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-3n-e2b-it
+library_name: transformers
+model_name: medgemma-4b-oraclebio_prompt
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for medgemma-4b-oraclebio_prompt
+
+This model is a fine-tuned version of [google/gemma-3n-e2b-it](https://huggingface.co/google/gemma-3n-e2b-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="kadcoder/medgemma-4b-oraclebio_prompt", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.19.1
+- Transformers: 4.53.1
+- Pytorch: 2.4.1
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
+
+## 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 +1,66 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3n-e2b-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "prediction_coefs",
+    "altup_projections.1",
+    "modality_router",
+    "o_proj",
+    "ffw_layer_1",
+    "ffw_layer_2",
+    "input_proj_linear",
+    "v_proj",
+    "altup_unembed_projections.1",
+    "per_layer_input_gate",
+    "per_layer_model_projection",
+    "gate_proj",
+    "linear_end",
+    "altup_projections.0",
+    "altup_unembed_projections.2",
+    "post",
+    "embedding_projection",
+    "linear_left",
+    "altup_projections.2",
+    "pos_proj",
+    "linear_start",
+    "q_proj",
+    "down_proj",
+    "linear_right",
+    "up_proj",
+    "altup_unembed_projections.0",
+    "k_proj",
+    "per_layer_projection",
+    "correction_coefs"
+  ],
+  "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:e05cf8cc5f852e0d145161f3e08bfaa431da694043919e5a7b2d78393a227fca
+size 2299383480

chat_template.jinja

@@ -0,0 +1,49 @@
+{{ 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'] == 'audio' -%}
+                {{ '<audio_soft_token>' }}
+            {%- elif item['type'] == 'image' -%}
+                {{ '<image_soft_token>' }}
+            {%- 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 +1,51 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
+  "dither": 0.0,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_size": 128,
+  "fft_length": 1024,
+  "fft_overdrive": true,
+  "frame_length": 512,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "input_scale_factor": 1.0,
+  "max_frequency": 7600.0,
+  "mel_floor": 1e-05,
+  "min_frequency": 125.0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "per_bin_mean": null,
+  "per_bin_stddev": null,
+  "preemphasis": 0.97,
+  "preemphasis_htk_flavor": true,
+  "processor_class": "Gemma3nProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": true,
+  "return_tensors": null,
+  "sampling_rate": 16000,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

processor_config.json

@@ -0,0 +1,5 @@
+{
+  "audio_seq_length": 188,
+  "image_seq_length": 256,
+  "processor_class": "Gemma3nProcessor"
+}

runs/Jul11_13-38-35_shivneri/events.out.tfevents.1752221320.shivneri

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3508a1f01df86e8e27392c8c5aa5bb6550701677cf71ee817be2195bcbbf98
+size 9601

runs/Jul11_13-55-03_shivneri/events.out.tfevents.1752222309.shivneri

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6b01d2e6f4d85cfd20ef8932730e2a6df859aa4d13b73438c1f445d61f4ae4
+size 9601

runs/Jul11_14-05-26_shivneri/events.out.tfevents.1752222931.shivneri

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048ff600ab33258c946caad03b27c4304774835141f4cf99f5cbed4a0267ba6a
+size 9597

runs/Jul14_10-13-15_shivneri/events.out.tfevents.1752468217.shivneri

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0bfd7bd691f50f535824488e0c53703d7ea04500295d68da67deee0fce9a2d3
+size 9601

runs/Jul14_10-24-15_shivneri/events.out.tfevents.1752468859.shivneri

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38933041225de7aced7b6ca2839badec650a5e34882f43c17eccedf86b97dfa
+size 9601

runs/Jul14_10-30-22_shivneri/events.out.tfevents.1752469226.shivneri

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa83838e8c3ba125a260808511494ec6b5fed6869a24e3148a1f865f641115a
+size 11011

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "audio_token": "<audio_soft_token>",
+  "boa_token": "<start_of_audio>",
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoa_token": "<end_of_audio>",
+  "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:ed504d44c6898db6d71f4abf77cf8e12a9ee3ac90bb1aec0e1edc012c4251b23
+size 33442708

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ac031eb0a87aabba756d0f187da17faa495bc1746c19689784401172cace2e
+size 5816