End of training

README.md

@@ -32,11 +32,11 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 8
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.33.0
+- 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": "4.33.0",
+  "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": "4.33.0"
+  "transformers_version": "4.32.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e53d362b93c86eaa5476ac25fe223b503430fa978a4c304cacdeac4dbf8bb0c
+oid sha256:63286db2961ea39aba18dadac3cffa2de1a77fd9496e7223a029eb72ce60d4a2
 size 706584273

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60653fc36402e24e3da53a772d4adf31266c06898d96f0274332783b61a76c43
+oid sha256:77d3fa61dff744b1dce728f1b128cf4849da4a4c2ee3ca5967f0b9516f206e08
 size 4027