Model save

README.md

@@ -0,0 +1,59 @@
+---
+license: gemma
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: google/paligemma-3b-pt-224
+datasets:
+- imagefolder
+model-index:
+- name: paligemma_educacode
+  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. -->
+
+# paligemma_educacode
+
+This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the imagefolder dataset.
+
+## 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma-3b-pt-224",
+  "bias": "none",
+  "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": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "o_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 sha256:14d572a7c05146bab15b77c5da395cd976cb6ea0dfefa923dc5de40ecb63cffa
+size 45258384

runs/Jun05_10-14-26_gpu-l4-ab/events.out.tfevents.1717582549.gpu-l4-ab.40677.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a22b5dfb8cfb8ef172dca6d91f91f02e72e130d21d2e259c01a8390f3480e3
+size 5682

runs/Jun05_10-20-37_gpu-l4-ab/events.out.tfevents.1717582837.gpu-l4-ab.42008.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3123335d87886495b4cba570d518be5c0993446cdcf254bd721639e5ff90d6e
+size 5682

runs/Jun05_12-33-55_gpu-l4-ab/events.out.tfevents.1717590836.gpu-l4-ab.64311.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e5119c42b97bfeb48afa352f41d435c7b683f500224002920c9b7e6ba62d2f
+size 5682

runs/Jun05_13-00-33_gpu-l4-ab/events.out.tfevents.1717592438.gpu-l4-ab.64311.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5d873c3dfdf1cdac4da0edd6175d8eab647cfa7cdbfa39b1f242c5306f530c
+size 5682

runs/Jun05_13-01-46_gpu-l4-ab/events.out.tfevents.1717592507.gpu-l4-ab.68303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9e2e9b8693155b401b54329b058c590046d88bf455eed250602ed48bcfdf8b
+size 5682

runs/Jun06_08-15-43_gpu-l4-ab/events.out.tfevents.1717661745.gpu-l4-ab.2926.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df72734355ef20c1f5f8044eb4925ff8d6950b259022830a9547f7c9384f422
+size 5201

runs/Jun06_08-25-37_gpu-l4-ab/events.out.tfevents.1717662338.gpu-l4-ab.9591.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df052391704e84512c532db39f3c8cb8a762179d14796b49d901fe0bfc2f023
+size 5201

runs/Jun06_08-44-12_gpu-l4-ab/events.out.tfevents.1717663503.gpu-l4-ab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd793704556c5c6725406becdb7d823ae5e4d9ba10fed08d0785ab87275df00
+size 5153

runs/Jun06_08-51-00_gpu-l4-ab/events.out.tfevents.1717663864.gpu-l4-ab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a20cec6967318be92575bc9ef09d710654b1679ea416fc0cd1c14c9f362de660
+size 5634

runs/Jun06_09-10-03_gpu-l4-ab/events.out.tfevents.1717665004.gpu-l4-ab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a7ec0f14ea8768bf16e4ad4e26f8172606c15a5414f033917e98f804c416ae
+size 6592

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d31753c17d5e9fd02ddc407e6c898088705486b4e67b8c9d0fabb8c10708ba6
+size 5112