Pushing tokenizer and

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-558/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,207 @@
+---
+base_model: google/gemma-3-270m
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-270m
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-270m",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9003ad8f05e04f56551741bc89b66e12dd0252d9160a34f5cd63458205d8e7
+size 30409120

added_tokens.json

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

checkpoint-400/README.md

@@ -0,0 +1,207 @@
+---
+base_model: google/gemma-3-270m
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-270m
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-400/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-270m",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7bba4d0601b5df8882e91b10ebf7f85d5b3d600a3e29c4af0f420f3c577997
+size 30409120

checkpoint-400/added_tokens.json

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

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f13c73f5add5ef4a9519209d324ab0251ed89096a4dc2a5fd486d1e853b1a1
+size 60967499

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb39cf4f06e607e87bd5dbf08c109bf1bbe81aafae94197ed8d9c3448d32488
+size 14645

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1097ffe58364125df1c4167fb990000d6808cf64e46ce32dbd2fb99038bcd02f
+size 1465

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "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": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2f60fd56eabb86ada6d0ef7c30d1ce71e1ed22af2d19e5238a9f0a5cdfa23c
+size 33384666

checkpoint-400/tokenizer.model

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

checkpoint-400/trainer_state.json

@@ -0,0 +1,215 @@
+{
+  "best_global_step": 400,
+  "best_metric": 1.4167424440383911,
+  "best_model_checkpoint": "./gemma3_finetune/checkpoint-400",
+  "epoch": 2.1508417508417508,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10774410774410774,
+      "grad_norm": 1.6064836978912354,
+      "learning_rate": 1.6964285714285715e-05,
+      "loss": 2.1903,
+      "step": 20
+    },
+    {
+      "epoch": 0.21548821548821548,
+      "grad_norm": 0.9092773199081421,
+      "learning_rate": 3.4821428571428574e-05,
+      "loss": 1.8574,
+      "step": 40
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.7761135101318359,
+      "learning_rate": 4.999559412596081e-05,
+      "loss": 1.6196,
+      "step": 60
+    },
+    {
+      "epoch": 0.43097643097643096,
+      "grad_norm": 0.6488329768180847,
+      "learning_rate": 4.974147171991723e-05,
+      "loss": 1.5175,
+      "step": 80
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.6469504237174988,
+      "learning_rate": 4.910026034587031e-05,
+      "loss": 1.4836,
+      "step": 100
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "eval_loss": 1.5036908388137817,
+      "eval_runtime": 14.2727,
+      "eval_samples_per_second": 87.65,
+      "eval_steps_per_second": 11.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.7555330395698547,
+      "learning_rate": 4.808199197976157e-05,
+      "loss": 1.4586,
+      "step": 120
+    },
+    {
+      "epoch": 0.7542087542087542,
+      "grad_norm": 0.7224211096763611,
+      "learning_rate": 4.670259778589074e-05,
+      "loss": 1.4615,
+      "step": 140
+    },
+    {
+      "epoch": 0.8619528619528619,
+      "grad_norm": 0.7545987963676453,
+      "learning_rate": 4.498365886828511e-05,
+      "loss": 1.4429,
+      "step": 160
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.6888415217399597,
+      "learning_rate": 4.295206862678802e-05,
+      "loss": 1.4457,
+      "step": 180
+    },
+    {
+      "epoch": 1.0754208754208754,
+      "grad_norm": 0.7888140678405762,
+      "learning_rate": 4.063961200042368e-05,
+      "loss": 1.4164,
+      "step": 200
+    },
+    {
+      "epoch": 1.0754208754208754,
+      "eval_loss": 1.450657606124878,
+      "eval_runtime": 14.314,
+      "eval_samples_per_second": 87.397,
+      "eval_steps_per_second": 10.968,
+      "step": 200
+    },
+    {
+      "epoch": 1.183164983164983,
+      "grad_norm": 0.7697953581809998,
+      "learning_rate": 3.8082468180922686e-05,
+      "loss": 1.4052,
+      "step": 220
+    },
+    {
+      "epoch": 1.290909090909091,
+      "grad_norm": 0.7794164419174194,
+      "learning_rate": 3.532064457662889e-05,
+      "loss": 1.4016,
+      "step": 240
+    },
+    {
+      "epoch": 1.3986531986531987,
+      "grad_norm": 0.7602345943450928,
+      "learning_rate": 3.239735088262007e-05,
+      "loss": 1.3902,
+      "step": 260
+    },
+    {
+      "epoch": 1.5063973063973064,
+      "grad_norm": 0.7201767563819885,
+      "learning_rate": 2.935832304993402e-05,
+      "loss": 1.3978,
+      "step": 280
+    },
+    {
+      "epoch": 1.614141414141414,
+      "grad_norm": 0.7935007214546204,
+      "learning_rate": 2.625110773063754e-05,
+      "loss": 1.3875,
+      "step": 300
+    },
+    {
+      "epoch": 1.614141414141414,
+      "eval_loss": 1.4275208711624146,
+      "eval_runtime": 14.2116,
+      "eval_samples_per_second": 88.027,
+      "eval_steps_per_second": 11.047,
+      "step": 300
+    },
+    {
+      "epoch": 1.7218855218855218,
+      "grad_norm": 0.746303379535675,
+      "learning_rate": 2.312431839384543e-05,
+      "loss": 1.393,
+      "step": 320
+    },
+    {
+      "epoch": 1.8296296296296295,
+      "grad_norm": 0.7554110884666443,
+      "learning_rate": 2.0026874751013972e-05,
+      "loss": 1.3853,
+      "step": 340
+    },
+    {
+      "epoch": 1.9373737373737374,
+      "grad_norm": 0.735357403755188,
+      "learning_rate": 1.7007237389966146e-05,
+      "loss": 1.3835,
+      "step": 360
+    },
+    {
+      "epoch": 2.043097643097643,
+      "grad_norm": 0.7572635412216187,
+      "learning_rate": 1.4112649592066293e-05,
+      "loss": 1.369,
+      "step": 380
+    },
+    {
+      "epoch": 2.1508417508417508,
+      "grad_norm": 0.7531948685646057,
+      "learning_rate": 1.1388398194579725e-05,
+      "loss": 1.3724,
+      "step": 400
+    },
+    {
+      "epoch": 2.1508417508417508,
+      "eval_loss": 1.4167424440383911,
+      "eval_runtime": 14.2716,
+      "eval_samples_per_second": 87.657,
+      "eval_steps_per_second": 11.001,
+      "step": 400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 558,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8469271511040000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a75d9a8eeff9861f89e8dd597061104867a6fa7c8237f424ce50a54352f47e4
+size 5777

checkpoint-500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: google/gemma-3-270m
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-270m
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-270m",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9003ad8f05e04f56551741bc89b66e12dd0252d9160a34f5cd63458205d8e7
+size 30409120

checkpoint-500/added_tokens.json

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

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e08440503d3138c6ab068acbfc3d1d76604a7cebd98a163b0fbb6112a41f5d
+size 60967499

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f531cff762cbe6dae46573825bcadb8a8e973d038041659e84256a988afa0b
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aebd8209d6581043d839f7a8f654032441119fb7b1aa6ae28119232c15456031
+size 1465

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "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": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2f60fd56eabb86ada6d0ef7c30d1ce71e1ed22af2d19e5238a9f0a5cdfa23c
+size 33384666

checkpoint-500/tokenizer.model

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

checkpoint-500/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_global_step": 500,
+  "best_metric": 1.4127447605133057,
+  "best_model_checkpoint": "./gemma3_finetune/checkpoint-500",
+  "epoch": 2.6895622895622897,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10774410774410774,
+      "grad_norm": 1.6064836978912354,
+      "learning_rate": 1.6964285714285715e-05,
+      "loss": 2.1903,
+      "step": 20
+    },
+    {
+      "epoch": 0.21548821548821548,
+      "grad_norm": 0.9092773199081421,
+      "learning_rate": 3.4821428571428574e-05,
+      "loss": 1.8574,
+      "step": 40
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.7761135101318359,
+      "learning_rate": 4.999559412596081e-05,
+      "loss": 1.6196,
+      "step": 60
+    },
+    {
+      "epoch": 0.43097643097643096,
+      "grad_norm": 0.6488329768180847,
+      "learning_rate": 4.974147171991723e-05,
+      "loss": 1.5175,
+      "step": 80
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.6469504237174988,
+      "learning_rate": 4.910026034587031e-05,
+      "loss": 1.4836,
+      "step": 100
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "eval_loss": 1.5036908388137817,
+      "eval_runtime": 14.2727,
+      "eval_samples_per_second": 87.65,
+      "eval_steps_per_second": 11.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.7555330395698547,
+      "learning_rate": 4.808199197976157e-05,
+      "loss": 1.4586,
+      "step": 120
+    },
+    {
+      "epoch": 0.7542087542087542,
+      "grad_norm": 0.7224211096763611,
+      "learning_rate": 4.670259778589074e-05,
+      "loss": 1.4615,
+      "step": 140
+    },
+    {
+      "epoch": 0.8619528619528619,
+      "grad_norm": 0.7545987963676453,
+      "learning_rate": 4.498365886828511e-05,
+      "loss": 1.4429,
+      "step": 160
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.6888415217399597,
+      "learning_rate": 4.295206862678802e-05,
+      "loss": 1.4457,
+      "step": 180
+    },
+    {
+      "epoch": 1.0754208754208754,
+      "grad_norm": 0.7888140678405762,
+      "learning_rate": 4.063961200042368e-05,
+      "loss": 1.4164,
+      "step": 200
+    },
+    {
+      "epoch": 1.0754208754208754,
+      "eval_loss": 1.450657606124878,
+      "eval_runtime": 14.314,
+      "eval_samples_per_second": 87.397,
+      "eval_steps_per_second": 10.968,
+      "step": 200
+    },
+    {
+      "epoch": 1.183164983164983,
+      "grad_norm": 0.7697953581809998,
+      "learning_rate": 3.8082468180922686e-05,
+      "loss": 1.4052,
+      "step": 220
+    },
+    {
+      "epoch": 1.290909090909091,
+      "grad_norm": 0.7794164419174194,
+      "learning_rate": 3.532064457662889e-05,
+      "loss": 1.4016,
+      "step": 240
+    },
+    {
+      "epoch": 1.3986531986531987,
+      "grad_norm": 0.7602345943450928,
+      "learning_rate": 3.239735088262007e-05,
+      "loss": 1.3902,
+      "step": 260
+    },
+    {
+      "epoch": 1.5063973063973064,
+      "grad_norm": 0.7201767563819885,
+      "learning_rate": 2.935832304993402e-05,
+      "loss": 1.3978,
+      "step": 280
+    },
+    {
+      "epoch": 1.614141414141414,
+      "grad_norm": 0.7935007214546204,
+      "learning_rate": 2.625110773063754e-05,
+      "loss": 1.3875,
+      "step": 300
+    },
+    {
+      "epoch": 1.614141414141414,
+      "eval_loss": 1.4275208711624146,
+      "eval_runtime": 14.2116,
+      "eval_samples_per_second": 88.027,
+      "eval_steps_per_second": 11.047,
+      "step": 300
+    },
+    {
+      "epoch": 1.7218855218855218,
+      "grad_norm": 0.746303379535675,
+      "learning_rate": 2.312431839384543e-05,
+      "loss": 1.393,
+      "step": 320
+    },
+    {
+      "epoch": 1.8296296296296295,
+      "grad_norm": 0.7554110884666443,
+      "learning_rate": 2.0026874751013972e-05,
+      "loss": 1.3853,
+      "step": 340
+    },
+    {
+      "epoch": 1.9373737373737374,
+      "grad_norm": 0.735357403755188,
+      "learning_rate": 1.7007237389966146e-05,
+      "loss": 1.3835,
+      "step": 360
+    },
+    {
+      "epoch": 2.043097643097643,
+      "grad_norm": 0.7572635412216187,
+      "learning_rate": 1.4112649592066293e-05,
+      "loss": 1.369,
+      "step": 380
+    },
+    {
+      "epoch": 2.1508417508417508,
+      "grad_norm": 0.7531948685646057,
+      "learning_rate": 1.1388398194579725e-05,
+      "loss": 1.3724,
+      "step": 400
+    },
+    {
+      "epoch": 2.1508417508417508,
+      "eval_loss": 1.4167424440383911,
+      "eval_runtime": 14.2716,
+      "eval_samples_per_second": 87.657,
+      "eval_steps_per_second": 11.001,
+      "step": 400
+    },
+    {
+      "epoch": 2.2585858585858585,
+      "grad_norm": 0.7567663192749023,
+      "learning_rate": 8.877105062283609e-06,
+      "loss": 1.3674,
+      "step": 420
+    },
+    {
+      "epoch": 2.366329966329966,
+      "grad_norm": 0.7656159400939941,
+      "learning_rate": 6.618060253503472e-06,
+      "loss": 1.3686,
+      "step": 440
+    },
+    {
+      "epoch": 2.474074074074074,
+      "grad_norm": 0.7571391463279724,
+      "learning_rate": 4.646607313425419e-06,
+      "loss": 1.3617,
+      "step": 460
+    },
+    {
+      "epoch": 2.581818181818182,
+      "grad_norm": 0.7939226627349854,
+      "learning_rate": 2.9935903119851757e-06,
+      "loss": 1.3648,
+      "step": 480
+    },
+    {
+      "epoch": 2.6895622895622897,
+      "grad_norm": 0.7923122048377991,
+      "learning_rate": 1.6848712776191767e-06,
+      "loss": 1.3694,
+      "step": 500
+    },
+    {
+      "epoch": 2.6895622895622897,
+      "eval_loss": 1.4127447605133057,
+      "eval_runtime": 14.3897,
+      "eval_samples_per_second": 86.937,
+      "eval_steps_per_second": 10.911,
+      "step": 500
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 558,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.059106504704e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a75d9a8eeff9861f89e8dd597061104867a6fa7c8237f424ce50a54352f47e4
+size 5777

checkpoint-558/README.md

@@ -0,0 +1,207 @@
+---
+base_model: google/gemma-3-270m
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-270m
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-558/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-270m",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-558/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3b28f69193ed82f8c9de2356b5d569d0f39c6a3971f5dbe518e55242904181
+size 30409120

checkpoint-558/added_tokens.json

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

checkpoint-558/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa02cafa9a61d05d12ec7756ec101232c9e7ed2dc7ad9875df881698ab03eaf5
+size 60967499

checkpoint-558/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421a6785ed3d99cbcfb1e2be82f21c654e1dee7f25e55e84d628ac08bc0a8ecd
+size 14645

checkpoint-558/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b20569a1815184e9dfde701c2981d99a676bf34ccc3abdf2fbeeac9fd804056
+size 1465

checkpoint-558/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "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": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-558/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2f60fd56eabb86ada6d0ef7c30d1ce71e1ed22af2d19e5238a9f0a5cdfa23c
+size 33384666

checkpoint-558/tokenizer.model

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

checkpoint-558/trainer_state.json

@@ -0,0 +1,272 @@
+{
+  "best_global_step": 500,
+  "best_metric": 1.4127447605133057,
+  "best_model_checkpoint": "./gemma3_finetune/checkpoint-500",
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 558,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10774410774410774,
+      "grad_norm": 1.6064836978912354,
+      "learning_rate": 1.6964285714285715e-05,
+      "loss": 2.1903,
+      "step": 20
+    },
+    {
+      "epoch": 0.21548821548821548,
+      "grad_norm": 0.9092773199081421,
+      "learning_rate": 3.4821428571428574e-05,
+      "loss": 1.8574,
+      "step": 40
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.7761135101318359,
+      "learning_rate": 4.999559412596081e-05,
+      "loss": 1.6196,
+      "step": 60
+    },
+    {
+      "epoch": 0.43097643097643096,
+      "grad_norm": 0.6488329768180847,
+      "learning_rate": 4.974147171991723e-05,
+      "loss": 1.5175,
+      "step": 80
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.6469504237174988,
+      "learning_rate": 4.910026034587031e-05,
+      "loss": 1.4836,
+      "step": 100
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "eval_loss": 1.5036908388137817,
+      "eval_runtime": 14.2727,
+      "eval_samples_per_second": 87.65,
+      "eval_steps_per_second": 11.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.7555330395698547,
+      "learning_rate": 4.808199197976157e-05,
+      "loss": 1.4586,
+      "step": 120
+    },
+    {
+      "epoch": 0.7542087542087542,
+      "grad_norm": 0.7224211096763611,
+      "learning_rate": 4.670259778589074e-05,
+      "loss": 1.4615,
+      "step": 140
+    },
+    {
+      "epoch": 0.8619528619528619,
+      "grad_norm": 0.7545987963676453,
+      "learning_rate": 4.498365886828511e-05,
+      "loss": 1.4429,
+      "step": 160
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.6888415217399597,
+      "learning_rate": 4.295206862678802e-05,
+      "loss": 1.4457,
+      "step": 180
+    },
+    {
+      "epoch": 1.0754208754208754,
+      "grad_norm": 0.7888140678405762,
+      "learning_rate": 4.063961200042368e-05,
+      "loss": 1.4164,
+      "step": 200
+    },
+    {
+      "epoch": 1.0754208754208754,
+      "eval_loss": 1.450657606124878,
+      "eval_runtime": 14.314,
+      "eval_samples_per_second": 87.397,
+      "eval_steps_per_second": 10.968,
+      "step": 200
+    },
+    {
+      "epoch": 1.183164983164983,
+      "grad_norm": 0.7697953581809998,
+      "learning_rate": 3.8082468180922686e-05,
+      "loss": 1.4052,
+      "step": 220
+    },
+    {
+      "epoch": 1.290909090909091,
+      "grad_norm": 0.7794164419174194,
+      "learning_rate": 3.532064457662889e-05,
+      "loss": 1.4016,
+      "step": 240
+    },
+    {
+      "epoch": 1.3986531986531987,
+      "grad_norm": 0.7602345943450928,
+      "learning_rate": 3.239735088262007e-05,
+      "loss": 1.3902,
+      "step": 260
+    },
+    {
+      "epoch": 1.5063973063973064,
+      "grad_norm": 0.7201767563819885,
+      "learning_rate": 2.935832304993402e-05,
+      "loss": 1.3978,
+      "step": 280
+    },
+    {
+      "epoch": 1.614141414141414,
+      "grad_norm": 0.7935007214546204,
+      "learning_rate": 2.625110773063754e-05,
+      "loss": 1.3875,
+      "step": 300
+    },
+    {
+      "epoch": 1.614141414141414,
+      "eval_loss": 1.4275208711624146,
+      "eval_runtime": 14.2116,
+      "eval_samples_per_second": 88.027,
+      "eval_steps_per_second": 11.047,
+      "step": 300
+    },
+    {
+      "epoch": 1.7218855218855218,
+      "grad_norm": 0.746303379535675,
+      "learning_rate": 2.312431839384543e-05,
+      "loss": 1.393,
+      "step": 320
+    },
+    {
+      "epoch": 1.8296296296296295,
+      "grad_norm": 0.7554110884666443,
+      "learning_rate": 2.0026874751013972e-05,
+      "loss": 1.3853,
+      "step": 340
+    },
+    {
+      "epoch": 1.9373737373737374,
+      "grad_norm": 0.735357403755188,
+      "learning_rate": 1.7007237389966146e-05,
+      "loss": 1.3835,
+      "step": 360
+    },
+    {
+      "epoch": 2.043097643097643,
+      "grad_norm": 0.7572635412216187,
+      "learning_rate": 1.4112649592066293e-05,
+      "loss": 1.369,
+      "step": 380
+    },
+    {
+      "epoch": 2.1508417508417508,
+      "grad_norm": 0.7531948685646057,
+      "learning_rate": 1.1388398194579725e-05,
+      "loss": 1.3724,
+      "step": 400
+    },
+    {
+      "epoch": 2.1508417508417508,
+      "eval_loss": 1.4167424440383911,
+      "eval_runtime": 14.2716,
+      "eval_samples_per_second": 87.657,
+      "eval_steps_per_second": 11.001,
+      "step": 400
+    },
+    {
+      "epoch": 2.2585858585858585,
+      "grad_norm": 0.7567663192749023,
+      "learning_rate": 8.877105062283609e-06,
+      "loss": 1.3674,
+      "step": 420
+    },
+    {
+      "epoch": 2.366329966329966,
+      "grad_norm": 0.7656159400939941,
+      "learning_rate": 6.618060253503472e-06,
+      "loss": 1.3686,
+      "step": 440
+    },
+    {
+      "epoch": 2.474074074074074,
+      "grad_norm": 0.7571391463279724,
+      "learning_rate": 4.646607313425419e-06,
+      "loss": 1.3617,
+      "step": 460
+    },
+    {
+      "epoch": 2.581818181818182,
+      "grad_norm": 0.7939226627349854,
+      "learning_rate": 2.9935903119851757e-06,
+      "loss": 1.3648,
+      "step": 480
+    },
+    {
+      "epoch": 2.6895622895622897,
+      "grad_norm": 0.7923122048377991,
+      "learning_rate": 1.6848712776191767e-06,
+      "loss": 1.3694,
+      "step": 500
+    },
+    {
+      "epoch": 2.6895622895622897,
+      "eval_loss": 1.4127447605133057,
+      "eval_runtime": 14.3897,
+      "eval_samples_per_second": 86.937,
+      "eval_steps_per_second": 10.911,
+      "step": 500
+    },
+    {
+      "epoch": 2.7973063973063974,
+      "grad_norm": 0.7516689896583557,
+      "learning_rate": 7.409255767952538e-07,
+      "loss": 1.3562,
+      "step": 520
+    },
+    {
+      "epoch": 2.905050505050505,
+      "grad_norm": 0.751866340637207,
+      "learning_rate": 1.7652156975161982e-07,
+      "loss": 1.3503,
+      "step": 540
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 558,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.181275398144e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-558/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a75d9a8eeff9861f89e8dd597061104867a6fa7c8237f424ce50a54352f47e4
+size 5777

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "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": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2f60fd56eabb86ada6d0ef7c30d1ce71e1ed22af2d19e5238a9f0a5cdfa23c
+size 33384666

tokenizer.model

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