Add files using upload-large-folder tool

.gitattributes

@@ -93,3 +93,13 @@ gsm8k__llama3_8b_instruct__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/tok
 csqa__llama3_8b_instruct__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gsm8k__qwen3_8b__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gsm8k__qwen3_8b__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gsm8k__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gsm8k__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text

csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59ae81e95c7ec1ff9f54ed6a4927ae87c231519bdc0c05297a5a5de3b71efb5
+size 83945296

csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59ae81e95c7ec1ff9f54ed6a4927ae87c231519bdc0c05297a5a5de3b71efb5
+size 83945296

csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885fe2c2d78351315673955bcfeb9a1e7cbc0e52f3b907967ed5d34fe17a658d
+size 168149539

csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c34190b141e145a0da05c3cc5e2ae305fe747004b04f8ad847787f46a9e03f3
+size 83945296

csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+library_name: peft
+---
+
+# 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 0.15.2

csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c34190b141e145a0da05c3cc5e2ae305fe747004b04f8ad847787f46a9e03f3
+size 83945296

csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9905f822a9cb3f7e06363edd46cd439038efe7fd176f8a2a0338409dd45d178f
+size 168149539

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f888fbf570c57885834fd84a2e2c7f931f2c515a8e977b9c09d0bf96018b6a
+size 87360584

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.8033509624132403e+17,
+    "train_loss": 0.5275962893256999,
+    "train_runtime": 463.0949,
+    "train_samples_per_second": 64.782,
+    "train_steps_per_second": 2.028
+}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/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 %}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+---
+
+# 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 0.15.2

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f888fbf570c57885834fd84a2e2c7f931f2c515a8e977b9c09d0bf96018b6a
+size 87360584

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/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
+}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/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 %}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7921f271ebc6b0c0c123869d051ffea8e6670bc9dcb0662706fcc51bdf20a00
+size 175012683

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json

@@ -0,0 +1,685 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 36.33285903930664,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 6.9124,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 37.845706939697266,
+      "learning_rate": 2.021276595744681e-06,
+      "loss": 6.6841,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 41.69117736816406,
+      "learning_rate": 3.0851063829787237e-06,
+      "loss": 6.721,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 50.03352737426758,
+      "learning_rate": 4.148936170212766e-06,
+      "loss": 6.1192,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 59.23619842529297,
+      "learning_rate": 5.212765957446809e-06,
+      "loss": 4.8473,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 5.8774261474609375,
+      "learning_rate": 6.276595744680851e-06,
+      "loss": 2.1142,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 6.693775653839111,
+      "learning_rate": 7.340425531914894e-06,
+      "loss": 1.6119,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 4.908555507659912,
+      "learning_rate": 8.404255319148937e-06,
+      "loss": 1.1825,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 2.0115675926208496,
+      "learning_rate": 9.46808510638298e-06,
+      "loss": 0.5337,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 0.8753984570503235,
+      "learning_rate": 9.999136119166803e-06,
+      "loss": 0.2692,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 0.8379660248756409,
+      "learning_rate": 9.9922268634943e-06,
+      "loss": 0.258,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.8429737687110901,
+      "learning_rate": 9.978417901361958e-06,
+      "loss": 0.234,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 0.6800509095191956,
+      "learning_rate": 9.95772831799724e-06,
+      "loss": 0.2045,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 1.0576311349868774,
+      "learning_rate": 9.930186708264902e-06,
+      "loss": 0.2049,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 0.681848406791687,
+      "learning_rate": 9.895831137146319e-06,
+      "loss": 0.1901,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 0.7110018730163574,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.1935,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 0.8011160492897034,
+      "learning_rate": 9.80687739258782e-06,
+      "loss": 0.1888,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.8912045359611511,
+      "learning_rate": 9.7524021612222e-06,
+      "loss": 0.194,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 1.1133105754852295,
+      "learning_rate": 9.691358682701927e-06,
+      "loss": 0.1843,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 1.3582327365875244,
+      "learning_rate": 9.623831324603755e-06,
+      "loss": 0.2121,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 1.2391612529754639,
+      "learning_rate": 9.549913415809084e-06,
+      "loss": 0.1797,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 1.0479785203933716,
+      "learning_rate": 9.469707117515068e-06,
+      "loss": 0.1636,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 1.0715245008468628,
+      "learning_rate": 9.383323282038632e-06,
+      "loss": 0.1693,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.9121628403663635,
+      "learning_rate": 9.29088129960862e-06,
+      "loss": 0.1296,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.2252585887908936,
+      "learning_rate": 9.192508933357753e-06,
+      "loss": 0.1393,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 1.1432126760482788,
+      "learning_rate": 9.088342142742493e-06,
+      "loss": 0.1796,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 1.1106261014938354,
+      "learning_rate": 8.978524895634842e-06,
+      "loss": 0.1672,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 1.1917647123336792,
+      "learning_rate": 8.86320896934581e-06,
+      "loss": 0.1813,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 1.1675026416778564,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.1847,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 2.2532408237457275,
+      "learning_rate": 8.616725966539831e-06,
+      "loss": 0.1642,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 1.000963807106018,
+      "learning_rate": 8.485899551698166e-06,
+      "loss": 0.1793,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 0.7248425483703613,
+      "learning_rate": 8.350255310200611e-06,
+      "loss": 0.1445,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 0.936930775642395,
+      "learning_rate": 8.209980714586955e-06,
+      "loss": 0.1495,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 0.8912279009819031,
+      "learning_rate": 8.065269636962765e-06,
+      "loss": 0.1478,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 1.2984365224838257,
+      "learning_rate": 7.916322081050708e-06,
+      "loss": 0.169,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.9977064728736877,
+      "learning_rate": 7.76334390576742e-06,
+      "loss": 0.1555,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 0.8419762849807739,
+      "learning_rate": 7.60654654070796e-06,
+      "loss": 0.1617,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.5433464050292969,
+      "learning_rate": 7.446146693931111e-06,
+      "loss": 0.1495,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 0.7475736737251282,
+      "learning_rate": 7.282366052449351e-06,
+      "loss": 0.1339,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 1.4355934858322144,
+      "learning_rate": 7.115430975837457e-06,
+      "loss": 0.1587,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.2254966497421265,
+      "learning_rate": 6.945572183383229e-06,
+      "loss": 0.1347,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 0.810607373714447,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.1292,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 1.0503230094909668,
+      "learning_rate": 6.598026207830428e-06,
+      "loss": 0.1636,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 1.5683962106704712,
+      "learning_rate": 6.4208193645237314e-06,
+      "loss": 0.1703,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 1.4046155214309692,
+      "learning_rate": 6.241648821085666e-06,
+      "loss": 0.1624,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 1.0360242128372192,
+      "learning_rate": 6.060762207319479e-06,
+      "loss": 0.1499,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 1.1383719444274902,
+      "learning_rate": 5.878409524791931e-06,
+      "loss": 0.1324,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 1.3533704280853271,
+      "learning_rate": 5.694842801308651e-06,
+      "loss": 0.1328,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 1.1995248794555664,
+      "learning_rate": 5.510315742589042e-06,
+      "loss": 0.1467,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 1.4972271919250488,
+      "learning_rate": 5.325083381622165e-06,
+      "loss": 0.1569,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 0.6726014018058777,
+      "learning_rate": 5.139401726188208e-06,
+      "loss": 0.1444,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 0.8959933519363403,
+      "learning_rate": 4.953527405032723e-06,
+      "loss": 0.1727,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 1.0952670574188232,
+      "learning_rate": 4.767717313182611e-06,
+      "loss": 0.1548,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 1.1545971632003784,
+      "learning_rate": 4.582228256894093e-06,
+      "loss": 0.1335,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 1.5466020107269287,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.168,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 1.089145302772522,
+      "learning_rate": 4.2132379032105695e-06,
+      "loss": 0.1604,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 1.0096254348754883,
+      "learning_rate": 4.030246583666437e-06,
+      "loss": 0.1418,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 0.9796081781387329,
+      "learning_rate": 3.848595550550401e-06,
+      "loss": 0.1403,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 1.1617341041564941,
+      "learning_rate": 3.668535861925509e-06,
+      "loss": 0.1433,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 0.7589540481567383,
+      "learning_rate": 3.4903163764736104e-06,
+      "loss": 0.1388,
+      "step": 600
+    },
+    {
+      "epoch": 1.9488817891373802,
+      "grad_norm": 0.7963077425956726,
+      "learning_rate": 3.314183409550293e-06,
+      "loss": 0.1251,
+      "step": 610
+    },
+    {
+      "epoch": 1.9808306709265175,
+      "grad_norm": 1.1559962034225464,
+      "learning_rate": 3.140380392754901e-06,
+      "loss": 0.1276,
+      "step": 620
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 0.6292369365692139,
+      "learning_rate": 2.969147537486175e-06,
+      "loss": 0.1428,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 1.1892845630645752,
+      "learning_rate": 2.800721502948506e-06,
+      "loss": 0.1454,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 0.8596490621566772,
+      "learning_rate": 2.635335069067617e-06,
+      "loss": 0.1368,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 0.8156671524047852,
+      "learning_rate": 2.4732168147677927e-06,
+      "loss": 0.1159,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 1.977015733718872,
+      "learning_rate": 2.314590802055232e-06,
+      "loss": 0.1417,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 1.2084506750106812,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.1242,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 1.1458317041397095,
+      "learning_rate": 2.0086873134540626e-06,
+      "loss": 0.1095,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 1.8264726400375366,
+      "learning_rate": 1.8618326236955908e-06,
+      "loss": 0.155,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 1.4171464443206787,
+      "learning_rate": 1.7193151634562071e-06,
+      "loss": 0.1258,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 1.4613436460494995,
+      "learning_rate": 1.581331904682089e-06,
+      "loss": 0.1518,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 1.093307614326477,
+      "learning_rate": 1.4480735526452427e-06,
+      "loss": 0.1299,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 1.374348521232605,
+      "learning_rate": 1.319724282371664e-06,
+      "loss": 0.147,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 1.2374401092529297,
+      "learning_rate": 1.1964614840949002e-06,
+      "loss": 0.1209,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 1.249546766281128,
+      "learning_rate": 1.078455518086784e-06,
+      "loss": 0.115,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 1.0231386423110962,
+      "learning_rate": 9.658694792042284e-07,
+      "loss": 0.1366,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 1.1464241743087769,
+      "learning_rate": 8.58858971477457e-07,
+      "loss": 0.1184,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 0.9766585230827332,
+      "learning_rate": 7.575718930512516e-07,
+      "loss": 0.1227,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 1.1977977752685547,
+      "learning_rate": 6.621482317764105e-07,
+      "loss": 0.1092,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 1.6657644510269165,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.1475,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 1.3672709465026855,
+      "learning_rate": 4.894104109594466e-07,
+      "loss": 0.1242,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 1.7629551887512207,
+      "learning_rate": 4.123349906194357e-07,
+      "loss": 0.1389,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 0.8762993812561035,
+      "learning_rate": 3.416001358759635e-07,
+      "loss": 0.1091,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 1.4116370677947998,
+      "learning_rate": 2.7730360865923954e-07,
+      "loss": 0.1272,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 1.2336490154266357,
+      "learning_rate": 2.1953427255185122e-07,
+      "loss": 0.1056,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 1.4972121715545654,
+      "learning_rate": 1.6837196997130434e-07,
+      "loss": 0.1287,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 1.169806957244873,
+      "learning_rate": 1.2388741182062348e-07,
+      "loss": 0.1094,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 1.0118532180786133,
+      "learning_rate": 8.614207975952083e-08,
+      "loss": 0.1464,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 1.9891964197158813,
+      "learning_rate": 5.518814123121885e-08,
+      "loss": 0.1388,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 1.1589871644973755,
+      "learning_rate": 3.10683773623488e-08,
+      "loss": 0.1236,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 1.1757524013519287,
+      "learning_rate": 1.3816123835588835e-08,
+      "loss": 0.1044,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 1.4213329553604126,
+      "learning_rate": 3.4552248167507576e-09,
+      "loss": 0.1423,
+      "step": 930
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8033509624132403e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_log.jsonl

@@ -0,0 +1,94 @@
+{"current_steps": 10, "total_steps": 939, "loss": 6.9124, "lr": 9.574468085106384e-07, "epoch": 0.03194888178913738, "percentage": 1.06, "elapsed_time": "0:00:05", "remaining_time": "0:08:59"}
+{"current_steps": 20, "total_steps": 939, "loss": 6.6841, "lr": 2.021276595744681e-06, "epoch": 0.06389776357827476, "percentage": 2.13, "elapsed_time": "0:00:10", "remaining_time": "0:08:07"}
+{"current_steps": 30, "total_steps": 939, "loss": 6.721, "lr": 3.0851063829787237e-06, "epoch": 0.09584664536741214, "percentage": 3.19, "elapsed_time": "0:00:15", "remaining_time": "0:07:48"}
+{"current_steps": 40, "total_steps": 939, "loss": 6.1192, "lr": 4.148936170212766e-06, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:00:20", "remaining_time": "0:07:34"}
+{"current_steps": 50, "total_steps": 939, "loss": 4.8473, "lr": 5.212765957446809e-06, "epoch": 0.1597444089456869, "percentage": 5.32, "elapsed_time": "0:00:24", "remaining_time": "0:07:23"}
+{"current_steps": 60, "total_steps": 939, "loss": 2.1142, "lr": 6.276595744680851e-06, "epoch": 0.19169329073482427, "percentage": 6.39, "elapsed_time": "0:00:29", "remaining_time": "0:07:15"}
+{"current_steps": 70, "total_steps": 939, "loss": 1.6119, "lr": 7.340425531914894e-06, "epoch": 0.22364217252396165, "percentage": 7.45, "elapsed_time": "0:00:34", "remaining_time": "0:07:07"}
+{"current_steps": 80, "total_steps": 939, "loss": 1.1825, "lr": 8.404255319148937e-06, "epoch": 0.25559105431309903, "percentage": 8.52, "elapsed_time": "0:00:39", "remaining_time": "0:07:01"}
+{"current_steps": 90, "total_steps": 939, "loss": 0.5337, "lr": 9.46808510638298e-06, "epoch": 0.28753993610223644, "percentage": 9.58, "elapsed_time": "0:00:44", "remaining_time": "0:06:55"}
+{"current_steps": 100, "total_steps": 939, "loss": 0.2692, "lr": 9.999136119166803e-06, "epoch": 0.3194888178913738, "percentage": 10.65, "elapsed_time": "0:00:48", "remaining_time": "0:06:48"}
+{"current_steps": 110, "total_steps": 939, "loss": 0.258, "lr": 9.9922268634943e-06, "epoch": 0.3514376996805112, "percentage": 11.71, "elapsed_time": "0:00:53", "remaining_time": "0:06:42"}
+{"current_steps": 120, "total_steps": 939, "loss": 0.234, "lr": 9.978417901361958e-06, "epoch": 0.38338658146964855, "percentage": 12.78, "elapsed_time": "0:00:58", "remaining_time": "0:06:37"}
+{"current_steps": 130, "total_steps": 939, "loss": 0.2045, "lr": 9.95772831799724e-06, "epoch": 0.41533546325878595, "percentage": 13.84, "elapsed_time": "0:01:02", "remaining_time": "0:06:32"}
+{"current_steps": 140, "total_steps": 939, "loss": 0.2049, "lr": 9.930186708264902e-06, "epoch": 0.4472843450479233, "percentage": 14.91, "elapsed_time": "0:01:07", "remaining_time": "0:06:26"}
+{"current_steps": 150, "total_steps": 939, "loss": 0.1901, "lr": 9.895831137146319e-06, "epoch": 0.4792332268370607, "percentage": 15.97, "elapsed_time": "0:01:12", "remaining_time": "0:06:21"}
+{"current_steps": 160, "total_steps": 939, "loss": 0.1935, "lr": 9.854709087130261e-06, "epoch": 0.5111821086261981, "percentage": 17.04, "elapsed_time": "0:01:17", "remaining_time": "0:06:16"}
+{"current_steps": 170, "total_steps": 939, "loss": 0.1888, "lr": 9.80687739258782e-06, "epoch": 0.5431309904153354, "percentage": 18.1, "elapsed_time": "0:01:22", "remaining_time": "0:06:11"}
+{"current_steps": 180, "total_steps": 939, "loss": 0.194, "lr": 9.7524021612222e-06, "epoch": 0.5750798722044729, "percentage": 19.17, "elapsed_time": "0:01:26", "remaining_time": "0:06:05"}
+{"current_steps": 190, "total_steps": 939, "loss": 0.1843, "lr": 9.691358682701927e-06, "epoch": 0.6070287539936102, "percentage": 20.23, "elapsed_time": "0:01:31", "remaining_time": "0:06:00"}
+{"current_steps": 200, "total_steps": 939, "loss": 0.2121, "lr": 9.623831324603755e-06, "epoch": 0.6389776357827476, "percentage": 21.3, "elapsed_time": "0:01:36", "remaining_time": "0:05:55"}
+{"current_steps": 210, "total_steps": 939, "loss": 0.1797, "lr": 9.549913415809084e-06, "epoch": 0.670926517571885, "percentage": 22.36, "elapsed_time": "0:01:41", "remaining_time": "0:05:50"}
+{"current_steps": 220, "total_steps": 939, "loss": 0.1636, "lr": 9.469707117515068e-06, "epoch": 0.7028753993610224, "percentage": 23.43, "elapsed_time": "0:01:45", "remaining_time": "0:05:45"}
+{"current_steps": 230, "total_steps": 939, "loss": 0.1693, "lr": 9.383323282038632e-06, "epoch": 0.7348242811501597, "percentage": 24.49, "elapsed_time": "0:01:50", "remaining_time": "0:05:41"}
+{"current_steps": 240, "total_steps": 939, "loss": 0.1296, "lr": 9.29088129960862e-06, "epoch": 0.7667731629392971, "percentage": 25.56, "elapsed_time": "0:01:55", "remaining_time": "0:05:36"}
+{"current_steps": 250, "total_steps": 939, "loss": 0.1393, "lr": 9.192508933357753e-06, "epoch": 0.7987220447284346, "percentage": 26.62, "elapsed_time": "0:02:00", "remaining_time": "0:05:31"}
+{"current_steps": 260, "total_steps": 939, "loss": 0.1796, "lr": 9.088342142742493e-06, "epoch": 0.8306709265175719, "percentage": 27.69, "elapsed_time": "0:02:04", "remaining_time": "0:05:26"}
+{"current_steps": 270, "total_steps": 939, "loss": 0.1672, "lr": 8.978524895634842e-06, "epoch": 0.8626198083067093, "percentage": 28.75, "elapsed_time": "0:02:09", "remaining_time": "0:05:21"}
+{"current_steps": 280, "total_steps": 939, "loss": 0.1813, "lr": 8.86320896934581e-06, "epoch": 0.8945686900958466, "percentage": 29.82, "elapsed_time": "0:02:14", "remaining_time": "0:05:16"}
+{"current_steps": 290, "total_steps": 939, "loss": 0.1847, "lr": 8.742553740855507e-06, "epoch": 0.9265175718849841, "percentage": 30.88, "elapsed_time": "0:02:19", "remaining_time": "0:05:11"}
+{"current_steps": 300, "total_steps": 939, "loss": 0.1642, "lr": 8.616725966539831e-06, "epoch": 0.9584664536741214, "percentage": 31.95, "elapsed_time": "0:02:23", "remaining_time": "0:05:06"}
+{"current_steps": 310, "total_steps": 939, "loss": 0.1793, "lr": 8.485899551698166e-06, "epoch": 0.9904153354632588, "percentage": 33.01, "elapsed_time": "0:02:28", "remaining_time": "0:05:01"}
+{"current_steps": 320, "total_steps": 939, "loss": 0.1445, "lr": 8.350255310200611e-06, "epoch": 1.0223642172523961, "percentage": 34.08, "elapsed_time": "0:02:33", "remaining_time": "0:04:57"}
+{"current_steps": 330, "total_steps": 939, "loss": 0.1495, "lr": 8.209980714586955e-06, "epoch": 1.0543130990415335, "percentage": 35.14, "elapsed_time": "0:02:38", "remaining_time": "0:04:52"}
+{"current_steps": 340, "total_steps": 939, "loss": 0.1478, "lr": 8.065269636962765e-06, "epoch": 1.0862619808306708, "percentage": 36.21, "elapsed_time": "0:02:43", "remaining_time": "0:04:47"}
+{"current_steps": 350, "total_steps": 939, "loss": 0.169, "lr": 7.916322081050708e-06, "epoch": 1.1182108626198084, "percentage": 37.27, "elapsed_time": "0:02:47", "remaining_time": "0:04:42"}
+{"current_steps": 360, "total_steps": 939, "loss": 0.1555, "lr": 7.76334390576742e-06, "epoch": 1.1501597444089458, "percentage": 38.34, "elapsed_time": "0:02:52", "remaining_time": "0:04:37"}
+{"current_steps": 370, "total_steps": 939, "loss": 0.1617, "lr": 7.60654654070796e-06, "epoch": 1.182108626198083, "percentage": 39.4, "elapsed_time": "0:02:57", "remaining_time": "0:04:32"}
+{"current_steps": 380, "total_steps": 939, "loss": 0.1495, "lr": 7.446146693931111e-06, "epoch": 1.2140575079872205, "percentage": 40.47, "elapsed_time": "0:03:01", "remaining_time": "0:04:27"}
+{"current_steps": 390, "total_steps": 939, "loss": 0.1339, "lr": 7.282366052449351e-06, "epoch": 1.2460063897763578, "percentage": 41.53, "elapsed_time": "0:03:06", "remaining_time": "0:04:22"}
+{"current_steps": 400, "total_steps": 939, "loss": 0.1587, "lr": 7.115430975837457e-06, "epoch": 1.2779552715654952, "percentage": 42.6, "elapsed_time": "0:03:11", "remaining_time": "0:04:17"}
+{"current_steps": 410, "total_steps": 939, "loss": 0.1347, "lr": 6.945572183383229e-06, "epoch": 1.3099041533546325, "percentage": 43.66, "elapsed_time": "0:03:16", "remaining_time": "0:04:13"}
+{"current_steps": 420, "total_steps": 939, "loss": 0.1292, "lr": 6.773024435212678e-06, "epoch": 1.34185303514377, "percentage": 44.73, "elapsed_time": "0:03:20", "remaining_time": "0:04:08"}
+{"current_steps": 430, "total_steps": 939, "loss": 0.1636, "lr": 6.598026207830428e-06, "epoch": 1.3738019169329074, "percentage": 45.79, "elapsed_time": "0:03:25", "remaining_time": "0:04:03"}
+{"current_steps": 440, "total_steps": 939, "loss": 0.1703, "lr": 6.4208193645237314e-06, "epoch": 1.4057507987220448, "percentage": 46.86, "elapsed_time": "0:03:30", "remaining_time": "0:03:58"}
+{"current_steps": 450, "total_steps": 939, "loss": 0.1624, "lr": 6.241648821085666e-06, "epoch": 1.4376996805111821, "percentage": 47.92, "elapsed_time": "0:03:35", "remaining_time": "0:03:53"}
+{"current_steps": 460, "total_steps": 939, "loss": 0.1499, "lr": 6.060762207319479e-06, "epoch": 1.4696485623003195, "percentage": 48.99, "elapsed_time": "0:03:39", "remaining_time": "0:03:48"}
+{"current_steps": 470, "total_steps": 939, "loss": 0.1324, "lr": 5.878409524791931e-06, "epoch": 1.5015974440894568, "percentage": 50.05, "elapsed_time": "0:03:44", "remaining_time": "0:03:44"}
+{"current_steps": 480, "total_steps": 939, "loss": 0.1328, "lr": 5.694842801308651e-06, "epoch": 1.5335463258785942, "percentage": 51.12, "elapsed_time": "0:03:49", "remaining_time": "0:03:39"}
+{"current_steps": 490, "total_steps": 939, "loss": 0.1467, "lr": 5.510315742589042e-06, "epoch": 1.5654952076677318, "percentage": 52.18, "elapsed_time": "0:03:53", "remaining_time": "0:03:34"}
+{"current_steps": 500, "total_steps": 939, "loss": 0.1569, "lr": 5.325083381622165e-06, "epoch": 1.5974440894568689, "percentage": 53.25, "elapsed_time": "0:03:58", "remaining_time": "0:03:29"}
+{"current_steps": 510, "total_steps": 939, "loss": 0.1444, "lr": 5.139401726188208e-06, "epoch": 1.6293929712460065, "percentage": 54.31, "elapsed_time": "0:04:03", "remaining_time": "0:03:24"}
+{"current_steps": 520, "total_steps": 939, "loss": 0.1727, "lr": 4.953527405032723e-06, "epoch": 1.6613418530351438, "percentage": 55.38, "elapsed_time": "0:04:08", "remaining_time": "0:03:20"}
+{"current_steps": 530, "total_steps": 939, "loss": 0.1548, "lr": 4.767717313182611e-06, "epoch": 1.6932907348242812, "percentage": 56.44, "elapsed_time": "0:04:13", "remaining_time": "0:03:15"}
+{"current_steps": 540, "total_steps": 939, "loss": 0.1335, "lr": 4.582228256894093e-06, "epoch": 1.7252396166134185, "percentage": 57.51, "elapsed_time": "0:04:17", "remaining_time": "0:03:10"}
+{"current_steps": 550, "total_steps": 939, "loss": 0.168, "lr": 4.397316598723385e-06, "epoch": 1.7571884984025559, "percentage": 58.57, "elapsed_time": "0:04:22", "remaining_time": "0:03:05"}
+{"current_steps": 560, "total_steps": 939, "loss": 0.1604, "lr": 4.2132379032105695e-06, "epoch": 1.7891373801916934, "percentage": 59.64, "elapsed_time": "0:04:27", "remaining_time": "0:03:00"}
+{"current_steps": 570, "total_steps": 939, "loss": 0.1418, "lr": 4.030246583666437e-06, "epoch": 1.8210862619808306, "percentage": 60.7, "elapsed_time": "0:04:32", "remaining_time": "0:02:56"}
+{"current_steps": 580, "total_steps": 939, "loss": 0.1403, "lr": 3.848595550550401e-06, "epoch": 1.8530351437699681, "percentage": 61.77, "elapsed_time": "0:04:36", "remaining_time": "0:02:51"}
+{"current_steps": 590, "total_steps": 939, "loss": 0.1433, "lr": 3.668535861925509e-06, "epoch": 1.8849840255591053, "percentage": 62.83, "elapsed_time": "0:04:41", "remaining_time": "0:02:46"}
+{"current_steps": 600, "total_steps": 939, "loss": 0.1388, "lr": 3.4903163764736104e-06, "epoch": 1.9169329073482428, "percentage": 63.9, "elapsed_time": "0:04:46", "remaining_time": "0:02:41"}
+{"current_steps": 610, "total_steps": 939, "loss": 0.1251, "lr": 3.314183409550293e-06, "epoch": 1.9488817891373802, "percentage": 64.96, "elapsed_time": "0:04:50", "remaining_time": "0:02:36"}
+{"current_steps": 620, "total_steps": 939, "loss": 0.1276, "lr": 3.140380392754901e-06, "epoch": 1.9808306709265175, "percentage": 66.03, "elapsed_time": "0:04:55", "remaining_time": "0:02:32"}
+{"current_steps": 630, "total_steps": 939, "loss": 0.1428, "lr": 2.969147537486175e-06, "epoch": 2.012779552715655, "percentage": 67.09, "elapsed_time": "0:05:00", "remaining_time": "0:02:27"}
+{"current_steps": 640, "total_steps": 939, "loss": 0.1454, "lr": 2.800721502948506e-06, "epoch": 2.0447284345047922, "percentage": 68.16, "elapsed_time": "0:05:05", "remaining_time": "0:02:22"}
+{"current_steps": 650, "total_steps": 939, "loss": 0.1368, "lr": 2.635335069067617e-06, "epoch": 2.07667731629393, "percentage": 69.22, "elapsed_time": "0:05:10", "remaining_time": "0:02:17"}
+{"current_steps": 660, "total_steps": 939, "loss": 0.1159, "lr": 2.4732168147677927e-06, "epoch": 2.108626198083067, "percentage": 70.29, "elapsed_time": "0:05:14", "remaining_time": "0:02:13"}
+{"current_steps": 670, "total_steps": 939, "loss": 0.1417, "lr": 2.314590802055232e-06, "epoch": 2.1405750798722045, "percentage": 71.35, "elapsed_time": "0:05:19", "remaining_time": "0:02:08"}
+{"current_steps": 680, "total_steps": 939, "loss": 0.1242, "lr": 2.159676266344222e-06, "epoch": 2.1725239616613417, "percentage": 72.42, "elapsed_time": "0:05:24", "remaining_time": "0:02:03"}
+{"current_steps": 690, "total_steps": 939, "loss": 0.1095, "lr": 2.0086873134540626e-06, "epoch": 2.2044728434504792, "percentage": 73.48, "elapsed_time": "0:05:29", "remaining_time": "0:01:58"}
+{"current_steps": 700, "total_steps": 939, "loss": 0.155, "lr": 1.8618326236955908e-06, "epoch": 2.236421725239617, "percentage": 74.55, "elapsed_time": "0:05:33", "remaining_time": "0:01:53"}
+{"current_steps": 710, "total_steps": 939, "loss": 0.1258, "lr": 1.7193151634562071e-06, "epoch": 2.268370607028754, "percentage": 75.61, "elapsed_time": "0:05:38", "remaining_time": "0:01:49"}
+{"current_steps": 720, "total_steps": 939, "loss": 0.1518, "lr": 1.581331904682089e-06, "epoch": 2.3003194888178915, "percentage": 76.68, "elapsed_time": "0:05:43", "remaining_time": "0:01:44"}
+{"current_steps": 730, "total_steps": 939, "loss": 0.1299, "lr": 1.4480735526452427e-06, "epoch": 2.3322683706070286, "percentage": 77.74, "elapsed_time": "0:05:48", "remaining_time": "0:01:39"}
+{"current_steps": 740, "total_steps": 939, "loss": 0.147, "lr": 1.319724282371664e-06, "epoch": 2.364217252396166, "percentage": 78.81, "elapsed_time": "0:05:52", "remaining_time": "0:01:34"}
+{"current_steps": 750, "total_steps": 939, "loss": 0.1209, "lr": 1.1964614840949002e-06, "epoch": 2.3961661341853033, "percentage": 79.87, "elapsed_time": "0:05:57", "remaining_time": "0:01:30"}
+{"current_steps": 760, "total_steps": 939, "loss": 0.115, "lr": 1.078455518086784e-06, "epoch": 2.428115015974441, "percentage": 80.94, "elapsed_time": "0:06:02", "remaining_time": "0:01:25"}
+{"current_steps": 770, "total_steps": 939, "loss": 0.1366, "lr": 9.658694792042284e-07, "epoch": 2.460063897763578, "percentage": 82.0, "elapsed_time": "0:06:06", "remaining_time": "0:01:20"}
+{"current_steps": 780, "total_steps": 939, "loss": 0.1184, "lr": 8.58858971477457e-07, "epoch": 2.4920127795527156, "percentage": 83.07, "elapsed_time": "0:06:11", "remaining_time": "0:01:15"}
+{"current_steps": 790, "total_steps": 939, "loss": 0.1227, "lr": 7.575718930512516e-07, "epoch": 2.523961661341853, "percentage": 84.13, "elapsed_time": "0:06:16", "remaining_time": "0:01:11"}
+{"current_steps": 800, "total_steps": 939, "loss": 0.1092, "lr": 6.621482317764105e-07, "epoch": 2.5559105431309903, "percentage": 85.2, "elapsed_time": "0:06:21", "remaining_time": "0:01:06"}
+{"current_steps": 810, "total_steps": 939, "loss": 0.1475, "lr": 5.727198717339511e-07, "epoch": 2.587859424920128, "percentage": 86.26, "elapsed_time": "0:06:26", "remaining_time": "0:01:01"}
+{"current_steps": 820, "total_steps": 939, "loss": 0.1242, "lr": 4.894104109594466e-07, "epoch": 2.619808306709265, "percentage": 87.33, "elapsed_time": "0:06:30", "remaining_time": "0:00:56"}
+{"current_steps": 830, "total_steps": 939, "loss": 0.1389, "lr": 4.123349906194357e-07, "epoch": 2.6517571884984026, "percentage": 88.39, "elapsed_time": "0:06:35", "remaining_time": "0:00:51"}
+{"current_steps": 840, "total_steps": 939, "loss": 0.1091, "lr": 3.416001358759635e-07, "epoch": 2.68370607028754, "percentage": 89.46, "elapsed_time": "0:06:40", "remaining_time": "0:00:47"}
+{"current_steps": 850, "total_steps": 939, "loss": 0.1272, "lr": 2.7730360865923954e-07, "epoch": 2.7156549520766773, "percentage": 90.52, "elapsed_time": "0:06:44", "remaining_time": "0:00:42"}
+{"current_steps": 860, "total_steps": 939, "loss": 0.1056, "lr": 2.1953427255185122e-07, "epoch": 2.747603833865815, "percentage": 91.59, "elapsed_time": "0:06:49", "remaining_time": "0:00:37"}
+{"current_steps": 870, "total_steps": 939, "loss": 0.1287, "lr": 1.6837196997130434e-07, "epoch": 2.779552715654952, "percentage": 92.65, "elapsed_time": "0:06:54", "remaining_time": "0:00:32"}
+{"current_steps": 880, "total_steps": 939, "loss": 0.1094, "lr": 1.2388741182062348e-07, "epoch": 2.8115015974440896, "percentage": 93.72, "elapsed_time": "0:06:59", "remaining_time": "0:00:28"}
+{"current_steps": 890, "total_steps": 939, "loss": 0.1464, "lr": 8.614207975952083e-08, "epoch": 2.8434504792332267, "percentage": 94.78, "elapsed_time": "0:07:03", "remaining_time": "0:00:23"}
+{"current_steps": 900, "total_steps": 939, "loss": 0.1388, "lr": 5.518814123121885e-08, "epoch": 2.8753993610223643, "percentage": 95.85, "elapsed_time": "0:07:08", "remaining_time": "0:00:18"}
+{"current_steps": 910, "total_steps": 939, "loss": 0.1236, "lr": 3.10683773623488e-08, "epoch": 2.9073482428115014, "percentage": 96.91, "elapsed_time": "0:07:13", "remaining_time": "0:00:13"}
+{"current_steps": 920, "total_steps": 939, "loss": 0.1044, "lr": 1.3816123835588835e-08, "epoch": 2.939297124600639, "percentage": 97.98, "elapsed_time": "0:07:17", "remaining_time": "0:00:09"}
+{"current_steps": 930, "total_steps": 939, "loss": 0.1423, "lr": 3.4552248167507576e-09, "epoch": 2.9712460063897765, "percentage": 99.04, "elapsed_time": "0:07:22", "remaining_time": "0:00:04"}
+{"current_steps": 939, "total_steps": 939, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:07:27", "remaining_time": "0:00:00"}

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json

@@ -0,0 +1,694 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 36.33285903930664,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 6.9124,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 37.845706939697266,
+      "learning_rate": 2.021276595744681e-06,
+      "loss": 6.6841,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 41.69117736816406,
+      "learning_rate": 3.0851063829787237e-06,
+      "loss": 6.721,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 50.03352737426758,
+      "learning_rate": 4.148936170212766e-06,
+      "loss": 6.1192,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 59.23619842529297,
+      "learning_rate": 5.212765957446809e-06,
+      "loss": 4.8473,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 5.8774261474609375,
+      "learning_rate": 6.276595744680851e-06,
+      "loss": 2.1142,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 6.693775653839111,
+      "learning_rate": 7.340425531914894e-06,
+      "loss": 1.6119,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 4.908555507659912,
+      "learning_rate": 8.404255319148937e-06,
+      "loss": 1.1825,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 2.0115675926208496,
+      "learning_rate": 9.46808510638298e-06,
+      "loss": 0.5337,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 0.8753984570503235,
+      "learning_rate": 9.999136119166803e-06,
+      "loss": 0.2692,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 0.8379660248756409,
+      "learning_rate": 9.9922268634943e-06,
+      "loss": 0.258,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.8429737687110901,
+      "learning_rate": 9.978417901361958e-06,
+      "loss": 0.234,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 0.6800509095191956,
+      "learning_rate": 9.95772831799724e-06,
+      "loss": 0.2045,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 1.0576311349868774,
+      "learning_rate": 9.930186708264902e-06,
+      "loss": 0.2049,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 0.681848406791687,
+      "learning_rate": 9.895831137146319e-06,
+      "loss": 0.1901,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 0.7110018730163574,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.1935,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 0.8011160492897034,
+      "learning_rate": 9.80687739258782e-06,
+      "loss": 0.1888,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.8912045359611511,
+      "learning_rate": 9.7524021612222e-06,
+      "loss": 0.194,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 1.1133105754852295,
+      "learning_rate": 9.691358682701927e-06,
+      "loss": 0.1843,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 1.3582327365875244,
+      "learning_rate": 9.623831324603755e-06,
+      "loss": 0.2121,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 1.2391612529754639,
+      "learning_rate": 9.549913415809084e-06,
+      "loss": 0.1797,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 1.0479785203933716,
+      "learning_rate": 9.469707117515068e-06,
+      "loss": 0.1636,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 1.0715245008468628,
+      "learning_rate": 9.383323282038632e-06,
+      "loss": 0.1693,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.9121628403663635,
+      "learning_rate": 9.29088129960862e-06,
+      "loss": 0.1296,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.2252585887908936,
+      "learning_rate": 9.192508933357753e-06,
+      "loss": 0.1393,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 1.1432126760482788,
+      "learning_rate": 9.088342142742493e-06,
+      "loss": 0.1796,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 1.1106261014938354,
+      "learning_rate": 8.978524895634842e-06,
+      "loss": 0.1672,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 1.1917647123336792,
+      "learning_rate": 8.86320896934581e-06,
+      "loss": 0.1813,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 1.1675026416778564,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.1847,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 2.2532408237457275,
+      "learning_rate": 8.616725966539831e-06,
+      "loss": 0.1642,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 1.000963807106018,
+      "learning_rate": 8.485899551698166e-06,
+      "loss": 0.1793,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 0.7248425483703613,
+      "learning_rate": 8.350255310200611e-06,
+      "loss": 0.1445,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 0.936930775642395,
+      "learning_rate": 8.209980714586955e-06,
+      "loss": 0.1495,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 0.8912279009819031,
+      "learning_rate": 8.065269636962765e-06,
+      "loss": 0.1478,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 1.2984365224838257,
+      "learning_rate": 7.916322081050708e-06,
+      "loss": 0.169,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.9977064728736877,
+      "learning_rate": 7.76334390576742e-06,
+      "loss": 0.1555,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 0.8419762849807739,
+      "learning_rate": 7.60654654070796e-06,
+      "loss": 0.1617,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.5433464050292969,
+      "learning_rate": 7.446146693931111e-06,
+      "loss": 0.1495,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 0.7475736737251282,
+      "learning_rate": 7.282366052449351e-06,
+      "loss": 0.1339,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 1.4355934858322144,
+      "learning_rate": 7.115430975837457e-06,
+      "loss": 0.1587,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.2254966497421265,
+      "learning_rate": 6.945572183383229e-06,
+      "loss": 0.1347,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 0.810607373714447,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.1292,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 1.0503230094909668,
+      "learning_rate": 6.598026207830428e-06,
+      "loss": 0.1636,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 1.5683962106704712,
+      "learning_rate": 6.4208193645237314e-06,
+      "loss": 0.1703,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 1.4046155214309692,
+      "learning_rate": 6.241648821085666e-06,
+      "loss": 0.1624,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 1.0360242128372192,
+      "learning_rate": 6.060762207319479e-06,
+      "loss": 0.1499,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 1.1383719444274902,
+      "learning_rate": 5.878409524791931e-06,
+      "loss": 0.1324,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 1.3533704280853271,
+      "learning_rate": 5.694842801308651e-06,
+      "loss": 0.1328,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 1.1995248794555664,
+      "learning_rate": 5.510315742589042e-06,
+      "loss": 0.1467,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 1.4972271919250488,
+      "learning_rate": 5.325083381622165e-06,
+      "loss": 0.1569,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 0.6726014018058777,
+      "learning_rate": 5.139401726188208e-06,
+      "loss": 0.1444,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 0.8959933519363403,
+      "learning_rate": 4.953527405032723e-06,
+      "loss": 0.1727,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 1.0952670574188232,
+      "learning_rate": 4.767717313182611e-06,
+      "loss": 0.1548,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 1.1545971632003784,
+      "learning_rate": 4.582228256894093e-06,
+      "loss": 0.1335,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 1.5466020107269287,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.168,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 1.089145302772522,
+      "learning_rate": 4.2132379032105695e-06,
+      "loss": 0.1604,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 1.0096254348754883,
+      "learning_rate": 4.030246583666437e-06,
+      "loss": 0.1418,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 0.9796081781387329,
+      "learning_rate": 3.848595550550401e-06,
+      "loss": 0.1403,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 1.1617341041564941,
+      "learning_rate": 3.668535861925509e-06,
+      "loss": 0.1433,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 0.7589540481567383,
+      "learning_rate": 3.4903163764736104e-06,
+      "loss": 0.1388,
+      "step": 600
+    },
+    {
+      "epoch": 1.9488817891373802,
+      "grad_norm": 0.7963077425956726,
+      "learning_rate": 3.314183409550293e-06,
+      "loss": 0.1251,
+      "step": 610
+    },
+    {
+      "epoch": 1.9808306709265175,
+      "grad_norm": 1.1559962034225464,
+      "learning_rate": 3.140380392754901e-06,
+      "loss": 0.1276,
+      "step": 620
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 0.6292369365692139,
+      "learning_rate": 2.969147537486175e-06,
+      "loss": 0.1428,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 1.1892845630645752,
+      "learning_rate": 2.800721502948506e-06,
+      "loss": 0.1454,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 0.8596490621566772,
+      "learning_rate": 2.635335069067617e-06,
+      "loss": 0.1368,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 0.8156671524047852,
+      "learning_rate": 2.4732168147677927e-06,
+      "loss": 0.1159,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 1.977015733718872,
+      "learning_rate": 2.314590802055232e-06,
+      "loss": 0.1417,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 1.2084506750106812,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.1242,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 1.1458317041397095,
+      "learning_rate": 2.0086873134540626e-06,
+      "loss": 0.1095,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 1.8264726400375366,
+      "learning_rate": 1.8618326236955908e-06,
+      "loss": 0.155,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 1.4171464443206787,
+      "learning_rate": 1.7193151634562071e-06,
+      "loss": 0.1258,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 1.4613436460494995,
+      "learning_rate": 1.581331904682089e-06,
+      "loss": 0.1518,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 1.093307614326477,
+      "learning_rate": 1.4480735526452427e-06,
+      "loss": 0.1299,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 1.374348521232605,
+      "learning_rate": 1.319724282371664e-06,
+      "loss": 0.147,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 1.2374401092529297,
+      "learning_rate": 1.1964614840949002e-06,
+      "loss": 0.1209,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 1.249546766281128,
+      "learning_rate": 1.078455518086784e-06,
+      "loss": 0.115,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 1.0231386423110962,
+      "learning_rate": 9.658694792042284e-07,
+      "loss": 0.1366,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 1.1464241743087769,
+      "learning_rate": 8.58858971477457e-07,
+      "loss": 0.1184,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 0.9766585230827332,
+      "learning_rate": 7.575718930512516e-07,
+      "loss": 0.1227,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 1.1977977752685547,
+      "learning_rate": 6.621482317764105e-07,
+      "loss": 0.1092,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 1.6657644510269165,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.1475,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 1.3672709465026855,
+      "learning_rate": 4.894104109594466e-07,
+      "loss": 0.1242,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 1.7629551887512207,
+      "learning_rate": 4.123349906194357e-07,
+      "loss": 0.1389,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 0.8762993812561035,
+      "learning_rate": 3.416001358759635e-07,
+      "loss": 0.1091,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 1.4116370677947998,
+      "learning_rate": 2.7730360865923954e-07,
+      "loss": 0.1272,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 1.2336490154266357,
+      "learning_rate": 2.1953427255185122e-07,
+      "loss": 0.1056,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 1.4972121715545654,
+      "learning_rate": 1.6837196997130434e-07,
+      "loss": 0.1287,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 1.169806957244873,
+      "learning_rate": 1.2388741182062348e-07,
+      "loss": 0.1094,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 1.0118532180786133,
+      "learning_rate": 8.614207975952083e-08,
+      "loss": 0.1464,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 1.9891964197158813,
+      "learning_rate": 5.518814123121885e-08,
+      "loss": 0.1388,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 1.1589871644973755,
+      "learning_rate": 3.10683773623488e-08,
+      "loss": 0.1236,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 1.1757524013519287,
+      "learning_rate": 1.3816123835588835e-08,
+      "loss": 0.1044,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 1.4213329553604126,
+      "learning_rate": 3.4552248167507576e-09,
+      "loss": 0.1423,
+      "step": 930
+    },
+    {
+      "epoch": 3.0,
+      "step": 939,
+      "total_flos": 1.8033509624132403e+17,
+      "train_loss": 0.5275962893256999,
+      "train_runtime": 463.0949,
+      "train_samples_per_second": 64.782,
+      "train_steps_per_second": 2.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8033509624132403e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the csqa__qwen3_8b__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f_lora_sft dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc556cc0eef508eb774759488ae917fb6b312a0dc043c82d664d3bc4af111d45
+size 87360584

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/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
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.4737480102602342e+17,
+    "train_loss": 0.4462493950058731,
+    "train_runtime": 438.8238,
+    "train_samples_per_second": 68.365,
+    "train_steps_per_second": 2.14
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/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 %}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+---
+
+# 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 0.15.2

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc556cc0eef508eb774759488ae917fb6b312a0dc043c82d664d3bc4af111d45
+size 87360584

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/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 %}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa7927adc0d9f6d98c82900cc6eef5bee0ed1e6b231854e34dc1dc8c1d602ca
+size 175012683

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d51a89f706019e82a1bece244691bbef31c0dc9544212f828d427b8052b077
+size 16389

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db2a9d890a3bdfb6477301adcccedc994df442a5cf1f4f617b4737086e632ef
+size 16389

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f99367832c29a5aff6042c0dc14d87a3ffc16ce9cc6466678227421d213c43
+size 16389

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2984cd1dfb7f3fdddf5cc99bb1dab2759a14eef425d83154d76b310151f5d01c
+size 16389

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb1eac572046e66de7e9c52bba4d61d758728542e4fdc6d8b194a6c29e10f96
+size 16389

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41da76e42d56dcd9ee4821dcdf66fd5f2e82e821081ec3e07cb7e1e952647992
+size 16389

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ef332606e64d74e7d5d444ae550c6edf2fe161722c5d652fd47845e2aa1894
+size 16389

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b125a8a8f1fcea8543fd480628a947fbdff2ec9452d6a7be7e77a426d76b0c
+size 16389

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70583c9a51d736f1353b66ad07c780d71300daef1dfeacad27c4a2efb4fd9d68
+size 1465

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8659b993a9025fced8eda027b3eb2c8012015107d38086de64143bfb5704ef31
+size 6161

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}