Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5298/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5200/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
+library_name: peft
+model_name: Gemma-3-4B-it-Medical-LoRA
+tags:
+- generated_from_trainer
+- trl
+- unsloth
+- sft
+licence: license
+---
+
+# Model Card for Gemma-3-4B-it-Medical-LoRA
+
+This model is a fine-tuned version of [unsloth/gemma-3-4b-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/gemma-3-4b-it-unsloth-bnb-4bit).
+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 0.14.0
+- TRL: 0.19.0
+- Transformers: 4.52.4
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7cbf3c9a6c6fe1f066f06d0a648ce613cbc07b7128188dc3304d2a595546f85
+size 119280712

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-5200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-5200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-5200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b16bf871837532892b2847d2e89d946113e3f0db14b737a62604528d405ddd5
+size 119280712

checkpoint-5200/added_tokens.json

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

checkpoint-5200/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-5200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a4f7bddb99975a7d3ceb2d23a97fc93d9a3d81a9511ac536117035d116a873
+size 62332474

checkpoint-5200/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

checkpoint-5200/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

checkpoint-5200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a79239f98d586c6d293becfe4724cb48ad892f743d1e770886cde54b3333d6
+size 14244

checkpoint-5200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a429a42158a31c11b8843cdeec4402cd147056e0b212dd4ad5498a298f2e5b94
+size 1064

checkpoint-5200/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-5200/tokenizer.json

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

checkpoint-5200/tokenizer.model

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

checkpoint-5200/trainer_state.json

@@ -0,0 +1,970 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.5003665089607239,
+  "best_model_checkpoint": "Gemma-3-4B-it-Medical-LoRA/checkpoint-200",
+  "epoch": 5.889266496743132,
+  "eval_steps": 200,
+  "global_step": 5200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.522846519947052,
+      "learning_rate": 0.0001955451348182884,
+      "loss": 0.7569,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.4961966276168823,
+      "learning_rate": 0.00018382180539273154,
+      "loss": 0.4753,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.512007474899292,
+      "learning_rate": 0.00017209847596717467,
+      "loss": 0.5535,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 0.8278496861457825,
+      "learning_rate": 0.00016037514654161782,
+      "loss": 0.5582,
+      "step": 200
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "eval_loss": 0.5003665089607239,
+      "eval_runtime": 566.8557,
+      "eval_samples_per_second": 2.768,
+      "eval_steps_per_second": 0.693,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.8043648600578308,
+      "learning_rate": 0.00014865181711606098,
+      "loss": 0.538,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8642493486404419,
+      "learning_rate": 0.0001369284876905041,
+      "loss": 0.5074,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.5464778542518616,
+      "learning_rate": 0.00012520515826494724,
+      "loss": 0.4882,
+      "step": 350
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.8210390210151672,
+      "learning_rate": 0.0001134818288393904,
+      "loss": 0.5102,
+      "step": 400
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "eval_loss": 0.5287922620773315,
+      "eval_runtime": 545.4754,
+      "eval_samples_per_second": 2.876,
+      "eval_steps_per_second": 0.72,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.9310616850852966,
+      "learning_rate": 0.00010175849941383353,
+      "loss": 0.5139,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 1.1925888061523438,
+      "learning_rate": 9.003516998827668e-05,
+      "loss": 0.5748,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 1.2190861701965332,
+      "learning_rate": 7.831184056271981e-05,
+      "loss": 0.53,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.9308417439460754,
+      "learning_rate": 6.658851113716296e-05,
+      "loss": 0.528,
+      "step": 600
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "eval_loss": 0.535805881023407,
+      "eval_runtime": 545.9453,
+      "eval_samples_per_second": 2.874,
+      "eval_steps_per_second": 0.72,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 1.1482899188995361,
+      "learning_rate": 5.486518171160609e-05,
+      "loss": 0.5532,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.6465129852294922,
+      "learning_rate": 4.3141852286049237e-05,
+      "loss": 0.5838,
+      "step": 700
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.1552118062973022,
+      "learning_rate": 3.1418522860492386e-05,
+      "loss": 0.5483,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 1.138253927230835,
+      "learning_rate": 1.9695193434935523e-05,
+      "loss": 0.5188,
+      "step": 800
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "eval_loss": 0.5232300162315369,
+      "eval_runtime": 545.2326,
+      "eval_samples_per_second": 2.878,
+      "eval_steps_per_second": 0.721,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.1961596012115479,
+      "learning_rate": 7.971864009378664e-06,
+      "loss": 0.5166,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 1.1366384029388428,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.4523,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 1.1627408266067505,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.467,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 1.2404801845550537,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4521,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "eval_loss": 0.5426932573318481,
+      "eval_runtime": 653.831,
+      "eval_samples_per_second": 2.4,
+      "eval_steps_per_second": 0.601,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 1.0068233013153076,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.4965,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 1.3524373769760132,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.4658,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 1.291171908378601,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.4945,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 1.673529028892517,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.4919,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "eval_loss": 0.5525731444358826,
+      "eval_runtime": 637.1064,
+      "eval_samples_per_second": 2.463,
+      "eval_steps_per_second": 0.617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 1.0850290060043335,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.4912,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 1.318361759185791,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.46,
+      "step": 1300
+    },
+    {
+      "epoch": 1.529028603794959,
+      "grad_norm": 1.5087871551513672,
+      "learning_rate": 4.8041474654377885e-05,
+      "loss": 0.4977,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "grad_norm": 1.5589851140975952,
+      "learning_rate": 4.228110599078341e-05,
+      "loss": 0.4558,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "eval_loss": 0.5318325161933899,
+      "eval_runtime": 633.698,
+      "eval_samples_per_second": 2.476,
+      "eval_steps_per_second": 0.62,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6423109600679693,
+      "grad_norm": 1.1275252103805542,
+      "learning_rate": 3.6520737327188945e-05,
+      "loss": 0.4792,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6989521382044748,
+      "grad_norm": 1.3600178956985474,
+      "learning_rate": 3.076036866359447e-05,
+      "loss": 0.4796,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7555933163409798,
+      "grad_norm": 1.4632591009140015,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4787,
+      "step": 1550
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 1.3220279216766357,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.4785,
+      "step": 1600
+    },
+    {
+      "epoch": 1.812234494477485,
+      "eval_loss": 0.5232844352722168,
+      "eval_runtime": 633.2557,
+      "eval_samples_per_second": 2.478,
+      "eval_steps_per_second": 0.621,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.71708083152771,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.4901,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 1.0889732837677002,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.475,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 1.226163387298584,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.4729,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 1.93405020236969,
+      "learning_rate": 6.491027109583811e-05,
+      "loss": 0.3981,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "eval_loss": 0.534080982208252,
+      "eval_runtime": 635.9448,
+      "eval_samples_per_second": 2.467,
+      "eval_steps_per_second": 0.618,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.4278013706207275,
+      "learning_rate": 6.109201985490646e-05,
+      "loss": 0.4229,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.6030181646347046,
+      "learning_rate": 5.72737686139748e-05,
+      "loss": 0.4363,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.3467751741409302,
+      "learning_rate": 5.345551737304315e-05,
+      "loss": 0.425,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.390838623046875,
+      "learning_rate": 4.963726613211149e-05,
+      "loss": 0.4185,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "eval_loss": 0.5372938513755798,
+      "eval_runtime": 635.7783,
+      "eval_samples_per_second": 2.468,
+      "eval_steps_per_second": 0.618,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 1.3252273797988892,
+      "learning_rate": 4.581901489117984e-05,
+      "loss": 0.43,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.2557967901229858,
+      "learning_rate": 4.2000763650248184e-05,
+      "loss": 0.4386,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.649653434753418,
+      "learning_rate": 3.818251240931654e-05,
+      "loss": 0.4273,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 1.5756187438964844,
+      "learning_rate": 3.4364261168384884e-05,
+      "loss": 0.3909,
+      "step": 2200
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "eval_loss": 0.542982280254364,
+      "eval_runtime": 635.1617,
+      "eval_samples_per_second": 2.47,
+      "eval_steps_per_second": 0.619,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.4305800199508667,
+      "learning_rate": 3.054600992745323e-05,
+      "loss": 0.4111,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.4521535634994507,
+      "learning_rate": 2.6727758686521576e-05,
+      "loss": 0.4402,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6615689606343813,
+      "grad_norm": 1.3872359991073608,
+      "learning_rate": 2.290950744558992e-05,
+      "loss": 0.4293,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "grad_norm": 1.6272056102752686,
+      "learning_rate": 1.909125620465827e-05,
+      "loss": 0.4145,
+      "step": 2400
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "eval_loss": 0.5353428721427917,
+      "eval_runtime": 628.4439,
+      "eval_samples_per_second": 2.497,
+      "eval_steps_per_second": 0.625,
+      "step": 2400
+    },
+    {
+      "epoch": 2.774851316907392,
+      "grad_norm": 1.1917740106582642,
+      "learning_rate": 1.5273004963726615e-05,
+      "loss": 0.4022,
+      "step": 2450
+    },
+    {
+      "epoch": 2.831492495043897,
+      "grad_norm": 1.5548139810562134,
+      "learning_rate": 1.145475372279496e-05,
+      "loss": 0.4155,
+      "step": 2500
+    },
+    {
+      "epoch": 2.888133673180402,
+      "grad_norm": 2.0399019718170166,
+      "learning_rate": 7.636502481863307e-06,
+      "loss": 0.4169,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "grad_norm": 1.6849918365478516,
+      "learning_rate": 3.818251240931654e-06,
+      "loss": 0.4145,
+      "step": 2600
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "eval_loss": 0.5327087640762329,
+      "eval_runtime": 636.4789,
+      "eval_samples_per_second": 2.465,
+      "eval_steps_per_second": 0.617,
+      "step": 2600
+    },
+    {
+      "epoch": 3.00113282356273,
+      "grad_norm": 1.1705021858215332,
+      "learning_rate": 0.0,
+      "loss": 0.3254,
+      "step": 2650
+    },
+    {
+      "epoch": 3.057774001699235,
+      "grad_norm": 1.3165022134780884,
+      "learning_rate": 4.757281553398059e-05,
+      "loss": 0.367,
+      "step": 2700
+    },
+    {
+      "epoch": 3.1144151798357407,
+      "grad_norm": 1.557210922241211,
+      "learning_rate": 4.4717304397487155e-05,
+      "loss": 0.3588,
+      "step": 2750
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "grad_norm": 1.7867581844329834,
+      "learning_rate": 4.186179326099372e-05,
+      "loss": 0.3761,
+      "step": 2800
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "eval_loss": 0.555277407169342,
+      "eval_runtime": 631.0969,
+      "eval_samples_per_second": 2.486,
+      "eval_steps_per_second": 0.623,
+      "step": 2800
+    },
+    {
+      "epoch": 3.227697536108751,
+      "grad_norm": 1.8431845903396606,
+      "learning_rate": 3.900628212450029e-05,
+      "loss": 0.402,
+      "step": 2850
+    },
+    {
+      "epoch": 3.2843387142452563,
+      "grad_norm": 2.415738344192505,
+      "learning_rate": 3.6150770988006854e-05,
+      "loss": 0.3614,
+      "step": 2900
+    },
+    {
+      "epoch": 3.3409798923817613,
+      "grad_norm": 1.8246201276779175,
+      "learning_rate": 3.329525985151342e-05,
+      "loss": 0.3896,
+      "step": 2950
+    },
+    {
+      "epoch": 3.397621070518267,
+      "grad_norm": 1.1022515296936035,
+      "learning_rate": 3.043974871501999e-05,
+      "loss": 0.3746,
+      "step": 3000
+    },
+    {
+      "epoch": 3.397621070518267,
+      "eval_loss": 0.5586006045341492,
+      "eval_runtime": 613.6818,
+      "eval_samples_per_second": 2.557,
+      "eval_steps_per_second": 0.64,
+      "step": 3000
+    },
+    {
+      "epoch": 3.454262248654772,
+      "grad_norm": 2.3615689277648926,
+      "learning_rate": 2.7584237578526556e-05,
+      "loss": 0.3748,
+      "step": 3050
+    },
+    {
+      "epoch": 3.5109034267912773,
+      "grad_norm": 2.1353960037231445,
+      "learning_rate": 2.4728726442033126e-05,
+      "loss": 0.38,
+      "step": 3100
+    },
+    {
+      "epoch": 3.5675446049277824,
+      "grad_norm": 1.7389541864395142,
+      "learning_rate": 2.1873215305539692e-05,
+      "loss": 0.3816,
+      "step": 3150
+    },
+    {
+      "epoch": 3.624185783064288,
+      "grad_norm": 1.8731958866119385,
+      "learning_rate": 1.9017704169046262e-05,
+      "loss": 0.388,
+      "step": 3200
+    },
+    {
+      "epoch": 3.624185783064288,
+      "eval_loss": 0.5509854555130005,
+      "eval_runtime": 605.0872,
+      "eval_samples_per_second": 2.593,
+      "eval_steps_per_second": 0.649,
+      "step": 3200
+    },
+    {
+      "epoch": 3.680826961200793,
+      "grad_norm": 1.814975380897522,
+      "learning_rate": 1.6162193032552828e-05,
+      "loss": 0.3897,
+      "step": 3250
+    },
+    {
+      "epoch": 3.7374681393372984,
+      "grad_norm": 1.8525991439819336,
+      "learning_rate": 1.3306681896059394e-05,
+      "loss": 0.3931,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7941093174738034,
+      "grad_norm": 2.1449315547943115,
+      "learning_rate": 1.0451170759565964e-05,
+      "loss": 0.3987,
+      "step": 3350
+    },
+    {
+      "epoch": 3.850750495610309,
+      "grad_norm": 1.2358556985855103,
+      "learning_rate": 7.59565962307253e-06,
+      "loss": 0.3695,
+      "step": 3400
+    },
+    {
+      "epoch": 3.850750495610309,
+      "eval_loss": 0.5485390424728394,
+      "eval_runtime": 606.2751,
+      "eval_samples_per_second": 2.588,
+      "eval_steps_per_second": 0.648,
+      "step": 3400
+    },
+    {
+      "epoch": 3.907391673746814,
+      "grad_norm": 2.7738165855407715,
+      "learning_rate": 4.7401484865790974e-06,
+      "loss": 0.3841,
+      "step": 3450
+    },
+    {
+      "epoch": 3.964032851883319,
+      "grad_norm": 2.6049118041992188,
+      "learning_rate": 1.8846373500856656e-06,
+      "loss": 0.3742,
+      "step": 3500
+    },
+    {
+      "epoch": 4.020390824129142,
+      "grad_norm": 1.459250569343567,
+      "learning_rate": 6.64009111617312e-05,
+      "loss": 0.3493,
+      "step": 3550
+    },
+    {
+      "epoch": 4.077032002265647,
+      "grad_norm": 1.3481236696243286,
+      "learning_rate": 6.450265755504936e-05,
+      "loss": 0.3414,
+      "step": 3600
+    },
+    {
+      "epoch": 4.077032002265647,
+      "eval_loss": 0.5706936717033386,
+      "eval_runtime": 626.8261,
+      "eval_samples_per_second": 2.503,
+      "eval_steps_per_second": 0.627,
+      "step": 3600
+    },
+    {
+      "epoch": 4.133673180402153,
+      "grad_norm": 1.5863535404205322,
+      "learning_rate": 6.260440394836751e-05,
+      "loss": 0.3964,
+      "step": 3650
+    },
+    {
+      "epoch": 4.190314358538657,
+      "grad_norm": 1.4147838354110718,
+      "learning_rate": 6.070615034168565e-05,
+      "loss": 0.3688,
+      "step": 3700
+    },
+    {
+      "epoch": 4.246955536675163,
+      "grad_norm": 1.7272146940231323,
+      "learning_rate": 5.88078967350038e-05,
+      "loss": 0.3554,
+      "step": 3750
+    },
+    {
+      "epoch": 4.303596714811668,
+      "grad_norm": 1.7022188901901245,
+      "learning_rate": 5.6909643128321947e-05,
+      "loss": 0.362,
+      "step": 3800
+    },
+    {
+      "epoch": 4.303596714811668,
+      "eval_loss": 0.5747559070587158,
+      "eval_runtime": 603.0566,
+      "eval_samples_per_second": 2.602,
+      "eval_steps_per_second": 0.652,
+      "step": 3800
+    },
+    {
+      "epoch": 4.360237892948174,
+      "grad_norm": 1.8977692127227783,
+      "learning_rate": 5.501138952164009e-05,
+      "loss": 0.3787,
+      "step": 3850
+    },
+    {
+      "epoch": 4.416879071084678,
+      "grad_norm": 1.7641384601593018,
+      "learning_rate": 5.311313591495825e-05,
+      "loss": 0.417,
+      "step": 3900
+    },
+    {
+      "epoch": 4.473520249221184,
+      "grad_norm": 1.6231164932250977,
+      "learning_rate": 5.121488230827639e-05,
+      "loss": 0.3691,
+      "step": 3950
+    },
+    {
+      "epoch": 4.530161427357689,
+      "grad_norm": 1.8207956552505493,
+      "learning_rate": 4.9316628701594535e-05,
+      "loss": 0.3806,
+      "step": 4000
+    },
+    {
+      "epoch": 4.530161427357689,
+      "eval_loss": 0.5716577768325806,
+      "eval_runtime": 602.7077,
+      "eval_samples_per_second": 2.603,
+      "eval_steps_per_second": 0.652,
+      "step": 4000
+    },
+    {
+      "epoch": 4.586802605494194,
+      "grad_norm": 1.501741886138916,
+      "learning_rate": 4.741837509491268e-05,
+      "loss": 0.3787,
+      "step": 4050
+    },
+    {
+      "epoch": 4.643443783630699,
+      "grad_norm": 3.1166610717773438,
+      "learning_rate": 4.552012148823083e-05,
+      "loss": 0.3726,
+      "step": 4100
+    },
+    {
+      "epoch": 4.700084961767205,
+      "grad_norm": 2.083258867263794,
+      "learning_rate": 4.362186788154898e-05,
+      "loss": 0.364,
+      "step": 4150
+    },
+    {
+      "epoch": 4.75672613990371,
+      "grad_norm": 1.941104769706726,
+      "learning_rate": 4.1723614274867124e-05,
+      "loss": 0.3914,
+      "step": 4200
+    },
+    {
+      "epoch": 4.75672613990371,
+      "eval_loss": 0.5698277354240417,
+      "eval_runtime": 604.4852,
+      "eval_samples_per_second": 2.596,
+      "eval_steps_per_second": 0.65,
+      "step": 4200
+    },
+    {
+      "epoch": 4.813367318040215,
+      "grad_norm": 1.896347165107727,
+      "learning_rate": 3.982536066818527e-05,
+      "loss": 0.3706,
+      "step": 4250
+    },
+    {
+      "epoch": 4.8700084961767205,
+      "grad_norm": 1.9356690645217896,
+      "learning_rate": 3.792710706150342e-05,
+      "loss": 0.3735,
+      "step": 4300
+    },
+    {
+      "epoch": 4.926649674313226,
+      "grad_norm": 2.048717975616455,
+      "learning_rate": 3.6028853454821566e-05,
+      "loss": 0.3775,
+      "step": 4350
+    },
+    {
+      "epoch": 4.983290852449731,
+      "grad_norm": 1.8730669021606445,
+      "learning_rate": 3.413059984813971e-05,
+      "loss": 0.3671,
+      "step": 4400
+    },
+    {
+      "epoch": 4.983290852449731,
+      "eval_loss": 0.5636136531829834,
+      "eval_runtime": 604.9156,
+      "eval_samples_per_second": 2.594,
+      "eval_steps_per_second": 0.65,
+      "step": 4400
+    },
+    {
+      "epoch": 5.039648824695553,
+      "grad_norm": 1.3539544343948364,
+      "learning_rate": 3.223234624145786e-05,
+      "loss": 0.328,
+      "step": 4450
+    },
+    {
+      "epoch": 5.096290002832059,
+      "grad_norm": 1.5452523231506348,
+      "learning_rate": 3.0334092634776008e-05,
+      "loss": 0.32,
+      "step": 4500
+    },
+    {
+      "epoch": 5.152931180968564,
+      "grad_norm": 1.3977546691894531,
+      "learning_rate": 2.843583902809415e-05,
+      "loss": 0.3084,
+      "step": 4550
+    },
+    {
+      "epoch": 5.20957235910507,
+      "grad_norm": 4.15449333190918,
+      "learning_rate": 2.6537585421412302e-05,
+      "loss": 0.3017,
+      "step": 4600
+    },
+    {
+      "epoch": 5.20957235910507,
+      "eval_loss": 0.5834115743637085,
+      "eval_runtime": 603.5666,
+      "eval_samples_per_second": 2.6,
+      "eval_steps_per_second": 0.651,
+      "step": 4600
+    },
+    {
+      "epoch": 5.266213537241574,
+      "grad_norm": 1.6772358417510986,
+      "learning_rate": 2.463933181473045e-05,
+      "loss": 0.3023,
+      "step": 4650
+    },
+    {
+      "epoch": 5.32285471537808,
+      "grad_norm": 1.5398720502853394,
+      "learning_rate": 2.2741078208048596e-05,
+      "loss": 0.3061,
+      "step": 4700
+    },
+    {
+      "epoch": 5.379495893514585,
+      "grad_norm": 1.567535638809204,
+      "learning_rate": 2.0842824601366744e-05,
+      "loss": 0.3143,
+      "step": 4750
+    },
+    {
+      "epoch": 5.43613707165109,
+      "grad_norm": 1.6017929315567017,
+      "learning_rate": 1.894457099468489e-05,
+      "loss": 0.3009,
+      "step": 4800
+    },
+    {
+      "epoch": 5.43613707165109,
+      "eval_loss": 0.5849186778068542,
+      "eval_runtime": 604.7855,
+      "eval_samples_per_second": 2.594,
+      "eval_steps_per_second": 0.65,
+      "step": 4800
+    },
+    {
+      "epoch": 5.492778249787595,
+      "grad_norm": 1.815103530883789,
+      "learning_rate": 1.7046317388003038e-05,
+      "loss": 0.3196,
+      "step": 4850
+    },
+    {
+      "epoch": 5.549419427924101,
+      "grad_norm": 1.6697149276733398,
+      "learning_rate": 1.5148063781321184e-05,
+      "loss": 0.301,
+      "step": 4900
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 1.9685876369476318,
+      "learning_rate": 1.3249810174639332e-05,
+      "loss": 0.3275,
+      "step": 4950
+    },
+    {
+      "epoch": 5.662701784197111,
+      "grad_norm": 1.4504376649856567,
+      "learning_rate": 1.135155656795748e-05,
+      "loss": 0.3089,
+      "step": 5000
+    },
+    {
+      "epoch": 5.662701784197111,
+      "eval_loss": 0.5848227739334106,
+      "eval_runtime": 604.1032,
+      "eval_samples_per_second": 2.597,
+      "eval_steps_per_second": 0.651,
+      "step": 5000
+    },
+    {
+      "epoch": 5.7193429623336165,
+      "grad_norm": 2.6677732467651367,
+      "learning_rate": 9.453302961275627e-06,
+      "loss": 0.3178,
+      "step": 5050
+    },
+    {
+      "epoch": 5.775984140470122,
+      "grad_norm": 2.2549753189086914,
+      "learning_rate": 7.555049354593774e-06,
+      "loss": 0.2891,
+      "step": 5100
+    },
+    {
+      "epoch": 5.8326253186066275,
+      "grad_norm": 1.5250205993652344,
+      "learning_rate": 5.656795747911921e-06,
+      "loss": 0.3122,
+      "step": 5150
+    },
+    {
+      "epoch": 5.889266496743132,
+      "grad_norm": 1.8577101230621338,
+      "learning_rate": 3.758542141230068e-06,
+      "loss": 0.3032,
+      "step": 5200
+    },
+    {
+      "epoch": 5.889266496743132,
+      "eval_loss": 0.5855553150177002,
+      "eval_runtime": 603.8918,
+      "eval_samples_per_second": 2.598,
+      "eval_steps_per_second": 0.651,
+      "step": 5200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5298,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.00118492293233e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9daeff4f7649949e91566fac7256a9010f7454bfc785ed8b3dcfee3bac4529
+size 5688

checkpoint-5298/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-5298/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-5298/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6587eda466902c73be292e0df60308d128375c820d98de52e49df0ad817c9e7
+size 119280712

checkpoint-5298/added_tokens.json

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

checkpoint-5298/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-5298/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2813af1c647346dba477e3ff0b3b19190e0636e6a8589639188c0d1bfef823fa
+size 62332474

checkpoint-5298/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

checkpoint-5298/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

checkpoint-5298/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a79239f98d586c6d293becfe4724cb48ad892f743d1e770886cde54b3333d6
+size 14244

checkpoint-5298/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfba7a2a2b51b29df7a572a2215627ac042f306353a8c0937d57adb53bb48ae
+size 1064

checkpoint-5298/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-5298/tokenizer.json

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

checkpoint-5298/tokenizer.model

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

checkpoint-5298/trainer_state.json

@@ -0,0 +1,977 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.5003665089607239,
+  "best_model_checkpoint": "Gemma-3-4B-it-Medical-LoRA/checkpoint-200",
+  "epoch": 6.0,
+  "eval_steps": 200,
+  "global_step": 5298,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.522846519947052,
+      "learning_rate": 0.0001955451348182884,
+      "loss": 0.7569,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.4961966276168823,
+      "learning_rate": 0.00018382180539273154,
+      "loss": 0.4753,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.512007474899292,
+      "learning_rate": 0.00017209847596717467,
+      "loss": 0.5535,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 0.8278496861457825,
+      "learning_rate": 0.00016037514654161782,
+      "loss": 0.5582,
+      "step": 200
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "eval_loss": 0.5003665089607239,
+      "eval_runtime": 566.8557,
+      "eval_samples_per_second": 2.768,
+      "eval_steps_per_second": 0.693,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.8043648600578308,
+      "learning_rate": 0.00014865181711606098,
+      "loss": 0.538,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8642493486404419,
+      "learning_rate": 0.0001369284876905041,
+      "loss": 0.5074,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.5464778542518616,
+      "learning_rate": 0.00012520515826494724,
+      "loss": 0.4882,
+      "step": 350
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.8210390210151672,
+      "learning_rate": 0.0001134818288393904,
+      "loss": 0.5102,
+      "step": 400
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "eval_loss": 0.5287922620773315,
+      "eval_runtime": 545.4754,
+      "eval_samples_per_second": 2.876,
+      "eval_steps_per_second": 0.72,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.9310616850852966,
+      "learning_rate": 0.00010175849941383353,
+      "loss": 0.5139,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 1.1925888061523438,
+      "learning_rate": 9.003516998827668e-05,
+      "loss": 0.5748,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 1.2190861701965332,
+      "learning_rate": 7.831184056271981e-05,
+      "loss": 0.53,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.9308417439460754,
+      "learning_rate": 6.658851113716296e-05,
+      "loss": 0.528,
+      "step": 600
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "eval_loss": 0.535805881023407,
+      "eval_runtime": 545.9453,
+      "eval_samples_per_second": 2.874,
+      "eval_steps_per_second": 0.72,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 1.1482899188995361,
+      "learning_rate": 5.486518171160609e-05,
+      "loss": 0.5532,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.6465129852294922,
+      "learning_rate": 4.3141852286049237e-05,
+      "loss": 0.5838,
+      "step": 700
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.1552118062973022,
+      "learning_rate": 3.1418522860492386e-05,
+      "loss": 0.5483,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 1.138253927230835,
+      "learning_rate": 1.9695193434935523e-05,
+      "loss": 0.5188,
+      "step": 800
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "eval_loss": 0.5232300162315369,
+      "eval_runtime": 545.2326,
+      "eval_samples_per_second": 2.878,
+      "eval_steps_per_second": 0.721,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.1961596012115479,
+      "learning_rate": 7.971864009378664e-06,
+      "loss": 0.5166,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 1.1366384029388428,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.4523,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 1.1627408266067505,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.467,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 1.2404801845550537,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4521,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "eval_loss": 0.5426932573318481,
+      "eval_runtime": 653.831,
+      "eval_samples_per_second": 2.4,
+      "eval_steps_per_second": 0.601,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 1.0068233013153076,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.4965,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 1.3524373769760132,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.4658,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 1.291171908378601,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.4945,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 1.673529028892517,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.4919,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "eval_loss": 0.5525731444358826,
+      "eval_runtime": 637.1064,
+      "eval_samples_per_second": 2.463,
+      "eval_steps_per_second": 0.617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 1.0850290060043335,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.4912,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 1.318361759185791,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.46,
+      "step": 1300
+    },
+    {
+      "epoch": 1.529028603794959,
+      "grad_norm": 1.5087871551513672,
+      "learning_rate": 4.8041474654377885e-05,
+      "loss": 0.4977,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "grad_norm": 1.5589851140975952,
+      "learning_rate": 4.228110599078341e-05,
+      "loss": 0.4558,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "eval_loss": 0.5318325161933899,
+      "eval_runtime": 633.698,
+      "eval_samples_per_second": 2.476,
+      "eval_steps_per_second": 0.62,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6423109600679693,
+      "grad_norm": 1.1275252103805542,
+      "learning_rate": 3.6520737327188945e-05,
+      "loss": 0.4792,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6989521382044748,
+      "grad_norm": 1.3600178956985474,
+      "learning_rate": 3.076036866359447e-05,
+      "loss": 0.4796,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7555933163409798,
+      "grad_norm": 1.4632591009140015,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4787,
+      "step": 1550
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 1.3220279216766357,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.4785,
+      "step": 1600
+    },
+    {
+      "epoch": 1.812234494477485,
+      "eval_loss": 0.5232844352722168,
+      "eval_runtime": 633.2557,
+      "eval_samples_per_second": 2.478,
+      "eval_steps_per_second": 0.621,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.71708083152771,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.4901,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 1.0889732837677002,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.475,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 1.226163387298584,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.4729,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 1.93405020236969,
+      "learning_rate": 6.491027109583811e-05,
+      "loss": 0.3981,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "eval_loss": 0.534080982208252,
+      "eval_runtime": 635.9448,
+      "eval_samples_per_second": 2.467,
+      "eval_steps_per_second": 0.618,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.4278013706207275,
+      "learning_rate": 6.109201985490646e-05,
+      "loss": 0.4229,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.6030181646347046,
+      "learning_rate": 5.72737686139748e-05,
+      "loss": 0.4363,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.3467751741409302,
+      "learning_rate": 5.345551737304315e-05,
+      "loss": 0.425,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.390838623046875,
+      "learning_rate": 4.963726613211149e-05,
+      "loss": 0.4185,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "eval_loss": 0.5372938513755798,
+      "eval_runtime": 635.7783,
+      "eval_samples_per_second": 2.468,
+      "eval_steps_per_second": 0.618,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 1.3252273797988892,
+      "learning_rate": 4.581901489117984e-05,
+      "loss": 0.43,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.2557967901229858,
+      "learning_rate": 4.2000763650248184e-05,
+      "loss": 0.4386,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.649653434753418,
+      "learning_rate": 3.818251240931654e-05,
+      "loss": 0.4273,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 1.5756187438964844,
+      "learning_rate": 3.4364261168384884e-05,
+      "loss": 0.3909,
+      "step": 2200
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "eval_loss": 0.542982280254364,
+      "eval_runtime": 635.1617,
+      "eval_samples_per_second": 2.47,
+      "eval_steps_per_second": 0.619,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.4305800199508667,
+      "learning_rate": 3.054600992745323e-05,
+      "loss": 0.4111,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.4521535634994507,
+      "learning_rate": 2.6727758686521576e-05,
+      "loss": 0.4402,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6615689606343813,
+      "grad_norm": 1.3872359991073608,
+      "learning_rate": 2.290950744558992e-05,
+      "loss": 0.4293,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "grad_norm": 1.6272056102752686,
+      "learning_rate": 1.909125620465827e-05,
+      "loss": 0.4145,
+      "step": 2400
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "eval_loss": 0.5353428721427917,
+      "eval_runtime": 628.4439,
+      "eval_samples_per_second": 2.497,
+      "eval_steps_per_second": 0.625,
+      "step": 2400
+    },
+    {
+      "epoch": 2.774851316907392,
+      "grad_norm": 1.1917740106582642,
+      "learning_rate": 1.5273004963726615e-05,
+      "loss": 0.4022,
+      "step": 2450
+    },
+    {
+      "epoch": 2.831492495043897,
+      "grad_norm": 1.5548139810562134,
+      "learning_rate": 1.145475372279496e-05,
+      "loss": 0.4155,
+      "step": 2500
+    },
+    {
+      "epoch": 2.888133673180402,
+      "grad_norm": 2.0399019718170166,
+      "learning_rate": 7.636502481863307e-06,
+      "loss": 0.4169,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "grad_norm": 1.6849918365478516,
+      "learning_rate": 3.818251240931654e-06,
+      "loss": 0.4145,
+      "step": 2600
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "eval_loss": 0.5327087640762329,
+      "eval_runtime": 636.4789,
+      "eval_samples_per_second": 2.465,
+      "eval_steps_per_second": 0.617,
+      "step": 2600
+    },
+    {
+      "epoch": 3.00113282356273,
+      "grad_norm": 1.1705021858215332,
+      "learning_rate": 0.0,
+      "loss": 0.3254,
+      "step": 2650
+    },
+    {
+      "epoch": 3.057774001699235,
+      "grad_norm": 1.3165022134780884,
+      "learning_rate": 4.757281553398059e-05,
+      "loss": 0.367,
+      "step": 2700
+    },
+    {
+      "epoch": 3.1144151798357407,
+      "grad_norm": 1.557210922241211,
+      "learning_rate": 4.4717304397487155e-05,
+      "loss": 0.3588,
+      "step": 2750
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "grad_norm": 1.7867581844329834,
+      "learning_rate": 4.186179326099372e-05,
+      "loss": 0.3761,
+      "step": 2800
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "eval_loss": 0.555277407169342,
+      "eval_runtime": 631.0969,
+      "eval_samples_per_second": 2.486,
+      "eval_steps_per_second": 0.623,
+      "step": 2800
+    },
+    {
+      "epoch": 3.227697536108751,
+      "grad_norm": 1.8431845903396606,
+      "learning_rate": 3.900628212450029e-05,
+      "loss": 0.402,
+      "step": 2850
+    },
+    {
+      "epoch": 3.2843387142452563,
+      "grad_norm": 2.415738344192505,
+      "learning_rate": 3.6150770988006854e-05,
+      "loss": 0.3614,
+      "step": 2900
+    },
+    {
+      "epoch": 3.3409798923817613,
+      "grad_norm": 1.8246201276779175,
+      "learning_rate": 3.329525985151342e-05,
+      "loss": 0.3896,
+      "step": 2950
+    },
+    {
+      "epoch": 3.397621070518267,
+      "grad_norm": 1.1022515296936035,
+      "learning_rate": 3.043974871501999e-05,
+      "loss": 0.3746,
+      "step": 3000
+    },
+    {
+      "epoch": 3.397621070518267,
+      "eval_loss": 0.5586006045341492,
+      "eval_runtime": 613.6818,
+      "eval_samples_per_second": 2.557,
+      "eval_steps_per_second": 0.64,
+      "step": 3000
+    },
+    {
+      "epoch": 3.454262248654772,
+      "grad_norm": 2.3615689277648926,
+      "learning_rate": 2.7584237578526556e-05,
+      "loss": 0.3748,
+      "step": 3050
+    },
+    {
+      "epoch": 3.5109034267912773,
+      "grad_norm": 2.1353960037231445,
+      "learning_rate": 2.4728726442033126e-05,
+      "loss": 0.38,
+      "step": 3100
+    },
+    {
+      "epoch": 3.5675446049277824,
+      "grad_norm": 1.7389541864395142,
+      "learning_rate": 2.1873215305539692e-05,
+      "loss": 0.3816,
+      "step": 3150
+    },
+    {
+      "epoch": 3.624185783064288,
+      "grad_norm": 1.8731958866119385,
+      "learning_rate": 1.9017704169046262e-05,
+      "loss": 0.388,
+      "step": 3200
+    },
+    {
+      "epoch": 3.624185783064288,
+      "eval_loss": 0.5509854555130005,
+      "eval_runtime": 605.0872,
+      "eval_samples_per_second": 2.593,
+      "eval_steps_per_second": 0.649,
+      "step": 3200
+    },
+    {
+      "epoch": 3.680826961200793,
+      "grad_norm": 1.814975380897522,
+      "learning_rate": 1.6162193032552828e-05,
+      "loss": 0.3897,
+      "step": 3250
+    },
+    {
+      "epoch": 3.7374681393372984,
+      "grad_norm": 1.8525991439819336,
+      "learning_rate": 1.3306681896059394e-05,
+      "loss": 0.3931,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7941093174738034,
+      "grad_norm": 2.1449315547943115,
+      "learning_rate": 1.0451170759565964e-05,
+      "loss": 0.3987,
+      "step": 3350
+    },
+    {
+      "epoch": 3.850750495610309,
+      "grad_norm": 1.2358556985855103,
+      "learning_rate": 7.59565962307253e-06,
+      "loss": 0.3695,
+      "step": 3400
+    },
+    {
+      "epoch": 3.850750495610309,
+      "eval_loss": 0.5485390424728394,
+      "eval_runtime": 606.2751,
+      "eval_samples_per_second": 2.588,
+      "eval_steps_per_second": 0.648,
+      "step": 3400
+    },
+    {
+      "epoch": 3.907391673746814,
+      "grad_norm": 2.7738165855407715,
+      "learning_rate": 4.7401484865790974e-06,
+      "loss": 0.3841,
+      "step": 3450
+    },
+    {
+      "epoch": 3.964032851883319,
+      "grad_norm": 2.6049118041992188,
+      "learning_rate": 1.8846373500856656e-06,
+      "loss": 0.3742,
+      "step": 3500
+    },
+    {
+      "epoch": 4.020390824129142,
+      "grad_norm": 1.459250569343567,
+      "learning_rate": 6.64009111617312e-05,
+      "loss": 0.3493,
+      "step": 3550
+    },
+    {
+      "epoch": 4.077032002265647,
+      "grad_norm": 1.3481236696243286,
+      "learning_rate": 6.450265755504936e-05,
+      "loss": 0.3414,
+      "step": 3600
+    },
+    {
+      "epoch": 4.077032002265647,
+      "eval_loss": 0.5706936717033386,
+      "eval_runtime": 626.8261,
+      "eval_samples_per_second": 2.503,
+      "eval_steps_per_second": 0.627,
+      "step": 3600
+    },
+    {
+      "epoch": 4.133673180402153,
+      "grad_norm": 1.5863535404205322,
+      "learning_rate": 6.260440394836751e-05,
+      "loss": 0.3964,
+      "step": 3650
+    },
+    {
+      "epoch": 4.190314358538657,
+      "grad_norm": 1.4147838354110718,
+      "learning_rate": 6.070615034168565e-05,
+      "loss": 0.3688,
+      "step": 3700
+    },
+    {
+      "epoch": 4.246955536675163,
+      "grad_norm": 1.7272146940231323,
+      "learning_rate": 5.88078967350038e-05,
+      "loss": 0.3554,
+      "step": 3750
+    },
+    {
+      "epoch": 4.303596714811668,
+      "grad_norm": 1.7022188901901245,
+      "learning_rate": 5.6909643128321947e-05,
+      "loss": 0.362,
+      "step": 3800
+    },
+    {
+      "epoch": 4.303596714811668,
+      "eval_loss": 0.5747559070587158,
+      "eval_runtime": 603.0566,
+      "eval_samples_per_second": 2.602,
+      "eval_steps_per_second": 0.652,
+      "step": 3800
+    },
+    {
+      "epoch": 4.360237892948174,
+      "grad_norm": 1.8977692127227783,
+      "learning_rate": 5.501138952164009e-05,
+      "loss": 0.3787,
+      "step": 3850
+    },
+    {
+      "epoch": 4.416879071084678,
+      "grad_norm": 1.7641384601593018,
+      "learning_rate": 5.311313591495825e-05,
+      "loss": 0.417,
+      "step": 3900
+    },
+    {
+      "epoch": 4.473520249221184,
+      "grad_norm": 1.6231164932250977,
+      "learning_rate": 5.121488230827639e-05,
+      "loss": 0.3691,
+      "step": 3950
+    },
+    {
+      "epoch": 4.530161427357689,
+      "grad_norm": 1.8207956552505493,
+      "learning_rate": 4.9316628701594535e-05,
+      "loss": 0.3806,
+      "step": 4000
+    },
+    {
+      "epoch": 4.530161427357689,
+      "eval_loss": 0.5716577768325806,
+      "eval_runtime": 602.7077,
+      "eval_samples_per_second": 2.603,
+      "eval_steps_per_second": 0.652,
+      "step": 4000
+    },
+    {
+      "epoch": 4.586802605494194,
+      "grad_norm": 1.501741886138916,
+      "learning_rate": 4.741837509491268e-05,
+      "loss": 0.3787,
+      "step": 4050
+    },
+    {
+      "epoch": 4.643443783630699,
+      "grad_norm": 3.1166610717773438,
+      "learning_rate": 4.552012148823083e-05,
+      "loss": 0.3726,
+      "step": 4100
+    },
+    {
+      "epoch": 4.700084961767205,
+      "grad_norm": 2.083258867263794,
+      "learning_rate": 4.362186788154898e-05,
+      "loss": 0.364,
+      "step": 4150
+    },
+    {
+      "epoch": 4.75672613990371,
+      "grad_norm": 1.941104769706726,
+      "learning_rate": 4.1723614274867124e-05,
+      "loss": 0.3914,
+      "step": 4200
+    },
+    {
+      "epoch": 4.75672613990371,
+      "eval_loss": 0.5698277354240417,
+      "eval_runtime": 604.4852,
+      "eval_samples_per_second": 2.596,
+      "eval_steps_per_second": 0.65,
+      "step": 4200
+    },
+    {
+      "epoch": 4.813367318040215,
+      "grad_norm": 1.896347165107727,
+      "learning_rate": 3.982536066818527e-05,
+      "loss": 0.3706,
+      "step": 4250
+    },
+    {
+      "epoch": 4.8700084961767205,
+      "grad_norm": 1.9356690645217896,
+      "learning_rate": 3.792710706150342e-05,
+      "loss": 0.3735,
+      "step": 4300
+    },
+    {
+      "epoch": 4.926649674313226,
+      "grad_norm": 2.048717975616455,
+      "learning_rate": 3.6028853454821566e-05,
+      "loss": 0.3775,
+      "step": 4350
+    },
+    {
+      "epoch": 4.983290852449731,
+      "grad_norm": 1.8730669021606445,
+      "learning_rate": 3.413059984813971e-05,
+      "loss": 0.3671,
+      "step": 4400
+    },
+    {
+      "epoch": 4.983290852449731,
+      "eval_loss": 0.5636136531829834,
+      "eval_runtime": 604.9156,
+      "eval_samples_per_second": 2.594,
+      "eval_steps_per_second": 0.65,
+      "step": 4400
+    },
+    {
+      "epoch": 5.039648824695553,
+      "grad_norm": 1.3539544343948364,
+      "learning_rate": 3.223234624145786e-05,
+      "loss": 0.328,
+      "step": 4450
+    },
+    {
+      "epoch": 5.096290002832059,
+      "grad_norm": 1.5452523231506348,
+      "learning_rate": 3.0334092634776008e-05,
+      "loss": 0.32,
+      "step": 4500
+    },
+    {
+      "epoch": 5.152931180968564,
+      "grad_norm": 1.3977546691894531,
+      "learning_rate": 2.843583902809415e-05,
+      "loss": 0.3084,
+      "step": 4550
+    },
+    {
+      "epoch": 5.20957235910507,
+      "grad_norm": 4.15449333190918,
+      "learning_rate": 2.6537585421412302e-05,
+      "loss": 0.3017,
+      "step": 4600
+    },
+    {
+      "epoch": 5.20957235910507,
+      "eval_loss": 0.5834115743637085,
+      "eval_runtime": 603.5666,
+      "eval_samples_per_second": 2.6,
+      "eval_steps_per_second": 0.651,
+      "step": 4600
+    },
+    {
+      "epoch": 5.266213537241574,
+      "grad_norm": 1.6772358417510986,
+      "learning_rate": 2.463933181473045e-05,
+      "loss": 0.3023,
+      "step": 4650
+    },
+    {
+      "epoch": 5.32285471537808,
+      "grad_norm": 1.5398720502853394,
+      "learning_rate": 2.2741078208048596e-05,
+      "loss": 0.3061,
+      "step": 4700
+    },
+    {
+      "epoch": 5.379495893514585,
+      "grad_norm": 1.567535638809204,
+      "learning_rate": 2.0842824601366744e-05,
+      "loss": 0.3143,
+      "step": 4750
+    },
+    {
+      "epoch": 5.43613707165109,
+      "grad_norm": 1.6017929315567017,
+      "learning_rate": 1.894457099468489e-05,
+      "loss": 0.3009,
+      "step": 4800
+    },
+    {
+      "epoch": 5.43613707165109,
+      "eval_loss": 0.5849186778068542,
+      "eval_runtime": 604.7855,
+      "eval_samples_per_second": 2.594,
+      "eval_steps_per_second": 0.65,
+      "step": 4800
+    },
+    {
+      "epoch": 5.492778249787595,
+      "grad_norm": 1.815103530883789,
+      "learning_rate": 1.7046317388003038e-05,
+      "loss": 0.3196,
+      "step": 4850
+    },
+    {
+      "epoch": 5.549419427924101,
+      "grad_norm": 1.6697149276733398,
+      "learning_rate": 1.5148063781321184e-05,
+      "loss": 0.301,
+      "step": 4900
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 1.9685876369476318,
+      "learning_rate": 1.3249810174639332e-05,
+      "loss": 0.3275,
+      "step": 4950
+    },
+    {
+      "epoch": 5.662701784197111,
+      "grad_norm": 1.4504376649856567,
+      "learning_rate": 1.135155656795748e-05,
+      "loss": 0.3089,
+      "step": 5000
+    },
+    {
+      "epoch": 5.662701784197111,
+      "eval_loss": 0.5848227739334106,
+      "eval_runtime": 604.1032,
+      "eval_samples_per_second": 2.597,
+      "eval_steps_per_second": 0.651,
+      "step": 5000
+    },
+    {
+      "epoch": 5.7193429623336165,
+      "grad_norm": 2.6677732467651367,
+      "learning_rate": 9.453302961275627e-06,
+      "loss": 0.3178,
+      "step": 5050
+    },
+    {
+      "epoch": 5.775984140470122,
+      "grad_norm": 2.2549753189086914,
+      "learning_rate": 7.555049354593774e-06,
+      "loss": 0.2891,
+      "step": 5100
+    },
+    {
+      "epoch": 5.8326253186066275,
+      "grad_norm": 1.5250205993652344,
+      "learning_rate": 5.656795747911921e-06,
+      "loss": 0.3122,
+      "step": 5150
+    },
+    {
+      "epoch": 5.889266496743132,
+      "grad_norm": 1.8577101230621338,
+      "learning_rate": 3.758542141230068e-06,
+      "loss": 0.3032,
+      "step": 5200
+    },
+    {
+      "epoch": 5.889266496743132,
+      "eval_loss": 0.5855553150177002,
+      "eval_runtime": 603.8918,
+      "eval_samples_per_second": 2.598,
+      "eval_steps_per_second": 0.651,
+      "step": 5200
+    },
+    {
+      "epoch": 5.945907674879638,
+      "grad_norm": 1.511374592781067,
+      "learning_rate": 1.8602885345482157e-06,
+      "loss": 0.3278,
+      "step": 5250
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5298,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.169929616696749e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5298/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9daeff4f7649949e91566fac7256a9010f7454bfc785ed8b3dcfee3bac4529
+size 5688

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

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