Upload TribalKnowledge-Qwen2.5-7B from TribalKnowledge-Qwen2.5-7B-output

.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-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1253/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: TribalKnowledge-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 TribalKnowledge-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": 128,
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_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 sha256:67822e201676faf4acc202917d7ce8c9b3716edad0425b94f91493699ce15bc9
+size 323014560

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-1000/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-1000/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": 128,
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_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-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e65ab5b12a04e746fe5af69338b8a5f1d0f5ad713d400ad9103ddeda56b1b1
+size 323014560

checkpoint-1000/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-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ab8881ad552c708f05b1df15756dbbf53c915cae7be43bad0ab241504e5c73
+size 646253883

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5ca7bc203b8fd40a650d807ec33b2c65f4b1dcf8365628c3f314800e33c39d
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9061ebd756ba5e23b94e9209f0337bed8e63f3ecfb6d09980ac886d6bccf3bc
+size 1465

checkpoint-1000/tokenizer.json

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

checkpoint-1000/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-1000/trainer_state.json

@@ -0,0 +1,434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7986821744122199,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.306920379027724,
+      "epoch": 0.019967054360305495,
+      "grad_norm": 0.03515625,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 2.448968811035156,
+      "mean_token_accuracy": 0.48531667422503233,
+      "num_tokens": 122713.0,
+      "step": 25
+    },
+    {
+      "entropy": 2.053416675031185,
+      "epoch": 0.03993410872061099,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.0001999595542133758,
+      "loss": 2.042926483154297,
+      "mean_token_accuracy": 0.5536270077899098,
+      "num_tokens": 245834.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.019237674474716,
+      "epoch": 0.05990116308091649,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 0.00019956707906498044,
+      "loss": 2.0004498291015627,
+      "mean_token_accuracy": 0.562225787602365,
+      "num_tokens": 367174.0,
+      "step": 75
+    },
+    {
+      "entropy": 2.014568568766117,
+      "epoch": 0.07986821744122198,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00019875870121543717,
+      "loss": 1.9949961853027345,
+      "mean_token_accuracy": 0.5627686691284179,
+      "num_tokens": 487834.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.9470337933301927,
+      "epoch": 0.09983527180152749,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00019753779734842827,
+      "loss": 1.9355754089355468,
+      "mean_token_accuracy": 0.5725972962379455,
+      "num_tokens": 611352.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.9996179219335317,
+      "epoch": 0.11980232616183298,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.0001959094673144354,
+      "loss": 1.9678744506835937,
+      "mean_token_accuracy": 0.5630620580911636,
+      "num_tokens": 735053.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.0072034925222395,
+      "epoch": 0.13976938052213847,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.00019388051282810022,
+      "loss": 1.9737957763671874,
+      "mean_token_accuracy": 0.5624778818339109,
+      "num_tokens": 855860.0,
+      "step": 175
+    },
+    {
+      "entropy": 1.9725533105432986,
+      "epoch": 0.15973643488244396,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.0001914594090567099,
+      "loss": 1.9277491760253906,
+      "mean_token_accuracy": 0.5647629579156637,
+      "num_tokens": 977334.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.9535374976694584,
+      "epoch": 0.17970348924274945,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.00018865626921848615,
+      "loss": 1.9351695251464844,
+      "mean_token_accuracy": 0.5722655826061964,
+      "num_tokens": 1092583.0,
+      "step": 225
+    },
+    {
+      "entropy": 1.9489152195304633,
+      "epoch": 0.19967054360305497,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 0.0001854828023385541,
+      "loss": 1.9120469665527344,
+      "mean_token_accuracy": 0.5757150813564658,
+      "num_tokens": 1212652.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.997425957247615,
+      "epoch": 0.21963759796336046,
+      "grad_norm": 0.0235595703125,
+      "learning_rate": 0.00018195226433904957,
+      "loss": 1.9783148193359374,
+      "mean_token_accuracy": 0.566706589795649,
+      "num_tokens": 1332055.0,
+      "step": 275
+    },
+    {
+      "entropy": 1.9235536295175553,
+      "epoch": 0.23960465232366596,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00017807940266766593,
+      "loss": 1.9035797119140625,
+      "mean_token_accuracy": 0.5777761967480183,
+      "num_tokens": 1452841.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.9555407621711494,
+      "epoch": 0.25957170668397145,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00017388039469593428,
+      "loss": 1.922522735595703,
+      "mean_token_accuracy": 0.573435662984848,
+      "num_tokens": 1572803.0,
+      "step": 325
+    },
+    {
+      "entropy": 1.9522953194752335,
+      "epoch": 0.27953876104427694,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00016937278014455336,
+      "loss": 1.914853057861328,
+      "mean_token_accuracy": 0.5744891692698002,
+      "num_tokens": 1697419.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.895245919264853,
+      "epoch": 0.29950581540458243,
+      "grad_norm": 0.026123046875,
+      "learning_rate": 0.00016457538781803623,
+      "loss": 1.8297265625,
+      "mean_token_accuracy": 0.5865043254941702,
+      "num_tokens": 1819231.0,
+      "step": 375
+    },
+    {
+      "entropy": 1.9276008826121689,
+      "epoch": 0.3194728697648879,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00015950825695471146,
+      "loss": 1.8969316101074218,
+      "mean_token_accuracy": 0.579356978982687,
+      "num_tokens": 1941170.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.9401621558889746,
+      "epoch": 0.3394399241251934,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.0001541925535206084,
+      "loss": 1.9100968933105469,
+      "mean_token_accuracy": 0.5764700850099325,
+      "num_tokens": 2065882.0,
+      "step": 425
+    },
+    {
+      "entropy": 1.9133401766419411,
+      "epoch": 0.3594069784854989,
+      "grad_norm": 0.0303955078125,
+      "learning_rate": 0.000148650481796876,
+      "loss": 1.8422721862792968,
+      "mean_token_accuracy": 0.5874501725286245,
+      "num_tokens": 2185024.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.9126300086826087,
+      "epoch": 0.3793740328458044,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00014290519163004495,
+      "loss": 1.8789381408691406,
+      "mean_token_accuracy": 0.5848022982478142,
+      "num_tokens": 2299587.0,
+      "step": 475
+    },
+    {
+      "entropy": 1.909918104019016,
+      "epoch": 0.39934108720610995,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.0001369806817325581,
+      "loss": 1.8951301574707031,
+      "mean_token_accuracy": 0.582027070298791,
+      "num_tokens": 2421897.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.9182585052400827,
+      "epoch": 0.41930814156641544,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.8786566162109375,
+      "mean_token_accuracy": 0.5797786585241557,
+      "num_tokens": 2544369.0,
+      "step": 525
+    },
+    {
+      "entropy": 1.8837098168581725,
+      "epoch": 0.43927519592672093,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.00012469363732622296,
+      "loss": 1.8448243713378907,
+      "mean_token_accuracy": 0.5849873025715351,
+      "num_tokens": 2671654.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.8790070757828652,
+      "epoch": 0.4592422502870264,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00011838242716077917,
+      "loss": 1.8447459411621094,
+      "mean_token_accuracy": 0.5876961750537157,
+      "num_tokens": 2796033.0,
+      "step": 575
+    },
+    {
+      "entropy": 1.8867588526010513,
+      "epoch": 0.4792093046473319,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.00011199443156402998,
+      "loss": 1.835140380859375,
+      "mean_token_accuracy": 0.5846484461426735,
+      "num_tokens": 2917243.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.9055894463136793,
+      "epoch": 0.4991763590076374,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 0.00010555633390008086,
+      "loss": 1.858441619873047,
+      "mean_token_accuracy": 0.5845886848121882,
+      "num_tokens": 3042703.0,
+      "step": 625
+    },
+    {
+      "entropy": 1.9573378081992268,
+      "epoch": 0.5191434133679429,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 9.909502681491316e-05,
+      "loss": 1.8958790588378907,
+      "mean_token_accuracy": 0.5772438555955887,
+      "num_tokens": 3160162.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.8727275183051824,
+      "epoch": 0.5391104677282484,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 9.263749990282754e-05,
+      "loss": 1.8269801330566406,
+      "mean_token_accuracy": 0.5881718883663416,
+      "num_tokens": 3285704.0,
+      "step": 675
+    },
+    {
+      "entropy": 1.871655127387494,
+      "epoch": 0.5590775220885539,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 8.621072696792363e-05,
+      "loss": 1.8388119506835938,
+      "mean_token_accuracy": 0.5867326802760363,
+      "num_tokens": 3410119.0,
+      "step": 700
+    },
+    {
+      "entropy": 1.8627979960665106,
+      "epoch": 0.5790445764488594,
+      "grad_norm": 0.035888671875,
+      "learning_rate": 7.984155335153711e-05,
+      "loss": 1.799385986328125,
+      "mean_token_accuracy": 0.5873606249690055,
+      "num_tokens": 3533765.0,
+      "step": 725
+    },
+    {
+      "entropy": 1.8317018933594227,
+      "epoch": 0.5990116308091649,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 7.35565837962798e-05,
+      "loss": 1.7772984313964844,
+      "mean_token_accuracy": 0.5965435421466827,
+      "num_tokens": 3657321.0,
+      "step": 750
+    },
+    {
+      "entropy": 1.8882549648359417,
+      "epoch": 0.6189786851694704,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 6.738207131508735e-05,
+      "loss": 1.8385765075683593,
+      "mean_token_accuracy": 0.59088682141155,
+      "num_tokens": 3779575.0,
+      "step": 775
+    },
+    {
+      "entropy": 1.8342267361842095,
+      "epoch": 0.6389457395297758,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 6.134380752948085e-05,
+      "loss": 1.800379180908203,
+      "mean_token_accuracy": 0.5952950984984636,
+      "num_tokens": 3896543.0,
+      "step": 800
+    },
+    {
+      "entropy": 1.873757717087865,
+      "epoch": 0.6589127938900814,
+      "grad_norm": 0.03564453125,
+      "learning_rate": 5.546701493511106e-05,
+      "loss": 1.8183651733398438,
+      "mean_token_accuracy": 0.5902918418496848,
+      "num_tokens": 4018098.0,
+      "step": 825
+    },
+    {
+      "entropy": 1.83077443132177,
+      "epoch": 0.6788798482503868,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 4.977624154460464e-05,
+      "loss": 1.7461175537109375,
+      "mean_token_accuracy": 0.598720720410347,
+      "num_tokens": 4141174.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.918299620486796,
+      "epoch": 0.6988469026106924,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 4.42952583478004e-05,
+      "loss": 1.9020709228515624,
+      "mean_token_accuracy": 0.5798033401742577,
+      "num_tokens": 4259185.0,
+      "step": 875
+    },
+    {
+      "entropy": 1.8444363391213119,
+      "epoch": 0.7188139569709978,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 3.904696001769571e-05,
+      "loss": 1.7869160461425782,
+      "mean_token_accuracy": 0.5964432079344988,
+      "num_tokens": 4377724.0,
+      "step": 900
+    },
+    {
+      "entropy": 1.8295260372944175,
+      "epoch": 0.7387810113313034,
+      "grad_norm": 0.031982421875,
+      "learning_rate": 3.4053269276865285e-05,
+      "loss": 1.778699951171875,
+      "mean_token_accuracy": 0.6018728485703468,
+      "num_tokens": 4497691.0,
+      "step": 925
+    },
+    {
+      "entropy": 1.8099911727011204,
+      "epoch": 0.7587480656916088,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 2.9335045323824496e-05,
+      "loss": 1.7513389587402344,
+      "mean_token_accuracy": 0.6039503507316113,
+      "num_tokens": 4616131.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.8742087873071431,
+      "epoch": 0.7787151200519143,
+      "grad_norm": 0.033203125,
+      "learning_rate": 2.491199670185008e-05,
+      "loss": 1.7982223510742188,
+      "mean_token_accuracy": 0.5908738762140274,
+      "num_tokens": 4737443.0,
+      "step": 975
+    },
+    {
+      "entropy": 1.869517589211464,
+      "epoch": 0.7986821744122199,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 2.0802598974215226e-05,
+      "loss": 1.8264849853515626,
+      "mean_token_accuracy": 0.5888447714596987,
+      "num_tokens": 4858100.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1253,
+  "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": 2.10805585396224e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a25a38f0a1a1ae775e5c8899125798a7e119a818cb9e0858ea862fa1e8abf29
+size 5649

checkpoint-1253/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-1253/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": 128,
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_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-1253/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67822e201676faf4acc202917d7ce8c9b3716edad0425b94f91493699ce15bc9
+size 323014560

checkpoint-1253/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-1253/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca11776b582823888c00b27cb1044cd26740a0a55e4b6cd074738a174896002
+size 646253883

checkpoint-1253/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f1b140ec912d50c220a1e0d28e24528c45699ad80f3bc372d3c94daad4775b
+size 14645

checkpoint-1253/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c088bba0ea5343d10ddb4d7baa91358395d41d1f46ecab95a94aeae93a130c31
+size 1465

checkpoint-1253/tokenizer.json

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

checkpoint-1253/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-1253/trainer_state.json

@@ -0,0 +1,534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1253,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.306920379027724,
+      "epoch": 0.019967054360305495,
+      "grad_norm": 0.03515625,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 2.448968811035156,
+      "mean_token_accuracy": 0.48531667422503233,
+      "num_tokens": 122713.0,
+      "step": 25
+    },
+    {
+      "entropy": 2.053416675031185,
+      "epoch": 0.03993410872061099,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.0001999595542133758,
+      "loss": 2.042926483154297,
+      "mean_token_accuracy": 0.5536270077899098,
+      "num_tokens": 245834.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.019237674474716,
+      "epoch": 0.05990116308091649,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 0.00019956707906498044,
+      "loss": 2.0004498291015627,
+      "mean_token_accuracy": 0.562225787602365,
+      "num_tokens": 367174.0,
+      "step": 75
+    },
+    {
+      "entropy": 2.014568568766117,
+      "epoch": 0.07986821744122198,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00019875870121543717,
+      "loss": 1.9949961853027345,
+      "mean_token_accuracy": 0.5627686691284179,
+      "num_tokens": 487834.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.9470337933301927,
+      "epoch": 0.09983527180152749,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00019753779734842827,
+      "loss": 1.9355754089355468,
+      "mean_token_accuracy": 0.5725972962379455,
+      "num_tokens": 611352.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.9996179219335317,
+      "epoch": 0.11980232616183298,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.0001959094673144354,
+      "loss": 1.9678744506835937,
+      "mean_token_accuracy": 0.5630620580911636,
+      "num_tokens": 735053.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.0072034925222395,
+      "epoch": 0.13976938052213847,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.00019388051282810022,
+      "loss": 1.9737957763671874,
+      "mean_token_accuracy": 0.5624778818339109,
+      "num_tokens": 855860.0,
+      "step": 175
+    },
+    {
+      "entropy": 1.9725533105432986,
+      "epoch": 0.15973643488244396,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.0001914594090567099,
+      "loss": 1.9277491760253906,
+      "mean_token_accuracy": 0.5647629579156637,
+      "num_tokens": 977334.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.9535374976694584,
+      "epoch": 0.17970348924274945,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.00018865626921848615,
+      "loss": 1.9351695251464844,
+      "mean_token_accuracy": 0.5722655826061964,
+      "num_tokens": 1092583.0,
+      "step": 225
+    },
+    {
+      "entropy": 1.9489152195304633,
+      "epoch": 0.19967054360305497,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 0.0001854828023385541,
+      "loss": 1.9120469665527344,
+      "mean_token_accuracy": 0.5757150813564658,
+      "num_tokens": 1212652.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.997425957247615,
+      "epoch": 0.21963759796336046,
+      "grad_norm": 0.0235595703125,
+      "learning_rate": 0.00018195226433904957,
+      "loss": 1.9783148193359374,
+      "mean_token_accuracy": 0.566706589795649,
+      "num_tokens": 1332055.0,
+      "step": 275
+    },
+    {
+      "entropy": 1.9235536295175553,
+      "epoch": 0.23960465232366596,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00017807940266766593,
+      "loss": 1.9035797119140625,
+      "mean_token_accuracy": 0.5777761967480183,
+      "num_tokens": 1452841.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.9555407621711494,
+      "epoch": 0.25957170668397145,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00017388039469593428,
+      "loss": 1.922522735595703,
+      "mean_token_accuracy": 0.573435662984848,
+      "num_tokens": 1572803.0,
+      "step": 325
+    },
+    {
+      "entropy": 1.9522953194752335,
+      "epoch": 0.27953876104427694,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00016937278014455336,
+      "loss": 1.914853057861328,
+      "mean_token_accuracy": 0.5744891692698002,
+      "num_tokens": 1697419.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.895245919264853,
+      "epoch": 0.29950581540458243,
+      "grad_norm": 0.026123046875,
+      "learning_rate": 0.00016457538781803623,
+      "loss": 1.8297265625,
+      "mean_token_accuracy": 0.5865043254941702,
+      "num_tokens": 1819231.0,
+      "step": 375
+    },
+    {
+      "entropy": 1.9276008826121689,
+      "epoch": 0.3194728697648879,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00015950825695471146,
+      "loss": 1.8969316101074218,
+      "mean_token_accuracy": 0.579356978982687,
+      "num_tokens": 1941170.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.9401621558889746,
+      "epoch": 0.3394399241251934,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.0001541925535206084,
+      "loss": 1.9100968933105469,
+      "mean_token_accuracy": 0.5764700850099325,
+      "num_tokens": 2065882.0,
+      "step": 425
+    },
+    {
+      "entropy": 1.9133401766419411,
+      "epoch": 0.3594069784854989,
+      "grad_norm": 0.0303955078125,
+      "learning_rate": 0.000148650481796876,
+      "loss": 1.8422721862792968,
+      "mean_token_accuracy": 0.5874501725286245,
+      "num_tokens": 2185024.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.9126300086826087,
+      "epoch": 0.3793740328458044,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00014290519163004495,
+      "loss": 1.8789381408691406,
+      "mean_token_accuracy": 0.5848022982478142,
+      "num_tokens": 2299587.0,
+      "step": 475
+    },
+    {
+      "entropy": 1.909918104019016,
+      "epoch": 0.39934108720610995,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.0001369806817325581,
+      "loss": 1.8951301574707031,
+      "mean_token_accuracy": 0.582027070298791,
+      "num_tokens": 2421897.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.9182585052400827,
+      "epoch": 0.41930814156641544,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.8786566162109375,
+      "mean_token_accuracy": 0.5797786585241557,
+      "num_tokens": 2544369.0,
+      "step": 525
+    },
+    {
+      "entropy": 1.8837098168581725,
+      "epoch": 0.43927519592672093,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.00012469363732622296,
+      "loss": 1.8448243713378907,
+      "mean_token_accuracy": 0.5849873025715351,
+      "num_tokens": 2671654.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.8790070757828652,
+      "epoch": 0.4592422502870264,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00011838242716077917,
+      "loss": 1.8447459411621094,
+      "mean_token_accuracy": 0.5876961750537157,
+      "num_tokens": 2796033.0,
+      "step": 575
+    },
+    {
+      "entropy": 1.8867588526010513,
+      "epoch": 0.4792093046473319,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.00011199443156402998,
+      "loss": 1.835140380859375,
+      "mean_token_accuracy": 0.5846484461426735,
+      "num_tokens": 2917243.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.9055894463136793,
+      "epoch": 0.4991763590076374,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 0.00010555633390008086,
+      "loss": 1.858441619873047,
+      "mean_token_accuracy": 0.5845886848121882,
+      "num_tokens": 3042703.0,
+      "step": 625
+    },
+    {
+      "entropy": 1.9573378081992268,
+      "epoch": 0.5191434133679429,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 9.909502681491316e-05,
+      "loss": 1.8958790588378907,
+      "mean_token_accuracy": 0.5772438555955887,
+      "num_tokens": 3160162.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.8727275183051824,
+      "epoch": 0.5391104677282484,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 9.263749990282754e-05,
+      "loss": 1.8269801330566406,
+      "mean_token_accuracy": 0.5881718883663416,
+      "num_tokens": 3285704.0,
+      "step": 675
+    },
+    {
+      "entropy": 1.871655127387494,
+      "epoch": 0.5590775220885539,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 8.621072696792363e-05,
+      "loss": 1.8388119506835938,
+      "mean_token_accuracy": 0.5867326802760363,
+      "num_tokens": 3410119.0,
+      "step": 700
+    },
+    {
+      "entropy": 1.8627979960665106,
+      "epoch": 0.5790445764488594,
+      "grad_norm": 0.035888671875,
+      "learning_rate": 7.984155335153711e-05,
+      "loss": 1.799385986328125,
+      "mean_token_accuracy": 0.5873606249690055,
+      "num_tokens": 3533765.0,
+      "step": 725
+    },
+    {
+      "entropy": 1.8317018933594227,
+      "epoch": 0.5990116308091649,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 7.35565837962798e-05,
+      "loss": 1.7772984313964844,
+      "mean_token_accuracy": 0.5965435421466827,
+      "num_tokens": 3657321.0,
+      "step": 750
+    },
+    {
+      "entropy": 1.8882549648359417,
+      "epoch": 0.6189786851694704,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 6.738207131508735e-05,
+      "loss": 1.8385765075683593,
+      "mean_token_accuracy": 0.59088682141155,
+      "num_tokens": 3779575.0,
+      "step": 775
+    },
+    {
+      "entropy": 1.8342267361842095,
+      "epoch": 0.6389457395297758,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 6.134380752948085e-05,
+      "loss": 1.800379180908203,
+      "mean_token_accuracy": 0.5952950984984636,
+      "num_tokens": 3896543.0,
+      "step": 800
+    },
+    {
+      "entropy": 1.873757717087865,
+      "epoch": 0.6589127938900814,
+      "grad_norm": 0.03564453125,
+      "learning_rate": 5.546701493511106e-05,
+      "loss": 1.8183651733398438,
+      "mean_token_accuracy": 0.5902918418496848,
+      "num_tokens": 4018098.0,
+      "step": 825
+    },
+    {
+      "entropy": 1.83077443132177,
+      "epoch": 0.6788798482503868,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 4.977624154460464e-05,
+      "loss": 1.7461175537109375,
+      "mean_token_accuracy": 0.598720720410347,
+      "num_tokens": 4141174.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.918299620486796,
+      "epoch": 0.6988469026106924,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 4.42952583478004e-05,
+      "loss": 1.9020709228515624,
+      "mean_token_accuracy": 0.5798033401742577,
+      "num_tokens": 4259185.0,
+      "step": 875
+    },
+    {
+      "entropy": 1.8444363391213119,
+      "epoch": 0.7188139569709978,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 3.904696001769571e-05,
+      "loss": 1.7869160461425782,
+      "mean_token_accuracy": 0.5964432079344988,
+      "num_tokens": 4377724.0,
+      "step": 900
+    },
+    {
+      "entropy": 1.8295260372944175,
+      "epoch": 0.7387810113313034,
+      "grad_norm": 0.031982421875,
+      "learning_rate": 3.4053269276865285e-05,
+      "loss": 1.778699951171875,
+      "mean_token_accuracy": 0.6018728485703468,
+      "num_tokens": 4497691.0,
+      "step": 925
+    },
+    {
+      "entropy": 1.8099911727011204,
+      "epoch": 0.7587480656916088,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 2.9335045323824496e-05,
+      "loss": 1.7513389587402344,
+      "mean_token_accuracy": 0.6039503507316113,
+      "num_tokens": 4616131.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.8742087873071431,
+      "epoch": 0.7787151200519143,
+      "grad_norm": 0.033203125,
+      "learning_rate": 2.491199670185008e-05,
+      "loss": 1.7982223510742188,
+      "mean_token_accuracy": 0.5908738762140274,
+      "num_tokens": 4737443.0,
+      "step": 975
+    },
+    {
+      "entropy": 1.869517589211464,
+      "epoch": 0.7986821744122199,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 2.0802598974215226e-05,
+      "loss": 1.8264849853515626,
+      "mean_token_accuracy": 0.5888447714596987,
+      "num_tokens": 4858100.0,
+      "step": 1000
+    },
+    {
+      "entropy": 1.844755928181112,
+      "epoch": 0.8186492287725253,
+      "grad_norm": 0.045654296875,
+      "learning_rate": 1.7024017549718275e-05,
+      "loss": 1.7819813537597655,
+      "mean_token_accuracy": 0.6003921093046665,
+      "num_tokens": 4975013.0,
+      "step": 1025
+    },
+    {
+      "entropy": 1.802000548671931,
+      "epoch": 0.8386162831328309,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 1.3592035980871953e-05,
+      "loss": 1.7438143920898437,
+      "mean_token_accuracy": 0.6064729103446007,
+      "num_tokens": 5097765.0,
+      "step": 1050
+    },
+    {
+      "entropy": 1.8947986670024692,
+      "epoch": 0.8585833374931363,
+      "grad_norm": 0.037841796875,
+      "learning_rate": 1.0520990034258726e-05,
+      "loss": 1.8379624938964845,
+      "mean_token_accuracy": 0.589176696240902,
+      "num_tokens": 5215823.0,
+      "step": 1075
+    },
+    {
+      "entropy": 1.7786260014213622,
+      "epoch": 0.8785503918534419,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 7.823707808448288e-06,
+      "loss": 1.7224624633789063,
+      "mean_token_accuracy": 0.606775107383728,
+      "num_tokens": 5338845.0,
+      "step": 1100
+    },
+    {
+      "entropy": 1.8222949595190585,
+      "epoch": 0.8985174462137473,
+      "grad_norm": 0.035400390625,
+      "learning_rate": 5.511456149611194e-06,
+      "loss": 1.7382611083984374,
+      "mean_token_accuracy": 0.6005137836188078,
+      "num_tokens": 5458318.0,
+      "step": 1125
+    },
+    {
+      "entropy": 1.8381199889071285,
+      "epoch": 0.9184845005740528,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 3.593893588656172e-06,
+      "loss": 1.809542694091797,
+      "mean_token_accuracy": 0.5936454942077398,
+      "num_tokens": 5584313.0,
+      "step": 1150
+    },
+    {
+      "entropy": 1.8231695614941419,
+      "epoch": 0.9384515549343583,
+      "grad_norm": 0.036376953125,
+      "learning_rate": 2.079029996478421e-06,
+      "loss": 1.7776606750488282,
+      "mean_token_accuracy": 0.5996202439069748,
+      "num_tokens": 5705797.0,
+      "step": 1175
+    },
+    {
+      "entropy": 1.8307033446803689,
+      "epoch": 0.9584186092946638,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 1.8075674438476563,
+      "mean_token_accuracy": 0.5957645285874605,
+      "num_tokens": 5820537.0,
+      "step": 1200
+    },
+    {
+      "entropy": 1.8334672911651433,
+      "epoch": 0.9783856636549693,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 2.8100217966149367e-07,
+      "loss": 1.8062632751464844,
+      "mean_token_accuracy": 0.5959254806488752,
+      "num_tokens": 5936413.0,
+      "step": 1225
+    },
+    {
+      "entropy": 1.8275573313236237,
+      "epoch": 0.9983527180152748,
+      "grad_norm": 0.029541015625,
+      "learning_rate": 5.348516070957654e-09,
+      "loss": 1.8030024719238282,
+      "mean_token_accuracy": 0.6040526380576193,
+      "num_tokens": 6054498.0,
+      "step": 1250
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1253,
+  "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": 2.631819711784704e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1253/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a25a38f0a1a1ae775e5c8899125798a7e119a818cb9e0858ea862fa1e8abf29
+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 sha256:8a25a38f0a1a1ae775e5c8899125798a7e119a818cb9e0858ea862fa1e8abf29
+size 5649