Training in progress, step 1000

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "google/mt5-base",
   "architectures": [
-    "T5ForConditionalGeneration"
+    "MT5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
@@ -16,7 +16,7 @@
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
+  "model_type": "mt5",
   "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbf29562b683c58c0d78ff8447a1d2977b3f2e399c4ea8661a009e1bb30817ac
+oid sha256:1adcc4f89c40c50ced6679bab8b846cd7e2c786308751f94d14b82697afce479
 size 2329638768

runs/Dec12_05-41-57_3a670e21f7be/events.out.tfevents.1733982120.3a670e21f7be.1553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bbc218be7f67ac6eaec86993beddd78964cd53afd059305658b3c2baf2efb3
+size 5691

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f1e8338a6a0de39b19e12b93214f3d14ba2646a95a12481cd581d8183678eb
+oid sha256:6c321417e74ad77cdd38f449c60945513bfc3f9665c59f4549afbc046c7aad16
 size 5304