Training in progress, step 700

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval/Information-Retrieval_evaluation_dev-claims-ir_results.csv

@@ -0,0 +1,10 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+0.3875968992248062,100,0.22077922077922077,0.4155844155844156,0.512987012987013,0.5974025974025974,0.22077922077922077,0.08701298701298703,0.1818181818181818,0.22012987012987018,0.15064935064935067,0.2786796536796537,0.09870129870129869,0.35725108225108226,0.34208410636982073,0.28201284876777993,0.22661376568740838
+0.7751937984496124,200,0.24675324675324675,0.44155844155844154,0.5584415584415584,0.6363636363636364,0.24675324675324675,0.10205627705627707,0.20346320346320346,0.2158008658008658,0.161038961038961,0.30043290043290044,0.10454545454545452,0.3747835497835498,0.36875386518243675,0.30063969751074027,0.24193309775554697
+1.1627906976744187,300,0.2597402597402597,0.44805194805194803,0.5454545454545454,0.6558441558441559,0.2597402597402597,0.09945887445887445,0.2056277056277056,0.23463203463203464,0.16103896103896106,0.30119047619047623,0.10519480519480519,0.3714285714285714,0.38059678416821285,0.30242021544786507,0.24391300259289583
+1.550387596899225,400,0.2597402597402597,0.487012987012987,0.551948051948052,0.6493506493506493,0.2597402597402597,0.0958874458874459,0.21428571428571427,0.24134199134199139,0.16233766233766234,0.2981601731601732,0.10584415584415585,0.3734848484848485,0.389831993403422,0.3047565545473863,0.24235817248799615
+1.937984496124031,500,0.2727272727272727,0.4805194805194805,0.5584415584415584,0.6623376623376623,0.2727272727272727,0.10324675324675325,0.21212121212121215,0.24080086580086582,0.161038961038961,0.2983766233766234,0.10714285714285714,0.38322510822510825,0.3966166769738198,0.3105041900625576,0.24549710155822038
+2.3255813953488373,600,0.2662337662337662,0.461038961038961,0.538961038961039,0.6558441558441559,0.2662337662337662,0.10335497835497835,0.20129870129870128,0.22316017316017311,0.15714285714285714,0.2844155844155844,0.10974025974025974,0.383008658008658,0.3863404452690168,0.3063498984162777,0.24028925887104047
+2.7131782945736433,700,0.2922077922077922,0.5,0.564935064935065,0.6818181818181818,0.2922077922077922,0.1156926406926407,0.22077922077922077,0.23917748917748916,0.16623376623376623,0.2989177489177489,0.11168831168831168,0.38625541125541124,0.41154658833230284,0.319416178754881,0.25606131954388667
+2.7131782945736433,700,0.2922077922077922,0.5,0.564935064935065,0.6818181818181818,0.2922077922077922,0.1156926406926407,0.22077922077922077,0.23917748917748916,0.16623376623376623,0.2989177489177489,0.11168831168831168,0.38625541125541124,0.41154658833230284,0.319416178754881,0.25606131954388667
+2.7131782945736433,700,0.2922077922077922,0.5,0.564935064935065,0.6818181818181818,0.2922077922077922,0.1156926406926407,0.22077922077922077,0.23917748917748916,0.16623376623376623,0.2989177489177489,0.11168831168831168,0.38625541125541124,0.41154658833230284,0.319416178754881,0.25606131954388667

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a6ce8e51ce66fa285a6397fd6965f51531b15acbd09e49bb4ef8383864595e
+size 133462128

runs/May16_02-22-29_Bookbot-GPU1/events.out.tfevents.1747326151.Bookbot-GPU1.681169.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b20525146545dac86fce45cb822cfe50d57788f880324c75ba8557c5c44cbab
+size 5941

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78699997a96e85102e845900e2dfaaa5573503910d046f19d8b36c6812142a3e
+size 6097