First commit

artifact.metadata

@@ -0,0 +1,47 @@
+{
+    "nprobe": 2,
+    "ncandidates": 8192,
+    "index_path": null,
+    "nbits": 1,
+    "kmeans_niters": 20,
+    "similarity": "cosine",
+    "bsize": 8,
+    "accumsteps": 1,
+    "lr": 1e-5,
+    "maxsteps": 400000,
+    "save_every": null,
+    "resume": false,
+    "warmup": 20000,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 64,
+    "use_ib_negatives": true,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "dim": 128,
+    "doc_maxlen": 180,
+    "mask_punctuation": true,
+    "checkpoint": "\/future\/u\/okhattab\/root\/unit\/experiments\/2021.10\/none\/kld.v3.nway32.l2.ib\/checkpoints\/colbert-150000\/",
+    "triples": "\/future\/u\/okhattab\/root\/unit\/experiments\/2021.10\/downstream.distillation.round2.2_score\/round2.nway6.cosine.ib\/examples.64.json",
+    "collection": "\/future\/u\/okhattab\/data\/MSMARCO\/collection.tsv",
+    "queries": "\/future\/u\/okhattab\/data\/MSMARCO\/queries.train.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/future\/u\/okhattab\/root\/unit\/experiments",
+    "experiment": "2021.10",
+    "index_root": null,
+    "name": "kldR2.nway64.ib",
+    "rank": 0,
+    "nranks": 4,
+    "amp": true,
+    "gpus": 8,
+    "meta": {
+        "hostname": "future-hgx-1.stanford.edu",
+        "git_branch": "api_residual_compression3_KLD",
+        "git_hash": "62198f65e45bc7887eda4fdd57f9d3a103c72a7b",
+        "git_commit_datetime": "2021-10-29 07:05:32-07:00",
+        "current_datetime": "Oct 29, 2021 ;  9:05AM PDT (-0700)",
+        "cmd": "\/future\/u\/okhattab\/repos\/QolBERT2\/tests\/train_kldR2_nway64.py",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/future/u/okhattab/root/unit/experiments/2021.10/none/kld.v3.nway32.l2.ib/checkpoints/colbert-150000/",
+  "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": "4.10.0",
+  "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 sha256:26e4c2f9f95a3da4442252bb40d99e4fbfd098e733edac1d785c9937b8a278da
+size 438405935

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/future/u/okhattab/root/unit/experiments/2021.10/none/kld.v3.nway32.l2.ib/checkpoints/colbert-150000/", "tokenizer_class": "BertTokenizer"}