Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -1,3 +1,57 @@
----
-license: cc-by-nc-4.0
----
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "./output_final_bge/checkpoint-1600",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.40.2",
+    "pytorch": "2.2.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9c8d33d4a75ec79eee12edad70edc5fce3a49332604d5211ed5dbae30cee2e
+size 1340612432

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a10c6a1e7dcb1f7668fa8bdf0ff40ad9db6deb3cde8ca4a45d7d63696073ce
+size 2673063841

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a3d253909d46c30158737382971501f3e075fc208b9496101ccb69908bb3e0
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b868aac597c798c1e10948b0494bfd4d580309159a86f5157c162d97f12e295
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f5163efa1e323085d4bf282843646e078964b4458c8f2d77af9d64c8fc1b78
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2cf4e4983f11de7fe56883059b5665b571feff0b789baa0c2040ef90c10273
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf56f8480df876f1ec7b9b4e4321292cf1013e4b22ea52c61ec00b3234eef0e4
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcaae17ca290e776d450a6f6ce0a1fa1f2fa8d170d725a2a90b0d907cec52ca6
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12c03c99f53c9a7192230ae45206237f1a67e22b5bd0b9445c92d92dafd0473
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d3cdb156a69c8d9e49ea49bb834598bb7a8736c3c74923144fac6b98b9c1ea
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166c070a1eed4da8d7b039b8187bd37aff8165f700e5070e8a8d4c177a33ef4a
+size 1064

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

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 +1,57 @@
+{
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.940298507462687,
+  "eval_steps": 500,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 0.2015659064054489,
+      "learning_rate": 3.73134328358209e-06,
+      "loss": 0.1198,
+      "step": 100
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 0.16025546193122864,
+      "learning_rate": 7.46268656716418e-06,
+      "loss": 0.0693,
+      "step": 200
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 0.1018073558807373,
+      "learning_rate": 9.867330016583748e-06,
+      "loss": 0.0496,
+      "step": 300
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 0.100601427257061,
+      "learning_rate": 9.45273631840796e-06,
+      "loss": 0.0341,
+      "step": 400
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 0.0992753654718399,
+      "learning_rate": 9.038142620232173e-06,
+      "loss": 0.0216,
+      "step": 500
+    },
+    {
+      "epoch": 4.477611940298507,
+      "grad_norm": 0.08199736475944519,
+      "learning_rate": 8.623548922056384e-06,
+      "loss": 0.0187,
+      "step": 600
+    },
+    {
+      "epoch": 5.223880597014926,
+      "grad_norm": 0.08397415280342102,
+      "learning_rate": 8.208955223880599e-06,
+      "loss": 0.0166,
+      "step": 700
+    },
+    {
+      "epoch": 5.970149253731344,
+      "grad_norm": 0.13193649053573608,
+      "learning_rate": 7.79436152570481e-06,
+      "loss": 0.013,
+      "step": 800
+    },
+    {
+      "epoch": 6.7164179104477615,
+      "grad_norm": 0.06592541933059692,
+      "learning_rate": 7.3797678275290215e-06,
+      "loss": 0.0109,
+      "step": 900
+    },
+    {
+      "epoch": 7.462686567164179,
+      "grad_norm": 0.0223555825650692,
+      "learning_rate": 6.965174129353235e-06,
+      "loss": 0.0105,
+      "step": 1000
+    },
+    {
+      "epoch": 8.208955223880597,
+      "grad_norm": 0.021410465240478516,
+      "learning_rate": 6.550580431177447e-06,
+      "loss": 0.0098,
+      "step": 1100
+    },
+    {
+      "epoch": 8.955223880597014,
+      "grad_norm": 0.09453420341014862,
+      "learning_rate": 6.135986733001659e-06,
+      "loss": 0.0091,
+      "step": 1200
+    },
+    {
+      "epoch": 9.701492537313433,
+      "grad_norm": 0.06435668468475342,
+      "learning_rate": 5.721393034825871e-06,
+      "loss": 0.0084,
+      "step": 1300
+    },
+    {
+      "epoch": 10.447761194029852,
+      "grad_norm": 0.09910629689693451,
+      "learning_rate": 5.306799336650083e-06,
+      "loss": 0.0088,
+      "step": 1400
+    },
+    {
+      "epoch": 11.194029850746269,
+      "grad_norm": 0.03590040281414986,
+      "learning_rate": 4.892205638474296e-06,
+      "loss": 0.0071,
+      "step": 1500
+    },
+    {
+      "epoch": 11.940298507462687,
+      "grad_norm": 0.04040609300136566,
+      "learning_rate": 4.477611940298508e-06,
+      "loss": 0.0073,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 800,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da4c15b601d6f576dcd179cd8b78a831ce9b72d07fa3dd500671fb02c60c38b
+size 5240