Training in progress, epoch 1

config.json

@@ -1,32 +1,32 @@
 {
-  "_name_or_path": "VietAI/vit5-large",
+  "_name_or_path": "VietAI/vit5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2816,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 768,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
+  "dense_act_fn": "relu",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
+  "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
+  "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.48.1",
   "use_cache": true,
-  "vocab_size": 36100
+  "vocab_size": 36096
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c8c8c4dec986de7b4113012a47895f54fda2c4a9ae2f5062f15867925e66b74
-size 3165207432
+oid sha256:cf4042fd1712c776de18373ad93a65ad56afd836468fa608d596fd2337a269d1
+size 903834408