Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-464/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-200/README.md

@@ -0,0 +1,208 @@
+---
+base_model: ./Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./Qwen3-4B-Instruct-2507
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.16.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen3-4B-Instruct-2507",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1a8edfe915361f46ee15ff54e805bb4102aac075069e143da8798a54f575a5
+size 1817430408

checkpoint-200/added_tokens.json

@@ -0,0 +1,31 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|analysis|>": 151670,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|forecast|>": 151671,
+  "<|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,
+  "<|response|>": 151669,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-200/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb82c7a96e352346fd9c532cc7a78d4993346b20d26e447c50efd8d1f44870a
+size 528908363

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124625e167eb28acbfc793cfcb3e8a08b32e7fea06501462bc9e420a5e1beb2a
+size 1383

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae31a1f07745133886de64683a6542968a818c2f2d468210dfced7cf8fa629d
+size 1465

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|analysis|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|forecast|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77247e5fb2e966d04e513068b17cca472e105e7c56953e9b1d27d70b93d77e6f
+size 11423221

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,254 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|analysis|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|forecast|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|response|>",
+    "<|analysis|>",
+    "<|forecast|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7241379310344827,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": 0.003562385216355324,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 6.5818,
+      "step": 2
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.00022410321980714798,
+      "learning_rate": 2.5e-05,
+      "loss": 3.1274,
+      "step": 4
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 0.001015713787637651,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 6.2659,
+      "step": 6
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 5.367869744077325e-05,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 2.6228,
+      "step": 8
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 4.5336004404816777e-05,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.5434,
+      "step": 10
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 4.627772432286292e-05,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 2.3415,
+      "step": 12
+    },
+    {
+      "epoch": 0.1206896551724138,
+      "grad_norm": 3.9416841900674626e-05,
+      "learning_rate": 0.00010833333333333333,
+      "loss": 2.3444,
+      "step": 14
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 3.731855395017192e-05,
+      "learning_rate": 0.000125,
+      "loss": 2.2561,
+      "step": 16
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 3.3787582651712e-05,
+      "learning_rate": 0.00014166666666666668,
+      "loss": 2.2835,
+      "step": 18
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 3.5183733416488394e-05,
+      "learning_rate": 0.00015833333333333332,
+      "loss": 2.1617,
+      "step": 20
+    },
+    {
+      "epoch": 0.1896551724137931,
+      "grad_norm": 2.609785042295698e-05,
+      "learning_rate": 0.000175,
+      "loss": 2.1658,
+      "step": 22
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 2.222553302999586e-05,
+      "learning_rate": 0.00019166666666666667,
+      "loss": 2.0384,
+      "step": 24
+    },
+    {
+      "epoch": 0.22413793103448276,
+      "grad_norm": 2.2757671104045585e-05,
+      "learning_rate": 0.00019999745104274993,
+      "loss": 2.1457,
+      "step": 26
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 2.0901892639813013e-05,
+      "learning_rate": 0.0001999770601644046,
+      "loss": 2.0479,
+      "step": 28
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 2.0703126210719347e-05,
+      "learning_rate": 0.0001999362825656992,
+      "loss": 2.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 2.1005034795962274e-05,
+      "learning_rate": 0.0001998751265617561,
+      "loss": 2.055,
+      "step": 32
+    },
+    {
+      "epoch": 0.29310344827586204,
+      "grad_norm": 1.9665612853714265e-05,
+      "learning_rate": 0.00019979360462313962,
+      "loss": 1.9215,
+      "step": 34
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 2.0705581846414134e-05,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 1.8961,
+      "step": 36
+    },
+    {
+      "epoch": 0.3275862068965517,
+      "grad_norm": 2.2074158550822176e-05,
+      "learning_rate": 0.00019956953358524774,
+      "loss": 1.9082,
+      "step": 38
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 2.1002635548938997e-05,
+      "learning_rate": 0.00019942703017718975,
+      "loss": 1.934,
+      "step": 40
+    },
+    {
+      "epoch": 0.3620689655172414,
+      "grad_norm": 1.9619050362962298e-05,
+      "learning_rate": 0.00019926425220757605,
+      "loss": 1.8817,
+      "step": 42
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 2.059372673102189e-05,
+      "learning_rate": 0.00019908123286911046,
+      "loss": 2.0008,
+      "step": 44
+    },
+    {
+      "epoch": 0.39655172413793105,
+      "grad_norm": 1.98649267986184e-05,
+      "learning_rate": 0.00019887800948199496,
+      "loss": 1.8766,
+      "step": 46
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 2.3096907170838676e-05,
+      "learning_rate": 0.00019865462348631944,
+      "loss": 1.7926,
+      "step": 48
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 2.106586362060625e-05,
+      "learning_rate": 0.0001984111204336116,
+      "loss": 1.9005,
+      "step": 50
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 2.156079062842764e-05,
+      "learning_rate": 0.0001981475499775484,
+      "loss": 1.9158,
+      "step": 52
+    },
+    {
+      "epoch": 0.46551724137931033,
+      "grad_norm": 2.2075933884480037e-05,
+      "learning_rate": 0.00019786396586383075,
+      "loss": 1.903,
+      "step": 54
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 2.0557081370498054e-05,
+      "learning_rate": 0.00019756042591922434,
+      "loss": 1.8811,
+      "step": 56
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.944549148902297e-05,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 1.8026,
+      "step": 58
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 2.6996058295480907e-05,
+      "learning_rate": 0.00019689373017815073,
+      "loss": 1.8647,
+      "step": 60
+    },
+    {
+      "epoch": 0.5344827586206896,
+      "grad_norm": 2.1660236598108895e-05,
+      "learning_rate": 0.00019653071033026633,
+      "loss": 1.8209,
+      "step": 62
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 2.476519875926897e-05,
+      "learning_rate": 0.00019614800652093686,
+      "loss": 1.8078,
+      "step": 64
+    },
+    {
+      "epoch": 0.5689655172413793,
+      "grad_norm": 2.4084582037176006e-05,
+      "learning_rate": 0.00019574569678881964,
+      "loss": 1.8253,
+      "step": 66
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 2.4040386051638052e-05,
+      "learning_rate": 0.00019532386317049383,
+      "loss": 1.8044,
+      "step": 68
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 2.3245340344146825e-05,
+      "learning_rate": 0.00019488259168373197,
+      "loss": 1.8383,
+      "step": 70
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 2.399735603830777e-05,
+      "learning_rate": 0.0001944219723099596,
+      "loss": 1.852,
+      "step": 72
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 2.5779550924198702e-05,
+      "learning_rate": 0.00019394209897590704,
+      "loss": 2.2878,
+      "step": 74
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 2.9553415515692905e-05,
+      "learning_rate": 0.00019344306953445633,
+      "loss": 1.9217,
+      "step": 76
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 2.9237366106826812e-05,
+      "learning_rate": 0.00019292498574468748,
+      "loss": 1.8601,
+      "step": 78
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 2.6727117074187845e-05,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 1.8181,
+      "step": 80
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 2.680359648365993e-05,
+      "learning_rate": 0.0001918320815622137,
+      "loss": 1.8295,
+      "step": 82
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 2.3158025214797817e-05,
+      "learning_rate": 0.0001912574840279516,
+      "loss": 1.8614,
+      "step": 84
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 3.017827111762017e-05,
+      "learning_rate": 0.00019066427781681315,
+      "loss": 1.757,
+      "step": 86
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 2.1740601368946955e-05,
+      "learning_rate": 0.00019005258389183851,
+      "loss": 1.8096,
+      "step": 88
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 2.1615645891870372e-05,
+      "learning_rate": 0.00018942252698597113,
+      "loss": 1.7802,
+      "step": 90
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 2.0820896679651923e-05,
+      "learning_rate": 0.00018877423557662305,
+      "loss": 1.7246,
+      "step": 92
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 2.3314805730478838e-05,
+      "learning_rate": 0.00018810784185947646,
+      "loss": 1.8366,
+      "step": 94
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 2.5301331334048882e-05,
+      "learning_rate": 0.00018742348172152726,
+      "loss": 1.8826,
+      "step": 96
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 2.6756286388263106e-05,
+      "learning_rate": 0.00018672129471337568,
+      "loss": 1.7417,
+      "step": 98
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 2.8393502361723222e-05,
+      "learning_rate": 0.00018600142402077006,
+      "loss": 1.8275,
+      "step": 100
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 2.184685035899747e-05,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 1.7819,
+      "step": 102
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 2.5997507691499777e-05,
+      "learning_rate": 0.00018450922232500966,
+      "loss": 1.8088,
+      "step": 104
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 2.3897668143035844e-05,
+      "learning_rate": 0.00018373719560264327,
+      "loss": 1.8686,
+      "step": 106
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 2.715570735745132e-05,
+      "learning_rate": 0.00018294809369535263,
+      "loss": 1.8138,
+      "step": 108
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 3.2870055292733014e-05,
+      "learning_rate": 0.00018214207751204918,
+      "loss": 1.8485,
+      "step": 110
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 2.1189727704040706e-05,
+      "learning_rate": 0.00018131931141070163,
+      "loss": 1.825,
+      "step": 112
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 4.0714276110520586e-05,
+      "learning_rate": 0.00018047996316482135,
+      "loss": 1.7557,
+      "step": 114
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.3534433643799275e-05,
+      "learning_rate": 0.00017962420392925066,
+      "loss": 1.6649,
+      "step": 116
+    },
+    {
+      "epoch": 1.0172413793103448,
+      "grad_norm": 3.003507481480483e-05,
+      "learning_rate": 0.00017875220820526218,
+      "loss": 1.7448,
+      "step": 118
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 2.9781367629766464e-05,
+      "learning_rate": 0.00017786415380497553,
+      "loss": 1.7457,
+      "step": 120
+    },
+    {
+      "epoch": 1.0517241379310345,
+      "grad_norm": 2.081507227558177e-05,
+      "learning_rate": 0.00017696022181509894,
+      "loss": 1.7675,
+      "step": 122
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 2.6256357159581967e-05,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 1.7417,
+      "step": 124
+    },
+    {
+      "epoch": 1.0862068965517242,
+      "grad_norm": 3.1936106097418815e-05,
+      "learning_rate": 0.00017510546556413498,
+      "loss": 1.7653,
+      "step": 126
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 2.2676726075587794e-05,
+      "learning_rate": 0.0001741550195137788,
+      "loss": 1.7457,
+      "step": 128
+    },
+    {
+      "epoch": 1.1206896551724137,
+      "grad_norm": 3.1191233574645594e-05,
+      "learning_rate": 0.00017318945221817255,
+      "loss": 1.7546,
+      "step": 130
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 2.654504351085052e-05,
+      "learning_rate": 0.0001722089605699875,
+      "loss": 1.695,
+      "step": 132
+    },
+    {
+      "epoch": 1.1551724137931034,
+      "grad_norm": 2.8716958695440553e-05,
+      "learning_rate": 0.00017121374450517916,
+      "loss": 1.7442,
+      "step": 134
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 3.173397635691799e-05,
+      "learning_rate": 0.00017020400696221737,
+      "loss": 1.8053,
+      "step": 136
+    },
+    {
+      "epoch": 1.1896551724137931,
+      "grad_norm": 2.7111556846648455e-05,
+      "learning_rate": 0.0001691799538407044,
+      "loss": 1.7553,
+      "step": 138
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 2.1949501388007775e-05,
+      "learning_rate": 0.00016814179395938913,
+      "loss": 1.6792,
+      "step": 140
+    },
+    {
+      "epoch": 1.2241379310344827,
+      "grad_norm": 2.9802749850205146e-05,
+      "learning_rate": 0.00016708973901358602,
+      "loss": 1.755,
+      "step": 142
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 2.4393058993155137e-05,
+      "learning_rate": 0.0001660240035320075,
+      "loss": 1.6939,
+      "step": 144
+    },
+    {
+      "epoch": 1.2586206896551724,
+      "grad_norm": 2.3840178982936777e-05,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 1.7703,
+      "step": 146
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 2.3855336621636525e-05,
+      "learning_rate": 0.00016385236298032183,
+      "loss": 1.7331,
+      "step": 148
+    },
+    {
+      "epoch": 1.293103448275862,
+      "grad_norm": 3.826155807473697e-05,
+      "learning_rate": 0.0001627469007380852,
+      "loss": 1.7543,
+      "step": 150
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 2.4928000129875727e-05,
+      "learning_rate": 0.0001616286435255153,
+      "loss": 1.7365,
+      "step": 152
+    },
+    {
+      "epoch": 1.3275862068965516,
+      "grad_norm": 3.5061420931015164e-05,
+      "learning_rate": 0.00016049781937089227,
+      "loss": 1.7058,
+      "step": 154
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 3.1686500733485445e-05,
+      "learning_rate": 0.00015935465886507142,
+      "loss": 1.6998,
+      "step": 156
+    },
+    {
+      "epoch": 1.3620689655172413,
+      "grad_norm": 2.7497104383655824e-05,
+      "learning_rate": 0.0001581993951144626,
+      "loss": 1.8166,
+      "step": 158
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 3.0560615414287895e-05,
+      "learning_rate": 0.0001570322636934964,
+      "loss": 1.6751,
+      "step": 160
+    },
+    {
+      "epoch": 1.396551724137931,
+      "grad_norm": 3.0291541406768374e-05,
+      "learning_rate": 0.00015585350259658746,
+      "loss": 1.7102,
+      "step": 162
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 2.4553977709729224e-05,
+      "learning_rate": 0.0001546633521896038,
+      "loss": 1.7563,
+      "step": 164
+    },
+    {
+      "epoch": 1.4310344827586206,
+      "grad_norm": 3.996691884822212e-05,
+      "learning_rate": 0.00015346205516085306,
+      "loss": 1.7017,
+      "step": 166
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 2.5090428607654758e-05,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 1.721,
+      "step": 168
+    },
+    {
+      "epoch": 1.4655172413793103,
+      "grad_norm": 4.993643597117625e-05,
+      "learning_rate": 0.00015102700330609,
+      "loss": 1.7036,
+      "step": 170
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 2.340052742511034e-05,
+      "learning_rate": 0.0001497937450211956,
+      "loss": 1.7574,
+      "step": 172
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.563516293070279e-05,
+      "learning_rate": 0.00014855033309551843,
+      "loss": 1.756,
+      "step": 174
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 3.225682667107321e-05,
+      "learning_rate": 0.00014729702107813436,
+      "loss": 1.8053,
+      "step": 176
+    },
+    {
+      "epoch": 1.5344827586206895,
+      "grad_norm": 2.349480018892791e-05,
+      "learning_rate": 0.00014603406453688654,
+      "loss": 1.7376,
+      "step": 178
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 4.0241888200398535e-05,
+      "learning_rate": 0.00014476172100627127,
+      "loss": 1.7475,
+      "step": 180
+    },
+    {
+      "epoch": 1.5689655172413794,
+      "grad_norm": 4.396059739519842e-05,
+      "learning_rate": 0.0001434802499349232,
+      "loss": 1.735,
+      "step": 182
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 3.024659599759616e-05,
+      "learning_rate": 0.00014218991263271024,
+      "loss": 1.7426,
+      "step": 184
+    },
+    {
+      "epoch": 1.603448275862069,
+      "grad_norm": 3.1224055419443175e-05,
+      "learning_rate": 0.00014089097221744868,
+      "loss": 1.6746,
+      "step": 186
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 2.243503877252806e-05,
+      "learning_rate": 0.00013958369356124986,
+      "loss": 1.6508,
+      "step": 188
+    },
+    {
+      "epoch": 1.6379310344827587,
+      "grad_norm": 2.4827659217407927e-05,
+      "learning_rate": 0.000138268343236509,
+      "loss": 1.7289,
+      "step": 190
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 2.582685192464851e-05,
+      "learning_rate": 0.0001369451894615474,
+      "loss": 1.7791,
+      "step": 192
+    },
+    {
+      "epoch": 1.6724137931034484,
+      "grad_norm": 3.327808735775761e-05,
+      "learning_rate": 0.00013561450204591896,
+      "loss": 1.8354,
+      "step": 194
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 4.714803071692586e-05,
+      "learning_rate": 0.00013427655233539228,
+      "loss": 1.7645,
+      "step": 196
+    },
+    {
+      "epoch": 1.706896551724138,
+      "grad_norm": 2.8617656425922178e-05,
+      "learning_rate": 0.00013293161315661931,
+      "loss": 1.7147,
+      "step": 198
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 2.9135431759641506e-05,
+      "learning_rate": 0.0001315799587615025,
+      "loss": 1.636,
+      "step": 200
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 464,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.897642293957755e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e0384a95773c4f9f1910994edd74cc0c1467bafb112774589033914dd397a4
+size 5713

checkpoint-400/README.md

@@ -0,0 +1,208 @@
+---
+base_model: ./Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./Qwen3-4B-Instruct-2507
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.16.0

checkpoint-400/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen3-4B-Instruct-2507",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc642db422e50800627b89ed84c36fcc8f8cad0f44edeb6f4f64ac4e70a82341
+size 1817430408

checkpoint-400/added_tokens.json

@@ -0,0 +1,31 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|analysis|>": 151670,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|forecast|>": 151671,
+  "<|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,
+  "<|response|>": 151669,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-400/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e6015a6070ba3f65bb9d76dd393b4217a940b0db3c822104c4179d6a28c0ccb
+size 528908363

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
+size 14645

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
+size 1383

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84d90b33e4206c1fad04873a475b979c3290542c7367de37a03878679850e4d
+size 1465

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|analysis|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|forecast|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77247e5fb2e966d04e513068b17cca472e105e7c56953e9b1d27d70b93d77e6f
+size 11423221

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,254 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|analysis|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|forecast|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|response|>",
+    "<|analysis|>",
+    "<|forecast|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-400/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.4482758620689653,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": 0.003562385216355324,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 6.5818,
+      "step": 2
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.00022410321980714798,
+      "learning_rate": 2.5e-05,
+      "loss": 3.1274,
+      "step": 4
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 0.001015713787637651,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 6.2659,
+      "step": 6
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 5.367869744077325e-05,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 2.6228,
+      "step": 8
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 4.5336004404816777e-05,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.5434,
+      "step": 10
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 4.627772432286292e-05,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 2.3415,
+      "step": 12
+    },
+    {
+      "epoch": 0.1206896551724138,
+      "grad_norm": 3.9416841900674626e-05,
+      "learning_rate": 0.00010833333333333333,
+      "loss": 2.3444,
+      "step": 14
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 3.731855395017192e-05,
+      "learning_rate": 0.000125,
+      "loss": 2.2561,
+      "step": 16
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 3.3787582651712e-05,
+      "learning_rate": 0.00014166666666666668,
+      "loss": 2.2835,
+      "step": 18
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 3.5183733416488394e-05,
+      "learning_rate": 0.00015833333333333332,
+      "loss": 2.1617,
+      "step": 20
+    },
+    {
+      "epoch": 0.1896551724137931,
+      "grad_norm": 2.609785042295698e-05,
+      "learning_rate": 0.000175,
+      "loss": 2.1658,
+      "step": 22
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 2.222553302999586e-05,
+      "learning_rate": 0.00019166666666666667,
+      "loss": 2.0384,
+      "step": 24
+    },
+    {
+      "epoch": 0.22413793103448276,
+      "grad_norm": 2.2757671104045585e-05,
+      "learning_rate": 0.00019999745104274993,
+      "loss": 2.1457,
+      "step": 26
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 2.0901892639813013e-05,
+      "learning_rate": 0.0001999770601644046,
+      "loss": 2.0479,
+      "step": 28
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 2.0703126210719347e-05,
+      "learning_rate": 0.0001999362825656992,
+      "loss": 2.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 2.1005034795962274e-05,
+      "learning_rate": 0.0001998751265617561,
+      "loss": 2.055,
+      "step": 32
+    },
+    {
+      "epoch": 0.29310344827586204,
+      "grad_norm": 1.9665612853714265e-05,
+      "learning_rate": 0.00019979360462313962,
+      "loss": 1.9215,
+      "step": 34
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 2.0705581846414134e-05,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 1.8961,
+      "step": 36
+    },
+    {
+      "epoch": 0.3275862068965517,
+      "grad_norm": 2.2074158550822176e-05,
+      "learning_rate": 0.00019956953358524774,
+      "loss": 1.9082,
+      "step": 38
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 2.1002635548938997e-05,
+      "learning_rate": 0.00019942703017718975,
+      "loss": 1.934,
+      "step": 40
+    },
+    {
+      "epoch": 0.3620689655172414,
+      "grad_norm": 1.9619050362962298e-05,
+      "learning_rate": 0.00019926425220757605,
+      "loss": 1.8817,
+      "step": 42
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 2.059372673102189e-05,
+      "learning_rate": 0.00019908123286911046,
+      "loss": 2.0008,
+      "step": 44
+    },
+    {
+      "epoch": 0.39655172413793105,
+      "grad_norm": 1.98649267986184e-05,
+      "learning_rate": 0.00019887800948199496,
+      "loss": 1.8766,
+      "step": 46
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 2.3096907170838676e-05,
+      "learning_rate": 0.00019865462348631944,
+      "loss": 1.7926,
+      "step": 48
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 2.106586362060625e-05,
+      "learning_rate": 0.0001984111204336116,
+      "loss": 1.9005,
+      "step": 50
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 2.156079062842764e-05,
+      "learning_rate": 0.0001981475499775484,
+      "loss": 1.9158,
+      "step": 52
+    },
+    {
+      "epoch": 0.46551724137931033,
+      "grad_norm": 2.2075933884480037e-05,
+      "learning_rate": 0.00019786396586383075,
+      "loss": 1.903,
+      "step": 54
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 2.0557081370498054e-05,
+      "learning_rate": 0.00019756042591922434,
+      "loss": 1.8811,
+      "step": 56
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.944549148902297e-05,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 1.8026,
+      "step": 58
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 2.6996058295480907e-05,
+      "learning_rate": 0.00019689373017815073,
+      "loss": 1.8647,
+      "step": 60
+    },
+    {
+      "epoch": 0.5344827586206896,
+      "grad_norm": 2.1660236598108895e-05,
+      "learning_rate": 0.00019653071033026633,
+      "loss": 1.8209,
+      "step": 62
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 2.476519875926897e-05,
+      "learning_rate": 0.00019614800652093686,
+      "loss": 1.8078,
+      "step": 64
+    },
+    {
+      "epoch": 0.5689655172413793,
+      "grad_norm": 2.4084582037176006e-05,
+      "learning_rate": 0.00019574569678881964,
+      "loss": 1.8253,
+      "step": 66
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 2.4040386051638052e-05,
+      "learning_rate": 0.00019532386317049383,
+      "loss": 1.8044,
+      "step": 68
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 2.3245340344146825e-05,
+      "learning_rate": 0.00019488259168373197,
+      "loss": 1.8383,
+      "step": 70
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 2.399735603830777e-05,
+      "learning_rate": 0.0001944219723099596,
+      "loss": 1.852,
+      "step": 72
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 2.5779550924198702e-05,
+      "learning_rate": 0.00019394209897590704,
+      "loss": 2.2878,
+      "step": 74
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 2.9553415515692905e-05,
+      "learning_rate": 0.00019344306953445633,
+      "loss": 1.9217,
+      "step": 76
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 2.9237366106826812e-05,
+      "learning_rate": 0.00019292498574468748,
+      "loss": 1.8601,
+      "step": 78
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 2.6727117074187845e-05,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 1.8181,
+      "step": 80
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 2.680359648365993e-05,
+      "learning_rate": 0.0001918320815622137,
+      "loss": 1.8295,
+      "step": 82
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 2.3158025214797817e-05,
+      "learning_rate": 0.0001912574840279516,
+      "loss": 1.8614,
+      "step": 84
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 3.017827111762017e-05,
+      "learning_rate": 0.00019066427781681315,
+      "loss": 1.757,
+      "step": 86
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 2.1740601368946955e-05,
+      "learning_rate": 0.00019005258389183851,
+      "loss": 1.8096,
+      "step": 88
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 2.1615645891870372e-05,
+      "learning_rate": 0.00018942252698597113,
+      "loss": 1.7802,
+      "step": 90
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 2.0820896679651923e-05,
+      "learning_rate": 0.00018877423557662305,
+      "loss": 1.7246,
+      "step": 92
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 2.3314805730478838e-05,
+      "learning_rate": 0.00018810784185947646,
+      "loss": 1.8366,
+      "step": 94
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 2.5301331334048882e-05,
+      "learning_rate": 0.00018742348172152726,
+      "loss": 1.8826,
+      "step": 96
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 2.6756286388263106e-05,
+      "learning_rate": 0.00018672129471337568,
+      "loss": 1.7417,
+      "step": 98
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 2.8393502361723222e-05,
+      "learning_rate": 0.00018600142402077006,
+      "loss": 1.8275,
+      "step": 100
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 2.184685035899747e-05,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 1.7819,
+      "step": 102
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 2.5997507691499777e-05,
+      "learning_rate": 0.00018450922232500966,
+      "loss": 1.8088,
+      "step": 104
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 2.3897668143035844e-05,
+      "learning_rate": 0.00018373719560264327,
+      "loss": 1.8686,
+      "step": 106
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 2.715570735745132e-05,
+      "learning_rate": 0.00018294809369535263,
+      "loss": 1.8138,
+      "step": 108
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 3.2870055292733014e-05,
+      "learning_rate": 0.00018214207751204918,
+      "loss": 1.8485,
+      "step": 110
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 2.1189727704040706e-05,
+      "learning_rate": 0.00018131931141070163,
+      "loss": 1.825,
+      "step": 112
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 4.0714276110520586e-05,
+      "learning_rate": 0.00018047996316482135,
+      "loss": 1.7557,
+      "step": 114
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.3534433643799275e-05,
+      "learning_rate": 0.00017962420392925066,
+      "loss": 1.6649,
+      "step": 116
+    },
+    {
+      "epoch": 1.0172413793103448,
+      "grad_norm": 3.003507481480483e-05,
+      "learning_rate": 0.00017875220820526218,
+      "loss": 1.7448,
+      "step": 118
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 2.9781367629766464e-05,
+      "learning_rate": 0.00017786415380497553,
+      "loss": 1.7457,
+      "step": 120
+    },
+    {
+      "epoch": 1.0517241379310345,
+      "grad_norm": 2.081507227558177e-05,
+      "learning_rate": 0.00017696022181509894,
+      "loss": 1.7675,
+      "step": 122
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 2.6256357159581967e-05,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 1.7417,
+      "step": 124
+    },
+    {
+      "epoch": 1.0862068965517242,
+      "grad_norm": 3.1936106097418815e-05,
+      "learning_rate": 0.00017510546556413498,
+      "loss": 1.7653,
+      "step": 126
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 2.2676726075587794e-05,
+      "learning_rate": 0.0001741550195137788,
+      "loss": 1.7457,
+      "step": 128
+    },
+    {
+      "epoch": 1.1206896551724137,
+      "grad_norm": 3.1191233574645594e-05,
+      "learning_rate": 0.00017318945221817255,
+      "loss": 1.7546,
+      "step": 130
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 2.654504351085052e-05,
+      "learning_rate": 0.0001722089605699875,
+      "loss": 1.695,
+      "step": 132
+    },
+    {
+      "epoch": 1.1551724137931034,
+      "grad_norm": 2.8716958695440553e-05,
+      "learning_rate": 0.00017121374450517916,
+      "loss": 1.7442,
+      "step": 134
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 3.173397635691799e-05,
+      "learning_rate": 0.00017020400696221737,
+      "loss": 1.8053,
+      "step": 136
+    },
+    {
+      "epoch": 1.1896551724137931,
+      "grad_norm": 2.7111556846648455e-05,
+      "learning_rate": 0.0001691799538407044,
+      "loss": 1.7553,
+      "step": 138
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 2.1949501388007775e-05,
+      "learning_rate": 0.00016814179395938913,
+      "loss": 1.6792,
+      "step": 140
+    },
+    {
+      "epoch": 1.2241379310344827,
+      "grad_norm": 2.9802749850205146e-05,
+      "learning_rate": 0.00016708973901358602,
+      "loss": 1.755,
+      "step": 142
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 2.4393058993155137e-05,
+      "learning_rate": 0.0001660240035320075,
+      "loss": 1.6939,
+      "step": 144
+    },
+    {
+      "epoch": 1.2586206896551724,
+      "grad_norm": 2.3840178982936777e-05,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 1.7703,
+      "step": 146
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 2.3855336621636525e-05,
+      "learning_rate": 0.00016385236298032183,
+      "loss": 1.7331,
+      "step": 148
+    },
+    {
+      "epoch": 1.293103448275862,
+      "grad_norm": 3.826155807473697e-05,
+      "learning_rate": 0.0001627469007380852,
+      "loss": 1.7543,
+      "step": 150
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 2.4928000129875727e-05,
+      "learning_rate": 0.0001616286435255153,
+      "loss": 1.7365,
+      "step": 152
+    },
+    {
+      "epoch": 1.3275862068965516,
+      "grad_norm": 3.5061420931015164e-05,
+      "learning_rate": 0.00016049781937089227,
+      "loss": 1.7058,
+      "step": 154
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 3.1686500733485445e-05,
+      "learning_rate": 0.00015935465886507142,
+      "loss": 1.6998,
+      "step": 156
+    },
+    {
+      "epoch": 1.3620689655172413,
+      "grad_norm": 2.7497104383655824e-05,
+      "learning_rate": 0.0001581993951144626,
+      "loss": 1.8166,
+      "step": 158
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 3.0560615414287895e-05,
+      "learning_rate": 0.0001570322636934964,
+      "loss": 1.6751,
+      "step": 160
+    },
+    {
+      "epoch": 1.396551724137931,
+      "grad_norm": 3.0291541406768374e-05,
+      "learning_rate": 0.00015585350259658746,
+      "loss": 1.7102,
+      "step": 162
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 2.4553977709729224e-05,
+      "learning_rate": 0.0001546633521896038,
+      "loss": 1.7563,
+      "step": 164
+    },
+    {
+      "epoch": 1.4310344827586206,
+      "grad_norm": 3.996691884822212e-05,
+      "learning_rate": 0.00015346205516085306,
+      "loss": 1.7017,
+      "step": 166
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 2.5090428607654758e-05,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 1.721,
+      "step": 168
+    },
+    {
+      "epoch": 1.4655172413793103,
+      "grad_norm": 4.993643597117625e-05,
+      "learning_rate": 0.00015102700330609,
+      "loss": 1.7036,
+      "step": 170
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 2.340052742511034e-05,
+      "learning_rate": 0.0001497937450211956,
+      "loss": 1.7574,
+      "step": 172
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.563516293070279e-05,
+      "learning_rate": 0.00014855033309551843,
+      "loss": 1.756,
+      "step": 174
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 3.225682667107321e-05,
+      "learning_rate": 0.00014729702107813436,
+      "loss": 1.8053,
+      "step": 176
+    },
+    {
+      "epoch": 1.5344827586206895,
+      "grad_norm": 2.349480018892791e-05,
+      "learning_rate": 0.00014603406453688654,
+      "loss": 1.7376,
+      "step": 178
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 4.0241888200398535e-05,
+      "learning_rate": 0.00014476172100627127,
+      "loss": 1.7475,
+      "step": 180
+    },
+    {
+      "epoch": 1.5689655172413794,
+      "grad_norm": 4.396059739519842e-05,
+      "learning_rate": 0.0001434802499349232,
+      "loss": 1.735,
+      "step": 182
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 3.024659599759616e-05,
+      "learning_rate": 0.00014218991263271024,
+      "loss": 1.7426,
+      "step": 184
+    },
+    {
+      "epoch": 1.603448275862069,
+      "grad_norm": 3.1224055419443175e-05,
+      "learning_rate": 0.00014089097221744868,
+      "loss": 1.6746,
+      "step": 186
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 2.243503877252806e-05,
+      "learning_rate": 0.00013958369356124986,
+      "loss": 1.6508,
+      "step": 188
+    },
+    {
+      "epoch": 1.6379310344827587,
+      "grad_norm": 2.4827659217407927e-05,
+      "learning_rate": 0.000138268343236509,
+      "loss": 1.7289,
+      "step": 190
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 2.582685192464851e-05,
+      "learning_rate": 0.0001369451894615474,
+      "loss": 1.7791,
+      "step": 192
+    },
+    {
+      "epoch": 1.6724137931034484,
+      "grad_norm": 3.327808735775761e-05,
+      "learning_rate": 0.00013561450204591896,
+      "loss": 1.8354,
+      "step": 194
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 4.714803071692586e-05,
+      "learning_rate": 0.00013427655233539228,
+      "loss": 1.7645,
+      "step": 196
+    },
+    {
+      "epoch": 1.706896551724138,
+      "grad_norm": 2.8617656425922178e-05,
+      "learning_rate": 0.00013293161315661931,
+      "loss": 1.7147,
+      "step": 198
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 2.9135431759641506e-05,
+      "learning_rate": 0.0001315799587615025,
+      "loss": 1.636,
+      "step": 200
+    },
+    {
+      "epoch": 1.7413793103448276,
+      "grad_norm": 4.291239019948989e-05,
+      "learning_rate": 0.0001302218647712706,
+      "loss": 1.6921,
+      "step": 202
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 3.172121796524152e-05,
+      "learning_rate": 0.00012885760812027589,
+      "loss": 1.7275,
+      "step": 204
+    },
+    {
+      "epoch": 1.7758620689655173,
+      "grad_norm": 3.2376061426475644e-05,
+      "learning_rate": 0.00012748746699952338,
+      "loss": 1.7325,
+      "step": 206
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 3.794002259382978e-05,
+      "learning_rate": 0.00012611172079994375,
+      "loss": 1.7961,
+      "step": 208
+    },
+    {
+      "epoch": 1.8103448275862069,
+      "grad_norm": 4.9185015086550266e-05,
+      "learning_rate": 0.00012473065005542155,
+      "loss": 1.7465,
+      "step": 210
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 3.3105872716987506e-05,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 1.636,
+      "step": 212
+    },
+    {
+      "epoch": 1.8448275862068966,
+      "grad_norm": 3.986067167716101e-05,
+      "learning_rate": 0.00012195366243840745,
+      "loss": 1.7073,
+      "step": 214
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 4.6539596951333806e-05,
+      "learning_rate": 0.00012055831183251607,
+      "loss": 1.688,
+      "step": 216
+    },
+    {
+      "epoch": 1.8793103448275863,
+      "grad_norm": 3.79367484129034e-05,
+      "learning_rate": 0.00011915876909941355,
+      "loss": 1.6092,
+      "step": 218
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 3.928501610062085e-05,
+      "learning_rate": 0.00011775531962543036,
+      "loss": 1.7035,
+      "step": 220
+    },
+    {
+      "epoch": 1.9137931034482758,
+      "grad_norm": 4.312846067477949e-05,
+      "learning_rate": 0.000116348249593536,
+      "loss": 1.7136,
+      "step": 222
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 4.311458906158805e-05,
+      "learning_rate": 0.00011493784592498252,
+      "loss": 1.648,
+      "step": 224
+    },
+    {
+      "epoch": 1.9482758620689655,
+      "grad_norm": 4.600015745381825e-05,
+      "learning_rate": 0.00011352439622079689,
+      "loss": 1.7695,
+      "step": 226
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 4.357201396487653e-05,
+      "learning_rate": 0.00011210818870313549,
+      "loss": 1.7199,
+      "step": 228
+    },
+    {
+      "epoch": 1.9827586206896552,
+      "grad_norm": 4.6237106289481744e-05,
+      "learning_rate": 0.00011068951215651132,
+      "loss": 1.6523,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.080967720365152e-05,
+      "learning_rate": 0.00010926865586890689,
+      "loss": 1.7521,
+      "step": 232
+    },
+    {
+      "epoch": 2.0172413793103448,
+      "grad_norm": 5.718940883525647e-05,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 1.5938,
+      "step": 234
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 4.2860374378506094e-05,
+      "learning_rate": 0.00010642156338600551,
+      "loss": 1.698,
+      "step": 236
+    },
+    {
+      "epoch": 2.0517241379310347,
+      "grad_norm": 5.48689131392166e-05,
+      "learning_rate": 0.0001049959077526714,
+      "loss": 1.6555,
+      "step": 238
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 5.724292350350879e-05,
+      "learning_rate": 0.00010356923338389806,
+      "loss": 1.7046,
+      "step": 240
+    },
+    {
+      "epoch": 2.086206896551724,
+      "grad_norm": 5.0994356570299715e-05,
+      "learning_rate": 0.00010214183119853582,
+      "loss": 1.6696,
+      "step": 242
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 6.0200225561857224e-05,
+      "learning_rate": 0.00010071399226384694,
+      "loss": 1.7165,
+      "step": 244
+    },
+    {
+      "epoch": 2.1206896551724137,
+      "grad_norm": 5.015491842641495e-05,
+      "learning_rate": 9.928600773615307e-05,
+      "loss": 1.7068,
+      "step": 246
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 6.368745380314067e-05,
+      "learning_rate": 9.78581688014642e-05,
+      "loss": 1.74,
+      "step": 248
+    },
+    {
+      "epoch": 2.1551724137931036,
+      "grad_norm": 5.946237070020288e-05,
+      "learning_rate": 9.643076661610196e-05,
+      "loss": 1.6914,
+      "step": 250
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 5.542474173125811e-05,
+      "learning_rate": 9.500409224732863e-05,
+      "loss": 1.7075,
+      "step": 252
+    },
+    {
+      "epoch": 2.189655172413793,
+      "grad_norm": 6.597842002520338e-05,
+      "learning_rate": 9.357843661399447e-05,
+      "loss": 1.71,
+      "step": 254
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 5.879228046978824e-05,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 1.6139,
+      "step": 256
+    },
+    {
+      "epoch": 2.2241379310344827,
+      "grad_norm": 5.7269386161351576e-05,
+      "learning_rate": 9.073134413109312e-05,
+      "loss": 1.6543,
+      "step": 258
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 5.378547211876139e-05,
+      "learning_rate": 8.931048784348875e-05,
+      "loss": 1.6489,
+      "step": 260
+    },
+    {
+      "epoch": 2.2586206896551726,
+      "grad_norm": 5.8273999457014725e-05,
+      "learning_rate": 8.789181129686452e-05,
+      "loss": 1.6617,
+      "step": 262
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 5.4671403631800786e-05,
+      "learning_rate": 8.647560377920311e-05,
+      "loss": 1.663,
+      "step": 264
+    },
+    {
+      "epoch": 2.293103448275862,
+      "grad_norm": 5.9202680859016255e-05,
+      "learning_rate": 8.50621540750175e-05,
+      "loss": 1.5901,
+      "step": 266
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 5.2928600780433044e-05,
+      "learning_rate": 8.365175040646402e-05,
+      "loss": 1.638,
+      "step": 268
+    },
+    {
+      "epoch": 2.3275862068965516,
+      "grad_norm": 5.589192733168602e-05,
+      "learning_rate": 8.224468037456969e-05,
+      "loss": 1.6413,
+      "step": 270
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 5.543338556890376e-05,
+      "learning_rate": 8.084123090058646e-05,
+      "loss": 1.7151,
+      "step": 272
+    },
+    {
+      "epoch": 2.3620689655172415,
+      "grad_norm": 5.86421083426103e-05,
+      "learning_rate": 7.944168816748395e-05,
+      "loss": 1.6831,
+      "step": 274
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 5.7719400501810014e-05,
+      "learning_rate": 7.804633756159259e-05,
+      "loss": 1.6163,
+      "step": 276
+    },
+    {
+      "epoch": 2.396551724137931,
+      "grad_norm": 5.793603486381471e-05,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 1.6747,
+      "step": 278
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 6.149085675133392e-05,
+      "learning_rate": 7.526934994457844e-05,
+      "loss": 1.7326,
+      "step": 280
+    },
+    {
+      "epoch": 2.4310344827586206,
+      "grad_norm": 6.359058170346543e-05,
+      "learning_rate": 7.388827920005627e-05,
+      "loss": 1.6795,
+      "step": 282
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 6.622547516599298e-05,
+      "learning_rate": 7.251253300047663e-05,
+      "loss": 1.6408,
+      "step": 284
+    },
+    {
+      "epoch": 2.4655172413793105,
+      "grad_norm": 6.301296525634825e-05,
+      "learning_rate": 7.114239187972416e-05,
+      "loss": 1.6468,
+      "step": 286
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 6.218779890332371e-05,
+      "learning_rate": 6.977813522872943e-05,
+      "loss": 1.71,
+      "step": 288
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 6.647199916187674e-05,
+      "learning_rate": 6.842004123849752e-05,
+      "loss": 1.7468,
+      "step": 290
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 6.713119364576414e-05,
+      "learning_rate": 6.70683868433807e-05,
+      "loss": 1.6354,
+      "step": 292
+    },
+    {
+      "epoch": 2.5344827586206895,
+      "grad_norm": 6.99372249073349e-05,
+      "learning_rate": 6.572344766460776e-05,
+      "loss": 1.7253,
+      "step": 294
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 6.832159124314785e-05,
+      "learning_rate": 6.438549795408106e-05,
+      "loss": 1.7338,
+      "step": 296
+    },
+    {
+      "epoch": 2.5689655172413794,
+      "grad_norm": 6.618772022193298e-05,
+      "learning_rate": 6.305481053845261e-05,
+      "loss": 1.6328,
+      "step": 298
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 7.179833482950926e-05,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.652,
+      "step": 300
+    },
+    {
+      "epoch": 2.603448275862069,
+      "grad_norm": 6.626212416449562e-05,
+      "learning_rate": 6.041630643875018e-05,
+      "loss": 1.7552,
+      "step": 302
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 6.928609946044162e-05,
+      "learning_rate": 5.910902778255134e-05,
+      "loss": 1.6969,
+      "step": 304
+    },
+    {
+      "epoch": 2.637931034482759,
+      "grad_norm": 7.145026029320434e-05,
+      "learning_rate": 5.7810087367289744e-05,
+      "loss": 1.7151,
+      "step": 306
+    },
+    {
+      "epoch": 2.655172413793103,
+      "grad_norm": 6.987711822148412e-05,
+      "learning_rate": 5.651975006507681e-05,
+      "loss": 1.6533,
+      "step": 308
+    },
+    {
+      "epoch": 2.6724137931034484,
+      "grad_norm": 6.940370803931728e-05,
+      "learning_rate": 5.5238278993728756e-05,
+      "loss": 1.6922,
+      "step": 310
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.0001817405573092401,
+      "learning_rate": 5.396593546311346e-05,
+      "loss": 1.6973,
+      "step": 312
+    },
+    {
+      "epoch": 2.706896551724138,
+      "grad_norm": 7.641298725502566e-05,
+      "learning_rate": 5.270297892186563e-05,
+      "loss": 1.7294,
+      "step": 314
+    },
+    {
+      "epoch": 2.7241379310344827,
+      "grad_norm": 6.699555524392053e-05,
+      "learning_rate": 5.1449666904481585e-05,
+      "loss": 1.6713,
+      "step": 316
+    },
+    {
+      "epoch": 2.7413793103448274,
+      "grad_norm": 6.963134364923462e-05,
+      "learning_rate": 5.0206254978804435e-05,
+      "loss": 1.7326,
+      "step": 318
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 7.145871495595202e-05,
+      "learning_rate": 4.8972996693910054e-05,
+      "loss": 1.7386,
+      "step": 320
+    },
+    {
+      "epoch": 2.7758620689655173,
+      "grad_norm": 6.800260598538443e-05,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 1.6939,
+      "step": 322
+    },
+    {
+      "epoch": 2.793103448275862,
+      "grad_norm": 6.864208990009502e-05,
+      "learning_rate": 4.653794483914696e-05,
+      "loss": 1.7581,
+      "step": 324
+    },
+    {
+      "epoch": 2.810344827586207,
+      "grad_norm": 7.070614083204418e-05,
+      "learning_rate": 4.5336647810396215e-05,
+      "loss": 1.7155,
+      "step": 326
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 7.455341255990788e-05,
+      "learning_rate": 4.414649740341258e-05,
+      "loss": 1.7955,
+      "step": 328
+    },
+    {
+      "epoch": 2.844827586206897,
+      "grad_norm": 7.38763774279505e-05,
+      "learning_rate": 4.296773630650358e-05,
+      "loss": 1.7269,
+      "step": 330
+    },
+    {
+      "epoch": 2.862068965517241,
+      "grad_norm": 7.165527495089918e-05,
+      "learning_rate": 4.180060488553743e-05,
+      "loss": 1.7887,
+      "step": 332
+    },
+    {
+      "epoch": 2.8793103448275863,
+      "grad_norm": 7.368691876763478e-05,
+      "learning_rate": 4.06453411349286e-05,
+      "loss": 1.7997,
+      "step": 334
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 7.610574539285153e-05,
+      "learning_rate": 3.9502180629107756e-05,
+      "loss": 1.7738,
+      "step": 336
+    },
+    {
+      "epoch": 2.913793103448276,
+      "grad_norm": 7.454157457686961e-05,
+      "learning_rate": 3.8371356474484746e-05,
+      "loss": 1.7776,
+      "step": 338
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 7.552184979431331e-05,
+      "learning_rate": 3.725309926191479e-05,
+      "loss": 1.7869,
+      "step": 340
+    },
+    {
+      "epoch": 2.9482758620689653,
+      "grad_norm": 7.433702558046207e-05,
+      "learning_rate": 3.6147637019678195e-05,
+      "loss": 1.8083,
+      "step": 342
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 7.243530126288533e-05,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 1.7669,
+      "step": 344
+    },
+    {
+      "epoch": 2.9827586206896552,
+      "grad_norm": 7.482223736587912e-05,
+      "learning_rate": 3.397599646799256e-05,
+      "loss": 1.7417,
+      "step": 346
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.792668813839555e-05,
+      "learning_rate": 3.291026098641397e-05,
+      "loss": 1.8761,
+      "step": 348
+    },
+    {
+      "epoch": 3.0172413793103448,
+      "grad_norm": 7.802840991644189e-05,
+      "learning_rate": 3.185820604061088e-05,
+      "loss": 1.7633,
+      "step": 350
+    },
+    {
+      "epoch": 3.0344827586206895,
+      "grad_norm": 6.89391017658636e-05,
+      "learning_rate": 3.0820046159295644e-05,
+      "loss": 1.687,
+      "step": 352
+    },
+    {
+      "epoch": 3.0517241379310347,
+      "grad_norm": 7.239273691084236e-05,
+      "learning_rate": 2.9795993037782655e-05,
+      "loss": 1.7539,
+      "step": 354
+    },
+    {
+      "epoch": 3.0689655172413794,
+      "grad_norm": 7.185838330769911e-05,
+      "learning_rate": 2.8786255494820835e-05,
+      "loss": 1.7366,
+      "step": 356
+    },
+    {
+      "epoch": 3.086206896551724,
+      "grad_norm": 7.206243026303127e-05,
+      "learning_rate": 2.7791039430012476e-05,
+      "loss": 1.7703,
+      "step": 358
+    },
+    {
+      "epoch": 3.103448275862069,
+      "grad_norm": 7.18203154974617e-05,
+      "learning_rate": 2.681054778182748e-05,
+      "loss": 1.7132,
+      "step": 360
+    },
+    {
+      "epoch": 3.1206896551724137,
+      "grad_norm": 6.849451165180653e-05,
+      "learning_rate": 2.5844980486221228e-05,
+      "loss": 1.7914,
+      "step": 362
+    },
+    {
+      "epoch": 3.1379310344827585,
+      "grad_norm": 7.244012522278354e-05,
+      "learning_rate": 2.4894534435865015e-05,
+      "loss": 1.7365,
+      "step": 364
+    },
+    {
+      "epoch": 3.1551724137931036,
+      "grad_norm": 6.781809497624636e-05,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 1.7446,
+      "step": 366
+    },
+    {
+      "epoch": 3.1724137931034484,
+      "grad_norm": 6.832330109318718e-05,
+      "learning_rate": 2.3039778184901084e-05,
+      "loss": 1.7554,
+      "step": 368
+    },
+    {
+      "epoch": 3.189655172413793,
+      "grad_norm": 6.69066866976209e-05,
+      "learning_rate": 2.2135846195024513e-05,
+      "loss": 1.7409,
+      "step": 370
+    },
+    {
+      "epoch": 3.206896551724138,
+      "grad_norm": 6.750784814357758e-05,
+      "learning_rate": 2.1247791794737826e-05,
+      "loss": 1.7058,
+      "step": 372
+    },
+    {
+      "epoch": 3.2241379310344827,
+      "grad_norm": 7.111330342013389e-05,
+      "learning_rate": 2.0375796070749363e-05,
+      "loss": 1.7842,
+      "step": 374
+    },
+    {
+      "epoch": 3.2413793103448274,
+      "grad_norm": 6.951171235414222e-05,
+      "learning_rate": 1.9520036835178668e-05,
+      "loss": 1.7586,
+      "step": 376
+    },
+    {
+      "epoch": 3.2586206896551726,
+      "grad_norm": 6.802480493206531e-05,
+      "learning_rate": 1.8680688589298368e-05,
+      "loss": 1.6923,
+      "step": 378
+    },
+    {
+      "epoch": 3.2758620689655173,
+      "grad_norm": 6.907380156917498e-05,
+      "learning_rate": 1.7857922487950874e-05,
+      "loss": 1.7892,
+      "step": 380
+    },
+    {
+      "epoch": 3.293103448275862,
+      "grad_norm": 6.635097815888003e-05,
+      "learning_rate": 1.7051906304647368e-05,
+      "loss": 1.8035,
+      "step": 382
+    },
+    {
+      "epoch": 3.310344827586207,
+      "grad_norm": 6.926745845703408e-05,
+      "learning_rate": 1.6262804397356746e-05,
+      "loss": 1.8157,
+      "step": 384
+    },
+    {
+      "epoch": 3.3275862068965516,
+      "grad_norm": 7.06208884366788e-05,
+      "learning_rate": 1.5490777674990376e-05,
+      "loss": 1.7965,
+      "step": 386
+    },
+    {
+      "epoch": 3.344827586206897,
+      "grad_norm": 6.897733692312613e-05,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 1.7867,
+      "step": 388
+    },
+    {
+      "epoch": 3.3620689655172415,
+      "grad_norm": 6.628095434280112e-05,
+      "learning_rate": 1.3998575979229944e-05,
+      "loss": 1.7529,
+      "step": 390
+    },
+    {
+      "epoch": 3.3793103448275863,
+      "grad_norm": 6.664723332505673e-05,
+      "learning_rate": 1.3278705286624327e-05,
+      "loss": 1.7666,
+      "step": 392
+    },
+    {
+      "epoch": 3.396551724137931,
+      "grad_norm": 6.862921145511791e-05,
+      "learning_rate": 1.2576518278472759e-05,
+      "loss": 1.7662,
+      "step": 394
+    },
+    {
+      "epoch": 3.413793103448276,
+      "grad_norm": 6.93115871399641e-05,
+      "learning_rate": 1.1892158140523546e-05,
+      "loss": 1.7767,
+      "step": 396
+    },
+    {
+      "epoch": 3.4310344827586206,
+      "grad_norm": 6.726732681272551e-05,
+      "learning_rate": 1.122576442337696e-05,
+      "loss": 1.7228,
+      "step": 398
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 6.953762203920633e-05,
+      "learning_rate": 1.057747301402887e-05,
+      "loss": 1.7798,
+      "step": 400
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 464,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.783464898608497e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e0384a95773c4f9f1910994edd74cc0c1467bafb112774589033914dd397a4
+size 5713

checkpoint-464/README.md

@@ -0,0 +1,208 @@
+---
+base_model: ./Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./Qwen3-4B-Instruct-2507
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.16.0

checkpoint-464/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen3-4B-Instruct-2507",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-464/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d818a7efd439d173e788b38d693b0728962bdc2852e112e0305524ec05c82c70
+size 1817430408

checkpoint-464/added_tokens.json

@@ -0,0 +1,31 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|analysis|>": 151670,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|forecast|>": 151671,
+  "<|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,
+  "<|response|>": 151669,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-464/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-464/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0a4dd8bd7c78e8a98e604bde47b849bd42b8a9a78dd210a9c419f464e3bde9
+size 528908363

checkpoint-464/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
+size 14645

checkpoint-464/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ffadc689508b4d6b54e1c7bfb0a509653a22a05c81606bd389cb29cba93b09
+size 1383

checkpoint-464/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70eb641fe76ee906eff77b6672eb4330d6c5410e8b5787b204b398ef72efe995
+size 1465

checkpoint-464/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|analysis|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|forecast|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

checkpoint-464/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77247e5fb2e966d04e513068b17cca472e105e7c56953e9b1d27d70b93d77e6f
+size 11423221

checkpoint-464/tokenizer_config.json

@@ -0,0 +1,254 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|analysis|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|forecast|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|response|>",
+    "<|analysis|>",
+    "<|forecast|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-464/trainer_state.json

@@ -0,0 +1,1658 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 464,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": 0.003562385216355324,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 6.5818,
+      "step": 2
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.00022410321980714798,
+      "learning_rate": 2.5e-05,
+      "loss": 3.1274,
+      "step": 4
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 0.001015713787637651,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 6.2659,
+      "step": 6
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 5.367869744077325e-05,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 2.6228,
+      "step": 8
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 4.5336004404816777e-05,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.5434,
+      "step": 10
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 4.627772432286292e-05,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 2.3415,
+      "step": 12
+    },
+    {
+      "epoch": 0.1206896551724138,
+      "grad_norm": 3.9416841900674626e-05,
+      "learning_rate": 0.00010833333333333333,
+      "loss": 2.3444,
+      "step": 14
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 3.731855395017192e-05,
+      "learning_rate": 0.000125,
+      "loss": 2.2561,
+      "step": 16
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 3.3787582651712e-05,
+      "learning_rate": 0.00014166666666666668,
+      "loss": 2.2835,
+      "step": 18
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 3.5183733416488394e-05,
+      "learning_rate": 0.00015833333333333332,
+      "loss": 2.1617,
+      "step": 20
+    },
+    {
+      "epoch": 0.1896551724137931,
+      "grad_norm": 2.609785042295698e-05,
+      "learning_rate": 0.000175,
+      "loss": 2.1658,
+      "step": 22
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 2.222553302999586e-05,
+      "learning_rate": 0.00019166666666666667,
+      "loss": 2.0384,
+      "step": 24
+    },
+    {
+      "epoch": 0.22413793103448276,
+      "grad_norm": 2.2757671104045585e-05,
+      "learning_rate": 0.00019999745104274993,
+      "loss": 2.1457,
+      "step": 26
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 2.0901892639813013e-05,
+      "learning_rate": 0.0001999770601644046,
+      "loss": 2.0479,
+      "step": 28
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 2.0703126210719347e-05,
+      "learning_rate": 0.0001999362825656992,
+      "loss": 2.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 2.1005034795962274e-05,
+      "learning_rate": 0.0001998751265617561,
+      "loss": 2.055,
+      "step": 32
+    },
+    {
+      "epoch": 0.29310344827586204,
+      "grad_norm": 1.9665612853714265e-05,
+      "learning_rate": 0.00019979360462313962,
+      "loss": 1.9215,
+      "step": 34
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 2.0705581846414134e-05,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 1.8961,
+      "step": 36
+    },
+    {
+      "epoch": 0.3275862068965517,
+      "grad_norm": 2.2074158550822176e-05,
+      "learning_rate": 0.00019956953358524774,
+      "loss": 1.9082,
+      "step": 38
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 2.1002635548938997e-05,
+      "learning_rate": 0.00019942703017718975,
+      "loss": 1.934,
+      "step": 40
+    },
+    {
+      "epoch": 0.3620689655172414,
+      "grad_norm": 1.9619050362962298e-05,
+      "learning_rate": 0.00019926425220757605,
+      "loss": 1.8817,
+      "step": 42
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 2.059372673102189e-05,
+      "learning_rate": 0.00019908123286911046,
+      "loss": 2.0008,
+      "step": 44
+    },
+    {
+      "epoch": 0.39655172413793105,
+      "grad_norm": 1.98649267986184e-05,
+      "learning_rate": 0.00019887800948199496,
+      "loss": 1.8766,
+      "step": 46
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 2.3096907170838676e-05,
+      "learning_rate": 0.00019865462348631944,
+      "loss": 1.7926,
+      "step": 48
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 2.106586362060625e-05,
+      "learning_rate": 0.0001984111204336116,
+      "loss": 1.9005,
+      "step": 50
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 2.156079062842764e-05,
+      "learning_rate": 0.0001981475499775484,
+      "loss": 1.9158,
+      "step": 52
+    },
+    {
+      "epoch": 0.46551724137931033,
+      "grad_norm": 2.2075933884480037e-05,
+      "learning_rate": 0.00019786396586383075,
+      "loss": 1.903,
+      "step": 54
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 2.0557081370498054e-05,
+      "learning_rate": 0.00019756042591922434,
+      "loss": 1.8811,
+      "step": 56
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.944549148902297e-05,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 1.8026,
+      "step": 58
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 2.6996058295480907e-05,
+      "learning_rate": 0.00019689373017815073,
+      "loss": 1.8647,
+      "step": 60
+    },
+    {
+      "epoch": 0.5344827586206896,
+      "grad_norm": 2.1660236598108895e-05,
+      "learning_rate": 0.00019653071033026633,
+      "loss": 1.8209,
+      "step": 62
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 2.476519875926897e-05,
+      "learning_rate": 0.00019614800652093686,
+      "loss": 1.8078,
+      "step": 64
+    },
+    {
+      "epoch": 0.5689655172413793,
+      "grad_norm": 2.4084582037176006e-05,
+      "learning_rate": 0.00019574569678881964,
+      "loss": 1.8253,
+      "step": 66
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 2.4040386051638052e-05,
+      "learning_rate": 0.00019532386317049383,
+      "loss": 1.8044,
+      "step": 68
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 2.3245340344146825e-05,
+      "learning_rate": 0.00019488259168373197,
+      "loss": 1.8383,
+      "step": 70
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 2.399735603830777e-05,
+      "learning_rate": 0.0001944219723099596,
+      "loss": 1.852,
+      "step": 72
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 2.5779550924198702e-05,
+      "learning_rate": 0.00019394209897590704,
+      "loss": 2.2878,
+      "step": 74
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 2.9553415515692905e-05,
+      "learning_rate": 0.00019344306953445633,
+      "loss": 1.9217,
+      "step": 76
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 2.9237366106826812e-05,
+      "learning_rate": 0.00019292498574468748,
+      "loss": 1.8601,
+      "step": 78
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 2.6727117074187845e-05,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 1.8181,
+      "step": 80
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 2.680359648365993e-05,
+      "learning_rate": 0.0001918320815622137,
+      "loss": 1.8295,
+      "step": 82
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 2.3158025214797817e-05,
+      "learning_rate": 0.0001912574840279516,
+      "loss": 1.8614,
+      "step": 84
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 3.017827111762017e-05,
+      "learning_rate": 0.00019066427781681315,
+      "loss": 1.757,
+      "step": 86
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 2.1740601368946955e-05,
+      "learning_rate": 0.00019005258389183851,
+      "loss": 1.8096,
+      "step": 88
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 2.1615645891870372e-05,
+      "learning_rate": 0.00018942252698597113,
+      "loss": 1.7802,
+      "step": 90
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 2.0820896679651923e-05,
+      "learning_rate": 0.00018877423557662305,
+      "loss": 1.7246,
+      "step": 92
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 2.3314805730478838e-05,
+      "learning_rate": 0.00018810784185947646,
+      "loss": 1.8366,
+      "step": 94
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 2.5301331334048882e-05,
+      "learning_rate": 0.00018742348172152726,
+      "loss": 1.8826,
+      "step": 96
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 2.6756286388263106e-05,
+      "learning_rate": 0.00018672129471337568,
+      "loss": 1.7417,
+      "step": 98
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 2.8393502361723222e-05,
+      "learning_rate": 0.00018600142402077006,
+      "loss": 1.8275,
+      "step": 100
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 2.184685035899747e-05,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 1.7819,
+      "step": 102
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 2.5997507691499777e-05,
+      "learning_rate": 0.00018450922232500966,
+      "loss": 1.8088,
+      "step": 104
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 2.3897668143035844e-05,
+      "learning_rate": 0.00018373719560264327,
+      "loss": 1.8686,
+      "step": 106
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 2.715570735745132e-05,
+      "learning_rate": 0.00018294809369535263,
+      "loss": 1.8138,
+      "step": 108
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 3.2870055292733014e-05,
+      "learning_rate": 0.00018214207751204918,
+      "loss": 1.8485,
+      "step": 110
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 2.1189727704040706e-05,
+      "learning_rate": 0.00018131931141070163,
+      "loss": 1.825,
+      "step": 112
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 4.0714276110520586e-05,
+      "learning_rate": 0.00018047996316482135,
+      "loss": 1.7557,
+      "step": 114
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.3534433643799275e-05,
+      "learning_rate": 0.00017962420392925066,
+      "loss": 1.6649,
+      "step": 116
+    },
+    {
+      "epoch": 1.0172413793103448,
+      "grad_norm": 3.003507481480483e-05,
+      "learning_rate": 0.00017875220820526218,
+      "loss": 1.7448,
+      "step": 118
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 2.9781367629766464e-05,
+      "learning_rate": 0.00017786415380497553,
+      "loss": 1.7457,
+      "step": 120
+    },
+    {
+      "epoch": 1.0517241379310345,
+      "grad_norm": 2.081507227558177e-05,
+      "learning_rate": 0.00017696022181509894,
+      "loss": 1.7675,
+      "step": 122
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 2.6256357159581967e-05,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 1.7417,
+      "step": 124
+    },
+    {
+      "epoch": 1.0862068965517242,
+      "grad_norm": 3.1936106097418815e-05,
+      "learning_rate": 0.00017510546556413498,
+      "loss": 1.7653,
+      "step": 126
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 2.2676726075587794e-05,
+      "learning_rate": 0.0001741550195137788,
+      "loss": 1.7457,
+      "step": 128
+    },
+    {
+      "epoch": 1.1206896551724137,
+      "grad_norm": 3.1191233574645594e-05,
+      "learning_rate": 0.00017318945221817255,
+      "loss": 1.7546,
+      "step": 130
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 2.654504351085052e-05,
+      "learning_rate": 0.0001722089605699875,
+      "loss": 1.695,
+      "step": 132
+    },
+    {
+      "epoch": 1.1551724137931034,
+      "grad_norm": 2.8716958695440553e-05,
+      "learning_rate": 0.00017121374450517916,
+      "loss": 1.7442,
+      "step": 134
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 3.173397635691799e-05,
+      "learning_rate": 0.00017020400696221737,
+      "loss": 1.8053,
+      "step": 136
+    },
+    {
+      "epoch": 1.1896551724137931,
+      "grad_norm": 2.7111556846648455e-05,
+      "learning_rate": 0.0001691799538407044,
+      "loss": 1.7553,
+      "step": 138
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 2.1949501388007775e-05,
+      "learning_rate": 0.00016814179395938913,
+      "loss": 1.6792,
+      "step": 140
+    },
+    {
+      "epoch": 1.2241379310344827,
+      "grad_norm": 2.9802749850205146e-05,
+      "learning_rate": 0.00016708973901358602,
+      "loss": 1.755,
+      "step": 142
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 2.4393058993155137e-05,
+      "learning_rate": 0.0001660240035320075,
+      "loss": 1.6939,
+      "step": 144
+    },
+    {
+      "epoch": 1.2586206896551724,
+      "grad_norm": 2.3840178982936777e-05,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 1.7703,
+      "step": 146
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 2.3855336621636525e-05,
+      "learning_rate": 0.00016385236298032183,
+      "loss": 1.7331,
+      "step": 148
+    },
+    {
+      "epoch": 1.293103448275862,
+      "grad_norm": 3.826155807473697e-05,
+      "learning_rate": 0.0001627469007380852,
+      "loss": 1.7543,
+      "step": 150
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 2.4928000129875727e-05,
+      "learning_rate": 0.0001616286435255153,
+      "loss": 1.7365,
+      "step": 152
+    },
+    {
+      "epoch": 1.3275862068965516,
+      "grad_norm": 3.5061420931015164e-05,
+      "learning_rate": 0.00016049781937089227,
+      "loss": 1.7058,
+      "step": 154
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 3.1686500733485445e-05,
+      "learning_rate": 0.00015935465886507142,
+      "loss": 1.6998,
+      "step": 156
+    },
+    {
+      "epoch": 1.3620689655172413,
+      "grad_norm": 2.7497104383655824e-05,
+      "learning_rate": 0.0001581993951144626,
+      "loss": 1.8166,
+      "step": 158
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 3.0560615414287895e-05,
+      "learning_rate": 0.0001570322636934964,
+      "loss": 1.6751,
+      "step": 160
+    },
+    {
+      "epoch": 1.396551724137931,
+      "grad_norm": 3.0291541406768374e-05,
+      "learning_rate": 0.00015585350259658746,
+      "loss": 1.7102,
+      "step": 162
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 2.4553977709729224e-05,
+      "learning_rate": 0.0001546633521896038,
+      "loss": 1.7563,
+      "step": 164
+    },
+    {
+      "epoch": 1.4310344827586206,
+      "grad_norm": 3.996691884822212e-05,
+      "learning_rate": 0.00015346205516085306,
+      "loss": 1.7017,
+      "step": 166
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 2.5090428607654758e-05,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 1.721,
+      "step": 168
+    },
+    {
+      "epoch": 1.4655172413793103,
+      "grad_norm": 4.993643597117625e-05,
+      "learning_rate": 0.00015102700330609,
+      "loss": 1.7036,
+      "step": 170
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 2.340052742511034e-05,
+      "learning_rate": 0.0001497937450211956,
+      "loss": 1.7574,
+      "step": 172
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.563516293070279e-05,
+      "learning_rate": 0.00014855033309551843,
+      "loss": 1.756,
+      "step": 174
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 3.225682667107321e-05,
+      "learning_rate": 0.00014729702107813436,
+      "loss": 1.8053,
+      "step": 176
+    },
+    {
+      "epoch": 1.5344827586206895,
+      "grad_norm": 2.349480018892791e-05,
+      "learning_rate": 0.00014603406453688654,
+      "loss": 1.7376,
+      "step": 178
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 4.0241888200398535e-05,
+      "learning_rate": 0.00014476172100627127,
+      "loss": 1.7475,
+      "step": 180
+    },
+    {
+      "epoch": 1.5689655172413794,
+      "grad_norm": 4.396059739519842e-05,
+      "learning_rate": 0.0001434802499349232,
+      "loss": 1.735,
+      "step": 182
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 3.024659599759616e-05,
+      "learning_rate": 0.00014218991263271024,
+      "loss": 1.7426,
+      "step": 184
+    },
+    {
+      "epoch": 1.603448275862069,
+      "grad_norm": 3.1224055419443175e-05,
+      "learning_rate": 0.00014089097221744868,
+      "loss": 1.6746,
+      "step": 186
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 2.243503877252806e-05,
+      "learning_rate": 0.00013958369356124986,
+      "loss": 1.6508,
+      "step": 188
+    },
+    {
+      "epoch": 1.6379310344827587,
+      "grad_norm": 2.4827659217407927e-05,
+      "learning_rate": 0.000138268343236509,
+      "loss": 1.7289,
+      "step": 190
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 2.582685192464851e-05,
+      "learning_rate": 0.0001369451894615474,
+      "loss": 1.7791,
+      "step": 192
+    },
+    {
+      "epoch": 1.6724137931034484,
+      "grad_norm": 3.327808735775761e-05,
+      "learning_rate": 0.00013561450204591896,
+      "loss": 1.8354,
+      "step": 194
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 4.714803071692586e-05,
+      "learning_rate": 0.00013427655233539228,
+      "loss": 1.7645,
+      "step": 196
+    },
+    {
+      "epoch": 1.706896551724138,
+      "grad_norm": 2.8617656425922178e-05,
+      "learning_rate": 0.00013293161315661931,
+      "loss": 1.7147,
+      "step": 198
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 2.9135431759641506e-05,
+      "learning_rate": 0.0001315799587615025,
+      "loss": 1.636,
+      "step": 200
+    },
+    {
+      "epoch": 1.7413793103448276,
+      "grad_norm": 4.291239019948989e-05,
+      "learning_rate": 0.0001302218647712706,
+      "loss": 1.6921,
+      "step": 202
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 3.172121796524152e-05,
+      "learning_rate": 0.00012885760812027589,
+      "loss": 1.7275,
+      "step": 204
+    },
+    {
+      "epoch": 1.7758620689655173,
+      "grad_norm": 3.2376061426475644e-05,
+      "learning_rate": 0.00012748746699952338,
+      "loss": 1.7325,
+      "step": 206
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 3.794002259382978e-05,
+      "learning_rate": 0.00012611172079994375,
+      "loss": 1.7961,
+      "step": 208
+    },
+    {
+      "epoch": 1.8103448275862069,
+      "grad_norm": 4.9185015086550266e-05,
+      "learning_rate": 0.00012473065005542155,
+      "loss": 1.7465,
+      "step": 210
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 3.3105872716987506e-05,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 1.636,
+      "step": 212
+    },
+    {
+      "epoch": 1.8448275862068966,
+      "grad_norm": 3.986067167716101e-05,
+      "learning_rate": 0.00012195366243840745,
+      "loss": 1.7073,
+      "step": 214
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 4.6539596951333806e-05,
+      "learning_rate": 0.00012055831183251607,
+      "loss": 1.688,
+      "step": 216
+    },
+    {
+      "epoch": 1.8793103448275863,
+      "grad_norm": 3.79367484129034e-05,
+      "learning_rate": 0.00011915876909941355,
+      "loss": 1.6092,
+      "step": 218
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 3.928501610062085e-05,
+      "learning_rate": 0.00011775531962543036,
+      "loss": 1.7035,
+      "step": 220
+    },
+    {
+      "epoch": 1.9137931034482758,
+      "grad_norm": 4.312846067477949e-05,
+      "learning_rate": 0.000116348249593536,
+      "loss": 1.7136,
+      "step": 222
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 4.311458906158805e-05,
+      "learning_rate": 0.00011493784592498252,
+      "loss": 1.648,
+      "step": 224
+    },
+    {
+      "epoch": 1.9482758620689655,
+      "grad_norm": 4.600015745381825e-05,
+      "learning_rate": 0.00011352439622079689,
+      "loss": 1.7695,
+      "step": 226
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 4.357201396487653e-05,
+      "learning_rate": 0.00011210818870313549,
+      "loss": 1.7199,
+      "step": 228
+    },
+    {
+      "epoch": 1.9827586206896552,
+      "grad_norm": 4.6237106289481744e-05,
+      "learning_rate": 0.00011068951215651132,
+      "loss": 1.6523,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.080967720365152e-05,
+      "learning_rate": 0.00010926865586890689,
+      "loss": 1.7521,
+      "step": 232
+    },
+    {
+      "epoch": 2.0172413793103448,
+      "grad_norm": 5.718940883525647e-05,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 1.5938,
+      "step": 234
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 4.2860374378506094e-05,
+      "learning_rate": 0.00010642156338600551,
+      "loss": 1.698,
+      "step": 236
+    },
+    {
+      "epoch": 2.0517241379310347,
+      "grad_norm": 5.48689131392166e-05,
+      "learning_rate": 0.0001049959077526714,
+      "loss": 1.6555,
+      "step": 238
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 5.724292350350879e-05,
+      "learning_rate": 0.00010356923338389806,
+      "loss": 1.7046,
+      "step": 240
+    },
+    {
+      "epoch": 2.086206896551724,
+      "grad_norm": 5.0994356570299715e-05,
+      "learning_rate": 0.00010214183119853582,
+      "loss": 1.6696,
+      "step": 242
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 6.0200225561857224e-05,
+      "learning_rate": 0.00010071399226384694,
+      "loss": 1.7165,
+      "step": 244
+    },
+    {
+      "epoch": 2.1206896551724137,
+      "grad_norm": 5.015491842641495e-05,
+      "learning_rate": 9.928600773615307e-05,
+      "loss": 1.7068,
+      "step": 246
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 6.368745380314067e-05,
+      "learning_rate": 9.78581688014642e-05,
+      "loss": 1.74,
+      "step": 248
+    },
+    {
+      "epoch": 2.1551724137931036,
+      "grad_norm": 5.946237070020288e-05,
+      "learning_rate": 9.643076661610196e-05,
+      "loss": 1.6914,
+      "step": 250
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 5.542474173125811e-05,
+      "learning_rate": 9.500409224732863e-05,
+      "loss": 1.7075,
+      "step": 252
+    },
+    {
+      "epoch": 2.189655172413793,
+      "grad_norm": 6.597842002520338e-05,
+      "learning_rate": 9.357843661399447e-05,
+      "loss": 1.71,
+      "step": 254
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 5.879228046978824e-05,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 1.6139,
+      "step": 256
+    },
+    {
+      "epoch": 2.2241379310344827,
+      "grad_norm": 5.7269386161351576e-05,
+      "learning_rate": 9.073134413109312e-05,
+      "loss": 1.6543,
+      "step": 258
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 5.378547211876139e-05,
+      "learning_rate": 8.931048784348875e-05,
+      "loss": 1.6489,
+      "step": 260
+    },
+    {
+      "epoch": 2.2586206896551726,
+      "grad_norm": 5.8273999457014725e-05,
+      "learning_rate": 8.789181129686452e-05,
+      "loss": 1.6617,
+      "step": 262
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 5.4671403631800786e-05,
+      "learning_rate": 8.647560377920311e-05,
+      "loss": 1.663,
+      "step": 264
+    },
+    {
+      "epoch": 2.293103448275862,
+      "grad_norm": 5.9202680859016255e-05,
+      "learning_rate": 8.50621540750175e-05,
+      "loss": 1.5901,
+      "step": 266
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 5.2928600780433044e-05,
+      "learning_rate": 8.365175040646402e-05,
+      "loss": 1.638,
+      "step": 268
+    },
+    {
+      "epoch": 2.3275862068965516,
+      "grad_norm": 5.589192733168602e-05,
+      "learning_rate": 8.224468037456969e-05,
+      "loss": 1.6413,
+      "step": 270
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 5.543338556890376e-05,
+      "learning_rate": 8.084123090058646e-05,
+      "loss": 1.7151,
+      "step": 272
+    },
+    {
+      "epoch": 2.3620689655172415,
+      "grad_norm": 5.86421083426103e-05,
+      "learning_rate": 7.944168816748395e-05,
+      "loss": 1.6831,
+      "step": 274
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 5.7719400501810014e-05,
+      "learning_rate": 7.804633756159259e-05,
+      "loss": 1.6163,
+      "step": 276
+    },
+    {
+      "epoch": 2.396551724137931,
+      "grad_norm": 5.793603486381471e-05,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 1.6747,
+      "step": 278
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 6.149085675133392e-05,
+      "learning_rate": 7.526934994457844e-05,
+      "loss": 1.7326,
+      "step": 280
+    },
+    {
+      "epoch": 2.4310344827586206,
+      "grad_norm": 6.359058170346543e-05,
+      "learning_rate": 7.388827920005627e-05,
+      "loss": 1.6795,
+      "step": 282
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 6.622547516599298e-05,
+      "learning_rate": 7.251253300047663e-05,
+      "loss": 1.6408,
+      "step": 284
+    },
+    {
+      "epoch": 2.4655172413793105,
+      "grad_norm": 6.301296525634825e-05,
+      "learning_rate": 7.114239187972416e-05,
+      "loss": 1.6468,
+      "step": 286
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 6.218779890332371e-05,
+      "learning_rate": 6.977813522872943e-05,
+      "loss": 1.71,
+      "step": 288
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 6.647199916187674e-05,
+      "learning_rate": 6.842004123849752e-05,
+      "loss": 1.7468,
+      "step": 290
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 6.713119364576414e-05,
+      "learning_rate": 6.70683868433807e-05,
+      "loss": 1.6354,
+      "step": 292
+    },
+    {
+      "epoch": 2.5344827586206895,
+      "grad_norm": 6.99372249073349e-05,
+      "learning_rate": 6.572344766460776e-05,
+      "loss": 1.7253,
+      "step": 294
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 6.832159124314785e-05,
+      "learning_rate": 6.438549795408106e-05,
+      "loss": 1.7338,
+      "step": 296
+    },
+    {
+      "epoch": 2.5689655172413794,
+      "grad_norm": 6.618772022193298e-05,
+      "learning_rate": 6.305481053845261e-05,
+      "loss": 1.6328,
+      "step": 298
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 7.179833482950926e-05,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.652,
+      "step": 300
+    },
+    {
+      "epoch": 2.603448275862069,
+      "grad_norm": 6.626212416449562e-05,
+      "learning_rate": 6.041630643875018e-05,
+      "loss": 1.7552,
+      "step": 302
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 6.928609946044162e-05,
+      "learning_rate": 5.910902778255134e-05,
+      "loss": 1.6969,
+      "step": 304
+    },
+    {
+      "epoch": 2.637931034482759,
+      "grad_norm": 7.145026029320434e-05,
+      "learning_rate": 5.7810087367289744e-05,
+      "loss": 1.7151,
+      "step": 306
+    },
+    {
+      "epoch": 2.655172413793103,
+      "grad_norm": 6.987711822148412e-05,
+      "learning_rate": 5.651975006507681e-05,
+      "loss": 1.6533,
+      "step": 308
+    },
+    {
+      "epoch": 2.6724137931034484,
+      "grad_norm": 6.940370803931728e-05,
+      "learning_rate": 5.5238278993728756e-05,
+      "loss": 1.6922,
+      "step": 310
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.0001817405573092401,
+      "learning_rate": 5.396593546311346e-05,
+      "loss": 1.6973,
+      "step": 312
+    },
+    {
+      "epoch": 2.706896551724138,
+      "grad_norm": 7.641298725502566e-05,
+      "learning_rate": 5.270297892186563e-05,
+      "loss": 1.7294,
+      "step": 314
+    },
+    {
+      "epoch": 2.7241379310344827,
+      "grad_norm": 6.699555524392053e-05,
+      "learning_rate": 5.1449666904481585e-05,
+      "loss": 1.6713,
+      "step": 316
+    },
+    {
+      "epoch": 2.7413793103448274,
+      "grad_norm": 6.963134364923462e-05,
+      "learning_rate": 5.0206254978804435e-05,
+      "loss": 1.7326,
+      "step": 318
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 7.145871495595202e-05,
+      "learning_rate": 4.8972996693910054e-05,
+      "loss": 1.7386,
+      "step": 320
+    },
+    {
+      "epoch": 2.7758620689655173,
+      "grad_norm": 6.800260598538443e-05,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 1.6939,
+      "step": 322
+    },
+    {
+      "epoch": 2.793103448275862,
+      "grad_norm": 6.864208990009502e-05,
+      "learning_rate": 4.653794483914696e-05,
+      "loss": 1.7581,
+      "step": 324
+    },
+    {
+      "epoch": 2.810344827586207,
+      "grad_norm": 7.070614083204418e-05,
+      "learning_rate": 4.5336647810396215e-05,
+      "loss": 1.7155,
+      "step": 326
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 7.455341255990788e-05,
+      "learning_rate": 4.414649740341258e-05,
+      "loss": 1.7955,
+      "step": 328
+    },
+    {
+      "epoch": 2.844827586206897,
+      "grad_norm": 7.38763774279505e-05,
+      "learning_rate": 4.296773630650358e-05,
+      "loss": 1.7269,
+      "step": 330
+    },
+    {
+      "epoch": 2.862068965517241,
+      "grad_norm": 7.165527495089918e-05,
+      "learning_rate": 4.180060488553743e-05,
+      "loss": 1.7887,
+      "step": 332
+    },
+    {
+      "epoch": 2.8793103448275863,
+      "grad_norm": 7.368691876763478e-05,
+      "learning_rate": 4.06453411349286e-05,
+      "loss": 1.7997,
+      "step": 334
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 7.610574539285153e-05,
+      "learning_rate": 3.9502180629107756e-05,
+      "loss": 1.7738,
+      "step": 336
+    },
+    {
+      "epoch": 2.913793103448276,
+      "grad_norm": 7.454157457686961e-05,
+      "learning_rate": 3.8371356474484746e-05,
+      "loss": 1.7776,
+      "step": 338
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 7.552184979431331e-05,
+      "learning_rate": 3.725309926191479e-05,
+      "loss": 1.7869,
+      "step": 340
+    },
+    {
+      "epoch": 2.9482758620689653,
+      "grad_norm": 7.433702558046207e-05,
+      "learning_rate": 3.6147637019678195e-05,
+      "loss": 1.8083,
+      "step": 342
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 7.243530126288533e-05,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 1.7669,
+      "step": 344
+    },
+    {
+      "epoch": 2.9827586206896552,
+      "grad_norm": 7.482223736587912e-05,
+      "learning_rate": 3.397599646799256e-05,
+      "loss": 1.7417,
+      "step": 346
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.792668813839555e-05,
+      "learning_rate": 3.291026098641397e-05,
+      "loss": 1.8761,
+      "step": 348
+    },
+    {
+      "epoch": 3.0172413793103448,
+      "grad_norm": 7.802840991644189e-05,
+      "learning_rate": 3.185820604061088e-05,
+      "loss": 1.7633,
+      "step": 350
+    },
+    {
+      "epoch": 3.0344827586206895,
+      "grad_norm": 6.89391017658636e-05,
+      "learning_rate": 3.0820046159295644e-05,
+      "loss": 1.687,
+      "step": 352
+    },
+    {
+      "epoch": 3.0517241379310347,
+      "grad_norm": 7.239273691084236e-05,
+      "learning_rate": 2.9795993037782655e-05,
+      "loss": 1.7539,
+      "step": 354
+    },
+    {
+      "epoch": 3.0689655172413794,
+      "grad_norm": 7.185838330769911e-05,
+      "learning_rate": 2.8786255494820835e-05,
+      "loss": 1.7366,
+      "step": 356
+    },
+    {
+      "epoch": 3.086206896551724,
+      "grad_norm": 7.206243026303127e-05,
+      "learning_rate": 2.7791039430012476e-05,
+      "loss": 1.7703,
+      "step": 358
+    },
+    {
+      "epoch": 3.103448275862069,
+      "grad_norm": 7.18203154974617e-05,
+      "learning_rate": 2.681054778182748e-05,
+      "loss": 1.7132,
+      "step": 360
+    },
+    {
+      "epoch": 3.1206896551724137,
+      "grad_norm": 6.849451165180653e-05,
+      "learning_rate": 2.5844980486221228e-05,
+      "loss": 1.7914,
+      "step": 362
+    },
+    {
+      "epoch": 3.1379310344827585,
+      "grad_norm": 7.244012522278354e-05,
+      "learning_rate": 2.4894534435865015e-05,
+      "loss": 1.7365,
+      "step": 364
+    },
+    {
+      "epoch": 3.1551724137931036,
+      "grad_norm": 6.781809497624636e-05,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 1.7446,
+      "step": 366
+    },
+    {
+      "epoch": 3.1724137931034484,
+      "grad_norm": 6.832330109318718e-05,
+      "learning_rate": 2.3039778184901084e-05,
+      "loss": 1.7554,
+      "step": 368
+    },
+    {
+      "epoch": 3.189655172413793,
+      "grad_norm": 6.69066866976209e-05,
+      "learning_rate": 2.2135846195024513e-05,
+      "loss": 1.7409,
+      "step": 370
+    },
+    {
+      "epoch": 3.206896551724138,
+      "grad_norm": 6.750784814357758e-05,
+      "learning_rate": 2.1247791794737826e-05,
+      "loss": 1.7058,
+      "step": 372
+    },
+    {
+      "epoch": 3.2241379310344827,
+      "grad_norm": 7.111330342013389e-05,
+      "learning_rate": 2.0375796070749363e-05,
+      "loss": 1.7842,
+      "step": 374
+    },
+    {
+      "epoch": 3.2413793103448274,
+      "grad_norm": 6.951171235414222e-05,
+      "learning_rate": 1.9520036835178668e-05,
+      "loss": 1.7586,
+      "step": 376
+    },
+    {
+      "epoch": 3.2586206896551726,
+      "grad_norm": 6.802480493206531e-05,
+      "learning_rate": 1.8680688589298368e-05,
+      "loss": 1.6923,
+      "step": 378
+    },
+    {
+      "epoch": 3.2758620689655173,
+      "grad_norm": 6.907380156917498e-05,
+      "learning_rate": 1.7857922487950874e-05,
+      "loss": 1.7892,
+      "step": 380
+    },
+    {
+      "epoch": 3.293103448275862,
+      "grad_norm": 6.635097815888003e-05,
+      "learning_rate": 1.7051906304647368e-05,
+      "loss": 1.8035,
+      "step": 382
+    },
+    {
+      "epoch": 3.310344827586207,
+      "grad_norm": 6.926745845703408e-05,
+      "learning_rate": 1.6262804397356746e-05,
+      "loss": 1.8157,
+      "step": 384
+    },
+    {
+      "epoch": 3.3275862068965516,
+      "grad_norm": 7.06208884366788e-05,
+      "learning_rate": 1.5490777674990376e-05,
+      "loss": 1.7965,
+      "step": 386
+    },
+    {
+      "epoch": 3.344827586206897,
+      "grad_norm": 6.897733692312613e-05,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 1.7867,
+      "step": 388
+    },
+    {
+      "epoch": 3.3620689655172415,
+      "grad_norm": 6.628095434280112e-05,
+      "learning_rate": 1.3998575979229944e-05,
+      "loss": 1.7529,
+      "step": 390
+    },
+    {
+      "epoch": 3.3793103448275863,
+      "grad_norm": 6.664723332505673e-05,
+      "learning_rate": 1.3278705286624327e-05,
+      "loss": 1.7666,
+      "step": 392
+    },
+    {
+      "epoch": 3.396551724137931,
+      "grad_norm": 6.862921145511791e-05,
+      "learning_rate": 1.2576518278472759e-05,
+      "loss": 1.7662,
+      "step": 394
+    },
+    {
+      "epoch": 3.413793103448276,
+      "grad_norm": 6.93115871399641e-05,
+      "learning_rate": 1.1892158140523546e-05,
+      "loss": 1.7767,
+      "step": 396
+    },
+    {
+      "epoch": 3.4310344827586206,
+      "grad_norm": 6.726732681272551e-05,
+      "learning_rate": 1.122576442337696e-05,
+      "loss": 1.7228,
+      "step": 398
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 6.953762203920633e-05,
+      "learning_rate": 1.057747301402887e-05,
+      "loss": 1.7798,
+      "step": 400
+    },
+    {
+      "epoch": 3.4655172413793105,
+      "grad_norm": 6.499426672235131e-05,
+      "learning_rate": 9.9474161081615e-06,
+      "loss": 1.7788,
+      "step": 402
+    },
+    {
+      "epoch": 3.4827586206896552,
+      "grad_norm": 7.109656144166365e-05,
+      "learning_rate": 9.335722183186868e-06,
+      "loss": 1.8461,
+      "step": 404
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 6.401236169040203e-05,
+      "learning_rate": 8.742515972048404e-06,
+      "loss": 1.7763,
+      "step": 406
+    },
+    {
+      "epoch": 3.5172413793103448,
+      "grad_norm": 6.046515409252606e-05,
+      "learning_rate": 8.167918437786315e-06,
+      "loss": 1.7883,
+      "step": 408
+    },
+    {
+      "epoch": 3.5344827586206895,
+      "grad_norm": 8.47960909595713e-05,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.8786,
+      "step": 410
+    },
+    {
+      "epoch": 3.5517241379310347,
+      "grad_norm": 6.603649671887979e-05,
+      "learning_rate": 7.07501425531254e-06,
+      "loss": 1.8065,
+      "step": 412
+    },
+    {
+      "epoch": 3.5689655172413794,
+      "grad_norm": 6.533504347316921e-05,
+      "learning_rate": 6.556930465543709e-06,
+      "loss": 1.792,
+      "step": 414
+    },
+    {
+      "epoch": 3.586206896551724,
+      "grad_norm": 6.376888632075861e-05,
+      "learning_rate": 6.057901024092949e-06,
+      "loss": 1.782,
+      "step": 416
+    },
+    {
+      "epoch": 3.603448275862069,
+      "grad_norm": 6.636454781983048e-05,
+      "learning_rate": 5.57802769004041e-06,
+      "loss": 1.7859,
+      "step": 418
+    },
+    {
+      "epoch": 3.6206896551724137,
+      "grad_norm": 6.567131640622392e-05,
+      "learning_rate": 5.1174083162680465e-06,
+      "loss": 1.7766,
+      "step": 420
+    },
+    {
+      "epoch": 3.637931034482759,
+      "grad_norm": 6.865750037832186e-05,
+      "learning_rate": 4.67613682950615e-06,
+      "loss": 1.8302,
+      "step": 422
+    },
+    {
+      "epoch": 3.655172413793103,
+      "grad_norm": 6.414071685867384e-05,
+      "learning_rate": 4.254303211180355e-06,
+      "loss": 1.7911,
+      "step": 424
+    },
+    {
+      "epoch": 3.6724137931034484,
+      "grad_norm": 6.754395872121677e-05,
+      "learning_rate": 3.851993479063154e-06,
+      "loss": 1.7664,
+      "step": 426
+    },
+    {
+      "epoch": 3.689655172413793,
+      "grad_norm": 6.551917613251135e-05,
+      "learning_rate": 3.4692896697336886e-06,
+      "loss": 1.7811,
+      "step": 428
+    },
+    {
+      "epoch": 3.706896551724138,
+      "grad_norm": 7.202311826404184e-05,
+      "learning_rate": 3.1062698218492724e-06,
+      "loss": 1.8226,
+      "step": 430
+    },
+    {
+      "epoch": 3.7241379310344827,
+      "grad_norm": 6.517766450997442e-05,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 1.8063,
+      "step": 432
+    },
+    {
+      "epoch": 3.7413793103448274,
+      "grad_norm": 6.443189340643585e-05,
+      "learning_rate": 2.439574080775675e-06,
+      "loss": 1.7537,
+      "step": 434
+    },
+    {
+      "epoch": 3.7586206896551726,
+      "grad_norm": 6.728331209160388e-05,
+      "learning_rate": 2.1360341361692517e-06,
+      "loss": 1.8045,
+      "step": 436
+    },
+    {
+      "epoch": 3.7758620689655173,
+      "grad_norm": 6.782256241422147e-05,
+      "learning_rate": 1.852450022451624e-06,
+      "loss": 1.7714,
+      "step": 438
+    },
+    {
+      "epoch": 3.793103448275862,
+      "grad_norm": 6.543852941831574e-05,
+      "learning_rate": 1.5888795663883904e-06,
+      "loss": 1.8291,
+      "step": 440
+    },
+    {
+      "epoch": 3.810344827586207,
+      "grad_norm": 6.210138235474005e-05,
+      "learning_rate": 1.3453765136805741e-06,
+      "loss": 1.736,
+      "step": 442
+    },
+    {
+      "epoch": 3.8275862068965516,
+      "grad_norm": 6.788953032810241e-05,
+      "learning_rate": 1.1219905180050449e-06,
+      "loss": 1.8532,
+      "step": 444
+    },
+    {
+      "epoch": 3.844827586206897,
+      "grad_norm": 6.382510036928579e-05,
+      "learning_rate": 9.187671308895418e-07,
+      "loss": 1.776,
+      "step": 446
+    },
+    {
+      "epoch": 3.862068965517241,
+      "grad_norm": 6.794829823775217e-05,
+      "learning_rate": 7.357477924239797e-07,
+      "loss": 1.7598,
+      "step": 448
+    },
+    {
+      "epoch": 3.8793103448275863,
+      "grad_norm": 6.589698750758544e-05,
+      "learning_rate": 5.729698228102653e-07,
+      "loss": 1.7108,
+      "step": 450
+    },
+    {
+      "epoch": 3.896551724137931,
+      "grad_norm": 6.492222746601328e-05,
+      "learning_rate": 4.304664147522619e-07,
+      "loss": 1.8017,
+      "step": 452
+    },
+    {
+      "epoch": 3.913793103448276,
+      "grad_norm": 6.393203511834145e-05,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 1.7412,
+      "step": 454
+    },
+    {
+      "epoch": 3.9310344827586206,
+      "grad_norm": 7.689798076171428e-05,
+      "learning_rate": 2.0639537686037991e-07,
+      "loss": 1.8375,
+      "step": 456
+    },
+    {
+      "epoch": 3.9482758620689653,
+      "grad_norm": 6.880257569719106e-05,
+      "learning_rate": 1.2487343824389986e-07,
+      "loss": 1.8256,
+      "step": 458
+    },
+    {
+      "epoch": 3.9655172413793105,
+      "grad_norm": 6.746077269781381e-05,
+      "learning_rate": 6.37174343008251e-08,
+      "loss": 1.7953,
+      "step": 460
+    },
+    {
+      "epoch": 3.9827586206896552,
+      "grad_norm": 6.316731014521793e-05,
+      "learning_rate": 2.2939835595392478e-08,
+      "loss": 1.7913,
+      "step": 462
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.769967098487541e-05,
+      "learning_rate": 2.5489572500814184e-09,
+      "loss": 1.7147,
+      "step": 464
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 464,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.702673043946209e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-464/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e0384a95773c4f9f1910994edd74cc0c1467bafb112774589033914dd397a4
+size 5713