Training in progress, epoch 1

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "VietAI/envit5-base",
+  "_name_or_path": "google/mt5-small",
   "architectures": [
-    "T5ForConditionalGeneration"
+    "MT5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 1024,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -16,17 +16,17 @@
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
+  "model_type": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 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": "4.41.2",
   "use_cache": true,
-  "vocab_size": 50048
+  "vocab_size": 250112
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0eeaaa193d4f8ebcfac508d005c5d0251f79ed2adb9ee0d0343e44ea4e0edea
-size 1100445544
+oid sha256:d3000aee8d618670e7095d6ad5d223437cb645b0bd2c1fe8eb49f25d127608bc
+size 1200729512

runs/Jun27_17-29-08_65cf56c37630/events.out.tfevents.1719509349.65cf56c37630.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627b33efe4c007699ade20573d052556d6531afb0a21bb47aa3206c7cedf2d3b
+size 5900

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dccec0de49d1ae9e1e1729390e88f5d7780279a01d13aafe41ed73ddf5b23737
+oid sha256:4c52e35cf3e289ecb9e75ce6b47473d34c81d65d3209dadb4de8ab7bcce03e4a
 size 5304