Add BAAI-bge-reranker-base-E5-Pairwise

Upload fine-tuned rerankers for BioASQ 14B

Co-authored-by: André Ribeiro <andrepedro2004@hotmail.com>
Co-authored-by: Rúben Garrido <rubengarrido@ua.pt>

.gitattributes

@@ -37,3 +37,4 @@ BAAI-bge-reranker-base-E2-S1-Mpairwise-FullDataTrue/tokenizer.json filter=lfs di
 BAAI-bge-reranker-v2-m3-E2-S1-Mpairwise-FullDataTrue/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 nvidia-llama-nemotron-rerank-1b-v2-E2-S4-Mmulti_neg_pairwise-Linfonce-FullData/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 nvidia-llama-nemotron-rerank-1b-v2_llama-E2-Pairwise/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+BAAI-bge-reranker-base-E5-Pairwise/tokenizer.json filter=lfs diff=lfs merge=lfs -text

BAAI-bge-reranker-base-E5-Pairwise/config.json

@@ -0,0 +1,36 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

BAAI-bge-reranker-base-E5-Pairwise/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2659cf013cf63322374d09b3b8f0e8d1a4715efc9c81ee2b741d1eedacaeb15c
+size 556113154

BAAI-bge-reranker-base-E5-Pairwise/ranx_results.json

@@ -0,0 +1,31 @@
+{
+    "model": "BAAI-bge-reranker-base",
+    "val_files": [
+        "../../data/val_data/13B1_golden.json",
+        "../../data/val_data/13B2_golden.json"
+    ],
+    "total": {
+        "ndcg@5": 0.7738414519321398,
+        "mrr": 0.8785050541955911,
+        "recall@10": 0.49848064854853713,
+        "recall@100": 0.9524249018162971,
+        "map@10": 0.43007114148968917,
+        "map-bioasq@10": 0.6686498599439776
+    },
+    "13B1_golden.json": {
+        "ndcg@5": 0.7035797327316681,
+        "mrr": 0.8343490439654123,
+        "recall@10": 0.4810022020196116,
+        "recall@100": 0.9549918571424268,
+        "map@10": 0.3931982316560657,
+        "map-bioasq@10": 0.5857215478784106
+    },
+    "13B2_golden.json": {
+        "ndcg@5": 0.8441031711326116,
+        "mrr": 0.9226610644257702,
+        "recall@10": 0.5159590950774625,
+        "recall@100": 0.949857946490167,
+        "map@10": 0.4669440513233126,
+        "map-bioasq@10": 0.7515781720095446
+    }
+}

BAAI-bge-reranker-base-E5-Pairwise/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0ea9553fbce9b918907144d32372eda17b22834aaa9222bfe94740d8dbfe79
+size 16781580

BAAI-bge-reranker-base-E5-Pairwise/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

BAAI-bge-reranker-base-E5-Pairwise/trainer_state.json

@@ -0,0 +1,963 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 6375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 14.5625,
+      "learning_rate": 1.9846274509803922e-05,
+      "loss": 0.6174153900146484,
+      "step": 50
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 9.5,
+      "learning_rate": 1.9689411764705883e-05,
+      "loss": 0.4893218612670898,
+      "step": 100
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 10.0,
+      "learning_rate": 1.9532549019607844e-05,
+      "loss": 0.4546327590942383,
+      "step": 150
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 8.0,
+      "learning_rate": 1.9375686274509805e-05,
+      "loss": 0.4748759078979492,
+      "step": 200
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.9218823529411766e-05,
+      "loss": 0.43912487030029296,
+      "step": 250
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 6.59375,
+      "learning_rate": 1.9061960784313727e-05,
+      "loss": 0.41661514282226564,
+      "step": 300
+    },
+    {
+      "epoch": 0.27450980392156865,
+      "grad_norm": 5.875,
+      "learning_rate": 1.8905098039215688e-05,
+      "loss": 0.40662124633789065,
+      "step": 350
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 9.375,
+      "learning_rate": 1.874823529411765e-05,
+      "loss": 0.4479010009765625,
+      "step": 400
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.8591372549019607e-05,
+      "loss": 0.4077738189697266,
+      "step": 450
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 7.78125,
+      "learning_rate": 1.843450980392157e-05,
+      "loss": 0.394873161315918,
+      "step": 500
+    },
+    {
+      "epoch": 0.43137254901960786,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.8277647058823532e-05,
+      "loss": 0.41435577392578127,
+      "step": 550
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 7.84375,
+      "learning_rate": 1.8120784313725493e-05,
+      "loss": 0.4017145538330078,
+      "step": 600
+    },
+    {
+      "epoch": 0.5098039215686274,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.796392156862745e-05,
+      "loss": 0.3824382019042969,
+      "step": 650
+    },
+    {
+      "epoch": 0.5490196078431373,
+      "grad_norm": 6.0625,
+      "learning_rate": 1.7807058823529412e-05,
+      "loss": 0.36567184448242185,
+      "step": 700
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 6.03125,
+      "learning_rate": 1.7650196078431373e-05,
+      "loss": 0.3558076477050781,
+      "step": 750
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 7.1875,
+      "learning_rate": 1.7493333333333334e-05,
+      "loss": 0.3840081787109375,
+      "step": 800
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 7.78125,
+      "learning_rate": 1.7336470588235295e-05,
+      "loss": 0.38639110565185547,
+      "step": 850
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.625,
+      "learning_rate": 1.7179607843137256e-05,
+      "loss": 0.3746152114868164,
+      "step": 900
+    },
+    {
+      "epoch": 0.7450980392156863,
+      "grad_norm": 8.0,
+      "learning_rate": 1.7022745098039217e-05,
+      "loss": 0.3704909515380859,
+      "step": 950
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 6.09375,
+      "learning_rate": 1.6865882352941178e-05,
+      "loss": 0.34691093444824217,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 8.5,
+      "learning_rate": 1.670901960784314e-05,
+      "loss": 0.3644472885131836,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8627450980392157,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.65521568627451e-05,
+      "loss": 0.39305294036865235,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9019607843137255,
+      "grad_norm": 5.21875,
+      "learning_rate": 1.639529411764706e-05,
+      "loss": 0.35348007202148435,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 4.84375,
+      "learning_rate": 1.6238431372549022e-05,
+      "loss": 0.37386600494384764,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 8.4375,
+      "learning_rate": 1.608156862745098e-05,
+      "loss": 0.3627701187133789,
+      "step": 1250
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.36879512667655945,
+      "eval_runtime": 0.7293,
+      "eval_samples_per_second": 230.356,
+      "eval_steps_per_second": 4.113,
+      "step": 1275
+    },
+    {
+      "epoch": 1.0196078431372548,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.592470588235294e-05,
+      "loss": 0.3407266998291016,
+      "step": 1300
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 7.875,
+      "learning_rate": 1.5767843137254902e-05,
+      "loss": 0.3742559814453125,
+      "step": 1350
+    },
+    {
+      "epoch": 1.0980392156862746,
+      "grad_norm": 6.375,
+      "learning_rate": 1.5610980392156866e-05,
+      "loss": 0.34328346252441405,
+      "step": 1400
+    },
+    {
+      "epoch": 1.1372549019607843,
+      "grad_norm": 7.0625,
+      "learning_rate": 1.5454117647058824e-05,
+      "loss": 0.33097625732421876,
+      "step": 1450
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 6.78125,
+      "learning_rate": 1.5297254901960785e-05,
+      "loss": 0.361868782043457,
+      "step": 1500
+    },
+    {
+      "epoch": 1.215686274509804,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.5140392156862746e-05,
+      "loss": 0.3421764373779297,
+      "step": 1550
+    },
+    {
+      "epoch": 1.2549019607843137,
+      "grad_norm": 10.0,
+      "learning_rate": 1.4983529411764707e-05,
+      "loss": 0.36190574645996093,
+      "step": 1600
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 7.65625,
+      "learning_rate": 1.4826666666666666e-05,
+      "loss": 0.35303070068359377,
+      "step": 1650
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 6.15625,
+      "learning_rate": 1.4669803921568627e-05,
+      "loss": 0.3698406982421875,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 8.9375,
+      "learning_rate": 1.451294117647059e-05,
+      "loss": 0.3683797454833984,
+      "step": 1750
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 8.3125,
+      "learning_rate": 1.4356078431372551e-05,
+      "loss": 0.34567497253417967,
+      "step": 1800
+    },
+    {
+      "epoch": 1.4509803921568627,
+      "grad_norm": 5.625,
+      "learning_rate": 1.419921568627451e-05,
+      "loss": 0.3647406768798828,
+      "step": 1850
+    },
+    {
+      "epoch": 1.4901960784313726,
+      "grad_norm": 8.375,
+      "learning_rate": 1.4042352941176472e-05,
+      "loss": 0.36686473846435547,
+      "step": 1900
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 6.1875,
+      "learning_rate": 1.3885490196078433e-05,
+      "loss": 0.33892982482910156,
+      "step": 1950
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 7.375,
+      "learning_rate": 1.3728627450980394e-05,
+      "loss": 0.388890380859375,
+      "step": 2000
+    },
+    {
+      "epoch": 1.607843137254902,
+      "grad_norm": 8.0,
+      "learning_rate": 1.3571764705882353e-05,
+      "loss": 0.3352519989013672,
+      "step": 2050
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 6.1875,
+      "learning_rate": 1.3414901960784314e-05,
+      "loss": 0.3363905715942383,
+      "step": 2100
+    },
+    {
+      "epoch": 1.6862745098039216,
+      "grad_norm": 8.5625,
+      "learning_rate": 1.3258039215686275e-05,
+      "loss": 0.3257523727416992,
+      "step": 2150
+    },
+    {
+      "epoch": 1.7254901960784315,
+      "grad_norm": 8.1875,
+      "learning_rate": 1.3101176470588238e-05,
+      "loss": 0.3489485549926758,
+      "step": 2200
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 8.625,
+      "learning_rate": 1.2944313725490197e-05,
+      "loss": 0.3352058410644531,
+      "step": 2250
+    },
+    {
+      "epoch": 1.803921568627451,
+      "grad_norm": 6.59375,
+      "learning_rate": 1.2787450980392158e-05,
+      "loss": 0.3481978607177734,
+      "step": 2300
+    },
+    {
+      "epoch": 1.843137254901961,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.2630588235294119e-05,
+      "loss": 0.351578369140625,
+      "step": 2350
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 8.4375,
+      "learning_rate": 1.247372549019608e-05,
+      "loss": 0.3407152557373047,
+      "step": 2400
+    },
+    {
+      "epoch": 1.9215686274509802,
+      "grad_norm": 10.1875,
+      "learning_rate": 1.231686274509804e-05,
+      "loss": 0.3472262954711914,
+      "step": 2450
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 5.59375,
+      "learning_rate": 1.216e-05,
+      "loss": 0.35561527252197267,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.5,
+      "learning_rate": 1.2003137254901961e-05,
+      "loss": 0.34180992126464843,
+      "step": 2550
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.33438509702682495,
+      "eval_runtime": 0.7319,
+      "eval_samples_per_second": 229.53,
+      "eval_steps_per_second": 4.099,
+      "step": 2550
+    },
+    {
+      "epoch": 2.0392156862745097,
+      "grad_norm": 8.75,
+      "learning_rate": 1.1846274509803923e-05,
+      "loss": 0.3579704666137695,
+      "step": 2600
+    },
+    {
+      "epoch": 2.0784313725490198,
+      "grad_norm": 9.0,
+      "learning_rate": 1.1689411764705882e-05,
+      "loss": 0.3624613952636719,
+      "step": 2650
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 6.375,
+      "learning_rate": 1.1532549019607845e-05,
+      "loss": 0.35766292572021485,
+      "step": 2700
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.1375686274509806e-05,
+      "loss": 0.3069021797180176,
+      "step": 2750
+    },
+    {
+      "epoch": 2.196078431372549,
+      "grad_norm": 7.96875,
+      "learning_rate": 1.1218823529411767e-05,
+      "loss": 0.3502107238769531,
+      "step": 2800
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 7.25,
+      "learning_rate": 1.1061960784313726e-05,
+      "loss": 0.37451370239257814,
+      "step": 2850
+    },
+    {
+      "epoch": 2.2745098039215685,
+      "grad_norm": 10.5,
+      "learning_rate": 1.0905098039215687e-05,
+      "loss": 0.3441119003295898,
+      "step": 2900
+    },
+    {
+      "epoch": 2.313725490196078,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.0748235294117648e-05,
+      "loss": 0.34129436492919923,
+      "step": 2950
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 5.0,
+      "learning_rate": 1.0591372549019609e-05,
+      "loss": 0.37896224975585935,
+      "step": 3000
+    },
+    {
+      "epoch": 2.392156862745098,
+      "grad_norm": 7.34375,
+      "learning_rate": 1.0434509803921568e-05,
+      "loss": 0.3395826721191406,
+      "step": 3050
+    },
+    {
+      "epoch": 2.431372549019608,
+      "grad_norm": 8.875,
+      "learning_rate": 1.027764705882353e-05,
+      "loss": 0.3493861389160156,
+      "step": 3100
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 7.25,
+      "learning_rate": 1.0120784313725492e-05,
+      "loss": 0.37749198913574217,
+      "step": 3150
+    },
+    {
+      "epoch": 2.5098039215686274,
+      "grad_norm": 6.96875,
+      "learning_rate": 9.963921568627451e-06,
+      "loss": 0.3630757141113281,
+      "step": 3200
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 7.65625,
+      "learning_rate": 9.807058823529412e-06,
+      "loss": 0.36715946197509763,
+      "step": 3250
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 8.75,
+      "learning_rate": 9.650196078431373e-06,
+      "loss": 0.3679790878295898,
+      "step": 3300
+    },
+    {
+      "epoch": 2.627450980392157,
+      "grad_norm": 8.0,
+      "learning_rate": 9.493333333333334e-06,
+      "loss": 0.3319590759277344,
+      "step": 3350
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 7.875,
+      "learning_rate": 9.336470588235294e-06,
+      "loss": 0.32076107025146483,
+      "step": 3400
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 5.875,
+      "learning_rate": 9.179607843137257e-06,
+      "loss": 0.35666507720947266,
+      "step": 3450
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 7.21875,
+      "learning_rate": 9.022745098039216e-06,
+      "loss": 0.34649703979492186,
+      "step": 3500
+    },
+    {
+      "epoch": 2.784313725490196,
+      "grad_norm": 6.84375,
+      "learning_rate": 8.865882352941177e-06,
+      "loss": 0.3233991241455078,
+      "step": 3550
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 5.4375,
+      "learning_rate": 8.709019607843138e-06,
+      "loss": 0.3478955078125,
+      "step": 3600
+    },
+    {
+      "epoch": 2.8627450980392157,
+      "grad_norm": 8.25,
+      "learning_rate": 8.552156862745099e-06,
+      "loss": 0.3602957916259766,
+      "step": 3650
+    },
+    {
+      "epoch": 2.9019607843137254,
+      "grad_norm": 8.125,
+      "learning_rate": 8.39529411764706e-06,
+      "loss": 0.33980278015136717,
+      "step": 3700
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 6.5625,
+      "learning_rate": 8.238431372549021e-06,
+      "loss": 0.34001258850097654,
+      "step": 3750
+    },
+    {
+      "epoch": 2.980392156862745,
+      "grad_norm": 4.8125,
+      "learning_rate": 8.08156862745098e-06,
+      "loss": 0.3320033264160156,
+      "step": 3800
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3175601065158844,
+      "eval_runtime": 0.7323,
+      "eval_samples_per_second": 229.42,
+      "eval_steps_per_second": 4.097,
+      "step": 3825
+    },
+    {
+      "epoch": 3.019607843137255,
+      "grad_norm": 9.1875,
+      "learning_rate": 7.924705882352941e-06,
+      "loss": 0.36894729614257815,
+      "step": 3850
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 7.59375,
+      "learning_rate": 7.767843137254902e-06,
+      "loss": 0.3473331451416016,
+      "step": 3900
+    },
+    {
+      "epoch": 3.0980392156862746,
+      "grad_norm": 8.1875,
+      "learning_rate": 7.610980392156863e-06,
+      "loss": 0.37878219604492186,
+      "step": 3950
+    },
+    {
+      "epoch": 3.1372549019607843,
+      "grad_norm": 10.375,
+      "learning_rate": 7.4541176470588236e-06,
+      "loss": 0.38238269805908204,
+      "step": 4000
+    },
+    {
+      "epoch": 3.176470588235294,
+      "grad_norm": 7.3125,
+      "learning_rate": 7.2972549019607854e-06,
+      "loss": 0.3562689971923828,
+      "step": 4050
+    },
+    {
+      "epoch": 3.215686274509804,
+      "grad_norm": 9.625,
+      "learning_rate": 7.140392156862746e-06,
+      "loss": 0.34791328430175783,
+      "step": 4100
+    },
+    {
+      "epoch": 3.2549019607843137,
+      "grad_norm": 9.375,
+      "learning_rate": 6.983529411764707e-06,
+      "loss": 0.37418155670166015,
+      "step": 4150
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 7.28125,
+      "learning_rate": 6.826666666666667e-06,
+      "loss": 0.4004151153564453,
+      "step": 4200
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 9.4375,
+      "learning_rate": 6.669803921568629e-06,
+      "loss": 0.409102783203125,
+      "step": 4250
+    },
+    {
+      "epoch": 3.372549019607843,
+      "grad_norm": 7.90625,
+      "learning_rate": 6.512941176470589e-06,
+      "loss": 0.38699291229248045,
+      "step": 4300
+    },
+    {
+      "epoch": 3.411764705882353,
+      "grad_norm": 6.5,
+      "learning_rate": 6.35607843137255e-06,
+      "loss": 0.35100364685058594,
+      "step": 4350
+    },
+    {
+      "epoch": 3.450980392156863,
+      "grad_norm": 8.1875,
+      "learning_rate": 6.19921568627451e-06,
+      "loss": 0.3584611129760742,
+      "step": 4400
+    },
+    {
+      "epoch": 3.4901960784313726,
+      "grad_norm": 11.4375,
+      "learning_rate": 6.042352941176471e-06,
+      "loss": 0.3638358306884766,
+      "step": 4450
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 7.1875,
+      "learning_rate": 5.885490196078431e-06,
+      "loss": 0.3751061248779297,
+      "step": 4500
+    },
+    {
+      "epoch": 3.568627450980392,
+      "grad_norm": 8.9375,
+      "learning_rate": 5.728627450980393e-06,
+      "loss": 0.35851234436035156,
+      "step": 4550
+    },
+    {
+      "epoch": 3.607843137254902,
+      "grad_norm": 9.5625,
+      "learning_rate": 5.571764705882353e-06,
+      "loss": 0.3616675567626953,
+      "step": 4600
+    },
+    {
+      "epoch": 3.6470588235294117,
+      "grad_norm": 7.125,
+      "learning_rate": 5.414901960784314e-06,
+      "loss": 0.36935760498046877,
+      "step": 4650
+    },
+    {
+      "epoch": 3.686274509803922,
+      "grad_norm": 9.3125,
+      "learning_rate": 5.2580392156862745e-06,
+      "loss": 0.37147811889648436,
+      "step": 4700
+    },
+    {
+      "epoch": 3.7254901960784315,
+      "grad_norm": 7.71875,
+      "learning_rate": 5.101176470588236e-06,
+      "loss": 0.3624166107177734,
+      "step": 4750
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 7.0,
+      "learning_rate": 4.9443137254901966e-06,
+      "loss": 0.3978874969482422,
+      "step": 4800
+    },
+    {
+      "epoch": 3.803921568627451,
+      "grad_norm": 7.5625,
+      "learning_rate": 4.787450980392157e-06,
+      "loss": 0.3623295211791992,
+      "step": 4850
+    },
+    {
+      "epoch": 3.843137254901961,
+      "grad_norm": 9.75,
+      "learning_rate": 4.630588235294118e-06,
+      "loss": 0.3738731384277344,
+      "step": 4900
+    },
+    {
+      "epoch": 3.8823529411764706,
+      "grad_norm": 8.875,
+      "learning_rate": 4.473725490196079e-06,
+      "loss": 0.3802723693847656,
+      "step": 4950
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 7.15625,
+      "learning_rate": 4.316862745098039e-06,
+      "loss": 0.36539669036865235,
+      "step": 5000
+    },
+    {
+      "epoch": 3.9607843137254903,
+      "grad_norm": 7.71875,
+      "learning_rate": 4.16e-06,
+      "loss": 0.37843170166015627,
+      "step": 5050
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 15.8125,
+      "learning_rate": 4.003137254901961e-06,
+      "loss": 0.4109536361694336,
+      "step": 5100
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.3134707510471344,
+      "eval_runtime": 0.6958,
+      "eval_samples_per_second": 241.46,
+      "eval_steps_per_second": 4.312,
+      "step": 5100
+    },
+    {
+      "epoch": 4.03921568627451,
+      "grad_norm": 7.3125,
+      "learning_rate": 3.846274509803922e-06,
+      "loss": 0.38864410400390625,
+      "step": 5150
+    },
+    {
+      "epoch": 4.078431372549019,
+      "grad_norm": 8.6875,
+      "learning_rate": 3.6894117647058826e-06,
+      "loss": 0.4023876953125,
+      "step": 5200
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 7.65625,
+      "learning_rate": 3.5325490196078432e-06,
+      "loss": 0.40609615325927734,
+      "step": 5250
+    },
+    {
+      "epoch": 4.1568627450980395,
+      "grad_norm": 9.125,
+      "learning_rate": 3.375686274509804e-06,
+      "loss": 0.37641597747802735,
+      "step": 5300
+    },
+    {
+      "epoch": 4.196078431372549,
+      "grad_norm": 8.0625,
+      "learning_rate": 3.218823529411765e-06,
+      "loss": 0.39501625061035156,
+      "step": 5350
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 9.5625,
+      "learning_rate": 3.0619607843137255e-06,
+      "loss": 0.4144803237915039,
+      "step": 5400
+    },
+    {
+      "epoch": 4.2745098039215685,
+      "grad_norm": 7.90625,
+      "learning_rate": 2.9050980392156865e-06,
+      "loss": 0.38548496246337893,
+      "step": 5450
+    },
+    {
+      "epoch": 4.313725490196078,
+      "grad_norm": 6.40625,
+      "learning_rate": 2.748235294117647e-06,
+      "loss": 0.4089166259765625,
+      "step": 5500
+    },
+    {
+      "epoch": 4.352941176470588,
+      "grad_norm": 9.4375,
+      "learning_rate": 2.5913725490196077e-06,
+      "loss": 0.4080876159667969,
+      "step": 5550
+    },
+    {
+      "epoch": 4.392156862745098,
+      "grad_norm": 7.0625,
+      "learning_rate": 2.434509803921569e-06,
+      "loss": 0.3910002517700195,
+      "step": 5600
+    },
+    {
+      "epoch": 4.431372549019608,
+      "grad_norm": 11.6875,
+      "learning_rate": 2.2776470588235297e-06,
+      "loss": 0.37938087463378906,
+      "step": 5650
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 8.75,
+      "learning_rate": 2.1207843137254903e-06,
+      "loss": 0.3560845184326172,
+      "step": 5700
+    },
+    {
+      "epoch": 4.509803921568627,
+      "grad_norm": 7.0,
+      "learning_rate": 1.9639215686274514e-06,
+      "loss": 0.3788024520874023,
+      "step": 5750
+    },
+    {
+      "epoch": 4.549019607843137,
+      "grad_norm": 7.4375,
+      "learning_rate": 1.807058823529412e-06,
+      "loss": 0.375964469909668,
+      "step": 5800
+    },
+    {
+      "epoch": 4.588235294117647,
+      "grad_norm": 7.625,
+      "learning_rate": 1.6501960784313728e-06,
+      "loss": 0.414542236328125,
+      "step": 5850
+    },
+    {
+      "epoch": 4.627450980392156,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.4933333333333336e-06,
+      "loss": 0.42268470764160154,
+      "step": 5900
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 7.96875,
+      "learning_rate": 1.3364705882352944e-06,
+      "loss": 0.40671161651611326,
+      "step": 5950
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 7.96875,
+      "learning_rate": 1.179607843137255e-06,
+      "loss": 0.4210764694213867,
+      "step": 6000
+    },
+    {
+      "epoch": 4.745098039215686,
+      "grad_norm": 9.125,
+      "learning_rate": 1.0227450980392158e-06,
+      "loss": 0.38931812286376954,
+      "step": 6050
+    },
+    {
+      "epoch": 4.784313725490196,
+      "grad_norm": 7.8125,
+      "learning_rate": 8.658823529411765e-07,
+      "loss": 0.3871194076538086,
+      "step": 6100
+    },
+    {
+      "epoch": 4.823529411764706,
+      "grad_norm": 10.0,
+      "learning_rate": 7.090196078431373e-07,
+      "loss": 0.3717901611328125,
+      "step": 6150
+    },
+    {
+      "epoch": 4.862745098039216,
+      "grad_norm": 8.75,
+      "learning_rate": 5.521568627450981e-07,
+      "loss": 0.40650894165039064,
+      "step": 6200
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 7.625,
+      "learning_rate": 3.9529411764705884e-07,
+      "loss": 0.39076881408691405,
+      "step": 6250
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 8.25,
+      "learning_rate": 2.3843137254901965e-07,
+      "loss": 0.4112423324584961,
+      "step": 6300
+    },
+    {
+      "epoch": 4.980392156862745,
+      "grad_norm": 7.40625,
+      "learning_rate": 8.156862745098041e-08,
+      "loss": 0.39700592041015625,
+      "step": 6350
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.31319624185562134,
+      "eval_runtime": 0.7279,
+      "eval_samples_per_second": 230.787,
+      "eval_steps_per_second": 4.121,
+      "step": 6375
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": null
+}

BAAI-bge-reranker-base-E5-Pairwise/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36968d3108b641d627c393002185baced80ce63d61d8a76440547cc21cbcf09a
+size 5265