Training in progress, step 4800

config.json

@@ -3,9 +3,9 @@
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 512,
+  "d_ff": 1024,
   "d_kv": 64,
-  "d_model": 128,
+  "d_model": 256,
   "decoder_start_token_id": 1,
   "dense_act_fn": "relu",
   "dropout_rate": 0.3,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537e0a9675dcc563ee624c35c19ba2d464d32594c2833c7309e9f5301bbd8c1e
-size 10538456
+oid sha256:2a8b1297b237304fdf356081e36e6591b408b0db759bded20e0f56f443765cd6
+size 29454424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c7553b75259bff048c1d76cc3549437519bcce4401a521f23a5914ffd80360
+oid sha256:b4ce67ebca446b6b6caba45b9fc27fdf79fdcab8443377ca428ec7e56a445621
 size 4728

vocab.json

@@ -1 +1 @@
-{"d": 0, "S": 1, "s": 2, "z": 3, ",": 4, "F": 5, "L": 6, "y": 7, "4": 8, "g": 9, "x": 10, "\u0144": 11, "\u012f": 12, "\u00f3": 13, "\u00e1": 14, "N": 15, "w": 16, "h": 17, "n": 18, "\u0105": 19, "c": 20, "l": 21, "1": 22, "(": 23, "\u02bc": 24, "k": 25, "t": 26, "E": 27, "G": 28, " ": 29, "O": 30, "j": 31, "\u0301": 32, "V": 33, "\u01eb": 34, "b": 35, "\u00e9": 36, "P": 37, "m": 38, "e": 39, "R": 40, "o": 41, ";": 42, "M": 43, "I": 44, "2": 45, ")": 46, "\u0119": 47, "a": 48, "D": 49, "\u0142": 50, "\u00ed": 51, "3": 52, "i": 53, "T": 54}
+{"F": 0, "\u0144": 1, "V": 2, "i": 3, "j": 4, "\u00e9": 5, "n": 6, ")": 7, "g": 8, "\u0119": 9, "1": 10, "(": 11, "\u02bc": 12, "\u0301": 13, "l": 14, "\u01eb": 15, "\u00e1": 16, "b": 17, "c": 18, "4": 19, "T": 20, "x": 21, "\u00ed": 22, "o": 23, "M": 24, "y": 25, "\u00f3": 26, "D": 27, "h": 28, "a": 29, "\u012f": 30, "3": 31, ",": 32, "z": 33, "N": 34, "\u0142": 35, "P": 36, "s": 37, "e": 38, "L": 39, "d": 40, "O": 41, "k": 42, "w": 43, "G": 44, "E": 45, "R": 46, " ": 47, "2": 48, "\u0105": 49, "m": 50, "S": 51, "I": 52, ";": 53, "t": 54}