Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c554363504214b1324ad38a84e6ea2bbfa3bb253e3dbce7010ea0942f506294f
+size 2271071852

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee473dc9d3996af3039b750bac6b7eb5f5f15ef55b82d5f5e143a1f814614713
+size 4542390410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1da78181b235b59c6f31bf207495cb7e49ec059cf7a064fdf281e1bc0e9105
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2afd7159392ac130603bd41b5d2978beb248ce1e704c3258868a9de9bba7aa
+size 1465

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4b3f18efdf78e089df9b8b87e8d3ea54ef0393550ee793a8686b47c54126a8
+size 17083167

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,477 @@
+{
+  "best_global_step": 2230,
+  "best_metric": 0.9941502463054187,
+  "best_model_checkpoint": "/workspace/hallucination/bge-reranker-v2-m3/v6/checkpoint-1784",
+  "epoch": 2.9941225860621326,
+  "eval_steps": 446,
+  "global_step": 2676,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.055975370836831795,
+      "grad_norm": 4.56851863861084,
+      "learning_rate": 2.9037037037037038e-06,
+      "loss": 0.1467,
+      "step": 50
+    },
+    {
+      "epoch": 0.11195074167366359,
+      "grad_norm": 1.2010878324508667,
+      "learning_rate": 5.866666666666666e-06,
+      "loss": 0.0727,
+      "step": 100
+    },
+    {
+      "epoch": 0.16792611251049538,
+      "grad_norm": 6.644562244415283,
+      "learning_rate": 7.99940362815711e-06,
+      "loss": 0.0405,
+      "step": 150
+    },
+    {
+      "epoch": 0.22390148334732718,
+      "grad_norm": 3.49969744682312,
+      "learning_rate": 7.98754320672899e-06,
+      "loss": 0.0358,
+      "step": 200
+    },
+    {
+      "epoch": 0.279876854184159,
+      "grad_norm": 3.164804220199585,
+      "learning_rate": 7.960521025612183e-06,
+      "loss": 0.0389,
+      "step": 250
+    },
+    {
+      "epoch": 0.33585222502099077,
+      "grad_norm": 4.480787754058838,
+      "learning_rate": 7.918439830731966e-06,
+      "loss": 0.0543,
+      "step": 300
+    },
+    {
+      "epoch": 0.39182759585782256,
+      "grad_norm": 5.254024028778076,
+      "learning_rate": 7.861459626615215e-06,
+      "loss": 0.0465,
+      "step": 350
+    },
+    {
+      "epoch": 0.44780296669465436,
+      "grad_norm": 0.4903552532196045,
+      "learning_rate": 7.789797068008236e-06,
+      "loss": 0.037,
+      "step": 400
+    },
+    {
+      "epoch": 0.4993003078645396,
+      "eval_accuracy": 0.9902377578334121,
+      "eval_f1": 0.9904202719406675,
+      "eval_loss": 0.03584026172757149,
+      "eval_precision": 0.9925673583152679,
+      "eval_recall": 0.9882824545174221,
+      "eval_runtime": 328.1406,
+      "eval_samples_per_second": 19.355,
+      "eval_steps_per_second": 1.21,
+      "step": 446
+    },
+    {
+      "epoch": 0.5037783375314862,
+      "grad_norm": 12.020153045654297,
+      "learning_rate": 7.703724636094536e-06,
+      "loss": 0.0334,
+      "step": 450
+    },
+    {
+      "epoch": 0.559753708368318,
+      "grad_norm": 9.890530586242676,
+      "learning_rate": 7.603569602444819e-06,
+      "loss": 0.0402,
+      "step": 500
+    },
+    {
+      "epoch": 0.6157290792051497,
+      "grad_norm": 8.32047176361084,
+      "learning_rate": 7.4897127846385005e-06,
+      "loss": 0.0367,
+      "step": 550
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "grad_norm": 0.729023277759552,
+      "learning_rate": 7.362587098288277e-06,
+      "loss": 0.0279,
+      "step": 600
+    },
+    {
+      "epoch": 0.7276798208788133,
+      "grad_norm": 0.38823333382606506,
+      "learning_rate": 7.222675910973328e-06,
+      "loss": 0.0226,
+      "step": 650
+    },
+    {
+      "epoch": 0.7836551917156451,
+      "grad_norm": 14.20788860321045,
+      "learning_rate": 7.070511204339955e-06,
+      "loss": 0.0285,
+      "step": 700
+    },
+    {
+      "epoch": 0.8396305625524769,
+      "grad_norm": 14.189713478088379,
+      "learning_rate": 6.906671551357899e-06,
+      "loss": 0.0183,
+      "step": 750
+    },
+    {
+      "epoch": 0.8956059333893087,
+      "grad_norm": 9.239374160766602,
+      "learning_rate": 6.731779916423332e-06,
+      "loss": 0.025,
+      "step": 800
+    },
+    {
+      "epoch": 0.9515813042261405,
+      "grad_norm": 7.430564880371094,
+      "learning_rate": 6.546501286673185e-06,
+      "loss": 0.0267,
+      "step": 850
+    },
+    {
+      "epoch": 0.9986006157290792,
+      "eval_accuracy": 0.9916548575027555,
+      "eval_f1": 0.9918649270913277,
+      "eval_loss": 0.03128722682595253,
+      "eval_precision": 0.9874694376528117,
+      "eval_recall": 0.996299722479186,
+      "eval_runtime": 328.6993,
+      "eval_samples_per_second": 19.322,
+      "eval_steps_per_second": 1.208,
+      "step": 892
+    },
+    {
+      "epoch": 1.0067170445004199,
+      "grad_norm": 1.4463914632797241,
+      "learning_rate": 6.351540143517212e-06,
+      "loss": 0.0215,
+      "step": 900
+    },
+    {
+      "epoch": 1.0626924153372517,
+      "grad_norm": 0.02502119354903698,
+      "learning_rate": 6.147637784001716e-06,
+      "loss": 0.0062,
+      "step": 950
+    },
+    {
+      "epoch": 1.1186677861740835,
+      "grad_norm": 0.039681658148765564,
+      "learning_rate": 5.935569502189897e-06,
+      "loss": 0.0034,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1746431570109153,
+      "grad_norm": 0.005194108001887798,
+      "learning_rate": 5.716141641275983e-06,
+      "loss": 0.0087,
+      "step": 1050
+    },
+    {
+      "epoch": 1.230618527847747,
+      "grad_norm": 0.17214158177375793,
+      "learning_rate": 5.490188527641829e-06,
+      "loss": 0.0156,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2865938986845789,
+      "grad_norm": 0.48181217908859253,
+      "learning_rate": 5.258569298513601e-06,
+      "loss": 0.0066,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3425692695214106,
+      "grad_norm": 0.12410200387239456,
+      "learning_rate": 5.0221646352806285e-06,
+      "loss": 0.0085,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3985446403582424,
+      "grad_norm": 0.03792842850089073,
+      "learning_rate": 4.781873414897317e-06,
+      "loss": 0.0179,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4545200111950742,
+      "grad_norm": 1.4860434532165527,
+      "learning_rate": 4.538609292100398e-06,
+      "loss": 0.0112,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4970612930310663,
+      "eval_accuracy": 0.9918123130215714,
+      "eval_f1": 0.9920196439533456,
+      "eval_loss": 0.03981148824095726,
+      "eval_precision": 0.9874732661167125,
+      "eval_recall": 0.9966080789392537,
+      "eval_runtime": 329.583,
+      "eval_samples_per_second": 19.27,
+      "eval_steps_per_second": 1.205,
+      "step": 1338
+    },
+    {
+      "epoch": 1.5104953820319058,
+      "grad_norm": 0.007759585976600647,
+      "learning_rate": 4.293297225436905e-06,
+      "loss": 0.0034,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5664707528687378,
+      "grad_norm": 0.02019183151423931,
+      "learning_rate": 4.046869960311881e-06,
+      "loss": 0.004,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6224461237055694,
+      "grad_norm": 0.03353915363550186,
+      "learning_rate": 3.8002644824282683e-06,
+      "loss": 0.0067,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6784214945424014,
+      "grad_norm": 3.9431345462799072,
+      "learning_rate": 3.5544184551039885e-06,
+      "loss": 0.0062,
+      "step": 1500
+    },
+    {
+      "epoch": 1.734396865379233,
+      "grad_norm": 0.009291726164519787,
+      "learning_rate": 3.3102666540125503e-06,
+      "loss": 0.0044,
+      "step": 1550
+    },
+    {
+      "epoch": 1.790372236216065,
+      "grad_norm": 0.024871619418263435,
+      "learning_rate": 3.06873741290328e-06,
+      "loss": 0.0044,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8463476070528966,
+      "grad_norm": 0.0040198941715061665,
+      "learning_rate": 2.8307490938155686e-06,
+      "loss": 0.0074,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9023229778897286,
+      "grad_norm": 0.010355140082538128,
+      "learning_rate": 2.597206595208356e-06,
+      "loss": 0.007,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9582983487265602,
+      "grad_norm": 0.05570561811327934,
+      "learning_rate": 2.36899791128193e-06,
+      "loss": 0.0114,
+      "step": 1750
+    },
+    {
+      "epoch": 1.996361600895606,
+      "eval_accuracy": 0.9935443237285467,
+      "eval_f1": 0.9936913371287891,
+      "eval_loss": 0.03450547158718109,
+      "eval_precision": 0.9917076167076168,
+      "eval_recall": 0.9956830095590503,
+      "eval_runtime": 329.5265,
+      "eval_samples_per_second": 19.273,
+      "eval_steps_per_second": 1.205,
+      "step": 1784
+    },
+    {
+      "epoch": 2.0134340890008398,
+      "grad_norm": 0.0031412208918482065,
+      "learning_rate": 2.146990755574473e-06,
+      "loss": 0.0049,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0694094598376713,
+      "grad_norm": 0.022113706916570663,
+      "learning_rate": 1.9320292616713783e-06,
+      "loss": 0.0023,
+      "step": 1850
+    },
+    {
+      "epoch": 2.1253848306745033,
+      "grad_norm": 0.013204299844801426,
+      "learning_rate": 1.7249307735721739e-06,
+      "loss": 0.0034,
+      "step": 1900
+    },
+    {
+      "epoch": 2.181360201511335,
+      "grad_norm": 0.34572720527648926,
+      "learning_rate": 1.526482737918981e-06,
+      "loss": 0.0002,
+      "step": 1950
+    },
+    {
+      "epoch": 2.237335572348167,
+      "grad_norm": 0.003737039864063263,
+      "learning_rate": 1.337439709903123e-06,
+      "loss": 0.0022,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2933109431849985,
+      "grad_norm": 0.0018848059698939323,
+      "learning_rate": 1.1585204842342755e-06,
+      "loss": 0.0001,
+      "step": 2050
+    },
+    {
+      "epoch": 2.3492863140218305,
+      "grad_norm": 0.0221543088555336,
+      "learning_rate": 9.904053620810118e-07,
+      "loss": 0.0002,
+      "step": 2100
+    },
+    {
+      "epoch": 2.405261684858662,
+      "grad_norm": 0.0014764212537556887,
+      "learning_rate": 8.337335643746119e-07,
+      "loss": 0.003,
+      "step": 2150
+    },
+    {
+      "epoch": 2.461237055695494,
+      "grad_norm": 0.24720342457294464,
+      "learning_rate": 6.891008013114716e-07,
+      "loss": 0.0025,
+      "step": 2200
+    },
+    {
+      "epoch": 2.494822278197593,
+      "eval_accuracy": 0.9940166902849945,
+      "eval_f1": 0.9941502463054187,
+      "eval_loss": 0.034027792513370514,
+      "eval_precision": 0.9926221948970181,
+      "eval_recall": 0.9956830095590503,
+      "eval_runtime": 328.5789,
+      "eval_samples_per_second": 19.329,
+      "eval_steps_per_second": 1.208,
+      "step": 2230
+    },
+    {
+      "epoch": 2.5172124265323257,
+      "grad_norm": 0.04605395719408989,
+      "learning_rate": 5.570570072955551e-07,
+      "loss": 0.0017,
+      "step": 2250
+    },
+    {
+      "epoch": 2.5731877973691577,
+      "grad_norm": 0.0023472148459404707,
+      "learning_rate": 4.3810424993327053e-07,
+      "loss": 0.0018,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6291631682059893,
+      "grad_norm": 0.0014394799945876002,
+      "learning_rate": 3.326948210313607e-07,
+      "loss": 0.0015,
+      "step": 2350
+    },
+    {
+      "epoch": 2.6851385390428213,
+      "grad_norm": 0.029553143307566643,
+      "learning_rate": 2.412295168563667e-07,
+      "loss": 0.0007,
+      "step": 2400
+    },
+    {
+      "epoch": 2.741113909879653,
+      "grad_norm": 0.0062004872597754,
+      "learning_rate": 1.6405611419461017e-07,
+      "loss": 0.0002,
+      "step": 2450
+    },
+    {
+      "epoch": 2.797089280716485,
+      "grad_norm": 1.4929763078689575,
+      "learning_rate": 1.0146804800713304e-07,
+      "loss": 0.0001,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8530646515533165,
+      "grad_norm": 0.0059923469088971615,
+      "learning_rate": 5.3703295707523854e-08,
+      "loss": 0.0011,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9090400223901485,
+      "grad_norm": 0.00393084529787302,
+      "learning_rate": 2.094347230492799e-08,
+      "loss": 0.0014,
+      "step": 2600
+    },
+    {
+      "epoch": 2.96501539322698,
+      "grad_norm": 0.0017132419161498547,
+      "learning_rate": 3.3131398527510567e-09,
+      "loss": 0.0017,
+      "step": 2650
+    },
+    {
+      "epoch": 2.9941225860621326,
+      "eval_accuracy": 0.9938592347661785,
+      "eval_f1": 0.9939935314954567,
+      "eval_loss": 0.033541660755872726,
+      "eval_precision": 0.9929230769230769,
+      "eval_recall": 0.9950662966389145,
+      "eval_runtime": 329.149,
+      "eval_samples_per_second": 19.295,
+      "eval_steps_per_second": 1.206,
+      "step": 2676
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2682,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 892,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.189990278329344e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee729c2bb4a99f17ec914518b1c84153a23588c0d97e881a73e40efd85d6c59e
+size 5777