Training in progress, step 500

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "google/t5-efficient-tiny",
   "architectures": [
-    "MT5ForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 1024,
@@ -16,7 +16,7 @@
   "is_encoder_decoder": true,
   "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
-  "model_type": "mt5",
+  "model_type": "t5",
   "n_positions": 512,
   "num_decoder_layers": 4,
   "num_heads": 4,
@@ -24,10 +24,8 @@
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d818b50dce06f37ccee826d3e856fba3415cfe7ba1f8af2cfc5a283a57fb92
-size 95192240
+oid sha256:ec5e19390f915af7d82e4e4d4ab59cbb91dfd4e2451e13a4fd5b2fcb2756dcd2
+size 62293080

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:460cb8fd56ae0d5ed6bae56009a47139062f18612f67c21b7c58a64d8f751025
-size 5112
+oid sha256:4268468d3d9674585a598e05f6471227d45012e3a5ed659ffc6e3c31b2b445df
+size 5176