Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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-2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-66/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/Qwen2.5-3B-Instruct
+library_name: peft
+model_name: globe-theatre-qwen25-3b-lora
+tags:
+- base_model:adapter:Qwen/Qwen2.5-3B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for globe-theatre-qwen25-3b-lora
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-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: 1.6.0
+- Transformers: 5.10.2
+- Pytorch: 2.11.0+cu128
+- Datasets: 5.0.0
+- 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/Qwen2.5-3B-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": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_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 sha256:9e90749472ac39dec2b80483b7c98680e95ec8b1920292ae13ee8b50cadeca17
+size 119801528

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-2/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-3B-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-2/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/Qwen2.5-3B-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": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70515326599a883cb72a971fcac2c77a873db8a68afdbe9b39c0163185e87d7d
+size 119801528

checkpoint-2/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-2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630cfb12c8e1e3659fe00e88f55938253566003127240f1b329c72e2db2d965c
+size 239900363

checkpoint-2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910a69df908656b84fc5747465e81d19f2c7de67ebe0eadfdbb98bcd5933a180
+size 14645

checkpoint-2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fdcd2562cf3166adf3765bf70a5123bdf92480863dbc3530647e4f1d81de651
+size 1465

checkpoint-2/tokenizer.json

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

checkpoint-2/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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09302325581395349,
+  "eval_steps": 25,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.1579806357622147,
+      "epoch": 0.046511627906976744,
+      "grad_norm": 4.12920618057251,
+      "learning_rate": 0.0002,
+      "loss": 3.5343387126922607,
+      "mean_token_accuracy": 0.4543117918074131,
+      "num_tokens": 2858.0,
+      "step": 1
+    },
+    {
+      "entropy": 2.381355881690979,
+      "epoch": 0.09302325581395349,
+      "grad_norm": 1.1530635356903076,
+      "learning_rate": 0.0001,
+      "loss": 3.1979384422302246,
+      "mean_token_accuracy": 0.47458284348249435,
+      "num_tokens": 5729.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "eval_entropy": 2.509654998779297,
+      "eval_loss": 3.1365580558776855,
+      "eval_mean_token_accuracy": 0.4810996651649475,
+      "eval_num_tokens": 5729.0,
+      "eval_runtime": 20.9136,
+      "eval_samples_per_second": 1.004,
+      "eval_steps_per_second": 0.143,
+      "step": 2
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 96409009692672.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f252f68f52357d4ff290307c822fe6a621cc40ea842f2aa372b8858c5d9c36
+size 5649

checkpoint-25/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-3B-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-25/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/Qwen2.5-3B-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": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_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-25/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb362b3f835360c6a7808db04b1c7c10cbd0ddebfc743914e1fd5b5d6390b0ba
+size 119801528

checkpoint-25/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-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1b5d87b260810afea48284009b6e805ee96d40447d2e66f107a55cf98ef8eb
+size 239900363

checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00834fbd33b0d6c164898a9444c72d97e60a896a491d50451bd670c748f26b6
+size 14645

checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2aecfb3dce65b3290a2d1051f23acd25a40887e44e4423df70fcc7c28d274b
+size 1465

checkpoint-25/tokenizer.json

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

checkpoint-25/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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-25/trainer_state.json

@@ -0,0 +1,295 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1395348837209303,
+  "eval_steps": 25,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.1579806357622147,
+      "epoch": 0.046511627906976744,
+      "grad_norm": 4.1606550216674805,
+      "learning_rate": 0.0002,
+      "loss": 3.5343387126922607,
+      "mean_token_accuracy": 0.4543117918074131,
+      "num_tokens": 2858.0,
+      "step": 1
+    },
+    {
+      "entropy": 2.383239656686783,
+      "epoch": 0.09302325581395349,
+      "grad_norm": 1.1439001560211182,
+      "learning_rate": 0.00019696969696969698,
+      "loss": 3.196744918823242,
+      "mean_token_accuracy": 0.4753075949847698,
+      "num_tokens": 5729.0,
+      "step": 2
+    },
+    {
+      "entropy": 2.611323744058609,
+      "epoch": 0.13953488372093023,
+      "grad_norm": 0.8999320864677429,
+      "learning_rate": 0.00019393939393939395,
+      "loss": 3.031313419342041,
+      "mean_token_accuracy": 0.4914238899946213,
+      "num_tokens": 8652.0,
+      "step": 3
+    },
+    {
+      "entropy": 2.6815119981765747,
+      "epoch": 0.18604651162790697,
+      "grad_norm": 0.9472066164016724,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 2.823822259902954,
+      "mean_token_accuracy": 0.5055175274610519,
+      "num_tokens": 11505.0,
+      "step": 4
+    },
+    {
+      "entropy": 2.6952448189258575,
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.0103695392608643,
+      "learning_rate": 0.0001878787878787879,
+      "loss": 2.653456449508667,
+      "mean_token_accuracy": 0.5434774681925774,
+      "num_tokens": 14305.0,
+      "step": 5
+    },
+    {
+      "entropy": 2.583629608154297,
+      "epoch": 0.27906976744186046,
+      "grad_norm": 1.0037801265716553,
+      "learning_rate": 0.00018484848484848484,
+      "loss": 2.4006030559539795,
+      "mean_token_accuracy": 0.5793078020215034,
+      "num_tokens": 17183.0,
+      "step": 6
+    },
+    {
+      "entropy": 2.5597729980945587,
+      "epoch": 0.32558139534883723,
+      "grad_norm": 0.8710836172103882,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 2.2892913818359375,
+      "mean_token_accuracy": 0.5941493511199951,
+      "num_tokens": 19984.0,
+      "step": 7
+    },
+    {
+      "entropy": 2.376883178949356,
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.9070297479629517,
+      "learning_rate": 0.0001787878787878788,
+      "loss": 2.0746352672576904,
+      "mean_token_accuracy": 0.6227477192878723,
+      "num_tokens": 22855.0,
+      "step": 8
+    },
+    {
+      "entropy": 2.258640706539154,
+      "epoch": 0.4186046511627907,
+      "grad_norm": 0.946723222732544,
+      "learning_rate": 0.00017575757575757578,
+      "loss": 2.0197558403015137,
+      "mean_token_accuracy": 0.6193782836198807,
+      "num_tokens": 25725.0,
+      "step": 9
+    },
+    {
+      "entropy": 2.0423424541950226,
+      "epoch": 0.46511627906976744,
+      "grad_norm": 0.967450737953186,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 1.9194402694702148,
+      "mean_token_accuracy": 0.6510066166520119,
+      "num_tokens": 28640.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.8195575922727585,
+      "epoch": 0.5116279069767442,
+      "grad_norm": 0.9876963496208191,
+      "learning_rate": 0.00016969696969696972,
+      "loss": 1.6916238069534302,
+      "mean_token_accuracy": 0.6843769624829292,
+      "num_tokens": 31466.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.657564640045166,
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.9327711462974548,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 1.6198698282241821,
+      "mean_token_accuracy": 0.6921377927064896,
+      "num_tokens": 34386.0,
+      "step": 12
+    },
+    {
+      "entropy": 1.5036935806274414,
+      "epoch": 0.6046511627906976,
+      "grad_norm": 0.9925690293312073,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.6096687316894531,
+      "mean_token_accuracy": 0.6979961171746254,
+      "num_tokens": 37253.0,
+      "step": 13
+    },
+    {
+      "entropy": 1.493466705083847,
+      "epoch": 0.6511627906976745,
+      "grad_norm": 0.7939132452011108,
+      "learning_rate": 0.0001606060606060606,
+      "loss": 1.5107256174087524,
+      "mean_token_accuracy": 0.7151075974106789,
+      "num_tokens": 40126.0,
+      "step": 14
+    },
+    {
+      "entropy": 1.4645536988973618,
+      "epoch": 0.6976744186046512,
+      "grad_norm": 0.7673895359039307,
+      "learning_rate": 0.00015757575757575757,
+      "loss": 1.498252272605896,
+      "mean_token_accuracy": 0.7205590456724167,
+      "num_tokens": 42987.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.4190728217363358,
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.7674983739852905,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 1.4531012773513794,
+      "mean_token_accuracy": 0.7277705073356628,
+      "num_tokens": 45824.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.4405420571565628,
+      "epoch": 0.7906976744186046,
+      "grad_norm": 0.8017104268074036,
+      "learning_rate": 0.00015151515151515152,
+      "loss": 1.4173262119293213,
+      "mean_token_accuracy": 0.7321867346763611,
+      "num_tokens": 48701.0,
+      "step": 17
+    },
+    {
+      "entropy": 1.4430709928274155,
+      "epoch": 0.8372093023255814,
+      "grad_norm": 0.719692587852478,
+      "learning_rate": 0.00014848484848484849,
+      "loss": 1.470382809638977,
+      "mean_token_accuracy": 0.7175731509923935,
+      "num_tokens": 51599.0,
+      "step": 18
+    },
+    {
+      "entropy": 1.4004132896661758,
+      "epoch": 0.8837209302325582,
+      "grad_norm": 0.7663323283195496,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 1.3906199932098389,
+      "mean_token_accuracy": 0.7266740947961807,
+      "num_tokens": 54512.0,
+      "step": 19
+    },
+    {
+      "entropy": 1.3797460794448853,
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.7134779691696167,
+      "learning_rate": 0.00014242424242424243,
+      "loss": 1.3138104677200317,
+      "mean_token_accuracy": 0.7396841123700142,
+      "num_tokens": 57288.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.4256091862916946,
+      "epoch": 0.9767441860465116,
+      "grad_norm": 0.7985653281211853,
+      "learning_rate": 0.0001393939393939394,
+      "loss": 1.4366086721420288,
+      "mean_token_accuracy": 0.7251775711774826,
+      "num_tokens": 60169.0,
+      "step": 21
+    },
+    {
+      "entropy": 1.3379312753677368,
+      "epoch": 1.0,
+      "grad_norm": 1.0615953207015991,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 1.3719230890274048,
+      "mean_token_accuracy": 0.7408558428287506,
+      "num_tokens": 61638.0,
+      "step": 22
+    },
+    {
+      "entropy": 1.3840602338314056,
+      "epoch": 1.0465116279069768,
+      "grad_norm": 0.6854942440986633,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.2929234504699707,
+      "mean_token_accuracy": 0.7477771267294884,
+      "num_tokens": 64544.0,
+      "step": 23
+    },
+    {
+      "entropy": 1.3140927851200104,
+      "epoch": 1.0930232558139534,
+      "grad_norm": 0.7578628659248352,
+      "learning_rate": 0.0001303030303030303,
+      "loss": 1.2306703329086304,
+      "mean_token_accuracy": 0.7550539150834084,
+      "num_tokens": 67387.0,
+      "step": 24
+    },
+    {
+      "entropy": 1.2623722553253174,
+      "epoch": 1.1395348837209303,
+      "grad_norm": 0.8415782451629639,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 1.2171947956085205,
+      "mean_token_accuracy": 0.7480703815817833,
+      "num_tokens": 70226.0,
+      "step": 25
+    },
+    {
+      "epoch": 1.1395348837209303,
+      "eval_entropy": 1.269708236058553,
+      "eval_loss": 1.3236218690872192,
+      "eval_mean_token_accuracy": 0.7468412717183431,
+      "eval_num_tokens": 70226.0,
+      "eval_runtime": 23.6754,
+      "eval_samples_per_second": 0.887,
+      "eval_steps_per_second": 0.127,
+      "step": 25
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 66,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1181780260896768.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-25/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d90e48fffad8a6ebb3bb804054cb6870cb9595177d5a606f4008edb172012b
+size 5649

checkpoint-50/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-3B-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-50/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/Qwen2.5-3B-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": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_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-50/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e16151c6f0776e5405b367bcebded49aa33d3a6707a12cc00721465329303df
+size 119801528

checkpoint-50/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-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3833c21639ea2fa74be3b2195d1d94624805d1c95f2ebed878fcfb8f8c35b293
+size 239900363

checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11640b86187bdf48c71339348dd0297d34cddc8c1c154ea35a13bbfb98ebd78e
+size 14645

checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eaf5c00b490894951565911f2ccd316fcf39759c432bfac95e986ab880a82b0
+size 1465

checkpoint-50/tokenizer.json

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

checkpoint-50/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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-50/trainer_state.json

@@ -0,0 +1,556 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2790697674418605,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.1579806357622147,
+      "epoch": 0.046511627906976744,
+      "grad_norm": 4.1606550216674805,
+      "learning_rate": 0.0002,
+      "loss": 3.5343387126922607,
+      "mean_token_accuracy": 0.4543117918074131,
+      "num_tokens": 2858.0,
+      "step": 1
+    },
+    {
+      "entropy": 2.383239656686783,
+      "epoch": 0.09302325581395349,
+      "grad_norm": 1.1439001560211182,
+      "learning_rate": 0.00019696969696969698,
+      "loss": 3.196744918823242,
+      "mean_token_accuracy": 0.4753075949847698,
+      "num_tokens": 5729.0,
+      "step": 2
+    },
+    {
+      "entropy": 2.611323744058609,
+      "epoch": 0.13953488372093023,
+      "grad_norm": 0.8999320864677429,
+      "learning_rate": 0.00019393939393939395,
+      "loss": 3.031313419342041,
+      "mean_token_accuracy": 0.4914238899946213,
+      "num_tokens": 8652.0,
+      "step": 3
+    },
+    {
+      "entropy": 2.6815119981765747,
+      "epoch": 0.18604651162790697,
+      "grad_norm": 0.9472066164016724,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 2.823822259902954,
+      "mean_token_accuracy": 0.5055175274610519,
+      "num_tokens": 11505.0,
+      "step": 4
+    },
+    {
+      "entropy": 2.6952448189258575,
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.0103695392608643,
+      "learning_rate": 0.0001878787878787879,
+      "loss": 2.653456449508667,
+      "mean_token_accuracy": 0.5434774681925774,
+      "num_tokens": 14305.0,
+      "step": 5
+    },
+    {
+      "entropy": 2.583629608154297,
+      "epoch": 0.27906976744186046,
+      "grad_norm": 1.0037801265716553,
+      "learning_rate": 0.00018484848484848484,
+      "loss": 2.4006030559539795,
+      "mean_token_accuracy": 0.5793078020215034,
+      "num_tokens": 17183.0,
+      "step": 6
+    },
+    {
+      "entropy": 2.5597729980945587,
+      "epoch": 0.32558139534883723,
+      "grad_norm": 0.8710836172103882,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 2.2892913818359375,
+      "mean_token_accuracy": 0.5941493511199951,
+      "num_tokens": 19984.0,
+      "step": 7
+    },
+    {
+      "entropy": 2.376883178949356,
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.9070297479629517,
+      "learning_rate": 0.0001787878787878788,
+      "loss": 2.0746352672576904,
+      "mean_token_accuracy": 0.6227477192878723,
+      "num_tokens": 22855.0,
+      "step": 8
+    },
+    {
+      "entropy": 2.258640706539154,
+      "epoch": 0.4186046511627907,
+      "grad_norm": 0.946723222732544,
+      "learning_rate": 0.00017575757575757578,
+      "loss": 2.0197558403015137,
+      "mean_token_accuracy": 0.6193782836198807,
+      "num_tokens": 25725.0,
+      "step": 9
+    },
+    {
+      "entropy": 2.0423424541950226,
+      "epoch": 0.46511627906976744,
+      "grad_norm": 0.967450737953186,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 1.9194402694702148,
+      "mean_token_accuracy": 0.6510066166520119,
+      "num_tokens": 28640.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.8195575922727585,
+      "epoch": 0.5116279069767442,
+      "grad_norm": 0.9876963496208191,
+      "learning_rate": 0.00016969696969696972,
+      "loss": 1.6916238069534302,
+      "mean_token_accuracy": 0.6843769624829292,
+      "num_tokens": 31466.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.657564640045166,
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.9327711462974548,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 1.6198698282241821,
+      "mean_token_accuracy": 0.6921377927064896,
+      "num_tokens": 34386.0,
+      "step": 12
+    },
+    {
+      "entropy": 1.5036935806274414,
+      "epoch": 0.6046511627906976,
+      "grad_norm": 0.9925690293312073,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.6096687316894531,
+      "mean_token_accuracy": 0.6979961171746254,
+      "num_tokens": 37253.0,
+      "step": 13
+    },
+    {
+      "entropy": 1.493466705083847,
+      "epoch": 0.6511627906976745,
+      "grad_norm": 0.7939132452011108,
+      "learning_rate": 0.0001606060606060606,
+      "loss": 1.5107256174087524,
+      "mean_token_accuracy": 0.7151075974106789,
+      "num_tokens": 40126.0,
+      "step": 14
+    },
+    {
+      "entropy": 1.4645536988973618,
+      "epoch": 0.6976744186046512,
+      "grad_norm": 0.7673895359039307,
+      "learning_rate": 0.00015757575757575757,
+      "loss": 1.498252272605896,
+      "mean_token_accuracy": 0.7205590456724167,
+      "num_tokens": 42987.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.4190728217363358,
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.7674983739852905,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 1.4531012773513794,
+      "mean_token_accuracy": 0.7277705073356628,
+      "num_tokens": 45824.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.4405420571565628,
+      "epoch": 0.7906976744186046,
+      "grad_norm": 0.8017104268074036,
+      "learning_rate": 0.00015151515151515152,
+      "loss": 1.4173262119293213,
+      "mean_token_accuracy": 0.7321867346763611,
+      "num_tokens": 48701.0,
+      "step": 17
+    },
+    {
+      "entropy": 1.4430709928274155,
+      "epoch": 0.8372093023255814,
+      "grad_norm": 0.719692587852478,
+      "learning_rate": 0.00014848484848484849,
+      "loss": 1.470382809638977,
+      "mean_token_accuracy": 0.7175731509923935,
+      "num_tokens": 51599.0,
+      "step": 18
+    },
+    {
+      "entropy": 1.4004132896661758,
+      "epoch": 0.8837209302325582,
+      "grad_norm": 0.7663323283195496,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 1.3906199932098389,
+      "mean_token_accuracy": 0.7266740947961807,
+      "num_tokens": 54512.0,
+      "step": 19
+    },
+    {
+      "entropy": 1.3797460794448853,
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.7134779691696167,
+      "learning_rate": 0.00014242424242424243,
+      "loss": 1.3138104677200317,
+      "mean_token_accuracy": 0.7396841123700142,
+      "num_tokens": 57288.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.4256091862916946,
+      "epoch": 0.9767441860465116,
+      "grad_norm": 0.7985653281211853,
+      "learning_rate": 0.0001393939393939394,
+      "loss": 1.4366086721420288,
+      "mean_token_accuracy": 0.7251775711774826,
+      "num_tokens": 60169.0,
+      "step": 21
+    },
+    {
+      "entropy": 1.3379312753677368,
+      "epoch": 1.0,
+      "grad_norm": 1.0615953207015991,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 1.3719230890274048,
+      "mean_token_accuracy": 0.7408558428287506,
+      "num_tokens": 61638.0,
+      "step": 22
+    },
+    {
+      "entropy": 1.3840602338314056,
+      "epoch": 1.0465116279069768,
+      "grad_norm": 0.6854942440986633,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.2929234504699707,
+      "mean_token_accuracy": 0.7477771267294884,
+      "num_tokens": 64544.0,
+      "step": 23
+    },
+    {
+      "entropy": 1.3140927851200104,
+      "epoch": 1.0930232558139534,
+      "grad_norm": 0.7578628659248352,
+      "learning_rate": 0.0001303030303030303,
+      "loss": 1.2306703329086304,
+      "mean_token_accuracy": 0.7550539150834084,
+      "num_tokens": 67387.0,
+      "step": 24
+    },
+    {
+      "entropy": 1.2623722553253174,
+      "epoch": 1.1395348837209303,
+      "grad_norm": 0.8415782451629639,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 1.2171947956085205,
+      "mean_token_accuracy": 0.7480703815817833,
+      "num_tokens": 70226.0,
+      "step": 25
+    },
+    {
+      "epoch": 1.1395348837209303,
+      "eval_entropy": 1.269708236058553,
+      "eval_loss": 1.3236218690872192,
+      "eval_mean_token_accuracy": 0.7468412717183431,
+      "eval_num_tokens": 70226.0,
+      "eval_runtime": 23.6754,
+      "eval_samples_per_second": 0.887,
+      "eval_steps_per_second": 0.127,
+      "step": 25
+    },
+    {
+      "entropy": 1.2569413930177689,
+      "epoch": 1.1860465116279069,
+      "grad_norm": 0.7056717872619629,
+      "learning_rate": 0.00012424242424242425,
+      "loss": 1.2411645650863647,
+      "mean_token_accuracy": 0.7509386241436005,
+      "num_tokens": 73108.0,
+      "step": 26
+    },
+    {
+      "entropy": 1.1610113084316254,
+      "epoch": 1.2325581395348837,
+      "grad_norm": 0.6524553894996643,
+      "learning_rate": 0.00012121212121212122,
+      "loss": 1.2357319593429565,
+      "mean_token_accuracy": 0.7581899166107178,
+      "num_tokens": 75997.0,
+      "step": 27
+    },
+    {
+      "entropy": 1.1316318660974503,
+      "epoch": 1.2790697674418605,
+      "grad_norm": 0.7145143747329712,
+      "learning_rate": 0.0001181818181818182,
+      "loss": 1.1603296995162964,
+      "mean_token_accuracy": 0.7560656443238258,
+      "num_tokens": 78843.0,
+      "step": 28
+    },
+    {
+      "entropy": 1.0897059589624405,
+      "epoch": 1.3255813953488373,
+      "grad_norm": 0.716164231300354,
+      "learning_rate": 0.00011515151515151516,
+      "loss": 1.1013548374176025,
+      "mean_token_accuracy": 0.7676788046956062,
+      "num_tokens": 81658.0,
+      "step": 29
+    },
+    {
+      "entropy": 1.1006843373179436,
+      "epoch": 1.372093023255814,
+      "grad_norm": 0.7658649682998657,
+      "learning_rate": 0.00011212121212121212,
+      "loss": 1.2547061443328857,
+      "mean_token_accuracy": 0.7541963085532188,
+      "num_tokens": 84536.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1640941053628922,
+      "epoch": 1.4186046511627908,
+      "grad_norm": 0.6944812536239624,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 1.2627403736114502,
+      "mean_token_accuracy": 0.7511968314647675,
+      "num_tokens": 87417.0,
+      "step": 31
+    },
+    {
+      "entropy": 1.1671042293310165,
+      "epoch": 1.4651162790697674,
+      "grad_norm": 0.6439647674560547,
+      "learning_rate": 0.00010606060606060606,
+      "loss": 1.1558995246887207,
+      "mean_token_accuracy": 0.7654487788677216,
+      "num_tokens": 90331.0,
+      "step": 32
+    },
+    {
+      "entropy": 1.1942840218544006,
+      "epoch": 1.5116279069767442,
+      "grad_norm": 0.6287422776222229,
+      "learning_rate": 0.00010303030303030303,
+      "loss": 1.1651532649993896,
+      "mean_token_accuracy": 0.7653707712888718,
+      "num_tokens": 93121.0,
+      "step": 33
+    },
+    {
+      "entropy": 1.1679446250200272,
+      "epoch": 1.558139534883721,
+      "grad_norm": 0.6145845651626587,
+      "learning_rate": 0.0001,
+      "loss": 1.1484891176223755,
+      "mean_token_accuracy": 0.7692908048629761,
+      "num_tokens": 95976.0,
+      "step": 34
+    },
+    {
+      "entropy": 1.192369356751442,
+      "epoch": 1.6046511627906976,
+      "grad_norm": 0.6312623620033264,
+      "learning_rate": 9.696969696969698e-05,
+      "loss": 1.1241192817687988,
+      "mean_token_accuracy": 0.7745805829763412,
+      "num_tokens": 98831.0,
+      "step": 35
+    },
+    {
+      "entropy": 1.1986273378133774,
+      "epoch": 1.6511627906976745,
+      "grad_norm": 0.631524384021759,
+      "learning_rate": 9.393939393939395e-05,
+      "loss": 1.1099392175674438,
+      "mean_token_accuracy": 0.7665266469120979,
+      "num_tokens": 101692.0,
+      "step": 36
+    },
+    {
+      "entropy": 1.1622384190559387,
+      "epoch": 1.697674418604651,
+      "grad_norm": 0.6554811000823975,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 1.1182700395584106,
+      "mean_token_accuracy": 0.7731309980154037,
+      "num_tokens": 104588.0,
+      "step": 37
+    },
+    {
+      "entropy": 1.1431942731142044,
+      "epoch": 1.744186046511628,
+      "grad_norm": 0.6505893468856812,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 1.1559628248214722,
+      "mean_token_accuracy": 0.7654054239392281,
+      "num_tokens": 107432.0,
+      "step": 38
+    },
+    {
+      "entropy": 1.0986781418323517,
+      "epoch": 1.7906976744186047,
+      "grad_norm": 0.6133966445922852,
+      "learning_rate": 8.484848484848486e-05,
+      "loss": 1.1038329601287842,
+      "mean_token_accuracy": 0.7741741612553596,
+      "num_tokens": 110290.0,
+      "step": 39
+    },
+    {
+      "entropy": 1.1940048933029175,
+      "epoch": 1.8372093023255816,
+      "grad_norm": 0.6706917881965637,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 1.2224962711334229,
+      "mean_token_accuracy": 0.7595749273896217,
+      "num_tokens": 113241.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.093463771045208,
+      "epoch": 1.8837209302325582,
+      "grad_norm": 0.6326221823692322,
+      "learning_rate": 7.878787878787879e-05,
+      "loss": 1.0774179697036743,
+      "mean_token_accuracy": 0.7765835002064705,
+      "num_tokens": 116058.0,
+      "step": 41
+    },
+    {
+      "entropy": 1.0873005762696266,
+      "epoch": 1.9302325581395348,
+      "grad_norm": 0.6181315183639526,
+      "learning_rate": 7.575757575757576e-05,
+      "loss": 1.0978009700775146,
+      "mean_token_accuracy": 0.7810145989060402,
+      "num_tokens": 118917.0,
+      "step": 42
+    },
+    {
+      "entropy": 1.1240383982658386,
+      "epoch": 1.9767441860465116,
+      "grad_norm": 0.6578682661056519,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 1.1661534309387207,
+      "mean_token_accuracy": 0.7703806236386299,
+      "num_tokens": 121826.0,
+      "step": 43
+    },
+    {
+      "entropy": 1.1067591309547424,
+      "epoch": 2.0,
+      "grad_norm": 0.859855592250824,
+      "learning_rate": 6.96969696969697e-05,
+      "loss": 1.1423782110214233,
+      "mean_token_accuracy": 0.7782015055418015,
+      "num_tokens": 123276.0,
+      "step": 44
+    },
+    {
+      "entropy": 1.007106527686119,
+      "epoch": 2.046511627906977,
+      "grad_norm": 0.6361871957778931,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.99169921875,
+      "mean_token_accuracy": 0.8010707274079323,
+      "num_tokens": 126131.0,
+      "step": 45
+    },
+    {
+      "entropy": 1.0915530025959015,
+      "epoch": 2.0930232558139537,
+      "grad_norm": 0.6246346831321716,
+      "learning_rate": 6.363636363636364e-05,
+      "loss": 1.0227229595184326,
+      "mean_token_accuracy": 0.7880896329879761,
+      "num_tokens": 129040.0,
+      "step": 46
+    },
+    {
+      "entropy": 1.0547040328383446,
+      "epoch": 2.13953488372093,
+      "grad_norm": 0.603927493095398,
+      "learning_rate": 6.060606060606061e-05,
+      "loss": 1.0576000213623047,
+      "mean_token_accuracy": 0.7919111326336861,
+      "num_tokens": 131913.0,
+      "step": 47
+    },
+    {
+      "entropy": 1.0246013700962067,
+      "epoch": 2.186046511627907,
+      "grad_norm": 0.6876993179321289,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 1.001023530960083,
+      "mean_token_accuracy": 0.7936117947101593,
+      "num_tokens": 134761.0,
+      "step": 48
+    },
+    {
+      "entropy": 1.0352526903152466,
+      "epoch": 2.2325581395348837,
+      "grad_norm": 0.6039313673973083,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 1.0032858848571777,
+      "mean_token_accuracy": 0.7948877811431885,
+      "num_tokens": 137615.0,
+      "step": 49
+    },
+    {
+      "entropy": 1.0240555480122566,
+      "epoch": 2.2790697674418605,
+      "grad_norm": 0.8708204627037048,
+      "learning_rate": 5.151515151515152e-05,
+      "loss": 1.0185186862945557,
+      "mean_token_accuracy": 0.7922521382570267,
+      "num_tokens": 140414.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.2790697674418605,
+      "eval_entropy": 1.0602943102518718,
+      "eval_loss": 1.200447678565979,
+      "eval_mean_token_accuracy": 0.7699050903320312,
+      "eval_num_tokens": 140414.0,
+      "eval_runtime": 23.5584,
+      "eval_samples_per_second": 0.891,
+      "eval_steps_per_second": 0.127,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 66,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2362921048522752.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d90e48fffad8a6ebb3bb804054cb6870cb9595177d5a606f4008edb172012b
+size 5649

checkpoint-66/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-3B-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-66/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/Qwen2.5-3B-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": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_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-66/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e90749472ac39dec2b80483b7c98680e95ec8b1920292ae13ee8b50cadeca17
+size 119801528

checkpoint-66/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-66/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9303c8bb5bc7726b4f215fed70e22b9519327c1d23b3dd58dd0f48529a9fe62
+size 239900363

checkpoint-66/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa96bffe1c83c14e17036638a6e2860624179ab07eea20990734cf7a58410c9
+size 14645

checkpoint-66/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0ef08a8896fc74249e1d03a7a19353047bad5d9925f4998a7d2908c9b7b155
+size 1465

checkpoint-66/tokenizer.json

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

checkpoint-66/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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-66/trainer_state.json

@@ -0,0 +1,727 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 25,
+  "global_step": 66,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.1579806357622147,
+      "epoch": 0.046511627906976744,
+      "grad_norm": 4.1606550216674805,
+      "learning_rate": 0.0002,
+      "loss": 3.5343387126922607,
+      "mean_token_accuracy": 0.4543117918074131,
+      "num_tokens": 2858.0,
+      "step": 1
+    },
+    {
+      "entropy": 2.383239656686783,
+      "epoch": 0.09302325581395349,
+      "grad_norm": 1.1439001560211182,
+      "learning_rate": 0.00019696969696969698,
+      "loss": 3.196744918823242,
+      "mean_token_accuracy": 0.4753075949847698,
+      "num_tokens": 5729.0,
+      "step": 2
+    },
+    {
+      "entropy": 2.611323744058609,
+      "epoch": 0.13953488372093023,
+      "grad_norm": 0.8999320864677429,
+      "learning_rate": 0.00019393939393939395,
+      "loss": 3.031313419342041,
+      "mean_token_accuracy": 0.4914238899946213,
+      "num_tokens": 8652.0,
+      "step": 3
+    },
+    {
+      "entropy": 2.6815119981765747,
+      "epoch": 0.18604651162790697,
+      "grad_norm": 0.9472066164016724,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 2.823822259902954,
+      "mean_token_accuracy": 0.5055175274610519,
+      "num_tokens": 11505.0,
+      "step": 4
+    },
+    {
+      "entropy": 2.6952448189258575,
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.0103695392608643,
+      "learning_rate": 0.0001878787878787879,
+      "loss": 2.653456449508667,
+      "mean_token_accuracy": 0.5434774681925774,
+      "num_tokens": 14305.0,
+      "step": 5
+    },
+    {
+      "entropy": 2.583629608154297,
+      "epoch": 0.27906976744186046,
+      "grad_norm": 1.0037801265716553,
+      "learning_rate": 0.00018484848484848484,
+      "loss": 2.4006030559539795,
+      "mean_token_accuracy": 0.5793078020215034,
+      "num_tokens": 17183.0,
+      "step": 6
+    },
+    {
+      "entropy": 2.5597729980945587,
+      "epoch": 0.32558139534883723,
+      "grad_norm": 0.8710836172103882,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 2.2892913818359375,
+      "mean_token_accuracy": 0.5941493511199951,
+      "num_tokens": 19984.0,
+      "step": 7
+    },
+    {
+      "entropy": 2.376883178949356,
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.9070297479629517,
+      "learning_rate": 0.0001787878787878788,
+      "loss": 2.0746352672576904,
+      "mean_token_accuracy": 0.6227477192878723,
+      "num_tokens": 22855.0,
+      "step": 8
+    },
+    {
+      "entropy": 2.258640706539154,
+      "epoch": 0.4186046511627907,
+      "grad_norm": 0.946723222732544,
+      "learning_rate": 0.00017575757575757578,
+      "loss": 2.0197558403015137,
+      "mean_token_accuracy": 0.6193782836198807,
+      "num_tokens": 25725.0,
+      "step": 9
+    },
+    {
+      "entropy": 2.0423424541950226,
+      "epoch": 0.46511627906976744,
+      "grad_norm": 0.967450737953186,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 1.9194402694702148,
+      "mean_token_accuracy": 0.6510066166520119,
+      "num_tokens": 28640.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.8195575922727585,
+      "epoch": 0.5116279069767442,
+      "grad_norm": 0.9876963496208191,
+      "learning_rate": 0.00016969696969696972,
+      "loss": 1.6916238069534302,
+      "mean_token_accuracy": 0.6843769624829292,
+      "num_tokens": 31466.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.657564640045166,
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.9327711462974548,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 1.6198698282241821,
+      "mean_token_accuracy": 0.6921377927064896,
+      "num_tokens": 34386.0,
+      "step": 12
+    },
+    {
+      "entropy": 1.5036935806274414,
+      "epoch": 0.6046511627906976,
+      "grad_norm": 0.9925690293312073,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.6096687316894531,
+      "mean_token_accuracy": 0.6979961171746254,
+      "num_tokens": 37253.0,
+      "step": 13
+    },
+    {
+      "entropy": 1.493466705083847,
+      "epoch": 0.6511627906976745,
+      "grad_norm": 0.7939132452011108,
+      "learning_rate": 0.0001606060606060606,
+      "loss": 1.5107256174087524,
+      "mean_token_accuracy": 0.7151075974106789,
+      "num_tokens": 40126.0,
+      "step": 14
+    },
+    {
+      "entropy": 1.4645536988973618,
+      "epoch": 0.6976744186046512,
+      "grad_norm": 0.7673895359039307,
+      "learning_rate": 0.00015757575757575757,
+      "loss": 1.498252272605896,
+      "mean_token_accuracy": 0.7205590456724167,
+      "num_tokens": 42987.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.4190728217363358,
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.7674983739852905,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 1.4531012773513794,
+      "mean_token_accuracy": 0.7277705073356628,
+      "num_tokens": 45824.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.4405420571565628,
+      "epoch": 0.7906976744186046,
+      "grad_norm": 0.8017104268074036,
+      "learning_rate": 0.00015151515151515152,
+      "loss": 1.4173262119293213,
+      "mean_token_accuracy": 0.7321867346763611,
+      "num_tokens": 48701.0,
+      "step": 17
+    },
+    {
+      "entropy": 1.4430709928274155,
+      "epoch": 0.8372093023255814,
+      "grad_norm": 0.719692587852478,
+      "learning_rate": 0.00014848484848484849,
+      "loss": 1.470382809638977,
+      "mean_token_accuracy": 0.7175731509923935,
+      "num_tokens": 51599.0,
+      "step": 18
+    },
+    {
+      "entropy": 1.4004132896661758,
+      "epoch": 0.8837209302325582,
+      "grad_norm": 0.7663323283195496,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 1.3906199932098389,
+      "mean_token_accuracy": 0.7266740947961807,
+      "num_tokens": 54512.0,
+      "step": 19
+    },
+    {
+      "entropy": 1.3797460794448853,
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.7134779691696167,
+      "learning_rate": 0.00014242424242424243,
+      "loss": 1.3138104677200317,
+      "mean_token_accuracy": 0.7396841123700142,
+      "num_tokens": 57288.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.4256091862916946,
+      "epoch": 0.9767441860465116,
+      "grad_norm": 0.7985653281211853,
+      "learning_rate": 0.0001393939393939394,
+      "loss": 1.4366086721420288,
+      "mean_token_accuracy": 0.7251775711774826,
+      "num_tokens": 60169.0,
+      "step": 21
+    },
+    {
+      "entropy": 1.3379312753677368,
+      "epoch": 1.0,
+      "grad_norm": 1.0615953207015991,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 1.3719230890274048,
+      "mean_token_accuracy": 0.7408558428287506,
+      "num_tokens": 61638.0,
+      "step": 22
+    },
+    {
+      "entropy": 1.3840602338314056,
+      "epoch": 1.0465116279069768,
+      "grad_norm": 0.6854942440986633,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.2929234504699707,
+      "mean_token_accuracy": 0.7477771267294884,
+      "num_tokens": 64544.0,
+      "step": 23
+    },
+    {
+      "entropy": 1.3140927851200104,
+      "epoch": 1.0930232558139534,
+      "grad_norm": 0.7578628659248352,
+      "learning_rate": 0.0001303030303030303,
+      "loss": 1.2306703329086304,
+      "mean_token_accuracy": 0.7550539150834084,
+      "num_tokens": 67387.0,
+      "step": 24
+    },
+    {
+      "entropy": 1.2623722553253174,
+      "epoch": 1.1395348837209303,
+      "grad_norm": 0.8415782451629639,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 1.2171947956085205,
+      "mean_token_accuracy": 0.7480703815817833,
+      "num_tokens": 70226.0,
+      "step": 25
+    },
+    {
+      "epoch": 1.1395348837209303,
+      "eval_entropy": 1.269708236058553,
+      "eval_loss": 1.3236218690872192,
+      "eval_mean_token_accuracy": 0.7468412717183431,
+      "eval_num_tokens": 70226.0,
+      "eval_runtime": 23.6754,
+      "eval_samples_per_second": 0.887,
+      "eval_steps_per_second": 0.127,
+      "step": 25
+    },
+    {
+      "entropy": 1.2569413930177689,
+      "epoch": 1.1860465116279069,
+      "grad_norm": 0.7056717872619629,
+      "learning_rate": 0.00012424242424242425,
+      "loss": 1.2411645650863647,
+      "mean_token_accuracy": 0.7509386241436005,
+      "num_tokens": 73108.0,
+      "step": 26
+    },
+    {
+      "entropy": 1.1610113084316254,
+      "epoch": 1.2325581395348837,
+      "grad_norm": 0.6524553894996643,
+      "learning_rate": 0.00012121212121212122,
+      "loss": 1.2357319593429565,
+      "mean_token_accuracy": 0.7581899166107178,
+      "num_tokens": 75997.0,
+      "step": 27
+    },
+    {
+      "entropy": 1.1316318660974503,
+      "epoch": 1.2790697674418605,
+      "grad_norm": 0.7145143747329712,
+      "learning_rate": 0.0001181818181818182,
+      "loss": 1.1603296995162964,
+      "mean_token_accuracy": 0.7560656443238258,
+      "num_tokens": 78843.0,
+      "step": 28
+    },
+    {
+      "entropy": 1.0897059589624405,
+      "epoch": 1.3255813953488373,
+      "grad_norm": 0.716164231300354,
+      "learning_rate": 0.00011515151515151516,
+      "loss": 1.1013548374176025,
+      "mean_token_accuracy": 0.7676788046956062,
+      "num_tokens": 81658.0,
+      "step": 29
+    },
+    {
+      "entropy": 1.1006843373179436,
+      "epoch": 1.372093023255814,
+      "grad_norm": 0.7658649682998657,
+      "learning_rate": 0.00011212121212121212,
+      "loss": 1.2547061443328857,
+      "mean_token_accuracy": 0.7541963085532188,
+      "num_tokens": 84536.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1640941053628922,
+      "epoch": 1.4186046511627908,
+      "grad_norm": 0.6944812536239624,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 1.2627403736114502,
+      "mean_token_accuracy": 0.7511968314647675,
+      "num_tokens": 87417.0,
+      "step": 31
+    },
+    {
+      "entropy": 1.1671042293310165,
+      "epoch": 1.4651162790697674,
+      "grad_norm": 0.6439647674560547,
+      "learning_rate": 0.00010606060606060606,
+      "loss": 1.1558995246887207,
+      "mean_token_accuracy": 0.7654487788677216,
+      "num_tokens": 90331.0,
+      "step": 32
+    },
+    {
+      "entropy": 1.1942840218544006,
+      "epoch": 1.5116279069767442,
+      "grad_norm": 0.6287422776222229,
+      "learning_rate": 0.00010303030303030303,
+      "loss": 1.1651532649993896,
+      "mean_token_accuracy": 0.7653707712888718,
+      "num_tokens": 93121.0,
+      "step": 33
+    },
+    {
+      "entropy": 1.1679446250200272,
+      "epoch": 1.558139534883721,
+      "grad_norm": 0.6145845651626587,
+      "learning_rate": 0.0001,
+      "loss": 1.1484891176223755,
+      "mean_token_accuracy": 0.7692908048629761,
+      "num_tokens": 95976.0,
+      "step": 34
+    },
+    {
+      "entropy": 1.192369356751442,
+      "epoch": 1.6046511627906976,
+      "grad_norm": 0.6312623620033264,
+      "learning_rate": 9.696969696969698e-05,
+      "loss": 1.1241192817687988,
+      "mean_token_accuracy": 0.7745805829763412,
+      "num_tokens": 98831.0,
+      "step": 35
+    },
+    {
+      "entropy": 1.1986273378133774,
+      "epoch": 1.6511627906976745,
+      "grad_norm": 0.631524384021759,
+      "learning_rate": 9.393939393939395e-05,
+      "loss": 1.1099392175674438,
+      "mean_token_accuracy": 0.7665266469120979,
+      "num_tokens": 101692.0,
+      "step": 36
+    },
+    {
+      "entropy": 1.1622384190559387,
+      "epoch": 1.697674418604651,
+      "grad_norm": 0.6554811000823975,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 1.1182700395584106,
+      "mean_token_accuracy": 0.7731309980154037,
+      "num_tokens": 104588.0,
+      "step": 37
+    },
+    {
+      "entropy": 1.1431942731142044,
+      "epoch": 1.744186046511628,
+      "grad_norm": 0.6505893468856812,
+      "learning_rate": 8.787878787878789e-05,
+      "loss": 1.1559628248214722,
+      "mean_token_accuracy": 0.7654054239392281,
+      "num_tokens": 107432.0,
+      "step": 38
+    },
+    {
+      "entropy": 1.0986781418323517,
+      "epoch": 1.7906976744186047,
+      "grad_norm": 0.6133966445922852,
+      "learning_rate": 8.484848484848486e-05,
+      "loss": 1.1038329601287842,
+      "mean_token_accuracy": 0.7741741612553596,
+      "num_tokens": 110290.0,
+      "step": 39
+    },
+    {
+      "entropy": 1.1940048933029175,
+      "epoch": 1.8372093023255816,
+      "grad_norm": 0.6706917881965637,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 1.2224962711334229,
+      "mean_token_accuracy": 0.7595749273896217,
+      "num_tokens": 113241.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.093463771045208,
+      "epoch": 1.8837209302325582,
+      "grad_norm": 0.6326221823692322,
+      "learning_rate": 7.878787878787879e-05,
+      "loss": 1.0774179697036743,
+      "mean_token_accuracy": 0.7765835002064705,
+      "num_tokens": 116058.0,
+      "step": 41
+    },
+    {
+      "entropy": 1.0873005762696266,
+      "epoch": 1.9302325581395348,
+      "grad_norm": 0.6181315183639526,
+      "learning_rate": 7.575757575757576e-05,
+      "loss": 1.0978009700775146,
+      "mean_token_accuracy": 0.7810145989060402,
+      "num_tokens": 118917.0,
+      "step": 42
+    },
+    {
+      "entropy": 1.1240383982658386,
+      "epoch": 1.9767441860465116,
+      "grad_norm": 0.6578682661056519,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 1.1661534309387207,
+      "mean_token_accuracy": 0.7703806236386299,
+      "num_tokens": 121826.0,
+      "step": 43
+    },
+    {
+      "entropy": 1.1067591309547424,
+      "epoch": 2.0,
+      "grad_norm": 0.859855592250824,
+      "learning_rate": 6.96969696969697e-05,
+      "loss": 1.1423782110214233,
+      "mean_token_accuracy": 0.7782015055418015,
+      "num_tokens": 123276.0,
+      "step": 44
+    },
+    {
+      "entropy": 1.007106527686119,
+      "epoch": 2.046511627906977,
+      "grad_norm": 0.6361871957778931,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.99169921875,
+      "mean_token_accuracy": 0.8010707274079323,
+      "num_tokens": 126131.0,
+      "step": 45
+    },
+    {
+      "entropy": 1.0915530025959015,
+      "epoch": 2.0930232558139537,
+      "grad_norm": 0.6246346831321716,
+      "learning_rate": 6.363636363636364e-05,
+      "loss": 1.0227229595184326,
+      "mean_token_accuracy": 0.7880896329879761,
+      "num_tokens": 129040.0,
+      "step": 46
+    },
+    {
+      "entropy": 1.0547040328383446,
+      "epoch": 2.13953488372093,
+      "grad_norm": 0.603927493095398,
+      "learning_rate": 6.060606060606061e-05,
+      "loss": 1.0576000213623047,
+      "mean_token_accuracy": 0.7919111326336861,
+      "num_tokens": 131913.0,
+      "step": 47
+    },
+    {
+      "entropy": 1.0246013700962067,
+      "epoch": 2.186046511627907,
+      "grad_norm": 0.6876993179321289,
+      "learning_rate": 5.757575757575758e-05,
+      "loss": 1.001023530960083,
+      "mean_token_accuracy": 0.7936117947101593,
+      "num_tokens": 134761.0,
+      "step": 48
+    },
+    {
+      "entropy": 1.0352526903152466,
+      "epoch": 2.2325581395348837,
+      "grad_norm": 0.6039313673973083,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 1.0032858848571777,
+      "mean_token_accuracy": 0.7948877811431885,
+      "num_tokens": 137615.0,
+      "step": 49
+    },
+    {
+      "entropy": 1.0240555480122566,
+      "epoch": 2.2790697674418605,
+      "grad_norm": 0.8708204627037048,
+      "learning_rate": 5.151515151515152e-05,
+      "loss": 1.0185186862945557,
+      "mean_token_accuracy": 0.7922521382570267,
+      "num_tokens": 140414.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.2790697674418605,
+      "eval_entropy": 1.0602943102518718,
+      "eval_loss": 1.200447678565979,
+      "eval_mean_token_accuracy": 0.7699050903320312,
+      "eval_num_tokens": 140414.0,
+      "eval_runtime": 23.5584,
+      "eval_samples_per_second": 0.891,
+      "eval_steps_per_second": 0.127,
+      "step": 50
+    },
+    {
+      "entropy": 1.0265027210116386,
+      "epoch": 2.3255813953488373,
+      "grad_norm": 0.6438567638397217,
+      "learning_rate": 4.848484848484849e-05,
+      "loss": 1.0175249576568604,
+      "mean_token_accuracy": 0.7826866135001183,
+      "num_tokens": 143284.0,
+      "step": 51
+    },
+    {
+      "entropy": 0.9898267388343811,
+      "epoch": 2.3720930232558137,
+      "grad_norm": 0.6375133991241455,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.9707764387130737,
+      "mean_token_accuracy": 0.7932744771242142,
+      "num_tokens": 146150.0,
+      "step": 52
+    },
+    {
+      "entropy": 1.0071745812892914,
+      "epoch": 2.4186046511627906,
+      "grad_norm": 0.6660930514335632,
+      "learning_rate": 4.242424242424243e-05,
+      "loss": 1.009242296218872,
+      "mean_token_accuracy": 0.7855371758341789,
+      "num_tokens": 149068.0,
+      "step": 53
+    },
+    {
+      "entropy": 0.9613702818751335,
+      "epoch": 2.4651162790697674,
+      "grad_norm": 0.7088518738746643,
+      "learning_rate": 3.939393939393939e-05,
+      "loss": 1.0165516138076782,
+      "mean_token_accuracy": 0.783820278942585,
+      "num_tokens": 151917.0,
+      "step": 54
+    },
+    {
+      "entropy": 0.9687683582305908,
+      "epoch": 2.511627906976744,
+      "grad_norm": 0.7164815664291382,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 1.0128358602523804,
+      "mean_token_accuracy": 0.7865022346377373,
+      "num_tokens": 154798.0,
+      "step": 55
+    },
+    {
+      "entropy": 1.055348590016365,
+      "epoch": 2.558139534883721,
+      "grad_norm": 0.6744108200073242,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.089644193649292,
+      "mean_token_accuracy": 0.7786232009530067,
+      "num_tokens": 157680.0,
+      "step": 56
+    },
+    {
+      "entropy": 0.9879975840449333,
+      "epoch": 2.604651162790698,
+      "grad_norm": 0.6763589978218079,
+      "learning_rate": 3.0303030303030306e-05,
+      "loss": 0.9537328481674194,
+      "mean_token_accuracy": 0.7971024885773659,
+      "num_tokens": 160507.0,
+      "step": 57
+    },
+    {
+      "entropy": 0.9627247974276543,
+      "epoch": 2.6511627906976747,
+      "grad_norm": 0.7175208926200867,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.9957941174507141,
+      "mean_token_accuracy": 0.7866578698158264,
+      "num_tokens": 163425.0,
+      "step": 58
+    },
+    {
+      "entropy": 1.0002940371632576,
+      "epoch": 2.697674418604651,
+      "grad_norm": 0.701934278011322,
+      "learning_rate": 2.4242424242424244e-05,
+      "loss": 1.0220932960510254,
+      "mean_token_accuracy": 0.7892234101891518,
+      "num_tokens": 166345.0,
+      "step": 59
+    },
+    {
+      "entropy": 1.025565043091774,
+      "epoch": 2.744186046511628,
+      "grad_norm": 0.745701014995575,
+      "learning_rate": 2.1212121212121215e-05,
+      "loss": 1.0702790021896362,
+      "mean_token_accuracy": 0.7797161340713501,
+      "num_tokens": 169237.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.039203941822052,
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.7017920613288879,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.998133659362793,
+      "mean_token_accuracy": 0.7900014817714691,
+      "num_tokens": 172060.0,
+      "step": 61
+    },
+    {
+      "entropy": 0.9565892815589905,
+      "epoch": 2.8372093023255816,
+      "grad_norm": 0.6405618190765381,
+      "learning_rate": 1.5151515151515153e-05,
+      "loss": 0.9477425813674927,
+      "mean_token_accuracy": 0.7926909402012825,
+      "num_tokens": 174911.0,
+      "step": 62
+    },
+    {
+      "entropy": 1.0012692958116531,
+      "epoch": 2.883720930232558,
+      "grad_norm": 0.6901278495788574,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 1.0073176622390747,
+      "mean_token_accuracy": 0.7831154614686966,
+      "num_tokens": 177785.0,
+      "step": 63
+    },
+    {
+      "entropy": 1.0543946996331215,
+      "epoch": 2.9302325581395348,
+      "grad_norm": 0.7121431231498718,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0966410636901855,
+      "mean_token_accuracy": 0.7801365330815315,
+      "num_tokens": 180657.0,
+      "step": 64
+    },
+    {
+      "entropy": 0.9581101983785629,
+      "epoch": 2.9767441860465116,
+      "grad_norm": 0.6658024191856384,
+      "learning_rate": 6.060606060606061e-06,
+      "loss": 0.9611006379127502,
+      "mean_token_accuracy": 0.7966474443674088,
+      "num_tokens": 183493.0,
+      "step": 65
+    },
+    {
+      "entropy": 1.041701763868332,
+      "epoch": 3.0,
+      "grad_norm": 0.990643322467804,
+      "learning_rate": 3.0303030303030305e-06,
+      "loss": 1.044697642326355,
+      "mean_token_accuracy": 0.7845684140920639,
+      "num_tokens": 184914.0,
+      "step": 66
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 1.0458589792251587,
+      "eval_loss": 1.186977505683899,
+      "eval_mean_token_accuracy": 0.770394523938497,
+      "eval_num_tokens": 184914.0,
+      "eval_runtime": 23.5158,
+      "eval_samples_per_second": 0.893,
+      "eval_steps_per_second": 0.128,
+      "step": 66
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 66,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3111777905098752.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-66/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d90e48fffad8a6ebb3bb804054cb6870cb9595177d5a606f4008edb172012b
+size 5649

tokenizer.json

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