End of training

README.md

@@ -32,19 +32,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 50
+- num_epochs: 5
+
+### Training results
+
+
 
 ### Framework versions
 
-- Transformers 4.32.0
-- Pytorch 2.0.1+cu117
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
 - Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -22,7 +22,7 @@
   "position_embedding_type": "absolute",
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.32.0",
+  "transformers_version": "4.32.1",
   "use_cache": true,
   "vision_config": {
     "dropout": 0.0,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 101,
   "eos_token_id": 102,
   "pad_token_id": 0,
-  "transformers_version": "4.32.0"
+  "transformers_version": "4.32.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb19154d60ae63b3c0f48b8bba14ade2d67ace854ee6b7101f0d428c35d9946
+oid sha256:a3c3c6f0fc98e6ac4c6fb2185eb76804bbe4181f93e4b8c0357dcd9513a76f09
 size 706584273

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e52ec23869b8cad54c8db947bbc364f0c511499f941a81d23bff1a3f15e9186
+oid sha256:124a4717a0c4f65834af87e779b24028d2a69e1effccf242b3be87e6a30e6bcb
 size 4027