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-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-908/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+model_name: Security-Qwen2.5-7B-output
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for Security-Qwen2.5-7B-output
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## 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 0.19.1
+- TRL: 1.2.0
+- Transformers: 5.5.1
+- Pytorch: 2.11.0+rocm7.2
+- Datasets: 4.8.4
+- 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 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-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,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bea2c800c592d6376322f86370cef343b9cad30631813bbf4eb8327edb738c2
+size 80792880

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-500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-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 0.19.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-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,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597db42c60b86460d97ee250a73557dcac9636efdfcd154946f65431bc22924c
+size 80792880

checkpoint-500/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-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e370ae572370dcca4dfd69bd08b290fe38dfae6a8c96387dccec49e8c5af948
+size 161810747

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8ea3f8c297a16df54f9515887b4d44118d846f841e964221c77afb21f2a85f
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93be60ba4e3413a9396f9537d4fc4af61213a760ae92cf3bbe8bd93f16406daa
+size 1465

checkpoint-500/tokenizer.json

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

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5511919525974921,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.9013997074961662,
+      "epoch": 0.027559597629874606,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 2.106939239501953,
+      "mean_token_accuracy": 0.5557776354253292,
+      "num_tokens": 140963.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.7775965774059295,
+      "epoch": 0.05511919525974921,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 0.0001997191078685512,
+      "loss": 1.7464599609375,
+      "mean_token_accuracy": 0.6121900254487991,
+      "num_tokens": 284944.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.6929514452815055,
+      "epoch": 0.0826787928896238,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00019865462348631944,
+      "loss": 1.6511944580078124,
+      "mean_token_accuracy": 0.6266605603694916,
+      "num_tokens": 425136.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.5028782638907432,
+      "epoch": 0.11023839051949842,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 0.00019680482470453816,
+      "loss": 1.4662600708007814,
+      "mean_token_accuracy": 0.659810485392809,
+      "num_tokens": 567966.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.4264089419692754,
+      "epoch": 0.13779798814937302,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 0.00019418443636395248,
+      "loss": 1.4101972961425782,
+      "mean_token_accuracy": 0.6815375398099422,
+      "num_tokens": 706204.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.1659171215072275,
+      "epoch": 0.1653575857792476,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 0.00019081431738250814,
+      "loss": 1.1057415008544922,
+      "mean_token_accuracy": 0.7461765056848526,
+      "num_tokens": 851807.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.1612900688499213,
+      "epoch": 0.19291718340912223,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.00018672129471337568,
+      "loss": 1.1313108062744142,
+      "mean_token_accuracy": 0.7447272512316704,
+      "num_tokens": 998421.0,
+      "step": 175
+    },
+    {
+      "entropy": 1.0649858928844333,
+      "epoch": 0.22047678103899684,
+      "grad_norm": 0.11328125,
+      "learning_rate": 0.00018193794979598656,
+      "loss": 1.0393009185791016,
+      "mean_token_accuracy": 0.763860610127449,
+      "num_tokens": 1141761.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8765474074520171,
+      "epoch": 0.24803637866887143,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 0.00017650235919998232,
+      "loss": 0.8135224914550782,
+      "mean_token_accuracy": 0.807485072016716,
+      "num_tokens": 1286611.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.8536889077164233,
+      "epoch": 0.27559597629874605,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00017045779152661297,
+      "loss": 0.8201860809326171,
+      "mean_token_accuracy": 0.8146287898719311,
+      "num_tokens": 1428015.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8703145318105817,
+      "epoch": 0.30315557392862064,
+      "grad_norm": 0.09765625,
+      "learning_rate": 0.00016385236298032183,
+      "loss": 0.815809326171875,
+      "mean_token_accuracy": 0.8103299827873707,
+      "num_tokens": 1574815.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.8991702864505351,
+      "epoch": 0.3307151715584952,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00015673865435224962,
+      "loss": 0.8489224243164063,
+      "mean_token_accuracy": 0.8056490634381771,
+      "num_tokens": 1717330.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7706374152004719,
+      "epoch": 0.35827476918836987,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 0.0001491732924645604,
+      "loss": 0.7274211883544922,
+      "mean_token_accuracy": 0.8297103045880795,
+      "num_tokens": 1859716.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.7342993662878871,
+      "epoch": 0.38583436681824446,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 0.00014121649940739301,
+      "loss": 0.7029119110107422,
+      "mean_token_accuracy": 0.8427872517704964,
+      "num_tokens": 2005201.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.7452906335704028,
+      "epoch": 0.41339396444811904,
+      "grad_norm": 0.1279296875,
+      "learning_rate": 0.00013293161315661931,
+      "loss": 0.7123774719238282,
+      "mean_token_accuracy": 0.8400052092969418,
+      "num_tokens": 2143419.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.6938006362970919,
+      "epoch": 0.4409535620779937,
+      "grad_norm": 0.1181640625,
+      "learning_rate": 0.00012438458338840706,
+      "loss": 0.6549488830566407,
+      "mean_token_accuracy": 0.8493785254657269,
+      "num_tokens": 2288125.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7443565137218684,
+      "epoch": 0.4685131597078683,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.6924254608154297,
+      "mean_token_accuracy": 0.8412553237378597,
+      "num_tokens": 2431404.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.645295873908326,
+      "epoch": 0.49607275733774286,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00010677778404380643,
+      "loss": 0.6191695022583008,
+      "mean_token_accuracy": 0.8578527195751667,
+      "num_tokens": 2571370.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6608448463864625,
+      "epoch": 0.5236323549676175,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 9.78581688014642e-05,
+      "loss": 0.6262045669555664,
+      "mean_token_accuracy": 0.856816074848175,
+      "num_tokens": 2714312.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.5949629322066903,
+      "epoch": 0.5511919525974921,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 8.895560304775387e-05,
+      "loss": 0.54037109375,
+      "mean_token_accuracy": 0.8706019401550293,
+      "num_tokens": 2850910.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2163674323684352e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f4507cae4004563bb50348f5e858baf28582cc170d5db69d774cd7b166a1b0
+size 5649

checkpoint-908/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-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 0.19.1

checkpoint-908/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-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,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-908/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bea2c800c592d6376322f86370cef343b9cad30631813bbf4eb8327edb738c2
+size 80792880

checkpoint-908/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-908/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03dc8e79786197923f0d097ac3b2d05eaa055d1c96041a0b7cb60ed9f25be64a
+size 161810747

checkpoint-908/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c675c79de694bb285f5145c400612438508f782f22756b1b88a92170c41b88
+size 14645

checkpoint-908/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9240945f0542e7d051938efc4a9ce0ef4b230fe6b6bc75718db3891c74982214
+size 1465

checkpoint-908/tokenizer.json

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

checkpoint-908/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-908/trainer_state.json

@@ -0,0 +1,394 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 908,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.9013997074961662,
+      "epoch": 0.027559597629874606,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 2.106939239501953,
+      "mean_token_accuracy": 0.5557776354253292,
+      "num_tokens": 140963.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.7775965774059295,
+      "epoch": 0.05511919525974921,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 0.0001997191078685512,
+      "loss": 1.7464599609375,
+      "mean_token_accuracy": 0.6121900254487991,
+      "num_tokens": 284944.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.6929514452815055,
+      "epoch": 0.0826787928896238,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00019865462348631944,
+      "loss": 1.6511944580078124,
+      "mean_token_accuracy": 0.6266605603694916,
+      "num_tokens": 425136.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.5028782638907432,
+      "epoch": 0.11023839051949842,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 0.00019680482470453816,
+      "loss": 1.4662600708007814,
+      "mean_token_accuracy": 0.659810485392809,
+      "num_tokens": 567966.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.4264089419692754,
+      "epoch": 0.13779798814937302,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 0.00019418443636395248,
+      "loss": 1.4101972961425782,
+      "mean_token_accuracy": 0.6815375398099422,
+      "num_tokens": 706204.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.1659171215072275,
+      "epoch": 0.1653575857792476,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 0.00019081431738250814,
+      "loss": 1.1057415008544922,
+      "mean_token_accuracy": 0.7461765056848526,
+      "num_tokens": 851807.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.1612900688499213,
+      "epoch": 0.19291718340912223,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.00018672129471337568,
+      "loss": 1.1313108062744142,
+      "mean_token_accuracy": 0.7447272512316704,
+      "num_tokens": 998421.0,
+      "step": 175
+    },
+    {
+      "entropy": 1.0649858928844333,
+      "epoch": 0.22047678103899684,
+      "grad_norm": 0.11328125,
+      "learning_rate": 0.00018193794979598656,
+      "loss": 1.0393009185791016,
+      "mean_token_accuracy": 0.763860610127449,
+      "num_tokens": 1141761.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8765474074520171,
+      "epoch": 0.24803637866887143,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 0.00017650235919998232,
+      "loss": 0.8135224914550782,
+      "mean_token_accuracy": 0.807485072016716,
+      "num_tokens": 1286611.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.8536889077164233,
+      "epoch": 0.27559597629874605,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00017045779152661297,
+      "loss": 0.8201860809326171,
+      "mean_token_accuracy": 0.8146287898719311,
+      "num_tokens": 1428015.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8703145318105817,
+      "epoch": 0.30315557392862064,
+      "grad_norm": 0.09765625,
+      "learning_rate": 0.00016385236298032183,
+      "loss": 0.815809326171875,
+      "mean_token_accuracy": 0.8103299827873707,
+      "num_tokens": 1574815.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.8991702864505351,
+      "epoch": 0.3307151715584952,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00015673865435224962,
+      "loss": 0.8489224243164063,
+      "mean_token_accuracy": 0.8056490634381771,
+      "num_tokens": 1717330.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7706374152004719,
+      "epoch": 0.35827476918836987,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 0.0001491732924645604,
+      "loss": 0.7274211883544922,
+      "mean_token_accuracy": 0.8297103045880795,
+      "num_tokens": 1859716.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.7342993662878871,
+      "epoch": 0.38583436681824446,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 0.00014121649940739301,
+      "loss": 0.7029119110107422,
+      "mean_token_accuracy": 0.8427872517704964,
+      "num_tokens": 2005201.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.7452906335704028,
+      "epoch": 0.41339396444811904,
+      "grad_norm": 0.1279296875,
+      "learning_rate": 0.00013293161315661931,
+      "loss": 0.7123774719238282,
+      "mean_token_accuracy": 0.8400052092969418,
+      "num_tokens": 2143419.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.6938006362970919,
+      "epoch": 0.4409535620779937,
+      "grad_norm": 0.1181640625,
+      "learning_rate": 0.00012438458338840706,
+      "loss": 0.6549488830566407,
+      "mean_token_accuracy": 0.8493785254657269,
+      "num_tokens": 2288125.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7443565137218684,
+      "epoch": 0.4685131597078683,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.6924254608154297,
+      "mean_token_accuracy": 0.8412553237378597,
+      "num_tokens": 2431404.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.645295873908326,
+      "epoch": 0.49607275733774286,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00010677778404380643,
+      "loss": 0.6191695022583008,
+      "mean_token_accuracy": 0.8578527195751667,
+      "num_tokens": 2571370.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6608448463864625,
+      "epoch": 0.5236323549676175,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 9.78581688014642e-05,
+      "loss": 0.6262045669555664,
+      "mean_token_accuracy": 0.856816074848175,
+      "num_tokens": 2714312.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.5949629322066903,
+      "epoch": 0.5511919525974921,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 8.895560304775387e-05,
+      "loss": 0.54037109375,
+      "mean_token_accuracy": 0.8706019401550293,
+      "num_tokens": 2850910.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7224912867229432,
+      "epoch": 0.5787515502273667,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 8.014095333542548e-05,
+      "loss": 0.7142529296875,
+      "mean_token_accuracy": 0.8413439232110977,
+      "num_tokens": 2999359.0,
+      "step": 525
+    },
+    {
+      "entropy": 0.7125124373659492,
+      "epoch": 0.6063111478572413,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 7.148438638451144e-05,
+      "loss": 0.6760162353515625,
+      "mean_token_accuracy": 0.8475173614919186,
+      "num_tokens": 3139525.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6205505744647235,
+      "epoch": 0.6338707454871159,
+      "grad_norm": 0.11669921875,
+      "learning_rate": 6.305481053845261e-05,
+      "loss": 0.6042692947387696,
+      "mean_token_accuracy": 0.8661120194196701,
+      "num_tokens": 3283709.0,
+      "step": 575
+    },
+    {
+      "entropy": 0.6542045682761818,
+      "epoch": 0.6614303431169904,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 5.4919327237202546e-05,
+      "loss": 0.6398629379272461,
+      "mean_token_accuracy": 0.8612794525921345,
+      "num_tokens": 3427270.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5916300803422928,
+      "epoch": 0.6889899407468651,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 4.714269687371581e-05,
+      "loss": 0.5418794250488281,
+      "mean_token_accuracy": 0.8722360366582871,
+      "num_tokens": 3568256.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.5375593125354499,
+      "epoch": 0.7165495383767397,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 3.978682328573063e-05,
+      "loss": 0.5057635116577148,
+      "mean_token_accuracy": 0.8873542912304402,
+      "num_tokens": 3709441.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6055101400800049,
+      "epoch": 0.7441091360066143,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 3.291026098641397e-05,
+      "loss": 0.5837324905395508,
+      "mean_token_accuracy": 0.8686715243756771,
+      "num_tokens": 3858373.0,
+      "step": 675
+    },
+    {
+      "entropy": 0.509702676339075,
+      "epoch": 0.7716687336364889,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 2.6567749056431467e-05,
+      "loss": 0.46534008026123047,
+      "mean_token_accuracy": 0.8935040257871151,
+      "num_tokens": 3998452.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6449116668663919,
+      "epoch": 0.7992283312663635,
+      "grad_norm": 0.08203125,
+      "learning_rate": 2.0809775407772503e-05,
+      "loss": 0.5881856155395507,
+      "mean_token_accuracy": 0.8635844677686692,
+      "num_tokens": 4139915.0,
+      "step": 725
+    },
+    {
+      "entropy": 0.575501447301358,
+      "epoch": 0.8267879288962381,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 1.5682174887895083e-05,
+      "loss": 0.5590339279174805,
+      "mean_token_accuracy": 0.8768933260440827,
+      "num_tokens": 4282188.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.5558508610818536,
+      "epoch": 0.8543475265261127,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 1.122576442337696e-05,
+      "loss": 0.5243261337280274,
+      "mean_token_accuracy": 0.8842477214336395,
+      "num_tokens": 4427400.0,
+      "step": 775
+    },
+    {
+      "entropy": 0.688429104378447,
+      "epoch": 0.8819071241559874,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 7.476018107417371e-06,
+      "loss": 0.623744010925293,
+      "mean_token_accuracy": 0.8572955358028412,
+      "num_tokens": 4567225.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5038102147076279,
+      "epoch": 0.909466721785862,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 4.462784817570331e-06,
+      "loss": 0.47533946990966797,
+      "mean_token_accuracy": 0.8936529903113842,
+      "num_tokens": 4709595.0,
+      "step": 825
+    },
+    {
+      "entropy": 0.5760456078313291,
+      "epoch": 0.9370263194157366,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 2.2100506115399377e-06,
+      "loss": 0.5174454879760743,
+      "mean_token_accuracy": 0.8788142189383507,
+      "num_tokens": 4853579.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5857030095718802,
+      "epoch": 0.9645859170456111,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 7.357477924239797e-07,
+      "loss": 0.5400792694091797,
+      "mean_token_accuracy": 0.8724570070207119,
+      "num_tokens": 4994351.0,
+      "step": 875
+    },
+    {
+      "entropy": 0.47729114089161156,
+      "epoch": 0.9921455146754857,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 5.161216329209184e-08,
+      "loss": 0.4375122833251953,
+      "mean_token_accuracy": 0.9014435681700707,
+      "num_tokens": 5136659.0,
+      "step": 900
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.209155120942981e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-908/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f4507cae4004563bb50348f5e858baf28582cc170d5db69d774cd7b166a1b0
+size 5649

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f4507cae4004563bb50348f5e858baf28582cc170d5db69d774cd7b166a1b0
+size 5649