Training in progress, epoch 1

README.md

@@ -1,23 +1,17 @@
 ---
-base_model: google/medgemma-4b-it
+base_model: google/medgemma-1.5-4b-it
 library_name: transformers
 model_name: dentalgemma
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
-license: mit
-datasets:
-- darmasrmz/radiograph_dental
-language:
-- en
-pipeline_tag: image-text-to-text
 ---
 
 # Model Card for dentalgemma
 
-This model is a fine-tuned version of [google/medgemma-4b-it](https://huggingface.co/google/medgemma-4b-it).
+This model is a fine-tuned version of [google/medgemma-1.5-4b-it](https://huggingface.co/google/medgemma-1.5-4b-it).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "google/medgemma-4b-it",
+  "base_model_name_or_path": "google/medgemma-1.5-4b-it",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -32,16 +32,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
     "v_proj",
-    "k_proj",
-    "up_proj",
-    "o_proj",
     "fc2",
+    "out_proj",
     "fc1",
+    "q_proj",
     "down_proj",
-    "out_proj"
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:187556779943891685fa542774bdff6561661e92fadca23a3f36cd7a2b957661
+oid sha256:e71146705fb8d57dff1dc5954bb4888178f88736ca5a4779a06d08682e414c0d
 size 2762134176

processor_config.json

@@ -1,7 +1,7 @@
 {
   "image_processor": {
     "data_format": "channels_first",
-    "do_convert_rgb": null,
+    "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,
     "do_resize": true,

runs/Feb23_06-26-40_192-222-52-209/events.out.tfevents.1771828000.192-222-52-209.34060.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d5b4897d93392b8ed2c4202df2833420a3fb1f691220da81548b0bf985ac51
+size 7511

runs/Feb23_06-36-12_192-222-52-209/events.out.tfevents.1771828572.192-222-52-209.34060.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84d1d1bbed6c6a541fc7dbdaa049617f6ed40236ac06d30368fa27c7e884bc9
+size 7514

runs/Feb23_06-38-37_192-222-52-209/events.out.tfevents.1771828717.192-222-52-209.34060.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce71ea87b3b4bf62c09505deee9e7b9b5d18d7a390b44bb6bcd99087d1ce9a7b
+size 11544

tokenizer_config.json

@@ -15,6 +15,7 @@
     "image_token": "<image_soft_token>"
   },
   "pad_token": "<pad>",
+  "padding_side": "right",
   "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a8565b9f58b643f9efa3fb4e81a54008382b394d4b5fa35e29d38a4def480d
+oid sha256:0089a2dfe17875840a892c6181bd86491d9eadb8c58c9a68ae8ef388322312c7
 size 5713