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
+bertweet_finetuned/preds_from_model.csv filter=lfs diff=lfs merge=lfs -text

bertweet_finetuned/best_checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6962af37895aaada2468609650dc4b33b70f32ee8686f655cdcd428cdeead064
+size 939408188

bertweet_finetuned/final_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9289d512b49a7037f4c24845ef6486a40721f8bfd51bbaebe1cdf8892c8cac04
+size 540584792

bertweet_finetuned/inference_config.json

@@ -0,0 +1 @@
+{"MAX_LEN": 128, "SEP": "</s>"}

bertweet_finetuned/label_classes.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e95d56cf907dc2aea39ee0bec10da0e1a67a0a0855ff9b508be45bbac494d76
+size 37

bertweet_finetuned/meta_pipeline.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b3af29249d2c287dd60b97d18c11ea725d7b4c36bf69c6de9222340ed04435
+size 4541

bertweet_finetuned/model_metadata.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb441c8486b604e107a17ade601b7c39dff2de06a63e903b2dad82c0e844fa1
+size 5140

bertweet_finetuned/preds_from_model.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f5ac19e9a45094dec107df5294c7323c3ed37f58092bdd78914d6bcc93b2cb
+size 61854171

bertweet_finetuned/tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

bertweet_finetuned/tokenizer/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

bertweet_finetuned/tokenizer/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalization": false,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BertweetTokenizer",
+  "unk_token": "<unk>"
+}

e5_large/best_checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e939f37e079360c857192f0edc597db8970a920b8172d6040a3eedcc80335842
+size 2049712089

e5_large/inference_config.json

@@ -0,0 +1 @@
+{"MAX_LEN": 128, "SEP": "[SEP]", "MODEL_NAME": "intfloat/e5-large-v2"}

e5_large/label_classes.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e95d56cf907dc2aea39ee0bec10da0e1a67a0a0855ff9b508be45bbac494d76
+size 37

e5_large/meta_pipeline.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4406893d7dc7e29d12cf25f18d3e27c20ebcf4bdbf04200a3a5eb3f9972b1c
+size 4539

e5_large/tokenizer/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

e5_large/tokenizer/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

e5_large/training_history.json

@@ -0,0 +1,192 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 0.6694036747442733,
+    "accuracy": 0.6384877920714098,
+    "precision": 0.6396098788152397,
+    "recall": 0.6384877920714098,
+    "f1": 0.6361877622449531,
+    "roc_auc": 0.6905002636963176,
+    "confusion_matrix": [
+      [
+        20710,
+        16304
+      ],
+      [
+        11236,
+        27930
+      ]
+    ]
+  },
+  {
+    "epoch": 2,
+    "train_loss": 0.5936620373939206,
+    "accuracy": 0.712050406930953,
+    "precision": 0.7125221690771839,
+    "recall": 0.712050406930953,
+    "f1": 0.711412016449667,
+    "roc_auc": 0.7885406459400497,
+    "confusion_matrix": [
+      [
+        24715,
+        12299
+      ],
+      [
+        9637,
+        29529
+      ]
+    ]
+  },
+  {
+    "epoch": 3,
+    "train_loss": 0.5445732520047349,
+    "accuracy": 0.7466264111315306,
+    "precision": 0.7470089523551816,
+    "recall": 0.7466264111315306,
+    "f1": 0.7466769304831232,
+    "roc_auc": 0.827907726657352,
+    "confusion_matrix": [
+      [
+        27886,
+        9128
+      ],
+      [
+        10174,
+        28992
+      ]
+    ]
+  },
+  {
+    "epoch": 4,
+    "train_loss": 0.5105602312859151,
+    "accuracy": 0.7633368338146496,
+    "precision": 0.7633707551299388,
+    "recall": 0.7633368338146496,
+    "f1": 0.7633502128901711,
+    "roc_auc": 0.8458466395889389,
+    "confusion_matrix": [
+      [
+        28082,
+        8932
+      ],
+      [
+        9097,
+        30069
+      ]
+    ]
+  },
+  {
+    "epoch": 5,
+    "train_loss": 0.48103076480012597,
+    "accuracy": 0.7764767655552639,
+    "precision": 0.7766028854553568,
+    "recall": 0.7764767655552639,
+    "f1": 0.7762931616528126,
+    "roc_auc": 0.8607994758196372,
+    "confusion_matrix": [
+      [
+        27822,
+        9192
+      ],
+      [
+        7836,
+        31330
+      ]
+    ]
+  },
+  {
+    "epoch": 6,
+    "train_loss": 0.45285762216234077,
+    "accuracy": 0.7863349960619586,
+    "precision": 0.786550974702636,
+    "recall": 0.7863349960619586,
+    "f1": 0.7863729433058431,
+    "roc_auc": 0.8707636359308418,
+    "confusion_matrix": [
+      [
+        29235,
+        7779
+      ],
+      [
+        8498,
+        30668
+      ]
+    ]
+  },
+  {
+    "epoch": 7,
+    "train_loss": 0.42440437866778397,
+    "accuracy": 0.7881333683381465,
+    "precision": 0.7919868312451798,
+    "recall": 0.7881333683381465,
+    "f1": 0.7878603466154905,
+    "roc_auc": 0.8755943217566788,
+    "confusion_matrix": [
+      [
+        30951,
+        6063
+      ],
+      [
+        10077,
+        29089
+      ]
+    ]
+  },
+  {
+    "epoch": 8,
+    "train_loss": 0.3885842357222038,
+    "accuracy": 0.7932528222630612,
+    "precision": 0.7932259994398904,
+    "recall": 0.7932528222630612,
+    "f1": 0.7932070934632307,
+    "roc_auc": 0.8779366478685279,
+    "confusion_matrix": [
+      [
+        28896,
+        8118
+      ],
+      [
+        7632,
+        31534
+      ]
+    ]
+  },
+  {
+    "epoch": 9,
+    "train_loss": 0.3425717065478533,
+    "accuracy": 0.7886584405355737,
+    "precision": 0.7887057068927522,
+    "recall": 0.7886584405355737,
+    "f1": 0.7885404112089442,
+    "roc_auc": 0.8750088332658279,
+    "confusion_matrix": [
+      [
+        28454,
+        8560
+      ],
+      [
+        7540,
+        31626
+      ]
+    ]
+  },
+  {
+    "epoch": 10,
+    "train_loss": 0.2898458522586866,
+    "accuracy": 0.7866631661853505,
+    "precision": 0.7867469948727277,
+    "recall": 0.7866631661853505,
+    "f1": 0.7865210069555763,
+    "roc_auc": 0.8706981988520192,
+    "confusion_matrix": [
+      [
+        28306,
+        8708
+      ],
+      [
+        7544,
+        31622
+      ]
+    ]
+  }
+]

embedding_dimension/embeddings/all-MiniLM-L6-v2_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9023267ad565f96cb00fcccff0da5a24d89061abc9614bcee8c55598fbbea85
+size 936087680

embedding_dimension/embeddings/all-MiniLM-L6-v2_val.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:051b400e5796b31cf55302d8a2d92dd4b8164a3b8b37b5e7d7d41076047e119b
+size 234023552

embedding_dimension/embeddings/all-mpnet-base-v2_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fb9594c31b6cfc9b77ca183672306aada3beb35c01fd6630750794574840d2
+size 1872175232

embedding_dimension/embeddings/all-mpnet-base-v2_val.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdceb5b0321b8d5e83d1941968daee4c5fd0f4f66a82614aead99d70743f842e
+size 468046976

embedding_dimension/embeddings/e5-large-v2_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6315aaad2c95e01b2ecc667e782bc356f53641c8a51af46af110e40c6beef5f1
+size 2496233600

embedding_dimension/embeddings/e5-large-v2_val.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fadbd0ccdba93db930502b8320c12b5cee76e9d304fd43db8b86619a26b1a6f3
+size 624062592

gpt2_large_sarcasm_finetuned/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1164ba8e8dfb344b4ea4054b75350acfd547133eb286f2e4f5bfb3864d094437
+size 3096259675

gpt2_large_sarcasm_finetuned/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gpt2_large_sarcasm_finetuned/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

gpt2_large_sarcasm_finetuned/training_history.json

@@ -0,0 +1,30 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 0.5006914643305583,
+    "train_acc": 0.7534943284165511,
+    "val_loss": 0.4765789475314265,
+    "val_acc": 0.770175899186138
+  },
+  {
+    "epoch": 2,
+    "train_loss": 0.41041818162335203,
+    "train_acc": 0.8138054961195197,
+    "val_loss": 0.485660226567899,
+    "val_acc": 0.7766211604095563
+  },
+  {
+    "epoch": 3,
+    "train_loss": 0.29277975993642885,
+    "train_acc": 0.8804642865998358,
+    "val_loss": 0.5854064271237948,
+    "val_acc": 0.7670517196114466
+  },
+  {
+    "epoch": 4,
+    "train_loss": 0.20523463562336314,
+    "train_acc": 0.9268914880303846,
+    "val_loss": 0.7716748032591614,
+    "val_acc": 0.7618928852717248
+  }
+]

gpt2_large_sarcasm_finetuned/training_metadata.json

@@ -0,0 +1,32 @@
+{
+  "epoch": 1,
+  "train_loss": 0.5006914643305583,
+  "train_acc": 0.7534943284165511,
+  "val_loss": 0.4765789475314265,
+  "val_acc": 0.770175899186138,
+  "model_config": {
+    "model_name": "gpt2-large",
+    "max_length": 128,
+    "num_labels": 2,
+    "use_parent_context": false
+  },
+  "training_config": {
+    "num_epochs": 6,
+    "batch_size": 8,
+    "learning_rate": 2e-05,
+    "warmup_steps": 500,
+    "weight_decay": 0.01,
+    "max_grad_norm": 1.0,
+    "gradient_accumulation_steps": 2,
+    "bf16": true,
+    "fp16": false,
+    "dataloader_num_workers": 4,
+    "save_steps": 1000,
+    "eval_steps": 500,
+    "logging_steps": 100,
+    "save_total_limit": 3,
+    "validation_split": 0.1,
+    "early_stopping_patience": 3,
+    "seed": 42
+  }
+}

gpt2_small_sarcasm_finetuned/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4324651096363dc3652ed6005ebdd7a8c1a5389d473155b4659fcd0e678ed6
+size 497809691

gpt2_small_sarcasm_finetuned/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gpt2_small_sarcasm_finetuned/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

gpt2_small_sarcasm_finetuned/training_history.json

@@ -0,0 +1,30 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 0.5349204899357074,
+    "train_acc": 0.7375567194808718,
+    "val_loss": 0.494891486287505,
+    "val_acc": 0.7595825676030454
+  },
+  {
+    "epoch": 2,
+    "train_loss": 0.465825739455718,
+    "train_acc": 0.7769887005896929,
+    "val_loss": 0.5023922561388189,
+    "val_acc": 0.7702152796009452
+  },
+  {
+    "epoch": 3,
+    "train_loss": 0.4263289485021802,
+    "train_acc": 0.8026329799259346,
+    "val_loss": 0.5046512643927501,
+    "val_acc": 0.7708453662378577
+  },
+  {
+    "epoch": 4,
+    "train_loss": 0.3876040897047569,
+    "train_acc": 0.8258998178267268,
+    "val_loss": 0.5368210367767664,
+    "val_acc": 0.7700446311367813
+  }
+]

gpt2_small_sarcasm_finetuned/training_metadata.json

@@ -0,0 +1,32 @@
+{
+  "epoch": 1,
+  "train_loss": 0.5349204899357074,
+  "train_acc": 0.7375567194808718,
+  "val_loss": 0.494891486287505,
+  "val_acc": 0.7595825676030454,
+  "model_config": {
+    "model_name": "gpt2",
+    "max_length": 128,
+    "num_labels": 2,
+    "use_parent_context": false
+  },
+  "training_config": {
+    "num_epochs": 6,
+    "batch_size": 16,
+    "learning_rate": 2e-05,
+    "warmup_steps": 500,
+    "weight_decay": 0.01,
+    "max_grad_norm": 1.0,
+    "gradient_accumulation_steps": 1,
+    "bf16": true,
+    "fp16": false,
+    "dataloader_num_workers": 4,
+    "save_steps": 1000,
+    "eval_steps": 500,
+    "logging_steps": 100,
+    "save_total_limit": 3,
+    "validation_split": 0.1,
+    "early_stopping_patience": 3,
+    "seed": 42
+  }
+}