Training in progress, step 500

config.json

@@ -18,7 +18,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.35.0",
   "type_vocab_size": 2,
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb29ecefa248b86ad1fe64fd1c6245800f7b684e832694d2802e305fa96f8ba6
-size 219052180
+oid sha256:9b1eea09bb2bec0935d7b28feaee725a657d005729be50ecf8025943f5e49f92
+size 438080896

runs/Nov17_21-26-02_mindsgpu04/events.out.tfevents.1700274988.mindsgpu04.2650441.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb1d22832029e0303c4a82fb662a795a2ae96b5bd1326ae5edc74c7be8b086f
+size 8822

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83592f417c949ede5082b3276dfa8388557bb596c12385bce6fb14fd5438f0ba
+oid sha256:490140751d841e070fffc592e8e537d53850d517b08cd9284b2197ab5bffe335
 size 4664