diff --git a/checkpoint-80/rng_state_5.pth b/checkpoint-80/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b096921a2d363a23167ec0f72aa2c4cb48bf4653
--- /dev/null
+++ b/checkpoint-80/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6b1177b8ca8dbf34bd6fd18a209180b9227c0cf77d461fbd7e0b9f9c95a3f5
+size 16389
diff --git a/checkpoint-80/rng_state_6.pth b/checkpoint-80/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..11cc9b6e381aa4515f69a487f354dbaaefaf7ea2
--- /dev/null
+++ b/checkpoint-80/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adc9a8b3dd0672048a55e956ef3c6c8a2178a4b454656c51af89b2cef258c01
+size 16389
diff --git a/checkpoint-80/rng_state_7.pth b/checkpoint-80/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1152e64fa5a679017de6cbcec1b0bfec71f2bb7f
--- /dev/null
+++ b/checkpoint-80/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b699180989ac2f292f3f75c343c07702e28771ea0fd791bd5d83bc45c244938e
+size 16389
diff --git a/checkpoint-80/rng_state_8.pth b/checkpoint-80/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..13c3a855c5e4308e110cd3be89e3f6ac55368aa6
--- /dev/null
+++ b/checkpoint-80/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab90162c14dfb0bd58c218edc0c0e591e8650193664e19c780b9602d9f07e95a
+size 16389
diff --git a/checkpoint-80/rng_state_9.pth b/checkpoint-80/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c4ca3fc1c359bbf8f683ce3696a299ddd9b37925
--- /dev/null
+++ b/checkpoint-80/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f98a4e76b0787562ebac45d5f59570f9d35455edeb67046ee33684076cc0b9
+size 16389
diff --git a/checkpoint-80/scheduler.pt b/checkpoint-80/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2a75b30a2941f2e5f0b0c391b8759717808ea600
--- /dev/null
+++ b/checkpoint-80/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855c5ec04e2add9a2ec37fe4c15cf2455a0d4ff6599359be5099580756d589f2
+size 1465
diff --git a/checkpoint-80/tokenizer.json b/checkpoint-80/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-80/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-80/tokenizer_config.json b/checkpoint-80/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-80/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-80/trainer_state.json b/checkpoint-80/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d3de346492141f2aecd0d7344629523a2c8b20e4
--- /dev/null
+++ b/checkpoint-80/trainer_state.json
@@ -0,0 +1,194 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2698412698412698,
+  "eval_steps": 500,
+  "global_step": 80,
+  "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
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0051969670884884e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-80/training_args.bin b/checkpoint-80/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-80/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-88/README.md b/checkpoint-88/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-88/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-88/adapter_config.json b/checkpoint-88/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-88/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-88/adapter_model.safetensors b/checkpoint-88/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1474192895f3d72bda46bafb2362b8642828af0b
--- /dev/null
+++ b/checkpoint-88/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37cbb486508a6dee878185dc49a6b8e5ae816602c6548da9c7134a30b273bd60
+size 1384975816
diff --git a/checkpoint-88/chat_template.jinja b/checkpoint-88/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-88/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-88/optimizer.pt b/checkpoint-88/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f203c4989a71f8f60be6bf78bd4ba9723afaf9ae
--- /dev/null
+++ b/checkpoint-88/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf34f1220cb78911cebc9022229e7c77b507e2888e1454030846c66f55f2dc2
+size 2770239667
diff --git a/checkpoint-88/rng_state_0.pth b/checkpoint-88/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2588bec155c8ce0f0443915993fb6978559b715b
--- /dev/null
+++ b/checkpoint-88/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ae0f631520c88bdb2a6afd38958318a15b74b5a686f55b5a8460a1dbd25958
+size 16389
diff --git a/checkpoint-88/rng_state_1.pth b/checkpoint-88/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d26671e89762bdcc2253fe96bb1f5aa9264ea41
--- /dev/null
+++ b/checkpoint-88/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b958c6e3c89f080e73b52e8625f7f18d29f1dd38b9fe47afde295d8b8fedd1
+size 16389
diff --git a/checkpoint-88/rng_state_10.pth b/checkpoint-88/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c8075dbd204959f674da6ba9841ff6d807bb9b38
--- /dev/null
+++ b/checkpoint-88/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d39c42a0e99b649060daad50babf4f0a789d5aa25709c578baa4c9b3fb6571
+size 16404
diff --git a/checkpoint-88/rng_state_11.pth b/checkpoint-88/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ac26e98823409239bd845b3198e2db1d967d8c0a
--- /dev/null
+++ b/checkpoint-88/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576993ce0cbca547dcc3c3d93624fde489b1dd9d5cd6a7b9ff80f48c676b9492
+size 16404
diff --git a/checkpoint-88/rng_state_12.pth b/checkpoint-88/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a76e1d1b0e625bb46ea5219be8c202ef3e0ded33
--- /dev/null
+++ b/checkpoint-88/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fb61175b69ddef3dbba3044851653a84498f9702b9f341f0fb23e677428af7
+size 16404
diff --git a/checkpoint-88/rng_state_13.pth b/checkpoint-88/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1e87435f4ff6b269861468b45d1fdb9336f62f48
--- /dev/null
+++ b/checkpoint-88/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28aadcf527f9aca3ebaaf67d53bb39595758a220ac83128227894564bdd3c1c2
+size 16404
diff --git a/checkpoint-88/rng_state_14.pth b/checkpoint-88/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..00bfcc41d361f1ad01d5d41517f15366cbf1b7db
--- /dev/null
+++ b/checkpoint-88/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a16b8addd245ff3e664264d67e749d83062d6e188d30b52e503814b4adf1235
+size 16404
diff --git a/checkpoint-88/rng_state_15.pth b/checkpoint-88/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c1e11f5191739e775b538620d24176ffa3061af2
--- /dev/null
+++ b/checkpoint-88/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b6e967702eced3777973bfee18d0160ebf5ce04fd7b2d58206d3255a70aab7
+size 16404
diff --git a/checkpoint-88/rng_state_16.pth b/checkpoint-88/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..913d9da29c7eb1994c03a03117006f1a8b930567
--- /dev/null
+++ b/checkpoint-88/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f556caed1af3ffe6e776d9e46650a640db49fcf4524cf1380a0f2362a9dd7ff
+size 16404
diff --git a/checkpoint-88/rng_state_17.pth b/checkpoint-88/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e09f8786c19ff1fb1954fbfba1bbd972230c3b35
--- /dev/null
+++ b/checkpoint-88/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea02ba0176fde363cc125b69b4657e7d63df95630bae08c643f208de8f65f75
+size 16404
diff --git a/checkpoint-88/rng_state_18.pth b/checkpoint-88/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2724369e92fa082c734e326a56c7d87940548ad1
--- /dev/null
+++ b/checkpoint-88/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13a7bce165b68191a479b7bdea3b84c7d74354340a3d60ea07b6e278a9ddc07
+size 16404
diff --git a/checkpoint-88/rng_state_19.pth b/checkpoint-88/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..99c01009bb338ac7912a240d03e0a42c43a24c00
--- /dev/null
+++ b/checkpoint-88/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0de654079193e14bb3c455ef2f8f9e5293bf57f8d411b3c44e7cb3a249e38c
+size 16404
diff --git a/checkpoint-88/rng_state_2.pth b/checkpoint-88/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f4aef33b88e8bfb39c6ff8ee5c9ea5137a5493dc
--- /dev/null
+++ b/checkpoint-88/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864bf944b7fe59c3d076145cb591c0b4202157a6de0befcb0b5797d05962d20e
+size 16389
diff --git a/checkpoint-88/rng_state_20.pth b/checkpoint-88/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4504e7ab8624429df9a0d31afe65473b6b857267
--- /dev/null
+++ b/checkpoint-88/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067f6d8b8579f6425cb6b76596f0886f844506f9186834c5b6e3e989d08df39d
+size 16404
diff --git a/checkpoint-88/rng_state_21.pth b/checkpoint-88/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..99303c892dfc9f2f4dc9d91dee32f54832920a24
--- /dev/null
+++ b/checkpoint-88/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e131d8cb2422a3bccdb05801b758de2019bf20adf3fe806812fe3da246773c0d
+size 16404
diff --git a/checkpoint-88/rng_state_22.pth b/checkpoint-88/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5bcb5ae1b8793017331e0e2d449631286e17f4f2
--- /dev/null
+++ b/checkpoint-88/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56232f8010fb324ef8e428a1b59671e3314cf8fa1205604bc9b0d10155f79ba
+size 16404
diff --git a/checkpoint-88/rng_state_23.pth b/checkpoint-88/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b5a079bc5f40fd30b7be5c39b8f2c7f58480cfb2
--- /dev/null
+++ b/checkpoint-88/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1194130652a967ed6e8f01b7f931aab16aaab7854abbe0843fc154d7ef8278d
+size 16404
diff --git a/checkpoint-88/rng_state_24.pth b/checkpoint-88/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fc55d1ac883f0d69fa5cd0c1a1be4633acde5224
--- /dev/null
+++ b/checkpoint-88/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596aaddaafbd1422744895e1d31debc933e3476206afb0bd2ede16f38a0a595a
+size 16404
diff --git a/checkpoint-88/rng_state_25.pth b/checkpoint-88/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ccec09d50e714c50c67ea5d7f67375407e484c6a
--- /dev/null
+++ b/checkpoint-88/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f842707323aecfd30ff8148cc9bd1d940704a4a573a40f6754079302ee6078
+size 16404
diff --git a/checkpoint-88/rng_state_26.pth b/checkpoint-88/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4f0b22d1f82297c36d13d2e92c8563848a207b02
--- /dev/null
+++ b/checkpoint-88/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8808086f3f3e338e55d89e2046a31ca289e2197277c3f34573ef9c47a52fb6ca
+size 16404
diff --git a/checkpoint-88/rng_state_27.pth b/checkpoint-88/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7a6433dfb57c26d63c02b44584f3f2da412a3742
--- /dev/null
+++ b/checkpoint-88/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dce8a99e08f9122e6f485ed11452889b063151d8655dad71a38397312df4ec0
+size 16404
diff --git a/checkpoint-88/rng_state_28.pth b/checkpoint-88/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..de8119eec3264c6849e782ad8eec4e0aa00db7fe
--- /dev/null
+++ b/checkpoint-88/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd7bfb236aade8570d551d55438500104df624a0423ee1587131e3f3dbd6c50
+size 16404
diff --git a/checkpoint-88/rng_state_29.pth b/checkpoint-88/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3937dfd12dff70dbfb49b9652771d5c133164aea
--- /dev/null
+++ b/checkpoint-88/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfb247beaca7fedae2d6d9ce303487f8f50f8020c5dd9f3bd2a19edde072434
+size 16404
diff --git a/checkpoint-88/rng_state_3.pth b/checkpoint-88/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..792f365afb633c8f25372ac7d6fff2ad42e2d907
--- /dev/null
+++ b/checkpoint-88/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d381ca785a7ecce76faa769336d5e9287283042919687663a237440b7f641981
+size 16389
diff --git a/checkpoint-88/rng_state_30.pth b/checkpoint-88/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..002730618f55b6d287308734f391a0a640d8341f
--- /dev/null
+++ b/checkpoint-88/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4cd686b5ced72e3919087efef025a8cc19afd8a1daa780d125f93fc1aca831
+size 16404
diff --git a/checkpoint-88/rng_state_31.pth b/checkpoint-88/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ea6a3e5f04f00ec0c2471628ae611e849e929785
--- /dev/null
+++ b/checkpoint-88/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2065bb03ec0cb8c7adfb8e58078f7a2a74088046998c76cbab4d882610f81e0
+size 16404
diff --git a/checkpoint-88/rng_state_4.pth b/checkpoint-88/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4e0e83eb55f7f51080ff0d5fd6ee2acd6e51c995
--- /dev/null
+++ b/checkpoint-88/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25b2926e255ab5ac840a9f11eb944262bc85d98693c39982d8dcc3076515a26
+size 16389
diff --git a/checkpoint-88/rng_state_5.pth b/checkpoint-88/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6014590755581e977b040c571edacde7c975f35e
--- /dev/null
+++ b/checkpoint-88/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1319a784c42a0f542af3dde1ebaf7211e2a2ef58e78f76b15c5559abd34fcd
+size 16389
diff --git a/checkpoint-88/rng_state_6.pth b/checkpoint-88/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f7e8976a778eec4b6b428462f63dbc6e8c4b56ab
--- /dev/null
+++ b/checkpoint-88/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bb2ebaaa80bc508c22054e7a05130706ae1b7fe42dd5c16e54965b6ce6378b
+size 16389
diff --git a/checkpoint-88/rng_state_7.pth b/checkpoint-88/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..079b4106b07984b078d3587d5dc86745dadbdf67
--- /dev/null
+++ b/checkpoint-88/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc096aa1d338785c5fd41f19069a46da703035e2efaf94e33c79fc9d31d068c4
+size 16389
diff --git a/checkpoint-88/rng_state_8.pth b/checkpoint-88/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fde62d96f39d6a7289489c90c6ae40fb8762c3cd
--- /dev/null
+++ b/checkpoint-88/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1758369857e543cf7017900da875d6b45582ed42103ee19b32680d536c7d29
+size 16389
diff --git a/checkpoint-88/rng_state_9.pth b/checkpoint-88/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b90e1e61e12c6b6e925f7583c22ea8e054820a16
--- /dev/null
+++ b/checkpoint-88/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06cfb0453654cdb18b0bd0eebbd8284f35f36cdd03b37e3eda5defe012cbedc1
+size 16389
diff --git a/checkpoint-88/scheduler.pt b/checkpoint-88/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2f06cc7583f5d01dd40298baaa21a8f55e5647fb
--- /dev/null
+++ b/checkpoint-88/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14d21de0f8a8e8e3bdf3b08844a35b70e11a05a6ed32dd16e673b6b89f5cf61
+size 1465
diff --git a/checkpoint-88/tokenizer.json b/checkpoint-88/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-88/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-88/tokenizer_config.json b/checkpoint-88/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-88/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-88/trainer_state.json b/checkpoint-88/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..345fedeadf056840723e6dd179c1da976c4a876c
--- /dev/null
+++ b/checkpoint-88/trainer_state.json
@@ -0,0 +1,204 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3968253968253967,
+  "eval_steps": 500,
+  "global_step": 88,
+  "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
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2061441073178214e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-88/training_args.bin b/checkpoint-88/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-88/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969
diff --git a/checkpoint-96/README.md b/checkpoint-96/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..37c2b88acde05c51d17a8d3ed589f71f09a0a796
--- /dev/null
+++ b/checkpoint-96/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-96/adapter_config.json b/checkpoint-96/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9c8c67dac500939db557df4279de3bcece92537
--- /dev/null
+++ b/checkpoint-96/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-96/adapter_model.safetensors b/checkpoint-96/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1d69f7373a368a013010b4d3eba57c193336e63d
--- /dev/null
+++ b/checkpoint-96/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4834f0040a03ab1790427305add73c7c8b435057046b679d405c980c673fb457
+size 1384975816
diff --git a/checkpoint-96/chat_template.jinja b/checkpoint-96/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fd6d05ba46a2052e1ab3ac65e3399865cfcda63d
--- /dev/null
+++ b/checkpoint-96/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-96/optimizer.pt b/checkpoint-96/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8739d834d08018b2f00386e29142f625294c06d4
--- /dev/null
+++ b/checkpoint-96/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f32e3e1b85e9bfe9ce7f792fa70213bcb2517a46f1592fbba8b0784634886a7
+size 2770239667
diff --git a/checkpoint-96/rng_state_0.pth b/checkpoint-96/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4e242e2906f3de3abc7048c2d22bb61097700300
--- /dev/null
+++ b/checkpoint-96/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f53bd0c86ab82445c737289dbb6db9e760bc5505f67738fc8be6c52a6d604b4
+size 16389
diff --git a/checkpoint-96/rng_state_1.pth b/checkpoint-96/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..385ed36d749b03db9b2bb20ea085ac1caae93c80
--- /dev/null
+++ b/checkpoint-96/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bfc88f8f87f663d79ea1a6180ecaf147233b724a48eb184ad7916453a17128
+size 16389
diff --git a/checkpoint-96/rng_state_10.pth b/checkpoint-96/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9dc6a43fd96bee4712b6d05df28b1daa0a8f398e
--- /dev/null
+++ b/checkpoint-96/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ffcc4ff4ff730bd2ceff16f720616f0504df376102674079cdb08d8f005031
+size 16404
diff --git a/checkpoint-96/rng_state_11.pth b/checkpoint-96/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c3b7a01d69b6d4af469a06dcabf1f5326e00671a
--- /dev/null
+++ b/checkpoint-96/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0cf6fd8eb80097f1654e9cec20a6f252761dd32d506f2d2406329844c0f5b27
+size 16404
diff --git a/checkpoint-96/rng_state_12.pth b/checkpoint-96/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..09ec40d5aebb1cfd2d222e8762a8ffcddac1b9ca
--- /dev/null
+++ b/checkpoint-96/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8e6b6efc64c615c1d15e1288b68b1d5ee6f56765a5225f6c491d08ec4dc7f2
+size 16404
diff --git a/checkpoint-96/rng_state_13.pth b/checkpoint-96/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5afc07a1f8954e322eba2439f9ae7a11e706750c
--- /dev/null
+++ b/checkpoint-96/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9d04c211f617bee116f8c113efb354cab61e8165ae16bf8e40e16b63fd666f
+size 16404
diff --git a/checkpoint-96/rng_state_14.pth b/checkpoint-96/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..42fe95e925c24693b0866071a11c901d9c736406
--- /dev/null
+++ b/checkpoint-96/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6cfebcbdf26e2c3360ca72430c811875fb9e364783a283bb60f966a97553d9
+size 16404
diff --git a/checkpoint-96/rng_state_15.pth b/checkpoint-96/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..65d020c99ffd3ceda4fddbcc52e72d143d9f30ff
--- /dev/null
+++ b/checkpoint-96/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5ac5354d903503f7ca999105c0294ac20ae36c2a3c2655c1deeec15337c1d0
+size 16404
diff --git a/checkpoint-96/rng_state_16.pth b/checkpoint-96/rng_state_16.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6dbeaedee646b518d51a3ebd01ab5122c8584aad
--- /dev/null
+++ b/checkpoint-96/rng_state_16.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9ffe42fe702859319444398d7b4bb29a7e317c9a1fdd218d9d228800afb9c8
+size 16404
diff --git a/checkpoint-96/rng_state_17.pth b/checkpoint-96/rng_state_17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..07a9e92fe9d04f6d8fb09719796d9c4ef2b16fd4
--- /dev/null
+++ b/checkpoint-96/rng_state_17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc15634fe0b7238aa102f6b847f8106dc957d0ebf4ac604feeac4ffdc3e2a207
+size 16404
diff --git a/checkpoint-96/rng_state_18.pth b/checkpoint-96/rng_state_18.pth
new file mode 100644
index 0000000000000000000000000000000000000000..10acf91b1e7522118c394491401fed5083eb7546
--- /dev/null
+++ b/checkpoint-96/rng_state_18.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9b5c4327a080896d53063b06f04d698ec6b5126b4a4d3b9f506c936dddcd5d
+size 16404
diff --git a/checkpoint-96/rng_state_19.pth b/checkpoint-96/rng_state_19.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cc895b0fcd07b94f5cad0e70a280833fc5cff762
--- /dev/null
+++ b/checkpoint-96/rng_state_19.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8dbbadbcc6e11650fdcd538f0d60559a5878ad0438c3679eb6e12c382c43ad
+size 16404
diff --git a/checkpoint-96/rng_state_2.pth b/checkpoint-96/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a3889325a82efba1f608cafdeace9cc75f6433bc
--- /dev/null
+++ b/checkpoint-96/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a408e4cf9044163c7d5a9ae7f062f7d25ab18d07492a83b20d53b36dded53906
+size 16389
diff --git a/checkpoint-96/rng_state_20.pth b/checkpoint-96/rng_state_20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..68f606ddb52b0510c89a8a783dc2766c014fa0b5
--- /dev/null
+++ b/checkpoint-96/rng_state_20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4265112f92f4408f70219b96b4ce1f18fae2301b731ab613c3180cf8977a6db
+size 16404
diff --git a/checkpoint-96/rng_state_21.pth b/checkpoint-96/rng_state_21.pth
new file mode 100644
index 0000000000000000000000000000000000000000..00e1d5e52da5779feee74520d15827dd30613ae8
--- /dev/null
+++ b/checkpoint-96/rng_state_21.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291def10f9adb59094762bd61736789f2e86b01b0a3d1c0c2cb34ddb30e66895
+size 16404
diff --git a/checkpoint-96/rng_state_22.pth b/checkpoint-96/rng_state_22.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a36f2bca1bfa27ee02242cd4c3f3fd698b1ad3ce
--- /dev/null
+++ b/checkpoint-96/rng_state_22.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17124cd30ebbc64fbf70da32b10c2a1bbb837bfc14b76a6c4f12778866271a3a
+size 16404
diff --git a/checkpoint-96/rng_state_23.pth b/checkpoint-96/rng_state_23.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0d32c1239c44ed261c8d62b565986363ff9b1ade
--- /dev/null
+++ b/checkpoint-96/rng_state_23.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec8f509ae4b1af8150f66c75f85d175ec40aceacdd6873e096ece6ab483773c
+size 16404
diff --git a/checkpoint-96/rng_state_24.pth b/checkpoint-96/rng_state_24.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f117715f6eb67eaebdb6f49bbdb0f9bbb6a25f2c
--- /dev/null
+++ b/checkpoint-96/rng_state_24.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8f878c46a91797a2d38e1717ddfd624e279c931a46c0259ad7d070611114ae
+size 16404
diff --git a/checkpoint-96/rng_state_25.pth b/checkpoint-96/rng_state_25.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f4e045394742f79cf713a6f3f680b29a5a681dbf
--- /dev/null
+++ b/checkpoint-96/rng_state_25.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e469e3dc2a06b8727a4e3a854355b4d3d6d455bc39a760921e2a0e07d95db3c0
+size 16404
diff --git a/checkpoint-96/rng_state_26.pth b/checkpoint-96/rng_state_26.pth
new file mode 100644
index 0000000000000000000000000000000000000000..18f398ea505f19476b328c23f8baca3a9a5f609c
--- /dev/null
+++ b/checkpoint-96/rng_state_26.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723aa1d76a98f7f3efd4488c97e2d398fad9f06e90d1b3c7e31e6c72e55e7467
+size 16404
diff --git a/checkpoint-96/rng_state_27.pth b/checkpoint-96/rng_state_27.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a59b2bc158668a56bec3379ff6b4afeb9745e8ea
--- /dev/null
+++ b/checkpoint-96/rng_state_27.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd1e535e2229e4158c9486f80b8d1c217d5d9fc3acae45d344a29e130d59905
+size 16404
diff --git a/checkpoint-96/rng_state_28.pth b/checkpoint-96/rng_state_28.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8042f32c357ceb37dac70817afb3fa57d9868d11
--- /dev/null
+++ b/checkpoint-96/rng_state_28.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08af720156e825bc0467b0c6d2389342f3e81800fec5254e8d7776b89417796
+size 16404
diff --git a/checkpoint-96/rng_state_29.pth b/checkpoint-96/rng_state_29.pth
new file mode 100644
index 0000000000000000000000000000000000000000..98b5b8c0e6b2d3bbf7ce87f2f7b23615904d2e4f
--- /dev/null
+++ b/checkpoint-96/rng_state_29.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a8045c761f2cba7d0997eeba6e05e9713621311d0ac92d047fa0a61565d79f
+size 16404
diff --git a/checkpoint-96/rng_state_3.pth b/checkpoint-96/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e0842a83e2b7614384a82f9e2bb9b28df5b86262
--- /dev/null
+++ b/checkpoint-96/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1d97859ab4ca23b1443824eb9c4422728411ab2abc11c8d156ba76337d4b49
+size 16389
diff --git a/checkpoint-96/rng_state_30.pth b/checkpoint-96/rng_state_30.pth
new file mode 100644
index 0000000000000000000000000000000000000000..41afc0c0a3e3706d3712899f00ed23be3c288758
--- /dev/null
+++ b/checkpoint-96/rng_state_30.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004c248b62df210cf2d6f7477a962e6498c320b1693df13cc5ec89bb99a74cc5
+size 16404
diff --git a/checkpoint-96/rng_state_31.pth b/checkpoint-96/rng_state_31.pth
new file mode 100644
index 0000000000000000000000000000000000000000..411e23011efc6749aee1e4acf262b4cf5a3cf3ef
--- /dev/null
+++ b/checkpoint-96/rng_state_31.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62d1c061c8e16992856dad441803f90eb1107b25c79c0068cea177e79370515
+size 16404
diff --git a/checkpoint-96/rng_state_4.pth b/checkpoint-96/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..69f8e2ae1f5fd8afb24549196f7f24524f801261
--- /dev/null
+++ b/checkpoint-96/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3eb6011c4a22bcce73c8c2f22c640a541c42f5803741400ec2631462aeb45c
+size 16389
diff --git a/checkpoint-96/rng_state_5.pth b/checkpoint-96/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8fc0aa49b65ceecb289daa497af8660af01fde97
--- /dev/null
+++ b/checkpoint-96/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1552518a7aa19b9d8219f05725c5b12918a25151e3df9ef87cc7479d65ba2d57
+size 16389
diff --git a/checkpoint-96/rng_state_6.pth b/checkpoint-96/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6f3e2070e834d0c9856f0f78ccfe5d3234210984
--- /dev/null
+++ b/checkpoint-96/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8cb33a885bbd1231876777eebef31bd317de014b50b5f245908c06c34efe34
+size 16389
diff --git a/checkpoint-96/rng_state_7.pth b/checkpoint-96/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..61ff477ffdff101fd06bcf7bf923dca2375d9af1
--- /dev/null
+++ b/checkpoint-96/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e39eec7f0768ccf719ee3f4511179664228d8f830449c4fca0122efcb159121
+size 16389
diff --git a/checkpoint-96/rng_state_8.pth b/checkpoint-96/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7ccda6e00ebeacdfc53a8bfab80f721939b7ebab
--- /dev/null
+++ b/checkpoint-96/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595ea5c06c75823a3bb13981cf5c7cae169774912948c701d3dbb85dd75386c9
+size 16389
diff --git a/checkpoint-96/rng_state_9.pth b/checkpoint-96/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..940017e9f00a17bbe8c3eea58d6b64500d561f4b
--- /dev/null
+++ b/checkpoint-96/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e317ff0bdf61cbcd88411947ddb5eae1e2df5556a1655abbbbd619bbacc16efc
+size 16389
diff --git a/checkpoint-96/scheduler.pt b/checkpoint-96/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..350550228df806b62bbd30f8bd5166af1df9ffbc
--- /dev/null
+++ b/checkpoint-96/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61e5f6f7d2e37b4a7f8054143d259852e46715498ef90aede4d93a30216dbe8
+size 1465
diff --git a/checkpoint-96/tokenizer.json b/checkpoint-96/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad
--- /dev/null
+++ b/checkpoint-96/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325
diff --git a/checkpoint-96/tokenizer_config.json b/checkpoint-96/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed1f99f3d50eecc9850623be644bd1131686cbe1
--- /dev/null
+++ b/checkpoint-96/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-96/trainer_state.json b/checkpoint-96/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9495db8b2bc37cc3bb8881019686b72b46eef934
--- /dev/null
+++ b/checkpoint-96/trainer_state.json
@@ -0,0 +1,224 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5238095238095237,
+  "eval_steps": 500,
+  "global_step": 96,
+  "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
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.406036463708799e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-96/training_args.bin b/checkpoint-96/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecc663b14909aac0dc69e6f9415a962ed6d4f84b
--- /dev/null
+++ b/checkpoint-96/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969