tart for sentence-bert form

Browse files

Files changed (5) hide show

config.json +93 -0
model.safetensors +3 -0
special_tokens_map.json +7 -0
tokenizer_config.json +57 -0
vocab.txt +0 -0

config.json ADDED Viewed

	@@ -0,0 +1,93 @@

+{
+  "T": 0.1,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "augmentation": "none",
+  "beta1": 0.9,
+  "beta2": 0.98,
+  "bi_encoder": false,
+  "chunk_length": 256,
+  "classifier_dropout": null,
+  "continue_training": false,
+  "contrastive_mode": "moco",
+  "dropout": 0.1,
+  "eps": 1e-06,
+  "eval_data": [
+    "minilm_denoised_T0_32_datasets_fixed_instruction_unfollowing_dev.jsonl"
+  ],
+  "eval_datasets": [],
+  "eval_datasets_dir": "./",
+  "eval_freq": 2000,
+  "eval_normalize_text": false,
+  "freeze_ctx_encoder": false,
+  "global_rank": 0,
+  "hard_order": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "kd": false,
+  "label_smoothing": 0.0,
+  "layer_norm_eps": 1e-12,
+  "loading_mode": "split",
+  "local_rank": 0,
+  "log_freq": 100,
+  "loss_type": "kl",
+  "lower_case": false,
+  "lr": 1e-05,
+  "lr_min_ratio": 0.0,
+  "main_addr": "learnfair7603",
+  "main_port": 15972,
+  "max_position_embeddings": 512,
+  "maxload": null,
+  "moco_train_mode_encoder_k": false,
+  "model_path": "/checkpoint/akariasai/contriever/contriever_wiki2020_ft_msmarco/checkpoint/step-10000/",
+  "model_type": "bert",
+  "momentum": 0.999,
+  "n_context": 50,
+  "negative_ctxs": 5,
+  "negative_hard_min_idx": 0,
+  "negative_hard_ratio": 0.1,
+  "norm_doc": false,
+  "norm_query": false,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_workers": 5,
+  "optim": "adamw",
+  "output_dir": "/checkpoint/akariasai/contriever/instruction_unfollowing_full_data_from_new_checkpoints_5_0.1",
+  "pad_token_id": 0,
+  "per_gpu_batch_size": 16,
+  "per_gpu_eval_batch_size": 16,
+  "pooling": "average",
+  "position_embedding_type": "absolute",
+  "prob_augmentation": 0.0,
+  "projection_size": 768,
+  "queue_size": 65536,
+  "random_init": false,
+  "random_sort": false,
+  "ratio_max": 0.5,
+  "ratio_min": 0.1,
+  "retriever_model_id": "bert-base-uncased",
+  "rho": 0.05,
+  "sampling_coefficient": 0.0,
+  "save_freq": 2000,
+  "scheduler": "linear",
+  "score_function": "dot",
+  "seed": 0,
+  "temperature": 0.05,
+  "torch_dtype": "float32",
+  "total_steps": 20000,
+  "train_data": [
+    "minilm_denoised_T0_32_datasets_fixed_instruction_unfollowing_train.jsonl"
+  ],
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522,
+  "warmup_steps": 1000,
+  "weight_decay": 0.01,
+  "world_size": 64
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:75e996d6c724ad23a7caa6fc19a6da520f580248483c80f4e3586ecd0a613e6b
+size 437951328

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,57 @@

+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "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]"
+}

vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff