Model save

README.md

@@ -0,0 +1,67 @@
+---
+library_name: peft
+license: other
+base_model: unsloth/medgemma-4b-it-unsloth-bnb-4bit
+tags:
+- base_model:adapter:unsloth/medgemma-4b-it-unsloth-bnb-4bit
+- lora
+- transformers
+- unsloth
+datasets:
+- imagefolder
+pipeline_tag: text-generation
+model-index:
+- name: derm-ai
+  results: []
+---
+
+<!-- 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. -->
+
+# derm-ai
+
+This model is a fine-tuned version of [unsloth/medgemma-4b-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/medgemma-4b-it-unsloth-bnb-4bit) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0633
+- eval_runtime: 87.8654
+- eval_samples_per_second: 1.138
+- eval_steps_per_second: 0.569
+- epoch: 0.4048
+- step: 110
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.16.0
+- Transformers 4.57.1
+- Pytorch 2.6.0+cu124
+- Datasets 4.3.0
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForConditionalGeneration",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/medgemma-4b-it-unsloth-bnb-4bit",
+  "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": [
+    "vision_model.post_layernorm"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "vision_model.post_layernorm",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "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:a19ed0e850efececeb8c8c091ea7a017a4a2f2ffd12d087198661be192643063
+size 131261784

runs/Nov10_13-19-24_9aed36e79a4e/events.out.tfevents.1762780821.9aed36e79a4e.48.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1910b9d9fa7a3965e1628ba6444a25be447988283852c544261938fae3e77806
+size 33480

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc35553b22b48f26b85d781b5373c4e2924ea2476969bc351630159e70bc38d
+size 5432