Add files using upload-large-folder tool

README.md

@@ -0,0 +1,59 @@
+---
+base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
+library_name: transformers
+model_name: Gemma-3-1B-it-Medical-finetuning
+tags:
+- generated_from_trainer
+- trl
+- unsloth
+- sft
+licence: license
+---
+
+# Model Card for Gemma-3-1B-it-Medical-finetuning
+
+This model is a fine-tuned version of [unsloth/gemma-3-1b-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/gemma-3-1b-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
+
+- 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}}
+}
+```

checkpoint-1050/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-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-1050/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-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).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1050/added_tokens.json

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

checkpoint-1050/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-1050/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea43ba48f87ef5af98ef31908f1f9c1f429fde6235e7dc435a0e0dfdd297a3c
+size 26913924

checkpoint-1050/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-1050/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1891815349759276,
+  "eval_steps": 354,
+  "global_step": 1050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7603653073310852,
+      "learning_rate": 0.0001978110599078341,
+      "loss": 0.9425,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.6873273849487305,
+      "learning_rate": 0.00019205069124423964,
+      "loss": 0.6078,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6323167085647583,
+      "learning_rate": 0.00018629032258064517,
+      "loss": 0.6748,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 1.0095610618591309,
+      "learning_rate": 0.0001805299539170507,
+      "loss": 0.6594,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.5822212100028992,
+      "learning_rate": 0.00017476958525345623,
+      "loss": 0.6317,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8490907549858093,
+      "learning_rate": 0.00016900921658986176,
+      "loss": 0.5742,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.6252707242965698,
+      "learning_rate": 0.0001632488479262673,
+      "loss": 0.5502,
+      "step": 350
+    },
+    {
+      "epoch": 0.4010195412064571,
+      "eval_loss": 0.6019027233123779,
+      "eval_runtime": 159.9351,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 2.457,
+      "step": 354
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.656812310218811,
+      "learning_rate": 0.00015748847926267282,
+      "loss": 0.5686,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.7391073703765869,
+      "learning_rate": 0.00015172811059907835,
+      "loss": 0.5701,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.9210707545280457,
+      "learning_rate": 0.00014596774193548388,
+      "loss": 0.6397,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8228403329849243,
+      "learning_rate": 0.00014020737327188939,
+      "loss": 0.5822,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.716748833656311,
+      "learning_rate": 0.00013444700460829494,
+      "loss": 0.5881,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.7144941091537476,
+      "learning_rate": 0.00012868663594470047,
+      "loss": 0.6032,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.016291618347168,
+      "learning_rate": 0.000122926267281106,
+      "loss": 0.6377,
+      "step": 700
+    },
+    {
+      "epoch": 0.8020390824129142,
+      "eval_loss": 0.5828524827957153,
+      "eval_runtime": 150.8754,
+      "eval_samples_per_second": 10.399,
+      "eval_steps_per_second": 2.605,
+      "step": 708
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.0243154764175415,
+      "learning_rate": 0.00011716589861751153,
+      "loss": 0.6005,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6541144251823425,
+      "learning_rate": 0.00011140552995391706,
+      "loss": 0.5723,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.0017038583755493,
+      "learning_rate": 0.00010564516129032258,
+      "loss": 0.5801,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.7527189254760742,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5511,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.7966899871826172,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.49,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7110822796821594,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4725,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.7837777733802795,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.527,
+      "step": 1050
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1766,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.542910187300531e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1150/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-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-1150/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-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).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1150/added_tokens.json

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

checkpoint-1150/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-1150/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-1150/trainer_state.json

@@ -0,0 +1,219 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.302463891248938,
+  "eval_steps": 354,
+  "global_step": 1150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7603653073310852,
+      "learning_rate": 0.0001978110599078341,
+      "loss": 0.9425,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.6873273849487305,
+      "learning_rate": 0.00019205069124423964,
+      "loss": 0.6078,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6323167085647583,
+      "learning_rate": 0.00018629032258064517,
+      "loss": 0.6748,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 1.0095610618591309,
+      "learning_rate": 0.0001805299539170507,
+      "loss": 0.6594,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.5822212100028992,
+      "learning_rate": 0.00017476958525345623,
+      "loss": 0.6317,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8490907549858093,
+      "learning_rate": 0.00016900921658986176,
+      "loss": 0.5742,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.6252707242965698,
+      "learning_rate": 0.0001632488479262673,
+      "loss": 0.5502,
+      "step": 350
+    },
+    {
+      "epoch": 0.4010195412064571,
+      "eval_loss": 0.6019027233123779,
+      "eval_runtime": 159.9351,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 2.457,
+      "step": 354
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.656812310218811,
+      "learning_rate": 0.00015748847926267282,
+      "loss": 0.5686,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.7391073703765869,
+      "learning_rate": 0.00015172811059907835,
+      "loss": 0.5701,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.9210707545280457,
+      "learning_rate": 0.00014596774193548388,
+      "loss": 0.6397,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8228403329849243,
+      "learning_rate": 0.00014020737327188939,
+      "loss": 0.5822,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.716748833656311,
+      "learning_rate": 0.00013444700460829494,
+      "loss": 0.5881,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.7144941091537476,
+      "learning_rate": 0.00012868663594470047,
+      "loss": 0.6032,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.016291618347168,
+      "learning_rate": 0.000122926267281106,
+      "loss": 0.6377,
+      "step": 700
+    },
+    {
+      "epoch": 0.8020390824129142,
+      "eval_loss": 0.5828524827957153,
+      "eval_runtime": 150.8754,
+      "eval_samples_per_second": 10.399,
+      "eval_steps_per_second": 2.605,
+      "step": 708
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.0243154764175415,
+      "learning_rate": 0.00011716589861751153,
+      "loss": 0.6005,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6541144251823425,
+      "learning_rate": 0.00011140552995391706,
+      "loss": 0.5723,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.0017038583755493,
+      "learning_rate": 0.00010564516129032258,
+      "loss": 0.5801,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.7527189254760742,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5511,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.7966899871826172,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.49,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7110822796821594,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4725,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.7837777733802795,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.527,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2027754177286887,
+      "eval_loss": 0.5833637714385986,
+      "eval_runtime": 150.6223,
+      "eval_samples_per_second": 10.417,
+      "eval_steps_per_second": 2.609,
+      "step": 1062
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 0.8119267821311951,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.4892,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 0.8631129860877991,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.5124,
+      "step": 1150
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1766,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.892113436180147e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-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-1300/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-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).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1300/added_tokens.json

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

checkpoint-1300/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-1300/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-1300/trainer_state.json

@@ -0,0 +1,240 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4723874256584537,
+  "eval_steps": 354,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7603653073310852,
+      "learning_rate": 0.0001978110599078341,
+      "loss": 0.9425,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.6873273849487305,
+      "learning_rate": 0.00019205069124423964,
+      "loss": 0.6078,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6323167085647583,
+      "learning_rate": 0.00018629032258064517,
+      "loss": 0.6748,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 1.0095610618591309,
+      "learning_rate": 0.0001805299539170507,
+      "loss": 0.6594,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.5822212100028992,
+      "learning_rate": 0.00017476958525345623,
+      "loss": 0.6317,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8490907549858093,
+      "learning_rate": 0.00016900921658986176,
+      "loss": 0.5742,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.6252707242965698,
+      "learning_rate": 0.0001632488479262673,
+      "loss": 0.5502,
+      "step": 350
+    },
+    {
+      "epoch": 0.4010195412064571,
+      "eval_loss": 0.6019027233123779,
+      "eval_runtime": 159.9351,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 2.457,
+      "step": 354
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.656812310218811,
+      "learning_rate": 0.00015748847926267282,
+      "loss": 0.5686,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.7391073703765869,
+      "learning_rate": 0.00015172811059907835,
+      "loss": 0.5701,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.9210707545280457,
+      "learning_rate": 0.00014596774193548388,
+      "loss": 0.6397,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8228403329849243,
+      "learning_rate": 0.00014020737327188939,
+      "loss": 0.5822,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.716748833656311,
+      "learning_rate": 0.00013444700460829494,
+      "loss": 0.5881,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.7144941091537476,
+      "learning_rate": 0.00012868663594470047,
+      "loss": 0.6032,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.016291618347168,
+      "learning_rate": 0.000122926267281106,
+      "loss": 0.6377,
+      "step": 700
+    },
+    {
+      "epoch": 0.8020390824129142,
+      "eval_loss": 0.5828524827957153,
+      "eval_runtime": 150.8754,
+      "eval_samples_per_second": 10.399,
+      "eval_steps_per_second": 2.605,
+      "step": 708
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.0243154764175415,
+      "learning_rate": 0.00011716589861751153,
+      "loss": 0.6005,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6541144251823425,
+      "learning_rate": 0.00011140552995391706,
+      "loss": 0.5723,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.0017038583755493,
+      "learning_rate": 0.00010564516129032258,
+      "loss": 0.5801,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.7527189254760742,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5511,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.7966899871826172,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.49,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7110822796821594,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4725,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.7837777733802795,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.527,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2027754177286887,
+      "eval_loss": 0.5833637714385986,
+      "eval_runtime": 150.6223,
+      "eval_samples_per_second": 10.417,
+      "eval_steps_per_second": 2.609,
+      "step": 1062
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 0.8119267821311951,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.4892,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 0.8631129860877991,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.5124,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 0.8685782551765442,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.4927,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 0.8397710919380188,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.5125,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 0.7606781721115112,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.4826,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1766,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.38804995875223e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1350/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-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-1350/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-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).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1350/added_tokens.json

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

checkpoint-1350/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-1350/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-1350/trainer_state.json

@@ -0,0 +1,247 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.529028603794959,
+  "eval_steps": 354,
+  "global_step": 1350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7603653073310852,
+      "learning_rate": 0.0001978110599078341,
+      "loss": 0.9425,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.6873273849487305,
+      "learning_rate": 0.00019205069124423964,
+      "loss": 0.6078,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6323167085647583,
+      "learning_rate": 0.00018629032258064517,
+      "loss": 0.6748,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 1.0095610618591309,
+      "learning_rate": 0.0001805299539170507,
+      "loss": 0.6594,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.5822212100028992,
+      "learning_rate": 0.00017476958525345623,
+      "loss": 0.6317,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8490907549858093,
+      "learning_rate": 0.00016900921658986176,
+      "loss": 0.5742,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.6252707242965698,
+      "learning_rate": 0.0001632488479262673,
+      "loss": 0.5502,
+      "step": 350
+    },
+    {
+      "epoch": 0.4010195412064571,
+      "eval_loss": 0.6019027233123779,
+      "eval_runtime": 159.9351,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 2.457,
+      "step": 354
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.656812310218811,
+      "learning_rate": 0.00015748847926267282,
+      "loss": 0.5686,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.7391073703765869,
+      "learning_rate": 0.00015172811059907835,
+      "loss": 0.5701,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.9210707545280457,
+      "learning_rate": 0.00014596774193548388,
+      "loss": 0.6397,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8228403329849243,
+      "learning_rate": 0.00014020737327188939,
+      "loss": 0.5822,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.716748833656311,
+      "learning_rate": 0.00013444700460829494,
+      "loss": 0.5881,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.7144941091537476,
+      "learning_rate": 0.00012868663594470047,
+      "loss": 0.6032,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.016291618347168,
+      "learning_rate": 0.000122926267281106,
+      "loss": 0.6377,
+      "step": 700
+    },
+    {
+      "epoch": 0.8020390824129142,
+      "eval_loss": 0.5828524827957153,
+      "eval_runtime": 150.8754,
+      "eval_samples_per_second": 10.399,
+      "eval_steps_per_second": 2.605,
+      "step": 708
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.0243154764175415,
+      "learning_rate": 0.00011716589861751153,
+      "loss": 0.6005,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6541144251823425,
+      "learning_rate": 0.00011140552995391706,
+      "loss": 0.5723,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.0017038583755493,
+      "learning_rate": 0.00010564516129032258,
+      "loss": 0.5801,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.7527189254760742,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5511,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.7966899871826172,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.49,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7110822796821594,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4725,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.7837777733802795,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.527,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2027754177286887,
+      "eval_loss": 0.5833637714385986,
+      "eval_runtime": 150.6223,
+      "eval_samples_per_second": 10.417,
+      "eval_steps_per_second": 2.609,
+      "step": 1062
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 0.8119267821311951,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.4892,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 0.8631129860877991,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.5124,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 0.8685782551765442,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.4927,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 0.8397710919380188,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.5125,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 0.7606781721115112,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.4826,
+      "step": 1300
+    },
+    {
+      "epoch": 1.529028603794959,
+      "grad_norm": 1.1354798078536987,
+      "learning_rate": 4.8041474654377885e-05,
+      "loss": 0.5101,
+      "step": 1350
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1766,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.561452082146586e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1400/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-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-1400/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-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).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1400/added_tokens.json

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

checkpoint-1400/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-1400/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-1400/trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5856697819314642,
+  "eval_steps": 354,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7603653073310852,
+      "learning_rate": 0.0001978110599078341,
+      "loss": 0.9425,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.6873273849487305,
+      "learning_rate": 0.00019205069124423964,
+      "loss": 0.6078,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6323167085647583,
+      "learning_rate": 0.00018629032258064517,
+      "loss": 0.6748,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 1.0095610618591309,
+      "learning_rate": 0.0001805299539170507,
+      "loss": 0.6594,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.5822212100028992,
+      "learning_rate": 0.00017476958525345623,
+      "loss": 0.6317,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8490907549858093,
+      "learning_rate": 0.00016900921658986176,
+      "loss": 0.5742,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.6252707242965698,
+      "learning_rate": 0.0001632488479262673,
+      "loss": 0.5502,
+      "step": 350
+    },
+    {
+      "epoch": 0.4010195412064571,
+      "eval_loss": 0.6019027233123779,
+      "eval_runtime": 159.9351,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 2.457,
+      "step": 354
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.656812310218811,
+      "learning_rate": 0.00015748847926267282,
+      "loss": 0.5686,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.7391073703765869,
+      "learning_rate": 0.00015172811059907835,
+      "loss": 0.5701,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.9210707545280457,
+      "learning_rate": 0.00014596774193548388,
+      "loss": 0.6397,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8228403329849243,
+      "learning_rate": 0.00014020737327188939,
+      "loss": 0.5822,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.716748833656311,
+      "learning_rate": 0.00013444700460829494,
+      "loss": 0.5881,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.7144941091537476,
+      "learning_rate": 0.00012868663594470047,
+      "loss": 0.6032,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.016291618347168,
+      "learning_rate": 0.000122926267281106,
+      "loss": 0.6377,
+      "step": 700
+    },
+    {
+      "epoch": 0.8020390824129142,
+      "eval_loss": 0.5828524827957153,
+      "eval_runtime": 150.8754,
+      "eval_samples_per_second": 10.399,
+      "eval_steps_per_second": 2.605,
+      "step": 708
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.0243154764175415,
+      "learning_rate": 0.00011716589861751153,
+      "loss": 0.6005,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6541144251823425,
+      "learning_rate": 0.00011140552995391706,
+      "loss": 0.5723,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.0017038583755493,
+      "learning_rate": 0.00010564516129032258,
+      "loss": 0.5801,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.7527189254760742,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5511,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.7966899871826172,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.49,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7110822796821594,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4725,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.7837777733802795,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.527,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2027754177286887,
+      "eval_loss": 0.5833637714385986,
+      "eval_runtime": 150.6223,
+      "eval_samples_per_second": 10.417,
+      "eval_steps_per_second": 2.609,
+      "step": 1062
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 0.8119267821311951,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.4892,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 0.8631129860877991,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.5124,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 0.8685782551765442,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.4927,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 0.8397710919380188,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.5125,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 0.7606781721115112,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.4826,
+      "step": 1300
+    },
+    {
+      "epoch": 1.529028603794959,
+      "grad_norm": 1.1354798078536987,
+      "learning_rate": 4.8041474654377885e-05,
+      "loss": 0.5101,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "grad_norm": 1.28499174118042,
+      "learning_rate": 4.228110599078341e-05,
+      "loss": 0.4687,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1766,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.733001206770867e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1550/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-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-1550/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-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).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1550/added_tokens.json

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

checkpoint-1550/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-1550/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-1550/trainer_state.json

@@ -0,0 +1,283 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7555933163409798,
+  "eval_steps": 354,
+  "global_step": 1550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7603653073310852,
+      "learning_rate": 0.0001978110599078341,
+      "loss": 0.9425,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.6873273849487305,
+      "learning_rate": 0.00019205069124423964,
+      "loss": 0.6078,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6323167085647583,
+      "learning_rate": 0.00018629032258064517,
+      "loss": 0.6748,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 1.0095610618591309,
+      "learning_rate": 0.0001805299539170507,
+      "loss": 0.6594,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.5822212100028992,
+      "learning_rate": 0.00017476958525345623,
+      "loss": 0.6317,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8490907549858093,
+      "learning_rate": 0.00016900921658986176,
+      "loss": 0.5742,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.6252707242965698,
+      "learning_rate": 0.0001632488479262673,
+      "loss": 0.5502,
+      "step": 350
+    },
+    {
+      "epoch": 0.4010195412064571,
+      "eval_loss": 0.6019027233123779,
+      "eval_runtime": 159.9351,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 2.457,
+      "step": 354
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.656812310218811,
+      "learning_rate": 0.00015748847926267282,
+      "loss": 0.5686,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.7391073703765869,
+      "learning_rate": 0.00015172811059907835,
+      "loss": 0.5701,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.9210707545280457,
+      "learning_rate": 0.00014596774193548388,
+      "loss": 0.6397,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8228403329849243,
+      "learning_rate": 0.00014020737327188939,
+      "loss": 0.5822,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.716748833656311,
+      "learning_rate": 0.00013444700460829494,
+      "loss": 0.5881,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.7144941091537476,
+      "learning_rate": 0.00012868663594470047,
+      "loss": 0.6032,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.016291618347168,
+      "learning_rate": 0.000122926267281106,
+      "loss": 0.6377,
+      "step": 700
+    },
+    {
+      "epoch": 0.8020390824129142,
+      "eval_loss": 0.5828524827957153,
+      "eval_runtime": 150.8754,
+      "eval_samples_per_second": 10.399,
+      "eval_steps_per_second": 2.605,
+      "step": 708
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.0243154764175415,
+      "learning_rate": 0.00011716589861751153,
+      "loss": 0.6005,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6541144251823425,
+      "learning_rate": 0.00011140552995391706,
+      "loss": 0.5723,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.0017038583755493,
+      "learning_rate": 0.00010564516129032258,
+      "loss": 0.5801,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.7527189254760742,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5511,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.7966899871826172,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.49,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7110822796821594,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4725,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.7837777733802795,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.527,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2027754177286887,
+      "eval_loss": 0.5833637714385986,
+      "eval_runtime": 150.6223,
+      "eval_samples_per_second": 10.417,
+      "eval_steps_per_second": 2.609,
+      "step": 1062
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 0.8119267821311951,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.4892,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 0.8631129860877991,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.5124,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 0.8685782551765442,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.4927,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 0.8397710919380188,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.5125,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 0.7606781721115112,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.4826,
+      "step": 1300
+    },
+    {
+      "epoch": 1.529028603794959,
+      "grad_norm": 1.1354798078536987,
+      "learning_rate": 4.8041474654377885e-05,
+      "loss": 0.5101,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "grad_norm": 1.28499174118042,
+      "learning_rate": 4.228110599078341e-05,
+      "loss": 0.4687,
+      "step": 1400
+    },
+    {
+      "epoch": 1.603794958935146,
+      "eval_loss": 0.5791710615158081,
+      "eval_runtime": 150.7437,
+      "eval_samples_per_second": 10.408,
+      "eval_steps_per_second": 2.607,
+      "step": 1416
+    },
+    {
+      "epoch": 1.6423109600679693,
+      "grad_norm": 0.7527874708175659,
+      "learning_rate": 3.6520737327188945e-05,
+      "loss": 0.4992,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6989521382044748,
+      "grad_norm": 0.9351261854171753,
+      "learning_rate": 3.076036866359447e-05,
+      "loss": 0.4873,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7555933163409798,
+      "grad_norm": 1.0196998119354248,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4946,
+      "step": 1550
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1766,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.23606136641943e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1750/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-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-1750/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-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).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1750/added_tokens.json

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

checkpoint-1750/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-1750/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
+  }
+}