End of training

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: google/paligemma-3b-pt-448
 library_name: transformers
 license: gemma
+base_model: google/paligemma-3b-mix-448
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # paligemma-rocov2
 
-This model is a fine-tuned version of [google/paligemma-3b-pt-448](https://huggingface.co/google/paligemma-3b-pt-448) on an unknown dataset.
+This model is a fine-tuned version of [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) on an unknown dataset.
 
 ## Model description
 
@@ -33,14 +33,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 4
+- num_epochs: 6
 
 ### Training results
 
@@ -50,5 +50,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.44.2
 - Pytorch 2.4.0+cu121
-- Datasets 3.0.0
+- Datasets 3.0.1
 - Tokenizers 0.19.1

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "content/paligemma_rocov2/checkpoint-95000",
-  "_vocab_size": 257216,
+  "_name_or_path": "google/paligemma-3b-mix-448",
   "architectures": [
     "PaliGemmaForConditionalGeneration"
   ],
   "bos_token_id": 2,
   "eos_token_id": 1,
   "hidden_size": 2048,
+  "ignore_index": -100,
   "image_token_index": 257152,
   "model_type": "paligemma",
   "pad_token_id": 0,
@@ -22,8 +22,8 @@
     "torch_dtype": "float32",
     "vocab_size": 257216
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.45.1",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
   "vision_config": {
     "hidden_size": 1152,
     "image_size": 448,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.44.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f386d29458bd3506cfc56a0160995c78a4ff64f9b54af19cd882d62a4eb25ae
+oid sha256:fc307bd4956b3d434485c27e0955fa1a4caab954e93d822b7d010fae27141a41
 size 4986813864

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:932622f017540e0293d32ffa49bdb2617f5911415e9874aee228242cf1bf9c85
+oid sha256:a86a96f37c4fd8369d3f9c7d5c2c1088c7e0b1c1d0ee3b6392ff305781818797
 size 861970608

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1feedb5d06bfd80099941e903459d7ca332bf5eb36d369b55b76106ac12dcc63
+oid sha256:7e725024b49990d5c5365c644c8a94df5558cca92588f9c34848382711e99b06
 size 5176