First model

CECorrelationEvaluator_sts-dev_results.csv

@@ -0,0 +1,5 @@
+epoch,steps,Pearson_Correlation,Spearman_Correlation
+0,-1,0.7617018772955358,0.7744871274110168
+1,-1,0.7965617373008531,0.809114329182002
+2,-1,0.8094413534982073,0.8137771508969135
+3,-1,0.8103337583392226,0.8128159936516876

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Musixmatch/umberto-commoncrawl-cased-v1",
+  "architectures": [
+    "CamembertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841fd18075afdd5ff75471603797be04304e651d5d05e4f8ebab5daa0a88da81
+size 442577261

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bf860fe6617aef791cff1de421f4e513a4df3049bfe9fdb7273bf69d444437
+size 793981

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "special_tokens_map_file": null, "name_or_path": "Musixmatch/umberto-commoncrawl-cased-v1", "tokenizer_class": "CamembertTokenizer"}