From 868c4304a19fb9e8d5ed3ea1b734e252b091a146 Mon Sep 17 00:00:00 2001
From: ModelHub XC <noreply@modelhub.org.cn>
Date: Thu, 1 Oct 2026 02:49:18 +0800
Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?=
 =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?=
 =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Model: 1010happy/claude_max_max7_perblock35-Qwen2-5-1-5B-seed10
Source: Original Platform
---
 .gitattributes         |  36 ++++++++
 README.md              | 201 +++++++++++++++++++++++++++++++++++++++++
 chat_template.jinja    |  54 +++++++++++
 config.json            |  62 +++++++++++++
 generation_config.json |   9 ++
 model.safetensors      |   3 +
 tokenizer.json         |   3 +
 tokenizer_config.json  |  30 ++++++
 training_logs.json     |   1 +
 9 files changed, 399 insertions(+)
 create mode 100644 .gitattributes
 create mode 100644 README.md
 create mode 100644 chat_template.jinja
 create mode 100644 config.json
 create mode 100644 generation_config.json
 create mode 100644 model.safetensors
 create mode 100644 tokenizer.json
 create mode 100644 tokenizer_config.json
 create mode 100644 training_logs.json

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..2480968
--- /dev/null
+++ b/README.md
@@ -0,0 +1,201 @@
+---
+library_name: transformers
+tags:
+- trl
+- sft
+---
+
+# 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. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **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]
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..28028c0
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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 %}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..7f4ad69
--- /dev/null
+++ b/config.json
@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..4e1b764
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "do_sample": false,
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "5.14.1"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..f04dd69
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fecf92fe71f79070551d7c41252e7394e35a9cfa3dbdee9695477884df7b88c1
+size 3087467144
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..34510ff
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..df536e9
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/training_logs.json b/training_logs.json
new file mode 100644
index 0000000..387e864
--- /dev/null
+++ b/training_logs.json
@@ -0,0 +1 @@
+[{"step": 10, "loss": 1.5137919425964355, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 20, "loss": 0.9137966156005859, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 30, "loss": 0.8356868743896484, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 40, "loss": 0.7394894599914551, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 50, "loss": 0.7229472160339355, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 60, "loss": 0.7127396583557128, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 70, "loss": 0.6798008441925049, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 80, "loss": 0.6428463935852051, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 90, "loss": 0.6323223114013672, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 100, "loss": 0.6358980655670166, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 110, "loss": 0.6362273693084717, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 120, "loss": 0.6055667400360107, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 130, "loss": 0.576851224899292, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 140, "loss": 0.5903679847717285, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 150, "loss": 0.6110738754272461, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 160, "loss": 0.5600853443145752, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 170, "loss": 0.5756892204284668, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 180, "loss": 0.5620709419250488, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 190, "loss": 0.5751183986663818, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 200, "loss": 0.5783648014068603, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 210, "loss": 0.5216079711914062, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 220, "loss": 0.5261220932006836, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 230, "loss": 0.5525682926177978, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 240, "loss": 0.549705696105957, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 250, "loss": 0.5236713409423828, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 260, "loss": 0.5465120792388916, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 270, "loss": 0.5295405387878418, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 280, "loss": 0.5056062698364258, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 290, "loss": 0.4831366062164307, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 300, "loss": 0.5264166831970215, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 310, "loss": 0.5023453235626221, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 320, "loss": 0.5075996398925782, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 330, "loss": 0.49302287101745607, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 340, "loss": 0.4792414665222168, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 350, "loss": 0.4743649959564209, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 360, "loss": 0.47952780723571775, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 370, "loss": 0.4890012741088867, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 380, "loss": 0.49666056632995603, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 390, "loss": 0.4800737380981445, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 400, "loss": 0.4955928802490234, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 410, "loss": 0.5054766178131104, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 420, "loss": 0.4729923248291016, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 430, "loss": 0.4625997543334961, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 440, "loss": 0.4811848640441895, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 450, "loss": 0.4780567169189453, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 460, "loss": 0.49033379554748535, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 470, "loss": 0.46168832778930663, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 480, "loss": 0.4954554557800293, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 490, "loss": 0.47626514434814454, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 500, "loss": 0.5134393692016601, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 510, "loss": 0.4785011291503906, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 520, "loss": 0.49104723930358884, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 530, "loss": 0.4548022270202637, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 540, "loss": 0.48142094612121583, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 550, "loss": 0.4771817684173584, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 560, "loss": 0.5107679843902588, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 570, "loss": 0.4427817344665527, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 580, "loss": 0.4746194839477539, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 590, "loss": 0.5114977359771729, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 600, "loss": 0.4627247333526611, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 610, "loss": 0.47262821197509763, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 620, "loss": 0.4878103733062744, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 630, "loss": 0.46667118072509767, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 640, "loss": 0.49881706237792967, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 650, "loss": 0.4604348182678223, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 660, "loss": 0.46343369483947755, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 670, "loss": 0.47187604904174807, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 680, "loss": 0.45656561851501465, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 690, "loss": 0.46276230812072755, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 700, "loss": 0.46104016304016116, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 710, "loss": 0.47778749465942383, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 720, "loss": 0.45834007263183596, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 730, "loss": 0.45184717178344724, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 740, "loss": 0.4769592761993408, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}, {"step": 750, "loss": 0.46434602737426756, "b": "teacher_2026-08-06_exp_0_p5_r7_i1"}]
\ No newline at end of file