Training in progress, epoch 1

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "allegro/plt5-small",
+  "architectures": [
+    "T5ForSequenceClassification"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "location",
+    "1": "neighbourhood",
+    "2": "composition",
+    "3": "affiliation",
+    "4": "alias",
+    "5": "nationality",
+    "6": "creator",
+    "7": "origin",
+    "8": "no relation"
+  },
+  "initializer_factor": 1,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "label2id": {
+    "affiliation": 3,
+    "alias": 4,
+    "composition": 2,
+    "creator": 6,
+    "location": 0,
+    "nationality": 5,
+    "neighbourhood": 1,
+    "no relation": 8,
+    "origin": 7
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0",
+  "use_cache": true,
+  "vocab_size": 50048
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1739a672e7409aa1d26e2f3ba2ad0c88acfd6caebb6e19a5211ca77566aa546b
+size 279884497

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a200b4b9d7106b32ea2340e5cd27033a5c03ae5ece9241ab6e1f685b938800b9
+size 1124950

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b53f2e1f2cd649e221488fbdf4967e7855712201333ff204afab640dd77bc2
+size 4091