Add files using upload-large-folder tool

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 checkpoint-234/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-351/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-117/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ead97c2cc6962b842a9b60e2017f2e75efaf07911114f6416bd8c6678b33026
+size 275341720

checkpoint-117/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7957ee392c79bfc2af1e470e8f491143b64f742b598627a28668c3af52f16992
+size 275341720

checkpoint-117/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4554d490c7479282a2fdcc91e9e692205f42b29aec8bb9e88e98d6896793d893
+size 551070514

checkpoint-117/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bf159e658361c0cccd2a3e111a399d6d175e449e1958e97d4660705b7ec4c8
+size 14512

checkpoint-117/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ca0bbcc57b0eed3876622536cce9c70479a3c9769fa09f4efc9705d3854868
+size 14512

checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4494decdbe1a83ff5b58dd2508b21285c231165e62af90d65758507130cf003
+size 1064

checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8c40885ce999030d3d57acd957f20b4472d53c795b1ea6e3e6fbf2d158b9ac
+size 5624

checkpoint-156/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978991dc4c67b8563e9a3c995b74d2db7da7b602667b501cbac757ff8fd90b8e
+size 275341720

checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f924bc576fbcd25aab3b34860596dbb6aa574a909a76a67008b7c7cfa26039d1
+size 551070514

checkpoint-156/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b292f6863ff83bece683612b656338acd72bcd3f369dc2bbb1b10bdb0e93bb9
+size 14512

checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78309d02640df6538af1eb482daf64fb6f76ffaf745b15f835c5a2f151159b3
+size 1064

checkpoint-156/tokenizer.json

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

checkpoint-195/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af09bcfc5c9eb1d68f630f5031a212a2acd1d3e252c1aa31e467f4a4ac0c908
+size 275341720

checkpoint-195/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1445ce432a0c753b09160c5357b0234b21eb69325b7ca65c10e9cb666766ae
+size 551070514

checkpoint-195/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6d0b1af01d4a6e124ca02c8ec986b32a14e40be4f999a930bf4fdbd6fad371
+size 14512

checkpoint-195/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f3990e8d3f8d5f619a4d8d23cb89b92e23169f9c48a841d5696f2f2e9ff2e1
+size 14512

checkpoint-195/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979953498d2539d45f899df80fda4fda14a4a2127bbdb4b3c9e6d7ff6e26196f
+size 1064

checkpoint-195/tokenizer.json

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

checkpoint-195/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8c40885ce999030d3d57acd957f20b4472d53c795b1ea6e3e6fbf2d158b9ac
+size 5624

checkpoint-234/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1abd5a3cbadab9002d9e44ae450ccddb421df11004e3c73318fd897d57ae22
+size 275341720

checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e473a745fb537e1da419f6378581d4a61de2929a9c0fc8e45f8360c72b0a64f
+size 551070514

checkpoint-234/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f81cb3d048fb7a51b5d46854b43e4720292e5fef7d4e55cf57ec6147f064f78
+size 14512

checkpoint-234/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66871be3862516f808ef622065fabe740ef310dc935a7f7fed35542b86aaa58f
+size 14512

checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a44b8ba0baeba3b44de28439825617514a8a8aa13bed83eef58cd80edca8bbd
+size 1064

checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8c40885ce999030d3d57acd957f20b4472d53c795b1ea6e3e6fbf2d158b9ac
+size 5624

checkpoint-273/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# 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 0.15.0

checkpoint-273/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93c352f236882050b56c17b193929d8903cc9b0dbcaba1c6315294befdea3d6
+size 275341720

checkpoint-273/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3dcae97fc4c9412e17c070a5682a5977a6e7781b7135a682469d20b7fcb6a1a
+size 551070514

checkpoint-273/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32734c7c5035812bdedba79b1dd331181dc9478d6dade2b06ec9d8131829c3e
+size 14512

checkpoint-273/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44d2c8a0f81b45e275b71968fc7afe034f0a7e536ebb564063663f4fb370839
+size 14512

checkpoint-273/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b992a5cf8cbbdedb2819ec7883ceb3d4cc6d15bf9f59a575244bc6143fbf4a09
+size 1064

checkpoint-273/tokenizer.json

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

checkpoint-273/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8c40885ce999030d3d57acd957f20b4472d53c795b1ea6e3e6fbf2d158b9ac
+size 5624

checkpoint-312/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# 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 0.15.0

checkpoint-312/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-312/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7f37d8e4fc1383a823cc1b1423995330831bfd32da913880ed53a4f947a0c9
+size 275341720

checkpoint-312/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-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b396a85cead7abbf1b7e2feab120190f9e6ee7b3e5dbec4ccb6fa57ba7dd2c95
+size 551070514

checkpoint-312/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6410b99c7f6764b4774bf02e5d0dca69f9aa66bc13093bb27d940b58e0f656
+size 14512

checkpoint-312/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799dbea59a0b035386cb6291b62a96a74fa07571aaaf433f4a19e056c12f114f
+size 14512

checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1d5f7931eece9323f32c6f46f6d357cb240f35fb784210d7e9af0a3ed15c59
+size 1064

checkpoint-312/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-312/tokenizer.json

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

checkpoint-312/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-312/trainer_state.json

@@ -0,0 +1,468 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.8126984126984125,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.296919047832489,
+      "learning_rate": 6.41025641025641e-06,
+      "loss": 3.8313,
+      "step": 5
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.33771219849586487,
+      "learning_rate": 1.282051282051282e-05,
+      "loss": 3.8502,
+      "step": 10
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.41062507033348083,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 3.8537,
+      "step": 15
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.5127325057983398,
+      "learning_rate": 2.564102564102564e-05,
+      "loss": 3.6949,
+      "step": 20
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.5786504149436951,
+      "learning_rate": 3.205128205128206e-05,
+      "loss": 3.5371,
+      "step": 25
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.6281372904777527,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 3.3822,
+      "step": 30
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.677841305732727,
+      "learning_rate": 4.4871794871794874e-05,
+      "loss": 3.0836,
+      "step": 35
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7423370480537415,
+      "learning_rate": 4.999899863449631e-05,
+      "loss": 2.5068,
+      "step": 40
+    },
+    {
+      "epoch": 1.126984126984127,
+      "grad_norm": 0.6677795648574829,
+      "learning_rate": 4.9963959264103544e-05,
+      "loss": 1.9914,
+      "step": 45
+    },
+    {
+      "epoch": 1.253968253968254,
+      "grad_norm": 0.7547211050987244,
+      "learning_rate": 4.98789318082748e-05,
+      "loss": 1.7329,
+      "step": 50
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.6714099645614624,
+      "learning_rate": 4.974408652685072e-05,
+      "loss": 1.4401,
+      "step": 55
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.6784941554069519,
+      "learning_rate": 4.955969343539162e-05,
+      "loss": 1.3861,
+      "step": 60
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "grad_norm": 0.8798362016677856,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 1.1406,
+      "step": 65
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.7543187737464905,
+      "learning_rate": 4.90438392204474e-05,
+      "loss": 1.2,
+      "step": 70
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.7632691860198975,
+      "learning_rate": 4.8713411048678635e-05,
+      "loss": 1.1137,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8194475173950195,
+      "learning_rate": 4.83354989019146e-05,
+      "loss": 0.8988,
+      "step": 80
+    },
+    {
+      "epoch": 2.126984126984127,
+      "grad_norm": 0.5129795670509338,
+      "learning_rate": 4.791085951527408e-05,
+      "loss": 1.0144,
+      "step": 85
+    },
+    {
+      "epoch": 2.253968253968254,
+      "grad_norm": 0.5384055972099304,
+      "learning_rate": 4.744034319097535e-05,
+      "loss": 0.9417,
+      "step": 90
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.5197637677192688,
+      "learning_rate": 4.692489209568234e-05,
+      "loss": 0.9124,
+      "step": 95
+    },
+    {
+      "epoch": 2.507936507936508,
+      "grad_norm": 0.5490031838417053,
+      "learning_rate": 4.636553837390051e-05,
+      "loss": 1.0367,
+      "step": 100
+    },
+    {
+      "epoch": 2.634920634920635,
+      "grad_norm": 0.4497690796852112,
+      "learning_rate": 4.5763402081200294e-05,
+      "loss": 0.9391,
+      "step": 105
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.40242263674736023,
+      "learning_rate": 4.511968894140639e-05,
+      "loss": 0.8668,
+      "step": 110
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.4423123598098755,
+      "learning_rate": 4.443568793224415e-05,
+      "loss": 0.9419,
+      "step": 115
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7325336933135986,
+      "learning_rate": 4.371276870427753e-05,
+      "loss": 0.9379,
+      "step": 120
+    },
+    {
+      "epoch": 3.126984126984127,
+      "grad_norm": 0.4649835526943207,
+      "learning_rate": 4.295237883830685e-05,
+      "loss": 0.8399,
+      "step": 125
+    },
+    {
+      "epoch": 3.253968253968254,
+      "grad_norm": 0.49590322375297546,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.8626,
+      "step": 130
+    },
+    {
+      "epoch": 3.380952380952381,
+      "grad_norm": 0.5896856188774109,
+      "learning_rate": 4.132534962458962e-05,
+      "loss": 0.8826,
+      "step": 135
+    },
+    {
+      "epoch": 3.507936507936508,
+      "grad_norm": 0.4864223301410675,
+      "learning_rate": 4.0461968256656376e-05,
+      "loss": 0.8538,
+      "step": 140
+    },
+    {
+      "epoch": 3.634920634920635,
+      "grad_norm": 0.5413251519203186,
+      "learning_rate": 3.956762568653378e-05,
+      "loss": 0.8788,
+      "step": 145
+    },
+    {
+      "epoch": 3.761904761904762,
+      "grad_norm": 0.5263978838920593,
+      "learning_rate": 3.8644112754862614e-05,
+      "loss": 0.8279,
+      "step": 150
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.5732172131538391,
+      "learning_rate": 3.76932787133117e-05,
+      "loss": 0.7522,
+      "step": 155
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8840337991714478,
+      "learning_rate": 3.6717027521617595e-05,
+      "loss": 0.8394,
+      "step": 160
+    },
+    {
+      "epoch": 4.1269841269841265,
+      "grad_norm": 0.5274865031242371,
+      "learning_rate": 3.5717314035076355e-05,
+      "loss": 0.8122,
+      "step": 165
+    },
+    {
+      "epoch": 4.253968253968254,
+      "grad_norm": 0.57438725233078,
+      "learning_rate": 3.4696140090121376e-05,
+      "loss": 0.8541,
+      "step": 170
+    },
+    {
+      "epoch": 4.380952380952381,
+      "grad_norm": 0.6474905610084534,
+      "learning_rate": 3.365555049582582e-05,
+      "loss": 0.7446,
+      "step": 175
+    },
+    {
+      "epoch": 4.507936507936508,
+      "grad_norm": 0.6062578558921814,
+      "learning_rate": 3.2597628939356175e-05,
+      "loss": 0.7282,
+      "step": 180
+    },
+    {
+      "epoch": 4.634920634920634,
+      "grad_norm": 0.7624045610427856,
+      "learning_rate": 3.152449381357593e-05,
+      "loss": 0.6846,
+      "step": 185
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.6446404457092285,
+      "learning_rate": 3.0438293975154186e-05,
+      "loss": 0.7597,
+      "step": 190
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 0.7280287146568298,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.6788,
+      "step": 195
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.213476538658142,
+      "learning_rate": 2.8235422036351382e-05,
+      "loss": 0.7306,
+      "step": 200
+    },
+    {
+      "epoch": 5.1269841269841265,
+      "grad_norm": 0.6391934156417847,
+      "learning_rate": 2.712316098910162e-05,
+      "loss": 0.5925,
+      "step": 205
+    },
+    {
+      "epoch": 5.253968253968254,
+      "grad_norm": 0.6667851209640503,
+      "learning_rate": 2.600664850273538e-05,
+      "loss": 0.6754,
+      "step": 210
+    },
+    {
+      "epoch": 5.380952380952381,
+      "grad_norm": 0.8730446100234985,
+      "learning_rate": 2.4888120293188916e-05,
+      "loss": 0.7179,
+      "step": 215
+    },
+    {
+      "epoch": 5.507936507936508,
+      "grad_norm": 0.8416940569877625,
+      "learning_rate": 2.3769816112703047e-05,
+      "loss": 0.6565,
+      "step": 220
+    },
+    {
+      "epoch": 5.634920634920634,
+      "grad_norm": 0.7638925909996033,
+      "learning_rate": 2.265397526492052e-05,
+      "loss": 0.629,
+      "step": 225
+    },
+    {
+      "epoch": 5.761904761904762,
+      "grad_norm": 0.8404481410980225,
+      "learning_rate": 2.154283212088168e-05,
+      "loss": 0.6779,
+      "step": 230
+    },
+    {
+      "epoch": 5.888888888888889,
+      "grad_norm": 0.7644646167755127,
+      "learning_rate": 2.043861164489719e-05,
+      "loss": 0.6363,
+      "step": 235
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.407417893409729,
+      "learning_rate": 1.934352493925695e-05,
+      "loss": 0.6873,
+      "step": 240
+    },
+    {
+      "epoch": 6.1269841269841265,
+      "grad_norm": 0.8645577430725098,
+      "learning_rate": 1.825976481669641e-05,
+      "loss": 0.6057,
+      "step": 245
+    },
+    {
+      "epoch": 6.253968253968254,
+      "grad_norm": 0.8925438523292542,
+      "learning_rate": 1.7189501409486062e-05,
+      "loss": 0.5787,
+      "step": 250
+    },
+    {
+      "epoch": 6.380952380952381,
+      "grad_norm": 1.0913372039794922,
+      "learning_rate": 1.613487782393661e-05,
+      "loss": 0.5813,
+      "step": 255
+    },
+    {
+      "epoch": 6.507936507936508,
+      "grad_norm": 1.0974910259246826,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 0.5534,
+      "step": 260
+    },
+    {
+      "epoch": 6.634920634920634,
+      "grad_norm": 0.9944404363632202,
+      "learning_rate": 1.4080961727707184e-05,
+      "loss": 0.5976,
+      "step": 265
+    },
+    {
+      "epoch": 6.761904761904762,
+      "grad_norm": 0.9145245552062988,
+      "learning_rate": 1.3085781999467303e-05,
+      "loss": 0.5592,
+      "step": 270
+    },
+    {
+      "epoch": 6.888888888888889,
+      "grad_norm": 1.0390015840530396,
+      "learning_rate": 1.2114459422291205e-05,
+      "loss": 0.5811,
+      "step": 275
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.7172333002090454,
+      "learning_rate": 1.116893898236716e-05,
+      "loss": 0.6019,
+      "step": 280
+    },
+    {
+      "epoch": 7.1269841269841265,
+      "grad_norm": 0.9733636975288391,
+      "learning_rate": 1.0251113999421935e-05,
+      "loss": 0.4985,
+      "step": 285
+    },
+    {
+      "epoch": 7.253968253968254,
+      "grad_norm": 1.0347152948379517,
+      "learning_rate": 9.362822335518063e-06,
+      "loss": 0.5585,
+      "step": 290
+    },
+    {
+      "epoch": 7.380952380952381,
+      "grad_norm": 0.8855388164520264,
+      "learning_rate": 8.505842714900297e-06,
+      "loss": 0.5163,
+      "step": 295
+    },
+    {
+      "epoch": 7.507936507936508,
+      "grad_norm": 1.2762815952301025,
+      "learning_rate": 7.681891162260015e-06,
+      "loss": 0.5637,
+      "step": 300
+    },
+    {
+      "epoch": 7.634920634920634,
+      "grad_norm": 1.1591953039169312,
+      "learning_rate": 6.892617566550044e-06,
+      "loss": 0.4971,
+      "step": 305
+    },
+    {
+      "epoch": 7.761904761904762,
+      "grad_norm": 1.12722647190094,
+      "learning_rate": 6.1396023772302465e-06,
+      "loss": 0.5231,
+      "step": 310
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 39,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6574602364780544e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8c40885ce999030d3d57acd957f20b4472d53c795b1ea6e3e6fbf2d158b9ac
+size 5624