Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,14 @@ 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-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-900/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: Maincode/Maincoder-1B
+library_name: peft
+model_name: maincoder-1b-toolcalling-lora
+tags:
+- base_model:adapter:Maincode/Maincoder-1B
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for maincoder-1b-toolcalling-lora
+
+This model is a fine-tuned version of [Maincode/Maincoder-1B](https://huggingface.co/Maincode/Maincoder-1B).
+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 0.17.1
+- TRL: 0.21.0
+- Transformers: 4.57.3
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.8.4
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Maincode/Maincoder-1B",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": 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 sha256:262aa7df6404543e20f0dde11b7971643ca568b6701eefa4e08c221725518604
+size 55111408

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '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 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-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Maincode/Maincoder-1B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Maincode/Maincoder-1B
+- 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 0.17.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Maincode/Maincoder-1B",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093e09efc7c93ba64eb2139609390e23ff5574401240c0df3ce85350084e924f
+size 55111408

checkpoint-100/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-100/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '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 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-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8789dc37c86a726128729e4c2470ec93bb4af3c89ed3e49f04adb9b0fe38eda5
+size 110484131

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c81353d18360a112220e3590e9331869a8adf8395d1f4eb39a29ff95fe588d0
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027203cd324846f900163fad9eecbe4aeb19c35a55cd188f85a03ff3e0f62d81
+size 1465

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2222222222222222,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 0.6193130612373352,
+      "learning_rate": 9.910000000000001e-05,
+      "loss": 1.654,
+      "mean_token_accuracy": 0.6766653224825859,
+      "num_tokens": 23330.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.5931444764137268,
+      "learning_rate": 9.81e-05,
+      "loss": 1.0695,
+      "mean_token_accuracy": 0.7898772016167641,
+      "num_tokens": 46070.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.3904027044773102,
+      "learning_rate": 9.71e-05,
+      "loss": 0.7556,
+      "mean_token_accuracy": 0.8578989505767822,
+      "num_tokens": 68719.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.32560470700263977,
+      "learning_rate": 9.61e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.8813577085733414,
+      "num_tokens": 92126.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.30384671688079834,
+      "learning_rate": 9.51e-05,
+      "loss": 0.5761,
+      "mean_token_accuracy": 0.8921546742320061,
+      "num_tokens": 114738.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "eval_loss": 0.5330827236175537,
+      "eval_mean_token_accuracy": 0.9009262701869011,
+      "eval_num_tokens": 114738.0,
+      "eval_runtime": 40.5094,
+      "eval_samples_per_second": 4.937,
+      "eval_steps_per_second": 4.937,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.40981799364089966,
+      "learning_rate": 9.41e-05,
+      "loss": 0.4978,
+      "mean_token_accuracy": 0.9065196111798286,
+      "num_tokens": 136310.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.5167299509048462,
+      "learning_rate": 9.310000000000001e-05,
+      "loss": 0.4466,
+      "mean_token_accuracy": 0.9203566908836365,
+      "num_tokens": 158193.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.5062010884284973,
+      "learning_rate": 9.21e-05,
+      "loss": 0.4003,
+      "mean_token_accuracy": 0.9284946233034134,
+      "num_tokens": 180767.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.38172802329063416,
+      "learning_rate": 9.11e-05,
+      "loss": 0.3457,
+      "mean_token_accuracy": 0.9404646947979927,
+      "num_tokens": 203203.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.4985530376434326,
+      "learning_rate": 9.010000000000001e-05,
+      "loss": 0.3271,
+      "mean_token_accuracy": 0.9434564337134361,
+      "num_tokens": 226070.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_loss": 0.3216829001903534,
+      "eval_mean_token_accuracy": 0.9481457704305649,
+      "eval_num_tokens": 226070.0,
+      "eval_runtime": 41.0245,
+      "eval_samples_per_second": 4.875,
+      "eval_steps_per_second": 4.875,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1094077520640000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f24a1d1fcf3561539dba436a511a781c825b96e542ffcf6aba86ad917df122
+size 6225

checkpoint-1000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Maincode/Maincoder-1B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Maincode/Maincoder-1B
+- 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 0.17.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Maincode/Maincoder-1B",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262aa7df6404543e20f0dde11b7971643ca568b6701eefa4e08c221725518604
+size 55111408

checkpoint-1000/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are 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 a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1528f3832f145fd518620483eec0423a1f1ae65064f157f2e3172977db3b3ff5
+size 110484131

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ff3eb75f21b56c3fc12c648f5272ffc2d353868f9bc476a8d8c21d094f426e
+size 14645

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+size 1383

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9008af82ea2c682c9b64de9d5bd271649247b8bd3c3761983a4def45d64125f2
+size 1465

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2222222222222223,
+  "eval_steps": 50,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 0.6193130612373352,
+      "learning_rate": 9.910000000000001e-05,
+      "loss": 1.654,
+      "mean_token_accuracy": 0.6766653224825859,
+      "num_tokens": 23330.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.5931444764137268,
+      "learning_rate": 9.81e-05,
+      "loss": 1.0695,
+      "mean_token_accuracy": 0.7898772016167641,
+      "num_tokens": 46070.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.3904027044773102,
+      "learning_rate": 9.71e-05,
+      "loss": 0.7556,
+      "mean_token_accuracy": 0.8578989505767822,
+      "num_tokens": 68719.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.32560470700263977,
+      "learning_rate": 9.61e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.8813577085733414,
+      "num_tokens": 92126.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.30384671688079834,
+      "learning_rate": 9.51e-05,
+      "loss": 0.5761,
+      "mean_token_accuracy": 0.8921546742320061,
+      "num_tokens": 114738.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "eval_loss": 0.5330827236175537,
+      "eval_mean_token_accuracy": 0.9009262701869011,
+      "eval_num_tokens": 114738.0,
+      "eval_runtime": 40.5094,
+      "eval_samples_per_second": 4.937,
+      "eval_steps_per_second": 4.937,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.40981799364089966,
+      "learning_rate": 9.41e-05,
+      "loss": 0.4978,
+      "mean_token_accuracy": 0.9065196111798286,
+      "num_tokens": 136310.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.5167299509048462,
+      "learning_rate": 9.310000000000001e-05,
+      "loss": 0.4466,
+      "mean_token_accuracy": 0.9203566908836365,
+      "num_tokens": 158193.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.5062010884284973,
+      "learning_rate": 9.21e-05,
+      "loss": 0.4003,
+      "mean_token_accuracy": 0.9284946233034134,
+      "num_tokens": 180767.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.38172802329063416,
+      "learning_rate": 9.11e-05,
+      "loss": 0.3457,
+      "mean_token_accuracy": 0.9404646947979927,
+      "num_tokens": 203203.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.4985530376434326,
+      "learning_rate": 9.010000000000001e-05,
+      "loss": 0.3271,
+      "mean_token_accuracy": 0.9434564337134361,
+      "num_tokens": 226070.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_loss": 0.3216829001903534,
+      "eval_mean_token_accuracy": 0.9481457704305649,
+      "eval_num_tokens": 226070.0,
+      "eval_runtime": 41.0245,
+      "eval_samples_per_second": 4.875,
+      "eval_steps_per_second": 4.875,
+      "step": 100
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 0.3317733108997345,
+      "learning_rate": 8.910000000000001e-05,
+      "loss": 0.2834,
+      "mean_token_accuracy": 0.9527689620852471,
+      "num_tokens": 251659.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.28577539324760437,
+      "learning_rate": 8.81e-05,
+      "loss": 0.262,
+      "mean_token_accuracy": 0.9557135447859764,
+      "num_tokens": 276141.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 0.4030509293079376,
+      "learning_rate": 8.71e-05,
+      "loss": 0.26,
+      "mean_token_accuracy": 0.9594775453209877,
+      "num_tokens": 299250.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.4423465132713318,
+      "learning_rate": 8.61e-05,
+      "loss": 0.2557,
+      "mean_token_accuracy": 0.9583914607763291,
+      "num_tokens": 323528.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.49233391880989075,
+      "learning_rate": 8.510000000000001e-05,
+      "loss": 0.2444,
+      "mean_token_accuracy": 0.9617681756615639,
+      "num_tokens": 346496.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 0.24680288136005402,
+      "eval_mean_token_accuracy": 0.963321838080883,
+      "eval_num_tokens": 346496.0,
+      "eval_runtime": 41.1525,
+      "eval_samples_per_second": 4.86,
+      "eval_steps_per_second": 4.86,
+      "step": 150
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.2696438133716583,
+      "learning_rate": 8.41e-05,
+      "loss": 0.2196,
+      "mean_token_accuracy": 0.9656250089406967,
+      "num_tokens": 371258.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 0.525949239730835,
+      "learning_rate": 8.31e-05,
+      "loss": 0.2122,
+      "mean_token_accuracy": 0.9669450834393502,
+      "num_tokens": 395722.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.38804805278778076,
+      "learning_rate": 8.21e-05,
+      "loss": 0.2097,
+      "mean_token_accuracy": 0.9699977666139603,
+      "num_tokens": 418830.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 0.38709455728530884,
+      "learning_rate": 8.11e-05,
+      "loss": 0.1914,
+      "mean_token_accuracy": 0.9692254871129989,
+      "num_tokens": 443015.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.28362640738487244,
+      "learning_rate": 8.010000000000001e-05,
+      "loss": 0.2051,
+      "mean_token_accuracy": 0.968667496740818,
+      "num_tokens": 465941.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_loss": 0.21475830674171448,
+      "eval_mean_token_accuracy": 0.9686776822805405,
+      "eval_num_tokens": 465941.0,
+      "eval_runtime": 40.8312,
+      "eval_samples_per_second": 4.898,
+      "eval_steps_per_second": 4.898,
+      "step": 200
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.17446358501911163,
+      "learning_rate": 7.910000000000001e-05,
+      "loss": 0.1992,
+      "mean_token_accuracy": 0.9691774398088455,
+      "num_tokens": 489869.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.47806766629219055,
+      "learning_rate": 7.81e-05,
+      "loss": 0.18,
+      "mean_token_accuracy": 0.9718323066830635,
+      "num_tokens": 514551.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 0.4450798034667969,
+      "learning_rate": 7.71e-05,
+      "loss": 0.1818,
+      "mean_token_accuracy": 0.9731900364160537,
+      "num_tokens": 539497.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.3654688596725464,
+      "learning_rate": 7.61e-05,
+      "loss": 0.2072,
+      "mean_token_accuracy": 0.9681414648890495,
+      "num_tokens": 560454.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.26568618416786194,
+      "learning_rate": 7.510000000000001e-05,
+      "loss": 0.1858,
+      "mean_token_accuracy": 0.9720202058553695,
+      "num_tokens": 584595.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "eval_loss": 0.19870425760746002,
+      "eval_mean_token_accuracy": 0.9720033320784569,
+      "eval_num_tokens": 584595.0,
+      "eval_runtime": 40.9104,
+      "eval_samples_per_second": 4.889,
+      "eval_steps_per_second": 4.889,
+      "step": 250
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.21654823422431946,
+      "learning_rate": 7.41e-05,
+      "loss": 0.1765,
+      "mean_token_accuracy": 0.9739127770066262,
+      "num_tokens": 608352.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3529929220676422,
+      "learning_rate": 7.31e-05,
+      "loss": 0.1726,
+      "mean_token_accuracy": 0.9745927527546883,
+      "num_tokens": 632550.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.2798812985420227,
+      "learning_rate": 7.21e-05,
+      "loss": 0.1814,
+      "mean_token_accuracy": 0.9733540549874306,
+      "num_tokens": 655957.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 0.28510963916778564,
+      "learning_rate": 7.11e-05,
+      "loss": 0.1789,
+      "mean_token_accuracy": 0.9735615655779839,
+      "num_tokens": 680743.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.22315602004528046,
+      "learning_rate": 7.01e-05,
+      "loss": 0.1777,
+      "mean_token_accuracy": 0.9739167138934135,
+      "num_tokens": 704844.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.18998412787914276,
+      "eval_mean_token_accuracy": 0.9746258324384689,
+      "eval_num_tokens": 704844.0,
+      "eval_runtime": 40.6816,
+      "eval_samples_per_second": 4.916,
+      "eval_steps_per_second": 4.916,
+      "step": 300
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.25007760524749756,
+      "learning_rate": 6.91e-05,
+      "loss": 0.1913,
+      "mean_token_accuracy": 0.9710126295685768,
+      "num_tokens": 724403.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.19620826840400696,
+      "learning_rate": 6.81e-05,
+      "loss": 0.1782,
+      "mean_token_accuracy": 0.9740939602255821,
+      "num_tokens": 748460.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.2543444037437439,
+      "learning_rate": 6.71e-05,
+      "loss": 0.1825,
+      "mean_token_accuracy": 0.972811259329319,
+      "num_tokens": 769992.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.12709860503673553,
+      "learning_rate": 6.610000000000001e-05,
+      "loss": 0.1828,
+      "mean_token_accuracy": 0.9728233471512795,
+      "num_tokens": 792260.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.24585242569446564,
+      "learning_rate": 6.510000000000001e-05,
+      "loss": 0.1798,
+      "mean_token_accuracy": 0.9745096892118454,
+      "num_tokens": 815593.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "eval_loss": 0.18533459305763245,
+      "eval_mean_token_accuracy": 0.9745631077885628,
+      "eval_num_tokens": 815593.0,
+      "eval_runtime": 40.662,
+      "eval_samples_per_second": 4.919,
+      "eval_steps_per_second": 4.919,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.22581206262111664,
+      "learning_rate": 6.41e-05,
+      "loss": 0.1807,
+      "mean_token_accuracy": 0.9736085414886475,
+      "num_tokens": 837982.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.2912260591983795,
+      "learning_rate": 6.31e-05,
+      "loss": 0.1668,
+      "mean_token_accuracy": 0.9759353816509246,
+      "num_tokens": 860757.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.1845020055770874,
+      "learning_rate": 6.21e-05,
+      "loss": 0.1839,
+      "mean_token_accuracy": 0.9732057675719261,
+      "num_tokens": 881639.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.2601327896118164,
+      "learning_rate": 6.110000000000001e-05,
+      "loss": 0.1652,
+      "mean_token_accuracy": 0.9748824626207352,
+      "num_tokens": 905643.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.16098515689373016,
+      "learning_rate": 6.0100000000000004e-05,
+      "loss": 0.171,
+      "mean_token_accuracy": 0.9756452158093453,
+      "num_tokens": 929665.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 0.18200141191482544,
+      "eval_mean_token_accuracy": 0.9752507287263871,
+      "eval_num_tokens": 929665.0,
+      "eval_runtime": 40.698,
+      "eval_samples_per_second": 4.914,
+      "eval_steps_per_second": 4.914,
+      "step": 400
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 0.16805872321128845,
+      "learning_rate": 5.91e-05,
+      "loss": 0.1718,
+      "mean_token_accuracy": 0.9748784646391868,
+      "num_tokens": 951866.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.14501382410526276,
+      "learning_rate": 5.8099999999999996e-05,
+      "loss": 0.1662,
+      "mean_token_accuracy": 0.9753882080316544,
+      "num_tokens": 975946.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.9555555555555556,
+      "grad_norm": 0.17429794371128082,
+      "learning_rate": 5.71e-05,
+      "loss": 0.1719,
+      "mean_token_accuracy": 0.9735226526856422,
+      "num_tokens": 997417.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.21708282828330994,
+      "learning_rate": 5.610000000000001e-05,
+      "loss": 0.1679,
+      "mean_token_accuracy": 0.9750987365841866,
+      "num_tokens": 1021762.0,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.11724573373794556,
+      "learning_rate": 5.5100000000000004e-05,
+      "loss": 0.1648,
+      "mean_token_accuracy": 0.9775774568319321,
+      "num_tokens": 1046469.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.18049028515815735,
+      "eval_mean_token_accuracy": 0.9776099815964698,
+      "eval_num_tokens": 1046469.0,
+      "eval_runtime": 40.8205,
+      "eval_samples_per_second": 4.899,
+      "eval_steps_per_second": 4.899,
+      "step": 450
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 0.13565418124198914,
+      "learning_rate": 5.410000000000001e-05,
+      "loss": 0.161,
+      "mean_token_accuracy": 0.9767818033695221,
+      "num_tokens": 1070354.0,
+      "step": 460
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 0.14690855145454407,
+      "learning_rate": 5.31e-05,
+      "loss": 0.1616,
+      "mean_token_accuracy": 0.9762020215392113,
+      "num_tokens": 1095160.0,
+      "step": 470
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.17638139426708221,
+      "learning_rate": 5.2100000000000006e-05,
+      "loss": 0.1633,
+      "mean_token_accuracy": 0.9768583804368973,
+      "num_tokens": 1118117.0,
+      "step": 480
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.18202361464500427,
+      "learning_rate": 5.11e-05,
+      "loss": 0.165,
+      "mean_token_accuracy": 0.9771157950162888,
+      "num_tokens": 1140967.0,
+      "step": 490
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.1454939991235733,
+      "learning_rate": 5.0100000000000005e-05,
+      "loss": 0.1647,
+      "mean_token_accuracy": 0.9771055221557617,
+      "num_tokens": 1165040.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "eval_loss": 0.17858880758285522,
+      "eval_mean_token_accuracy": 0.9758283907175064,
+      "eval_num_tokens": 1165040.0,
+      "eval_runtime": 40.5796,
+      "eval_samples_per_second": 4.929,
+      "eval_steps_per_second": 4.929,
+      "step": 500
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.18715986609458923,
+      "learning_rate": 4.91e-05,
+      "loss": 0.1647,
+      "mean_token_accuracy": 0.9763637855648994,
+      "num_tokens": 1188748.0,
+      "step": 510
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 0.1779111623764038,
+      "learning_rate": 4.8100000000000004e-05,
+      "loss": 0.1696,
+      "mean_token_accuracy": 0.9764641597867012,
+      "num_tokens": 1211411.0,
+      "step": 520
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.19597475230693817,
+      "learning_rate": 4.71e-05,
+      "loss": 0.1707,
+      "mean_token_accuracy": 0.976306001842022,
+      "num_tokens": 1233545.0,
+      "step": 530
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.15781964361667633,
+      "learning_rate": 4.61e-05,
+      "loss": 0.1617,
+      "mean_token_accuracy": 0.9768658638000488,
+      "num_tokens": 1257597.0,
+      "step": 540
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.16846869885921478,
+      "learning_rate": 4.5100000000000005e-05,
+      "loss": 0.1643,
+      "mean_token_accuracy": 0.9779975593090058,
+      "num_tokens": 1280857.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "eval_loss": 0.17742373049259186,
+      "eval_mean_token_accuracy": 0.975758826136589,
+      "eval_num_tokens": 1280857.0,
+      "eval_runtime": 40.7021,
+      "eval_samples_per_second": 4.914,
+      "eval_steps_per_second": 4.914,
+      "step": 550
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 0.09051565825939178,
+      "learning_rate": 4.41e-05,
+      "loss": 0.1672,
+      "mean_token_accuracy": 0.9775181457400322,
+      "num_tokens": 1304923.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.12825968861579895,
+      "learning_rate": 4.3100000000000004e-05,
+      "loss": 0.1709,
+      "mean_token_accuracy": 0.976058243215084,
+      "num_tokens": 1326584.0,
+      "step": 570
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 0.11256464570760727,
+      "learning_rate": 4.21e-05,
+      "loss": 0.1566,
+      "mean_token_accuracy": 0.9770786449313164,
+      "num_tokens": 1351586.0,
+      "step": 580
+    },
+    {
+      "epoch": 1.3111111111111111,
+      "grad_norm": 0.19633373618125916,
+      "learning_rate": 4.11e-05,
+      "loss": 0.1815,
+      "mean_token_accuracy": 0.9755366548895836,
+      "num_tokens": 1372532.0,
+      "step": 590
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.1573602855205536,
+      "learning_rate": 4.0100000000000006e-05,
+      "loss": 0.1666,
+      "mean_token_accuracy": 0.9768186181783676,
+      "num_tokens": 1395159.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_loss": 0.17687298357486725,
+      "eval_mean_token_accuracy": 0.9778035506606102,
+      "eval_num_tokens": 1395159.0,
+      "eval_runtime": 40.6718,
+      "eval_samples_per_second": 4.917,
+      "eval_steps_per_second": 4.917,
+      "step": 600
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.13229654729366302,
+      "learning_rate": 3.91e-05,
+      "loss": 0.1554,
+      "mean_token_accuracy": 0.9773815423250198,
+      "num_tokens": 1419268.0,
+      "step": 610
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 0.13749773800373077,
+      "learning_rate": 3.8100000000000005e-05,
+      "loss": 0.1619,
+      "mean_token_accuracy": 0.9785586386919022,
+      "num_tokens": 1443302.0,
+      "step": 620
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.1410885453224182,
+      "learning_rate": 3.71e-05,
+      "loss": 0.1665,
+      "mean_token_accuracy": 0.9780510842800141,
+      "num_tokens": 1465561.0,
+      "step": 630
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 0.191091850399971,
+      "learning_rate": 3.61e-05,
+      "loss": 0.1655,
+      "mean_token_accuracy": 0.9782152384519577,
+      "num_tokens": 1488865.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.19034996628761292,
+      "learning_rate": 3.51e-05,
+      "loss": 0.1692,
+      "mean_token_accuracy": 0.9753783032298088,
+      "num_tokens": 1510010.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "eval_loss": 0.17606773972511292,
+      "eval_mean_token_accuracy": 0.9765824827551842,
+      "eval_num_tokens": 1510010.0,
+      "eval_runtime": 40.6251,
+      "eval_samples_per_second": 4.923,
+      "eval_steps_per_second": 4.923,
+      "step": 650
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.1246759369969368,
+      "learning_rate": 3.41e-05,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.9783496215939522,
+      "num_tokens": 1533645.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 0.14433911442756653,
+      "learning_rate": 3.3100000000000005e-05,
+      "loss": 0.1751,
+      "mean_token_accuracy": 0.9757299274206161,
+      "num_tokens": 1555222.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 0.09897135943174362,
+      "learning_rate": 3.21e-05,
+      "loss": 0.1538,
+      "mean_token_accuracy": 0.9790621817111969,
+      "num_tokens": 1578797.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.11254730075597763,
+      "learning_rate": 3.1100000000000004e-05,
+      "loss": 0.1506,
+      "mean_token_accuracy": 0.9802307024598121,
+      "num_tokens": 1604438.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.10534244775772095,
+      "learning_rate": 3.01e-05,
+      "loss": 0.1642,
+      "mean_token_accuracy": 0.9772371336817741,
+      "num_tokens": 1626780.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "eval_loss": 0.17524176836013794,
+      "eval_mean_token_accuracy": 0.9759097599983215,
+      "eval_num_tokens": 1626780.0,
+      "eval_runtime": 41.004,
+      "eval_samples_per_second": 4.878,
+      "eval_steps_per_second": 4.878,
+      "step": 700
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 0.14336709678173065,
+      "learning_rate": 2.91e-05,
+      "loss": 0.1595,
+      "mean_token_accuracy": 0.977231676876545,
+      "num_tokens": 1649439.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.18425902724266052,
+      "learning_rate": 2.8100000000000005e-05,
+      "loss": 0.1646,
+      "mean_token_accuracy": 0.9778214260935784,
+      "num_tokens": 1671958.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.12844131886959076,
+      "learning_rate": 2.7100000000000005e-05,
+      "loss": 0.1693,
+      "mean_token_accuracy": 0.9771967604756355,
+      "num_tokens": 1694994.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 0.12891170382499695,
+      "learning_rate": 2.61e-05,
+      "loss": 0.161,
+      "mean_token_accuracy": 0.9793439760804177,
+      "num_tokens": 1719686.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.12332133948802948,
+      "learning_rate": 2.51e-05,
+      "loss": 0.1555,
+      "mean_token_accuracy": 0.9788334503769874,
+      "num_tokens": 1744365.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 0.1749415248632431,
+      "eval_mean_token_accuracy": 0.9778647214174271,
+      "eval_num_tokens": 1744365.0,
+      "eval_runtime": 40.6207,
+      "eval_samples_per_second": 4.924,
+      "eval_steps_per_second": 4.924,
+      "step": 750
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 0.20146825909614563,
+      "learning_rate": 2.41e-05,
+      "loss": 0.1559,
+      "mean_token_accuracy": 0.9788876891136169,
+      "num_tokens": 1768804.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.12395230680704117,
+      "learning_rate": 2.3100000000000002e-05,
+      "loss": 0.1606,
+      "mean_token_accuracy": 0.9783805578947067,
+      "num_tokens": 1791264.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.15062493085861206,
+      "learning_rate": 2.2100000000000002e-05,
+      "loss": 0.1594,
+      "mean_token_accuracy": 0.9800337478518486,
+      "num_tokens": 1815439.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.7555555555555555,
+      "grad_norm": 0.14727267622947693,
+      "learning_rate": 2.11e-05,
+      "loss": 0.1609,
+      "mean_token_accuracy": 0.9797701701521874,
+      "num_tokens": 1839541.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.14255313575267792,
+      "learning_rate": 2.01e-05,
+      "loss": 0.1632,
+      "mean_token_accuracy": 0.9785327047109604,
+      "num_tokens": 1862487.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "eval_loss": 0.1741703748703003,
+      "eval_mean_token_accuracy": 0.9780414113402367,
+      "eval_num_tokens": 1862487.0,
+      "eval_runtime": 40.5514,
+      "eval_samples_per_second": 4.932,
+      "eval_steps_per_second": 4.932,
+      "step": 800
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.13947232067584991,
+      "learning_rate": 1.91e-05,
+      "loss": 0.1633,
+      "mean_token_accuracy": 0.9781667277216911,
+      "num_tokens": 1887435.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 0.13715006411075592,
+      "learning_rate": 1.81e-05,
+      "loss": 0.1758,
+      "mean_token_accuracy": 0.9765221685171127,
+      "num_tokens": 1908438.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.8444444444444446,
+      "grad_norm": 0.14724566042423248,
+      "learning_rate": 1.7100000000000002e-05,
+      "loss": 0.1636,
+      "mean_token_accuracy": 0.9784929260611535,
+      "num_tokens": 1931471.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.12384811788797379,
+      "learning_rate": 1.6100000000000002e-05,
+      "loss": 0.15,
+      "mean_token_accuracy": 0.9788558304309845,
+      "num_tokens": 1955944.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.2311498075723648,
+      "learning_rate": 1.51e-05,
+      "loss": 0.1565,
+      "mean_token_accuracy": 0.977969428896904,
+      "num_tokens": 1978822.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "eval_loss": 0.1739804595708847,
+      "eval_mean_token_accuracy": 0.9762575566768646,
+      "eval_num_tokens": 1978822.0,
+      "eval_runtime": 40.9407,
+      "eval_samples_per_second": 4.885,
+      "eval_steps_per_second": 4.885,
+      "step": 850
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 0.15526416897773743,
+      "learning_rate": 1.4099999999999999e-05,
+      "loss": 0.1574,
+      "mean_token_accuracy": 0.9787370949983597,
+      "num_tokens": 2002989.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.13134504854679108,
+      "learning_rate": 1.3100000000000002e-05,
+      "loss": 0.1766,
+      "mean_token_accuracy": 0.9767401814460754,
+      "num_tokens": 2025070.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.24305500090122223,
+      "learning_rate": 1.2100000000000001e-05,
+      "loss": 0.1571,
+      "mean_token_accuracy": 0.978802427649498,
+      "num_tokens": 2048924.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 0.16169771552085876,
+      "learning_rate": 1.11e-05,
+      "loss": 0.1554,
+      "mean_token_accuracy": 0.9774592310190201,
+      "num_tokens": 2072389.0,
+      "step": 890
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.11251533031463623,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 0.1694,
+      "mean_token_accuracy": 0.9790247350931167,
+      "num_tokens": 2092938.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.1734553575515747,
+      "eval_mean_token_accuracy": 0.9805351263284683,
+      "eval_num_tokens": 2092938.0,
+      "eval_runtime": 40.8549,
+      "eval_samples_per_second": 4.895,
+      "eval_steps_per_second": 4.895,
+      "step": 900
+    },
+    {
+      "epoch": 2.022222222222222,
+      "grad_norm": 0.14182798564434052,
+      "learning_rate": 9.100000000000001e-06,
+      "loss": 0.1593,
+      "mean_token_accuracy": 0.9806110426783562,
+      "num_tokens": 2117439.0,
+      "step": 910
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 0.13165000081062317,
+      "learning_rate": 8.1e-06,
+      "loss": 0.1532,
+      "mean_token_accuracy": 0.980982506275177,
+      "num_tokens": 2143284.0,
+      "step": 920
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.13505029678344727,
+      "learning_rate": 7.1e-06,
+      "loss": 0.1602,
+      "mean_token_accuracy": 0.9789509087800979,
+      "num_tokens": 2166692.0,
+      "step": 930
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 0.16785164177417755,
+      "learning_rate": 6.1e-06,
+      "loss": 0.1637,
+      "mean_token_accuracy": 0.9785576567053795,
+      "num_tokens": 2189796.0,
+      "step": 940
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.1329684853553772,
+      "learning_rate": 5.1e-06,
+      "loss": 0.1497,
+      "mean_token_accuracy": 0.9809095978736877,
+      "num_tokens": 2215533.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.111111111111111,
+      "eval_loss": 0.17318324744701385,
+      "eval_mean_token_accuracy": 0.9781925734877587,
+      "eval_num_tokens": 2215533.0,
+      "eval_runtime": 40.6397,
+      "eval_samples_per_second": 4.921,
+      "eval_steps_per_second": 4.921,
+      "step": 950
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.15546564757823944,
+      "learning_rate": 4.1000000000000006e-06,
+      "loss": 0.1598,
+      "mean_token_accuracy": 0.979330213367939,
+      "num_tokens": 2238719.0,
+      "step": 960
+    },
+    {
+      "epoch": 2.1555555555555554,
+      "grad_norm": 0.20469367504119873,
+      "learning_rate": 3.1e-06,
+      "loss": 0.1589,
+      "mean_token_accuracy": 0.9795133844017982,
+      "num_tokens": 2260964.0,
+      "step": 970
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.14832386374473572,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.158,
+      "mean_token_accuracy": 0.9798341304063797,
+      "num_tokens": 2284590.0,
+      "step": 980
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.1651660054922104,
+      "learning_rate": 1.1e-06,
+      "loss": 0.1664,
+      "mean_token_accuracy": 0.9788132831454277,
+      "num_tokens": 2306316.0,
+      "step": 990
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.1315845400094986,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 0.1641,
+      "mean_token_accuracy": 0.978704534471035,
+      "num_tokens": 2328618.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 0.1731773316860199,
+      "eval_mean_token_accuracy": 0.9781978166103363,
+      "eval_num_tokens": 2328618.0,
+      "eval_runtime": 40.7486,
+      "eval_samples_per_second": 4.908,
+      "eval_steps_per_second": 4.908,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1269467899136e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f24a1d1fcf3561539dba436a511a781c825b96e542ffcf6aba86ad917df122
+size 6225

checkpoint-200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Maincode/Maincoder-1B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Maincode/Maincoder-1B
+- 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 0.17.1

checkpoint-200/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Maincode/Maincoder-1B",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dcb540ff4dc2540e2bd363ce28028787b6b6b4f6698a8537fe7d6f58e0f4e74
+size 55111408

checkpoint-200/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-200/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '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 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-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4a3eacd2d7009dd07e34c04f23b77a586b8ab047caa19c0a5fbb3835385cbd
+size 110484131

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475ac8dac7f22b85ca45f829097f3c4fa9f2b7ba63ccc7dba229264b9b144b4f
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124625e167eb28acbfc793cfcb3e8a08b32e7fea06501462bc9e420a5e1beb2a
+size 1383

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793b45e356907c0dd0ce0a30dee131ac2edb92e56cb56cf8c95af4feabe3d5a8
+size 1465

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896