Training in progress, step 500

config.json

@@ -53,7 +53,7 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.52.4",
+  "transformers_version": "4.51.3",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b4662dbe0867eedfd67bc6701e9f7c98fadec4dd520a5cd67802b5add5568ca
+oid sha256:77be049d286664589e4231592250d05b48c94074dd5f7b45eb493682c6c43d96
 size 151061672

runs/Jun08_00-08-44_dgx1/events.out.tfevents.1749316131.dgx1.1087.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b51935ddfcaee03f5873af9b07c8231f32dab9a11d12064e0a9cac54ce62cb9
+size 6705

runs/Jun08_00-26-18_dgx1/events.out.tfevents.1749317183.dgx1.3847000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85eba42adeb6843af50e66dbaccf630c71f52f9efc6cbe5100d99a60d2a43c9
+size 8072

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a04ae3668ae7250ce36f42dad55c150f9f06934c258655f56937556d7370920
-size 5432
+oid sha256:f002cf15d3b6b1f80ea6893acda56a9c6feed5ffb3b1bfa6f9f67aa69846499a
+size 5841