Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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-1218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,62 @@
----
-license: apache-2.0
----
+---
+base_model: Qwen/Qwen2.5-14B-Instruct
+library_name: peft
+model_name: rfc-model-output
+tags:
+- base_model:adapter:Qwen/Qwen2.5-14B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for rfc-model-output
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-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: 5.6.0
+- 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/Qwen2.5-14B-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": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_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 sha256:234a9a624be87bcab1c099d6a9b4aae497b761bb829cd1f46962f485bc882824
+size 137716248

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/Qwen2.5-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-14B-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/Qwen2.5-14B-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": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_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 sha256:74f137b775b1fb972ee0dabb0466f1cfa7b3b169d6ee7856a24d5831e55a1c3c
+size 137716248

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:db2631de4b03e3087853aec8a6611d850ee61948b600cd6462cde13a8a0367c0
+size 275819843

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff02d6746a15327f6d132f7cc486e46f01bc7b32f8586a5e890cf2180737618
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6139aaa6db114ae152e7eb972ef8f75abd6dcc179fe5d5f9d5715ff454196460
+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 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|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": 0.8213552361396304,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.9327721463143825,
+      "epoch": 0.02053388090349076,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 0.00012972972972972974,
+      "loss": 0.9855536651611329,
+      "mean_token_accuracy": 0.7679368060827255,
+      "num_tokens": 201640.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.8724879887700081,
+      "epoch": 0.04106776180698152,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.00019994905570360817,
+      "loss": 0.8708956909179687,
+      "mean_token_accuracy": 0.7903838059306145,
+      "num_tokens": 404792.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8544691229611635,
+      "epoch": 0.061601642710472276,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.00019951602516690988,
+      "loss": 0.8482267761230469,
+      "mean_token_accuracy": 0.7932471469044685,
+      "num_tokens": 606810.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.8944924513995648,
+      "epoch": 0.08213552361396304,
+      "grad_norm": 0.1640625,
+      "learning_rate": 0.0001986430349043317,
+      "loss": 0.8818518829345703,
+      "mean_token_accuracy": 0.7834139719605446,
+      "num_tokens": 807549.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.9099837489426136,
+      "epoch": 0.1026694045174538,
+      "grad_norm": 0.14453125,
+      "learning_rate": 0.0001973339444003735,
+      "loss": 0.8984813690185547,
+      "mean_token_accuracy": 0.7812782523036003,
+      "num_tokens": 1008223.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.8356300877034664,
+      "epoch": 0.12320328542094455,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.0001955945411359792,
+      "loss": 0.8289723205566406,
+      "mean_token_accuracy": 0.7977875503897667,
+      "num_tokens": 1209811.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8626699298620224,
+      "epoch": 0.1437371663244353,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00019343251500211975,
+      "loss": 0.8522069549560547,
+      "mean_token_accuracy": 0.789976358115673,
+      "num_tokens": 1411353.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.8640103512257338,
+      "epoch": 0.16427104722792607,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.00019085742430283322,
+      "loss": 0.8584527587890625,
+      "mean_token_accuracy": 0.7891600033640862,
+      "num_tokens": 1614555.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8809252215921879,
+      "epoch": 0.18480492813141683,
+      "grad_norm": 0.1640625,
+      "learning_rate": 0.0001878806534980221,
+      "loss": 0.87360107421875,
+      "mean_token_accuracy": 0.7867547670006751,
+      "num_tokens": 1816672.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.8541410507261753,
+      "epoch": 0.2053388090349076,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 0.0001845153628728274,
+      "loss": 0.8500338745117187,
+      "mean_token_accuracy": 0.7926329699158668,
+      "num_tokens": 2018500.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8946534705162048,
+      "epoch": 0.22587268993839835,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00018077643035609004,
+      "loss": 0.8828852844238281,
+      "mean_token_accuracy": 0.7846844819188118,
+      "num_tokens": 2220866.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.8587514898180961,
+      "epoch": 0.2464065708418891,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.0001766803857451204,
+      "loss": 0.8391613006591797,
+      "mean_token_accuracy": 0.7931238517165184,
+      "num_tokens": 2421013.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.876440706178546,
+      "epoch": 0.2669404517453799,
+      "grad_norm": 0.1796875,
+      "learning_rate": 0.00017224533762756776,
+      "loss": 0.8661175537109375,
+      "mean_token_accuracy": 0.7875098848342895,
+      "num_tokens": 2623081.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.8844135162234307,
+      "epoch": 0.2874743326488706,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.00016749089332346713,
+      "loss": 0.8735830688476562,
+      "mean_token_accuracy": 0.7862337788939476,
+      "num_tokens": 2824382.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.7987543179094792,
+      "epoch": 0.3080082135523614,
+      "grad_norm": 0.154296875,
+      "learning_rate": 0.00016243807220139988,
+      "loss": 0.79259033203125,
+      "mean_token_accuracy": 0.804975683093071,
+      "num_tokens": 3026700.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.8895229130983353,
+      "epoch": 0.32854209445585214,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.0001571092127519967,
+      "loss": 0.8765971374511718,
+      "mean_token_accuracy": 0.7862004506587982,
+      "num_tokens": 3228741.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.8609522663801908,
+      "epoch": 0.3490759753593429,
+      "grad_norm": 0.1484375,
+      "learning_rate": 0.00015152787382960968,
+      "loss": 0.8444467163085938,
+      "mean_token_accuracy": 0.793184621334076,
+      "num_tokens": 3428336.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.8780751578509808,
+      "epoch": 0.36960985626283366,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001457187304987645,
+      "loss": 0.8594348907470704,
+      "mean_token_accuracy": 0.7891285745799541,
+      "num_tokens": 3626721.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.815336870700121,
+      "epoch": 0.39014373716632444,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 0.0001397074649458544,
+      "loss": 0.8068878936767578,
+      "mean_token_accuracy": 0.8028223878145218,
+      "num_tokens": 3829062.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.8639824625849724,
+      "epoch": 0.4106776180698152,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00013352065293835397,
+      "loss": 0.8533393096923828,
+      "mean_token_accuracy": 0.7899997106194496,
+      "num_tokens": 4030678.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.8904591681063175,
+      "epoch": 0.43121149897330596,
+      "grad_norm": 0.162109375,
+      "learning_rate": 0.00012718564633351772,
+      "loss": 0.8847498321533203,
+      "mean_token_accuracy": 0.7833931747078896,
+      "num_tokens": 4233119.0,
+      "step": 525
+    },
+    {
+      "entropy": 0.8268530152738094,
+      "epoch": 0.4517453798767967,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00012073045215598952,
+      "loss": 0.8184004211425782,
+      "mean_token_accuracy": 0.7992048686742783,
+      "num_tokens": 4434734.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.7941572253406047,
+      "epoch": 0.4722792607802875,
+      "grad_norm": 0.173828125,
+      "learning_rate": 0.00011418360877892164,
+      "loss": 0.7798463439941407,
+      "mean_token_accuracy": 0.8061937466263771,
+      "num_tokens": 4636778.0,
+      "step": 575
+    },
+    {
+      "entropy": 0.8667953862249851,
+      "epoch": 0.4928131416837782,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00010757405975600534,
+      "loss": 0.8635111999511719,
+      "mean_token_accuracy": 0.7889971971511841,
+      "num_tokens": 4839819.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.8342785247415304,
+      "epoch": 0.5133470225872689,
+      "grad_norm": 0.1416015625,
+      "learning_rate": 0.00010093102586220055,
+      "loss": 0.8236666870117187,
+      "mean_token_accuracy": 0.796975427120924,
+      "num_tokens": 5041753.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.8055999881774187,
+      "epoch": 0.5338809034907598,
+      "grad_norm": 0.158203125,
+      "learning_rate": 9.42838759088723e-05,
+      "loss": 0.7989521789550781,
+      "mean_token_accuracy": 0.805096383690834,
+      "num_tokens": 5245040.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.8180603013932705,
+      "epoch": 0.5544147843942505,
+      "grad_norm": 0.150390625,
+      "learning_rate": 8.76619969044592e-05,
+      "loss": 0.802100601196289,
+      "mean_token_accuracy": 0.8017301180958748,
+      "num_tokens": 5446302.0,
+      "step": 675
+    },
+    {
+      "entropy": 0.8475391804426908,
+      "epoch": 0.5749486652977412,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 8.109466413469238e-05,
+      "loss": 0.8385409545898438,
+      "mean_token_accuracy": 0.7944941192865371,
+      "num_tokens": 5647189.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.8185767906159163,
+      "epoch": 0.5954825462012321,
+      "grad_norm": 0.201171875,
+      "learning_rate": 7.461091173674022e-05,
+      "loss": 0.80953369140625,
+      "mean_token_accuracy": 0.7994823551177979,
+      "num_tokens": 5849070.0,
+      "step": 725
+    },
+    {
+      "entropy": 0.8287316697835923,
+      "epoch": 0.6160164271047228,
+      "grad_norm": 0.193359375,
+      "learning_rate": 6.823940433946921e-05,
+      "loss": 0.8172183227539063,
+      "mean_token_accuracy": 0.8001478153467179,
+      "num_tokens": 6051514.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.8862237848341465,
+      "epoch": 0.6365503080082136,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 6.200831033729863e-05,
+      "loss": 0.8690660095214844,
+      "mean_token_accuracy": 0.7873855569958687,
+      "num_tokens": 6251375.0,
+      "step": 775
+    },
+    {
+      "entropy": 0.7810994558781386,
+      "epoch": 0.6570841889117043,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 5.5945177357904934e-05,
+      "loss": 0.7692386627197265,
+      "mean_token_accuracy": 0.8092155620455742,
+      "num_tokens": 6453040.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.8132312067598104,
+      "epoch": 0.6776180698151951,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 5.007681047433139e-05,
+      "loss": 0.8110353088378907,
+      "mean_token_accuracy": 0.8015294006466865,
+      "num_tokens": 6656782.0,
+      "step": 825
+    },
+    {
+      "entropy": 0.8274586813151836,
+      "epoch": 0.6981519507186859,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 4.442915369992802e-05,
+      "loss": 0.815575942993164,
+      "mean_token_accuracy": 0.7989534091949463,
+      "num_tokens": 6858454.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.8976877976208926,
+      "epoch": 0.7186858316221766,
+      "grad_norm": 0.162109375,
+      "learning_rate": 3.902717529003005e-05,
+      "loss": 0.8837800598144532,
+      "mean_token_accuracy": 0.7825979651510715,
+      "num_tokens": 7058361.0,
+      "step": 875
+    },
+    {
+      "entropy": 0.8282124460488558,
+      "epoch": 0.7392197125256673,
+      "grad_norm": 0.1640625,
+      "learning_rate": 3.389475735745761e-05,
+      "loss": 0.8223667907714843,
+      "mean_token_accuracy": 0.79724593937397,
+      "num_tokens": 7261833.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.8559306030720473,
+      "epoch": 0.7597535934291582,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 2.9054590289843396e-05,
+      "loss": 0.8454450988769531,
+      "mean_token_accuracy": 0.7930123561620712,
+      "num_tokens": 7463682.0,
+      "step": 925
+    },
+    {
+      "entropy": 0.8133819183707237,
+      "epoch": 0.7802874743326489,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 2.452807243557116e-05,
+      "loss": 0.8075272369384766,
+      "mean_token_accuracy": 0.8024582426249981,
+      "num_tokens": 7666583.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.8377064400911332,
+      "epoch": 0.8008213552361396,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 2.0335215501810777e-05,
+      "loss": 0.825996322631836,
+      "mean_token_accuracy": 0.7960993593931198,
+      "num_tokens": 7867378.0,
+      "step": 975
+    },
+    {
+      "entropy": 0.8585446905344725,
+      "epoch": 0.8213552361396304,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.6494556082886036e-05,
+      "loss": 0.8439271545410156,
+      "mean_token_accuracy": 0.7945261257886886,
+      "num_tokens": 8068940.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1218,
+  "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": 6.807092753482138e+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 sha256:00c74c540ba486e37b2ecd571f6abb225f08e6945cd9424b3c389d45073e7ec7
+size 5713

checkpoint-1218/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-14B-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-1218/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/Qwen2.5-14B-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": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_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-1218/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234a9a624be87bcab1c099d6a9b4aae497b761bb829cd1f46962f485bc882824
+size 137716248

checkpoint-1218/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-1218/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7084439896f3c03e54044a76252fd5498a3317b8e3d278976eb1efa9f2c2c9d6
+size 275819843

checkpoint-1218/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e2046090c2eb039f24137681b28da388e31434b4fbca6430ca94d6ba82ac4e
+size 14645

checkpoint-1218/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3369d35408474ce20c366a8744cbd23421e743bad2afe92aced69322e81ead
+size 1465

checkpoint-1218/tokenizer.json

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

checkpoint-1218/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1218/trainer_state.json

@@ -0,0 +1,514 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1218,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.9327721463143825,
+      "epoch": 0.02053388090349076,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 0.00012972972972972974,
+      "loss": 0.9855536651611329,
+      "mean_token_accuracy": 0.7679368060827255,
+      "num_tokens": 201640.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.8724879887700081,
+      "epoch": 0.04106776180698152,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.00019994905570360817,
+      "loss": 0.8708956909179687,
+      "mean_token_accuracy": 0.7903838059306145,
+      "num_tokens": 404792.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8544691229611635,
+      "epoch": 0.061601642710472276,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.00019951602516690988,
+      "loss": 0.8482267761230469,
+      "mean_token_accuracy": 0.7932471469044685,
+      "num_tokens": 606810.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.8944924513995648,
+      "epoch": 0.08213552361396304,
+      "grad_norm": 0.1640625,
+      "learning_rate": 0.0001986430349043317,
+      "loss": 0.8818518829345703,
+      "mean_token_accuracy": 0.7834139719605446,
+      "num_tokens": 807549.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.9099837489426136,
+      "epoch": 0.1026694045174538,
+      "grad_norm": 0.14453125,
+      "learning_rate": 0.0001973339444003735,
+      "loss": 0.8984813690185547,
+      "mean_token_accuracy": 0.7812782523036003,
+      "num_tokens": 1008223.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.8356300877034664,
+      "epoch": 0.12320328542094455,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.0001955945411359792,
+      "loss": 0.8289723205566406,
+      "mean_token_accuracy": 0.7977875503897667,
+      "num_tokens": 1209811.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8626699298620224,
+      "epoch": 0.1437371663244353,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00019343251500211975,
+      "loss": 0.8522069549560547,
+      "mean_token_accuracy": 0.789976358115673,
+      "num_tokens": 1411353.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.8640103512257338,
+      "epoch": 0.16427104722792607,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.00019085742430283322,
+      "loss": 0.8584527587890625,
+      "mean_token_accuracy": 0.7891600033640862,
+      "num_tokens": 1614555.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8809252215921879,
+      "epoch": 0.18480492813141683,
+      "grad_norm": 0.1640625,
+      "learning_rate": 0.0001878806534980221,
+      "loss": 0.87360107421875,
+      "mean_token_accuracy": 0.7867547670006751,
+      "num_tokens": 1816672.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.8541410507261753,
+      "epoch": 0.2053388090349076,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 0.0001845153628728274,
+      "loss": 0.8500338745117187,
+      "mean_token_accuracy": 0.7926329699158668,
+      "num_tokens": 2018500.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8946534705162048,
+      "epoch": 0.22587268993839835,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00018077643035609004,
+      "loss": 0.8828852844238281,
+      "mean_token_accuracy": 0.7846844819188118,
+      "num_tokens": 2220866.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.8587514898180961,
+      "epoch": 0.2464065708418891,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.0001766803857451204,
+      "loss": 0.8391613006591797,
+      "mean_token_accuracy": 0.7931238517165184,
+      "num_tokens": 2421013.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.876440706178546,
+      "epoch": 0.2669404517453799,
+      "grad_norm": 0.1796875,
+      "learning_rate": 0.00017224533762756776,
+      "loss": 0.8661175537109375,
+      "mean_token_accuracy": 0.7875098848342895,
+      "num_tokens": 2623081.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.8844135162234307,
+      "epoch": 0.2874743326488706,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.00016749089332346713,
+      "loss": 0.8735830688476562,
+      "mean_token_accuracy": 0.7862337788939476,
+      "num_tokens": 2824382.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.7987543179094792,
+      "epoch": 0.3080082135523614,
+      "grad_norm": 0.154296875,
+      "learning_rate": 0.00016243807220139988,
+      "loss": 0.79259033203125,
+      "mean_token_accuracy": 0.804975683093071,
+      "num_tokens": 3026700.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.8895229130983353,
+      "epoch": 0.32854209445585214,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.0001571092127519967,
+      "loss": 0.8765971374511718,
+      "mean_token_accuracy": 0.7862004506587982,
+      "num_tokens": 3228741.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.8609522663801908,
+      "epoch": 0.3490759753593429,
+      "grad_norm": 0.1484375,
+      "learning_rate": 0.00015152787382960968,
+      "loss": 0.8444467163085938,
+      "mean_token_accuracy": 0.793184621334076,
+      "num_tokens": 3428336.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.8780751578509808,
+      "epoch": 0.36960985626283366,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001457187304987645,
+      "loss": 0.8594348907470704,
+      "mean_token_accuracy": 0.7891285745799541,
+      "num_tokens": 3626721.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.815336870700121,
+      "epoch": 0.39014373716632444,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 0.0001397074649458544,
+      "loss": 0.8068878936767578,
+      "mean_token_accuracy": 0.8028223878145218,
+      "num_tokens": 3829062.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.8639824625849724,
+      "epoch": 0.4106776180698152,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00013352065293835397,
+      "loss": 0.8533393096923828,
+      "mean_token_accuracy": 0.7899997106194496,
+      "num_tokens": 4030678.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.8904591681063175,
+      "epoch": 0.43121149897330596,
+      "grad_norm": 0.162109375,
+      "learning_rate": 0.00012718564633351772,
+      "loss": 0.8847498321533203,
+      "mean_token_accuracy": 0.7833931747078896,
+      "num_tokens": 4233119.0,
+      "step": 525
+    },
+    {
+      "entropy": 0.8268530152738094,
+      "epoch": 0.4517453798767967,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00012073045215598952,
+      "loss": 0.8184004211425782,
+      "mean_token_accuracy": 0.7992048686742783,
+      "num_tokens": 4434734.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.7941572253406047,
+      "epoch": 0.4722792607802875,
+      "grad_norm": 0.173828125,
+      "learning_rate": 0.00011418360877892164,
+      "loss": 0.7798463439941407,
+      "mean_token_accuracy": 0.8061937466263771,
+      "num_tokens": 4636778.0,
+      "step": 575
+    },
+    {
+      "entropy": 0.8667953862249851,
+      "epoch": 0.4928131416837782,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00010757405975600534,
+      "loss": 0.8635111999511719,
+      "mean_token_accuracy": 0.7889971971511841,
+      "num_tokens": 4839819.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.8342785247415304,
+      "epoch": 0.5133470225872689,
+      "grad_norm": 0.1416015625,
+      "learning_rate": 0.00010093102586220055,
+      "loss": 0.8236666870117187,
+      "mean_token_accuracy": 0.796975427120924,
+      "num_tokens": 5041753.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.8055999881774187,
+      "epoch": 0.5338809034907598,
+      "grad_norm": 0.158203125,
+      "learning_rate": 9.42838759088723e-05,
+      "loss": 0.7989521789550781,
+      "mean_token_accuracy": 0.805096383690834,
+      "num_tokens": 5245040.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.8180603013932705,
+      "epoch": 0.5544147843942505,
+      "grad_norm": 0.150390625,
+      "learning_rate": 8.76619969044592e-05,
+      "loss": 0.802100601196289,
+      "mean_token_accuracy": 0.8017301180958748,
+      "num_tokens": 5446302.0,
+      "step": 675
+    },
+    {
+      "entropy": 0.8475391804426908,
+      "epoch": 0.5749486652977412,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 8.109466413469238e-05,
+      "loss": 0.8385409545898438,
+      "mean_token_accuracy": 0.7944941192865371,
+      "num_tokens": 5647189.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.8185767906159163,
+      "epoch": 0.5954825462012321,
+      "grad_norm": 0.201171875,
+      "learning_rate": 7.461091173674022e-05,
+      "loss": 0.80953369140625,
+      "mean_token_accuracy": 0.7994823551177979,
+      "num_tokens": 5849070.0,
+      "step": 725
+    },
+    {
+      "entropy": 0.8287316697835923,
+      "epoch": 0.6160164271047228,
+      "grad_norm": 0.193359375,
+      "learning_rate": 6.823940433946921e-05,
+      "loss": 0.8172183227539063,
+      "mean_token_accuracy": 0.8001478153467179,
+      "num_tokens": 6051514.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.8862237848341465,
+      "epoch": 0.6365503080082136,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 6.200831033729863e-05,
+      "loss": 0.8690660095214844,
+      "mean_token_accuracy": 0.7873855569958687,
+      "num_tokens": 6251375.0,
+      "step": 775
+    },
+    {
+      "entropy": 0.7810994558781386,
+      "epoch": 0.6570841889117043,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 5.5945177357904934e-05,
+      "loss": 0.7692386627197265,
+      "mean_token_accuracy": 0.8092155620455742,
+      "num_tokens": 6453040.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.8132312067598104,
+      "epoch": 0.6776180698151951,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 5.007681047433139e-05,
+      "loss": 0.8110353088378907,
+      "mean_token_accuracy": 0.8015294006466865,
+      "num_tokens": 6656782.0,
+      "step": 825
+    },
+    {
+      "entropy": 0.8274586813151836,
+      "epoch": 0.6981519507186859,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 4.442915369992802e-05,
+      "loss": 0.815575942993164,
+      "mean_token_accuracy": 0.7989534091949463,
+      "num_tokens": 6858454.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.8976877976208926,
+      "epoch": 0.7186858316221766,
+      "grad_norm": 0.162109375,
+      "learning_rate": 3.902717529003005e-05,
+      "loss": 0.8837800598144532,
+      "mean_token_accuracy": 0.7825979651510715,
+      "num_tokens": 7058361.0,
+      "step": 875
+    },
+    {
+      "entropy": 0.8282124460488558,
+      "epoch": 0.7392197125256673,
+      "grad_norm": 0.1640625,
+      "learning_rate": 3.389475735745761e-05,
+      "loss": 0.8223667907714843,
+      "mean_token_accuracy": 0.79724593937397,
+      "num_tokens": 7261833.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.8559306030720473,
+      "epoch": 0.7597535934291582,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 2.9054590289843396e-05,
+      "loss": 0.8454450988769531,
+      "mean_token_accuracy": 0.7930123561620712,
+      "num_tokens": 7463682.0,
+      "step": 925
+    },
+    {
+      "entropy": 0.8133819183707237,
+      "epoch": 0.7802874743326489,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 2.452807243557116e-05,
+      "loss": 0.8075272369384766,
+      "mean_token_accuracy": 0.8024582426249981,
+      "num_tokens": 7666583.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.8377064400911332,
+      "epoch": 0.8008213552361396,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 2.0335215501810777e-05,
+      "loss": 0.825996322631836,
+      "mean_token_accuracy": 0.7960993593931198,
+      "num_tokens": 7867378.0,
+      "step": 975
+    },
+    {
+      "entropy": 0.8585446905344725,
+      "epoch": 0.8213552361396304,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.6494556082886036e-05,
+      "loss": 0.8439271545410156,
+      "mean_token_accuracy": 0.7945261257886886,
+      "num_tokens": 8068940.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.8176959943026304,
+      "epoch": 0.8418891170431212,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 1.3023073710106726e-05,
+      "loss": 0.8095787048339844,
+      "mean_token_accuracy": 0.8031405085325241,
+      "num_tokens": 8273099.0,
+      "step": 1025
+    },
+    {
+      "entropy": 0.8056896831095218,
+      "epoch": 0.8624229979466119,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 9.936115785366818e-06,
+      "loss": 0.7893988800048828,
+      "mean_token_accuracy": 0.8052867284417152,
+      "num_tokens": 8473495.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.8300137943774462,
+      "epoch": 0.8829568788501027,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 7.247329730376428e-06,
+      "loss": 0.8155036926269531,
+      "mean_token_accuracy": 0.7991513350605964,
+      "num_tokens": 8673737.0,
+      "step": 1075
+    },
+    {
+      "entropy": 0.8159111841768026,
+      "epoch": 0.9034907597535934,
+      "grad_norm": 0.140625,
+      "learning_rate": 4.968602651495779e-06,
+      "loss": 0.7988214111328125,
+      "mean_token_accuracy": 0.8009992632269859,
+      "num_tokens": 8873700.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.7891377609223127,
+      "epoch": 0.9240246406570842,
+      "grad_norm": 0.150390625,
+      "learning_rate": 3.110008786912122e-06,
+      "loss": 0.7799327087402343,
+      "mean_token_accuracy": 0.8081652447581291,
+      "num_tokens": 9076270.0,
+      "step": 1125
+    },
+    {
+      "entropy": 0.7982633775472641,
+      "epoch": 0.944558521560575,
+      "grad_norm": 0.18359375,
+      "learning_rate": 1.6797649684956119e-06,
+      "loss": 0.7916005706787109,
+      "mean_token_accuracy": 0.8044543984532356,
+      "num_tokens": 9279889.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.8694525339081883,
+      "epoch": 0.9650924024640657,
+      "grad_norm": 0.177734375,
+      "learning_rate": 6.841942952369618e-07,
+      "loss": 0.8574421691894532,
+      "mean_token_accuracy": 0.7883387035131455,
+      "num_tokens": 9481072.0,
+      "step": 1175
+    },
+    {
+      "entropy": 0.7400653018802404,
+      "epoch": 0.9856262833675564,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.2769817886626456e-07,
+      "loss": 0.7348995208740234,
+      "mean_token_accuracy": 0.8198987892270089,
+      "num_tokens": 9683838.0,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1218,
+  "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": 8.289904376732713e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1218/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c74c540ba486e37b2ecd571f6abb225f08e6945cd9424b3c389d45073e7ec7
+size 5713

checkpoint-500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-14B-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/Qwen2.5-14B-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": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_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-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baabde4a77fc6dc06a2c2ba6e7d668eda7873012a39a2625e027ce09f4c503c4
+size 137716248

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:eba3cf2d3ba5507d16e6b7f4806800b2a12ffba45b22458d13598abc59c490eb
+size 275819843

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a248915dafbd7ae492916e8e3b07a84280dd83804293d963a986f5ea88523a05
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7652e22ba8c9f33df03ad6ae69a9c8787cb48432329278c58bc74e8cf0195f4
+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 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|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": 0.4106776180698152,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.9327721463143825,
+      "epoch": 0.02053388090349076,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 0.00012972972972972974,
+      "loss": 0.9855536651611329,
+      "mean_token_accuracy": 0.7679368060827255,
+      "num_tokens": 201640.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.8724879887700081,
+      "epoch": 0.04106776180698152,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.00019994905570360817,
+      "loss": 0.8708956909179687,
+      "mean_token_accuracy": 0.7903838059306145,
+      "num_tokens": 404792.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8544691229611635,
+      "epoch": 0.061601642710472276,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.00019951602516690988,
+      "loss": 0.8482267761230469,
+      "mean_token_accuracy": 0.7932471469044685,
+      "num_tokens": 606810.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.8944924513995648,
+      "epoch": 0.08213552361396304,
+      "grad_norm": 0.1640625,
+      "learning_rate": 0.0001986430349043317,
+      "loss": 0.8818518829345703,
+      "mean_token_accuracy": 0.7834139719605446,
+      "num_tokens": 807549.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.9099837489426136,
+      "epoch": 0.1026694045174538,
+      "grad_norm": 0.14453125,
+      "learning_rate": 0.0001973339444003735,
+      "loss": 0.8984813690185547,
+      "mean_token_accuracy": 0.7812782523036003,
+      "num_tokens": 1008223.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.8356300877034664,
+      "epoch": 0.12320328542094455,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.0001955945411359792,
+      "loss": 0.8289723205566406,
+      "mean_token_accuracy": 0.7977875503897667,
+      "num_tokens": 1209811.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8626699298620224,
+      "epoch": 0.1437371663244353,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00019343251500211975,
+      "loss": 0.8522069549560547,
+      "mean_token_accuracy": 0.789976358115673,
+      "num_tokens": 1411353.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.8640103512257338,
+      "epoch": 0.16427104722792607,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.00019085742430283322,
+      "loss": 0.8584527587890625,
+      "mean_token_accuracy": 0.7891600033640862,
+      "num_tokens": 1614555.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8809252215921879,
+      "epoch": 0.18480492813141683,
+      "grad_norm": 0.1640625,
+      "learning_rate": 0.0001878806534980221,
+      "loss": 0.87360107421875,
+      "mean_token_accuracy": 0.7867547670006751,
+      "num_tokens": 1816672.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.8541410507261753,
+      "epoch": 0.2053388090349076,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 0.0001845153628728274,
+      "loss": 0.8500338745117187,
+      "mean_token_accuracy": 0.7926329699158668,
+      "num_tokens": 2018500.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8946534705162048,
+      "epoch": 0.22587268993839835,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00018077643035609004,
+      "loss": 0.8828852844238281,
+      "mean_token_accuracy": 0.7846844819188118,
+      "num_tokens": 2220866.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.8587514898180961,
+      "epoch": 0.2464065708418891,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.0001766803857451204,
+      "loss": 0.8391613006591797,
+      "mean_token_accuracy": 0.7931238517165184,
+      "num_tokens": 2421013.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.876440706178546,
+      "epoch": 0.2669404517453799,
+      "grad_norm": 0.1796875,
+      "learning_rate": 0.00017224533762756776,
+      "loss": 0.8661175537109375,
+      "mean_token_accuracy": 0.7875098848342895,
+      "num_tokens": 2623081.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.8844135162234307,
+      "epoch": 0.2874743326488706,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.00016749089332346713,
+      "loss": 0.8735830688476562,
+      "mean_token_accuracy": 0.7862337788939476,
+      "num_tokens": 2824382.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.7987543179094792,
+      "epoch": 0.3080082135523614,
+      "grad_norm": 0.154296875,
+      "learning_rate": 0.00016243807220139988,
+      "loss": 0.79259033203125,
+      "mean_token_accuracy": 0.804975683093071,
+      "num_tokens": 3026700.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.8895229130983353,
+      "epoch": 0.32854209445585214,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.0001571092127519967,
+      "loss": 0.8765971374511718,
+      "mean_token_accuracy": 0.7862004506587982,
+      "num_tokens": 3228741.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.8609522663801908,
+      "epoch": 0.3490759753593429,
+      "grad_norm": 0.1484375,
+      "learning_rate": 0.00015152787382960968,
+      "loss": 0.8444467163085938,
+      "mean_token_accuracy": 0.793184621334076,
+      "num_tokens": 3428336.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.8780751578509808,
+      "epoch": 0.36960985626283366,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001457187304987645,
+      "loss": 0.8594348907470704,
+      "mean_token_accuracy": 0.7891285745799541,
+      "num_tokens": 3626721.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.815336870700121,
+      "epoch": 0.39014373716632444,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 0.0001397074649458544,
+      "loss": 0.8068878936767578,
+      "mean_token_accuracy": 0.8028223878145218,
+      "num_tokens": 3829062.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.8639824625849724,
+      "epoch": 0.4106776180698152,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00013352065293835397,
+      "loss": 0.8533393096923828,
+      "mean_token_accuracy": 0.7899997106194496,
+      "num_tokens": 4030678.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1218,
+  "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": 3.400347382112133e+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 sha256:00c74c540ba486e37b2ecd571f6abb225f08e6945cd9424b3c389d45073e7ec7
+size 5713

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|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 sha256:00c74c540ba486e37b2ecd571f6abb225f08e6945cd9424b3c389d45073e7ec7
+size 5713