Training in progress, step 500

config.json

@@ -45,7 +45,7 @@
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.37.0.dev0",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

merges.txt

@@ -1,4 +1,5 @@
 #version: 0.2
+Ġ t
 Ġ a
 Ġt h
 i n

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f32d36e3c3ee2d16eb7af33211bece5b2a16313fb2671d52eb742b58033cc6c1
+oid sha256:323967b98d4d6e0f5bd9b911b2eb7feecbfc04d73b91b36c2adade9bd83e998a
 size 966995080

runs/Jun11_09-35-24_kudsit-dgxserver/events.out.tfevents.1718078749.kudsit-dgxserver.1626661.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4caa26b0707fda258cd6201fa8525258bf2e46077a724460d19f5536e380fa0
+size 10487

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c56ff61e2ab4092178a03ff9a1e85c979aab95a44a828dc31e54817bc55430
-size 4411
+oid sha256:7a49060711db9124add6bc6bd98ffb99e8e1b5b8939e9d628d27a55e5884ada3
+size 5240