Training in progress, step 1000

.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

@@ -1,58 +1,58 @@
 ---
-library_name: transformers
-license: gemma
 base_model: google/gemma-3n-E4B-it
+library_name: transformers
+model_name: gemma-3n-E4B-transcribe-zh-tw-1
 tags:
 - generated_from_trainer
-model-index:
-- name: gemma-3n-E4B-transcribe-zh-tw-1
-  results: []
+- trl
+- sft
+licence: license
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# gemma-3n-E4B-transcribe-zh-tw-1
-
-This model is a fine-tuned version of [google/gemma-3n-E4B-it](https://huggingface.co/google/gemma-3n-E4B-it) on an unknown dataset.
+# Model Card for gemma-3n-E4B-transcribe-zh-tw-1
 
-## Model description
+This model is a fine-tuned version of [google/gemma-3n-E4B-it](https://huggingface.co/google/gemma-3n-E4B-it).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-More information needed
+## Quick start
 
-## Intended uses & limitations
+```python
+from transformers import pipeline
 
-More information needed
+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="JacobLinCool/gemma-3n-E4B-transcribe-zh-tw-1", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-## Training and evaluation data
+## Training procedure
 
-More information needed
+ 
 
-## Training procedure
 
-### Training hyperparameters
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 4
-- eval_batch_size: 4
-- seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 8
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 3
+### Framework versions
 
-### Training results
+- TRL: 0.19.0
+- Transformers: 4.53.0
+- Pytorch: 2.8.0.dev20250319+cu128
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
 
-| Training Loss | Epoch | Step | Validation Loss | Cer    | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:---:|
-| No log        | 0     | 0    | 8.2124          | 2.2923 | 1.0 |
+## Citations
 
 
-### Framework versions
 
-- Transformers 4.53.0
-- Pytorch 2.8.0.dev20250319+cu128
-- Datasets 3.6.0
-- Tokenizers 0.21.2
+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 +1,61 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3n-E4B-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": 1,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "altup_unembed_projections.2",
+    "per_layer_projection",
+    "linear_end",
+    "linear_start",
+    "ffw_layer_1",
+    "per_layer_model_projection",
+    "correction_coefs",
+    "pos_proj",
+    "altup_unembed_projections.1",
+    "altup_projections.0",
+    "down_proj",
+    "v_proj",
+    "modality_router",
+    "per_layer_input_gate",
+    "altup_projections.2",
+    "ffw_layer_2",
+    "post",
+    "gate_proj",
+    "prediction_coefs",
+    "o_proj",
+    "q_proj",
+    "linear_right",
+    "altup_unembed_projections.0",
+    "linear_left",
+    "embedding_projection",
+    "input_proj_linear",
+    "k_proj",
+    "altup_projections.1"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82f6b427fab5c6277e902b680eddec235d3401cca47349c7af06c71f4d12d6f
+size 444884256

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 -%}

runs/Jun28_07-47-04_8fa2e96bced5/events.out.tfevents.1751096841.8fa2e96bced5.295305.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c250c26e26e1185ce759f2a46eb9b762892c339db4d1b0da4d7857b2b00a7f6
+size 338811

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dec283e75b72e538f1cfa1ae8ef0ce7da8ec54fbbfc71eb9139d3275703da1c
-size 5969
+oid sha256:7a2ce00daeadd7c0c8033a71070edcf6b1dd57db3255aae04d041659b28a4f34
+size 6289