Model artifacts

artifact.metadata

@@ -0,0 +1,54 @@
+{
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "index_path": null,
+    "nbits": 1,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 32,
+    "accumsteps": 1,
+    "lr": 3e-6,
+    "maxsteps": 500000,
+    "save_every": null,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "epochs": 1,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 220,
+    "mask_punctuation": true,
+    "checkpoint": "bert-base-uncased",
+    "triples": "\/workdisk\/nosnap\/datasets\/open_domain_data\/colbert\/nq-triplets_train.json",
+    "collection": "\/workdisk\/nosnap\/datasets\/open_domain_data\/colbert\/collection.tsv",
+    "queries": "\/workdisk\/nosnap\/datasets\/open_domain_data\/colbert\/nq-queries_train.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/workdisk\/code\/colbertv2\/experiments",
+    "experiment": "wiki-nq",
+    "index_root": null,
+    "name": "2022-11\/08\/22.14.30",
+    "rank": 0,
+    "nranks": 4,
+    "amp": true,
+    "gpus": 4,
+    "wandb_project": "colbert_v2",
+    "meta": {
+        "hostname": "pizsak-research-tc2tt-zppl2",
+        "git_branch": "peter-enable-training",
+        "git_hash": "80838542bbe7e08d5e37985f54b5ec81636a4913",
+        "git_commit_datetime": "2022-11-08 22:21:50+02:00",
+        "current_datetime": "Nov 09, 2022 ;  8:00PM IST (+0200)",
+        "cmd": "train_model.py",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.21.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1bec40b1017382ccc95108076cb8e47ed7084122f0ec74107f1ccc1a2e6d11
+size 438392879

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}