Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "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_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1024, "out_features": 1024, "bias": true, "activation_function": "torch.nn.modules.linear.Identity"}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda75013d1a16ef6b0a215d52de37fd50df3f67904ccc294aa0bcab4e267a71f
+size 4198560

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "NewModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "dunzhang/stella_en_400M_v5--configuration.NewConfig",
+    "AutoModel": "dunzhang/stella_en_400M_v5--modeling.NewModel"
+  },
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pack_qkv": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "ntk"
+  },
+  "rope_theta": 160000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "type_vocab_size": 2,
+  "unpad_inputs": true,
+  "use_memory_efficient_attention": true,
+  "vocab_size": 30528
+}

config_sentence_transformers.json

@@ -0,0 +1,13 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.50.0",
+    "pytorch": "2.5.1"
+  },
+  "prompts": {
+    "s2p_query": "Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: ",
+    "s2s_query": "Instruct: Retrieve semantically similar text.\nQuery: "
+  },
+  "default_prompt_name": "s2p_query",
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816d11097ca3b011bee4def5c99f257969c4be81431d04761dec18714a27a7e9
+size 1736585680

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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9140c6001501ef659f2ea2e9edb02fcccced05fa47725e0e0801d507779f63f
+size 3481735546

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291d8d2e0322ce6c681c57ea7bdbac7532824c813c0c3ed39d298aa21579eaec
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e16f9b588a924244f9969cf04623d60ccadeca602ecde0a29252c4283797a6
+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 +1,63 @@
+{
+  "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_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 8000,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 10,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08928571428571429,
+      "grad_norm": 4.220582485198975,
+      "learning_rate": 1.8545454545454545e-05,
+      "loss": 0.5247,
+      "step": 10
+    },
+    {
+      "epoch": 0.08928571428571429,
+      "eval_cosine_accuracy@10": 0.9232,
+      "eval_cosine_map@10": 0.7928948412698413,
+      "eval_cosine_mrr@10": 0.7928948412698423,
+      "eval_cosine_ndcg@10": 0.824742899849948,
+      "eval_cosine_ndcg@5": 0.812892030900665,
+      "eval_cosine_precision@10": 0.09232,
+      "eval_cosine_recall@10": 0.9232,
+      "eval_runtime": 1282.162,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 2.7735073566436768,
+      "learning_rate": 1.672727272727273e-05,
+      "loss": 0.2625,
+      "step": 20
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "eval_cosine_accuracy@10": 0.9378,
+      "eval_cosine_map@10": 0.8144230952380952,
+      "eval_cosine_mrr@10": 0.814423095238096,
+      "eval_cosine_ndcg@10": 0.8445932268348066,
+      "eval_cosine_ndcg@5": 0.8336211588077829,
+      "eval_cosine_precision@10": 0.09378,
+      "eval_cosine_recall@10": 0.9378,
+      "eval_runtime": 1288.0613,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 2.932309627532959,
+      "learning_rate": 1.4909090909090911e-05,
+      "loss": 0.2159,
+      "step": 30
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "eval_cosine_accuracy@10": 0.9396,
+      "eval_cosine_map@10": 0.818978492063492,
+      "eval_cosine_mrr@10": 0.8189784920634932,
+      "eval_cosine_ndcg@10": 0.8484828966348447,
+      "eval_cosine_ndcg@5": 0.8380117690520594,
+      "eval_cosine_precision@10": 0.09395999999999999,
+      "eval_cosine_recall@10": 0.9396,
+      "eval_runtime": 1308.2277,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 2.4678637981414795,
+      "learning_rate": 1.3090909090909092e-05,
+      "loss": 0.1849,
+      "step": 40
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "eval_cosine_accuracy@10": 0.9414,
+      "eval_cosine_map@10": 0.8186321428571428,
+      "eval_cosine_mrr@10": 0.8186321428571437,
+      "eval_cosine_ndcg@10": 0.8486552385975977,
+      "eval_cosine_ndcg@5": 0.8377794199819455,
+      "eval_cosine_precision@10": 0.09413999999999999,
+      "eval_cosine_recall@10": 0.9414,
+      "eval_runtime": 1281.8705,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "grad_norm": 2.1064774990081787,
+      "learning_rate": 1.1272727272727272e-05,
+      "loss": 0.2149,
+      "step": 50
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "eval_cosine_accuracy@10": 0.942,
+      "eval_cosine_map@10": 0.821033253968254,
+      "eval_cosine_mrr@10": 0.8210332539682544,
+      "eval_cosine_ndcg@10": 0.8505642735409379,
+      "eval_cosine_ndcg@5": 0.8397014659657067,
+      "eval_cosine_precision@10": 0.09419999999999999,
+      "eval_cosine_recall@10": 0.942,
+      "eval_runtime": 1275.955,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 3.9118406772613525,
+      "learning_rate": 9.454545454545456e-06,
+      "loss": 0.1538,
+      "step": 60
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "eval_cosine_accuracy@10": 0.9438,
+      "eval_cosine_map@10": 0.8241567460317459,
+      "eval_cosine_mrr@10": 0.8241567460317474,
+      "eval_cosine_ndcg@10": 0.8533755474292473,
+      "eval_cosine_ndcg@5": 0.8428576369899689,
+      "eval_cosine_precision@10": 0.09437999999999999,
+      "eval_cosine_recall@10": 0.9438,
+      "eval_runtime": 1276.4632,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 2.9728310108184814,
+      "learning_rate": 7.636363636363638e-06,
+      "loss": 0.1617,
+      "step": 70
+    },
+    {
+      "epoch": 0.625,
+      "eval_cosine_accuracy@10": 0.9448,
+      "eval_cosine_map@10": 0.8254956349206349,
+      "eval_cosine_mrr@10": 0.8254956349206359,
+      "eval_cosine_ndcg@10": 0.8547094156469267,
+      "eval_cosine_ndcg@5": 0.8446210346982691,
+      "eval_cosine_precision@10": 0.09448,
+      "eval_cosine_recall@10": 0.9448,
+      "eval_runtime": 1274.4263,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 3.048156261444092,
+      "learning_rate": 5.8181818181818185e-06,
+      "loss": 0.1463,
+      "step": 80
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "eval_cosine_accuracy@10": 0.946,
+      "eval_cosine_map@10": 0.8287913492063491,
+      "eval_cosine_mrr@10": 0.8287913492063491,
+      "eval_cosine_ndcg@10": 0.8574792669591755,
+      "eval_cosine_ndcg@5": 0.8479235486804159,
+      "eval_cosine_precision@10": 0.09459999999999999,
+      "eval_cosine_recall@10": 0.946,
+      "eval_runtime": 1276.0558,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "grad_norm": 2.149644374847412,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1626,
+      "step": 90
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "eval_cosine_accuracy@10": 0.9468,
+      "eval_cosine_map@10": 0.8308209523809524,
+      "eval_cosine_mrr@10": 0.830820952380953,
+      "eval_cosine_ndcg@10": 0.8592108288677366,
+      "eval_cosine_ndcg@5": 0.8496323082056843,
+      "eval_cosine_precision@10": 0.09468,
+      "eval_cosine_recall@10": 0.9468,
+      "eval_runtime": 1276.4978,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 2.9060189723968506,
+      "learning_rate": 2.181818181818182e-06,
+      "loss": 0.1334,
+      "step": 100
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "eval_cosine_accuracy@10": 0.9468,
+      "eval_cosine_map@10": 0.831592142857143,
+      "eval_cosine_mrr@10": 0.8315921428571436,
+      "eval_cosine_ndcg@10": 0.8597814254203698,
+      "eval_cosine_ndcg@5": 0.8500116553923436,
+      "eval_cosine_precision@10": 0.09468,
+      "eval_cosine_recall@10": 0.9468,
+      "eval_runtime": 1276.5741,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.9821428571428571,
+      "grad_norm": 2.804260730743408,
+      "learning_rate": 3.6363636363636366e-07,
+      "loss": 0.168,
+      "step": 110
+    },
+    {
+      "epoch": 0.9821428571428571,
+      "eval_cosine_accuracy@10": 0.9466,
+      "eval_cosine_map@10": 0.8322816666666666,
+      "eval_cosine_mrr@10": 0.8322816666666671,
+      "eval_cosine_ndcg@10": 0.8602810144357889,
+      "eval_cosine_ndcg@5": 0.8507439067474944,
+      "eval_cosine_precision@10": 0.09466,
+      "eval_cosine_recall@10": 0.9466,
+      "eval_runtime": 1276.7849,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a64bf6bdb8005bf4f3b834eb43316cadec8ca8480d2a8db974112ca65c5f89
+size 5560