Upload folder using huggingface_hub

.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2610888a5e618ffc8f0b53132863acbc9f77393713120fa3d44286b3437310
+size 1069306400

.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
+.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/gemma-3-1b-it
+library_name: peft
+model_name: model
+tags:
+- base_model:adapter:unsloth/gemma-3-1b-it
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for model
+
+This model is a fine-tuned version of [unsloth/gemma-3-1b-it](https://huggingface.co/unsloth/gemma-3-1b-it).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.17.1
+- TRL: 0.23.0
+- Transformers: 4.56.2
+- Pytorch: 2.8.0+cu126
+- Datasets: 4.2.0
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_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 sha256:51a0d437d01825d7d6aab4366dda599c1dc274bae65257af3e0726a07777eafc
+size 417513640

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3-1b-it
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ed7f9518243ee8decfafa42ea22d51d4283c0a1d83f3292ca4ab832a2e078c
+size 417513640

checkpoint-500/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-500/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f465fdb1505981db0f5220fde502e13e021c8f79df5ef679616e7136b293ea8
+size 212422229

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a2123a5dbe87fecf683724a46f0c8fc56ecbe6426bbd0e402438a60e40b6a0
+size 1465

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-500/trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5974440894568689,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 11.206622123718262,
+      "learning_rate": 7.5e-06,
+      "loss": 1.9859,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 3.7908952236175537,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.7824,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 2.964991807937622,
+      "learning_rate": 2.4166666666666667e-05,
+      "loss": 0.4965,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 2.3779187202453613,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.4616,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 2.5278868675231934,
+      "learning_rate": 4.0833333333333334e-05,
+      "loss": 0.4106,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 2.2696661949157715,
+      "learning_rate": 4.9166666666666665e-05,
+      "loss": 0.4006,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 2.5393056869506836,
+      "learning_rate": 4.9166666666666665e-05,
+      "loss": 0.4128,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 1.7245150804519653,
+      "learning_rate": 4.8240740740740744e-05,
+      "loss": 0.3724,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.5854761600494385,
+      "learning_rate": 4.731481481481482e-05,
+      "loss": 0.3842,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 1.9313678741455078,
+      "learning_rate": 4.638888888888889e-05,
+      "loss": 0.3671,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 1.405590295791626,
+      "learning_rate": 4.546296296296296e-05,
+      "loss": 0.3716,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 1.8853315114974976,
+      "learning_rate": 4.4537037037037036e-05,
+      "loss": 0.3422,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 1.6390379667282104,
+      "learning_rate": 4.3611111111111116e-05,
+      "loss": 0.3665,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 1.83126962184906,
+      "learning_rate": 4.268518518518519e-05,
+      "loss": 0.3609,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 2.023432731628418,
+      "learning_rate": 4.175925925925926e-05,
+      "loss": 0.311,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 1.3261724710464478,
+      "learning_rate": 4.0833333333333334e-05,
+      "loss": 0.3227,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 1.6062400341033936,
+      "learning_rate": 3.990740740740741e-05,
+      "loss": 0.3454,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 1.912152647972107,
+      "learning_rate": 3.898148148148149e-05,
+      "loss": 0.339,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 1.320884346961975,
+      "learning_rate": 3.805555555555555e-05,
+      "loss": 0.3357,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 1.4513561725616455,
+      "learning_rate": 3.712962962962963e-05,
+      "loss": 0.2974,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 1.4858988523483276,
+      "learning_rate": 3.6203703703703706e-05,
+      "loss": 0.3123,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 1.4934345483779907,
+      "learning_rate": 3.527777777777778e-05,
+      "loss": 0.2982,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 1.4448986053466797,
+      "learning_rate": 3.435185185185185e-05,
+      "loss": 0.3137,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 1.4921764135360718,
+      "learning_rate": 3.3425925925925924e-05,
+      "loss": 0.3238,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.4823459386825562,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.3199,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 1.3530499935150146,
+      "learning_rate": 3.157407407407408e-05,
+      "loss": 0.2884,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 1.4053056240081787,
+      "learning_rate": 3.064814814814815e-05,
+      "loss": 0.3063,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 1.5317288637161255,
+      "learning_rate": 2.9722222222222223e-05,
+      "loss": 0.3086,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 1.2986602783203125,
+      "learning_rate": 2.87962962962963e-05,
+      "loss": 0.2922,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 1.3176311254501343,
+      "learning_rate": 2.7870370370370375e-05,
+      "loss": 0.2915,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 1.3167009353637695,
+      "learning_rate": 2.6944444444444445e-05,
+      "loss": 0.3138,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 1.2647294998168945,
+      "learning_rate": 2.601851851851852e-05,
+      "loss": 0.2349,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 1.681065320968628,
+      "learning_rate": 2.5092592592592594e-05,
+      "loss": 0.1935,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 1.378735899925232,
+      "learning_rate": 2.4166666666666667e-05,
+      "loss": 0.2119,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 1.3662972450256348,
+      "learning_rate": 2.324074074074074e-05,
+      "loss": 0.2017,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 1.2679312229156494,
+      "learning_rate": 2.2314814814814816e-05,
+      "loss": 0.1737,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 1.449556827545166,
+      "learning_rate": 2.138888888888889e-05,
+      "loss": 0.2056,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.8932950496673584,
+      "learning_rate": 2.0462962962962965e-05,
+      "loss": 0.2187,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 1.0975728034973145,
+      "learning_rate": 1.9537037037037038e-05,
+      "loss": 0.1991,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 1.5841988325119019,
+      "learning_rate": 1.861111111111111e-05,
+      "loss": 0.2088,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.408890724182129,
+      "learning_rate": 1.7685185185185184e-05,
+      "loss": 0.2217,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 1.4187753200531006,
+      "learning_rate": 1.675925925925926e-05,
+      "loss": 0.1805,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 1.314961552619934,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.1783,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 1.3834567070007324,
+      "learning_rate": 1.490740740740741e-05,
+      "loss": 0.1915,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 1.163780689239502,
+      "learning_rate": 1.3981481481481482e-05,
+      "loss": 0.1783,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 1.2646948099136353,
+      "learning_rate": 1.3055555555555557e-05,
+      "loss": 0.1939,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 2.082306146621704,
+      "learning_rate": 1.212962962962963e-05,
+      "loss": 0.175,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 1.479463815689087,
+      "learning_rate": 1.1203703703703704e-05,
+      "loss": 0.2032,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 1.603749394416809,
+      "learning_rate": 1.0277777777777777e-05,
+      "loss": 0.2098,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 1.5476616621017456,
+      "learning_rate": 9.351851851851852e-06,
+      "loss": 0.2193,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.281652283622912e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa51c4c3219441d7d7b0f90855cdb9b1f74eca96e9e0723896bcb0f3d1914878
+size 6225

checkpoint-600/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3-1b-it
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-600/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a0d437d01825d7d6aab4366dda599c1dc274bae65257af3e0726a07777eafc
+size 417513640

checkpoint-600/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-600/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfaa998071a0f290766abb99e5f8546e9463365bb57761c16bf6f7692183a8af
+size 212422229

checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ae3778a43ab33194e3eb557cd3e82c54c63f22364e734be5b5c32d5a5037dd
+size 1465

checkpoint-600/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-600/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-600/trainer_state.json

@@ -0,0 +1,454 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9169329073482428,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 11.206622123718262,
+      "learning_rate": 7.5e-06,
+      "loss": 1.9859,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 3.7908952236175537,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.7824,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 2.964991807937622,
+      "learning_rate": 2.4166666666666667e-05,
+      "loss": 0.4965,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 2.3779187202453613,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.4616,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 2.5278868675231934,
+      "learning_rate": 4.0833333333333334e-05,
+      "loss": 0.4106,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 2.2696661949157715,
+      "learning_rate": 4.9166666666666665e-05,
+      "loss": 0.4006,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 2.5393056869506836,
+      "learning_rate": 4.9166666666666665e-05,
+      "loss": 0.4128,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 1.7245150804519653,
+      "learning_rate": 4.8240740740740744e-05,
+      "loss": 0.3724,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.5854761600494385,
+      "learning_rate": 4.731481481481482e-05,
+      "loss": 0.3842,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 1.9313678741455078,
+      "learning_rate": 4.638888888888889e-05,
+      "loss": 0.3671,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 1.405590295791626,
+      "learning_rate": 4.546296296296296e-05,
+      "loss": 0.3716,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 1.8853315114974976,
+      "learning_rate": 4.4537037037037036e-05,
+      "loss": 0.3422,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 1.6390379667282104,
+      "learning_rate": 4.3611111111111116e-05,
+      "loss": 0.3665,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 1.83126962184906,
+      "learning_rate": 4.268518518518519e-05,
+      "loss": 0.3609,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 2.023432731628418,
+      "learning_rate": 4.175925925925926e-05,
+      "loss": 0.311,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 1.3261724710464478,
+      "learning_rate": 4.0833333333333334e-05,
+      "loss": 0.3227,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 1.6062400341033936,
+      "learning_rate": 3.990740740740741e-05,
+      "loss": 0.3454,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 1.912152647972107,
+      "learning_rate": 3.898148148148149e-05,
+      "loss": 0.339,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 1.320884346961975,
+      "learning_rate": 3.805555555555555e-05,
+      "loss": 0.3357,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 1.4513561725616455,
+      "learning_rate": 3.712962962962963e-05,
+      "loss": 0.2974,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 1.4858988523483276,
+      "learning_rate": 3.6203703703703706e-05,
+      "loss": 0.3123,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 1.4934345483779907,
+      "learning_rate": 3.527777777777778e-05,
+      "loss": 0.2982,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 1.4448986053466797,
+      "learning_rate": 3.435185185185185e-05,
+      "loss": 0.3137,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 1.4921764135360718,
+      "learning_rate": 3.3425925925925924e-05,
+      "loss": 0.3238,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.4823459386825562,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.3199,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 1.3530499935150146,
+      "learning_rate": 3.157407407407408e-05,
+      "loss": 0.2884,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 1.4053056240081787,
+      "learning_rate": 3.064814814814815e-05,
+      "loss": 0.3063,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 1.5317288637161255,
+      "learning_rate": 2.9722222222222223e-05,
+      "loss": 0.3086,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 1.2986602783203125,
+      "learning_rate": 2.87962962962963e-05,
+      "loss": 0.2922,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 1.3176311254501343,
+      "learning_rate": 2.7870370370370375e-05,
+      "loss": 0.2915,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 1.3167009353637695,
+      "learning_rate": 2.6944444444444445e-05,
+      "loss": 0.3138,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 1.2647294998168945,
+      "learning_rate": 2.601851851851852e-05,
+      "loss": 0.2349,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 1.681065320968628,
+      "learning_rate": 2.5092592592592594e-05,
+      "loss": 0.1935,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 1.378735899925232,
+      "learning_rate": 2.4166666666666667e-05,
+      "loss": 0.2119,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 1.3662972450256348,
+      "learning_rate": 2.324074074074074e-05,
+      "loss": 0.2017,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 1.2679312229156494,
+      "learning_rate": 2.2314814814814816e-05,
+      "loss": 0.1737,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 1.449556827545166,
+      "learning_rate": 2.138888888888889e-05,
+      "loss": 0.2056,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.8932950496673584,
+      "learning_rate": 2.0462962962962965e-05,
+      "loss": 0.2187,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 1.0975728034973145,
+      "learning_rate": 1.9537037037037038e-05,
+      "loss": 0.1991,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 1.5841988325119019,
+      "learning_rate": 1.861111111111111e-05,
+      "loss": 0.2088,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.408890724182129,
+      "learning_rate": 1.7685185185185184e-05,
+      "loss": 0.2217,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 1.4187753200531006,
+      "learning_rate": 1.675925925925926e-05,
+      "loss": 0.1805,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 1.314961552619934,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.1783,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 1.3834567070007324,
+      "learning_rate": 1.490740740740741e-05,
+      "loss": 0.1915,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 1.163780689239502,
+      "learning_rate": 1.3981481481481482e-05,
+      "loss": 0.1783,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 1.2646948099136353,
+      "learning_rate": 1.3055555555555557e-05,
+      "loss": 0.1939,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 2.082306146621704,
+      "learning_rate": 1.212962962962963e-05,
+      "loss": 0.175,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 1.479463815689087,
+      "learning_rate": 1.1203703703703704e-05,
+      "loss": 0.2032,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 1.603749394416809,
+      "learning_rate": 1.0277777777777777e-05,
+      "loss": 0.2098,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 1.5476616621017456,
+      "learning_rate": 9.351851851851852e-06,
+      "loss": 0.2193,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 1.359187364578247,
+      "learning_rate": 8.425925925925926e-06,
+      "loss": 0.2106,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 1.213533639907837,
+      "learning_rate": 7.5e-06,
+      "loss": 0.1876,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 1.0894689559936523,
+      "learning_rate": 6.574074074074074e-06,
+      "loss": 0.191,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 1.357428789138794,
+      "learning_rate": 5.6481481481481485e-06,
+      "loss": 0.1816,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 1.600085735321045,
+      "learning_rate": 4.722222222222222e-06,
+      "loss": 0.1939,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 1.475881814956665,
+      "learning_rate": 3.7962962962962964e-06,
+      "loss": 0.1884,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 1.8336604833602905,
+      "learning_rate": 2.8703703703703706e-06,
+      "loss": 0.1929,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 1.9997520446777344,
+      "learning_rate": 1.9444444444444444e-06,
+      "loss": 0.1973,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 1.144436240196228,
+      "learning_rate": 1.0185185185185188e-06,
+      "loss": 0.1956,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 1.5843777656555176,
+      "learning_rate": 9.25925925925926e-08,
+      "loss": 0.1883,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.542523864987392e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa51c4c3219441d7d7b0f90855cdb9b1f74eca96e9e0723896bcb0f3d1914878
+size 6225

config.json

@@ -0,0 +1,64 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "torch_dtype": "float16",
+  "eos_token_id": 106,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
+  "transformers_version": "4.56.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.10.1",
+  "use_cache": true,
+  "vocab_size": 262144
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7ade13d5867f3ac3e72974c3a5157c15f9066f63ac6e68cf78934401609111
+size 1999811208

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074