Upload folder using huggingface_hub

.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

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: MoritzLaurer/mDeBERTa-v3-base-mnli-xnli
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.40547820925712585
+
+f1: 0.8509544787077826
+
+precision: 0.8474287106994882
+
+recall: 0.8545097075448513
+
+auc: 0.9024178348450937
+
+accuracy: 0.8176919622810956

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

checkpoint-3341/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli",
+  "_num_labels": 2,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "in-character",
+    "1": "out-of-character"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "in-character": 0,
+    "out-of-character": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

checkpoint-3341/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db3c56c71229589e5cb6b92fbac028b4ac4418342c591dd1cf5b4ec55ad0990
+size 1115268200

checkpoint-3341/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25473caab367f83e9d8ddd3ece1d0524f3c220add11f9d0ad8f39118823deaaf
+size 2230650362

checkpoint-3341/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c2f7bf4888c9640fe86145b5fd8fc8152e18ee97089aeaf29d199a2b1e960a
+size 13990

checkpoint-3341/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d38a546d89e80d65205a3317378d5850a248f277d5319207ec6487b4395cb1
+size 1064

checkpoint-3341/trainer_state.json

@@ -0,0 +1,986 @@
+{
+  "best_metric": 0.40547820925712585,
+  "best_model_checkpoint": "mDeBERTa-v3-base-mnli-xnli-dnd/checkpoint-3341",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3341,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0074827895839568994,
+      "grad_norm": 4.059116363525391,
+      "learning_rate": 3.7313432835820893e-06,
+      "loss": 0.6987,
+      "step": 25
+    },
+    {
+      "epoch": 0.014965579167913799,
+      "grad_norm": 3.396561861038208,
+      "learning_rate": 7.4626865671641785e-06,
+      "loss": 0.6773,
+      "step": 50
+    },
+    {
+      "epoch": 0.022448368751870697,
+      "grad_norm": 4.667275905609131,
+      "learning_rate": 1.119402985074627e-05,
+      "loss": 0.6562,
+      "step": 75
+    },
+    {
+      "epoch": 0.029931158335827598,
+      "grad_norm": 4.270143508911133,
+      "learning_rate": 1.4925373134328357e-05,
+      "loss": 0.6451,
+      "step": 100
+    },
+    {
+      "epoch": 0.037413947919784495,
+      "grad_norm": 6.245508193969727,
+      "learning_rate": 1.865671641791045e-05,
+      "loss": 0.6372,
+      "step": 125
+    },
+    {
+      "epoch": 0.044896737503741395,
+      "grad_norm": 8.381564140319824,
+      "learning_rate": 2.238805970149254e-05,
+      "loss": 0.6065,
+      "step": 150
+    },
+    {
+      "epoch": 0.052379527087698295,
+      "grad_norm": 5.698436260223389,
+      "learning_rate": 2.6119402985074626e-05,
+      "loss": 0.5725,
+      "step": 175
+    },
+    {
+      "epoch": 0.059862316671655195,
+      "grad_norm": 6.78079080581665,
+      "learning_rate": 2.9850746268656714e-05,
+      "loss": 0.5438,
+      "step": 200
+    },
+    {
+      "epoch": 0.06734510625561209,
+      "grad_norm": 4.647417068481445,
+      "learning_rate": 3.358208955223881e-05,
+      "loss": 0.5975,
+      "step": 225
+    },
+    {
+      "epoch": 0.07482789583956899,
+      "grad_norm": 5.508735179901123,
+      "learning_rate": 3.73134328358209e-05,
+      "loss": 0.5774,
+      "step": 250
+    },
+    {
+      "epoch": 0.08231068542352589,
+      "grad_norm": 6.2550458908081055,
+      "learning_rate": 4.104477611940299e-05,
+      "loss": 0.5779,
+      "step": 275
+    },
+    {
+      "epoch": 0.08979347500748279,
+      "grad_norm": 6.34486198425293,
+      "learning_rate": 4.477611940298508e-05,
+      "loss": 0.5835,
+      "step": 300
+    },
+    {
+      "epoch": 0.09727626459143969,
+      "grad_norm": 11.040050506591797,
+      "learning_rate": 4.850746268656717e-05,
+      "loss": 0.5475,
+      "step": 325
+    },
+    {
+      "epoch": 0.10475905417539659,
+      "grad_norm": 8.249756813049316,
+      "learning_rate": 4.975049900199601e-05,
+      "loss": 0.5557,
+      "step": 350
+    },
+    {
+      "epoch": 0.11224184375935349,
+      "grad_norm": 3.8277997970581055,
+      "learning_rate": 4.933466400532269e-05,
+      "loss": 0.5059,
+      "step": 375
+    },
+    {
+      "epoch": 0.11972463334331039,
+      "grad_norm": 3.1715078353881836,
+      "learning_rate": 4.891882900864937e-05,
+      "loss": 0.5417,
+      "step": 400
+    },
+    {
+      "epoch": 0.12720742292726728,
+      "grad_norm": 7.743518829345703,
+      "learning_rate": 4.8502994011976046e-05,
+      "loss": 0.5032,
+      "step": 425
+    },
+    {
+      "epoch": 0.13469021251122418,
+      "grad_norm": 5.770236015319824,
+      "learning_rate": 4.808715901530273e-05,
+      "loss": 0.4911,
+      "step": 450
+    },
+    {
+      "epoch": 0.14217300209518108,
+      "grad_norm": 4.398015022277832,
+      "learning_rate": 4.767132401862941e-05,
+      "loss": 0.5252,
+      "step": 475
+    },
+    {
+      "epoch": 0.14965579167913798,
+      "grad_norm": 23.583471298217773,
+      "learning_rate": 4.725548902195609e-05,
+      "loss": 0.5005,
+      "step": 500
+    },
+    {
+      "epoch": 0.15713858126309488,
+      "grad_norm": 2.395005226135254,
+      "learning_rate": 4.683965402528277e-05,
+      "loss": 0.562,
+      "step": 525
+    },
+    {
+      "epoch": 0.16462137084705178,
+      "grad_norm": 2.9066038131713867,
+      "learning_rate": 4.642381902860945e-05,
+      "loss": 0.4656,
+      "step": 550
+    },
+    {
+      "epoch": 0.17210416043100868,
+      "grad_norm": 9.273233413696289,
+      "learning_rate": 4.600798403193613e-05,
+      "loss": 0.6357,
+      "step": 575
+    },
+    {
+      "epoch": 0.17958695001496558,
+      "grad_norm": 2.02755069732666,
+      "learning_rate": 4.559214903526281e-05,
+      "loss": 0.6515,
+      "step": 600
+    },
+    {
+      "epoch": 0.18706973959892248,
+      "grad_norm": 6.606990814208984,
+      "learning_rate": 4.517631403858949e-05,
+      "loss": 0.5818,
+      "step": 625
+    },
+    {
+      "epoch": 0.19455252918287938,
+      "grad_norm": 22.710664749145508,
+      "learning_rate": 4.476047904191617e-05,
+      "loss": 0.5306,
+      "step": 650
+    },
+    {
+      "epoch": 0.20203531876683628,
+      "grad_norm": 3.1198155879974365,
+      "learning_rate": 4.434464404524285e-05,
+      "loss": 0.5635,
+      "step": 675
+    },
+    {
+      "epoch": 0.20951810835079318,
+      "grad_norm": 2.4390244483947754,
+      "learning_rate": 4.392880904856953e-05,
+      "loss": 0.4779,
+      "step": 700
+    },
+    {
+      "epoch": 0.21700089793475008,
+      "grad_norm": 7.443247318267822,
+      "learning_rate": 4.351297405189621e-05,
+      "loss": 0.5732,
+      "step": 725
+    },
+    {
+      "epoch": 0.22448368751870698,
+      "grad_norm": 7.480808258056641,
+      "learning_rate": 4.3097139055222893e-05,
+      "loss": 0.5574,
+      "step": 750
+    },
+    {
+      "epoch": 0.23196647710266388,
+      "grad_norm": 3.3201472759246826,
+      "learning_rate": 4.268130405854957e-05,
+      "loss": 0.4929,
+      "step": 775
+    },
+    {
+      "epoch": 0.23944926668662078,
+      "grad_norm": 20.688968658447266,
+      "learning_rate": 4.226546906187625e-05,
+      "loss": 0.596,
+      "step": 800
+    },
+    {
+      "epoch": 0.24693205627057768,
+      "grad_norm": 4.053366661071777,
+      "learning_rate": 4.184963406520293e-05,
+      "loss": 0.4967,
+      "step": 825
+    },
+    {
+      "epoch": 0.25441484585453455,
+      "grad_norm": 5.196917533874512,
+      "learning_rate": 4.143379906852961e-05,
+      "loss": 0.4415,
+      "step": 850
+    },
+    {
+      "epoch": 0.2618976354384915,
+      "grad_norm": 6.801918029785156,
+      "learning_rate": 4.101796407185629e-05,
+      "loss": 0.4998,
+      "step": 875
+    },
+    {
+      "epoch": 0.26938042502244836,
+      "grad_norm": 3.020432949066162,
+      "learning_rate": 4.060212907518297e-05,
+      "loss": 0.5615,
+      "step": 900
+    },
+    {
+      "epoch": 0.2768632146064053,
+      "grad_norm": 1.862509846687317,
+      "learning_rate": 4.018629407850965e-05,
+      "loss": 0.4653,
+      "step": 925
+    },
+    {
+      "epoch": 0.28434600419036216,
+      "grad_norm": 8.588277816772461,
+      "learning_rate": 3.977045908183633e-05,
+      "loss": 0.5572,
+      "step": 950
+    },
+    {
+      "epoch": 0.2918287937743191,
+      "grad_norm": 5.132936954498291,
+      "learning_rate": 3.935462408516301e-05,
+      "loss": 0.5228,
+      "step": 975
+    },
+    {
+      "epoch": 0.29931158335827596,
+      "grad_norm": 5.957391738891602,
+      "learning_rate": 3.893878908848969e-05,
+      "loss": 0.5093,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3067943729422329,
+      "grad_norm": 6.140280723571777,
+      "learning_rate": 3.852295409181637e-05,
+      "loss": 0.4869,
+      "step": 1025
+    },
+    {
+      "epoch": 0.31427716252618976,
+      "grad_norm": 4.803741455078125,
+      "learning_rate": 3.810711909514305e-05,
+      "loss": 0.5162,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3217599521101467,
+      "grad_norm": 4.811578750610352,
+      "learning_rate": 3.7691284098469734e-05,
+      "loss": 0.5407,
+      "step": 1075
+    },
+    {
+      "epoch": 0.32924274169410356,
+      "grad_norm": 18.00532341003418,
+      "learning_rate": 3.727544910179641e-05,
+      "loss": 0.4616,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3367255312780605,
+      "grad_norm": 6.0717010498046875,
+      "learning_rate": 3.685961410512309e-05,
+      "loss": 0.4624,
+      "step": 1125
+    },
+    {
+      "epoch": 0.34420832086201736,
+      "grad_norm": 3.2662813663482666,
+      "learning_rate": 3.644377910844977e-05,
+      "loss": 0.5201,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3516911104459743,
+      "grad_norm": 3.59017276763916,
+      "learning_rate": 3.6027944111776455e-05,
+      "loss": 0.4812,
+      "step": 1175
+    },
+    {
+      "epoch": 0.35917390002993116,
+      "grad_norm": 7.663816928863525,
+      "learning_rate": 3.5612109115103126e-05,
+      "loss": 0.4407,
+      "step": 1200
+    },
+    {
+      "epoch": 0.36665668961388803,
+      "grad_norm": 5.2263407707214355,
+      "learning_rate": 3.5196274118429805e-05,
+      "loss": 0.4543,
+      "step": 1225
+    },
+    {
+      "epoch": 0.37413947919784496,
+      "grad_norm": 15.237629890441895,
+      "learning_rate": 3.478043912175648e-05,
+      "loss": 0.5069,
+      "step": 1250
+    },
+    {
+      "epoch": 0.38162226878180183,
+      "grad_norm": 16.1485538482666,
+      "learning_rate": 3.436460412508317e-05,
+      "loss": 0.4123,
+      "step": 1275
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "grad_norm": 2.711836576461792,
+      "learning_rate": 3.394876912840985e-05,
+      "loss": 0.5798,
+      "step": 1300
+    },
+    {
+      "epoch": 0.39658784794971563,
+      "grad_norm": 9.17324447631836,
+      "learning_rate": 3.3532934131736525e-05,
+      "loss": 0.4668,
+      "step": 1325
+    },
+    {
+      "epoch": 0.40407063753367256,
+      "grad_norm": 5.9319047927856445,
+      "learning_rate": 3.3117099135063204e-05,
+      "loss": 0.4833,
+      "step": 1350
+    },
+    {
+      "epoch": 0.41155342711762943,
+      "grad_norm": 1.7995569705963135,
+      "learning_rate": 3.270126413838989e-05,
+      "loss": 0.499,
+      "step": 1375
+    },
+    {
+      "epoch": 0.41903621670158636,
+      "grad_norm": 3.604038953781128,
+      "learning_rate": 3.228542914171657e-05,
+      "loss": 0.4182,
+      "step": 1400
+    },
+    {
+      "epoch": 0.42651900628554323,
+      "grad_norm": 20.409942626953125,
+      "learning_rate": 3.1869594145043246e-05,
+      "loss": 0.4604,
+      "step": 1425
+    },
+    {
+      "epoch": 0.43400179586950016,
+      "grad_norm": 3.52787184715271,
+      "learning_rate": 3.1453759148369925e-05,
+      "loss": 0.5126,
+      "step": 1450
+    },
+    {
+      "epoch": 0.44148458545345703,
+      "grad_norm": 5.209261894226074,
+      "learning_rate": 3.103792415169661e-05,
+      "loss": 0.5798,
+      "step": 1475
+    },
+    {
+      "epoch": 0.44896737503741396,
+      "grad_norm": 2.947472095489502,
+      "learning_rate": 3.062208915502329e-05,
+      "loss": 0.5215,
+      "step": 1500
+    },
+    {
+      "epoch": 0.45645016462137084,
+      "grad_norm": 7.958189964294434,
+      "learning_rate": 3.0206254158349967e-05,
+      "loss": 0.472,
+      "step": 1525
+    },
+    {
+      "epoch": 0.46393295420532776,
+      "grad_norm": 2.645322322845459,
+      "learning_rate": 2.979041916167665e-05,
+      "loss": 0.4566,
+      "step": 1550
+    },
+    {
+      "epoch": 0.47141574378928464,
+      "grad_norm": 7.029107570648193,
+      "learning_rate": 2.9374584165003327e-05,
+      "loss": 0.4619,
+      "step": 1575
+    },
+    {
+      "epoch": 0.47889853337324156,
+      "grad_norm": 5.63282585144043,
+      "learning_rate": 2.8958749168330006e-05,
+      "loss": 0.4959,
+      "step": 1600
+    },
+    {
+      "epoch": 0.48638132295719844,
+      "grad_norm": 2.9673337936401367,
+      "learning_rate": 2.8542914171656687e-05,
+      "loss": 0.39,
+      "step": 1625
+    },
+    {
+      "epoch": 0.49386411254115536,
+      "grad_norm": 24.8010311126709,
+      "learning_rate": 2.8127079174983366e-05,
+      "loss": 0.3776,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5013469021251122,
+      "grad_norm": 2.339782238006592,
+      "learning_rate": 2.7711244178310048e-05,
+      "loss": 0.4797,
+      "step": 1675
+    },
+    {
+      "epoch": 0.5088296917090691,
+      "grad_norm": 5.149988651275635,
+      "learning_rate": 2.7295409181636726e-05,
+      "loss": 0.4535,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5163124812930261,
+      "grad_norm": 8.524362564086914,
+      "learning_rate": 2.6879574184963408e-05,
+      "loss": 0.4421,
+      "step": 1725
+    },
+    {
+      "epoch": 0.523795270876983,
+      "grad_norm": 4.499845504760742,
+      "learning_rate": 2.6463739188290087e-05,
+      "loss": 0.3448,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5312780604609398,
+      "grad_norm": 2.887631416320801,
+      "learning_rate": 2.604790419161677e-05,
+      "loss": 0.583,
+      "step": 1775
+    },
+    {
+      "epoch": 0.5387608500448967,
+      "grad_norm": 1.4689120054244995,
+      "learning_rate": 2.5632069194943447e-05,
+      "loss": 0.4272,
+      "step": 1800
+    },
+    {
+      "epoch": 0.5462436396288536,
+      "grad_norm": 6.976527690887451,
+      "learning_rate": 2.521623419827013e-05,
+      "loss": 0.5061,
+      "step": 1825
+    },
+    {
+      "epoch": 0.5537264292128106,
+      "grad_norm": 5.614429473876953,
+      "learning_rate": 2.4800399201596807e-05,
+      "loss": 0.3377,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5612092187967674,
+      "grad_norm": 5.337092876434326,
+      "learning_rate": 2.438456420492349e-05,
+      "loss": 0.497,
+      "step": 1875
+    },
+    {
+      "epoch": 0.5686920083807243,
+      "grad_norm": 8.761651039123535,
+      "learning_rate": 2.3968729208250168e-05,
+      "loss": 0.4626,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5761747979646812,
+      "grad_norm": 4.3848466873168945,
+      "learning_rate": 2.355289421157685e-05,
+      "loss": 0.5425,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5836575875486382,
+      "grad_norm": 2.7267236709594727,
+      "learning_rate": 2.3137059214903528e-05,
+      "loss": 0.3931,
+      "step": 1950
+    },
+    {
+      "epoch": 0.591140377132595,
+      "grad_norm": 4.476986885070801,
+      "learning_rate": 2.272122421823021e-05,
+      "loss": 0.421,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5986231667165519,
+      "grad_norm": 5.569231033325195,
+      "learning_rate": 2.2305389221556888e-05,
+      "loss": 0.388,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6061059563005088,
+      "grad_norm": 4.156082630157471,
+      "learning_rate": 2.1889554224883567e-05,
+      "loss": 0.4566,
+      "step": 2025
+    },
+    {
+      "epoch": 0.6135887458844658,
+      "grad_norm": 4.638250827789307,
+      "learning_rate": 2.147371922821025e-05,
+      "loss": 0.4129,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6210715354684226,
+      "grad_norm": 3.4790878295898438,
+      "learning_rate": 2.1057884231536927e-05,
+      "loss": 0.3975,
+      "step": 2075
+    },
+    {
+      "epoch": 0.6285543250523795,
+      "grad_norm": 13.76499080657959,
+      "learning_rate": 2.0642049234863606e-05,
+      "loss": 0.4153,
+      "step": 2100
+    },
+    {
+      "epoch": 0.6360371146363364,
+      "grad_norm": 4.2070488929748535,
+      "learning_rate": 2.0226214238190287e-05,
+      "loss": 0.4893,
+      "step": 2125
+    },
+    {
+      "epoch": 0.6435199042202934,
+      "grad_norm": 1.6636909246444702,
+      "learning_rate": 1.9810379241516966e-05,
+      "loss": 0.5545,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6510026938042502,
+      "grad_norm": 2.6627988815307617,
+      "learning_rate": 1.9394544244843644e-05,
+      "loss": 0.4123,
+      "step": 2175
+    },
+    {
+      "epoch": 0.6584854833882071,
+      "grad_norm": 2.606734275817871,
+      "learning_rate": 1.8978709248170326e-05,
+      "loss": 0.4147,
+      "step": 2200
+    },
+    {
+      "epoch": 0.665968272972164,
+      "grad_norm": 4.407214164733887,
+      "learning_rate": 1.8562874251497005e-05,
+      "loss": 0.3227,
+      "step": 2225
+    },
+    {
+      "epoch": 0.673451062556121,
+      "grad_norm": 10.648530960083008,
+      "learning_rate": 1.8147039254823687e-05,
+      "loss": 0.5225,
+      "step": 2250
+    },
+    {
+      "epoch": 0.6809338521400778,
+      "grad_norm": 4.558552265167236,
+      "learning_rate": 1.7731204258150365e-05,
+      "loss": 0.4262,
+      "step": 2275
+    },
+    {
+      "epoch": 0.6884166417240347,
+      "grad_norm": 10.879168510437012,
+      "learning_rate": 1.7315369261477047e-05,
+      "loss": 0.4286,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6958994313079916,
+      "grad_norm": 3.295769453048706,
+      "learning_rate": 1.6899534264803725e-05,
+      "loss": 0.4639,
+      "step": 2325
+    },
+    {
+      "epoch": 0.7033822208919486,
+      "grad_norm": 5.799977779388428,
+      "learning_rate": 1.6483699268130407e-05,
+      "loss": 0.4348,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7108650104759054,
+      "grad_norm": 3.625521659851074,
+      "learning_rate": 1.6067864271457086e-05,
+      "loss": 0.4088,
+      "step": 2375
+    },
+    {
+      "epoch": 0.7183478000598623,
+      "grad_norm": 4.514614105224609,
+      "learning_rate": 1.5652029274783768e-05,
+      "loss": 0.4301,
+      "step": 2400
+    },
+    {
+      "epoch": 0.7258305896438192,
+      "grad_norm": 11.377728462219238,
+      "learning_rate": 1.5236194278110446e-05,
+      "loss": 0.4906,
+      "step": 2425
+    },
+    {
+      "epoch": 0.7333133792277761,
+      "grad_norm": 1.329950213432312,
+      "learning_rate": 1.4820359281437126e-05,
+      "loss": 0.4753,
+      "step": 2450
+    },
+    {
+      "epoch": 0.740796168811733,
+      "grad_norm": 4.047940254211426,
+      "learning_rate": 1.4404524284763806e-05,
+      "loss": 0.3542,
+      "step": 2475
+    },
+    {
+      "epoch": 0.7482789583956899,
+      "grad_norm": 6.413780689239502,
+      "learning_rate": 1.3988689288090487e-05,
+      "loss": 0.5139,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7557617479796468,
+      "grad_norm": 1.494303584098816,
+      "learning_rate": 1.3572854291417167e-05,
+      "loss": 0.3883,
+      "step": 2525
+    },
+    {
+      "epoch": 0.7632445375636037,
+      "grad_norm": 6.560792446136475,
+      "learning_rate": 1.3157019294743847e-05,
+      "loss": 0.4551,
+      "step": 2550
+    },
+    {
+      "epoch": 0.7707273271475606,
+      "grad_norm": 3.7073848247528076,
+      "learning_rate": 1.2741184298070527e-05,
+      "loss": 0.4342,
+      "step": 2575
+    },
+    {
+      "epoch": 0.7782101167315175,
+      "grad_norm": 6.4910359382629395,
+      "learning_rate": 1.2325349301397205e-05,
+      "loss": 0.3286,
+      "step": 2600
+    },
+    {
+      "epoch": 0.7856929063154744,
+      "grad_norm": 7.595745086669922,
+      "learning_rate": 1.1909514304723886e-05,
+      "loss": 0.4118,
+      "step": 2625
+    },
+    {
+      "epoch": 0.7931756958994313,
+      "grad_norm": 5.437306880950928,
+      "learning_rate": 1.1493679308050566e-05,
+      "loss": 0.4666,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8006584854833882,
+      "grad_norm": 2.1218721866607666,
+      "learning_rate": 1.1077844311377246e-05,
+      "loss": 0.4041,
+      "step": 2675
+    },
+    {
+      "epoch": 0.8081412750673451,
+      "grad_norm": 2.611057996749878,
+      "learning_rate": 1.0662009314703926e-05,
+      "loss": 0.3704,
+      "step": 2700
+    },
+    {
+      "epoch": 0.815624064651302,
+      "grad_norm": 3.661681652069092,
+      "learning_rate": 1.0246174318030606e-05,
+      "loss": 0.3822,
+      "step": 2725
+    },
+    {
+      "epoch": 0.8231068542352589,
+      "grad_norm": 4.607560157775879,
+      "learning_rate": 9.830339321357286e-06,
+      "loss": 0.4149,
+      "step": 2750
+    },
+    {
+      "epoch": 0.8305896438192159,
+      "grad_norm": 4.618942737579346,
+      "learning_rate": 9.414504324683967e-06,
+      "loss": 0.4174,
+      "step": 2775
+    },
+    {
+      "epoch": 0.8380724334031727,
+      "grad_norm": 5.718959808349609,
+      "learning_rate": 8.998669328010647e-06,
+      "loss": 0.4027,
+      "step": 2800
+    },
+    {
+      "epoch": 0.8455552229871296,
+      "grad_norm": 3.5075976848602295,
+      "learning_rate": 8.582834331337327e-06,
+      "loss": 0.4384,
+      "step": 2825
+    },
+    {
+      "epoch": 0.8530380125710865,
+      "grad_norm": 8.008058547973633,
+      "learning_rate": 8.166999334664007e-06,
+      "loss": 0.3897,
+      "step": 2850
+    },
+    {
+      "epoch": 0.8605208021550435,
+      "grad_norm": 3.166041851043701,
+      "learning_rate": 7.751164337990686e-06,
+      "loss": 0.339,
+      "step": 2875
+    },
+    {
+      "epoch": 0.8680035917390003,
+      "grad_norm": 10.711910247802734,
+      "learning_rate": 7.335329341317365e-06,
+      "loss": 0.4284,
+      "step": 2900
+    },
+    {
+      "epoch": 0.8754863813229572,
+      "grad_norm": 1.658119559288025,
+      "learning_rate": 6.919494344644045e-06,
+      "loss": 0.3585,
+      "step": 2925
+    },
+    {
+      "epoch": 0.8829691709069141,
+      "grad_norm": 11.725804328918457,
+      "learning_rate": 6.503659347970725e-06,
+      "loss": 0.4542,
+      "step": 2950
+    },
+    {
+      "epoch": 0.8904519604908709,
+      "grad_norm": 13.12930679321289,
+      "learning_rate": 6.0878243512974054e-06,
+      "loss": 0.3438,
+      "step": 2975
+    },
+    {
+      "epoch": 0.8979347500748279,
+      "grad_norm": 12.93932819366455,
+      "learning_rate": 5.671989354624086e-06,
+      "loss": 0.3635,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9054175396587848,
+      "grad_norm": 0.6720038652420044,
+      "learning_rate": 5.256154357950766e-06,
+      "loss": 0.4396,
+      "step": 3025
+    },
+    {
+      "epoch": 0.9129003292427417,
+      "grad_norm": 5.34990930557251,
+      "learning_rate": 4.840319361277446e-06,
+      "loss": 0.4032,
+      "step": 3050
+    },
+    {
+      "epoch": 0.9203831188266985,
+      "grad_norm": 1.8587225675582886,
+      "learning_rate": 4.424484364604125e-06,
+      "loss": 0.4679,
+      "step": 3075
+    },
+    {
+      "epoch": 0.9278659084106555,
+      "grad_norm": 6.022444725036621,
+      "learning_rate": 4.008649367930805e-06,
+      "loss": 0.3566,
+      "step": 3100
+    },
+    {
+      "epoch": 0.9353486979946124,
+      "grad_norm": 8.346709251403809,
+      "learning_rate": 3.592814371257485e-06,
+      "loss": 0.4395,
+      "step": 3125
+    },
+    {
+      "epoch": 0.9428314875785693,
+      "grad_norm": 1.5148768424987793,
+      "learning_rate": 3.1769793745841653e-06,
+      "loss": 0.3577,
+      "step": 3150
+    },
+    {
+      "epoch": 0.9503142771625261,
+      "grad_norm": 9.207695007324219,
+      "learning_rate": 2.761144377910845e-06,
+      "loss": 0.3368,
+      "step": 3175
+    },
+    {
+      "epoch": 0.9577970667464831,
+      "grad_norm": 7.755685329437256,
+      "learning_rate": 2.345309381237525e-06,
+      "loss": 0.4368,
+      "step": 3200
+    },
+    {
+      "epoch": 0.96527985633044,
+      "grad_norm": 9.233366966247559,
+      "learning_rate": 1.929474384564205e-06,
+      "loss": 0.339,
+      "step": 3225
+    },
+    {
+      "epoch": 0.9727626459143969,
+      "grad_norm": 4.844126224517822,
+      "learning_rate": 1.513639387890885e-06,
+      "loss": 0.4115,
+      "step": 3250
+    },
+    {
+      "epoch": 0.9802454354983537,
+      "grad_norm": 5.265417575836182,
+      "learning_rate": 1.097804391217565e-06,
+      "loss": 0.3768,
+      "step": 3275
+    },
+    {
+      "epoch": 0.9877282250823107,
+      "grad_norm": 4.222898960113525,
+      "learning_rate": 6.819693945442449e-07,
+      "loss": 0.452,
+      "step": 3300
+    },
+    {
+      "epoch": 0.9952110146662676,
+      "grad_norm": 8.413681030273438,
+      "learning_rate": 2.661343978709248e-07,
+      "loss": 0.375,
+      "step": 3325
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8176919622810956,
+      "eval_auc": 0.9024178348450937,
+      "eval_f1": 0.8509544787077826,
+      "eval_loss": 0.40547820925712585,
+      "eval_precision": 0.8474287106994882,
+      "eval_recall": 0.8545097075448513,
+      "eval_runtime": 1668.8106,
+      "eval_samples_per_second": 4.003,
+      "eval_steps_per_second": 0.25,
+      "step": 3341
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3341,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1757876485773312.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3341/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:befff7270d1a6c6686f743f6a23693911730b33978c93c96cd90536086e6df65
+size 5368

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli",
+  "_num_labels": 2,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "in-character",
+    "1": "out-of-character"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "in-character": 0,
+    "out-of-character": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db3c56c71229589e5cb6b92fbac028b4ac4418342c591dd1cf5b4ec55ad0990
+size 1115268200

runs/Jan14_14-08-43_r-maliru-dnd-autotrain-qwc498pd-27eb3-4nsxw/events.out.tfevents.1736863725.r-maliru-dnd-autotrain-qwc498pd-27eb3-4nsxw.108.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0395e5e4768286e7a6b6a0a43cde9041d9c031fd28f553baa444c9d10ae11ff6
-size 33375
+oid sha256:a15de790667499c57d34bf854a5250bd1dcfa9d7bcfebe4950824509dad2383e
+size 34459

runs/Jan14_14-08-43_r-maliru-dnd-autotrain-qwc498pd-27eb3-4nsxw/events.out.tfevents.1736897047.r-maliru-dnd-autotrain-qwc498pd-27eb3-4nsxw.108.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c29a790b87f765dadd87730a0583ca26ae9cb96277d3a033263dd4f91a07d2
+size 607

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07bf017c59c05b71d2f3de3ca420eeae57572049bc2903e829a041e6a1a25df9
+size 16316391

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250101": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:befff7270d1a6c6686f743f6a23693911730b33978c93c96cd90536086e6df65
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "mDeBERTa-v3-base-mnli-xnli-dnd/autotrain-data",
+    "model": "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli",
+    "lr": 5e-05,
+    "epochs": 1,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "mDeBERTa-v3-base-mnli-xnli-dnd",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "Maliru",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}