adddign model files

checkpoints/colbert-10000/artifact.metadata

@@ -0,0 +1,57 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 4,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 16,
+    "accumsteps": 1,
+    "lr": 5e-6,
+    "maxsteps": 500000,
+    "save_every": 19854,
+    "warmup": 19854,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "ColBERT-mmacro-de-1M",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "dbmdz\/bert-base-german-cased",
+    "triples": "\/kaggle\/input\/mmarco-de-10m\/triples.train.colbert.jsonl",
+    "collection": "\/kaggle\/input\/mmarco-de-10m\/corpus.train.colbert.tsv",
+    "queries": "\/kaggle\/input\/mmarco-de-10m\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2024-02\/26\/08.29.22",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "faa3efed3289",
+        "current_datetime": "Feb 26, 2024 ;  9:45AM UTC (+0000)",
+        "cmd": "\/opt\/conda\/lib\/python3.10\/site-packages\/ipykernel_launcher.py -f \/tmp\/tmpclobcmzl.json --HistoryManager.hist_file=:memory:",
+        "version": "colbert-v0.4"
+    }
+}

checkpoints/colbert-10000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

checkpoints/colbert-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb3580978eb4f8c8d6078a4bf7fbe57ed91424f0225d53af02447ca1cab90be
+size 440127384

checkpoints/colbert-10000/special_tokens_map.json

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

checkpoints/colbert-10000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoints/colbert-20000/artifact.metadata

@@ -0,0 +1,57 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 4,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 16,
+    "accumsteps": 1,
+    "lr": 5e-6,
+    "maxsteps": 500000,
+    "save_every": 19854,
+    "warmup": 19854,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "ColBERT-mmacro-de-1M",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "dbmdz\/bert-base-german-cased",
+    "triples": "\/kaggle\/input\/mmarco-de-10m\/triples.train.colbert.jsonl",
+    "collection": "\/kaggle\/input\/mmarco-de-10m\/corpus.train.colbert.tsv",
+    "queries": "\/kaggle\/input\/mmarco-de-10m\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2024-02\/26\/08.29.22",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "faa3efed3289",
+        "current_datetime": "Feb 26, 2024 ; 11:00AM UTC (+0000)",
+        "cmd": "\/opt\/conda\/lib\/python3.10\/site-packages\/ipykernel_launcher.py -f \/tmp\/tmpclobcmzl.json --HistoryManager.hist_file=:memory:",
+        "version": "colbert-v0.4"
+    }
+}

checkpoints/colbert-20000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

checkpoints/colbert-20000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e01adf4d129f593b44d596b095fa9c4f510350c569d1a1ca23ebe0ac2fdc4c
+size 440127384

checkpoints/colbert-20000/special_tokens_map.json

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

checkpoints/colbert-20000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoints/colbert-25000/artifact.metadata

@@ -0,0 +1,57 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 4,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 16,
+    "accumsteps": 1,
+    "lr": 5e-6,
+    "maxsteps": 500000,
+    "save_every": 19854,
+    "warmup": 19854,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "ColBERT-mmacro-de-1M",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "dbmdz\/bert-base-german-cased",
+    "triples": "\/kaggle\/input\/mmarco-de-10m\/triples.train.colbert.jsonl",
+    "collection": "\/kaggle\/input\/mmarco-de-10m\/corpus.train.colbert.tsv",
+    "queries": "\/kaggle\/input\/mmarco-de-10m\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2024-02\/26\/08.29.22",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "faa3efed3289",
+        "current_datetime": "Feb 26, 2024 ; 11:37AM UTC (+0000)",
+        "cmd": "\/opt\/conda\/lib\/python3.10\/site-packages\/ipykernel_launcher.py -f \/tmp\/tmpclobcmzl.json --HistoryManager.hist_file=:memory:",
+        "version": "colbert-v0.4"
+    }
+}

checkpoints/colbert-25000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

checkpoints/colbert-25000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8a1fc62c368a71f0078e9212d27deb2167e67d9d3d3265f62d0d40e8d322c6
+size 440127384

checkpoints/colbert-25000/special_tokens_map.json

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

checkpoints/colbert-25000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoints/colbert-30000/artifact.metadata

@@ -0,0 +1,57 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 4,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 16,
+    "accumsteps": 1,
+    "lr": 5e-6,
+    "maxsteps": 500000,
+    "save_every": 19854,
+    "warmup": 19854,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "ColBERT-mmacro-de-1M",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "dbmdz\/bert-base-german-cased",
+    "triples": "\/kaggle\/input\/mmarco-de-10m\/triples.train.colbert.jsonl",
+    "collection": "\/kaggle\/input\/mmarco-de-10m\/corpus.train.colbert.tsv",
+    "queries": "\/kaggle\/input\/mmarco-de-10m\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2024-02\/26\/08.29.22",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "faa3efed3289",
+        "current_datetime": "Feb 26, 2024 ; 12:15PM UTC (+0000)",
+        "cmd": "\/opt\/conda\/lib\/python3.10\/site-packages\/ipykernel_launcher.py -f \/tmp\/tmpclobcmzl.json --HistoryManager.hist_file=:memory:",
+        "version": "colbert-v0.4"
+    }
+}

checkpoints/colbert-30000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

checkpoints/colbert-30000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d735e1eb9985078b15c23c699ce2e9e26c6110be2feb7dff2cd9d9e367cca4e3
+size 440127384

checkpoints/colbert-30000/special_tokens_map.json

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

checkpoints/colbert-30000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoints/colbert-32000/artifact.metadata

@@ -0,0 +1,57 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 4,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 16,
+    "accumsteps": 1,
+    "lr": 5e-6,
+    "maxsteps": 500000,
+    "save_every": 19854,
+    "warmup": 19854,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "ColBERT-mmacro-de-1M",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "dbmdz\/bert-base-german-cased",
+    "triples": "\/kaggle\/input\/mmarco-de-10m\/triples.train.colbert.jsonl",
+    "collection": "\/kaggle\/input\/mmarco-de-10m\/corpus.train.colbert.tsv",
+    "queries": "\/kaggle\/input\/mmarco-de-10m\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2024-02\/26\/08.29.22",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "faa3efed3289",
+        "current_datetime": "Feb 26, 2024 ; 12:29PM UTC (+0000)",
+        "cmd": "\/opt\/conda\/lib\/python3.10\/site-packages\/ipykernel_launcher.py -f \/tmp\/tmpclobcmzl.json --HistoryManager.hist_file=:memory:",
+        "version": "colbert-v0.4"
+    }
+}

checkpoints/colbert-32000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

checkpoints/colbert-32000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef942611b86abbffc5228864cda441085e2299c71f3c9db94ef27cf41125ebf
+size 440127384

checkpoints/colbert-32000/special_tokens_map.json

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

checkpoints/colbert-32000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoints/colbert-40000/artifact.metadata

@@ -0,0 +1,57 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 4,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 16,
+    "accumsteps": 1,
+    "lr": 5e-6,
+    "maxsteps": 500000,
+    "save_every": 19854,
+    "warmup": 19854,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "ColBERT-mmacro-de-1M",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "dbmdz\/bert-base-german-cased",
+    "triples": "\/kaggle\/input\/mmarco-de-10m\/triples.train.colbert.jsonl",
+    "collection": "\/kaggle\/input\/mmarco-de-10m\/corpus.train.colbert.tsv",
+    "queries": "\/kaggle\/input\/mmarco-de-10m\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2024-02\/26\/08.29.22",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "faa3efed3289",
+        "current_datetime": "Feb 26, 2024 ;  1:29PM UTC (+0000)",
+        "cmd": "\/opt\/conda\/lib\/python3.10\/site-packages\/ipykernel_launcher.py -f \/tmp\/tmpclobcmzl.json --HistoryManager.hist_file=:memory:",
+        "version": "colbert-v0.4"
+    }
+}

checkpoints/colbert-40000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

checkpoints/colbert-40000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50f7606fbd4a65b7f623daf363431a736c66efc938fae9277e838afb07e5008
+size 440127384

checkpoints/colbert-40000/special_tokens_map.json

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

checkpoints/colbert-40000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoints/colbert-50000/artifact.metadata

@@ -0,0 +1,57 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 4,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 16,
+    "accumsteps": 1,
+    "lr": 5e-6,
+    "maxsteps": 500000,
+    "save_every": 19854,
+    "warmup": 19854,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "ColBERT-mmacro-de-1M",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "dbmdz\/bert-base-german-cased",
+    "triples": "\/kaggle\/input\/mmarco-de-10m\/triples.train.colbert.jsonl",
+    "collection": "\/kaggle\/input\/mmarco-de-10m\/corpus.train.colbert.tsv",
+    "queries": "\/kaggle\/input\/mmarco-de-10m\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2024-02\/26\/08.29.22",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "faa3efed3289",
+        "current_datetime": "Feb 26, 2024 ;  2:44PM UTC (+0000)",
+        "cmd": "\/opt\/conda\/lib\/python3.10\/site-packages\/ipykernel_launcher.py -f \/tmp\/tmpclobcmzl.json --HistoryManager.hist_file=:memory:",
+        "version": "colbert-v0.4"
+    }
+}

checkpoints/colbert-50000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

checkpoints/colbert-50000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5399b46a58a25da805e1f487f621c85a59c72271451cdefa0bf212e8232c60e
+size 440127384

checkpoints/colbert-50000/special_tokens_map.json

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

checkpoints/colbert-50000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}