palicoqiqi/paligemma_VQAv2_enel645

README.md

@@ -1,13 +1,13 @@
----
-library_name: peft
-license: gemma
-base_model: google/paligemma-3b-pt-224
-tags:
-- generated_from_trainer
-model-index:
-- name: paligemma_vqav2
-  results: []
----
+---
+library_name: peft
+license: gemma
+base_model: google/paligemma-3b-pt-224
+tags:
+- generated_from_trainer
+model-index:
+- name: paligemma_vqav2
+  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. -->
@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # paligemma_vqav2
 
 This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3071
 
 ## Model description
 
@@ -35,40 +33,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- learning_rate: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_HF 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: 3
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 17.5324       | 0.2262 | 100  | 0.8638          |
-| 2.2935        | 0.4525 | 200  | 0.4939          |
-| 1.6276        | 0.6787 | 300  | 0.4693          |
-| 1.5973        | 0.9050 | 400  | 0.3865          |
-| 1.2928        | 1.1312 | 500  | 0.3795          |
-| 1.0865        | 1.3575 | 600  | 0.3382          |
-| 1.0657        | 1.5837 | 700  | 0.4016          |
-| 1.0918        | 1.8100 | 800  | 0.3423          |
-| 1.0015        | 2.0362 | 900  | 0.3159          |
-| 0.9093        | 2.2624 | 1000 | 0.3216          |
-| 0.9995        | 2.4887 | 1100 | 0.3557          |
-| 0.7912        | 2.7149 | 1200 | 0.3161          |
-| 0.6624        | 2.9412 | 1300 | 0.3071          |
-
+- num_epochs: 6
 
 ### Framework versions
 
 - PEFT 0.13.2
-- Transformers 4.46.1
-- Pytorch 2.4.1+cu124
-- Datasets 2.19.1
-- Tokenizers 0.20.1
+- Transformers 4.46.2
+- Pytorch 2.1.2.post304
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -1,34 +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": [
-    "down_proj",
-    "k_proj",
-    "o_proj",
-    "up_proj",
-    "gate_proj",
-    "v_proj",
-    "q_proj"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
+{
+  "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": [
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63703968662ec270f383e4e91b2f9d827e7451c733c48cc850b4049639e455c7
+oid sha256:09013496531ce3b9953bd80d756d8876370a4b4e77081bc130d93174bf7a2786
 size 45258384

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72665fa7d0db68b4a63d9cb6a34146d8e5bc28665f2fb2d9b65c2b5395cee0e8
+oid sha256:5cd5e916ff8acf471dc1bc737112d05a6ca7ec0cfc74d806a4377cf65ea339f0
 size 5240