873a4ab27e7
--- /dev/null
+++ b/checkpoint-160/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b6f9931a55ea6a6eac89711fff47efb1410d38a3c548cacd8cec8788469617
+size 16404
diff --git a/checkpoint-160/rng_state_16.pth b/checkpoint-160/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ae6dfae8ea44b27589d1f56e91b1a78000afdeae
--- /dev/null
+++ b/checkpoint-160/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bf0287f06bb65a92bbbe19a778a641e871e5359a61fceee5a7b3323a19a7b1
+size 16404
diff --git a/checkpoint-160/rng_state_17.pth b/checkpoint-160/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e181f9f3b9e97701ed0ac9da9f9c5fdd499b3a99
--- /dev/null
+++ b/checkpoint-160/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ffb0e86c6e889291c106ad93e51d6711dad9aa14fe39cce8837fd67db66d9e9
+size 16404
diff --git a/checkpoint-160/rng_state_18.pth b/checkpoint-160/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f4b9a104f693bd63f24924dd55f84c66b26f1600
--- /dev/null
+++ b/checkpoint-160/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd638df5eccba41da5c2da4b87cb8c5e39730675aa74b47eae6d6d2d92179581
+size 16404
diff --git a/checkpoint-160/rng_state_19.pth b/checkpoint-160/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..36acd84ba81aa4e7c15d602d4e92ee61bfbecd16
--- /dev/null
+++ b/checkpoint-160/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5ef67f333925ee1feb7d5424fd005d56cd997f767d71b097b5bcbaa89d085d
+size 16404
diff --git a/checkpoint-160/rng_state_2.pth b/checkpoint-160/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..344469fa452ed22927808625b4417e0229ff6157
--- /dev/null
+++ b/checkpoint-160/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ccf1690dea4163451ca9681a98e75837c6cce77409bf51920359c51d14bda4
+size 16389
diff --git a/checkpoint-160/rng_state_20.pth b/checkpoint-160/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..63470204fe7d469949ccbf04b17e782a01cf58ff
--- /dev/null
+++ b/checkpoint-160/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3d71527b461d7c3f2ad35ff2af88a3358ccf09aad6fb5a9545bc66f592ee61
+size 16404
diff --git a/checkpoint-160/rng_state_21.pth b/checkpoint-160/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..60d82a1166c8323890ad2511f35e8bd95ab0e253
--- /dev/null
+++ b/checkpoint-160/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb57844a472c3b99368634714e1dbfbc4add62d595b3015b8342a3646171bb49
+size 16404
diff --git a/checkpoint-160/rng_state_22.pth b/checkpoint-160/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..23c134a42ecd67106bd7f941156965157d89abf7
--- /dev/null
+++ b/checkpoint-160/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba88c61e157b5da36630d77e055623b60ac6cf6e323e5e34a01799cd98009f83
+size 16404
diff --git a/checkpoint-160/rng_state_23.pth b/checkpoint-160/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ee33a3ad7cb482ae97a635cdd30e8d7e68dd8cf4
--- /dev/null
+++ b/checkpoint-160/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61c8aebb04bc6b2421d363a5316d2e5bf99624acd389c4b7f7c225893520d8a
+size 16404
diff --git a/checkpoint-160/rng_state_24.pth b/checkpoint-160/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b2d00091b898e0247647d3109ddb7223d7b6ef0c
--- /dev/null
+++ b/checkpoint-160/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e568375dad37154a438fc39a24adae23064702181c53288a2a44f3acdabf2d
+size 16404
diff --git a/checkpoint-160/rng_state_25.pth b/checkpoint-160/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..18e1e330eaa375d837d3f5b5a20e0bf775195a42
--- /dev/null
+++ b/checkpoint-160/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbbf680082fd431ebf26072446a02b4ea3906d2be4c5a341603381ef166134f
+size 16404
diff --git a/checkpoint-160/rng_state_26.pth b/checkpoint-160/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7b7f086e93883f5f334327492473bed2e9f54f15
--- /dev/null
+++ b/checkpoint-160/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af318cb85259a5edc485a574657e9b2ddc9a61695165d6349c56a54810fa5849
+size 16404
diff --git a/checkpoint-160/rng_state_27.pth b/checkpoint-160/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ceccdf8303ee5619d76ec3b30a20468406977635
--- /dev/null
+++ b/checkpoint-160/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4aa3c8b6fcd5ad3f0768da68c2835ed1ad3e3137b140f27e1c6fe965e29a258
+size 16404
diff --git a/checkpoint-160/rng_state_28.pth b/checkpoint-160/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..66c7d205890a75dee227ce0111ec81485a758d7d
--- /dev/null
+++ b/checkpoint-160/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1db51c1a5c68962db5c81a25662053bfb09a916d1944c50b1214b86cdad3d02
+size 16404
diff --git a/checkpoint-160/rng_state_29.pth b/checkpoint-160/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cb67338a7fce919a05530765016e3a0f2f382988
--- /dev/null
+++ b/checkpoint-160/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3e775902406705bfb4deb7f88b4f382125d24140403103de5c2bfe35158bf9
+size 16404
diff --git a/checkpoint-160/rng_state_3.pth b/checkpoint-160/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6b2fca5f1ef8fe2a24a80f64795c97fd93f95f13
--- /dev/null
+++ b/checkpoint-160/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60abbc36b01c01354ee3728e8f9a148585a5f00f011e51284fb06901a6790226
+size 16389
diff --git a/checkpoint-160/rng_state_30.pth b/checkpoint-160/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..84d4641435a95d71c2cbcbd0ad72d8dabd795ed0
--- /dev/null
+++ b/checkpoint-160/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c984b3cc179375e0e835427133537b8085c7a64a2825991b3cb7bdda7087c51
+size 16404
diff --git a/checkpoint-160/rng_state_31.pth b/checkpoint-160/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7da841569900d40e7cd55c22c9747989b8fdf603
--- /dev/null
+++ b/checkpoint-160/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ddf5949a4d97b60c34a952f97511043656413a50723f962bed3ba902aa6d6b2
+size 16404
diff --git a/checkpoint-160/rng_state_4.pth b/checkpoint-160/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..11a56b13acb67bc0246f9bd12563dcefb269d28c
--- /dev/null
+++ b/checkpoint-160/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8cd50b585d12de0421ef72c0a24678244a52894bfc43c9d5c897722dbc5dd0
+size 16389
diff --git a/checkpoint-160/rng_state_5.pth b/checkpoint-160/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e0ca87dd8cd5e8f2e03b76964540729438470164
--- /dev/null
+++ b/checkpoint-160/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c5ddc8ba2271b692f5bbecafd33e4113c1f708160efe16597590ee139f7519
+size 16389
diff --git a/checkpoint-160/rng_state_6.pth b/checkpoint-160/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..173bdf693dbab59f188192fb10ed3cf4d220fb95
--- /dev/null
+++ b/checkpoint-160/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af934c622adef0dc700536cc950a0ee4989e740c5310b97d202e6aec8680b3a4
+size 16389
diff --git a/checkpoint-160/rng_state_7.pth b/checkpoint-160/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b00848c29880ecd4c0b8175f4a51f02d118f92e2
--- /dev/null
+++ b/checkpoint-160/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef84463b715f629d337c57ffeafa18a0636e231f1ba742319bbf261c58630eb4
+size 16389
diff --git a/checkpoint-160/rng_state_8.pth b/checkpoint-160/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ea238fb6b449ba7ee5b8cdd9a72bde55dcea5d42
--- /dev/null
+++ b/checkpoint-160/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8765cbce1ceb673f00e3bea972585b4b6e87fb2aef226c95d3273a5908aadc0
+size 16389
diff --git a/checkpoint-160/rng_state_9.pth b/checkpoint-160/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..64fc96620e290da416e7189b31f5e4fcd650faa5
--- /dev/null
+++ b/checkpoint-160/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b5777f6f29ad3176f538f1a39a4e03d233f7b5d33481b3d575179c7f63f210
+size 16389
diff --git a/checkpoint-160/scheduler.pt b/checkpoint-160/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4b3dab906916e2602ed73ccae881b4763ec0ff0d
--- /dev/null
+++ b/checkpoint-160/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad50274b81fad914b38f04ca76621b098d686105e6b47fab5ae893ce25eefad
+size 1465
diff --git a/checkpoint-160/tokenizer.json b/checkpoint-160/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-160/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-160/tokenizer_config.json b/checkpoint-160/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-160/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-160/trainer_state.json b/checkpoint-160/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e49747bf63d61439fd51101b6d4df06fd20037de
--- /dev/null
+++ b/checkpoint-160/trainer_state.json
@@ -0,0 +1,354 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5396825396825395,
+  "eval_steps": 500,
+  "global_step": 160,
+  "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
+    },
+    {
+      "entropy": 0.06085996180772781,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.13919851183891296,
+      "learning_rate": 8.657988130699848e-06,
+      "loss": 0.06093168258666992,
+      "mean_token_accuracy": 0.975907814502716,
+      "num_tokens": 62928491.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.06154095679521561,
+      "epoch": 2.3015873015873014,
+      "grad_norm": 0.1471860557794571,
+      "learning_rate": 7.096195292140173e-06,
+      "loss": 0.06225389242172241,
+      "mean_token_accuracy": 0.9755991458892822,
+      "num_tokens": 65183865.0,
+      "step": 145
+    },
+    {
+      "entropy": 0.06028798446059227,
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.1381225436925888,
+      "learning_rate": 5.666233057256756e-06,
+      "loss": 0.05946478247642517,
+      "mean_token_accuracy": 0.9772057175636292,
+      "num_tokens": 67455033.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.05786149725317955,
+      "epoch": 2.4603174603174605,
+      "grad_norm": 0.1443004608154297,
+      "learning_rate": 4.378630628514388e-06,
+      "loss": 0.05805859565734863,
+      "mean_token_accuracy": 0.9774470567703247,
+      "num_tokens": 69702174.0,
+      "step": 155
+    },
+    {
+      "entropy": 0.05872737467288971,
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.15280300378799438,
+      "learning_rate": 3.2428689742461188e-06,
+      "loss": 0.058740425109863284,
+      "mean_token_accuracy": 0.9766229271888733,
+      "num_tokens": 71937597.0,
+      "step": 160
+    }
+  ],
+  "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": 4.011093300881654e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-160/training_args.bin b/checkpoint-160/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-160/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-168/README.md b/checkpoint-168/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-168/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-168/adapter_config.json b/checkpoint-168/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-168/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-168/adapter_model.safetensors b/checkpoint-168/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1ea2dd9b16b466f177df10d3e6ab5aac860b9f0c
--- /dev/null
+++ b/checkpoint-168/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee24b8cf8ebb013a81be0d874cf52ed974f861a31be46bbda9f9c4857163ec68
+size 1384975816
diff --git a/checkpoint-168/chat_template.jinja b/checkpoint-168/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-168/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-168/optimizer.pt b/checkpoint-168/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..65355a66475c555ee30889f18145c3aed92f608a
--- /dev/null
+++ b/checkpoint-168/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ab45decf32ddcb4b01d9db640aa052f5e53422736b4b95e2635e9125b776f1
+size 2770239667
diff --git a/checkpoint-168/rng_state_0.pth b/checkpoint-168/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..57cb70321891ffd09b5a1e611a3229ba882f548b
--- /dev/null
+++ b/checkpoint-168/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916428d808f87949b10a2328eb02c48078ce042d7e084de22e863c42f40e3e62
+size 16389
diff --git a/checkpoint-168/rng_state_1.pth b/checkpoint-168/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..af83ddc75a0f41de4eae4d8cc170bca204312066
--- /dev/null
+++ b/checkpoint-168/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55eeb78cd1af657d14e8e026a5b89f0a423e4191f5fec75dad92c57d996cc9c9
+size 16389
diff --git a/checkpoint-168/rng_state_10.pth b/checkpoint-168/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..eae9ebb5b274cad4880aa6c0739bfa0182265a68
--- /dev/null
+++ b/checkpoint-168/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00dbe7689f1e34f7803ae4dc32f30ac5a5ce1660ebf5e7c60949cbf5fe7f251a
+size 16404
diff --git a/checkpoint-168/rng_state_11.pth b/checkpoint-168/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b6f2a0d81d517de808e170b4cc1600f3dc09583f
--- /dev/null
+++ b/checkpoint-168/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd371fc6b4b355f85f91420e547d27cd615e8acf8198c70ae42b5fe75f5da70
+size 16404
diff --git a/checkpoint-168/rng_state_12.pth b/checkpoint-168/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..399050e1fd7de1ae271b8362ec6d5d9f250698cb
--- /dev/null
+++ b/checkpoint-168/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bebb6ac5d98df9b122a1ad4b469205ba212d55ef3e94d33cc96e546149989c
+size 16404
diff --git a/checkpoint-168/rng_state_13.pth b/checkpoint-168/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..363f9c9cbac6b2c347a23f4c25d985ace46b9c42
--- /dev/null
+++ b/checkpoint-168/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733253a35ba90c311cb478e7c0f863d85656bb96bac987653dc15594f74bcf9c
+size 16404
diff --git a/checkpoint-168/rng_state_14.pth b/checkpoint-168/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2782c48c561e12b57e79f99853409571d7435fd1
--- /dev/null
+++ b/checkpoint-168/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1577c905404cc06843f50c8411a6fc3b76786f13eea667269e7e0d1064e1182
+size 16404
diff --git a/checkpoint-168/rng_state_15.pth b/checkpoint-168/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..60695bdae5de1fd9836ede54438e821c3cdb9992
--- /dev/null
+++ b/checkpoint-168/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0596a57656aeae634db5fac6616f1536f063a23369de570fa76865ba53e466bd
+size 16404
diff --git a/checkpoint-168/rng_state_16.pth b/checkpoint-168/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0d150f9e7d79ed3f80fedb074a8df2124560e06b
--- /dev/null
+++ b/checkpoint-168/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ba0c25d21d625bb7ffc8b172906d69228240c8b2feb55d57d6ebf30fffd41c
+size 16404
diff --git a/checkpoint-168/rng_state_17.pth b/checkpoint-168/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..87427f864af39dd2b38d94c6657b44c7e313a2da
--- /dev/null
+++ b/checkpoint-168/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a966eb994163bf6efedb40f7db1cb0a5a8df1d49dd6d9d427fce259523d0bc22
+size 16404
diff --git a/checkpoint-168/rng_state_18.pth b/checkpoint-168/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..17a3ecad43fa2a95afb66dc64d8a9dcd4d9828fe
--- /dev/null
+++ b/checkpoint-168/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a676628934b5144a1bdd6aac3b39f0d8038dfb85745e2c6b6543cf2a28a5df7
+size 16404
diff --git a/checkpoint-168/rng_state_19.pth b/checkpoint-168/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7810387efb2be14a66a9b3589c4c2eeab55386b7
--- /dev/null
+++ b/checkpoint-168/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f65d5ee3ac6966a0fbcaf84b251f0e6c1be706106d0e4c9e30c648c9a384e0
+size 16404
diff --git a/checkpoint-168/rng_state_2.pth b/checkpoint-168/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..303c64d4ac1a9963bdc142c0de6813a3c6e5980b
--- /dev/null
+++ b/checkpoint-168/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7933f3d18076f78d112b05c6e592bc193a8d453bc0bde6ad67645f531c84f2
+size 16389
diff --git a/checkpoint-168/rng_state_20.pth b/checkpoint-168/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..785547b85181797c38daaa002ba708191512845f
--- /dev/null
+++ b/checkpoint-168/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9de0a98bda56361c1a7d25c1167ada90ba878907513c5e37b4a91803b7007c
+size 16404
diff --git a/checkpoint-168/rng_state_21.pth b/checkpoint-168/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a94ad3b47180559671b280befd6e88bdfc5720bd
--- /dev/null
+++ b/checkpoint-168/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb141897c2f97dd941f1faa40ab361912628bd8023df008787aba792c730197e
+size 16404
diff --git a/checkpoint-168/rng_state_22.pth b/checkpoint-168/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5f85829049a3bed26999e40347614e8fab0e7b1e
--- /dev/null
+++ b/checkpoint-168/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c10e6bc7490adebfc5d964c9cba6faaa662d5aebce48946622de8e774ae374
+size 16404
diff --git a/checkpoint-168/rng_state_23.pth b/checkpoint-168/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6527d881cce91a7c16237a39c9c1f62d16881ea2
--- /dev/null
+++ b/checkpoint-168/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a601a1c7690ea02255573dfdc038b9dd6cf560a50dcede7dbfd22d3f31a110
+size 16404
diff --git a/checkpoint-168/rng_state_24.pth b/checkpoint-168/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..befb3d2638a2c144d9aa13b070a014d9d7f11928
--- /dev/null
+++ b/checkpoint-168/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cadb02c0d81febe4785050d8bb07509cf2dcf122f0eec866eacc8a8a7c540e
+size 16404
diff --git a/checkpoint-168/rng_state_25.pth b/checkpoint-168/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ce3aaaba5993132ce04c0cc5764699ab6e507df0
--- /dev/null
+++ b/checkpoint-168/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f581c60d0ade234058ae75337d47984630d57f7b15959f2887176bd0ae006b
+size 16404
diff --git a/checkpoint-168/rng_state_26.pth b/checkpoint-168/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..16af5ce31226c0cab621cf0fcf702a45ac752ba3
--- /dev/null
+++ b/checkpoint-168/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0873954f96d6c55d4c650ad8b9f082a8a7472794fb555f5c2042db77e397b83f
+size 16404
diff --git a/checkpoint-168/rng_state_27.pth b/checkpoint-168/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d7def77be98b2e8d821a79fc839c22a8d754fd00
--- /dev/null
+++ b/checkpoint-168/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7046d2864cbfd15352f9bc992735fdd93f4ef9909fbabb2384aa480dab913836
+size 16404
diff --git a/checkpoint-168/rng_state_28.pth b/checkpoint-168/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4114cb6318ed2e33de96fb8b9c5fc6a51facb098
--- /dev/null
+++ b/checkpoint-168/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff4775f7772d319c3e8f0955d8b4ff84fec8ea2d7dbfe577e1ef8203656afe8
+size 16404
diff --git a/checkpoint-168/rng_state_29.pth b/checkpoint-168/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..523e5cd39788ff069d5cc9bdbcf386b54ebd36b8
--- /dev/null
+++ b/checkpoint-168/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd5c6677961965b40afe626c1eb5ed8546e01036f5c76123ba98366a7d73e62
+size 16404
diff --git a/checkpoint-168/rng_state_3.pth b/checkpoint-168/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..406e5c40a48ee876c84b8bf3e4b4d92a5015bb50
--- /dev/null
+++ b/checkpoint-168/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9392c3d69f606e8bae818de9760ea4ce6aa924a36d8a9933907c4362f3db1d19
+size 16389
diff --git a/checkpoint-168/rng_state_30.pth b/checkpoint-168/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e20b0f822f548cee81166833100f208996fc1f77
--- /dev/null
+++ b/checkpoint-168/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a219d74e57fb40d751fb0205877449443bd25612f79337d73d999d100ecc735b
+size 16404
diff --git a/checkpoint-168/rng_state_31.pth b/checkpoint-168/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5129d694a997ce607629ae847598fc749a34a50b
--- /dev/null
+++ b/checkpoint-168/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fec23c9c90cb242146ca6dbba2a6998e713fc8046cfa53f394d0184b1b3e18a
+size 16404
diff --git a/checkpoint-168/rng_state_4.pth b/checkpoint-168/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..84c92c8f42ce95ca4e9e542287c82cbda12417f4
--- /dev/null
+++ b/checkpoint-168/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88f603c998a5d97c2fd010b174800bc509ab8f0045222c6ee4641ec06bfc444
+size 16389
diff --git a/checkpoint-168/rng_state_5.pth b/checkpoint-168/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ff51100cd20922bc5aae1151f3441aa80d805aa8
--- /dev/null
+++ b/checkpoint-168/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71395e0326567c6fb3865c3c1abbe6c172181d7010d38a3cc5eab37f3f457b93
+size 16389
diff --git a/checkpoint-168/rng_state_6.pth b/checkpoint-168/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a7eaa250114eb70a87828c675b7aedd3863991c0
--- /dev/null
+++ b/checkpoint-168/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8754e7fcdaa77eb539ed35e37edc3b047eab50c52022ddce258f5bf9df83fbc8
+size 16389
diff --git a/checkpoint-168/rng_state_7.pth b/checkpoint-168/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..192f5d486097aa4e50f6a9292a6f3e0be83d25d2
--- /dev/null
+++ b/checkpoint-168/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c80a12d8f33f9cfa2acd7ea7db8b5595e724591a7ffa81fba099ce39fee728
+size 16389
diff --git a/checkpoint-168/rng_state_8.pth b/checkpoint-168/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c9bb2aed36b2a0d345311c81e9c38907a0a846b7
--- /dev/null
+++ b/checkpoint-168/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c59532891909e23e29ae93aace5717dedd869fb31c0cb0e384eadc45c6ddd1a
+size 16389
diff --git a/checkpoint-168/rng_state_9.pth b/checkpoint-168/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..658007373ce5a9b0d0ff3be2d4849fa3f9ae34b1
--- /dev/null
+++ b/checkpoint-168/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4486f0c7d944d965bf6438b911c4c1b1f8af00e40c129170bdbc000db805a704
+size 16389
diff --git a/checkpoint-168/scheduler.pt b/checkpoint-168/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..796e00288485f39ed345c8ad1ebd1b848e234185
--- /dev/null
+++ b/checkpoint-168/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6adef1ed100a9da7204373b874f41ae5e45478a63a7aa60399bf902870fc322
+size 1465
diff --git a/checkpoint-168/tokenizer.json b/checkpoint-168/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-168/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-168/tokenizer_config.json b/checkpoint-168/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-168/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-168/trainer_state.json b/checkpoint-168/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..043b9a563764f761dcfae98e828b5206f2b0b5a0
--- /dev/null
+++ b/checkpoint-168/trainer_state.json
@@ -0,0 +1,364 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6666666666666665,
+  "eval_steps": 500,
+  "global_step": 168,
+  "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
+    },
+    {
+      "entropy": 0.06085996180772781,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.13919851183891296,
+      "learning_rate": 8.657988130699848e-06,
+      "loss": 0.06093168258666992,
+      "mean_token_accuracy": 0.975907814502716,
+      "num_tokens": 62928491.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.06154095679521561,
+      "epoch": 2.3015873015873014,
+      "grad_norm": 0.1471860557794571,
+      "learning_rate": 7.096195292140173e-06,
+      "loss": 0.06225389242172241,
+      "mean_token_accuracy": 0.9755991458892822,
+      "num_tokens": 65183865.0,
+      "step": 145
+    },
+    {
+      "entropy": 0.06028798446059227,
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.1381225436925888,
+      "learning_rate": 5.666233057256756e-06,
+      "loss": 0.05946478247642517,
+      "mean_token_accuracy": 0.9772057175636292,
+      "num_tokens": 67455033.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.05786149725317955,
+      "epoch": 2.4603174603174605,
+      "grad_norm": 0.1443004608154297,
+      "learning_rate": 4.378630628514388e-06,
+      "loss": 0.05805859565734863,
+      "mean_token_accuracy": 0.9774470567703247,
+      "num_tokens": 69702174.0,
+      "step": 155
+    },
+    {
+      "entropy": 0.05872737467288971,
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.15280300378799438,
+      "learning_rate": 3.2428689742461188e-06,
+      "loss": 0.058740425109863284,
+      "mean_token_accuracy": 0.9766229271888733,
+      "num_tokens": 71937597.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.05862027704715729,
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.13461482524871826,
+      "learning_rate": 2.267311017694107e-06,
+      "loss": 0.05860599875450134,
+      "mean_token_accuracy": 0.9768976211547852,
+      "num_tokens": 74179028.0,
+      "step": 165
+    }
+  ],
+  "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": 4.211681613773275e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-168/training_args.bin b/checkpoint-168/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-168/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-176/README.md b/checkpoint-176/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-176/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-176/adapter_config.json b/checkpoint-176/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-176/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-176/adapter_model.safetensors b/checkpoint-176/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a1d7f15db948c9b1975d9cceb68d42d91122ee10
--- /dev/null
+++ b/checkpoint-176/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b208cdc5c6bcbcbe41747b9502c160f71dc2dd0f158a6e13c34c86b9405489
+size 1384975816
diff --git a/checkpoint-176/chat_template.jinja b/checkpoint-176/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-176/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-176/optimizer.pt b/checkpoint-176/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..047dd82a7e8bba5583768dd4ed658642ddeeffed
--- /dev/null
+++ b/checkpoint-176/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec292634ba6236fc2250e0ec278715e99654f5ccc078808e6edf7c022e70c674
+size 2770239667
diff --git a/checkpoint-176/rng_state_0.pth b/checkpoint-176/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a1a757d4dc2a31b782b94cb209bbff3f832c0e0d
--- /dev/null
+++ b/checkpoint-176/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5cc13880581cf32ae80c431681a73fbe8a6cc85a8c2f48db1b28eb76a3e1bbc
+size 16389
diff --git a/checkpoint-176/rng_state_1.pth b/checkpoint-176/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0076e68ddd5f313fb797e763c166c8a6b9fbdd38
--- /dev/null
+++ b/checkpoint-176/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6360a0b65ffff7fe5649efad124bf1687606a685f8819d29f24e4679e9438e
+size 16389
diff --git a/checkpoint-176/rng_state_10.pth b/checkpoint-176/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c0e37e4355497010e68e331531bae7d9fccf32e1
--- /dev/null
+++ b/checkpoint-176/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e412dc51c9ce3a36ee99923cd0029c87c09507955b92696838f857633661014e
+size 16404
diff --git a/checkpoint-176/rng_state_11.pth b/checkpoint-176/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f94decaa2c47428859493c8def22286246f26333
--- /dev/null
+++ b/checkpoint-176/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33857a5ab2d9628ec722b4ddc83adad2bf3cdf7da625e4d38eac02027998f245
+size 16404
diff --git a/checkpoint-176/rng_state_12.pth b/checkpoint-176/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c6e58f5d9c4ca8faff8a4ec7837ecef4a73a679e
--- /dev/null
+++ b/checkpoint-176/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb2258120a4512950b210af02a443bdaf22824043cfcf497e7f322bf05bf7cb
+size 16404
diff --git a/checkpoint-176/rng_state_13.pth b/checkpoint-176/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9af1de376f726b0d91d3e76214928305db27f673
--- /dev/null
+++ b/checkpoint-176/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88097dd3a2c9c0b88e359be372ad764ba5c3e7ac162d8ce0bb550c3a6ae1012b
+size 16404
diff --git a/checkpoint-176/rng_state_14.pth b/checkpoint-176/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e14560d9d6613ed0916dd68d72a70a9377630789
--- /dev/null
+++ b/checkpoint-176/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a97119fede398810aa6bca643e8ad5cede0b3bc3777be70531fd38ffba9f88
+size 16404
diff --git a/checkpoint-176/rng_state_15.pth b/checkpoint-176/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9fe0d7b7465c391bdb32cce608ac12e74caacfd1
--- /dev/null
+++ b/checkpoint-176/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d92c18e72c0d29bfa5aadd5d50aae686374d996313987700bd4c371fd2bac2
+size 16404
diff --git a/checkpoint-176/rng_state_16.pth b/checkpoint-176/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..039c287bd505a3d47029680f31ffd3f58929ccac
--- /dev/null
+++ b/checkpoint-176/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168efc6458fe3fe49a65de3830d5bacfb7d594b542b32538565c9e827813d11e
+size 16404
diff --git a/checkpoint-176/rng_state_17.pth b/checkpoint-176/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..49593773f8e5ab4ff2caa340c48599bdf2ef2ac8
--- /dev/null
+++ b/checkpoint-176/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97ef54f59f340943815790020dfc33c91453556160b74415a2e2d095a08d399
+size 16404
diff --git a/checkpoint-176/rng_state_18.pth b/checkpoint-176/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6942ccc4153a28caee182d04d01c3fb2c2fe2006
--- /dev/null
+++ b/checkpoint-176/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56bc1729402786c878b77c6d97196efaf737f91d43b6dda07e8f3944e6b2c77
+size 16404
diff --git a/checkpoint-176/rng_state_19.pth b/checkpoint-176/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c1a4c2179d2626038998ff7ea0894381194259c9
--- /dev/null
+++ b/checkpoint-176/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f93723f3916aaa79afd217a8aecfeb3890692fd08bbe4db15b4a9c352e110bd
+size 16404
diff --git a/checkpoint-176/rng_state_2.pth b/checkpoint-176/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ddc946b22491ab8e0bab960de32c76e552ba7604
--- /dev/null
+++ b/checkpoint-176/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76b63ed48766f7b2db8178b4775f0ccf4382805bdc9d32eda7146e92bfb8d04
+size 16389
diff --git a/checkpoint-176/rng_state_20.pth b/checkpoint-176/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6f63d1626d26c4574538b0e0eeaa5447065192be
--- /dev/null
+++ b/checkpoint-176/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f95b65f13f1d126b4a471531c53e0c47b91880875cb573d6a8b3d2290cb31ee
+size 16404
diff --git a/checkpoint-176/rng_state_21.pth b/checkpoint-176/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f9e96f63c24bdcdf36ad23838e7c59d12eda48db
--- /dev/null
+++ b/checkpoint-176/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b891bc7abb6001176337b53ee58e319224f52df8b1b3a7f38f6b654d5dcdb17
+size 16404
diff --git a/checkpoint-176/rng_state_22.pth b/checkpoint-176/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..96ab26dfee05f893c5eed0714d69d38adcde87aa
--- /dev/null
+++ b/checkpoint-176/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f70b79d445b64045d1ceb5fb5ff5ea574374547c58aa846f82ad8d1603ca8b3
+size 16404
diff --git a/checkpoint-176/rng_state_23.pth b/checkpoint-176/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f375d8f36039d5ad897dcf0f068cf236dbb41460
--- /dev/null
+++ b/checkpoint-176/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f5cd640e0d88fc68510d102dc38baaedfea035be5c4c29251d5c1bae94aa2a
+size 16404
diff --git a/checkpoint-176/rng_state_24.pth b/checkpoint-176/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..19c164fb2b0e694d54c033ca98b8346a61362278
--- /dev/null
+++ b/checkpoint-176/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7a981e8d2c72f37ac16e92215de839ec3f3dd163a9cbefcb7b1eb8fa313b80
+size 16404
diff --git a/checkpoint-176/rng_state_25.pth b/checkpoint-176/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ec40a248cad48db68d44af31d26fb417871031b2
--- /dev/null
+++ b/checkpoint-176/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6252e301318cb2ad3539e479d48341524418907d60eafd8ab995c608b12445
+size 16404
diff --git a/checkpoint-176/rng_state_26.pth b/checkpoint-176/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93bbf2e702614f77d77f3b4787dcf43f7b638033
--- /dev/null
+++ b/checkpoint-176/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068245ed4a494e6bfeaa6e13cdfea13f7578d5b6533ea4afc7b78566103ec97e
+size 16404
diff --git a/checkpoint-176/rng_state_27.pth b/checkpoint-176/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2caa3a913aca2bba98b2e71d1d82a7ebea77d145
--- /dev/null
+++ b/checkpoint-176/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106b33df9ed92d4470dd4180c3aefa9f3345e5a535a3902d485d22bcc8e92d75
+size 16404
diff --git a/checkpoint-176/rng_state_28.pth b/checkpoint-176/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d356bc5c0ba393b9b6fa954c4573c00c6b264782
--- /dev/null
+++ b/checkpoint-176/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:956323b43a4ab6894cdbd03c142be5346c2477994c863da4d71ecc692ac5ef76
+size 16404
diff --git a/checkpoint-176/rng_state_29.pth b/checkpoint-176/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..48aca28a38e94579034a0d5b12b84a4eb7ecda36
--- /dev/null
+++ b/checkpoint-176/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732de9b304963682a54e9d528e7d870cdf479054d2894549671db2507e03f99b
+size 16404
diff --git a/checkpoint-176/rng_state_3.pth b/checkpoint-176/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4d2fc6a571f4b460f7784e7dc026ced491f42980
--- /dev/null
+++ b/checkpoint-176/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4eb89ae61d9a96596e87de8ee6b0a028f85b272d2c5214d3a1af570ab8bbc5e
+size 16389
diff --git a/checkpoint-176/rng_state_30.pth b/checkpoint-176/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8d7239085e73f9069c5a2ac25b6bddc81ce830d2
--- /dev/null
+++ b/checkpoint-176/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7c20f8084c63918af8f5ec7ee5d1d24a2d5c4ea88ead048ecbd4343e788217
+size 16404
diff --git a/checkpoint-176/rng_state_31.pth b/checkpoint-176/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..698a171f8baa09d7945e69b52d0f47f366714dbd
--- /dev/null
+++ b/checkpoint-176/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6b6d3747450e7dea35e44dfeed16964a0c8a2711bb9a04ab73ca8a5f97d549
+size 16404
diff --git a/checkpoint-176/rng_state_4.pth b/checkpoint-176/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..897c03b6a4209ee91c7f8d477d86dfc96d8f273c
--- /dev/null
+++ b/checkpoint-176/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1fa6a0e79b91730ec8f5a49f386bec60409fb589a1a548d4483ad3ca94420e4
+size 16389
diff --git a/checkpoint-176/rng_state_5.pth b/checkpoint-176/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fdb14125c761bdd2603b220e833d776a397e80c2
--- /dev/null
+++ b/checkpoint-176/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb23d02e7800684139829a3caaaaf3283876b8d911c24da2b82fd25e02705b2
+size 16389
diff --git a/checkpoint-176/rng_state_6.pth b/checkpoint-176/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..33bd93a19db72064590b0bc3eec31e38dc301487
--- /dev/null
+++ b/checkpoint-176/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3924cd452d8a9ac42a0264a0f42e4f0c58e1fba7af2ed5c3f943e73adfce233
+size 16389
diff --git a/checkpoint-176/rng_state_7.pth b/checkpoint-176/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..be883477cac186bc1675d9bb0fbb4a926c2341c8
--- /dev/null
+++ b/checkpoint-176/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73272bb0faff6e15d5f224f2dac87209db9a53d09a291fb24db7a62f4e49c3a5
+size 16389
diff --git a/checkpoint-176/rng_state_8.pth b/checkpoint-176/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4c0bdee8d0cc09485be3910fb3f3bbaa585ab42e
--- /dev/null
+++ b/checkpoint-176/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da2e08c82b6d2d02935c3c3f1875bf48cd84e53f12d31448abda008e249e9f2
+size 16389
diff --git a/checkpoint-176/rng_state_9.pth b/checkpoint-176/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ada9649e58320207f6af163ec05a1e7f1ae02664
--- /dev/null
+++ b/checkpoint-176/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf1f32fe506d44655250a12cf1802b7a6236b9469380f53d11049ac5d7e4849
+size 16389
diff --git a/checkpoint-176/scheduler.pt b/checkpoint-176/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f6f74fd84b6eb25d4eb898e08ad118f0fc8a255a
--- /dev/null
+++ b/checkpoint-176/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85937d5699b5dfd18991ec3aff674c3a34cdec98e609071e1d1f6e13ea522d7a
+size 1465
diff --git a/checkpoint-176/tokenizer.json b/checkpoint-176/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-176/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-176/tokenizer_config.json b/checkpoint-176/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-176/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-176/trainer_state.json b/checkpoint-176/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5e0b1cf156bcf62b76a8f4cc57d5511beb32185f
--- /dev/null
+++ b/checkpoint-176/trainer_state.json
@@ -0,0 +1,384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.7936507936507935,
+  "eval_steps": 500,
+  "global_step": 176,
+  "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
+    },
+    {
+      "entropy": 0.06085996180772781,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.13919851183891296,
+      "learning_rate": 8.657988130699848e-06,
+      "loss": 0.06093168258666992,
+      "mean_token_accuracy": 0.975907814502716,
+      "num_tokens": 62928491.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.06154095679521561,
+      "epoch": 2.3015873015873014,
+      "grad_norm": 0.1471860557794571,
+      "learning_rate": 7.096195292140173e-06,
+      "loss": 0.06225389242172241,
+      "mean_token_accuracy": 0.9755991458892822,
+      "num_tokens": 65183865.0,
+      "step": 145
+    },
+    {
+      "entropy": 0.06028798446059227,
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.1381225436925888,
+      "learning_rate": 5.666233057256756e-06,
+      "loss": 0.05946478247642517,
+      "mean_token_accuracy": 0.9772057175636292,
+      "num_tokens": 67455033.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.05786149725317955,
+      "epoch": 2.4603174603174605,
+      "grad_norm": 0.1443004608154297,
+      "learning_rate": 4.378630628514388e-06,
+      "loss": 0.05805859565734863,
+      "mean_token_accuracy": 0.9774470567703247,
+      "num_tokens": 69702174.0,
+      "step": 155
+    },
+    {
+      "entropy": 0.05872737467288971,
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.15280300378799438,
+      "learning_rate": 3.2428689742461188e-06,
+      "loss": 0.058740425109863284,
+      "mean_token_accuracy": 0.9766229271888733,
+      "num_tokens": 71937597.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.05862027704715729,
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.13461482524871826,
+      "learning_rate": 2.267311017694107e-06,
+      "loss": 0.05860599875450134,
+      "mean_token_accuracy": 0.9768976211547852,
+      "num_tokens": 74179028.0,
+      "step": 165
+    },
+    {
+      "entropy": 0.059079910069704054,
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.14060291647911072,
+      "learning_rate": 1.4591400585218544e-06,
+      "loss": 0.058356738090515135,
+      "mean_token_accuracy": 0.977295708656311,
+      "num_tokens": 76426869.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.058903105556964874,
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.1497332900762558,
+      "learning_rate": 8.243068802169906e-07,
+      "loss": 0.05870553255081177,
+      "mean_token_accuracy": 0.9769431948661804,
+      "num_tokens": 78682661.0,
+      "step": 175
+    }
+  ],
+  "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": 4.41167595631018e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-176/training_args.bin b/checkpoint-176/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-176/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-184/README.md b/checkpoint-184/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-184/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-184/adapter_config.json b/checkpoint-184/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-184/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-184/adapter_model.safetensors b/checkpoint-184/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e1ad09a985def2d3449c9ef191f8b42a71a1f2e0
--- /dev/null
+++ b/checkpoint-184/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9878fa5b5b747949a85ecddab1fc9b7d683f0542f183321570876c57699055e1
+size 1384975816
diff --git a/checkpoint-184/chat_template.jinja b/checkpoint-184/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-184/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-184/optimizer.pt b/checkpoint-184/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bb69470f8bcea1655c941433fb449b6dea811c69
--- /dev/null
+++ b/checkpoint-184/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25da6e56d54f25041ecd14bb045fc30faa7afe5a29abba9793449115bc53fcd6
+size 2770239667
diff --git a/checkpoint-184/rng_state_0.pth b/checkpoint-184/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1d2e0d8fe96a8c591e6aa59c71b389cbac54b298
--- /dev/null
+++ b/checkpoint-184/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3fbf7e38aaa9f7ab9f474c4936271789bbbf575ece88d31c52414c4a9a5649
+size 16389
diff --git a/checkpoint-184/rng_state_1.pth b/checkpoint-184/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..76d52c013ceacb7b85b06884a27dc2d398a13601
--- /dev/null
+++ b/checkpoint-184/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1ed095c45fe970ffe7a2bc85d21a1aca7c30733c9fd75cda7f171bd8815cbe
+size 16389
diff --git a/checkpoint-184/rng_state_10.pth b/checkpoint-184/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ef6d8b870f9b17b6f2f4a28fa567749ea2056e0b
--- /dev/null
+++ b/checkpoint-184/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cc1de43f57d871b8dd5bbc4ac08e29735e5bd924a80ae3365894c46586c69c
+size 16404
diff --git a/checkpoint-184/rng_state_11.pth b/checkpoint-184/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..23409e203bb83be39eff8418e805d91747c08946
--- /dev/null
+++ b/checkpoint-184/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426561362b60e658e1751b86da707b69a414a6c2617d30d899579b240ecf8a09
+size 16404
diff --git a/checkpoint-184/rng_state_12.pth b/checkpoint-184/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..49455e9e228b777ac3b3a18cb6f1850fad800103
--- /dev/null
+++ b/checkpoint-184/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0632a9108fcb070b0ba52ae8a154f01b787e72d0bcd4a0516e9bd471f9cc82fb
+size 16404
diff --git a/checkpoint-184/rng_state_13.pth b/checkpoint-184/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cec0628486afad845592f74fdcee74d53cd21816
--- /dev/null
+++ b/checkpoint-184/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c887cc5ea956855e6256a5b3cf13955de5939d465c220bc2cf901a2e05d77c46
+size 16404
diff --git a/checkpoint-184/rng_state_14.pth b/checkpoint-184/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6df05003fa0e14c99cc69a3f2dc5e3b30c7f657c
--- /dev/null
+++ b/checkpoint-184/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea310b9de4439b6d7bafee14aa13fd32c18dd174d6f182eae3d00ccd6016282
+size 16404
diff --git a/checkpoint-184/rng_state_15.pth b/checkpoint-184/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3ae8eb15751aa0711e8dc27b59c1e21509d15661
--- /dev/null
+++ b/checkpoint-184/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aecbcf034ef6d003d99f9a6afcd1308317172053cf612866860b659789a9c491
+size 16404
diff --git a/checkpoint-184/rng_state_16.pth b/checkpoint-184/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7fd8a7d4f248205af596ead930e9d9be98156f93
--- /dev/null
+++ b/checkpoint-184/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaff9ea7fcc107ae1572d2e6c57a7098f3809dc2d57c2f8fedab359b96814a3f
+size 16404
diff --git a/checkpoint-184/rng_state_17.pth b/checkpoint-184/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..659892e91799915d81f608dbffef88361623bc0a
--- /dev/null
+++ b/checkpoint-184/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f518f180de20d760f856e65d299fc30ceda787812e1e2abd1e4e13cc6d8bd7
+size 16404
diff --git a/checkpoint-184/rng_state_18.pth b/checkpoint-184/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0faa4c3e07a5682a4577e4684b36ae7ce5a7011d
--- /dev/null
+++ b/checkpoint-184/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ef4137d8c104eac17ef435d338621836dc03c17d4e9088226b903114226f6a
+size 16404
diff --git a/checkpoint-184/rng_state_19.pth b/checkpoint-184/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..29f9ee3997f598c522a5937520b604bf6066a3ef
--- /dev/null
+++ b/checkpoint-184/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f26a469238e9b9acf2563a169ebdcf3e0529499fe03b7bb926842a15166087
+size 16404
diff --git a/checkpoint-184/rng_state_2.pth b/checkpoint-184/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5c5f8842502e587fc633de13e2c3eefe642c22a4
--- /dev/null
+++ b/checkpoint-184/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019258315b6e8d9f193ecd3613c152951d82d92704a24735350acd88567fa751
+size 16389
diff --git a/checkpoint-184/rng_state_20.pth b/checkpoint-184/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..57443c0c6521e36dc3eae31c175fb81060506190
--- /dev/null
+++ b/checkpoint-184/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866c25315899b876a4bac7eca23347c1b6c8366dbef5f849be9caa5cece7dc42
+size 16404
diff --git a/checkpoint-184/rng_state_21.pth b/checkpoint-184/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b6c4cfd74a2527dc1aa86d8f1c3794b007152ecd
--- /dev/null
+++ b/checkpoint-184/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c67e48a366efe83059d22e1fa06fc36fc63b98d7c863960c31a7641d97fc78
+size 16404
diff --git a/checkpoint-184/rng_state_22.pth b/checkpoint-184/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..84c595e5a63ace1c534828b5453f4ac098851adc
--- /dev/null
+++ b/checkpoint-184/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0432aa82360df23689eb772dfa329ed109c7424d64186e9c71034a218141af9
+size 16404
diff --git a/checkpoint-184/rng_state_23.pth b/checkpoint-184/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9accd4f93a142223172252d31c8a66204fc3d35e
--- /dev/null
+++ b/checkpoint-184/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a016e7e1201f823b0ebb10389440f4743bf056379a2e7152af78f3c3291faf4d
+size 16404
diff --git a/checkpoint-184/rng_state_24.pth b/checkpoint-184/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9c9dd179592a292c706685a9a359ecbcc8333ec6
--- /dev/null
+++ b/checkpoint-184/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8b283b046b63e0c4515e33d448b4c24c7e0805b8e7c40e6ebc54c8930065b5
+size 16404
diff --git a/checkpoint-184/rng_state_25.pth b/checkpoint-184/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..79a5526169b3571007856a4cf42a8a57899d96df
--- /dev/null
+++ b/checkpoint-184/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b8ef9a2a0f9fd8bded2b691aff88a40df067fbb98217d4197138b07a112837
+size 16404
diff --git a/checkpoint-184/rng_state_26.pth b/checkpoint-184/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b81622c2f30efd92e88877c55aa05df4868a53fa
--- /dev/null
+++ b/checkpoint-184/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1a0df642070e28ad6a61bc5e660d8200a1554eb2b53cfb93118b95557474a5
+size 16404
diff --git a/checkpoint-184/rng_state_27.pth b/checkpoint-184/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..695f247cb129d8c6db6987330c8b0aaf5f39c76f
--- /dev/null
+++ b/checkpoint-184/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ed950c47224f6b742f94d9b964e5afb26fb2fe88d444a126643c13e080655a
+size 16404
diff --git a/checkpoint-184/rng_state_28.pth b/checkpoint-184/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5b38f40c0bf8df1a58a394ed684975ef8ac37cf0
--- /dev/null
+++ b/checkpoint-184/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf6cd438fec5293df5476ede213993d869a8615864c9ba6894d1872d4368e4e
+size 16404
diff --git a/checkpoint-184/rng_state_29.pth b/checkpoint-184/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..66b009095c1a81e8a9500f0da4cb2d8b7427f741
--- /dev/null
+++ b/checkpoint-184/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11299f40e8a24c2dadd0e21ee6c41316bda3d2daa1f73279af1c9b26a58154ac
+size 16404
diff --git a/checkpoint-184/rng_state_3.pth b/checkpoint-184/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..41109056524de629c0306ee6423707868177dbfe
--- /dev/null
+++ b/checkpoint-184/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c952f8dee7b7a93ec6d15c84f3ca292b8531baa391db9aa8f3456d73bf1f84a
+size 16389
diff --git a/checkpoint-184/rng_state_30.pth b/checkpoint-184/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fdbdcd23fdaab39f528587ec3cbbbc0a484a59ce
--- /dev/null
+++ b/checkpoint-184/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76e1c392c866ea02f936352ac7a2a19dda256bbf1e754a350a35dbc72d8d129
+size 16404
diff --git a/checkpoint-184/rng_state_31.pth b/checkpoint-184/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3f9a4f6e6d87a75f9c4b02b1905db9af6d87b95d
--- /dev/null
+++ b/checkpoint-184/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e188207320ff582b624b039cd827b8072e74bf9a4955b3115c1825bbc615454
+size 16404
diff --git a/checkpoint-184/rng_state_4.pth b/checkpoint-184/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a16d8ff6ae130aafd337d678eee1b4b2e37f6aa9
--- /dev/null
+++ b/checkpoint-184/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712477618fad418b6b94ccb1ed236208ee040f3558356e30e9e8e712ead2cecc
+size 16389
diff --git a/checkpoint-184/rng_state_5.pth b/checkpoint-184/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..be4b202d6de32e330ebe822ec0da13c94f777860
--- /dev/null
+++ b/checkpoint-184/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098ff73927280eb00e57a0d9d919de4fcb8b90d3b0a7933d6c38c27984685283
+size 16389
diff --git a/checkpoint-184/rng_state_6.pth b/checkpoint-184/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d82a9b1753ede27b52b0cafafdd93d73384ca768
--- /dev/null
+++ b/checkpoint-184/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f908c2bf424c68db04fd9ec43164f123ef78f84b92a8504e908f7d203eff062
+size 16389
diff --git a/checkpoint-184/rng_state_7.pth b/checkpoint-184/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..15924bf92037d94fbff0a7c5551330c198b5baeb
--- /dev/null
+++ b/checkpoint-184/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e13bc810b5dfa72907076f8b82c35768b18a269e4b779507d40051f376278a
+size 16389
diff --git a/checkpoint-184/rng_state_8.pth b/checkpoint-184/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3778f5f734e75a1482129d64b8b415c6263ec818
--- /dev/null
+++ b/checkpoint-184/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26bc134f76ace6d09f392c618500d5f3932697ca8d858ff6fffdfc329793fa70
+size 16389
diff --git a/checkpoint-184/rng_state_9.pth b/checkpoint-184/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dbe35a55e0a9704c5f2867d437793a445dcf3f81
--- /dev/null
+++ b/checkpoint-184/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2287c37af3cf13c9ffdbe9b18a1d37c036dcfd67ccf5c73ec448fec4fbf9c199
+size 16389
diff --git a/checkpoint-184/scheduler.pt b/checkpoint-184/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..00a2019d82a4a57a3a96a0dfded66d79b59d9bed
--- /dev/null
+++ b/checkpoint-184/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538151d1917205f48c429d1a4100a25e21b4fa31db908bcc91ce348d7a9e1301
+size 1465
diff --git a/checkpoint-184/tokenizer.json b/checkpoint-184/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-184/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-184/tokenizer_config.json b/checkpoint-184/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-184/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-184/trainer_state.json b/checkpoint-184/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..8371dd8bf344577014c745f68346b8894598944a
--- /dev/null
+++ b/checkpoint-184/trainer_state.json
@@ -0,0 +1,394 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9206349206349205,
+  "eval_steps": 500,
+  "global_step": 184,
+  "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
+    },
+    {
+      "entropy": 0.06085996180772781,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.13919851183891296,
+      "learning_rate": 8.657988130699848e-06,
+      "loss": 0.06093168258666992,
+      "mean_token_accuracy": 0.975907814502716,
+      "num_tokens": 62928491.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.06154095679521561,
+      "epoch": 2.3015873015873014,
+      "grad_norm": 0.1471860557794571,
+      "learning_rate": 7.096195292140173e-06,
+      "loss": 0.06225389242172241,
+      "mean_token_accuracy": 0.9755991458892822,
+      "num_tokens": 65183865.0,
+      "step": 145
+    },
+    {
+      "entropy": 0.06028798446059227,
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.1381225436925888,
+      "learning_rate": 5.666233057256756e-06,
+      "loss": 0.05946478247642517,
+      "mean_token_accuracy": 0.9772057175636292,
+      "num_tokens": 67455033.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.05786149725317955,
+      "epoch": 2.4603174603174605,
+      "grad_norm": 0.1443004608154297,
+      "learning_rate": 4.378630628514388e-06,
+      "loss": 0.05805859565734863,
+      "mean_token_accuracy": 0.9774470567703247,
+      "num_tokens": 69702174.0,
+      "step": 155
+    },
+    {
+      "entropy": 0.05872737467288971,
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.15280300378799438,
+      "learning_rate": 3.2428689742461188e-06,
+      "loss": 0.058740425109863284,
+      "mean_token_accuracy": 0.9766229271888733,
+      "num_tokens": 71937597.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.05862027704715729,
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.13461482524871826,
+      "learning_rate": 2.267311017694107e-06,
+      "loss": 0.05860599875450134,
+      "mean_token_accuracy": 0.9768976211547852,
+      "num_tokens": 74179028.0,
+      "step": 165
+    },
+    {
+      "entropy": 0.059079910069704054,
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.14060291647911072,
+      "learning_rate": 1.4591400585218544e-06,
+      "loss": 0.058356738090515135,
+      "mean_token_accuracy": 0.977295708656311,
+      "num_tokens": 76426869.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.058903105556964874,
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.1497332900762558,
+      "learning_rate": 8.243068802169906e-07,
+      "loss": 0.05870553255081177,
+      "mean_token_accuracy": 0.9769431948661804,
+      "num_tokens": 78682661.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.060907012224197386,
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.1522296518087387,
+      "learning_rate": 3.674859328472752e-07,
+      "loss": 0.060805785655975345,
+      "mean_token_accuracy": 0.9766618490219117,
+      "num_tokens": 80928205.0,
+      "step": 180
+    }
+  ],
+  "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": 4.611729142046523e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-184/training_args.bin b/checkpoint-184/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-184/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-189/README.md b/checkpoint-189/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-189/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-189/adapter_config.json b/checkpoint-189/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-189/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-189/adapter_model.safetensors b/checkpoint-189/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..612d14caf04604788dbb5d930ecb3d229d7cf435
--- /dev/null
+++ b/checkpoint-189/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7196a05434a33d93df0f37c80b26acc5c0c98fc254f9798c9942abd713dfe65d
+size 1384975816
diff --git a/checkpoint-189/chat_template.jinja b/checkpoint-189/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-189/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-189/optimizer.pt b/checkpoint-189/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7a75a85b0b687571c7cfc700be6b3a9aa5634c54
--- /dev/null
+++ b/checkpoint-189/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f6cda1a64884aa5162cb22c7cdeae97ae54feabde052be88ca8eca01ed775f
+size 2770239667
diff --git a/checkpoint-189/rng_state_0.pth b/checkpoint-189/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..73bef69d7a0adca7b6b73280085e9d6506f7637f
--- /dev/null
+++ b/checkpoint-189/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e724995e1d60862f78c717c204b1db85a22e64cbc90a10103a5bf24d682849
+size 16389
diff --git a/checkpoint-189/rng_state_1.pth b/checkpoint-189/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3cf7f01142f0fc67026e53d80ae7bc73e1b13c91
--- /dev/null
+++ b/checkpoint-189/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109f180cfa2a10bb96561e5ecabd0505080e75962d1870356a7e2b7b4b35e03b
+size 16389
diff --git a/checkpoint-189/rng_state_10.pth b/checkpoint-189/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5fe04e2b9621196a011c4aad612c3bab37bfc5cd
--- /dev/null
+++ b/checkpoint-189/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29166671e6d2b5d10ef2591fb5b54a853a346a3832d354d5a946acf83819017a
+size 16404
diff --git a/checkpoint-189/rng_state_11.pth b/checkpoint-189/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d0b7e9f152d2b223ed20ce77febd726ad37560bc
--- /dev/null
+++ b/checkpoint-189/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14be7984eef81f246749ad01b5cdb45752cdcc6839e135c7060ec79068437d50
+size 16404
diff --git a/checkpoint-189/rng_state_12.pth b/checkpoint-189/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7582db2c77fb084366bba26ac5df6681241bd924
--- /dev/null
+++ b/checkpoint-189/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abc63c249e19974d6e2f1fda552b6b33efa6cac16bac2a635083495f782e528
+size 16404
diff --git a/checkpoint-189/rng_state_13.pth b/checkpoint-189/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..34068662a059b58d6e77bbdbfd52be525500e902
--- /dev/null
+++ b/checkpoint-189/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de875d2a6b4c25333c745a01b156bf0d7d2dbba51272a06bf841744c5301f4b
+size 16404
diff --git a/checkpoint-189/rng_state_14.pth b/checkpoint-189/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4dd3f6c1aeb48e0ce434f1622692f24a6c1f9e28
--- /dev/null
+++ b/checkpoint-189/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105cba3d685858423c8d8bc9be6f4d7d2dc4be8b945d86279ab8598ab82b28a6
+size 16404
diff --git a/checkpoint-189/rng_state_15.pth b/checkpoint-189/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d1559a94f8c8a1c81d89ac1e087b45607ed2f8b8
--- /dev/null
+++ b/checkpoint-189/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2b761355fd29449236de312862aab141d5f4d9b14ca9021166c85e4f7d06b4
+size 16404
diff --git a/checkpoint-189/rng_state_16.pth b/checkpoint-189/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..97af098eb5c1cdc61a03ef3c98cb18e7d88e9e17
--- /dev/null
+++ b/checkpoint-189/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f56782bdb7215644e141ee43d4d7ed8ab4738da3f1d8e099f8ea43441760f7
+size 16404
diff --git a/checkpoint-189/rng_state_17.pth b/checkpoint-189/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..daa783c6c9bba604f4747726eac317c9980272ac
--- /dev/null
+++ b/checkpoint-189/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06b8d2bf7c089a55a19f7da179f0e9fba5f17f5d6a79fb8f03b75579f77efe1
+size 16404
diff --git a/checkpoint-189/rng_state_18.pth b/checkpoint-189/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1f5971bd97ce3db70c8c087b8ee82ac9f1df7ab5
--- /dev/null
+++ b/checkpoint-189/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09141715eba76be1e1ee95a96fc27b5fdc9122db891676761fdfaae9c8a1be96
+size 16404
diff --git a/checkpoint-189/rng_state_19.pth b/checkpoint-189/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2f593b7e4f33e8cef700436b3f316497630e383f
--- /dev/null
+++ b/checkpoint-189/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1bee15a057ed7da905ba690c1791eed3cba6727a88b10d4a429f07b1572240
+size 16404
diff --git a/checkpoint-189/rng_state_2.pth b/checkpoint-189/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a47c9b4381244000f080e5909478ea4806e7d743
--- /dev/null
+++ b/checkpoint-189/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39b523fb153cd0a898b743fefb6e83d9a73b4a7ae06fe6f49d743374b9baeef
+size 16389
diff --git a/checkpoint-189/rng_state_20.pth b/checkpoint-189/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..85f01739eb6ce89ee2208e229a7c83aa40157ef2
--- /dev/null
+++ b/checkpoint-189/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f23e6615f54656c8e058c1a0b2dc4a564b8fdb60809e0abf34bd92fb460fc05
+size 16404
diff --git a/checkpoint-189/rng_state_21.pth b/checkpoint-189/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..690ca92c9823b949c4d362d96b697c24a959afd8
--- /dev/null
+++ b/checkpoint-189/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950ae8735b1ed8401cc8d7f2b42ae96c29511140597ad8067265013bdab998f3
+size 16404
diff --git a/checkpoint-189/rng_state_22.pth b/checkpoint-189/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1ed3deb10d0b4e0fc86faed022046bd1025c6bab
--- /dev/null
+++ b/checkpoint-189/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac66e7965e9a89456707a396ce1777f2ae3ca26ae24dcd3f0f534337063f552
+size 16404
diff --git a/checkpoint-189/rng_state_23.pth b/checkpoint-189/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2000f35a7f9d8d9e682230dd36a7f1dc209b67b5
--- /dev/null
+++ b/checkpoint-189/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e617958e79707e1a4001b686ad4ff154917b4a522685c2011da1fa1f198a25e1
+size 16404
diff --git a/checkpoint-189/rng_state_24.pth b/checkpoint-189/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fe8a9c8bbd0f45b5e4dd0b83ef55a762cd3fbf0c
--- /dev/null
+++ b/checkpoint-189/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28018a6cbeb1051bab51f28be27742e344a78461c3895031878254e44a4cc76a
+size 16404
diff --git a/checkpoint-189/rng_state_25.pth b/checkpoint-189/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6beb5b5a87a120262b159b427402ddbd020beb42
--- /dev/null
+++ b/checkpoint-189/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d721925bec46b3d7a68f2db1c22fb9676e2f920e09038a7651502c659bf7d931
+size 16404
diff --git a/checkpoint-189/rng_state_26.pth b/checkpoint-189/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0bb8840a5613dffe8f35978a35b69f65acd27396
--- /dev/null
+++ b/checkpoint-189/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe40a93d84a6ef89b03928cbbaacf904a1798b01fc6d4cf8302c08fbba133aa
+size 16404
diff --git a/checkpoint-189/rng_state_27.pth b/checkpoint-189/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b62c31b450c99b91d82b90313ab8e101ffaf2af6
--- /dev/null
+++ b/checkpoint-189/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b065e1b1ef5d828beb1e1d2da10fec865c32075e757cff42b27b9b0a216649
+size 16404
diff --git a/checkpoint-189/rng_state_28.pth b/checkpoint-189/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0ba0cd51d6cb259b917edaf2a7178a461d757259
--- /dev/null
+++ b/checkpoint-189/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4df692087a4d969dc53a0d1eee73bf611d13878ad088e621b9f587b554c091
+size 16404
diff --git a/checkpoint-189/rng_state_29.pth b/checkpoint-189/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0e3dbb553658e4dceda6e9e24f8615ba5b3cb516
--- /dev/null
+++ b/checkpoint-189/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3447f1ca3b950c534f537863a87b7fc5748e895024277c5e5dd3eafbc85b721
+size 16404
diff --git a/checkpoint-189/rng_state_3.pth b/checkpoint-189/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2e10afdfab2bc92a764007ccee3d903124b7c9ac
--- /dev/null
+++ b/checkpoint-189/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82eea653970b2da0e9a479e9ddf35ef4c27eb4d066069165993fc964eede3a8c
+size 16389
diff --git a/checkpoint-189/rng_state_30.pth b/checkpoint-189/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cda7adf8bb550eb8d863a45b4725d5b8c8323e42
--- /dev/null
+++ b/checkpoint-189/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa91624ff14d8edae3c2249dcf22abcd027a6121b7eae455e8cf50a8c3449c7
+size 16404
diff --git a/checkpoint-189/rng_state_31.pth b/checkpoint-189/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..83729a71f22265f0d383638150de7fc2276d693e
--- /dev/null
+++ b/checkpoint-189/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd0c3ca0b7fdffca03e1213ba646b15362d1e279cd02c6afed998fd5b2deea4
+size 16404
diff --git a/checkpoint-189/rng_state_4.pth b/checkpoint-189/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9c2ecc51616d9f02102214e70c0dcfa5e474a6f0
--- /dev/null
+++ b/checkpoint-189/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584cd619826320eba9528da572ab178c9e336c24564ef8bad4fe3acfb409d7ce
+size 16389
diff --git a/checkpoint-189/rng_state_5.pth b/checkpoint-189/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..55f0737d2e8f1c8b30e118adfc4deee6dbe523e8
--- /dev/null
+++ b/checkpoint-189/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f361298be25c8a7fb40b2c871ab13bfc2946d8b1ba58a13edc84a367fe99fee9
+size 16389
diff --git a/checkpoint-189/rng_state_6.pth b/checkpoint-189/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c419b7ca9705c7e079245b8cf8df043f9674813f
--- /dev/null
+++ b/checkpoint-189/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfcca91274706065950cffb16e25e66138c0c544e3175464808593360ab9f36
+size 16389