Upload fine-tuned Qwen3-8B Star Trek Guard model

.gitattributes

@@ -36,3 +36,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 checkpoint-129/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-43/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-282/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-423/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -32,13 +32,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "k_proj",
-    "down_proj",
-    "up_proj",
     "o_proj",
+    "gate_proj",
+    "up_proj",
     "q_proj",
-    "gate_proj"
+    "v_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "SEQ_CLS",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fd10687a3b042a21452b6974f1cbae33b6731dfc458060f1aafb3fcc0c654e
+oid sha256:6a376f7fa8fc2c01b99ec090ce9e5952efb8e065ddaac171ac8bd78afa87f19c
 size 174672024

checkpoint-282/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+tags:
+- base_model:adapter:Qwen/Qwen3-8B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-282/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-282/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a376f7fa8fc2c01b99ec090ce9e5952efb8e065ddaac171ac8bd78afa87f19c
+size 174672024

checkpoint-282/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-282/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-282/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f84147918cdfa770c42ecb41602225288a2215653910c396d819417f8a39a22
+size 349545045

checkpoint-282/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b33ded9d0c18e6b1a7c59acb589b4b8e806aee9b66e1f51b2fa1d95df76c5a
+size 14645

checkpoint-282/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2413303f8cc4896ff03ff856f48c267288f959cca2b28755717558005ebf1de
+size 1465

checkpoint-282/special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": "<|im_end|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-282/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6583c532ebcffab265f0693ef8624858bd22dece1754500925f53e5dc5f058
+size 11422929

checkpoint-282/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": "<|im_end|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-282/trainer_state.json

@@ -0,0 +1,253 @@
+{
+  "best_global_step": 282,
+  "best_metric": 0.0,
+  "best_model_checkpoint": "./star_trek_guard_finetuned/checkpoint-282",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 282,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0071111111111111115,
+      "grad_norm": 1424.3302001953125,
+      "learning_rate": 0.0,
+      "loss": 34.4477,
+      "step": 1
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 359.5785827636719,
+      "learning_rate": 4.186046511627907e-05,
+      "loss": 25.5053,
+      "step": 10
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 55.2808952331543,
+      "learning_rate": 8.837209302325582e-05,
+      "loss": 4.533,
+      "step": 20
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.00021057801495771855,
+      "learning_rate": 0.00013488372093023256,
+      "loss": 0.1875,
+      "step": 30
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001813953488372093,
+      "loss": 0.6068,
+      "step": 40
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.00012314319610595703,
+      "learning_rate": 0.00019987699691483048,
+      "loss": 1.8401,
+      "step": 50
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0010618583764880896,
+      "learning_rate": 0.00019912640693269752,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.018764492124319077,
+      "learning_rate": 0.00019769868307835994,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 7.790327072143555e-05,
+      "learning_rate": 0.00019560357815343577,
+      "loss": 0.003,
+      "step": 80
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.00014328956604003906,
+      "learning_rate": 0.00019285540384897073,
+      "loss": 0.04,
+      "step": 90
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.08614543080329895,
+      "learning_rate": 0.00018947293298207635,
+      "loss": 0.1796,
+      "step": 100
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001854792712585539,
+      "loss": 0.0002,
+      "step": 110
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0016153233591467142,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0269,
+      "step": 120
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.000989419175311923,
+      "learning_rate": 0.0001757714869760335,
+      "loss": 0.4039,
+      "step": 130
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.8112388849258423,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.7485,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.00433349609375,
+      "eval_runtime": 37.2872,
+      "eval_samples_per_second": 13.409,
+      "eval_steps_per_second": 3.352,
+      "step": 141
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.00020039081573486328,
+      "learning_rate": 0.00016399685405033167,
+      "loss": 0.3372,
+      "step": 150
+    },
+    {
+      "epoch": 1.1351111111111112,
+      "grad_norm": 0.006611417979001999,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.2062222222222223,
+      "grad_norm": 2.5033950805664062e-05,
+      "learning_rate": 0.0001504765537734844,
+      "loss": 0.0735,
+      "step": 170
+    },
+    {
+      "epoch": 1.2773333333333334,
+      "grad_norm": 3.987550735473633e-05,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.2116,
+      "step": 180
+    },
+    {
+      "epoch": 1.3484444444444446,
+      "grad_norm": 8.791685104370117e-05,
+      "learning_rate": 0.00013557938469225167,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.4195555555555557,
+      "grad_norm": 0.00015270709991455078,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.4906666666666666,
+      "grad_norm": 152.50794982910156,
+      "learning_rate": 0.00011971170274514802,
+      "loss": 0.2612,
+      "step": 210
+    },
+    {
+      "epoch": 1.561777777777778,
+      "grad_norm": 0.00700717605650425,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.0043,
+      "step": 220
+    },
+    {
+      "epoch": 1.6328888888888888,
+      "grad_norm": 0.025026371702551842,
+      "learning_rate": 0.00010330633693173082,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.0,
+      "learning_rate": 9.504162453267777e-05,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.775111111111111,
+      "grad_norm": 0.00010925531387329102,
+      "learning_rate": 8.681078286579311e-05,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.8462222222222222,
+      "grad_norm": 1.3470649719238281e-05,
+      "learning_rate": 7.867003692562534e-05,
+      "loss": 0.2697,
+      "step": 260
+    },
+    {
+      "epoch": 1.9173333333333333,
+      "grad_norm": 5.3822994232177734e-05,
+      "learning_rate": 7.067499626155354e-05,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.9884444444444445,
+      "grad_norm": 1.329183578491211e-05,
+      "learning_rate": 6.28802751081779e-05,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.0,
+      "eval_runtime": 37.3645,
+      "eval_samples_per_second": 13.382,
+      "eval_steps_per_second": 3.345,
+      "step": 282
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 423,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.93252304093184e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-282/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9ac0021bae9c45958187a61a786b7468c5a90acff199940c5f1b2d7c478c0b
+size 5841

checkpoint-423/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+tags:
+- base_model:adapter:Qwen/Qwen3-8B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-423/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-423/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb3e239d93eae3ef937a7f7d12a010e08e067928907f89098c664dc7cef58d1a
+size 174672024

checkpoint-423/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-423/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-423/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681e47c14fcad7ebeebf2da85426491dfc02e6a6ce7eeb8f61ccce944bc49e62
+size 349545045

checkpoint-423/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebe2100ae4b14b3e3a78d058940f5a382da4532dc8137789fe0624815d6a3fa
+size 14645

checkpoint-423/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dbb23a7f7568c49d5fd63ef60f502240d770b6864697d79e1f163063e33e79
+size 1465

checkpoint-423/special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": "<|im_end|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-423/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6583c532ebcffab265f0693ef8624858bd22dece1754500925f53e5dc5f058
+size 11422929

checkpoint-423/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": "<|im_end|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-423/trainer_state.json

@@ -0,0 +1,359 @@
+{
+  "best_global_step": 282,
+  "best_metric": 0.0,
+  "best_model_checkpoint": "./star_trek_guard_finetuned/checkpoint-282",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 423,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0071111111111111115,
+      "grad_norm": 1424.3302001953125,
+      "learning_rate": 0.0,
+      "loss": 34.4477,
+      "step": 1
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 359.5785827636719,
+      "learning_rate": 4.186046511627907e-05,
+      "loss": 25.5053,
+      "step": 10
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 55.2808952331543,
+      "learning_rate": 8.837209302325582e-05,
+      "loss": 4.533,
+      "step": 20
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.00021057801495771855,
+      "learning_rate": 0.00013488372093023256,
+      "loss": 0.1875,
+      "step": 30
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001813953488372093,
+      "loss": 0.6068,
+      "step": 40
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.00012314319610595703,
+      "learning_rate": 0.00019987699691483048,
+      "loss": 1.8401,
+      "step": 50
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0010618583764880896,
+      "learning_rate": 0.00019912640693269752,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.018764492124319077,
+      "learning_rate": 0.00019769868307835994,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 7.790327072143555e-05,
+      "learning_rate": 0.00019560357815343577,
+      "loss": 0.003,
+      "step": 80
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.00014328956604003906,
+      "learning_rate": 0.00019285540384897073,
+      "loss": 0.04,
+      "step": 90
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.08614543080329895,
+      "learning_rate": 0.00018947293298207635,
+      "loss": 0.1796,
+      "step": 100
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001854792712585539,
+      "loss": 0.0002,
+      "step": 110
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0016153233591467142,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0269,
+      "step": 120
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.000989419175311923,
+      "learning_rate": 0.0001757714869760335,
+      "loss": 0.4039,
+      "step": 130
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.8112388849258423,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.7485,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.00433349609375,
+      "eval_runtime": 37.2872,
+      "eval_samples_per_second": 13.409,
+      "eval_steps_per_second": 3.352,
+      "step": 141
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.00020039081573486328,
+      "learning_rate": 0.00016399685405033167,
+      "loss": 0.3372,
+      "step": 150
+    },
+    {
+      "epoch": 1.1351111111111112,
+      "grad_norm": 0.006611417979001999,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.2062222222222223,
+      "grad_norm": 2.5033950805664062e-05,
+      "learning_rate": 0.0001504765537734844,
+      "loss": 0.0735,
+      "step": 170
+    },
+    {
+      "epoch": 1.2773333333333334,
+      "grad_norm": 3.987550735473633e-05,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.2116,
+      "step": 180
+    },
+    {
+      "epoch": 1.3484444444444446,
+      "grad_norm": 8.791685104370117e-05,
+      "learning_rate": 0.00013557938469225167,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.4195555555555557,
+      "grad_norm": 0.00015270709991455078,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.4906666666666666,
+      "grad_norm": 152.50794982910156,
+      "learning_rate": 0.00011971170274514802,
+      "loss": 0.2612,
+      "step": 210
+    },
+    {
+      "epoch": 1.561777777777778,
+      "grad_norm": 0.00700717605650425,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.0043,
+      "step": 220
+    },
+    {
+      "epoch": 1.6328888888888888,
+      "grad_norm": 0.025026371702551842,
+      "learning_rate": 0.00010330633693173082,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.0,
+      "learning_rate": 9.504162453267777e-05,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.775111111111111,
+      "grad_norm": 0.00010925531387329102,
+      "learning_rate": 8.681078286579311e-05,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.8462222222222222,
+      "grad_norm": 1.3470649719238281e-05,
+      "learning_rate": 7.867003692562534e-05,
+      "loss": 0.2697,
+      "step": 260
+    },
+    {
+      "epoch": 1.9173333333333333,
+      "grad_norm": 5.3822994232177734e-05,
+      "learning_rate": 7.067499626155354e-05,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.9884444444444445,
+      "grad_norm": 1.329183578491211e-05,
+      "learning_rate": 6.28802751081779e-05,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.0,
+      "eval_runtime": 37.3645,
+      "eval_samples_per_second": 13.382,
+      "eval_steps_per_second": 3.345,
+      "step": 282
+    },
+    {
+      "epoch": 2.056888888888889,
+      "grad_norm": 2.580881118774414e-05,
+      "learning_rate": 5.533911931471936e-05,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 1.3649463653564453e-05,
+      "learning_rate": 4.810304262187852e-05,
+      "loss": 0.0475,
+      "step": 300
+    },
+    {
+      "epoch": 2.1991111111111112,
+      "grad_norm": 1.3887882232666016e-05,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.2702222222222224,
+      "grad_norm": 1.3113021850585938e-05,
+      "learning_rate": 3.4741423847583134e-05,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.3413333333333335,
+      "grad_norm": 9.423494338989258e-05,
+      "learning_rate": 2.87071551708603e-05,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.4124444444444446,
+      "grad_norm": 0.00020039081573486328,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.4835555555555557,
+      "grad_norm": 0.07984881103038788,
+      "learning_rate": 1.8137518531330767e-05,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.554666666666667,
+      "grad_norm": 9.775161743164062e-05,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 2.6257777777777775,
+      "grad_norm": 0.00018417835235595703,
+      "learning_rate": 9.80087698670411e-06,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.696888888888889,
+      "grad_norm": 1.3530254364013672e-05,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 5.316734313964844e-05,
+      "learning_rate": 3.924632386315186e-06,
+      "loss": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.8391111111111114,
+      "grad_norm": 0.000179290771484375,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 0.0001,
+      "step": 400
+    },
+    {
+      "epoch": 2.910222222222222,
+      "grad_norm": 0.0,
+      "learning_rate": 6.690733646361857e-07,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.981333333333333,
+      "grad_norm": 2.759695053100586e-05,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.960464477539063e-08,
+      "eval_runtime": 37.235,
+      "eval_samples_per_second": 13.428,
+      "eval_steps_per_second": 3.357,
+      "step": 423
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 423,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.89878456139776e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-423/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9ac0021bae9c45958187a61a786b7468c5a90acff199940c5f1b2d7c478c0b
+size 5841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efad51cdca3984b765dba48c52a09a5007546018e1c6a619dd8f2b1f9d0ddfb0
+oid sha256:be9ac0021bae9c45958187a61a786b7468c5a90acff199940c5f1b2d7c478c0b
 size 5841