Upload T5ForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/outputs/epoch-13-train-loss-0.1418-val-loss-0.1954",
+  "_name_or_path": "/content/drive/MyDrive/ML/frame-semantic-transformer/framenet/small/final-2/epoch=36--train_loss=0.0481--val_loss=0.2159--val_frame_classification_f1=0.8726746589499793--val_args_extraction_f1=0.7550093507881379--val_trigger_identification_f1=0.7518560179977504",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -7,11 +7,14 @@
   "d_kv": 64,
   "d_model": 512,
   "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "relu",
+  "inference_loader": "Framenet17InferenceLoader",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
+  "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
@@ -52,7 +55,8 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.19.2",
+  "training_loader": "Framenet17TrainingLoader",
+  "transformers_version": "4.26.1",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:700556231489b8eb5bc6ed196a78c5468808d4ee42074b714673003343130c44
-size 242068411
+oid sha256:d8aeaebb417883d4c941d56919e39ff9ebe3c5104b236b3ba9e33795cde95935
+size 242069785