Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,18 @@ 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
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-5500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-6500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-7500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/README.md

@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-12b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-12b-it
+- llama-factory
+- 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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/adapter_config.json

@@ -0,0 +1,183 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-12b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "45.self_attn.k_proj",
+    "language_model.layers.26.self_attn.v_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "33.self_attn.v_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "31.self_attn.k_proj",
+    "41.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "30.self_attn.k_proj",
+    "46.self_attn.q_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "38.self_attn.k_proj",
+    "30.self_attn.v_proj",
+    "42.self_attn.k_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.25.self_attn.q_proj",
+    "35.self_attn.k_proj",
+    "language_model.layers.24.self_attn.k_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "43.self_attn.k_proj",
+    "46.self_attn.k_proj",
+    "29.self_attn.q_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "language_model.layers.26.self_attn.k_proj",
+    "language_model.layers.6.self_attn.k_proj",
+    "31.self_attn.v_proj",
+    "32.self_attn.v_proj",
+    "36.self_attn.v_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "29.self_attn.v_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "37.self_attn.k_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "36.self_attn.k_proj",
+    "32.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "28.self_attn.k_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "29.self_attn.k_proj",
+    "35.self_attn.v_proj",
+    "34.self_attn.v_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "45.self_attn.v_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.26.self_attn.q_proj",
+    "32.self_attn.q_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "46.self_attn.v_proj",
+    "34.self_attn.q_proj",
+    "41.self_attn.q_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "35.self_attn.q_proj",
+    "44.self_attn.v_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "language_model.layers.25.self_attn.v_proj",
+    "o_proj",
+    "40.self_attn.k_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "41.self_attn.v_proj",
+    "43.self_attn.q_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "44.self_attn.q_proj",
+    "38.self_attn.q_proj",
+    "gate_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "33.self_attn.k_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "47.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "38.self_attn.v_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.8.self_attn.v_proj",
+    "42.self_attn.v_proj",
+    "30.self_attn.q_proj",
+    "34.self_attn.k_proj",
+    "language_model.layers.22.self_attn.q_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "40.self_attn.v_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.25.self_attn.k_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "down_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "39.self_attn.k_proj",
+    "39.self_attn.q_proj",
+    "28.self_attn.q_proj",
+    "42.self_attn.q_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "47.self_attn.q_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "language_model.layers.24.self_attn.q_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "27.self_attn.v_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "47.self_attn.k_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "31.self_attn.q_proj",
+    "45.self_attn.q_proj",
+    "37.self_attn.v_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "44.self_attn.k_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "43.self_attn.v_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "39.self_attn.v_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.24.self_attn.v_proj",
+    "33.self_attn.q_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "40.self_attn.q_proj",
+    "37.self_attn.q_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "36.self_attn.q_proj",
+    "up_proj",
+    "27.self_attn.k_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "language_model.layers.17.self_attn.v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957f53d715467ed75bf93e4c863716ae1f45b9997939b00c3d419efb1fa81e1a
+size 131040264

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/added_tokens.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/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 -%}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de5e8a63f6c3c4b02297e58ec0448d97c42348698008d16cb938aa54fea87e1
+size 262458115

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "pad_size": null,
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/processor_config.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35427a52c2efa0fec120cbb82740a723aa8d3e013602949cd14e4d8478d1643
+size 14917

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d28cccba7c0c8f513cc13c0161799b66265594f5d089d75bdeeb0b6f8e034e0
+size 14917

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f607abe2a990f88222f8b88ece6b196c0805a49700f255922f6acb3dce633a2
+size 1465

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/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
+  }
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/tokenizer.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/tokenizer.model

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0016758899970944258,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00016758899970944257,
+      "grad_norm": 95.10325622558594,
+      "learning_rate": 1.6591251885369532e-07,
+      "loss": 9.9716,
+      "step": 100
+    },
+    {
+      "epoch": 0.00033517799941888514,
+      "grad_norm": 117.05254364013672,
+      "learning_rate": 3.3350092173621586e-07,
+      "loss": 9.601,
+      "step": 200
+    },
+    {
+      "epoch": 0.0005027669991283277,
+      "grad_norm": 69.19080352783203,
+      "learning_rate": 5.010893246187364e-07,
+      "loss": 6.6882,
+      "step": 300
+    },
+    {
+      "epoch": 0.0006703559988377703,
+      "grad_norm": 9.027195930480957,
+      "learning_rate": 6.686777275012569e-07,
+      "loss": 1.8263,
+      "step": 400
+    },
+    {
+      "epoch": 0.0008379449985472129,
+      "grad_norm": 3.1505911350250244,
+      "learning_rate": 8.362661303837775e-07,
+      "loss": 0.3846,
+      "step": 500
+    },
+    {
+      "epoch": 0.0010055339982566554,
+      "grad_norm": 2.917604923248291,
+      "learning_rate": 1.003854533266298e-06,
+      "loss": 0.2385,
+      "step": 600
+    },
+    {
+      "epoch": 0.001173122997966098,
+      "grad_norm": 2.870957136154175,
+      "learning_rate": 1.1714429361488186e-06,
+      "loss": 0.2143,
+      "step": 700
+    },
+    {
+      "epoch": 0.0013407119976755406,
+      "grad_norm": 2.8623578548431396,
+      "learning_rate": 1.339031339031339e-06,
+      "loss": 0.2114,
+      "step": 800
+    },
+    {
+      "epoch": 0.0015083009973849832,
+      "grad_norm": 1.8653913736343384,
+      "learning_rate": 1.5066197419138597e-06,
+      "loss": 0.2068,
+      "step": 900
+    },
+    {
+      "epoch": 0.0016758899970944258,
+      "grad_norm": 2.1829867362976074,
+      "learning_rate": 1.67420814479638e-06,
+      "loss": 0.2062,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 596698,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.774484412860203e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089ea3461a5d21a09ac904572b0a994bbb43c806a83762f7511b05f9b263664b
+size 6225

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/README.md

@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-12b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-12b-it
+- llama-factory
+- 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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/adapter_config.json

@@ -0,0 +1,183 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-12b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "45.self_attn.k_proj",
+    "language_model.layers.26.self_attn.v_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "33.self_attn.v_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "31.self_attn.k_proj",
+    "41.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "30.self_attn.k_proj",
+    "46.self_attn.q_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "38.self_attn.k_proj",
+    "30.self_attn.v_proj",
+    "42.self_attn.k_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.25.self_attn.q_proj",
+    "35.self_attn.k_proj",
+    "language_model.layers.24.self_attn.k_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "43.self_attn.k_proj",
+    "46.self_attn.k_proj",
+    "29.self_attn.q_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "language_model.layers.26.self_attn.k_proj",
+    "language_model.layers.6.self_attn.k_proj",
+    "31.self_attn.v_proj",
+    "32.self_attn.v_proj",
+    "36.self_attn.v_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "29.self_attn.v_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "37.self_attn.k_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "36.self_attn.k_proj",
+    "32.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "28.self_attn.k_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "29.self_attn.k_proj",
+    "35.self_attn.v_proj",
+    "34.self_attn.v_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "45.self_attn.v_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.26.self_attn.q_proj",
+    "32.self_attn.q_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "46.self_attn.v_proj",
+    "34.self_attn.q_proj",
+    "41.self_attn.q_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "35.self_attn.q_proj",
+    "44.self_attn.v_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "language_model.layers.25.self_attn.v_proj",
+    "o_proj",
+    "40.self_attn.k_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "41.self_attn.v_proj",
+    "43.self_attn.q_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "44.self_attn.q_proj",
+    "38.self_attn.q_proj",
+    "gate_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "33.self_attn.k_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "47.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "38.self_attn.v_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.8.self_attn.v_proj",
+    "42.self_attn.v_proj",
+    "30.self_attn.q_proj",
+    "34.self_attn.k_proj",
+    "language_model.layers.22.self_attn.q_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "40.self_attn.v_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.25.self_attn.k_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "down_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "39.self_attn.k_proj",
+    "39.self_attn.q_proj",
+    "28.self_attn.q_proj",
+    "42.self_attn.q_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "47.self_attn.q_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "language_model.layers.24.self_attn.q_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "27.self_attn.v_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "47.self_attn.k_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "31.self_attn.q_proj",
+    "45.self_attn.q_proj",
+    "37.self_attn.v_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "44.self_attn.k_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "43.self_attn.v_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "39.self_attn.v_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.24.self_attn.v_proj",
+    "33.self_attn.q_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "40.self_attn.q_proj",
+    "37.self_attn.q_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "36.self_attn.q_proj",
+    "up_proj",
+    "27.self_attn.k_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "language_model.layers.17.self_attn.v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e668f94480695bd2866b923e2b5ef80a67a91be80cc92214ad0b14a094299a71
+size 131040264

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/added_tokens.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/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 -%}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd79285aeca7de74c09ec3442f29bb7bf1a7813f4ca6ca5e62a360368f5c5a66
+size 262458115

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "pad_size": null,
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/processor_config.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:967f2e82cde4baf5a1f17fed19e68963ba39aba08e86e400990a6db827c23436
+size 14917

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14fe8d57843db60759c696c62000b2c94657a635b437bde97f52198a791f384d
+size 14917

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c696d0cb207790ccee54557e4b3238bd6388debe0d6bf7322b1561d47b4783
+size 1465

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/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
+  }
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/tokenizer.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/tokenizer.model

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0025138349956416385,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00016758899970944257,
+      "grad_norm": 95.10325622558594,
+      "learning_rate": 1.6591251885369532e-07,
+      "loss": 9.9716,
+      "step": 100
+    },
+    {
+      "epoch": 0.00033517799941888514,
+      "grad_norm": 117.05254364013672,
+      "learning_rate": 3.3350092173621586e-07,
+      "loss": 9.601,
+      "step": 200
+    },
+    {
+      "epoch": 0.0005027669991283277,
+      "grad_norm": 69.19080352783203,
+      "learning_rate": 5.010893246187364e-07,
+      "loss": 6.6882,
+      "step": 300
+    },
+    {
+      "epoch": 0.0006703559988377703,
+      "grad_norm": 9.027195930480957,
+      "learning_rate": 6.686777275012569e-07,
+      "loss": 1.8263,
+      "step": 400
+    },
+    {
+      "epoch": 0.0008379449985472129,
+      "grad_norm": 3.1505911350250244,
+      "learning_rate": 8.362661303837775e-07,
+      "loss": 0.3846,
+      "step": 500
+    },
+    {
+      "epoch": 0.0010055339982566554,
+      "grad_norm": 2.917604923248291,
+      "learning_rate": 1.003854533266298e-06,
+      "loss": 0.2385,
+      "step": 600
+    },
+    {
+      "epoch": 0.001173122997966098,
+      "grad_norm": 2.870957136154175,
+      "learning_rate": 1.1714429361488186e-06,
+      "loss": 0.2143,
+      "step": 700
+    },
+    {
+      "epoch": 0.0013407119976755406,
+      "grad_norm": 2.8623578548431396,
+      "learning_rate": 1.339031339031339e-06,
+      "loss": 0.2114,
+      "step": 800
+    },
+    {
+      "epoch": 0.0015083009973849832,
+      "grad_norm": 1.8653913736343384,
+      "learning_rate": 1.5066197419138597e-06,
+      "loss": 0.2068,
+      "step": 900
+    },
+    {
+      "epoch": 0.0016758899970944258,
+      "grad_norm": 2.1829867362976074,
+      "learning_rate": 1.67420814479638e-06,
+      "loss": 0.2062,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0018434789968038684,
+      "grad_norm": 2.0153186321258545,
+      "learning_rate": 1.8417965476789007e-06,
+      "loss": 0.2059,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0020110679965133107,
+      "grad_norm": 1.4869704246520996,
+      "learning_rate": 2.009384950561421e-06,
+      "loss": 0.2049,
+      "step": 1200
+    },
+    {
+      "epoch": 0.0021786569962227533,
+      "grad_norm": 3.2191996574401855,
+      "learning_rate": 2.1769733534439417e-06,
+      "loss": 0.205,
+      "step": 1300
+    },
+    {
+      "epoch": 0.002346245995932196,
+      "grad_norm": 2.707939863204956,
+      "learning_rate": 2.3445617563264623e-06,
+      "loss": 0.2039,
+      "step": 1400
+    },
+    {
+      "epoch": 0.0025138349956416385,
+      "grad_norm": 2.536839723587036,
+      "learning_rate": 2.512150159208983e-06,
+      "loss": 0.203,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 596698,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.656973851430224e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089ea3461a5d21a09ac904572b0a994bbb43c806a83762f7511b05f9b263664b
+size 6225

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/README.md

@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-12b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-12b-it
+- llama-factory
+- 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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/adapter_config.json

@@ -0,0 +1,183 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-12b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "45.self_attn.k_proj",
+    "language_model.layers.26.self_attn.v_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "33.self_attn.v_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "31.self_attn.k_proj",
+    "41.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "30.self_attn.k_proj",
+    "46.self_attn.q_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "38.self_attn.k_proj",
+    "30.self_attn.v_proj",
+    "42.self_attn.k_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.25.self_attn.q_proj",
+    "35.self_attn.k_proj",
+    "language_model.layers.24.self_attn.k_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "43.self_attn.k_proj",
+    "46.self_attn.k_proj",
+    "29.self_attn.q_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "language_model.layers.26.self_attn.k_proj",
+    "language_model.layers.6.self_attn.k_proj",
+    "31.self_attn.v_proj",
+    "32.self_attn.v_proj",
+    "36.self_attn.v_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "29.self_attn.v_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "37.self_attn.k_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "36.self_attn.k_proj",
+    "32.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "28.self_attn.k_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "29.self_attn.k_proj",
+    "35.self_attn.v_proj",
+    "34.self_attn.v_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "45.self_attn.v_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.26.self_attn.q_proj",
+    "32.self_attn.q_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "46.self_attn.v_proj",
+    "34.self_attn.q_proj",
+    "41.self_attn.q_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "35.self_attn.q_proj",
+    "44.self_attn.v_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "language_model.layers.25.self_attn.v_proj",
+    "o_proj",
+    "40.self_attn.k_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "41.self_attn.v_proj",
+    "43.self_attn.q_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "44.self_attn.q_proj",
+    "38.self_attn.q_proj",
+    "gate_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "33.self_attn.k_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "47.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "38.self_attn.v_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.8.self_attn.v_proj",
+    "42.self_attn.v_proj",
+    "30.self_attn.q_proj",
+    "34.self_attn.k_proj",
+    "language_model.layers.22.self_attn.q_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "40.self_attn.v_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.25.self_attn.k_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "down_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "39.self_attn.k_proj",
+    "39.self_attn.q_proj",
+    "28.self_attn.q_proj",
+    "42.self_attn.q_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "47.self_attn.q_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "language_model.layers.24.self_attn.q_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "27.self_attn.v_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "47.self_attn.k_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "31.self_attn.q_proj",
+    "45.self_attn.q_proj",
+    "37.self_attn.v_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "44.self_attn.k_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "43.self_attn.v_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "39.self_attn.v_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.24.self_attn.v_proj",
+    "33.self_attn.q_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "40.self_attn.q_proj",
+    "37.self_attn.q_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "36.self_attn.q_proj",
+    "up_proj",
+    "27.self_attn.k_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "language_model.layers.17.self_attn.v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49c3548562a21d82aadde9af192a9913a07c8934fffcd040fd65184f878931d
+size 131040264

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/added_tokens.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/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 -%}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f7d64c8706a072c77ad7340a1a6f1790b3186915176cd8d71a58a532aaa1a1
+size 262458115

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "pad_size": null,
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/processor_config.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dbf038fa7ae5d94221521613b5efff5095a7535c5709ad62ae5c6d331ff0c5
+size 14917

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645dffcd843647d251aaeb3ddc36fe0a074ac895e1e318dd8df115ced74eec08
+size 14917

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4d2a2b5fb0a77400b6ba49e5ca9dc1b7f6b1961fd479ead6adcd35287573e9
+size 1465

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/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
+  }
+}

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/tokenizer.json

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

gemma3-12b_mmlupro_bbh/lora/sft/checkpoint-2000/tokenizer.model

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