Add files using upload-large-folder tool

.gitattributes

@@ -70,3 +70,4 @@ checkpoint-1450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-2700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2150/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f5b45c55e74415f03f5968a21fecbacd98f41b5efc3be528f5b9d3eec6a361
+size 52231312

checkpoint-2150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5174a5dae8de8d43a05262b471d566c57006d9cc20f011daf4579851eb78b383
+size 27860634

checkpoint-2150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
+size 14244

checkpoint-2150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2bfd7aa4dccc3ea4af50133012cfdc40b9e332676e4d5987f0348ed93a899c
+size 1064

checkpoint-2150/tokenizer.json

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

checkpoint-2150/tokenizer.model

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

checkpoint-2150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a005f970f4cec3bcd1f966ef18d4a684fb77d0ec7f69f10a53aafcf21569519
+size 5752

checkpoint-2300/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-2300/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-2300/added_tokens.json

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

checkpoint-2300/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-2300/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-2300/trainer_state.json

@@ -0,0 +1,404 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.604927782497876,
+  "eval_steps": 354,
+  "global_step": 2300,
+  "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
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 0.9896508455276489,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.4895,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.150964617729187,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.5164,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 0.8384917378425598,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.4914,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 0.9231545329093933,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.4939,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0045312942509206,
+      "eval_loss": 0.5844214558601379,
+      "eval_runtime": 166.1298,
+      "eval_samples_per_second": 9.444,
+      "eval_steps_per_second": 2.366,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 0.9673134088516235,
+      "learning_rate": 0.00014248089741505446,
+      "loss": 0.4303,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.33237624168396,
+      "learning_rate": 0.00014085514550479596,
+      "loss": 0.4594,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.068943738937378,
+      "learning_rate": 0.0001392293935945375,
+      "loss": 0.4939,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.1625093221664429,
+      "learning_rate": 0.00013760364168427899,
+      "loss": 0.4757,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.080735683441162,
+      "learning_rate": 0.00013597788977402048,
+      "loss": 0.4724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 0.8823259472846985,
+      "learning_rate": 0.00013435213786376198,
+      "loss": 0.4821,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.0513312816619873,
+      "learning_rate": 0.0001327263859535035,
+      "loss": 0.479,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4055508354573774,
+      "eval_loss": 0.6049736738204956,
+      "eval_runtime": 156.3245,
+      "eval_samples_per_second": 10.037,
+      "eval_steps_per_second": 2.514,
+      "step": 2124
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.0902981758117676,
+      "learning_rate": 0.000131100634043245,
+      "loss": 0.4749,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 0.9050194025039673,
+      "learning_rate": 0.0001294748821329865,
+      "loss": 0.4346,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.0356699228286743,
+      "learning_rate": 0.00012784913022272803,
+      "loss": 0.4685,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.0071344375610352,
+      "learning_rate": 0.00012622337831246953,
+      "loss": 0.5,
+      "step": 2300
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6181,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 7.76218753362793e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2450/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-2450/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-2450/added_tokens.json

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

checkpoint-2450/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-2450/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-2450/trainer_state.json

@@ -0,0 +1,425 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.774851316907392,
+  "eval_steps": 354,
+  "global_step": 2450,
+  "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
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 0.9896508455276489,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.4895,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.150964617729187,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.5164,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 0.8384917378425598,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.4914,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 0.9231545329093933,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.4939,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0045312942509206,
+      "eval_loss": 0.5844214558601379,
+      "eval_runtime": 166.1298,
+      "eval_samples_per_second": 9.444,
+      "eval_steps_per_second": 2.366,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 0.9673134088516235,
+      "learning_rate": 0.00014248089741505446,
+      "loss": 0.4303,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.33237624168396,
+      "learning_rate": 0.00014085514550479596,
+      "loss": 0.4594,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.068943738937378,
+      "learning_rate": 0.0001392293935945375,
+      "loss": 0.4939,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.1625093221664429,
+      "learning_rate": 0.00013760364168427899,
+      "loss": 0.4757,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.080735683441162,
+      "learning_rate": 0.00013597788977402048,
+      "loss": 0.4724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 0.8823259472846985,
+      "learning_rate": 0.00013435213786376198,
+      "loss": 0.4821,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.0513312816619873,
+      "learning_rate": 0.0001327263859535035,
+      "loss": 0.479,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4055508354573774,
+      "eval_loss": 0.6049736738204956,
+      "eval_runtime": 156.3245,
+      "eval_samples_per_second": 10.037,
+      "eval_steps_per_second": 2.514,
+      "step": 2124
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.0902981758117676,
+      "learning_rate": 0.000131100634043245,
+      "loss": 0.4749,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 0.9050194025039673,
+      "learning_rate": 0.0001294748821329865,
+      "loss": 0.4346,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.0356699228286743,
+      "learning_rate": 0.00012784913022272803,
+      "loss": 0.4685,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.0071344375610352,
+      "learning_rate": 0.00012622337831246953,
+      "loss": 0.5,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6615689606343813,
+      "grad_norm": 1.0409235954284668,
+      "learning_rate": 0.00012459762640221103,
+      "loss": 0.4908,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "grad_norm": 0.8756324052810669,
+      "learning_rate": 0.00012297187449195252,
+      "loss": 0.4765,
+      "step": 2400
+    },
+    {
+      "epoch": 2.774851316907392,
+      "grad_norm": 0.6662527918815613,
+      "learning_rate": 0.00012134612258169405,
+      "loss": 0.4524,
+      "step": 2450
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6181,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 8.260217637683328e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2700/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da0cb9588c724e28d2543e52cfc36a57b53a477bcc2239de63eb79589d4949d
+size 52231312

checkpoint-3650/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-3650/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-3650/added_tokens.json

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

checkpoint-3650/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-3650/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-3650/trainer_state.json

@@ -0,0 +1,625 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.133673180402153,
+  "eval_steps": 354,
+  "global_step": 3650,
+  "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
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 0.9896508455276489,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.4895,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.150964617729187,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.5164,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 0.8384917378425598,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.4914,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 0.9231545329093933,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.4939,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0045312942509206,
+      "eval_loss": 0.5844214558601379,
+      "eval_runtime": 166.1298,
+      "eval_samples_per_second": 9.444,
+      "eval_steps_per_second": 2.366,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 0.9673134088516235,
+      "learning_rate": 0.00014248089741505446,
+      "loss": 0.4303,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.33237624168396,
+      "learning_rate": 0.00014085514550479596,
+      "loss": 0.4594,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.068943738937378,
+      "learning_rate": 0.0001392293935945375,
+      "loss": 0.4939,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.1625093221664429,
+      "learning_rate": 0.00013760364168427899,
+      "loss": 0.4757,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.080735683441162,
+      "learning_rate": 0.00013597788977402048,
+      "loss": 0.4724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 0.8823259472846985,
+      "learning_rate": 0.00013435213786376198,
+      "loss": 0.4821,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.0513312816619873,
+      "learning_rate": 0.0001327263859535035,
+      "loss": 0.479,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4055508354573774,
+      "eval_loss": 0.6049736738204956,
+      "eval_runtime": 156.3245,
+      "eval_samples_per_second": 10.037,
+      "eval_steps_per_second": 2.514,
+      "step": 2124
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.0902981758117676,
+      "learning_rate": 0.000131100634043245,
+      "loss": 0.4749,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 0.9050194025039673,
+      "learning_rate": 0.0001294748821329865,
+      "loss": 0.4346,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.0356699228286743,
+      "learning_rate": 0.00012784913022272803,
+      "loss": 0.4685,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.0071344375610352,
+      "learning_rate": 0.00012622337831246953,
+      "loss": 0.5,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6615689606343813,
+      "grad_norm": 1.0409235954284668,
+      "learning_rate": 0.00012459762640221103,
+      "loss": 0.4908,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "grad_norm": 0.8756324052810669,
+      "learning_rate": 0.00012297187449195252,
+      "loss": 0.4765,
+      "step": 2400
+    },
+    {
+      "epoch": 2.774851316907392,
+      "grad_norm": 0.6662527918815613,
+      "learning_rate": 0.00012134612258169405,
+      "loss": 0.4524,
+      "step": 2450
+    },
+    {
+      "epoch": 2.8065703766638346,
+      "eval_loss": 0.5904644727706909,
+      "eval_runtime": 157.1505,
+      "eval_samples_per_second": 9.984,
+      "eval_steps_per_second": 2.501,
+      "step": 2478
+    },
+    {
+      "epoch": 2.831492495043897,
+      "grad_norm": 1.0368993282318115,
+      "learning_rate": 0.00011972037067143556,
+      "loss": 0.4661,
+      "step": 2500
+    },
+    {
+      "epoch": 2.888133673180402,
+      "grad_norm": 1.0678080320358276,
+      "learning_rate": 0.00011809461876117705,
+      "loss": 0.4812,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "grad_norm": 1.2212059497833252,
+      "learning_rate": 0.00011646886685091856,
+      "loss": 0.482,
+      "step": 2600
+    },
+    {
+      "epoch": 3.00113282356273,
+      "grad_norm": 0.757663369178772,
+      "learning_rate": 0.00011484311494066007,
+      "loss": 0.5062,
+      "step": 2650
+    },
+    {
+      "epoch": 3.057774001699235,
+      "grad_norm": 0.8512151837348938,
+      "learning_rate": 0.00011321736303040155,
+      "loss": 0.3651,
+      "step": 2700
+    },
+    {
+      "epoch": 3.1144151798357407,
+      "grad_norm": 0.9610685706138611,
+      "learning_rate": 0.00011159161112014307,
+      "loss": 0.3626,
+      "step": 2750
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "grad_norm": 1.0879671573638916,
+      "learning_rate": 0.00010996585920988458,
+      "loss": 0.3637,
+      "step": 2800
+    },
+    {
+      "epoch": 3.207306711979609,
+      "eval_loss": 0.6150493025779724,
+      "eval_runtime": 157.6799,
+      "eval_samples_per_second": 9.951,
+      "eval_steps_per_second": 2.492,
+      "step": 2832
+    },
+    {
+      "epoch": 3.227697536108751,
+      "grad_norm": 1.1237863302230835,
+      "learning_rate": 0.00010834010729962609,
+      "loss": 0.4015,
+      "step": 2850
+    },
+    {
+      "epoch": 3.2843387142452563,
+      "grad_norm": 0.7940804958343506,
+      "learning_rate": 0.00010671435538936759,
+      "loss": 0.3572,
+      "step": 2900
+    },
+    {
+      "epoch": 3.3409798923817613,
+      "grad_norm": 1.7029999494552612,
+      "learning_rate": 0.0001050886034791091,
+      "loss": 0.3902,
+      "step": 2950
+    },
+    {
+      "epoch": 3.397621070518267,
+      "grad_norm": 0.8232925534248352,
+      "learning_rate": 0.00010346285156885061,
+      "loss": 0.3814,
+      "step": 3000
+    },
+    {
+      "epoch": 3.454262248654772,
+      "grad_norm": 0.9208984375,
+      "learning_rate": 0.0001018370996585921,
+      "loss": 0.377,
+      "step": 3050
+    },
+    {
+      "epoch": 3.5109034267912773,
+      "grad_norm": 1.1689094305038452,
+      "learning_rate": 0.00010021134774833361,
+      "loss": 0.3887,
+      "step": 3100
+    },
+    {
+      "epoch": 3.5675446049277824,
+      "grad_norm": 1.014140009880066,
+      "learning_rate": 9.858559583807512e-05,
+      "loss": 0.3842,
+      "step": 3150
+    },
+    {
+      "epoch": 3.6083262531860663,
+      "eval_loss": 0.6243398785591125,
+      "eval_runtime": 156.6849,
+      "eval_samples_per_second": 10.014,
+      "eval_steps_per_second": 2.508,
+      "step": 3186
+    },
+    {
+      "epoch": 3.624185783064288,
+      "grad_norm": 1.0292681455612183,
+      "learning_rate": 9.695984392781662e-05,
+      "loss": 0.3943,
+      "step": 3200
+    },
+    {
+      "epoch": 3.680826961200793,
+      "grad_norm": 1.2736083269119263,
+      "learning_rate": 9.533409201755813e-05,
+      "loss": 0.3999,
+      "step": 3250
+    },
+    {
+      "epoch": 3.7374681393372984,
+      "grad_norm": 1.344642162322998,
+      "learning_rate": 9.370834010729963e-05,
+      "loss": 0.4082,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7941093174738034,
+      "grad_norm": 1.2667014598846436,
+      "learning_rate": 9.208258819704113e-05,
+      "loss": 0.4103,
+      "step": 3350
+    },
+    {
+      "epoch": 3.850750495610309,
+      "grad_norm": 0.8207750916481018,
+      "learning_rate": 9.045683628678264e-05,
+      "loss": 0.3772,
+      "step": 3400
+    },
+    {
+      "epoch": 3.907391673746814,
+      "grad_norm": 1.0670604705810547,
+      "learning_rate": 8.883108437652414e-05,
+      "loss": 0.3937,
+      "step": 3450
+    },
+    {
+      "epoch": 3.964032851883319,
+      "grad_norm": 1.0088903903961182,
+      "learning_rate": 8.720533246626565e-05,
+      "loss": 0.3802,
+      "step": 3500
+    },
+    {
+      "epoch": 4.009062588501841,
+      "eval_loss": 0.6412317156791687,
+      "eval_runtime": 156.2398,
+      "eval_samples_per_second": 10.042,
+      "eval_steps_per_second": 2.515,
+      "step": 3540
+    },
+    {
+      "epoch": 4.020390824129142,
+      "grad_norm": 1.1471121311187744,
+      "learning_rate": 8.557958055600716e-05,
+      "loss": 0.3746,
+      "step": 3550
+    },
+    {
+      "epoch": 4.077032002265647,
+      "grad_norm": 0.8562577366828918,
+      "learning_rate": 8.395382864574867e-05,
+      "loss": 0.2778,
+      "step": 3600
+    },
+    {
+      "epoch": 4.133673180402153,
+      "grad_norm": 1.1746776103973389,
+      "learning_rate": 8.232807673549017e-05,
+      "loss": 0.326,
+      "step": 3650
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6181,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 1.2298081541578445e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4400/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-4400/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-4400/added_tokens.json

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

checkpoint-4400/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-4400/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-4400/trainer_state.json

@@ -0,0 +1,746 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.983290852449731,
+  "eval_steps": 354,
+  "global_step": 4400,
+  "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
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 0.9896508455276489,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.4895,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.150964617729187,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.5164,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 0.8384917378425598,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.4914,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 0.9231545329093933,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.4939,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0045312942509206,
+      "eval_loss": 0.5844214558601379,
+      "eval_runtime": 166.1298,
+      "eval_samples_per_second": 9.444,
+      "eval_steps_per_second": 2.366,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 0.9673134088516235,
+      "learning_rate": 0.00014248089741505446,
+      "loss": 0.4303,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.33237624168396,
+      "learning_rate": 0.00014085514550479596,
+      "loss": 0.4594,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.068943738937378,
+      "learning_rate": 0.0001392293935945375,
+      "loss": 0.4939,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.1625093221664429,
+      "learning_rate": 0.00013760364168427899,
+      "loss": 0.4757,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.080735683441162,
+      "learning_rate": 0.00013597788977402048,
+      "loss": 0.4724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 0.8823259472846985,
+      "learning_rate": 0.00013435213786376198,
+      "loss": 0.4821,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.0513312816619873,
+      "learning_rate": 0.0001327263859535035,
+      "loss": 0.479,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4055508354573774,
+      "eval_loss": 0.6049736738204956,
+      "eval_runtime": 156.3245,
+      "eval_samples_per_second": 10.037,
+      "eval_steps_per_second": 2.514,
+      "step": 2124
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.0902981758117676,
+      "learning_rate": 0.000131100634043245,
+      "loss": 0.4749,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 0.9050194025039673,
+      "learning_rate": 0.0001294748821329865,
+      "loss": 0.4346,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.0356699228286743,
+      "learning_rate": 0.00012784913022272803,
+      "loss": 0.4685,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.0071344375610352,
+      "learning_rate": 0.00012622337831246953,
+      "loss": 0.5,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6615689606343813,
+      "grad_norm": 1.0409235954284668,
+      "learning_rate": 0.00012459762640221103,
+      "loss": 0.4908,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "grad_norm": 0.8756324052810669,
+      "learning_rate": 0.00012297187449195252,
+      "loss": 0.4765,
+      "step": 2400
+    },
+    {
+      "epoch": 2.774851316907392,
+      "grad_norm": 0.6662527918815613,
+      "learning_rate": 0.00012134612258169405,
+      "loss": 0.4524,
+      "step": 2450
+    },
+    {
+      "epoch": 2.8065703766638346,
+      "eval_loss": 0.5904644727706909,
+      "eval_runtime": 157.1505,
+      "eval_samples_per_second": 9.984,
+      "eval_steps_per_second": 2.501,
+      "step": 2478
+    },
+    {
+      "epoch": 2.831492495043897,
+      "grad_norm": 1.0368993282318115,
+      "learning_rate": 0.00011972037067143556,
+      "loss": 0.4661,
+      "step": 2500
+    },
+    {
+      "epoch": 2.888133673180402,
+      "grad_norm": 1.0678080320358276,
+      "learning_rate": 0.00011809461876117705,
+      "loss": 0.4812,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "grad_norm": 1.2212059497833252,
+      "learning_rate": 0.00011646886685091856,
+      "loss": 0.482,
+      "step": 2600
+    },
+    {
+      "epoch": 3.00113282356273,
+      "grad_norm": 0.757663369178772,
+      "learning_rate": 0.00011484311494066007,
+      "loss": 0.5062,
+      "step": 2650
+    },
+    {
+      "epoch": 3.057774001699235,
+      "grad_norm": 0.8512151837348938,
+      "learning_rate": 0.00011321736303040155,
+      "loss": 0.3651,
+      "step": 2700
+    },
+    {
+      "epoch": 3.1144151798357407,
+      "grad_norm": 0.9610685706138611,
+      "learning_rate": 0.00011159161112014307,
+      "loss": 0.3626,
+      "step": 2750
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "grad_norm": 1.0879671573638916,
+      "learning_rate": 0.00010996585920988458,
+      "loss": 0.3637,
+      "step": 2800
+    },
+    {
+      "epoch": 3.207306711979609,
+      "eval_loss": 0.6150493025779724,
+      "eval_runtime": 157.6799,
+      "eval_samples_per_second": 9.951,
+      "eval_steps_per_second": 2.492,
+      "step": 2832
+    },
+    {
+      "epoch": 3.227697536108751,
+      "grad_norm": 1.1237863302230835,
+      "learning_rate": 0.00010834010729962609,
+      "loss": 0.4015,
+      "step": 2850
+    },
+    {
+      "epoch": 3.2843387142452563,
+      "grad_norm": 0.7940804958343506,
+      "learning_rate": 0.00010671435538936759,
+      "loss": 0.3572,
+      "step": 2900
+    },
+    {
+      "epoch": 3.3409798923817613,
+      "grad_norm": 1.7029999494552612,
+      "learning_rate": 0.0001050886034791091,
+      "loss": 0.3902,
+      "step": 2950
+    },
+    {
+      "epoch": 3.397621070518267,
+      "grad_norm": 0.8232925534248352,
+      "learning_rate": 0.00010346285156885061,
+      "loss": 0.3814,
+      "step": 3000
+    },
+    {
+      "epoch": 3.454262248654772,
+      "grad_norm": 0.9208984375,
+      "learning_rate": 0.0001018370996585921,
+      "loss": 0.377,
+      "step": 3050
+    },
+    {
+      "epoch": 3.5109034267912773,
+      "grad_norm": 1.1689094305038452,
+      "learning_rate": 0.00010021134774833361,
+      "loss": 0.3887,
+      "step": 3100
+    },
+    {
+      "epoch": 3.5675446049277824,
+      "grad_norm": 1.014140009880066,
+      "learning_rate": 9.858559583807512e-05,
+      "loss": 0.3842,
+      "step": 3150
+    },
+    {
+      "epoch": 3.6083262531860663,
+      "eval_loss": 0.6243398785591125,
+      "eval_runtime": 156.6849,
+      "eval_samples_per_second": 10.014,
+      "eval_steps_per_second": 2.508,
+      "step": 3186
+    },
+    {
+      "epoch": 3.624185783064288,
+      "grad_norm": 1.0292681455612183,
+      "learning_rate": 9.695984392781662e-05,
+      "loss": 0.3943,
+      "step": 3200
+    },
+    {
+      "epoch": 3.680826961200793,
+      "grad_norm": 1.2736083269119263,
+      "learning_rate": 9.533409201755813e-05,
+      "loss": 0.3999,
+      "step": 3250
+    },
+    {
+      "epoch": 3.7374681393372984,
+      "grad_norm": 1.344642162322998,
+      "learning_rate": 9.370834010729963e-05,
+      "loss": 0.4082,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7941093174738034,
+      "grad_norm": 1.2667014598846436,
+      "learning_rate": 9.208258819704113e-05,
+      "loss": 0.4103,
+      "step": 3350
+    },
+    {
+      "epoch": 3.850750495610309,
+      "grad_norm": 0.8207750916481018,
+      "learning_rate": 9.045683628678264e-05,
+      "loss": 0.3772,
+      "step": 3400
+    },
+    {
+      "epoch": 3.907391673746814,
+      "grad_norm": 1.0670604705810547,
+      "learning_rate": 8.883108437652414e-05,
+      "loss": 0.3937,
+      "step": 3450
+    },
+    {
+      "epoch": 3.964032851883319,
+      "grad_norm": 1.0088903903961182,
+      "learning_rate": 8.720533246626565e-05,
+      "loss": 0.3802,
+      "step": 3500
+    },
+    {
+      "epoch": 4.009062588501841,
+      "eval_loss": 0.6412317156791687,
+      "eval_runtime": 156.2398,
+      "eval_samples_per_second": 10.042,
+      "eval_steps_per_second": 2.515,
+      "step": 3540
+    },
+    {
+      "epoch": 4.020390824129142,
+      "grad_norm": 1.1471121311187744,
+      "learning_rate": 8.557958055600716e-05,
+      "loss": 0.3746,
+      "step": 3550
+    },
+    {
+      "epoch": 4.077032002265647,
+      "grad_norm": 0.8562577366828918,
+      "learning_rate": 8.395382864574867e-05,
+      "loss": 0.2778,
+      "step": 3600
+    },
+    {
+      "epoch": 4.133673180402153,
+      "grad_norm": 1.1746776103973389,
+      "learning_rate": 8.232807673549017e-05,
+      "loss": 0.326,
+      "step": 3650
+    },
+    {
+      "epoch": 4.190314358538657,
+      "grad_norm": 0.9672653675079346,
+      "learning_rate": 8.070232482523168e-05,
+      "loss": 0.2942,
+      "step": 3700
+    },
+    {
+      "epoch": 4.246955536675163,
+      "grad_norm": 1.1328763961791992,
+      "learning_rate": 7.907657291497318e-05,
+      "loss": 0.284,
+      "step": 3750
+    },
+    {
+      "epoch": 4.303596714811668,
+      "grad_norm": 1.1571893692016602,
+      "learning_rate": 7.745082100471468e-05,
+      "loss": 0.2909,
+      "step": 3800
+    },
+    {
+      "epoch": 4.360237892948174,
+      "grad_norm": 1.2159768342971802,
+      "learning_rate": 7.582506909445619e-05,
+      "loss": 0.2968,
+      "step": 3850
+    },
+    {
+      "epoch": 4.410082129708298,
+      "eval_loss": 0.6717728972434998,
+      "eval_runtime": 157.5885,
+      "eval_samples_per_second": 9.956,
+      "eval_steps_per_second": 2.494,
+      "step": 3894
+    },
+    {
+      "epoch": 4.416879071084678,
+      "grad_norm": 1.5386378765106201,
+      "learning_rate": 7.419931718419769e-05,
+      "loss": 0.3411,
+      "step": 3900
+    },
+    {
+      "epoch": 4.473520249221184,
+      "grad_norm": 0.8602418899536133,
+      "learning_rate": 7.25735652739392e-05,
+      "loss": 0.2978,
+      "step": 3950
+    },
+    {
+      "epoch": 4.530161427357689,
+      "grad_norm": 1.1013133525848389,
+      "learning_rate": 7.09478133636807e-05,
+      "loss": 0.3159,
+      "step": 4000
+    },
+    {
+      "epoch": 4.586802605494194,
+      "grad_norm": 1.4029144048690796,
+      "learning_rate": 6.932206145342221e-05,
+      "loss": 0.2968,
+      "step": 4050
+    },
+    {
+      "epoch": 4.643443783630699,
+      "grad_norm": 1.5415537357330322,
+      "learning_rate": 6.769630954316372e-05,
+      "loss": 0.3035,
+      "step": 4100
+    },
+    {
+      "epoch": 4.700084961767205,
+      "grad_norm": 1.136186957359314,
+      "learning_rate": 6.607055763290522e-05,
+      "loss": 0.2937,
+      "step": 4150
+    },
+    {
+      "epoch": 4.75672613990371,
+      "grad_norm": 1.255430817604065,
+      "learning_rate": 6.444480572264673e-05,
+      "loss": 0.3143,
+      "step": 4200
+    },
+    {
+      "epoch": 4.811101670914755,
+      "eval_loss": 0.663857102394104,
+      "eval_runtime": 156.8952,
+      "eval_samples_per_second": 10.0,
+      "eval_steps_per_second": 2.505,
+      "step": 4248
+    },
+    {
+      "epoch": 4.813367318040215,
+      "grad_norm": 1.861267328262329,
+      "learning_rate": 6.281905381238823e-05,
+      "loss": 0.3015,
+      "step": 4250
+    },
+    {
+      "epoch": 4.8700084961767205,
+      "grad_norm": 1.413987636566162,
+      "learning_rate": 6.119330190212974e-05,
+      "loss": 0.2981,
+      "step": 4300
+    },
+    {
+      "epoch": 4.926649674313226,
+      "grad_norm": 1.5306217670440674,
+      "learning_rate": 5.956754999187124e-05,
+      "loss": 0.3035,
+      "step": 4350
+    },
+    {
+      "epoch": 4.983290852449731,
+      "grad_norm": 0.8410525918006897,
+      "learning_rate": 5.794179808161275e-05,
+      "loss": 0.2922,
+      "step": 4400
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6181,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 1.4817105399965184e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5100/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-5100/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-5100/added_tokens.json

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

checkpoint-5100/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-5100/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-5100/trainer_state.json

@@ -0,0 +1,860 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.775984140470122,
+  "eval_steps": 354,
+  "global_step": 5100,
+  "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
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 0.9896508455276489,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.4895,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.150964617729187,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.5164,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 0.8384917378425598,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.4914,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 0.9231545329093933,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.4939,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0045312942509206,
+      "eval_loss": 0.5844214558601379,
+      "eval_runtime": 166.1298,
+      "eval_samples_per_second": 9.444,
+      "eval_steps_per_second": 2.366,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 0.9673134088516235,
+      "learning_rate": 0.00014248089741505446,
+      "loss": 0.4303,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.33237624168396,
+      "learning_rate": 0.00014085514550479596,
+      "loss": 0.4594,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.068943738937378,
+      "learning_rate": 0.0001392293935945375,
+      "loss": 0.4939,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.1625093221664429,
+      "learning_rate": 0.00013760364168427899,
+      "loss": 0.4757,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.080735683441162,
+      "learning_rate": 0.00013597788977402048,
+      "loss": 0.4724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 0.8823259472846985,
+      "learning_rate": 0.00013435213786376198,
+      "loss": 0.4821,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.0513312816619873,
+      "learning_rate": 0.0001327263859535035,
+      "loss": 0.479,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4055508354573774,
+      "eval_loss": 0.6049736738204956,
+      "eval_runtime": 156.3245,
+      "eval_samples_per_second": 10.037,
+      "eval_steps_per_second": 2.514,
+      "step": 2124
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.0902981758117676,
+      "learning_rate": 0.000131100634043245,
+      "loss": 0.4749,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 0.9050194025039673,
+      "learning_rate": 0.0001294748821329865,
+      "loss": 0.4346,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.0356699228286743,
+      "learning_rate": 0.00012784913022272803,
+      "loss": 0.4685,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.0071344375610352,
+      "learning_rate": 0.00012622337831246953,
+      "loss": 0.5,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6615689606343813,
+      "grad_norm": 1.0409235954284668,
+      "learning_rate": 0.00012459762640221103,
+      "loss": 0.4908,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "grad_norm": 0.8756324052810669,
+      "learning_rate": 0.00012297187449195252,
+      "loss": 0.4765,
+      "step": 2400
+    },
+    {
+      "epoch": 2.774851316907392,
+      "grad_norm": 0.6662527918815613,
+      "learning_rate": 0.00012134612258169405,
+      "loss": 0.4524,
+      "step": 2450
+    },
+    {
+      "epoch": 2.8065703766638346,
+      "eval_loss": 0.5904644727706909,
+      "eval_runtime": 157.1505,
+      "eval_samples_per_second": 9.984,
+      "eval_steps_per_second": 2.501,
+      "step": 2478
+    },
+    {
+      "epoch": 2.831492495043897,
+      "grad_norm": 1.0368993282318115,
+      "learning_rate": 0.00011972037067143556,
+      "loss": 0.4661,
+      "step": 2500
+    },
+    {
+      "epoch": 2.888133673180402,
+      "grad_norm": 1.0678080320358276,
+      "learning_rate": 0.00011809461876117705,
+      "loss": 0.4812,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "grad_norm": 1.2212059497833252,
+      "learning_rate": 0.00011646886685091856,
+      "loss": 0.482,
+      "step": 2600
+    },
+    {
+      "epoch": 3.00113282356273,
+      "grad_norm": 0.757663369178772,
+      "learning_rate": 0.00011484311494066007,
+      "loss": 0.5062,
+      "step": 2650
+    },
+    {
+      "epoch": 3.057774001699235,
+      "grad_norm": 0.8512151837348938,
+      "learning_rate": 0.00011321736303040155,
+      "loss": 0.3651,
+      "step": 2700
+    },
+    {
+      "epoch": 3.1144151798357407,
+      "grad_norm": 0.9610685706138611,
+      "learning_rate": 0.00011159161112014307,
+      "loss": 0.3626,
+      "step": 2750
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "grad_norm": 1.0879671573638916,
+      "learning_rate": 0.00010996585920988458,
+      "loss": 0.3637,
+      "step": 2800
+    },
+    {
+      "epoch": 3.207306711979609,
+      "eval_loss": 0.6150493025779724,
+      "eval_runtime": 157.6799,
+      "eval_samples_per_second": 9.951,
+      "eval_steps_per_second": 2.492,
+      "step": 2832
+    },
+    {
+      "epoch": 3.227697536108751,
+      "grad_norm": 1.1237863302230835,
+      "learning_rate": 0.00010834010729962609,
+      "loss": 0.4015,
+      "step": 2850
+    },
+    {
+      "epoch": 3.2843387142452563,
+      "grad_norm": 0.7940804958343506,
+      "learning_rate": 0.00010671435538936759,
+      "loss": 0.3572,
+      "step": 2900
+    },
+    {
+      "epoch": 3.3409798923817613,
+      "grad_norm": 1.7029999494552612,
+      "learning_rate": 0.0001050886034791091,
+      "loss": 0.3902,
+      "step": 2950
+    },
+    {
+      "epoch": 3.397621070518267,
+      "grad_norm": 0.8232925534248352,
+      "learning_rate": 0.00010346285156885061,
+      "loss": 0.3814,
+      "step": 3000
+    },
+    {
+      "epoch": 3.454262248654772,
+      "grad_norm": 0.9208984375,
+      "learning_rate": 0.0001018370996585921,
+      "loss": 0.377,
+      "step": 3050
+    },
+    {
+      "epoch": 3.5109034267912773,
+      "grad_norm": 1.1689094305038452,
+      "learning_rate": 0.00010021134774833361,
+      "loss": 0.3887,
+      "step": 3100
+    },
+    {
+      "epoch": 3.5675446049277824,
+      "grad_norm": 1.014140009880066,
+      "learning_rate": 9.858559583807512e-05,
+      "loss": 0.3842,
+      "step": 3150
+    },
+    {
+      "epoch": 3.6083262531860663,
+      "eval_loss": 0.6243398785591125,
+      "eval_runtime": 156.6849,
+      "eval_samples_per_second": 10.014,
+      "eval_steps_per_second": 2.508,
+      "step": 3186
+    },
+    {
+      "epoch": 3.624185783064288,
+      "grad_norm": 1.0292681455612183,
+      "learning_rate": 9.695984392781662e-05,
+      "loss": 0.3943,
+      "step": 3200
+    },
+    {
+      "epoch": 3.680826961200793,
+      "grad_norm": 1.2736083269119263,
+      "learning_rate": 9.533409201755813e-05,
+      "loss": 0.3999,
+      "step": 3250
+    },
+    {
+      "epoch": 3.7374681393372984,
+      "grad_norm": 1.344642162322998,
+      "learning_rate": 9.370834010729963e-05,
+      "loss": 0.4082,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7941093174738034,
+      "grad_norm": 1.2667014598846436,
+      "learning_rate": 9.208258819704113e-05,
+      "loss": 0.4103,
+      "step": 3350
+    },
+    {
+      "epoch": 3.850750495610309,
+      "grad_norm": 0.8207750916481018,
+      "learning_rate": 9.045683628678264e-05,
+      "loss": 0.3772,
+      "step": 3400
+    },
+    {
+      "epoch": 3.907391673746814,
+      "grad_norm": 1.0670604705810547,
+      "learning_rate": 8.883108437652414e-05,
+      "loss": 0.3937,
+      "step": 3450
+    },
+    {
+      "epoch": 3.964032851883319,
+      "grad_norm": 1.0088903903961182,
+      "learning_rate": 8.720533246626565e-05,
+      "loss": 0.3802,
+      "step": 3500
+    },
+    {
+      "epoch": 4.009062588501841,
+      "eval_loss": 0.6412317156791687,
+      "eval_runtime": 156.2398,
+      "eval_samples_per_second": 10.042,
+      "eval_steps_per_second": 2.515,
+      "step": 3540
+    },
+    {
+      "epoch": 4.020390824129142,
+      "grad_norm": 1.1471121311187744,
+      "learning_rate": 8.557958055600716e-05,
+      "loss": 0.3746,
+      "step": 3550
+    },
+    {
+      "epoch": 4.077032002265647,
+      "grad_norm": 0.8562577366828918,
+      "learning_rate": 8.395382864574867e-05,
+      "loss": 0.2778,
+      "step": 3600
+    },
+    {
+      "epoch": 4.133673180402153,
+      "grad_norm": 1.1746776103973389,
+      "learning_rate": 8.232807673549017e-05,
+      "loss": 0.326,
+      "step": 3650
+    },
+    {
+      "epoch": 4.190314358538657,
+      "grad_norm": 0.9672653675079346,
+      "learning_rate": 8.070232482523168e-05,
+      "loss": 0.2942,
+      "step": 3700
+    },
+    {
+      "epoch": 4.246955536675163,
+      "grad_norm": 1.1328763961791992,
+      "learning_rate": 7.907657291497318e-05,
+      "loss": 0.284,
+      "step": 3750
+    },
+    {
+      "epoch": 4.303596714811668,
+      "grad_norm": 1.1571893692016602,
+      "learning_rate": 7.745082100471468e-05,
+      "loss": 0.2909,
+      "step": 3800
+    },
+    {
+      "epoch": 4.360237892948174,
+      "grad_norm": 1.2159768342971802,
+      "learning_rate": 7.582506909445619e-05,
+      "loss": 0.2968,
+      "step": 3850
+    },
+    {
+      "epoch": 4.410082129708298,
+      "eval_loss": 0.6717728972434998,
+      "eval_runtime": 157.5885,
+      "eval_samples_per_second": 9.956,
+      "eval_steps_per_second": 2.494,
+      "step": 3894
+    },
+    {
+      "epoch": 4.416879071084678,
+      "grad_norm": 1.5386378765106201,
+      "learning_rate": 7.419931718419769e-05,
+      "loss": 0.3411,
+      "step": 3900
+    },
+    {
+      "epoch": 4.473520249221184,
+      "grad_norm": 0.8602418899536133,
+      "learning_rate": 7.25735652739392e-05,
+      "loss": 0.2978,
+      "step": 3950
+    },
+    {
+      "epoch": 4.530161427357689,
+      "grad_norm": 1.1013133525848389,
+      "learning_rate": 7.09478133636807e-05,
+      "loss": 0.3159,
+      "step": 4000
+    },
+    {
+      "epoch": 4.586802605494194,
+      "grad_norm": 1.4029144048690796,
+      "learning_rate": 6.932206145342221e-05,
+      "loss": 0.2968,
+      "step": 4050
+    },
+    {
+      "epoch": 4.643443783630699,
+      "grad_norm": 1.5415537357330322,
+      "learning_rate": 6.769630954316372e-05,
+      "loss": 0.3035,
+      "step": 4100
+    },
+    {
+      "epoch": 4.700084961767205,
+      "grad_norm": 1.136186957359314,
+      "learning_rate": 6.607055763290522e-05,
+      "loss": 0.2937,
+      "step": 4150
+    },
+    {
+      "epoch": 4.75672613990371,
+      "grad_norm": 1.255430817604065,
+      "learning_rate": 6.444480572264673e-05,
+      "loss": 0.3143,
+      "step": 4200
+    },
+    {
+      "epoch": 4.811101670914755,
+      "eval_loss": 0.663857102394104,
+      "eval_runtime": 156.8952,
+      "eval_samples_per_second": 10.0,
+      "eval_steps_per_second": 2.505,
+      "step": 4248
+    },
+    {
+      "epoch": 4.813367318040215,
+      "grad_norm": 1.861267328262329,
+      "learning_rate": 6.281905381238823e-05,
+      "loss": 0.3015,
+      "step": 4250
+    },
+    {
+      "epoch": 4.8700084961767205,
+      "grad_norm": 1.413987636566162,
+      "learning_rate": 6.119330190212974e-05,
+      "loss": 0.2981,
+      "step": 4300
+    },
+    {
+      "epoch": 4.926649674313226,
+      "grad_norm": 1.5306217670440674,
+      "learning_rate": 5.956754999187124e-05,
+      "loss": 0.3035,
+      "step": 4350
+    },
+    {
+      "epoch": 4.983290852449731,
+      "grad_norm": 0.8410525918006897,
+      "learning_rate": 5.794179808161275e-05,
+      "loss": 0.2922,
+      "step": 4400
+    },
+    {
+      "epoch": 5.039648824695553,
+      "grad_norm": 0.9183124899864197,
+      "learning_rate": 5.631604617135425e-05,
+      "loss": 0.2512,
+      "step": 4450
+    },
+    {
+      "epoch": 5.096290002832059,
+      "grad_norm": 1.317425012588501,
+      "learning_rate": 5.469029426109576e-05,
+      "loss": 0.2263,
+      "step": 4500
+    },
+    {
+      "epoch": 5.152931180968564,
+      "grad_norm": 0.9315819144248962,
+      "learning_rate": 5.306454235083727e-05,
+      "loss": 0.2228,
+      "step": 4550
+    },
+    {
+      "epoch": 5.20957235910507,
+      "grad_norm": 1.3793691396713257,
+      "learning_rate": 5.1438790440578765e-05,
+      "loss": 0.215,
+      "step": 4600
+    },
+    {
+      "epoch": 5.211838006230529,
+      "eval_loss": 0.7431890964508057,
+      "eval_runtime": 156.3917,
+      "eval_samples_per_second": 10.033,
+      "eval_steps_per_second": 2.513,
+      "step": 4602
+    },
+    {
+      "epoch": 5.266213537241574,
+      "grad_norm": 1.0755746364593506,
+      "learning_rate": 4.981303853032028e-05,
+      "loss": 0.2209,
+      "step": 4650
+    },
+    {
+      "epoch": 5.32285471537808,
+      "grad_norm": 0.9018359780311584,
+      "learning_rate": 4.818728662006178e-05,
+      "loss": 0.2229,
+      "step": 4700
+    },
+    {
+      "epoch": 5.379495893514585,
+      "grad_norm": 1.2067404985427856,
+      "learning_rate": 4.656153470980329e-05,
+      "loss": 0.2333,
+      "step": 4750
+    },
+    {
+      "epoch": 5.43613707165109,
+      "grad_norm": 1.4685208797454834,
+      "learning_rate": 4.493578279954479e-05,
+      "loss": 0.2187,
+      "step": 4800
+    },
+    {
+      "epoch": 5.492778249787595,
+      "grad_norm": 1.2736314535140991,
+      "learning_rate": 4.33100308892863e-05,
+      "loss": 0.2374,
+      "step": 4850
+    },
+    {
+      "epoch": 5.549419427924101,
+      "grad_norm": 1.1849429607391357,
+      "learning_rate": 4.16842789790278e-05,
+      "loss": 0.2155,
+      "step": 4900
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 1.4427177906036377,
+      "learning_rate": 4.005852706876931e-05,
+      "loss": 0.246,
+      "step": 4950
+    },
+    {
+      "epoch": 5.612857547436986,
+      "eval_loss": 0.7509253025054932,
+      "eval_runtime": 156.7527,
+      "eval_samples_per_second": 10.009,
+      "eval_steps_per_second": 2.507,
+      "step": 4956
+    },
+    {
+      "epoch": 5.662701784197111,
+      "grad_norm": 1.3218597173690796,
+      "learning_rate": 3.843277515851081e-05,
+      "loss": 0.2258,
+      "step": 5000
+    },
+    {
+      "epoch": 5.7193429623336165,
+      "grad_norm": 1.1751331090927124,
+      "learning_rate": 3.680702324825232e-05,
+      "loss": 0.2374,
+      "step": 5050
+    },
+    {
+      "epoch": 5.775984140470122,
+      "grad_norm": 1.555324912071228,
+      "learning_rate": 3.518127133799383e-05,
+      "loss": 0.2111,
+      "step": 5100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6181,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 1.7180052929396813e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5200/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-5200/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-5200/added_tokens.json

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

checkpoint-5200/chat_template.jinja

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

checkpoint-5200/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
+  }
+}