Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-327/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d276a0fbffe1a182923226bdb522064a937d4ce714d0757f20dbc8ae3116ba3
+size 66126768

chat_template.jinja

@@ -0,0 +1,9 @@
+{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+' %}{% 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 }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:
+' + content + '
+
+### Response:
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '
+
+' }}{% endif %}{% endfor %}

checkpoint-250/README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-250/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5000888b2f817c4f6ec297f189f5e14caf4a699c47d159cb79bc424d2bb4bf3b
+size 66126768

checkpoint-250/chat_template.jinja

@@ -0,0 +1,9 @@
+{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+' %}{% 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 }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:
+' + content + '
+
+### Response:
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '
+
+' }}{% endif %}{% endfor %}

checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4665f210f499939bd69f309c641565f8cbffa038125eeb8ca94ae7ebcd00aa
+size 132544890

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b50626f6a2d5823cbb6c20c0d4b035b79d012ee694939c2ea97c3cf603650a
+size 14244

checkpoint-250/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c68c6e81b2043731b2066422bc1aebcfdcc8f836f3eabd6ad514bb6e43a8dc
+size 988

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf437f15cd3fcfec5af14b97a574fe34c305119ffac0aa83e99931515fc14b5
+size 1064

checkpoint-250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

checkpoint-250/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-250/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2942528735632184,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.18391317129135132,
+      "learning_rate": 0.00019449541284403672,
+      "loss": 0.38197338581085205,
+      "step": 10
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.14778141677379608,
+      "learning_rate": 0.00018837920489296636,
+      "loss": 0.12924295663833618,
+      "step": 20
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.0928393080830574,
+      "learning_rate": 0.00018226299694189605,
+      "loss": 0.10623193979263305,
+      "step": 30
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.12639197707176208,
+      "learning_rate": 0.0001761467889908257,
+      "loss": 0.10601885318756103,
+      "step": 40
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.11163435131311417,
+      "learning_rate": 0.00017003058103975534,
+      "loss": 0.09006149768829345,
+      "step": 50
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.06934115290641785,
+      "learning_rate": 0.00016391437308868503,
+      "loss": 0.0927188515663147,
+      "step": 60
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.09345990419387817,
+      "learning_rate": 0.0001577981651376147,
+      "loss": 0.10100839138031006,
+      "step": 70
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.08753989636898041,
+      "learning_rate": 0.00015168195718654435,
+      "loss": 0.0789786159992218,
+      "step": 80
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.13514496386051178,
+      "learning_rate": 0.00014556574923547402,
+      "loss": 0.07820955514907837,
+      "step": 90
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.1325644999742508,
+      "learning_rate": 0.00013944954128440368,
+      "loss": 0.08956178426742553,
+      "step": 100
+    },
+    {
+      "epoch": 1.0091954022988505,
+      "grad_norm": 0.11423685401678085,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.09496147632598877,
+      "step": 110
+    },
+    {
+      "epoch": 1.1011494252873564,
+      "grad_norm": 0.08740504831075668,
+      "learning_rate": 0.000127217125382263,
+      "loss": 0.08737512230873108,
+      "step": 120
+    },
+    {
+      "epoch": 1.193103448275862,
+      "grad_norm": 0.07782809436321259,
+      "learning_rate": 0.00012110091743119268,
+      "loss": 0.07404522895812989,
+      "step": 130
+    },
+    {
+      "epoch": 1.2850574712643679,
+      "grad_norm": 0.14405833184719086,
+      "learning_rate": 0.00011498470948012233,
+      "loss": 0.06943418979644775,
+      "step": 140
+    },
+    {
+      "epoch": 1.3770114942528735,
+      "grad_norm": 0.1064399853348732,
+      "learning_rate": 0.00010886850152905199,
+      "loss": 0.07198014259338378,
+      "step": 150
+    },
+    {
+      "epoch": 1.4689655172413794,
+      "grad_norm": 0.1051010936498642,
+      "learning_rate": 0.00010275229357798166,
+      "loss": 0.07075391411781311,
+      "step": 160
+    },
+    {
+      "epoch": 1.560919540229885,
+      "grad_norm": 0.10268348455429077,
+      "learning_rate": 9.663608562691132e-05,
+      "loss": 0.0763627827167511,
+      "step": 170
+    },
+    {
+      "epoch": 1.6528735632183909,
+      "grad_norm": 0.10808967053890228,
+      "learning_rate": 9.051987767584099e-05,
+      "loss": 0.06987376809120179,
+      "step": 180
+    },
+    {
+      "epoch": 1.7448275862068967,
+      "grad_norm": 0.0796312764286995,
+      "learning_rate": 8.440366972477065e-05,
+      "loss": 0.06609394550323486,
+      "step": 190
+    },
+    {
+      "epoch": 1.8367816091954023,
+      "grad_norm": 0.08713788539171219,
+      "learning_rate": 7.828746177370031e-05,
+      "loss": 0.07024483680725098,
+      "step": 200
+    },
+    {
+      "epoch": 1.928735632183908,
+      "grad_norm": 0.0875263661146164,
+      "learning_rate": 7.217125382262997e-05,
+      "loss": 0.0659551739692688,
+      "step": 210
+    },
+    {
+      "epoch": 2.018390804597701,
+      "grad_norm": 0.12321627140045166,
+      "learning_rate": 6.605504587155963e-05,
+      "loss": 0.06620625853538513,
+      "step": 220
+    },
+    {
+      "epoch": 2.110344827586207,
+      "grad_norm": 0.08318830281496048,
+      "learning_rate": 5.99388379204893e-05,
+      "loss": 0.05962467789649963,
+      "step": 230
+    },
+    {
+      "epoch": 2.2022988505747128,
+      "grad_norm": 0.07575304806232452,
+      "learning_rate": 5.382262996941896e-05,
+      "loss": 0.051931560039520264,
+      "step": 240
+    },
+    {
+      "epoch": 2.2942528735632184,
+      "grad_norm": 0.08224116265773773,
+      "learning_rate": 4.7706422018348626e-05,
+      "loss": 0.06514100432395935,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 327,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.130058760548352e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1315169111d51de66ae42d33f469b1d4e05758f58d5c44dc9a9d3b59fff13006
+size 5176

checkpoint-300/README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-300/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f81844757e6f829405c99f3616950be5c85d94992c155151094b7e4833b11e6
+size 66126768

checkpoint-300/chat_template.jinja

@@ -0,0 +1,9 @@
+{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+' %}{% 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 }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:
+' + content + '
+
+### Response:
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '
+
+' }}{% endif %}{% endfor %}

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c59a95ef0e8b802daf48b72c2fb4291b67cc49ebf734bcb060c4e97c6050f4
+size 132544890

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6669b66bcf1896d0b3276103e568e43beb42b15a6a472e198584faaa016298ac
+size 14244

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c852b1c266b81ad33622067d7dadb27814ab6638ea8e4f9cd67d3515606d043d
+size 988

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d068f0f4bdf6b4cbc451fcd9841e5d16887374f82053fcafe5850b5c68ceb9fb
+size 1064

checkpoint-300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.754022988505747,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.18391317129135132,
+      "learning_rate": 0.00019449541284403672,
+      "loss": 0.38197338581085205,
+      "step": 10
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.14778141677379608,
+      "learning_rate": 0.00018837920489296636,
+      "loss": 0.12924295663833618,
+      "step": 20
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.0928393080830574,
+      "learning_rate": 0.00018226299694189605,
+      "loss": 0.10623193979263305,
+      "step": 30
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.12639197707176208,
+      "learning_rate": 0.0001761467889908257,
+      "loss": 0.10601885318756103,
+      "step": 40
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.11163435131311417,
+      "learning_rate": 0.00017003058103975534,
+      "loss": 0.09006149768829345,
+      "step": 50
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.06934115290641785,
+      "learning_rate": 0.00016391437308868503,
+      "loss": 0.0927188515663147,
+      "step": 60
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.09345990419387817,
+      "learning_rate": 0.0001577981651376147,
+      "loss": 0.10100839138031006,
+      "step": 70
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.08753989636898041,
+      "learning_rate": 0.00015168195718654435,
+      "loss": 0.0789786159992218,
+      "step": 80
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.13514496386051178,
+      "learning_rate": 0.00014556574923547402,
+      "loss": 0.07820955514907837,
+      "step": 90
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.1325644999742508,
+      "learning_rate": 0.00013944954128440368,
+      "loss": 0.08956178426742553,
+      "step": 100
+    },
+    {
+      "epoch": 1.0091954022988505,
+      "grad_norm": 0.11423685401678085,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.09496147632598877,
+      "step": 110
+    },
+    {
+      "epoch": 1.1011494252873564,
+      "grad_norm": 0.08740504831075668,
+      "learning_rate": 0.000127217125382263,
+      "loss": 0.08737512230873108,
+      "step": 120
+    },
+    {
+      "epoch": 1.193103448275862,
+      "grad_norm": 0.07782809436321259,
+      "learning_rate": 0.00012110091743119268,
+      "loss": 0.07404522895812989,
+      "step": 130
+    },
+    {
+      "epoch": 1.2850574712643679,
+      "grad_norm": 0.14405833184719086,
+      "learning_rate": 0.00011498470948012233,
+      "loss": 0.06943418979644775,
+      "step": 140
+    },
+    {
+      "epoch": 1.3770114942528735,
+      "grad_norm": 0.1064399853348732,
+      "learning_rate": 0.00010886850152905199,
+      "loss": 0.07198014259338378,
+      "step": 150
+    },
+    {
+      "epoch": 1.4689655172413794,
+      "grad_norm": 0.1051010936498642,
+      "learning_rate": 0.00010275229357798166,
+      "loss": 0.07075391411781311,
+      "step": 160
+    },
+    {
+      "epoch": 1.560919540229885,
+      "grad_norm": 0.10268348455429077,
+      "learning_rate": 9.663608562691132e-05,
+      "loss": 0.0763627827167511,
+      "step": 170
+    },
+    {
+      "epoch": 1.6528735632183909,
+      "grad_norm": 0.10808967053890228,
+      "learning_rate": 9.051987767584099e-05,
+      "loss": 0.06987376809120179,
+      "step": 180
+    },
+    {
+      "epoch": 1.7448275862068967,
+      "grad_norm": 0.0796312764286995,
+      "learning_rate": 8.440366972477065e-05,
+      "loss": 0.06609394550323486,
+      "step": 190
+    },
+    {
+      "epoch": 1.8367816091954023,
+      "grad_norm": 0.08713788539171219,
+      "learning_rate": 7.828746177370031e-05,
+      "loss": 0.07024483680725098,
+      "step": 200
+    },
+    {
+      "epoch": 1.928735632183908,
+      "grad_norm": 0.0875263661146164,
+      "learning_rate": 7.217125382262997e-05,
+      "loss": 0.0659551739692688,
+      "step": 210
+    },
+    {
+      "epoch": 2.018390804597701,
+      "grad_norm": 0.12321627140045166,
+      "learning_rate": 6.605504587155963e-05,
+      "loss": 0.06620625853538513,
+      "step": 220
+    },
+    {
+      "epoch": 2.110344827586207,
+      "grad_norm": 0.08318830281496048,
+      "learning_rate": 5.99388379204893e-05,
+      "loss": 0.05962467789649963,
+      "step": 230
+    },
+    {
+      "epoch": 2.2022988505747128,
+      "grad_norm": 0.07575304806232452,
+      "learning_rate": 5.382262996941896e-05,
+      "loss": 0.051931560039520264,
+      "step": 240
+    },
+    {
+      "epoch": 2.2942528735632184,
+      "grad_norm": 0.08224116265773773,
+      "learning_rate": 4.7706422018348626e-05,
+      "loss": 0.06514100432395935,
+      "step": 250
+    },
+    {
+      "epoch": 2.386206896551724,
+      "grad_norm": 0.11719097942113876,
+      "learning_rate": 4.159021406727829e-05,
+      "loss": 0.06397714018821717,
+      "step": 260
+    },
+    {
+      "epoch": 2.4781609195402297,
+      "grad_norm": 0.06252411007881165,
+      "learning_rate": 3.5474006116207956e-05,
+      "loss": 0.06488621830940247,
+      "step": 270
+    },
+    {
+      "epoch": 2.5701149425287357,
+      "grad_norm": 0.09748537093400955,
+      "learning_rate": 2.9357798165137618e-05,
+      "loss": 0.060347968339920045,
+      "step": 280
+    },
+    {
+      "epoch": 2.6620689655172414,
+      "grad_norm": 0.08546270430088043,
+      "learning_rate": 2.324159021406728e-05,
+      "loss": 0.05238440036773682,
+      "step": 290
+    },
+    {
+      "epoch": 2.754022988505747,
+      "grad_norm": 0.10481763631105423,
+      "learning_rate": 1.712538226299694e-05,
+      "loss": 0.04942976236343384,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 327,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.758120367825715e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1315169111d51de66ae42d33f469b1d4e05758f58d5c44dc9a9d3b59fff13006
+size 5176

checkpoint-327/README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-327/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-327/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e796a12d1333a1108f38f457e9b9a594bc0eb5db3d699b950a724e66f911f1
+size 66126768

checkpoint-327/chat_template.jinja

@@ -0,0 +1,9 @@
+{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+' %}{% 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 }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:
+' + content + '
+
+### Response:
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '
+
+' }}{% endif %}{% endfor %}

checkpoint-327/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54361732e4c6d9d42d68416fe4a5a482b31c7c251246ff01314f3215e0abec46
+size 132544890

checkpoint-327/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9ad31b6021f870a1f4437a70c3557ab29d153e123c8e0337666b29e088a102
+size 14244

checkpoint-327/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31be240fb8ca2218bce70aa99c841aba39ceb9239110beabd7a49ddb952ba629
+size 988

checkpoint-327/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7c716c5cfcfbd4ffe8b9e080bbfcdce2bd2576fe8183942840531b42f3d7e2
+size 1064

checkpoint-327/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

checkpoint-327/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-327/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 327,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.18391317129135132,
+      "learning_rate": 0.00019449541284403672,
+      "loss": 0.38197338581085205,
+      "step": 10
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.14778141677379608,
+      "learning_rate": 0.00018837920489296636,
+      "loss": 0.12924295663833618,
+      "step": 20
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.0928393080830574,
+      "learning_rate": 0.00018226299694189605,
+      "loss": 0.10623193979263305,
+      "step": 30
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.12639197707176208,
+      "learning_rate": 0.0001761467889908257,
+      "loss": 0.10601885318756103,
+      "step": 40
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.11163435131311417,
+      "learning_rate": 0.00017003058103975534,
+      "loss": 0.09006149768829345,
+      "step": 50
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.06934115290641785,
+      "learning_rate": 0.00016391437308868503,
+      "loss": 0.0927188515663147,
+      "step": 60
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.09345990419387817,
+      "learning_rate": 0.0001577981651376147,
+      "loss": 0.10100839138031006,
+      "step": 70
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.08753989636898041,
+      "learning_rate": 0.00015168195718654435,
+      "loss": 0.0789786159992218,
+      "step": 80
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.13514496386051178,
+      "learning_rate": 0.00014556574923547402,
+      "loss": 0.07820955514907837,
+      "step": 90
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.1325644999742508,
+      "learning_rate": 0.00013944954128440368,
+      "loss": 0.08956178426742553,
+      "step": 100
+    },
+    {
+      "epoch": 1.0091954022988505,
+      "grad_norm": 0.11423685401678085,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.09496147632598877,
+      "step": 110
+    },
+    {
+      "epoch": 1.1011494252873564,
+      "grad_norm": 0.08740504831075668,
+      "learning_rate": 0.000127217125382263,
+      "loss": 0.08737512230873108,
+      "step": 120
+    },
+    {
+      "epoch": 1.193103448275862,
+      "grad_norm": 0.07782809436321259,
+      "learning_rate": 0.00012110091743119268,
+      "loss": 0.07404522895812989,
+      "step": 130
+    },
+    {
+      "epoch": 1.2850574712643679,
+      "grad_norm": 0.14405833184719086,
+      "learning_rate": 0.00011498470948012233,
+      "loss": 0.06943418979644775,
+      "step": 140
+    },
+    {
+      "epoch": 1.3770114942528735,
+      "grad_norm": 0.1064399853348732,
+      "learning_rate": 0.00010886850152905199,
+      "loss": 0.07198014259338378,
+      "step": 150
+    },
+    {
+      "epoch": 1.4689655172413794,
+      "grad_norm": 0.1051010936498642,
+      "learning_rate": 0.00010275229357798166,
+      "loss": 0.07075391411781311,
+      "step": 160
+    },
+    {
+      "epoch": 1.560919540229885,
+      "grad_norm": 0.10268348455429077,
+      "learning_rate": 9.663608562691132e-05,
+      "loss": 0.0763627827167511,
+      "step": 170
+    },
+    {
+      "epoch": 1.6528735632183909,
+      "grad_norm": 0.10808967053890228,
+      "learning_rate": 9.051987767584099e-05,
+      "loss": 0.06987376809120179,
+      "step": 180
+    },
+    {
+      "epoch": 1.7448275862068967,
+      "grad_norm": 0.0796312764286995,
+      "learning_rate": 8.440366972477065e-05,
+      "loss": 0.06609394550323486,
+      "step": 190
+    },
+    {
+      "epoch": 1.8367816091954023,
+      "grad_norm": 0.08713788539171219,
+      "learning_rate": 7.828746177370031e-05,
+      "loss": 0.07024483680725098,
+      "step": 200
+    },
+    {
+      "epoch": 1.928735632183908,
+      "grad_norm": 0.0875263661146164,
+      "learning_rate": 7.217125382262997e-05,
+      "loss": 0.0659551739692688,
+      "step": 210
+    },
+    {
+      "epoch": 2.018390804597701,
+      "grad_norm": 0.12321627140045166,
+      "learning_rate": 6.605504587155963e-05,
+      "loss": 0.06620625853538513,
+      "step": 220
+    },
+    {
+      "epoch": 2.110344827586207,
+      "grad_norm": 0.08318830281496048,
+      "learning_rate": 5.99388379204893e-05,
+      "loss": 0.05962467789649963,
+      "step": 230
+    },
+    {
+      "epoch": 2.2022988505747128,
+      "grad_norm": 0.07575304806232452,
+      "learning_rate": 5.382262996941896e-05,
+      "loss": 0.051931560039520264,
+      "step": 240
+    },
+    {
+      "epoch": 2.2942528735632184,
+      "grad_norm": 0.08224116265773773,
+      "learning_rate": 4.7706422018348626e-05,
+      "loss": 0.06514100432395935,
+      "step": 250
+    },
+    {
+      "epoch": 2.386206896551724,
+      "grad_norm": 0.11719097942113876,
+      "learning_rate": 4.159021406727829e-05,
+      "loss": 0.06397714018821717,
+      "step": 260
+    },
+    {
+      "epoch": 2.4781609195402297,
+      "grad_norm": 0.06252411007881165,
+      "learning_rate": 3.5474006116207956e-05,
+      "loss": 0.06488621830940247,
+      "step": 270
+    },
+    {
+      "epoch": 2.5701149425287357,
+      "grad_norm": 0.09748537093400955,
+      "learning_rate": 2.9357798165137618e-05,
+      "loss": 0.060347968339920045,
+      "step": 280
+    },
+    {
+      "epoch": 2.6620689655172414,
+      "grad_norm": 0.08546270430088043,
+      "learning_rate": 2.324159021406728e-05,
+      "loss": 0.05238440036773682,
+      "step": 290
+    },
+    {
+      "epoch": 2.754022988505747,
+      "grad_norm": 0.10481763631105423,
+      "learning_rate": 1.712538226299694e-05,
+      "loss": 0.04942976236343384,
+      "step": 300
+    },
+    {
+      "epoch": 2.845977011494253,
+      "grad_norm": 0.08988472819328308,
+      "learning_rate": 1.1009174311926607e-05,
+      "loss": 0.0647299349308014,
+      "step": 310
+    },
+    {
+      "epoch": 2.9379310344827587,
+      "grad_norm": 0.08786249905824661,
+      "learning_rate": 4.892966360856269e-06,
+      "loss": 0.06125383973121643,
+      "step": 320
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 327,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.092351880937472e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-327/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1315169111d51de66ae42d33f469b1d4e05758f58d5c44dc9a9d3b59fff13006
+size 5176

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,33 @@
+{"current_steps": 10, "total_steps": 327, "loss": 0.38197338581085205, "lr": 0.00019449541284403672, "epoch": 0.09195402298850575, "percentage": 3.06, "elapsed_time": "0:03:54", "remaining_time": "2:04:07"}
+{"current_steps": 20, "total_steps": 327, "loss": 0.12924295663833618, "lr": 0.00018837920489296636, "epoch": 0.1839080459770115, "percentage": 6.12, "elapsed_time": "0:08:25", "remaining_time": "2:09:12"}
+{"current_steps": 30, "total_steps": 327, "loss": 0.10623193979263305, "lr": 0.00018226299694189605, "epoch": 0.27586206896551724, "percentage": 9.17, "elapsed_time": "0:12:54", "remaining_time": "2:07:52"}
+{"current_steps": 40, "total_steps": 327, "loss": 0.10601885318756103, "lr": 0.0001761467889908257, "epoch": 0.367816091954023, "percentage": 12.23, "elapsed_time": "0:17:24", "remaining_time": "2:04:55"}
+{"current_steps": 50, "total_steps": 327, "loss": 0.09006149768829345, "lr": 0.00017003058103975534, "epoch": 0.45977011494252873, "percentage": 15.29, "elapsed_time": "0:21:53", "remaining_time": "2:01:17"}
+{"current_steps": 60, "total_steps": 327, "loss": 0.0927188515663147, "lr": 0.00016391437308868503, "epoch": 0.5517241379310345, "percentage": 18.35, "elapsed_time": "0:26:23", "remaining_time": "1:57:25"}
+{"current_steps": 70, "total_steps": 327, "loss": 0.10100839138031006, "lr": 0.0001577981651376147, "epoch": 0.6436781609195402, "percentage": 21.41, "elapsed_time": "0:30:46", "remaining_time": "1:53:00"}
+{"current_steps": 80, "total_steps": 327, "loss": 0.0789786159992218, "lr": 0.00015168195718654435, "epoch": 0.735632183908046, "percentage": 24.46, "elapsed_time": "0:35:11", "remaining_time": "1:48:40"}
+{"current_steps": 90, "total_steps": 327, "loss": 0.07820955514907837, "lr": 0.00014556574923547402, "epoch": 0.8275862068965517, "percentage": 27.52, "elapsed_time": "0:39:38", "remaining_time": "1:44:22"}
+{"current_steps": 100, "total_steps": 327, "loss": 0.08956178426742553, "lr": 0.00013944954128440368, "epoch": 0.9195402298850575, "percentage": 30.58, "elapsed_time": "0:44:04", "remaining_time": "1:40:03"}
+{"current_steps": 110, "total_steps": 327, "loss": 0.09496147632598877, "lr": 0.00013333333333333334, "epoch": 1.0091954022988505, "percentage": 33.64, "elapsed_time": "0:48:23", "remaining_time": "1:35:27"}
+{"current_steps": 120, "total_steps": 327, "loss": 0.08737512230873108, "lr": 0.000127217125382263, "epoch": 1.1011494252873564, "percentage": 36.7, "elapsed_time": "0:52:50", "remaining_time": "1:31:08"}
+{"current_steps": 130, "total_steps": 327, "loss": 0.07404522895812989, "lr": 0.00012110091743119268, "epoch": 1.193103448275862, "percentage": 39.76, "elapsed_time": "0:57:17", "remaining_time": "1:26:48"}
+{"current_steps": 140, "total_steps": 327, "loss": 0.06943418979644775, "lr": 0.00011498470948012233, "epoch": 1.2850574712643679, "percentage": 42.81, "elapsed_time": "1:01:44", "remaining_time": "1:22:28"}
+{"current_steps": 150, "total_steps": 327, "loss": 0.07198014259338378, "lr": 0.00010886850152905199, "epoch": 1.3770114942528735, "percentage": 45.87, "elapsed_time": "1:06:10", "remaining_time": "1:18:05"}
+{"current_steps": 160, "total_steps": 327, "loss": 0.07075391411781311, "lr": 0.00010275229357798166, "epoch": 1.4689655172413794, "percentage": 48.93, "elapsed_time": "1:10:39", "remaining_time": "1:13:44"}
+{"current_steps": 170, "total_steps": 327, "loss": 0.0763627827167511, "lr": 9.663608562691132e-05, "epoch": 1.560919540229885, "percentage": 51.99, "elapsed_time": "1:15:05", "remaining_time": "1:09:21"}
+{"current_steps": 180, "total_steps": 327, "loss": 0.06987376809120179, "lr": 9.051987767584099e-05, "epoch": 1.6528735632183909, "percentage": 55.05, "elapsed_time": "1:19:32", "remaining_time": "1:04:57"}
+{"current_steps": 190, "total_steps": 327, "loss": 0.06609394550323486, "lr": 8.440366972477065e-05, "epoch": 1.7448275862068967, "percentage": 58.1, "elapsed_time": "1:23:59", "remaining_time": "1:00:33"}
+{"current_steps": 200, "total_steps": 327, "loss": 0.07024483680725098, "lr": 7.828746177370031e-05, "epoch": 1.8367816091954023, "percentage": 61.16, "elapsed_time": "1:28:26", "remaining_time": "0:56:09"}
+{"current_steps": 210, "total_steps": 327, "loss": 0.0659551739692688, "lr": 7.217125382262997e-05, "epoch": 1.928735632183908, "percentage": 64.22, "elapsed_time": "1:32:54", "remaining_time": "0:51:45"}
+{"current_steps": 220, "total_steps": 327, "loss": 0.06620625853538513, "lr": 6.605504587155963e-05, "epoch": 2.018390804597701, "percentage": 67.28, "elapsed_time": "1:37:11", "remaining_time": "0:47:16"}
+{"current_steps": 230, "total_steps": 327, "loss": 0.05962467789649963, "lr": 5.99388379204893e-05, "epoch": 2.110344827586207, "percentage": 70.34, "elapsed_time": "1:41:37", "remaining_time": "0:42:51"}
+{"current_steps": 240, "total_steps": 327, "loss": 0.051931560039520264, "lr": 5.382262996941896e-05, "epoch": 2.2022988505747128, "percentage": 73.39, "elapsed_time": "1:46:04", "remaining_time": "0:38:27"}
+{"current_steps": 250, "total_steps": 327, "loss": 0.06514100432395935, "lr": 4.7706422018348626e-05, "epoch": 2.2942528735632184, "percentage": 76.45, "elapsed_time": "1:50:31", "remaining_time": "0:34:02"}
+{"current_steps": 260, "total_steps": 327, "loss": 0.06397714018821717, "lr": 4.159021406727829e-05, "epoch": 2.386206896551724, "percentage": 79.51, "elapsed_time": "1:54:59", "remaining_time": "0:29:37"}
+{"current_steps": 270, "total_steps": 327, "loss": 0.06488621830940247, "lr": 3.5474006116207956e-05, "epoch": 2.4781609195402297, "percentage": 82.57, "elapsed_time": "1:59:26", "remaining_time": "0:25:12"}
+{"current_steps": 280, "total_steps": 327, "loss": 0.060347968339920045, "lr": 2.9357798165137618e-05, "epoch": 2.5701149425287357, "percentage": 85.63, "elapsed_time": "2:03:53", "remaining_time": "0:20:47"}
+{"current_steps": 290, "total_steps": 327, "loss": 0.05238440036773682, "lr": 2.324159021406728e-05, "epoch": 2.6620689655172414, "percentage": 88.69, "elapsed_time": "2:08:20", "remaining_time": "0:16:22"}
+{"current_steps": 300, "total_steps": 327, "loss": 0.04942976236343384, "lr": 1.712538226299694e-05, "epoch": 2.754022988505747, "percentage": 91.74, "elapsed_time": "2:12:48", "remaining_time": "0:11:57"}
+{"current_steps": 310, "total_steps": 327, "loss": 0.0647299349308014, "lr": 1.1009174311926607e-05, "epoch": 2.845977011494253, "percentage": 94.8, "elapsed_time": "2:17:16", "remaining_time": "0:07:31"}
+{"current_steps": 320, "total_steps": 327, "loss": 0.06125383973121643, "lr": 4.892966360856269e-06, "epoch": 2.9379310344827587, "percentage": 97.86, "elapsed_time": "2:21:43", "remaining_time": "0:03:06"}
+{"current_steps": 327, "total_steps": 327, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:24:42", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1315169111d51de66ae42d33f469b1d4e05758f58d5c44dc9a9d3b59fff13006
+size 5176