Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+library_name: transformers
+tags:
+- autotrain
+- text-classification
+base_model: microsoft/deberta-v3-base
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.19243484735488892
+
+f1: 0.9402777777777778
+
+precision: 0.9344375431331953
+
+recall: 0.9461914744933613
+
+auc: 0.9790224542805533
+
+accuracy: 0.9399021663172606

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

checkpoint-1432/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "_num_labels": 2,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "factual",
+    "1": "hallucinated"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "factual": 0,
+    "hallucinated": 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": "4.48.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-1432/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53db1f838bad4817f6c1cbdc35f126268c9e7925ae44600a7d908634592d258
+size 737719272

checkpoint-1432/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66cde081c954ee1b6a070c5cb3f9805d0aed4483e84bcbc33f05783aaf7fa401
+size 1475558394

checkpoint-1432/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9c0c6bd44eea60ace25470af0729bd426c197dedb4a97bdc350d443317fbb5
+size 14244

checkpoint-1432/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024f15676ce0b36a018340af28bc9f42314be542c5257fb96d76facebe0b3f96
+size 1064

checkpoint-1432/trainer_state.json

@@ -0,0 +1,467 @@
+{
+  "best_metric": 0.19243484735488892,
+  "best_model_checkpoint": "openeval-deberta-long/checkpoint-1432",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1432,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03494060097833683,
+      "grad_norm": 0.5007327795028687,
+      "learning_rate": 1.3966480446927375e-06,
+      "loss": 0.6937,
+      "step": 25
+    },
+    {
+      "epoch": 0.06988120195667366,
+      "grad_norm": 0.7577518820762634,
+      "learning_rate": 2.793296089385475e-06,
+      "loss": 0.696,
+      "step": 50
+    },
+    {
+      "epoch": 0.10482180293501048,
+      "grad_norm": 0.664239227771759,
+      "learning_rate": 4.189944134078213e-06,
+      "loss": 0.6919,
+      "step": 75
+    },
+    {
+      "epoch": 0.13976240391334732,
+      "grad_norm": 1.636892557144165,
+      "learning_rate": 5.58659217877095e-06,
+      "loss": 0.6745,
+      "step": 100
+    },
+    {
+      "epoch": 0.17470300489168414,
+      "grad_norm": 13.113431930541992,
+      "learning_rate": 6.983240223463687e-06,
+      "loss": 0.5972,
+      "step": 125
+    },
+    {
+      "epoch": 0.20964360587002095,
+      "grad_norm": 9.875704765319824,
+      "learning_rate": 8.379888268156426e-06,
+      "loss": 0.4869,
+      "step": 150
+    },
+    {
+      "epoch": 0.2445842068483578,
+      "grad_norm": 6.724992275238037,
+      "learning_rate": 9.720670391061454e-06,
+      "loss": 0.3554,
+      "step": 175
+    },
+    {
+      "epoch": 0.27952480782669464,
+      "grad_norm": 6.992024898529053,
+      "learning_rate": 1.1117318435754193e-05,
+      "loss": 0.3781,
+      "step": 200
+    },
+    {
+      "epoch": 0.31446540880503143,
+      "grad_norm": 5.473155498504639,
+      "learning_rate": 1.2513966480446928e-05,
+      "loss": 0.3273,
+      "step": 225
+    },
+    {
+      "epoch": 0.3494060097833683,
+      "grad_norm": 4.137131214141846,
+      "learning_rate": 1.3910614525139665e-05,
+      "loss": 0.3163,
+      "step": 250
+    },
+    {
+      "epoch": 0.3843466107617051,
+      "grad_norm": 6.087327003479004,
+      "learning_rate": 1.5307262569832404e-05,
+      "loss": 0.2807,
+      "step": 275
+    },
+    {
+      "epoch": 0.4192872117400419,
+      "grad_norm": 3.0208468437194824,
+      "learning_rate": 1.670391061452514e-05,
+      "loss": 0.3206,
+      "step": 300
+    },
+    {
+      "epoch": 0.45422781271837875,
+      "grad_norm": 3.7232978343963623,
+      "learning_rate": 1.8100558659217878e-05,
+      "loss": 0.3244,
+      "step": 325
+    },
+    {
+      "epoch": 0.4891684136967156,
+      "grad_norm": 2.8207011222839355,
+      "learning_rate": 1.9497206703910617e-05,
+      "loss": 0.2896,
+      "step": 350
+    },
+    {
+      "epoch": 0.5241090146750524,
+      "grad_norm": 4.429826259613037,
+      "learning_rate": 1.990052844264843e-05,
+      "loss": 0.267,
+      "step": 375
+    },
+    {
+      "epoch": 0.5590496156533893,
+      "grad_norm": 4.5808281898498535,
+      "learning_rate": 1.9745104134286604e-05,
+      "loss": 0.2599,
+      "step": 400
+    },
+    {
+      "epoch": 0.593990216631726,
+      "grad_norm": 4.419271469116211,
+      "learning_rate": 1.9589679825924777e-05,
+      "loss": 0.2979,
+      "step": 425
+    },
+    {
+      "epoch": 0.6289308176100629,
+      "grad_norm": 3.6506881713867188,
+      "learning_rate": 1.9434255517562946e-05,
+      "loss": 0.2505,
+      "step": 450
+    },
+    {
+      "epoch": 0.6638714185883997,
+      "grad_norm": 4.1857428550720215,
+      "learning_rate": 1.927883120920112e-05,
+      "loss": 0.2551,
+      "step": 475
+    },
+    {
+      "epoch": 0.6988120195667366,
+      "grad_norm": 2.720244884490967,
+      "learning_rate": 1.9123406900839293e-05,
+      "loss": 0.2595,
+      "step": 500
+    },
+    {
+      "epoch": 0.7337526205450734,
+      "grad_norm": 7.484561920166016,
+      "learning_rate": 1.8967982592477466e-05,
+      "loss": 0.2716,
+      "step": 525
+    },
+    {
+      "epoch": 0.7686932215234102,
+      "grad_norm": 4.350545406341553,
+      "learning_rate": 1.8812558284115635e-05,
+      "loss": 0.2505,
+      "step": 550
+    },
+    {
+      "epoch": 0.803633822501747,
+      "grad_norm": 3.8413989543914795,
+      "learning_rate": 1.8657133975753808e-05,
+      "loss": 0.2668,
+      "step": 575
+    },
+    {
+      "epoch": 0.8385744234800838,
+      "grad_norm": 3.7154204845428467,
+      "learning_rate": 1.850170966739198e-05,
+      "loss": 0.2582,
+      "step": 600
+    },
+    {
+      "epoch": 0.8735150244584207,
+      "grad_norm": 3.3066325187683105,
+      "learning_rate": 1.8346285359030154e-05,
+      "loss": 0.2347,
+      "step": 625
+    },
+    {
+      "epoch": 0.9084556254367575,
+      "grad_norm": 4.231185436248779,
+      "learning_rate": 1.8190861050668327e-05,
+      "loss": 0.2328,
+      "step": 650
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 3.8417835235595703,
+      "learning_rate": 1.8035436742306497e-05,
+      "loss": 0.2278,
+      "step": 675
+    },
+    {
+      "epoch": 0.9783368273934312,
+      "grad_norm": 7.155228614807129,
+      "learning_rate": 1.788001243394467e-05,
+      "loss": 0.2344,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9210342417889588,
+      "eval_auc": 0.970677486288683,
+      "eval_f1": 0.9224433768016472,
+      "eval_loss": 0.23471280932426453,
+      "eval_precision": 0.9062710721510452,
+      "eval_recall": 0.939203354297694,
+      "eval_runtime": 25.6664,
+      "eval_samples_per_second": 111.507,
+      "eval_steps_per_second": 3.507,
+      "step": 716
+    },
+    {
+      "epoch": 1.0125786163522013,
+      "grad_norm": 7.216368675231934,
+      "learning_rate": 1.7724588125582843e-05,
+      "loss": 0.2379,
+      "step": 725
+    },
+    {
+      "epoch": 1.047519217330538,
+      "grad_norm": 4.109630107879639,
+      "learning_rate": 1.7569163817221016e-05,
+      "loss": 0.2088,
+      "step": 750
+    },
+    {
+      "epoch": 1.082459818308875,
+      "grad_norm": 5.42812967300415,
+      "learning_rate": 1.7413739508859186e-05,
+      "loss": 0.1858,
+      "step": 775
+    },
+    {
+      "epoch": 1.1174004192872118,
+      "grad_norm": 2.5309982299804688,
+      "learning_rate": 1.725831520049736e-05,
+      "loss": 0.2089,
+      "step": 800
+    },
+    {
+      "epoch": 1.1523410202655486,
+      "grad_norm": 1.9790273904800415,
+      "learning_rate": 1.7102890892135532e-05,
+      "loss": 0.1803,
+      "step": 825
+    },
+    {
+      "epoch": 1.1872816212438855,
+      "grad_norm": 4.115412712097168,
+      "learning_rate": 1.6947466583773705e-05,
+      "loss": 0.2199,
+      "step": 850
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 2.643507719039917,
+      "learning_rate": 1.6792042275411874e-05,
+      "loss": 0.2483,
+      "step": 875
+    },
+    {
+      "epoch": 1.257162823200559,
+      "grad_norm": 2.535555124282837,
+      "learning_rate": 1.6636617967050048e-05,
+      "loss": 0.2304,
+      "step": 900
+    },
+    {
+      "epoch": 1.292103424178896,
+      "grad_norm": 1.9010531902313232,
+      "learning_rate": 1.648119365868822e-05,
+      "loss": 0.204,
+      "step": 925
+    },
+    {
+      "epoch": 1.3270440251572326,
+      "grad_norm": 5.073601722717285,
+      "learning_rate": 1.6325769350326394e-05,
+      "loss": 0.1329,
+      "step": 950
+    },
+    {
+      "epoch": 1.3619846261355695,
+      "grad_norm": 1.4883824586868286,
+      "learning_rate": 1.6170345041964563e-05,
+      "loss": 0.1795,
+      "step": 975
+    },
+    {
+      "epoch": 1.3969252271139063,
+      "grad_norm": 1.97958505153656,
+      "learning_rate": 1.6014920733602736e-05,
+      "loss": 0.1825,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4318658280922432,
+      "grad_norm": 5.010092735290527,
+      "learning_rate": 1.585949642524091e-05,
+      "loss": 0.1654,
+      "step": 1025
+    },
+    {
+      "epoch": 1.46680642907058,
+      "grad_norm": 3.9141337871551514,
+      "learning_rate": 1.5710289089213556e-05,
+      "loss": 0.1875,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5017470300489169,
+      "grad_norm": 4.0560736656188965,
+      "learning_rate": 1.5554864780851726e-05,
+      "loss": 0.1944,
+      "step": 1075
+    },
+    {
+      "epoch": 1.5366876310272537,
+      "grad_norm": 4.090770721435547,
+      "learning_rate": 1.540565744482437e-05,
+      "loss": 0.1882,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5716282320055905,
+      "grad_norm": 1.0099297761917114,
+      "learning_rate": 1.5250233136462544e-05,
+      "loss": 0.1625,
+      "step": 1125
+    },
+    {
+      "epoch": 1.6065688329839274,
+      "grad_norm": 8.940227508544922,
+      "learning_rate": 1.5094808828100716e-05,
+      "loss": 0.163,
+      "step": 1150
+    },
+    {
+      "epoch": 1.641509433962264,
+      "grad_norm": 3.1504862308502197,
+      "learning_rate": 1.4939384519738889e-05,
+      "loss": 0.1936,
+      "step": 1175
+    },
+    {
+      "epoch": 1.676450034940601,
+      "grad_norm": 3.5162193775177,
+      "learning_rate": 1.478396021137706e-05,
+      "loss": 0.1445,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7113906359189377,
+      "grad_norm": 9.932061195373535,
+      "learning_rate": 1.4628535903015233e-05,
+      "loss": 0.2089,
+      "step": 1225
+    },
+    {
+      "epoch": 1.7463312368972748,
+      "grad_norm": 4.012052536010742,
+      "learning_rate": 1.4473111594653404e-05,
+      "loss": 0.1518,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7812718378756114,
+      "grad_norm": 5.264890193939209,
+      "learning_rate": 1.4317687286291578e-05,
+      "loss": 0.1951,
+      "step": 1275
+    },
+    {
+      "epoch": 1.8162124388539485,
+      "grad_norm": 2.545083522796631,
+      "learning_rate": 1.416226297792975e-05,
+      "loss": 0.1692,
+      "step": 1300
+    },
+    {
+      "epoch": 1.851153039832285,
+      "grad_norm": 4.632214069366455,
+      "learning_rate": 1.4006838669567922e-05,
+      "loss": 0.182,
+      "step": 1325
+    },
+    {
+      "epoch": 1.886093640810622,
+      "grad_norm": 2.7571890354156494,
+      "learning_rate": 1.3851414361206095e-05,
+      "loss": 0.2029,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9210342417889588,
+      "grad_norm": 2.971035957336426,
+      "learning_rate": 1.3695990052844266e-05,
+      "loss": 0.1449,
+      "step": 1375
+    },
+    {
+      "epoch": 1.9559748427672956,
+      "grad_norm": 3.9962940216064453,
+      "learning_rate": 1.354056574448244e-05,
+      "loss": 0.1713,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9909154437456325,
+      "grad_norm": 2.5077712535858154,
+      "learning_rate": 1.338514143612061e-05,
+      "loss": 0.1701,
+      "step": 1425
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9399021663172606,
+      "eval_auc": 0.9790224542805533,
+      "eval_f1": 0.9402777777777778,
+      "eval_loss": 0.19243484735488892,
+      "eval_precision": 0.9344375431331953,
+      "eval_recall": 0.9461914744933613,
+      "eval_runtime": 25.705,
+      "eval_samples_per_second": 111.34,
+      "eval_steps_per_second": 3.501,
+      "step": 1432
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3575,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2048597520809984e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1432/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e439c1ed2e6ba654d4936cd35360c025a08a7e8ef07b3d6088fd6a03600eb4f3
+size 5368

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "_num_labels": 2,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "factual",
+    "1": "hallucinated"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "factual": 0,
+    "hallucinated": 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": "4.48.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53db1f838bad4817f6c1cbdc35f126268c9e7925ae44600a7d908634592d258
+size 737719272

runs/Feb23_22-53-19_r-jgilhuly16-openeval-94min0on-6d120-ig5z0/events.out.tfevents.1740351200.r-jgilhuly16-openeval-94min0on-6d120-ig5z0.214.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac94d1e45dfe5151ecc6d66e8d7c02c89ff776f13c53ce768a04e54a53ab56be
-size 31921
+oid sha256:ea42918b49ed8fe661776b835f20b01f9f196f63f519f5be9ede13e2eadc1e4b
+size 38491

runs/Feb23_22-53-19_r-jgilhuly16-openeval-94min0on-6d120-ig5z0/events.out.tfevents.1740354216.r-jgilhuly16-openeval-94min0on-6d120-ig5z0.214.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21018bdc6ab21ddec507e842df6decd8b9ea504c479315548eabd11555fc06f
+size 607

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

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
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "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:e439c1ed2e6ba654d4936cd35360c025a08a7e8ef07b3d6088fd6a03600eb4f3
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "openeval-deberta-long/autotrain-data",
+    "model": "microsoft/deberta-v3-base",
+    "lr": 2e-05,
+    "epochs": 5,
+    "max_seq_length": 512,
+    "batch_size": 16,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 2,
+    "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": "openeval-deberta-long",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "jgilhuly16",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}