Add model

CERerankingEvaluator_train-eval_results.csv

@@ -0,0 +1,64 @@
+epoch,steps,MRR@10
+0,10000,0.5516428571428571
+0,20000,0.5693511904761904
+0,30000,0.5603849206349206
+0,40000,0.5249920634920635
+0,50000,0.501452380952381
+0,60000,0.5223412698412698
+0,70000,0.019930555555555552
+0,80000,0.1
+0,90000,0.5030555555555555
+0,100000,0.985
+0,110000,0.24
+0,120000,0.995
+0,130000,0.135
+0,140000,0.06330555555555556
+0,150000,0.5398055555555555
+0,160000,0.785
+0,170000,0.3506666666666666
+0,180000,0.1963452380952381
+0,190000,0.08798611111111111
+0,200000,0.8279166666666665
+0,210000,0.4415833333333333
+0,220000,1.0
+0,230000,0.3698095238095238
+0,240000,0.43
+0,250000,0.35
+0,260000,0.06287698412698413
+0,270000,0.99
+0,280000,0.885
+0,290000,1.0
+0,300000,0.945
+0,310000,0.985
+0,320000,0.7991666666666666
+0,330000,1.0
+0,340000,0.43
+0,350000,0.175
+0,360000,0.9225
+0,370000,1.0
+0,380000,0.575
+0,390000,1.0
+0,400000,0.205
+0,410000,1.0
+0,420000,0.5507500000000001
+0,430000,1.0
+0,440000,1.0
+0,450000,1.0
+0,460000,0.41
+0,470000,0.995
+0,480000,1.0
+0,490000,0.06780158730158731
+0,500000,0.4
+0,510000,0.77
+0,520000,1.0
+0,530000,0.8276666666666666
+0,540000,1.0
+0,550000,0.5896666666666667
+0,560000,0.9925
+0,570000,0.45
+0,580000,0.8
+0,590000,1.0
+0,600000,0.21767063492063493
+0,610000,0.9591666666666667
+0,620000,1.0
+0,-1,0.995

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "allegro/herbert-large-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "HerbertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e7d887dcbc975078374c8e4c3d8131b9e7ae63f21330096c111a784989c0dd
+size 1420500597

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lowercase_and_remove_accent": false,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "allegro/herbert-large-cased",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--allegro--herbert-large-cased/snapshots/8d0fa3bc0566c3a332bec0d471c8d8c37b5cbb90/special_tokens_map.json",
+  "tokenizer_class": "HerbertTokenizer",
+  "unk_token": "<unk>"
+}