Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: google/gemma-3-27b-it
+library_name: transformers
+model_name: GRPO_gemma_27b_language
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for GRPO_gemma_27b_language
+
+This model is a fine-tuned version of [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Marszzibros/GRPO_gemma_27b_language", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.23.0
+- Transformers: 4.56.1
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.3.2
+- Tokenizers: 0.22.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,154 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-27b-it",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "language_model.layers.32.self_attn.k_proj",
+    "language_model.layers.30.self_attn.q_proj",
+    "language_model.layers.46.self_attn.q_proj",
+    "language_model.layers.39.self_attn.k_proj",
+    "language_model.layers.27.self_attn.k_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "language_model.layers.29.self_attn.k_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "language_model.layers.26.self_attn.q_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "language_model.layers.48.self_attn.q_proj",
+    "language_model.layers.60.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.33.self_attn.k_proj",
+    "language_model.layers.47.self_attn.k_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "language_model.layers.37.self_attn.q_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "language_model.layers.42.self_attn.k_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "language_model.layers.44.self_attn.k_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "language_model.layers.26.self_attn.k_proj",
+    "language_model.layers.6.self_attn.k_proj",
+    "language_model.layers.28.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "language_model.layers.61.self_attn.q_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "language_model.layers.25.self_attn.k_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.43.self_attn.q_proj",
+    "language_model.layers.49.self_attn.q_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "language_model.layers.56.self_attn.k_proj",
+    "language_model.layers.29.self_attn.q_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.52.self_attn.q_proj",
+    "language_model.layers.47.self_attn.q_proj",
+    "language_model.layers.52.self_attn.k_proj",
+    "language_model.layers.57.self_attn.q_proj",
+    "language_model.layers.51.self_attn.q_proj",
+    "language_model.layers.53.self_attn.q_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "language_model.layers.33.self_attn.q_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "language_model.layers.36.self_attn.q_proj",
+    "language_model.layers.55.self_attn.k_proj",
+    "language_model.layers.61.self_attn.k_proj",
+    "language_model.layers.24.self_attn.q_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "language_model.layers.34.self_attn.q_proj",
+    "language_model.layers.40.self_attn.k_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "language_model.layers.54.self_attn.q_proj",
+    "language_model.layers.27.self_attn.q_proj",
+    "language_model.layers.60.self_attn.q_proj",
+    "language_model.layers.34.self_attn.k_proj",
+    "language_model.layers.55.self_attn.q_proj",
+    "language_model.layers.45.self_attn.q_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "language_model.layers.46.self_attn.k_proj",
+    "language_model.layers.41.self_attn.q_proj",
+    "language_model.layers.50.self_attn.q_proj",
+    "language_model.layers.59.self_attn.q_proj",
+    "language_model.layers.58.self_attn.k_proj",
+    "language_model.layers.24.self_attn.k_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "language_model.layers.25.self_attn.q_proj",
+    "language_model.layers.48.self_attn.k_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.36.self_attn.k_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "language_model.layers.35.self_attn.k_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "language_model.layers.28.self_attn.q_proj",
+    "language_model.layers.43.self_attn.k_proj",
+    "language_model.layers.38.self_attn.k_proj",
+    "language_model.layers.44.self_attn.q_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "language_model.layers.31.self_attn.k_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.32.self_attn.q_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "language_model.layers.45.self_attn.k_proj",
+    "language_model.layers.50.self_attn.k_proj",
+    "language_model.layers.57.self_attn.k_proj",
+    "language_model.layers.39.self_attn.q_proj",
+    "language_model.layers.40.self_attn.q_proj",
+    "language_model.layers.59.self_attn.k_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "language_model.layers.30.self_attn.k_proj",
+    "language_model.layers.31.self_attn.q_proj",
+    "language_model.layers.56.self_attn.q_proj",
+    "language_model.layers.51.self_attn.k_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.54.self_attn.k_proj",
+    "language_model.layers.53.self_attn.k_proj",
+    "language_model.layers.37.self_attn.k_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "language_model.layers.35.self_attn.q_proj",
+    "language_model.layers.38.self_attn.q_proj",
+    "language_model.layers.49.self_attn.k_proj",
+    "language_model.layers.41.self_attn.k_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.42.self_attn.q_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.58.self_attn.q_proj",
+    "language_model.layers.22.self_attn.q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7735b623949b8b850a8eceb2de9978762c1d0d87eed7273bb78e5f72669887cb
+size 268210800

added_tokens.json

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

chat_template.jinja

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

preprocessor_config.json

@@ -0,0 +1,37 @@
+{
+  "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_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,
+  "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
+  }
+}

processor_config.json

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

runs/Oct09_01-28-33_hgnode01.cluster/events.out.tfevents.1759987715.hgnode01.cluster.3424797.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55f6a6ac683146d826230420429f236ec6a5e1c7290f25764204cd36a99536b
+size 12408

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": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d786405177734910d7a3db625c2826640964a0b4e5cdbbd70620ae3313a01bef
+size 33384722

tokenizer.model

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

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47a00637c6a7989bb1d4a6849b77435047fbdf17631ab1d67dff22f3974bd66
+size 5816