Training in progress, epoch 1

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/mt5-base",
+  "_name_or_path": "google/mt5-large",
   "architectures": [
     "MT5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -17,9 +17,9 @@
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "mt5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5768ba65117aee553f2138c340157a014c03012285737288f0737e8cceafb0b9
-size 2329638768
+oid sha256:e9ff8d96b12f59b17e9494be03cb970fb19e78d904e5af7963173480f2974980
+size 4918393736

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6542b847c8e64dca9c6fa8665d5ca649e6956750c0070a2d710e39a705de29c5
+oid sha256:64a63885ad441bdce019849dcc702b82d8df04a920ce0838da2822899e343c17
 size 5304