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-740/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: Wireless-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 Wireless-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": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "gate_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
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb71a7a980c85a2b5dbab6ef5eb8f5235dc88280370a018a6fbde42f4f2246b
+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": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "gate_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
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5c6fa0e162bfd0b7048a94b29f51fbb6a0bfb415fe8fbbfe5fc1b477b7fd6e
+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:b1443ccbdf86836a1a57b06a58098a98cefdadeaee3daec4c8c9538cb1916dca
+size 161810747

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64825d10071b6e360fbd75b7733befa195070ae1cd13f207dd9f680acf703fc
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46acd56dbda9f929a00cf625ec4805fd02f41c8c682e52d50a8718cf98d26cfd
+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": 0.6763611768684478,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.810372607409954,
+      "epoch": 0.033818058843422386,
+      "grad_norm": 0.03564453125,
+      "learning_rate": 0.00019999904008949706,
+      "loss": 1.961472625732422,
+      "mean_token_accuracy": 0.5825667985156179,
+      "num_tokens": 156162.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.630317051112652,
+      "epoch": 0.06763611768684477,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00019935180094484163,
+      "loss": 1.5934637451171876,
+      "mean_token_accuracy": 0.6405555133521557,
+      "num_tokens": 314902.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.4665888720750808,
+      "epoch": 0.10145417653026716,
+      "grad_norm": 0.1220703125,
+      "learning_rate": 0.00019751364095427692,
+      "loss": 1.430908203125,
+      "mean_token_accuracy": 0.6695231589674949,
+      "num_tokens": 466632.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.392833354473114,
+      "epoch": 0.13527223537368954,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.00019450659397154355,
+      "loss": 1.3299276733398437,
+      "mean_token_accuracy": 0.6912748428061605,
+      "num_tokens": 624850.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.1405542536824942,
+      "epoch": 0.16909029421711194,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.00019036670519061188,
+      "loss": 1.0945913696289062,
+      "mean_token_accuracy": 0.7419995337724685,
+      "num_tokens": 781370.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.0725987593457103,
+      "epoch": 0.2029083530605343,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 0.0001851435990752769,
+      "loss": 1.0093214416503906,
+      "mean_token_accuracy": 0.7651712036132813,
+      "num_tokens": 938626.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.9529129752889276,
+      "epoch": 0.2367264119039567,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 0.0001788998845153021,
+      "loss": 0.8964275360107422,
+      "mean_token_accuracy": 0.7902284222841263,
+      "num_tokens": 1094352.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.862411651480943,
+      "epoch": 0.2705444707473791,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00017171040433945005,
+      "loss": 0.8004817199707032,
+      "mean_token_accuracy": 0.8113848954439163,
+      "num_tokens": 1251490.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7631507751531899,
+      "epoch": 0.3043625295908015,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016366133818141893,
+      "loss": 0.7039064025878906,
+      "mean_token_accuracy": 0.8357413372397423,
+      "num_tokens": 1406770.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.7098334492836148,
+      "epoch": 0.3381805884342239,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 0.0001548491694525464,
+      "loss": 0.6646959686279297,
+      "mean_token_accuracy": 0.8501214118301869,
+      "num_tokens": 1561213.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.7675167324021459,
+      "epoch": 0.37199864727764625,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.00014537952880408473,
+      "loss": 0.71765869140625,
+      "mean_token_accuracy": 0.835702428817749,
+      "num_tokens": 1724371.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.6311481145210565,
+      "epoch": 0.4058167061210686,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00013536592794235696,
+      "loss": 0.5955865478515625,
+      "mean_token_accuracy": 0.8682514359802007,
+      "num_tokens": 1885062.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7570231725927442,
+      "epoch": 0.43963476496449105,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.00012492839897443553,
+      "loss": 0.7146268463134766,
+      "mean_token_accuracy": 0.8396708873659372,
+      "num_tokens": 2043297.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.5249405995476991,
+      "epoch": 0.4734528238079134,
+      "grad_norm": 0.078125,
+      "learning_rate": 0.00011419205559437998,
+      "loss": 0.49004329681396486,
+      "mean_token_accuracy": 0.8892295673489571,
+      "num_tokens": 2196510.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.6064728916622698,
+      "epoch": 0.5072708826513358,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 0.00010328559335696188,
+      "loss": 0.5641261291503906,
+      "mean_token_accuracy": 0.8721542170643807,
+      "num_tokens": 2354986.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.5784782155323773,
+      "epoch": 0.5410889414947582,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 9.233974701595655e-05,
+      "loss": 0.5496908950805665,
+      "mean_token_accuracy": 0.8779391979053617,
+      "num_tokens": 2515773.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5494727499317378,
+      "epoch": 0.5749070003381805,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 8.14857234187453e-05,
+      "loss": 0.5182221984863281,
+      "mean_token_accuracy": 0.8837397874891758,
+      "num_tokens": 2674952.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.5801290932204575,
+      "epoch": 0.608725059181603,
+      "grad_norm": 0.091796875,
+      "learning_rate": 7.08536287419749e-05,
+      "loss": 0.5686647033691407,
+      "mean_token_accuracy": 0.8799975875392556,
+      "num_tokens": 2830234.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.48558603684417906,
+      "epoch": 0.6425431180250254,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 6.0570908920855706e-05,
+      "loss": 0.42860363006591795,
+      "mean_token_accuracy": 0.9008280988037586,
+      "num_tokens": 2989837.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.4568167580384761,
+      "epoch": 0.6763611768684478,
+      "grad_norm": 0.095703125,
+      "learning_rate": 5.076082196652754e-05,
+      "loss": 0.45085529327392576,
+      "mean_token_accuracy": 0.9038965445756912,
+      "num_tokens": 3143012.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 740,
+  "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": 1.3409954843692646e+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:d91d0617bbc00237ab4e5b0661f2b8c1a40a7c5da784b1ce1cf8063d9f5960de
+size 5649

checkpoint-740/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-740/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": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "gate_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
+}

checkpoint-740/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb71a7a980c85a2b5dbab6ef5eb8f5235dc88280370a018a6fbde42f4f2246b
+size 80792880

checkpoint-740/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-740/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218212761efeefb4f33b1fe7a73d1e6cd71f8e93a5f24e5720885a2d872a5bf8
+size 161810747

checkpoint-740/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e774cacc1f67054be341f8ea74fa8fc9188b80c72365e3515cafbda108c0b338
+size 14645

checkpoint-740/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb91e8b0947350fc0ab8199f236dd65adf237c65bdad561c4c8e85ffb027deb
+size 1465

checkpoint-740/tokenizer.json

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

checkpoint-740/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-740/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": 740,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.810372607409954,
+      "epoch": 0.033818058843422386,
+      "grad_norm": 0.03564453125,
+      "learning_rate": 0.00019999904008949706,
+      "loss": 1.961472625732422,
+      "mean_token_accuracy": 0.5825667985156179,
+      "num_tokens": 156162.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.630317051112652,
+      "epoch": 0.06763611768684477,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00019935180094484163,
+      "loss": 1.5934637451171876,
+      "mean_token_accuracy": 0.6405555133521557,
+      "num_tokens": 314902.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.4665888720750808,
+      "epoch": 0.10145417653026716,
+      "grad_norm": 0.1220703125,
+      "learning_rate": 0.00019751364095427692,
+      "loss": 1.430908203125,
+      "mean_token_accuracy": 0.6695231589674949,
+      "num_tokens": 466632.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.392833354473114,
+      "epoch": 0.13527223537368954,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.00019450659397154355,
+      "loss": 1.3299276733398437,
+      "mean_token_accuracy": 0.6912748428061605,
+      "num_tokens": 624850.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.1405542536824942,
+      "epoch": 0.16909029421711194,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.00019036670519061188,
+      "loss": 1.0945913696289062,
+      "mean_token_accuracy": 0.7419995337724685,
+      "num_tokens": 781370.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.0725987593457103,
+      "epoch": 0.2029083530605343,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 0.0001851435990752769,
+      "loss": 1.0093214416503906,
+      "mean_token_accuracy": 0.7651712036132813,
+      "num_tokens": 938626.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.9529129752889276,
+      "epoch": 0.2367264119039567,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 0.0001788998845153021,
+      "loss": 0.8964275360107422,
+      "mean_token_accuracy": 0.7902284222841263,
+      "num_tokens": 1094352.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.862411651480943,
+      "epoch": 0.2705444707473791,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00017171040433945005,
+      "loss": 0.8004817199707032,
+      "mean_token_accuracy": 0.8113848954439163,
+      "num_tokens": 1251490.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7631507751531899,
+      "epoch": 0.3043625295908015,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016366133818141893,
+      "loss": 0.7039064025878906,
+      "mean_token_accuracy": 0.8357413372397423,
+      "num_tokens": 1406770.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.7098334492836148,
+      "epoch": 0.3381805884342239,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 0.0001548491694525464,
+      "loss": 0.6646959686279297,
+      "mean_token_accuracy": 0.8501214118301869,
+      "num_tokens": 1561213.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.7675167324021459,
+      "epoch": 0.37199864727764625,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.00014537952880408473,
+      "loss": 0.71765869140625,
+      "mean_token_accuracy": 0.835702428817749,
+      "num_tokens": 1724371.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.6311481145210565,
+      "epoch": 0.4058167061210686,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00013536592794235696,
+      "loss": 0.5955865478515625,
+      "mean_token_accuracy": 0.8682514359802007,
+      "num_tokens": 1885062.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7570231725927442,
+      "epoch": 0.43963476496449105,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.00012492839897443553,
+      "loss": 0.7146268463134766,
+      "mean_token_accuracy": 0.8396708873659372,
+      "num_tokens": 2043297.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.5249405995476991,
+      "epoch": 0.4734528238079134,
+      "grad_norm": 0.078125,
+      "learning_rate": 0.00011419205559437998,
+      "loss": 0.49004329681396486,
+      "mean_token_accuracy": 0.8892295673489571,
+      "num_tokens": 2196510.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.6064728916622698,
+      "epoch": 0.5072708826513358,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 0.00010328559335696188,
+      "loss": 0.5641261291503906,
+      "mean_token_accuracy": 0.8721542170643807,
+      "num_tokens": 2354986.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.5784782155323773,
+      "epoch": 0.5410889414947582,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 9.233974701595655e-05,
+      "loss": 0.5496908950805665,
+      "mean_token_accuracy": 0.8779391979053617,
+      "num_tokens": 2515773.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5494727499317378,
+      "epoch": 0.5749070003381805,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 8.14857234187453e-05,
+      "loss": 0.5182221984863281,
+      "mean_token_accuracy": 0.8837397874891758,
+      "num_tokens": 2674952.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.5801290932204575,
+      "epoch": 0.608725059181603,
+      "grad_norm": 0.091796875,
+      "learning_rate": 7.08536287419749e-05,
+      "loss": 0.5686647033691407,
+      "mean_token_accuracy": 0.8799975875392556,
+      "num_tokens": 2830234.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.48558603684417906,
+      "epoch": 0.6425431180250254,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 6.0570908920855706e-05,
+      "loss": 0.42860363006591795,
+      "mean_token_accuracy": 0.9008280988037586,
+      "num_tokens": 2989837.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.4568167580384761,
+      "epoch": 0.6763611768684478,
+      "grad_norm": 0.095703125,
+      "learning_rate": 5.076082196652754e-05,
+      "loss": 0.45085529327392576,
+      "mean_token_accuracy": 0.9038965445756912,
+      "num_tokens": 3143012.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.44007344283163546,
+      "epoch": 0.7101792357118701,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 4.15409604836838e-05,
+      "loss": 0.41196117401123045,
+      "mean_token_accuracy": 0.9095691731572151,
+      "num_tokens": 3300477.0,
+      "step": 525
+    },
+    {
+      "entropy": 0.4962937253713608,
+      "epoch": 0.7439972945552925,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 3.3021842098898934e-05,
+      "loss": 0.4741514205932617,
+      "mean_token_accuracy": 0.896233549118042,
+      "num_tokens": 3454477.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.45510641247965394,
+      "epoch": 0.7778153533987149,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 2.530558469606351e-05,
+      "loss": 0.4256900787353516,
+      "mean_token_accuracy": 0.9090374359488487,
+      "num_tokens": 3614381.0,
+      "step": 575
+    },
+    {
+      "entropy": 0.4509261836577207,
+      "epoch": 0.8116334122421373,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 1.8484682338758152e-05,
+      "loss": 0.4140806198120117,
+      "mean_token_accuracy": 0.9066468042135238,
+      "num_tokens": 3770302.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.48186022156849506,
+      "epoch": 0.8454514710855597,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 1.2640896552470794e-05,
+      "loss": 0.4636331939697266,
+      "mean_token_accuracy": 0.9016842505335808,
+      "num_tokens": 3929478.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.45708779353648427,
+      "epoch": 0.8792695299289821,
+      "grad_norm": 0.0125732421875,
+      "learning_rate": 7.844276256755346e-06,
+      "loss": 0.45078208923339846,
+      "mean_token_accuracy": 0.9030292834341526,
+      "num_tokens": 4084974.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.5012604260630905,
+      "epoch": 0.9130875887724045,
+      "grad_norm": 0.072265625,
+      "learning_rate": 4.152318095313778e-06,
+      "loss": 0.47621334075927735,
+      "mean_token_accuracy": 0.8943454670906067,
+      "num_tokens": 4246619.0,
+      "step": 675
+    },
+    {
+      "entropy": 0.41868842981755733,
+      "epoch": 0.9469056476158269,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 1.609277229047801e-06,
+      "loss": 0.38456172943115235,
+      "mean_token_accuracy": 0.9145496153831482,
+      "num_tokens": 4405485.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.4935927293263376,
+      "epoch": 0.9807237064592492,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 2.4563685353949925e-07,
+      "loss": 0.47506561279296877,
+      "mean_token_accuracy": 0.8976721769571304,
+      "num_tokens": 4564678.0,
+      "step": 725
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 740,
+  "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": 1.9858744653595546e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-740/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d91d0617bbc00237ab4e5b0661f2b8c1a40a7c5da784b1ce1cf8063d9f5960de
+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:d91d0617bbc00237ab4e5b0661f2b8c1a40a7c5da784b1ce1cf8063d9f5960de
+size 5649