End of training

README.md

@@ -0,0 +1,60 @@
+---
+library_name: peft
+license: gemma
+base_model: google/paligemma2-3b-pt-448
+tags:
+- base_model:adapter:google/paligemma2-3b-pt-448
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: finetuned_paligemma2_classification
+  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. -->
+
+# finetuned_paligemma2_classification
+
+This model is a fine-tuned version of [google/paligemma2-3b-pt-448](https://huggingface.co/google/paligemma2-3b-pt-448) on an unknown 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: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- 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
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.1.0
+- Pytorch 2.7.1+cu118
+- Datasets 4.5.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma2-3b-pt-448",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "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 sha256:05ed380994ad95ed09f1cf6ec9d1ebd7d9578af7d851c4b34a280537581b6b6b
+size 47585944

runs/Feb10_11-19-18_FAIE-AI-09/events.out.tfevents.1770693624.FAIE-AI-09

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc07e3e319e3ed3f7e0e1b9796f1a9ab1a9b4e3bc129d93d9775ba0db629151e
+size 6200

runs/Feb10_11-25-33_FAIE-AI-09/events.out.tfevents.1770693933.FAIE-AI-09

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80f96843852f30a4e520ee2b9e325b39412038fecc9d70945ca2df40e5ae4a3
+size 6200

runs/Feb10_11-33-36_FAIE-AI-09/events.out.tfevents.1770694416.FAIE-AI-09

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6709d96726094b4be76b1cff5cd36d9144474d8fc7f6004456494ae8bf6d86c9
+size 6200

runs/Feb10_11-43-32_FAIE-AI-09/events.out.tfevents.1770695012.FAIE-AI-09

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19057c998469da0ed09f92096d30dd2b5bf393d51134ff95fcc7f7bcde8f32f0
+size 8748

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e36b224bc720373a32d821acca523e9eda85723231381172cf12c587546191
+size 5201