Training in progress, epoch 1

config.json

@@ -1,24 +1,24 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForSequenceClassification"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
   "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",
   "id2label": {
     "0": "needs service",
     "1": "provides service"
   },
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
+  "is_gated_act": false,
   "label2id": {
     "needs service": 0,
     "provides service": 1
@@ -63,7 +63,6 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.32.1",
   "use_cache": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525273fca55909238467bf65b85383843e0c64df9730d0bce3816645a9c03ced
-size 894080577
+oid sha256:f30e59617231419f166d99bfa80745781cf37afe6c54ca20d55f2abb3a3e40a1
+size 894072097

tokenizer_config.json

@@ -106,7 +106,6 @@
   "extra_ids": 100,
   "model_max_length": 512,
   "pad_token": "<pad>",
-  "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a367b6c635431d9e0a6713b4e5314f38c4915300d2679b4ed44d605d599d3a
+oid sha256:5c0216fe5f081098ffad20039a43e5f2ad784570b9e7bdbe8b8d157837bfe1e6
 size 4091