Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "intfloat/e5-base-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "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": "4.43.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca13bc8aec989e9a3b0b6b2d6bd3b78a76b8e74af970bf11ed2439a43bd4107
+size 871298443

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c81c190a8516134f608abe751bea3649006264731f09971fe3c2e8d08b85c1
+size 437996607

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af266d39a02086d559fe6d90a4cfa581ac1cfc37b27094e60b7a900e81e4397
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fd3249d1f0c8f0a709ca7d23cca1ab18991f9e1d2cb993c67776daf1509756
+size 1465

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.0,
+  "eval_steps": 500,
+  "global_step": 165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 188.44981384277344,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 9.2983,
+      "step": 10
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 83.63673400878906,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 5.2395,
+      "step": 20
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 48.23883819580078,
+      "learning_rate": 9.595959595959597e-06,
+      "loss": 1.8746,
+      "step": 30
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 38.73075866699219,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.3606,
+      "step": 40
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 24.69623565673828,
+      "learning_rate": 8.585858585858587e-06,
+      "loss": 0.8711,
+      "step": 50
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 21.219209671020508,
+      "learning_rate": 8.08080808080808e-06,
+      "loss": 0.6953,
+      "step": 60
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 22.02012062072754,
+      "learning_rate": 7.5757575757575764e-06,
+      "loss": 0.6719,
+      "step": 70
+    },
+    {
+      "epoch": 7.2727272727272725,
+      "grad_norm": 25.328935623168945,
+      "learning_rate": 7.070707070707071e-06,
+      "loss": 0.5414,
+      "step": 80
+    },
+    {
+      "epoch": 8.181818181818182,
+      "grad_norm": 11.913020133972168,
+      "learning_rate": 6.565656565656566e-06,
+      "loss": 0.6012,
+      "step": 90
+    },
+    {
+      "epoch": 9.090909090909092,
+      "grad_norm": 15.604564666748047,
+      "learning_rate": 6.060606060606061e-06,
+      "loss": 0.4448,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 10.70217514038086,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.4277,
+      "step": 110
+    },
+    {
+      "epoch": 10.909090909090908,
+      "grad_norm": 14.791255950927734,
+      "learning_rate": 5.0505050505050515e-06,
+      "loss": 0.3909,
+      "step": 120
+    },
+    {
+      "epoch": 11.818181818181818,
+      "grad_norm": 15.777950286865234,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.316,
+      "step": 130
+    },
+    {
+      "epoch": 12.727272727272727,
+      "grad_norm": 12.46717643737793,
+      "learning_rate": 4.04040404040404e-06,
+      "loss": 0.3042,
+      "step": 140
+    },
+    {
+      "epoch": 13.636363636363637,
+      "grad_norm": 12.875164985656738,
+      "learning_rate": 3.5353535353535356e-06,
+      "loss": 0.3085,
+      "step": 150
+    },
+    {
+      "epoch": 14.545454545454545,
+      "grad_norm": 10.16179084777832,
+      "learning_rate": 3.0303030303030305e-06,
+      "loss": 0.2959,
+      "step": 160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a48750f2f2278bad81830ee1d8dc934b97498603cfa8727b5f7e82256e0335a
+size 5713