Training in progress, epoch 0

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/DOAN_4/mT5/t5-large",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 4096,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -17,9 +17,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57995ad781ab482844f8a340368a83010d743c5e045046fe97213b6aed40283
-size 2950848513
+oid sha256:878324a71bcbd3d703f00abbf7f6fd142e145520a861b7e2be78203094ea594f
+size 891702929

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 32,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 32
+      "Fixed": 512
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -104,7 +104,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f34a9346e28926dc8d07999a99a31c196a56a006e6cccf7f88de43f57d4ec47d
+oid sha256:e78922009462f5826379fe5f2a1e253c1eecc1ab7ddf2d45f79a3d47fe5c3eb3
 size 4091