Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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-147/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,62 @@
 ---
 base_model: Qwen/Qwen2.5-32B-Instruct
-base_model_revision: 5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd
+library_name: peft
+model_name: defend-identity-lora-v002
+tags:
+- base_model:adapter:Qwen/Qwen2.5-32B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
 ---
 
-# DEFEND Identity LoRA v002
+# Model Card for defend-identity-lora-v002
 
-Clean adapter trained from pinned Qwen2.5-32B-Instruct revision `5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd`.
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-This is a new training run (not continued from v001).
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.20.0
+- TRL: 1.10.0
+- Transformers: 5.15.0
+- Pytorch: 2.12.0+cu130
+- Datasets: 5.0.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6e9afd486c3aae186041235aca03f11b3a2950bc23e70d3748ea00f39434fa
+size 268557056

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 %}

checkpoint-147/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-32B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-32B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0

checkpoint-147/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-147/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6e9afd486c3aae186041235aca03f11b3a2950bc23e70d3748ea00f39434fa
+size 268557056

checkpoint-147/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 %}

checkpoint-147/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6bf34a538b4033c39a4cc0db02eb168e9529efa815855104d94b79b305111e5
+size 273701989

checkpoint-147/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffdecd1f3d1090ae23c75fa51826996f691e56b32613cd446521f64ea5c37650
+size 14645

checkpoint-147/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c6f9529d009191b0ee0b8b8a8204c7ff7f42a294c6e5d29bab792a096b36c7
+size 1465

checkpoint-147/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-147/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "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
+}

checkpoint-147/trainer_state.json

@@ -0,0 +1,324 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6612249977886677,
+      "epoch": 0.03404255319148936,
+      "grad_norm": 2.28125,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 5.1158195495605465,
+      "mean_token_accuracy": 0.3411124350503087,
+      "num_tokens": 12338.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.7161438561975957,
+      "epoch": 0.06808510638297872,
+      "grad_norm": 3.421875,
+      "learning_rate": 1.8e-05,
+      "loss": 4.932054138183593,
+      "mean_token_accuracy": 0.34090186562389135,
+      "num_tokens": 24228.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.8052345253527164,
+      "epoch": 0.10212765957446808,
+      "grad_norm": 1.9609375,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 4.3712615966796875,
+      "mean_token_accuracy": 0.37591628544032574,
+      "num_tokens": 36607.0,
+      "step": 15
+    },
+    {
+      "entropy": 2.1016422733664513,
+      "epoch": 0.13617021276595745,
+      "grad_norm": 1.5703125,
+      "learning_rate": 3.8e-05,
+      "loss": 3.642262268066406,
+      "mean_token_accuracy": 0.4129604626446962,
+      "num_tokens": 48067.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.3243144676089287,
+      "epoch": 0.1702127659574468,
+      "grad_norm": 2.015625,
+      "learning_rate": 4.8e-05,
+      "loss": 2.9660737991333006,
+      "mean_token_accuracy": 0.4782245371490717,
+      "num_tokens": 59636.0,
+      "step": 25
+    },
+    {
+      "entropy": 2.302782629430294,
+      "epoch": 0.20425531914893616,
+      "grad_norm": 1.4296875,
+      "learning_rate": 5.8e-05,
+      "loss": 2.5412269592285157,
+      "mean_token_accuracy": 0.5392776299268007,
+      "num_tokens": 71707.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.188954807817936,
+      "epoch": 0.23829787234042554,
+      "grad_norm": 0.71875,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 2.2308956146240235,
+      "mean_token_accuracy": 0.5898199148476124,
+      "num_tokens": 84024.0,
+      "step": 35
+    },
+    {
+      "entropy": 2.2109520554542543,
+      "epoch": 0.2723404255319149,
+      "grad_norm": 0.859375,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.964349365234375,
+      "mean_token_accuracy": 0.6209986783564091,
+      "num_tokens": 96306.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.0961234346032143,
+      "epoch": 0.30638297872340425,
+      "grad_norm": 0.7265625,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.792983055114746,
+      "mean_token_accuracy": 0.6284430582076311,
+      "num_tokens": 108229.0,
+      "step": 45
+    },
+    {
+      "entropy": 1.671985263749957,
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.8e-05,
+      "loss": 1.5038132667541504,
+      "mean_token_accuracy": 0.6809367395937442,
+      "num_tokens": 120313.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.6443435620516538,
+      "epoch": 0.37446808510638296,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.958100506132127e-05,
+      "loss": 1.4452999114990235,
+      "mean_token_accuracy": 0.6813344601541758,
+      "num_tokens": 132222.0,
+      "step": 55
+    },
+    {
+      "entropy": 1.4775371879339219,
+      "epoch": 0.4085106382978723,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.789086620939936e-05,
+      "loss": 1.3673093795776368,
+      "mean_token_accuracy": 0.6939370810985566,
+      "num_tokens": 144737.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.362747695669532,
+      "epoch": 0.4425531914893617,
+      "grad_norm": 0.5390625,
+      "learning_rate": 9.494758705426978e-05,
+      "loss": 1.2551464080810546,
+      "mean_token_accuracy": 0.718667059391737,
+      "num_tokens": 156461.0,
+      "step": 65
+    },
+    {
+      "entropy": 1.4880228728055953,
+      "epoch": 0.4765957446808511,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.082818315286055e-05,
+      "loss": 1.3538105010986328,
+      "mean_token_accuracy": 0.7009879656136035,
+      "num_tokens": 167343.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.3466651082038879,
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.6796875,
+      "learning_rate": 8.564044522734147e-05,
+      "loss": 1.2858383178710937,
+      "mean_token_accuracy": 0.7119019150733947,
+      "num_tokens": 178638.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.2633912980556488,
+      "epoch": 0.5446808510638298,
+      "grad_norm": 0.69921875,
+      "learning_rate": 7.952011865029614e-05,
+      "loss": 1.1970553398132324,
+      "mean_token_accuracy": 0.7300039514899254,
+      "num_tokens": 190643.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.2618269324302673,
+      "epoch": 0.5787234042553191,
+      "grad_norm": 0.66015625,
+      "learning_rate": 7.262735145222696e-05,
+      "loss": 1.1030343055725098,
+      "mean_token_accuracy": 0.7353190571069718,
+      "num_tokens": 202328.0,
+      "step": 85
+    },
+    {
+      "entropy": 1.2507698042318225,
+      "epoch": 0.6127659574468085,
+      "grad_norm": 0.66015625,
+      "learning_rate": 6.514250379489753e-05,
+      "loss": 1.133834457397461,
+      "mean_token_accuracy": 0.7314565621316433,
+      "num_tokens": 213840.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.2799267198890447,
+      "epoch": 0.6468085106382979,
+      "grad_norm": 0.640625,
+      "learning_rate": 5.726142856227452e-05,
+      "loss": 1.1554755210876464,
+      "mean_token_accuracy": 0.7302999064326287,
+      "num_tokens": 225649.0,
+      "step": 95
+    },
+    {
+      "entropy": 1.1757509659975767,
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.7109375,
+      "learning_rate": 4.919034655987493e-05,
+      "loss": 1.060139274597168,
+      "mean_token_accuracy": 0.7470736525952816,
+      "num_tokens": 237320.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2040388137102127,
+      "epoch": 0.7148936170212766,
+      "grad_norm": 0.70703125,
+      "learning_rate": 4.114045042103887e-05,
+      "loss": 1.0966894149780273,
+      "mean_token_accuracy": 0.7398598760366439,
+      "num_tokens": 249781.0,
+      "step": 105
+    },
+    {
+      "entropy": 1.2984253257513045,
+      "epoch": 0.7489361702127659,
+      "grad_norm": 0.76953125,
+      "learning_rate": 3.332237841745898e-05,
+      "loss": 1.16298828125,
+      "mean_token_accuracy": 0.7219951130449772,
+      "num_tokens": 260474.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.131225979141891,
+      "epoch": 0.7829787234042553,
+      "grad_norm": 0.578125,
+      "learning_rate": 2.5940702775459747e-05,
+      "loss": 1.010167694091797,
+      "mean_token_accuracy": 0.75770732909441,
+      "num_tokens": 271936.0,
+      "step": 115
+    },
+    {
+      "entropy": 1.1314816752448678,
+      "epoch": 0.8170212765957446,
+      "grad_norm": 0.6484375,
+      "learning_rate": 1.9188576719953633e-05,
+      "loss": 1.0260458946228028,
+      "mean_token_accuracy": 0.7487939164042473,
+      "num_tokens": 283647.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.1653054066002368,
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.8203125,
+      "learning_rate": 1.3242680314639993e-05,
+      "loss": 1.0705586433410645,
+      "mean_token_accuracy": 0.748039523512125,
+      "num_tokens": 294672.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.2385535925626754,
+      "epoch": 0.8851063829787233,
+      "grad_norm": 0.875,
+      "learning_rate": 8.25859734853645e-06,
+      "loss": 1.117280864715576,
+      "mean_token_accuracy": 0.7358166418969632,
+      "num_tokens": 305646.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.1569571590051055,
+      "epoch": 0.9191489361702128,
+      "grad_norm": 0.734375,
+      "learning_rate": 4.366744239922998e-06,
+      "loss": 1.0218097686767578,
+      "mean_token_accuracy": 0.7512762233614921,
+      "num_tokens": 317522.0,
+      "step": 135
+    },
+    {
+      "entropy": 1.2956396371126175,
+      "epoch": 0.9531914893617022,
+      "grad_norm": 0.640625,
+      "learning_rate": 1.6689574843694433e-06,
+      "loss": 1.1682409286499023,
+      "mean_token_accuracy": 0.7267132062464953,
+      "num_tokens": 328188.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.1794268768280745,
+      "epoch": 0.9872340425531915,
+      "grad_norm": 0.796875,
+      "learning_rate": 2.3582894166930268e-07,
+      "loss": 1.0452459335327149,
+      "mean_token_accuracy": 0.7454933904111385,
+      "num_tokens": 340204.0,
+      "step": 145
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 147,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 6.64226666827776e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-147/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af857186485f7886bd37e125673eb8925184021c8781eed36ce7d1c3b1cc9521
+size 5713

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "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
+}