Upload LoRA adapter and tokenizer files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: solidity_qwen_model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# solidity_qwen_model
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) on the solidity_contract dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 192
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B",
+  "bias": "none",
+  "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_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",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49840fc86515e540dc4067a705e4e947842a7182a45cd391701fbde2cea8c64f
+size 161533192

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9975062344139651,
+    "total_flos": 3.3406622246696387e+18,
+    "train_loss": 0.3431886351108551,
+    "train_runtime": 6744.2555,
+    "train_samples_per_second": 5.708,
+    "train_steps_per_second": 0.03
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B
+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 0.12.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B",
+  "bias": "none",
+  "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_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",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754d21f8d0190978922bc6441fd0266095b30f172c011324b9ae13e36fd1d0d3
+size 161533192

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/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3dbb4a0508b0ea66840ab8c1c672a8dda8e70b340e815f727c599c71bf475d
+size 323290986

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907c12226ecdf43dba67851e83271fdef71067a7356fdfbc51102aa77f8dc621
+size 14512

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c823ffdb29651f325e8222b22491b308d123d1a0ffb96706f08fb6efe661de
+size 14512

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7708307d1b959a393541df6c657dca87476d08205aaca5feb82f751cfc227436
+size 1064

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 +1,208 @@
+{
+  "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 messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.49875311720698257,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02493765586034913,
+      "grad_norm": 0.04108215495944023,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.4044,
+      "step": 5
+    },
+    {
+      "epoch": 0.04987531172069826,
+      "grad_norm": 0.025228893384337425,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 0.391,
+      "step": 10
+    },
+    {
+      "epoch": 0.07481296758104738,
+      "grad_norm": 0.025317281484603882,
+      "learning_rate": 4.9309248009941914e-05,
+      "loss": 0.3583,
+      "step": 15
+    },
+    {
+      "epoch": 0.09975062344139651,
+      "grad_norm": 0.023856163024902344,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.3771,
+      "step": 20
+    },
+    {
+      "epoch": 0.12468827930174564,
+      "grad_norm": 0.02556118369102478,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.3408,
+      "step": 25
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "grad_norm": 0.026844358071684837,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.3665,
+      "step": 30
+    },
+    {
+      "epoch": 0.1745635910224439,
+      "grad_norm": 0.02702774479985237,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 0.3508,
+      "step": 35
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 0.02752436138689518,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.3558,
+      "step": 40
+    },
+    {
+      "epoch": 0.22443890274314215,
+      "grad_norm": 0.029124287888407707,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 0.3579,
+      "step": 45
+    },
+    {
+      "epoch": 0.24937655860349128,
+      "grad_norm": 0.03660265728831291,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.3333,
+      "step": 50
+    },
+    {
+      "epoch": 0.2743142144638404,
+      "grad_norm": 0.027973175048828125,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 0.3263,
+      "step": 55
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "grad_norm": 0.03005453571677208,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.3476,
+      "step": 60
+    },
+    {
+      "epoch": 0.32418952618453867,
+      "grad_norm": 0.03571762889623642,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 0.3294,
+      "step": 65
+    },
+    {
+      "epoch": 0.3491271820448878,
+      "grad_norm": 0.03382609412074089,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 0.356,
+      "step": 70
+    },
+    {
+      "epoch": 0.3740648379052369,
+      "grad_norm": 0.03247227147221565,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.3304,
+      "step": 75
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.03641534969210625,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.3436,
+      "step": 80
+    },
+    {
+      "epoch": 0.4239401496259352,
+      "grad_norm": 0.03509656339883804,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.3388,
+      "step": 85
+    },
+    {
+      "epoch": 0.4488778054862843,
+      "grad_norm": 0.03508240357041359,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.3367,
+      "step": 90
+    },
+    {
+      "epoch": 0.47381546134663344,
+      "grad_norm": 0.04164772108197212,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.3561,
+      "step": 95
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 0.03994197025895119,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3182,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 1.6709646114210447e+18,
+  "train_batch_size": 8,
+  "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:f85ee3253ce2430836b5bfdd00d31d93672e95e995579ef99ce619afab5ba0a5
+size 5432

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B
+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 0.12.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B",
+  "bias": "none",
+  "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_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",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49840fc86515e540dc4067a705e4e947842a7182a45cd391701fbde2cea8c64f
+size 161533192

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/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a265c9dd28ae5933c7e78b76975a0e2d10aa210e2cb3259fa8a0708b52b4324a
+size 323290986

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44a482d877d1e427529771f4afc5b8148e12ae31b70daa89b564cb90f2e0365
+size 14512

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d2765fb13b4f4f1821493596447940bdb6e6eba3d84dba8e4cb81cd6c91592
+size 14512

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27b052646dcb561cbd68156c30bd466ce59bda64cf3c8eba9c3c1113af9827c
+size 1064

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

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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 messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,313 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9975062344139651,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02493765586034913,
+      "grad_norm": 0.04108215495944023,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.4044,
+      "step": 5
+    },
+    {
+      "epoch": 0.04987531172069826,
+      "grad_norm": 0.025228893384337425,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 0.391,
+      "step": 10
+    },
+    {
+      "epoch": 0.07481296758104738,
+      "grad_norm": 0.025317281484603882,
+      "learning_rate": 4.9309248009941914e-05,
+      "loss": 0.3583,
+      "step": 15
+    },
+    {
+      "epoch": 0.09975062344139651,
+      "grad_norm": 0.023856163024902344,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.3771,
+      "step": 20
+    },
+    {
+      "epoch": 0.12468827930174564,
+      "grad_norm": 0.02556118369102478,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.3408,
+      "step": 25
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "grad_norm": 0.026844358071684837,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.3665,
+      "step": 30
+    },
+    {
+      "epoch": 0.1745635910224439,
+      "grad_norm": 0.02702774479985237,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 0.3508,
+      "step": 35
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 0.02752436138689518,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.3558,
+      "step": 40
+    },
+    {
+      "epoch": 0.22443890274314215,
+      "grad_norm": 0.029124287888407707,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 0.3579,
+      "step": 45
+    },
+    {
+      "epoch": 0.24937655860349128,
+      "grad_norm": 0.03660265728831291,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.3333,
+      "step": 50
+    },
+    {
+      "epoch": 0.2743142144638404,
+      "grad_norm": 0.027973175048828125,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 0.3263,
+      "step": 55
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "grad_norm": 0.03005453571677208,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.3476,
+      "step": 60
+    },
+    {
+      "epoch": 0.32418952618453867,
+      "grad_norm": 0.03571762889623642,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 0.3294,
+      "step": 65
+    },
+    {
+      "epoch": 0.3491271820448878,
+      "grad_norm": 0.03382609412074089,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 0.356,
+      "step": 70
+    },
+    {
+      "epoch": 0.3740648379052369,
+      "grad_norm": 0.03247227147221565,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.3304,
+      "step": 75
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.03641534969210625,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.3436,
+      "step": 80
+    },
+    {
+      "epoch": 0.4239401496259352,
+      "grad_norm": 0.03509656339883804,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.3388,
+      "step": 85
+    },
+    {
+      "epoch": 0.4488778054862843,
+      "grad_norm": 0.03508240357041359,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.3367,
+      "step": 90
+    },
+    {
+      "epoch": 0.47381546134663344,
+      "grad_norm": 0.04164772108197212,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.3561,
+      "step": 95
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 0.03994197025895119,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3182,
+      "step": 100
+    },
+    {
+      "epoch": 0.5236907730673317,
+      "grad_norm": 0.038153909146785736,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.3331,
+      "step": 105
+    },
+    {
+      "epoch": 0.5486284289276808,
+      "grad_norm": 0.03781621903181076,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.3383,
+      "step": 110
+    },
+    {
+      "epoch": 0.57356608478803,
+      "grad_norm": 0.04167185723781586,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.3366,
+      "step": 115
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 0.042504750192165375,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.3324,
+      "step": 120
+    },
+    {
+      "epoch": 0.6234413965087282,
+      "grad_norm": 0.043039821088314056,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.303,
+      "step": 125
+    },
+    {
+      "epoch": 0.6483790523690773,
+      "grad_norm": 0.04201623052358627,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.35,
+      "step": 130
+    },
+    {
+      "epoch": 0.6733167082294265,
+      "grad_norm": 0.04364593327045441,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.331,
+      "step": 135
+    },
+    {
+      "epoch": 0.6982543640897756,
+      "grad_norm": 0.04168755188584328,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.344,
+      "step": 140
+    },
+    {
+      "epoch": 0.7231920199501247,
+      "grad_norm": 0.04454099014401436,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.3567,
+      "step": 145
+    },
+    {
+      "epoch": 0.7481296758104738,
+      "grad_norm": 0.07072897255420685,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.3184,
+      "step": 150
+    },
+    {
+      "epoch": 0.773067331670823,
+      "grad_norm": 0.04532039538025856,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.3279,
+      "step": 155
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 0.04330899938941002,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.3372,
+      "step": 160
+    },
+    {
+      "epoch": 0.8229426433915212,
+      "grad_norm": 0.04454395920038223,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.3553,
+      "step": 165
+    },
+    {
+      "epoch": 0.8478802992518704,
+      "grad_norm": 0.05742543563246727,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.3361,
+      "step": 170
+    },
+    {
+      "epoch": 0.8728179551122195,
+      "grad_norm": 0.04155350476503372,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.3335,
+      "step": 175
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "grad_norm": 0.04169079288840294,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.3425,
+      "step": 180
+    },
+    {
+      "epoch": 0.9226932668329177,
+      "grad_norm": 0.04245175048708916,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.3247,
+      "step": 185
+    },
+    {
+      "epoch": 0.9476309226932669,
+      "grad_norm": 0.03987717628479004,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.3314,
+      "step": 190
+    },
+    {
+      "epoch": 0.972568578553616,
+      "grad_norm": 0.11724965274333954,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.3354,
+      "step": 195
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 0.04020114243030548,
+      "learning_rate": 0.0,
+      "loss": 0.3413,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 3.3406622246696387e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f85ee3253ce2430836b5bfdd00d31d93672e95e995579ef99ce619afab5ba0a5
+size 5432

llamaboard_config.yaml

@@ -0,0 +1,66 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Qwen2.5-Coder-7B
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: default
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 8
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- solidity_contract
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 12
+train.learning_rate: 5e-5
+train.logging_steps: 5
+train.lora_alpha: 32
+train.lora_dropout: 0.1
+train.lora_rank: 16
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '1.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.shift_attn: false
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 0

running_log.txt

@@ -0,0 +1,397 @@
+[WARNING|2025-03-26 10:33:41] logging.py:162 >> `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+[INFO|2025-03-26 10:33:41] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2025-03-26 10:33:42] parser.py:355 >> Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2025-03-26 10:33:42] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/config.json
+
+[INFO|2025-03-26 10:33:42] configuration_utils.py:746 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-26 10:33:43] tokenization_utils_base.py:2211 >> loading file vocab.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/vocab.json
+
+[INFO|2025-03-26 10:33:43] tokenization_utils_base.py:2211 >> loading file merges.txt from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/merges.txt
+
+[INFO|2025-03-26 10:33:43] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/tokenizer.json
+
+[INFO|2025-03-26 10:33:43] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-03-26 10:33:43] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-03-26 10:33:43] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/tokenizer_config.json
+
+[INFO|2025-03-26 10:33:43] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-03-26 10:33:44] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/config.json
+
+[INFO|2025-03-26 10:33:44] configuration_utils.py:746 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-26 10:33:44] tokenization_utils_base.py:2211 >> loading file vocab.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/vocab.json
+
+[INFO|2025-03-26 10:33:44] tokenization_utils_base.py:2211 >> loading file merges.txt from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/merges.txt
+
+[INFO|2025-03-26 10:33:44] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/tokenizer.json
+
+[INFO|2025-03-26 10:33:44] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-03-26 10:33:44] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-03-26 10:33:44] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/tokenizer_config.json
+
+[INFO|2025-03-26 10:33:45] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-03-26 10:33:45] logging.py:157 >> Loading dataset new-datasets/solidity_v3.json...
+
+[INFO|2025-03-26 10:34:08] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/config.json
+
+[INFO|2025-03-26 10:34:08] configuration_utils.py:746 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-26 10:34:08] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/model.safetensors.index.json
+
+[INFO|2025-03-26 10:34:08] modeling_utils.py:1670 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-03-26 10:34:08] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151643
+}
+
+
+[INFO|2025-03-26 10:34:14] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.
+
+
+[INFO|2025-03-26 10:34:14] modeling_utils.py:4808 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-Coder-7B.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
+
+[INFO|2025-03-26 10:34:14] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/generation_config.json
+
+[INFO|2025-03-26 10:34:14] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048
+}
+
+
+[INFO|2025-03-26 10:34:14] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-03-26 10:34:14] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-03-26 10:34:14] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-03-26 10:34:14] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2025-03-26 10:34:14] logging.py:157 >> Found linear modules: q_proj,k_proj,up_proj,down_proj,gate_proj,o_proj,v_proj
+
+[INFO|2025-03-26 10:34:15] logging.py:157 >> trainable params: 40,370,176 || all params: 7,655,986,688 || trainable%: 0.5273
+
+[INFO|2025-03-26 10:34:15] trainer.py:698 >> Using auto half precision backend
+
+[INFO|2025-03-26 10:34:15] trainer.py:2313 >> ***** Running training *****
+
+[INFO|2025-03-26 10:34:15] trainer.py:2314 >>   Num examples = 38,495
+
+[INFO|2025-03-26 10:34:15] trainer.py:2315 >>   Num Epochs = 1
+
+[INFO|2025-03-26 10:34:15] trainer.py:2316 >>   Instantaneous batch size per device = 8
+
+[INFO|2025-03-26 10:34:15] trainer.py:2319 >>   Total train batch size (w. parallel, distributed & accumulation) = 192
+
+[INFO|2025-03-26 10:34:15] trainer.py:2320 >>   Gradient Accumulation steps = 12
+
+[INFO|2025-03-26 10:34:15] trainer.py:2321 >>   Total optimization steps = 200
+
+[INFO|2025-03-26 10:34:15] trainer.py:2322 >>   Number of trainable parameters = 40,370,176
+
+[INFO|2025-03-26 10:37:04] logging.py:157 >> {'loss': 0.4044, 'learning_rate': 4.9923e-05, 'epoch': 0.02}
+
+[INFO|2025-03-26 10:39:53] logging.py:157 >> {'loss': 0.3910, 'learning_rate': 4.9692e-05, 'epoch': 0.05}
+
+[INFO|2025-03-26 10:42:42] logging.py:157 >> {'loss': 0.3583, 'learning_rate': 4.9309e-05, 'epoch': 0.07}
+
+[INFO|2025-03-26 10:45:30] logging.py:157 >> {'loss': 0.3771, 'learning_rate': 4.8776e-05, 'epoch': 0.10}
+
+[INFO|2025-03-26 10:48:19] logging.py:157 >> {'loss': 0.3408, 'learning_rate': 4.8097e-05, 'epoch': 0.12}
+
+[INFO|2025-03-26 10:51:08] logging.py:157 >> {'loss': 0.3665, 'learning_rate': 4.7275e-05, 'epoch': 0.15}
+
+[INFO|2025-03-26 10:53:56] logging.py:157 >> {'loss': 0.3508, 'learning_rate': 4.6316e-05, 'epoch': 0.17}
+
+[INFO|2025-03-26 10:56:44] logging.py:157 >> {'loss': 0.3558, 'learning_rate': 4.5225e-05, 'epoch': 0.20}
+
+[INFO|2025-03-26 10:59:33] logging.py:157 >> {'loss': 0.3579, 'learning_rate': 4.4010e-05, 'epoch': 0.22}
+
+[INFO|2025-03-26 11:02:21] logging.py:157 >> {'loss': 0.3333, 'learning_rate': 4.2678e-05, 'epoch': 0.25}
+
+[INFO|2025-03-26 11:05:10] logging.py:157 >> {'loss': 0.3263, 'learning_rate': 4.1236e-05, 'epoch': 0.27}
+
+[INFO|2025-03-26 11:07:58] logging.py:157 >> {'loss': 0.3476, 'learning_rate': 3.9695e-05, 'epoch': 0.30}
+
+[INFO|2025-03-26 11:10:47] logging.py:157 >> {'loss': 0.3294, 'learning_rate': 3.8062e-05, 'epoch': 0.32}
+
+[INFO|2025-03-26 11:13:35] logging.py:157 >> {'loss': 0.3560, 'learning_rate': 3.6350e-05, 'epoch': 0.35}
+
+[INFO|2025-03-26 11:16:24] logging.py:157 >> {'loss': 0.3304, 'learning_rate': 3.4567e-05, 'epoch': 0.37}
+
+[INFO|2025-03-26 11:19:13] logging.py:157 >> {'loss': 0.3436, 'learning_rate': 3.2725e-05, 'epoch': 0.40}
+
+[INFO|2025-03-26 11:22:01] logging.py:157 >> {'loss': 0.3388, 'learning_rate': 3.0836e-05, 'epoch': 0.42}
+
+[INFO|2025-03-26 11:24:49] logging.py:157 >> {'loss': 0.3367, 'learning_rate': 2.8911e-05, 'epoch': 0.45}
+
+[INFO|2025-03-26 11:27:38] logging.py:157 >> {'loss': 0.3561, 'learning_rate': 2.6961e-05, 'epoch': 0.47}
+
+[INFO|2025-03-26 11:30:26] logging.py:157 >> {'loss': 0.3182, 'learning_rate': 2.5000e-05, 'epoch': 0.50}
+
+[INFO|2025-03-26 11:30:26] trainer.py:3801 >> Saving model checkpoint to saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model/checkpoint-100
+
+[INFO|2025-03-26 11:30:27] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/config.json
+
+[INFO|2025-03-26 11:30:27] configuration_utils.py:746 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-26 11:30:27] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model/checkpoint-100/tokenizer_config.json
+
+[INFO|2025-03-26 11:30:27] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model/checkpoint-100/special_tokens_map.json
+
+[INFO|2025-03-26 11:33:17] logging.py:157 >> {'loss': 0.3331, 'learning_rate': 2.3039e-05, 'epoch': 0.52}
+
+[INFO|2025-03-26 11:36:05] logging.py:157 >> {'loss': 0.3383, 'learning_rate': 2.1089e-05, 'epoch': 0.55}
+
+[INFO|2025-03-26 11:38:54] logging.py:157 >> {'loss': 0.3366, 'learning_rate': 1.9164e-05, 'epoch': 0.57}
+
+[INFO|2025-03-26 11:41:43] logging.py:157 >> {'loss': 0.3324, 'learning_rate': 1.7275e-05, 'epoch': 0.60}
+
+[INFO|2025-03-26 11:44:31] logging.py:157 >> {'loss': 0.3030, 'learning_rate': 1.5433e-05, 'epoch': 0.62}
+
+[INFO|2025-03-26 11:47:20] logging.py:157 >> {'loss': 0.3500, 'learning_rate': 1.3650e-05, 'epoch': 0.65}
+
+[INFO|2025-03-26 11:50:08] logging.py:157 >> {'loss': 0.3310, 'learning_rate': 1.1938e-05, 'epoch': 0.67}
+
+[INFO|2025-03-26 11:52:57] logging.py:157 >> {'loss': 0.3440, 'learning_rate': 1.0305e-05, 'epoch': 0.70}
+
+[INFO|2025-03-26 11:55:45] logging.py:157 >> {'loss': 0.3567, 'learning_rate': 8.7638e-06, 'epoch': 0.72}
+
+[INFO|2025-03-26 11:58:34] logging.py:157 >> {'loss': 0.3184, 'learning_rate': 7.3223e-06, 'epoch': 0.75}
+
+[INFO|2025-03-26 12:01:21] logging.py:157 >> {'loss': 0.3279, 'learning_rate': 5.9899e-06, 'epoch': 0.77}
+
+[INFO|2025-03-26 12:04:10] logging.py:157 >> {'loss': 0.3372, 'learning_rate': 4.7746e-06, 'epoch': 0.80}
+
+[INFO|2025-03-26 12:06:58] logging.py:157 >> {'loss': 0.3553, 'learning_rate': 3.6840e-06, 'epoch': 0.82}
+
+[INFO|2025-03-26 12:09:47] logging.py:157 >> {'loss': 0.3361, 'learning_rate': 2.7248e-06, 'epoch': 0.85}
+
+[INFO|2025-03-26 12:12:36] logging.py:157 >> {'loss': 0.3335, 'learning_rate': 1.9030e-06, 'epoch': 0.87}
+
+[INFO|2025-03-26 12:15:25] logging.py:157 >> {'loss': 0.3425, 'learning_rate': 1.2236e-06, 'epoch': 0.90}
+
+[INFO|2025-03-26 12:18:12] logging.py:157 >> {'loss': 0.3247, 'learning_rate': 6.9075e-07, 'epoch': 0.92}
+
+[INFO|2025-03-26 12:21:01] logging.py:157 >> {'loss': 0.3314, 'learning_rate': 3.0779e-07, 'epoch': 0.95}
+
+[INFO|2025-03-26 12:23:49] logging.py:157 >> {'loss': 0.3354, 'learning_rate': 7.7067e-08, 'epoch': 0.97}
+
+[INFO|2025-03-26 12:26:38] logging.py:157 >> {'loss': 0.3413, 'learning_rate': 0.0000e+00, 'epoch': 1.00}
+
+[INFO|2025-03-26 12:26:38] trainer.py:3801 >> Saving model checkpoint to saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model/checkpoint-200
+
+[INFO|2025-03-26 12:26:38] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/config.json
+
+[INFO|2025-03-26 12:26:38] configuration_utils.py:746 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-26 12:26:39] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model/checkpoint-200/tokenizer_config.json
+
+[INFO|2025-03-26 12:26:39] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model/checkpoint-200/special_tokens_map.json
+
+[INFO|2025-03-26 12:26:39] trainer.py:2584 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-03-26 12:26:39] trainer.py:3801 >> Saving model checkpoint to saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model
+
+[INFO|2025-03-26 12:26:40] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B/snapshots/0396a76181e127dfc13e5c5ec48a8cee09938b02/config.json
+
+[INFO|2025-03-26 12:26:40] configuration_utils.py:746 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-26 12:26:40] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model/tokenizer_config.json
+
+[INFO|2025-03-26 12:26:40] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model/special_tokens_map.json
+
+[WARNING|2025-03-26 12:26:40] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-03-26 12:26:40] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-03-26 12:26:40] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

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
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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 messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9975062344139651,
+    "total_flos": 3.3406622246696387e+18,
+    "train_loss": 0.3431886351108551,
+    "train_runtime": 6744.2555,
+    "train_samples_per_second": 5.708,
+    "train_steps_per_second": 0.03
+}

trainer_log.jsonl

@@ -0,0 +1,41 @@
+{"current_steps": 5, "total_steps": 200, "loss": 0.4044, "lr": 4.99229333433282e-05, "epoch": 0.02493765586034913, "percentage": 2.5, "elapsed_time": "0:02:49", "remaining_time": "1:50:03"}
+{"current_steps": 10, "total_steps": 200, "loss": 0.391, "lr": 4.9692208514878444e-05, "epoch": 0.04987531172069826, "percentage": 5.0, "elapsed_time": "0:05:38", "remaining_time": "1:47:04"}
+{"current_steps": 15, "total_steps": 200, "loss": 0.3583, "lr": 4.9309248009941914e-05, "epoch": 0.07481296758104738, "percentage": 7.5, "elapsed_time": "0:08:26", "remaining_time": "1:44:07"}
+{"current_steps": 20, "total_steps": 200, "loss": 0.3771, "lr": 4.877641290737884e-05, "epoch": 0.09975062344139651, "percentage": 10.0, "elapsed_time": "0:11:15", "remaining_time": "1:41:18"}
+{"current_steps": 25, "total_steps": 200, "loss": 0.3408, "lr": 4.8096988312782174e-05, "epoch": 0.12468827930174564, "percentage": 12.5, "elapsed_time": "0:14:04", "remaining_time": "1:38:30"}
+{"current_steps": 30, "total_steps": 200, "loss": 0.3665, "lr": 4.72751631047092e-05, "epoch": 0.14962593516209477, "percentage": 15.0, "elapsed_time": "0:16:52", "remaining_time": "1:35:40"}
+{"current_steps": 35, "total_steps": 200, "loss": 0.3508, "lr": 4.6316004108852305e-05, "epoch": 0.1745635910224439, "percentage": 17.5, "elapsed_time": "0:19:40", "remaining_time": "1:32:45"}
+{"current_steps": 40, "total_steps": 200, "loss": 0.3558, "lr": 4.522542485937369e-05, "epoch": 0.19950124688279303, "percentage": 20.0, "elapsed_time": "0:22:29", "remaining_time": "1:29:56"}
+{"current_steps": 45, "total_steps": 200, "loss": 0.3579, "lr": 4.401014914000078e-05, "epoch": 0.22443890274314215, "percentage": 22.5, "elapsed_time": "0:25:17", "remaining_time": "1:27:07"}
+{"current_steps": 50, "total_steps": 200, "loss": 0.3333, "lr": 4.267766952966369e-05, "epoch": 0.24937655860349128, "percentage": 25.0, "elapsed_time": "0:28:05", "remaining_time": "1:24:17"}
+{"current_steps": 55, "total_steps": 200, "loss": 0.3263, "lr": 4.123620120825459e-05, "epoch": 0.2743142144638404, "percentage": 27.5, "elapsed_time": "0:30:54", "remaining_time": "1:21:29"}
+{"current_steps": 60, "total_steps": 200, "loss": 0.3476, "lr": 3.969463130731183e-05, "epoch": 0.29925187032418954, "percentage": 30.0, "elapsed_time": "0:33:43", "remaining_time": "1:18:40"}
+{"current_steps": 65, "total_steps": 200, "loss": 0.3294, "lr": 3.8062464117898724e-05, "epoch": 0.32418952618453867, "percentage": 32.5, "elapsed_time": "0:36:31", "remaining_time": "1:15:52"}
+{"current_steps": 70, "total_steps": 200, "loss": 0.356, "lr": 3.634976249348867e-05, "epoch": 0.3491271820448878, "percentage": 35.0, "elapsed_time": "0:39:20", "remaining_time": "1:13:03"}
+{"current_steps": 75, "total_steps": 200, "loss": 0.3304, "lr": 3.456708580912725e-05, "epoch": 0.3740648379052369, "percentage": 37.5, "elapsed_time": "0:42:09", "remaining_time": "1:10:15"}
+{"current_steps": 80, "total_steps": 200, "loss": 0.3436, "lr": 3.272542485937369e-05, "epoch": 0.39900249376558605, "percentage": 40.0, "elapsed_time": "0:44:57", "remaining_time": "1:07:26"}
+{"current_steps": 85, "total_steps": 200, "loss": 0.3388, "lr": 3.083613409639764e-05, "epoch": 0.4239401496259352, "percentage": 42.5, "elapsed_time": "0:47:45", "remaining_time": "1:04:37"}
+{"current_steps": 90, "total_steps": 200, "loss": 0.3367, "lr": 2.8910861626005776e-05, "epoch": 0.4488778054862843, "percentage": 45.0, "elapsed_time": "0:50:34", "remaining_time": "1:01:48"}
+{"current_steps": 95, "total_steps": 200, "loss": 0.3561, "lr": 2.6961477393196126e-05, "epoch": 0.47381546134663344, "percentage": 47.5, "elapsed_time": "0:53:23", "remaining_time": "0:59:00"}
+{"current_steps": 100, "total_steps": 200, "loss": 0.3182, "lr": 2.5e-05, "epoch": 0.49875311720698257, "percentage": 50.0, "elapsed_time": "0:56:11", "remaining_time": "0:56:11"}
+{"current_steps": 105, "total_steps": 200, "loss": 0.3331, "lr": 2.303852260680388e-05, "epoch": 0.5236907730673317, "percentage": 52.5, "elapsed_time": "0:59:01", "remaining_time": "0:53:24"}
+{"current_steps": 110, "total_steps": 200, "loss": 0.3383, "lr": 2.1089138373994223e-05, "epoch": 0.5486284289276808, "percentage": 55.0, "elapsed_time": "1:01:50", "remaining_time": "0:50:35"}
+{"current_steps": 115, "total_steps": 200, "loss": 0.3366, "lr": 1.9163865903602374e-05, "epoch": 0.57356608478803, "percentage": 57.5, "elapsed_time": "1:04:39", "remaining_time": "0:47:47"}
+{"current_steps": 120, "total_steps": 200, "loss": 0.3324, "lr": 1.7274575140626318e-05, "epoch": 0.5985037406483791, "percentage": 60.0, "elapsed_time": "1:07:27", "remaining_time": "0:44:58"}
+{"current_steps": 125, "total_steps": 200, "loss": 0.303, "lr": 1.5432914190872757e-05, "epoch": 0.6234413965087282, "percentage": 62.5, "elapsed_time": "1:10:16", "remaining_time": "0:42:09"}
+{"current_steps": 130, "total_steps": 200, "loss": 0.35, "lr": 1.3650237506511331e-05, "epoch": 0.6483790523690773, "percentage": 65.0, "elapsed_time": "1:13:04", "remaining_time": "0:39:20"}
+{"current_steps": 135, "total_steps": 200, "loss": 0.331, "lr": 1.1937535882101281e-05, "epoch": 0.6733167082294265, "percentage": 67.5, "elapsed_time": "1:15:53", "remaining_time": "0:36:32"}
+{"current_steps": 140, "total_steps": 200, "loss": 0.344, "lr": 1.0305368692688174e-05, "epoch": 0.6982543640897756, "percentage": 70.0, "elapsed_time": "1:18:41", "remaining_time": "0:33:43"}
+{"current_steps": 145, "total_steps": 200, "loss": 0.3567, "lr": 8.763798791745411e-06, "epoch": 0.7231920199501247, "percentage": 72.5, "elapsed_time": "1:21:29", "remaining_time": "0:30:54"}
+{"current_steps": 150, "total_steps": 200, "loss": 0.3184, "lr": 7.3223304703363135e-06, "epoch": 0.7481296758104738, "percentage": 75.0, "elapsed_time": "1:24:18", "remaining_time": "0:28:06"}
+{"current_steps": 155, "total_steps": 200, "loss": 0.3279, "lr": 5.989850859999227e-06, "epoch": 0.773067331670823, "percentage": 77.5, "elapsed_time": "1:27:06", "remaining_time": "0:25:17"}
+{"current_steps": 160, "total_steps": 200, "loss": 0.3372, "lr": 4.7745751406263165e-06, "epoch": 0.7980049875311721, "percentage": 80.0, "elapsed_time": "1:29:54", "remaining_time": "0:22:28"}
+{"current_steps": 165, "total_steps": 200, "loss": 0.3553, "lr": 3.6839958911476957e-06, "epoch": 0.8229426433915212, "percentage": 82.5, "elapsed_time": "1:32:43", "remaining_time": "0:19:40"}
+{"current_steps": 170, "total_steps": 200, "loss": 0.3361, "lr": 2.7248368952908053e-06, "epoch": 0.8478802992518704, "percentage": 85.0, "elapsed_time": "1:35:31", "remaining_time": "0:16:51"}
+{"current_steps": 175, "total_steps": 200, "loss": 0.3335, "lr": 1.9030116872178316e-06, "epoch": 0.8728179551122195, "percentage": 87.5, "elapsed_time": "1:38:20", "remaining_time": "0:14:02"}
+{"current_steps": 180, "total_steps": 200, "loss": 0.3425, "lr": 1.2235870926211619e-06, "epoch": 0.8977556109725686, "percentage": 90.0, "elapsed_time": "1:41:09", "remaining_time": "0:11:14"}
+{"current_steps": 185, "total_steps": 200, "loss": 0.3247, "lr": 6.907519900580861e-07, "epoch": 0.9226932668329177, "percentage": 92.5, "elapsed_time": "1:43:57", "remaining_time": "0:08:25"}
+{"current_steps": 190, "total_steps": 200, "loss": 0.3314, "lr": 3.077914851215585e-07, "epoch": 0.9476309226932669, "percentage": 95.0, "elapsed_time": "1:46:45", "remaining_time": "0:05:37"}
+{"current_steps": 195, "total_steps": 200, "loss": 0.3354, "lr": 7.706665667180091e-08, "epoch": 0.972568578553616, "percentage": 97.5, "elapsed_time": "1:49:33", "remaining_time": "0:02:48"}
+{"current_steps": 200, "total_steps": 200, "loss": 0.3413, "lr": 0.0, "epoch": 0.9975062344139651, "percentage": 100.0, "elapsed_time": "1:52:22", "remaining_time": "0:00:00"}
+{"current_steps": 200, "total_steps": 200, "epoch": 0.9975062344139651, "percentage": 100.0, "elapsed_time": "1:52:24", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9975062344139651,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02493765586034913,
+      "grad_norm": 0.04108215495944023,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.4044,
+      "step": 5
+    },
+    {
+      "epoch": 0.04987531172069826,
+      "grad_norm": 0.025228893384337425,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 0.391,
+      "step": 10
+    },
+    {
+      "epoch": 0.07481296758104738,
+      "grad_norm": 0.025317281484603882,
+      "learning_rate": 4.9309248009941914e-05,
+      "loss": 0.3583,
+      "step": 15
+    },
+    {
+      "epoch": 0.09975062344139651,
+      "grad_norm": 0.023856163024902344,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.3771,
+      "step": 20
+    },
+    {
+      "epoch": 0.12468827930174564,
+      "grad_norm": 0.02556118369102478,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.3408,
+      "step": 25
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "grad_norm": 0.026844358071684837,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.3665,
+      "step": 30
+    },
+    {
+      "epoch": 0.1745635910224439,
+      "grad_norm": 0.02702774479985237,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 0.3508,
+      "step": 35
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 0.02752436138689518,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.3558,
+      "step": 40
+    },
+    {
+      "epoch": 0.22443890274314215,
+      "grad_norm": 0.029124287888407707,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 0.3579,
+      "step": 45
+    },
+    {
+      "epoch": 0.24937655860349128,
+      "grad_norm": 0.03660265728831291,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.3333,
+      "step": 50
+    },
+    {
+      "epoch": 0.2743142144638404,
+      "grad_norm": 0.027973175048828125,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 0.3263,
+      "step": 55
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "grad_norm": 0.03005453571677208,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.3476,
+      "step": 60
+    },
+    {
+      "epoch": 0.32418952618453867,
+      "grad_norm": 0.03571762889623642,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 0.3294,
+      "step": 65
+    },
+    {
+      "epoch": 0.3491271820448878,
+      "grad_norm": 0.03382609412074089,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 0.356,
+      "step": 70
+    },
+    {
+      "epoch": 0.3740648379052369,
+      "grad_norm": 0.03247227147221565,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.3304,
+      "step": 75
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.03641534969210625,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.3436,
+      "step": 80
+    },
+    {
+      "epoch": 0.4239401496259352,
+      "grad_norm": 0.03509656339883804,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.3388,
+      "step": 85
+    },
+    {
+      "epoch": 0.4488778054862843,
+      "grad_norm": 0.03508240357041359,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.3367,
+      "step": 90
+    },
+    {
+      "epoch": 0.47381546134663344,
+      "grad_norm": 0.04164772108197212,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.3561,
+      "step": 95
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 0.03994197025895119,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3182,
+      "step": 100
+    },
+    {
+      "epoch": 0.5236907730673317,
+      "grad_norm": 0.038153909146785736,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.3331,
+      "step": 105
+    },
+    {
+      "epoch": 0.5486284289276808,
+      "grad_norm": 0.03781621903181076,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.3383,
+      "step": 110
+    },
+    {
+      "epoch": 0.57356608478803,
+      "grad_norm": 0.04167185723781586,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.3366,
+      "step": 115
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 0.042504750192165375,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.3324,
+      "step": 120
+    },
+    {
+      "epoch": 0.6234413965087282,
+      "grad_norm": 0.043039821088314056,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.303,
+      "step": 125
+    },
+    {
+      "epoch": 0.6483790523690773,
+      "grad_norm": 0.04201623052358627,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.35,
+      "step": 130
+    },
+    {
+      "epoch": 0.6733167082294265,
+      "grad_norm": 0.04364593327045441,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.331,
+      "step": 135
+    },
+    {
+      "epoch": 0.6982543640897756,
+      "grad_norm": 0.04168755188584328,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.344,
+      "step": 140
+    },
+    {
+      "epoch": 0.7231920199501247,
+      "grad_norm": 0.04454099014401436,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.3567,
+      "step": 145
+    },
+    {
+      "epoch": 0.7481296758104738,
+      "grad_norm": 0.07072897255420685,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.3184,
+      "step": 150
+    },
+    {
+      "epoch": 0.773067331670823,
+      "grad_norm": 0.04532039538025856,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.3279,
+      "step": 155
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 0.04330899938941002,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.3372,
+      "step": 160
+    },
+    {
+      "epoch": 0.8229426433915212,
+      "grad_norm": 0.04454395920038223,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.3553,
+      "step": 165
+    },
+    {
+      "epoch": 0.8478802992518704,
+      "grad_norm": 0.05742543563246727,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.3361,
+      "step": 170
+    },
+    {
+      "epoch": 0.8728179551122195,
+      "grad_norm": 0.04155350476503372,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.3335,
+      "step": 175
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "grad_norm": 0.04169079288840294,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.3425,
+      "step": 180
+    },
+    {
+      "epoch": 0.9226932668329177,
+      "grad_norm": 0.04245175048708916,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.3247,
+      "step": 185
+    },
+    {
+      "epoch": 0.9476309226932669,
+      "grad_norm": 0.03987717628479004,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.3314,
+      "step": 190
+    },
+    {
+      "epoch": 0.972568578553616,
+      "grad_norm": 0.11724965274333954,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.3354,
+      "step": 195
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 0.04020114243030548,
+      "learning_rate": 0.0,
+      "loss": 0.3413,
+      "step": 200
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "step": 200,
+      "total_flos": 3.3406622246696387e+18,
+      "train_loss": 0.3431886351108551,
+      "train_runtime": 6744.2555,
+      "train_samples_per_second": 5.708,
+      "train_steps_per_second": 0.03
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 3.3406622246696387e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f85ee3253ce2430836b5bfdd00d31d93672e95e995579ef99ce619afab5ba0a5
+size 5432

training_args.yaml

@@ -0,0 +1,31 @@
+bf16: true
+cutoff_len: 2048
+dataset: solidity_contract
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 12
+learning_rate: 5.0e-05
+logging_steps: 5
+lora_alpha: 32
+lora_dropout: 0.1
+lora_rank: 16
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: Qwen/Qwen2.5-Coder-7B
+num_train_epochs: 1.0
+optim: adamw_torch
+output_dir: saves/Qwen2.5-Coder-7B/lora/solidity_qwen_model
+packing: false
+per_device_train_batch_size: 8
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 100
+stage: sft
+template: default
+warmup_steps: 0