Add model

CERerankingEvaluator_train-eval_results.csv

@@ -0,0 +1,46 @@
+epoch,steps,MRR@10
+0,10000,0.5321865079365079
+0,20000,0.5443194444444444
+0,30000,0.5412202380952381
+0,40000,0.5455099206349207
+0,50000,0.5356011904761906
+0,60000,0.5489186507936508
+0,70000,0.5429027777777777
+0,80000,0.5415376984126984
+0,90000,0.5671150793650793
+0,100000,0.564468253968254
+0,110000,0.5689067460317461
+0,120000,0.5808531746031746
+0,130000,0.5699880952380952
+0,140000,0.5731904761904763
+0,150000,0.5595873015873016
+0,160000,0.5784087301587302
+0,170000,0.5478511904761905
+0,180000,0.584593253968254
+0,190000,0.5686249999999999
+0,200000,0.5640813492063492
+0,210000,0.4563948412698413
+0,220000,0.5706904761904762
+0,230000,0.5713253968253968
+0,240000,0.5590178571428571
+0,250000,0.5491289682539682
+0,260000,0.5668650793650793
+0,270000,0.563984126984127
+0,280000,0.579392857142857
+0,290000,0.5748214285714286
+0,300000,0.5593948412698413
+0,310000,0.567220238095238
+0,320000,0.5513511904761905
+0,330000,0.571515873015873
+0,340000,0.584936507936508
+0,350000,0.5599900793650794
+0,360000,0.562297619047619
+0,370000,0.5582440476190476
+0,380000,0.5552857142857143
+0,390000,0.5577619047619047
+0,400000,0.5660595238095238
+0,410000,0.5566210317460317
+0,420000,0.5886964285714287
+0,430000,0.5576805555555555
+0,440000,0.5634166666666667
+0,450000,0.5739027777777779

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "allegro/herbert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "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 sha256:61b9138ea5b0b6b4c8fb344ec4e9195e427703208bfe22b1add1e903b8ef0a0c
+size 497847413

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-base-cased",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": "/home/kwojtasik/.cache/huggingface/hub/models--allegro--herbert-base-cased/snapshots/50e33e0567be0c0b313832314c586e3df0dc2297/special_tokens_map.json",
+  "tokenizer_class": "HerbertTokenizer",
+  "unk_token": "<unk>"
+}