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-779/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: IETF-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 IETF-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",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "q_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 sha256:1f07e4aa865ed2eb9c53da6017d476a353596dca881c6e507ecf67f068fc03ed
+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",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "q_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:bbc6e60173182f44d0ce4a263ac4346744ae53e2cfde4a6ba2446dc105d055ba
+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 sha256:7d0d3dc25596d0aaff74d53c7afe13e3eed1cfdca4aa3230775ca78c13c94da6
+size 161810747

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de56e1cbaa2429efc4a2abac15af6277c32725fe86465e79da895726eb9be095
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc374eeeaeac9766e753de36badba3c05dafdf6623bd90d975f5cef05d4224d
+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": 0.6419515326592842,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.769014136493206,
+      "epoch": 0.03209757663296421,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 0.0002,
+      "loss": 1.927232666015625,
+      "mean_token_accuracy": 0.5845547493547201,
+      "num_tokens": 147388.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.5947067447006702,
+      "epoch": 0.06419515326592842,
+      "grad_norm": 0.0703125,
+      "learning_rate": 0.00019945941475610623,
+      "loss": 1.5756130981445313,
+      "mean_token_accuracy": 0.6429479970037937,
+      "num_tokens": 291902.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.4042670665308834,
+      "epoch": 0.09629272989889263,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00019784350367254322,
+      "loss": 1.3896011352539062,
+      "mean_token_accuracy": 0.6840905399620533,
+      "num_tokens": 436739.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.2599401247128845,
+      "epoch": 0.12839030653185685,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 0.00019516973750305532,
+      "loss": 1.247992630004883,
+      "mean_token_accuracy": 0.7115654723346233,
+      "num_tokens": 578709.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.1777591889351606,
+      "epoch": 0.16048788316482104,
+      "grad_norm": 0.0859375,
+      "learning_rate": 0.0001914670242183795,
+      "loss": 1.1679031372070312,
+      "mean_token_accuracy": 0.7358129184693099,
+      "num_tokens": 723238.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.0801194526255131,
+      "epoch": 0.19258545979778527,
+      "grad_norm": 0.1064453125,
+      "learning_rate": 0.00018677539646179707,
+      "loss": 1.0448343658447266,
+      "mean_token_accuracy": 0.7570553781092166,
+      "num_tokens": 866427.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.0227313496544956,
+      "epoch": 0.22468303643074947,
+      "grad_norm": 0.080078125,
+      "learning_rate": 0.00018114557872800905,
+      "loss": 1.023138198852539,
+      "mean_token_accuracy": 0.7729750864207745,
+      "num_tokens": 1012131.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.8637316187471151,
+      "epoch": 0.2567806130637137,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00017463843894486937,
+      "loss": 0.8490833282470703,
+      "mean_token_accuracy": 0.8087801007926464,
+      "num_tokens": 1157299.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8652995108067989,
+      "epoch": 0.2888781896966779,
+      "grad_norm": 0.07373046875,
+      "learning_rate": 0.00016732433038731242,
+      "loss": 0.8502191162109375,
+      "mean_token_accuracy": 0.8063283850252628,
+      "num_tokens": 1299656.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.7840015215892344,
+      "epoch": 0.3209757663296421,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.0001592823310385073,
+      "loss": 0.7785140228271484,
+      "mean_token_accuracy": 0.8246484726667405,
+      "num_tokens": 1441547.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8248297751229257,
+      "epoch": 0.35307334296260634,
+      "grad_norm": 0.1279296875,
+      "learning_rate": 0.00015059938862204127,
+      "loss": 0.8086457824707032,
+      "mean_token_accuracy": 0.8171890932321548,
+      "num_tokens": 1582972.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.770206793518737,
+      "epoch": 0.38517091959557054,
+      "grad_norm": 0.12890625,
+      "learning_rate": 0.00014136938054879283,
+      "loss": 0.7686289978027344,
+      "mean_token_accuracy": 0.8326107160747052,
+      "num_tokens": 1731903.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.8494727142900228,
+      "epoch": 0.41726849622853474,
+      "grad_norm": 0.072265625,
+      "learning_rate": 0.0001316920989420703,
+      "loss": 0.842440185546875,
+      "mean_token_accuracy": 0.812195960432291,
+      "num_tokens": 1877046.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.7691456920653582,
+      "epoch": 0.44936607286149893,
+      "grad_norm": 0.08984375,
+      "learning_rate": 0.00012167217171462566,
+      "loss": 0.7498253631591797,
+      "mean_token_accuracy": 0.8340029817819595,
+      "num_tokens": 2020060.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.6002831929549575,
+      "epoch": 0.4814636494944632,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 0.00011141793136253986,
+      "loss": 0.574959716796875,
+      "mean_token_accuracy": 0.8719502376019954,
+      "num_tokens": 2163196.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.5365751892980188,
+      "epoch": 0.5135612261274274,
+      "grad_norm": 0.060546875,
+      "learning_rate": 0.00010104024370624644,
+      "loss": 0.5327357482910157,
+      "mean_token_accuracy": 0.8794836418330669,
+      "num_tokens": 2306310.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.6227946990681812,
+      "epoch": 0.5456588027603916,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 9.065130924199998e-05,
+      "loss": 0.6111849975585938,
+      "mean_token_accuracy": 0.8625345961749553,
+      "num_tokens": 2451606.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.5804533056542277,
+      "epoch": 0.5777563793933558,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 8.036345006322359e-05,
+      "loss": 0.5718699645996094,
+      "mean_token_accuracy": 0.8725813579559326,
+      "num_tokens": 2597270.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6302943672612309,
+      "epoch": 0.60985395602632,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 7.028789546718326e-05,
+      "loss": 0.6353359985351562,
+      "mean_token_accuracy": 0.8635560862720013,
+      "num_tokens": 2742612.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.5299606989277527,
+      "epoch": 0.6419515326592842,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 6.053357937665237e-05,
+      "loss": 0.5236670303344727,
+      "mean_token_accuracy": 0.8828775423765183,
+      "num_tokens": 2887935.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 779,
+  "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": 1.2321644951250432e+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 sha256:98cced242d15386fcfcda9d5cf0ba061acaa74c8d4e02c76df9f6e2decffa709
+size 5649

checkpoint-779/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-779/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",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "q_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-779/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f07e4aa865ed2eb9c53da6017d476a353596dca881c6e507ecf67f068fc03ed
+size 80792880

checkpoint-779/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-779/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d8fa0e848d35445244cb0968db3be25ee19c5cd975c60717c89a666f6644f9
+size 161810747

checkpoint-779/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6d1bcbf11cec9fb7feef48add7a06444c6d21ecc16788aa83effaafd13df50
+size 14645

checkpoint-779/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d998117d15fe9161bca7403a0a9cf4559bbd438812ecbbde90cae3266384afd9
+size 1465

checkpoint-779/tokenizer.json

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

checkpoint-779/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-779/trainer_state.json

@@ -0,0 +1,344 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 779,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.769014136493206,
+      "epoch": 0.03209757663296421,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 0.0002,
+      "loss": 1.927232666015625,
+      "mean_token_accuracy": 0.5845547493547201,
+      "num_tokens": 147388.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.5947067447006702,
+      "epoch": 0.06419515326592842,
+      "grad_norm": 0.0703125,
+      "learning_rate": 0.00019945941475610623,
+      "loss": 1.5756130981445313,
+      "mean_token_accuracy": 0.6429479970037937,
+      "num_tokens": 291902.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.4042670665308834,
+      "epoch": 0.09629272989889263,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00019784350367254322,
+      "loss": 1.3896011352539062,
+      "mean_token_accuracy": 0.6840905399620533,
+      "num_tokens": 436739.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.2599401247128845,
+      "epoch": 0.12839030653185685,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 0.00019516973750305532,
+      "loss": 1.247992630004883,
+      "mean_token_accuracy": 0.7115654723346233,
+      "num_tokens": 578709.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.1777591889351606,
+      "epoch": 0.16048788316482104,
+      "grad_norm": 0.0859375,
+      "learning_rate": 0.0001914670242183795,
+      "loss": 1.1679031372070312,
+      "mean_token_accuracy": 0.7358129184693099,
+      "num_tokens": 723238.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.0801194526255131,
+      "epoch": 0.19258545979778527,
+      "grad_norm": 0.1064453125,
+      "learning_rate": 0.00018677539646179707,
+      "loss": 1.0448343658447266,
+      "mean_token_accuracy": 0.7570553781092166,
+      "num_tokens": 866427.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.0227313496544956,
+      "epoch": 0.22468303643074947,
+      "grad_norm": 0.080078125,
+      "learning_rate": 0.00018114557872800905,
+      "loss": 1.023138198852539,
+      "mean_token_accuracy": 0.7729750864207745,
+      "num_tokens": 1012131.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.8637316187471151,
+      "epoch": 0.2567806130637137,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00017463843894486937,
+      "loss": 0.8490833282470703,
+      "mean_token_accuracy": 0.8087801007926464,
+      "num_tokens": 1157299.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8652995108067989,
+      "epoch": 0.2888781896966779,
+      "grad_norm": 0.07373046875,
+      "learning_rate": 0.00016732433038731242,
+      "loss": 0.8502191162109375,
+      "mean_token_accuracy": 0.8063283850252628,
+      "num_tokens": 1299656.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.7840015215892344,
+      "epoch": 0.3209757663296421,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.0001592823310385073,
+      "loss": 0.7785140228271484,
+      "mean_token_accuracy": 0.8246484726667405,
+      "num_tokens": 1441547.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8248297751229257,
+      "epoch": 0.35307334296260634,
+      "grad_norm": 0.1279296875,
+      "learning_rate": 0.00015059938862204127,
+      "loss": 0.8086457824707032,
+      "mean_token_accuracy": 0.8171890932321548,
+      "num_tokens": 1582972.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.770206793518737,
+      "epoch": 0.38517091959557054,
+      "grad_norm": 0.12890625,
+      "learning_rate": 0.00014136938054879283,
+      "loss": 0.7686289978027344,
+      "mean_token_accuracy": 0.8326107160747052,
+      "num_tokens": 1731903.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.8494727142900228,
+      "epoch": 0.41726849622853474,
+      "grad_norm": 0.072265625,
+      "learning_rate": 0.0001316920989420703,
+      "loss": 0.842440185546875,
+      "mean_token_accuracy": 0.812195960432291,
+      "num_tokens": 1877046.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.7691456920653582,
+      "epoch": 0.44936607286149893,
+      "grad_norm": 0.08984375,
+      "learning_rate": 0.00012167217171462566,
+      "loss": 0.7498253631591797,
+      "mean_token_accuracy": 0.8340029817819595,
+      "num_tokens": 2020060.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.6002831929549575,
+      "epoch": 0.4814636494944632,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 0.00011141793136253986,
+      "loss": 0.574959716796875,
+      "mean_token_accuracy": 0.8719502376019954,
+      "num_tokens": 2163196.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.5365751892980188,
+      "epoch": 0.5135612261274274,
+      "grad_norm": 0.060546875,
+      "learning_rate": 0.00010104024370624644,
+      "loss": 0.5327357482910157,
+      "mean_token_accuracy": 0.8794836418330669,
+      "num_tokens": 2306310.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.6227946990681812,
+      "epoch": 0.5456588027603916,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 9.065130924199998e-05,
+      "loss": 0.6111849975585938,
+      "mean_token_accuracy": 0.8625345961749553,
+      "num_tokens": 2451606.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.5804533056542277,
+      "epoch": 0.5777563793933558,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 8.036345006322359e-05,
+      "loss": 0.5718699645996094,
+      "mean_token_accuracy": 0.8725813579559326,
+      "num_tokens": 2597270.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6302943672612309,
+      "epoch": 0.60985395602632,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 7.028789546718326e-05,
+      "loss": 0.6353359985351562,
+      "mean_token_accuracy": 0.8635560862720013,
+      "num_tokens": 2742612.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.5299606989277527,
+      "epoch": 0.6419515326592842,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 6.053357937665237e-05,
+      "loss": 0.5236670303344727,
+      "mean_token_accuracy": 0.8828775423765183,
+      "num_tokens": 2887935.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.6732268288638443,
+      "epoch": 0.6740491092922485,
+      "grad_norm": 0.056640625,
+      "learning_rate": 5.1205962578487155e-05,
+      "loss": 0.6722711181640625,
+      "mean_token_accuracy": 0.8543066729605198,
+      "num_tokens": 3035549.0,
+      "step": 525
+    },
+    {
+      "entropy": 0.4612098385160789,
+      "epoch": 0.7061466859252127,
+      "grad_norm": 0.041748046875,
+      "learning_rate": 4.240589251272342e-05,
+      "loss": 0.4541243743896484,
+      "mean_token_accuracy": 0.9010929284989834,
+      "num_tokens": 3180083.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5990941160498187,
+      "epoch": 0.7382442625581769,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 3.422851293981676e-05,
+      "loss": 0.6069795989990234,
+      "mean_token_accuracy": 0.8644757103919983,
+      "num_tokens": 3325528.0,
+      "step": 575
+    },
+    {
+      "entropy": 0.5454245122382417,
+      "epoch": 0.7703418391911411,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 2.6762235274383772e-05,
+      "loss": 0.5289861679077148,
+      "mean_token_accuracy": 0.8816468404233455,
+      "num_tokens": 3469264.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5093659822596237,
+      "epoch": 0.8024394158241053,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 2.008778270707944e-05,
+      "loss": 0.503768424987793,
+      "mean_token_accuracy": 0.8897754719853401,
+      "num_tokens": 3614662.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.5269298075186089,
+      "epoch": 0.8345369924570695,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 1.4277317449282834e-05,
+      "loss": 0.5159123229980469,
+      "mean_token_accuracy": 0.8846879424154759,
+      "num_tokens": 3757746.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6054773937677964,
+      "epoch": 0.8666345690900337,
+      "grad_norm": 0.068359375,
+      "learning_rate": 9.393660536564408e-06,
+      "loss": 0.5959170532226562,
+      "mean_token_accuracy": 0.8715771237760782,
+      "num_tokens": 3904293.0,
+      "step": 675
+    },
+    {
+      "entropy": 0.4945011454587802,
+      "epoch": 0.8987321457229979,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 5.489612626189245e-06,
+      "loss": 0.4754390335083008,
+      "mean_token_accuracy": 0.8915398253500462,
+      "num_tokens": 4043791.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5794008405366913,
+      "epoch": 0.9308297223559622,
+      "grad_norm": 0.0703125,
+      "learning_rate": 2.607383131993424e-06,
+      "loss": 0.5824679565429688,
+      "mean_token_accuracy": 0.8722238828241825,
+      "num_tokens": 4189274.0,
+      "step": 725
+    },
+    {
+      "entropy": 0.5977670075232163,
+      "epoch": 0.9629272989889264,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 7.781338686584927e-07,
+      "loss": 0.5879628372192383,
+      "mean_token_accuracy": 0.8674677063524723,
+      "num_tokens": 4333425.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.5161540248058736,
+      "epoch": 0.9950248756218906,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 2.164213936770576e-08,
+      "loss": 0.497758674621582,
+      "mean_token_accuracy": 0.8871022827923298,
+      "num_tokens": 4479844.0,
+      "step": 775
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 779,
+  "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": 1.9211835200717107e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-779/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98cced242d15386fcfcda9d5cf0ba061acaa74c8d4e02c76df9f6e2decffa709
+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 sha256:98cced242d15386fcfcda9d5cf0ba061acaa74c8d4e02c76df9f6e2decffa709
+size 5649