Upload 11 files

.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 +1,37 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "NOT",
+    "1": "CLICKBAIT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "CLICKBAIT": 1,
+    "NOT": 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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "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 sha256:2d7a6436817169350b01add89aee2b60499f6b1d6bb682bdb1538463c5ab5930
+size 1112205008

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0659984a4025b8a363ba36484d0223ec604f976290c8f6c498df9c9d083de2
+size 2224529221

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6b96220c3adc2f2b0c7d9f9cf33549a031be9030480a94df787e6428c29860
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:560b78473254f10b9b03b31693cd92d340e289c1c7c59cf9e3af8002a3c14da3
+size 627

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62bf674b1c395bed20f40d50c04a2b4de2478fe605f07bc768335299bc8161e1
+size 17083021

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": 0.1280977874994278,
+  "best_model_checkpoint": "saved_model/checkpoint-7574",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 7574,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9867969368893584e-05,
+      "loss": 0.2264,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9735938737787167e-05,
+      "loss": 0.1508,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9603908106680753e-05,
+      "loss": 0.131,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9471877475574335e-05,
+      "loss": 0.1143,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9339846844467918e-05,
+      "loss": 0.1038,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.92078162133615e-05,
+      "loss": 0.1031,
+      "step": 3000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9075785582255083e-05,
+      "loss": 0.0996,
+      "step": 3500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8943754951148666e-05,
+      "loss": 0.0957,
+      "step": 4000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.881172432004225e-05,
+      "loss": 0.0929,
+      "step": 4500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8679693688935834e-05,
+      "loss": 0.0875,
+      "step": 5000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.8547663057829417e-05,
+      "loss": 0.0888,
+      "step": 5500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.8415632426723e-05,
+      "loss": 0.0779,
+      "step": 6000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.8283601795616582e-05,
+      "loss": 0.0768,
+      "step": 6500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.8151571164510168e-05,
+      "loss": 0.0733,
+      "step": 7000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.801954053340375e-05,
+      "loss": 0.0749,
+      "step": 7500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9679495642989173,
+      "eval_loss": 0.1280977874994278,
+      "eval_macro_f1": 0.9678598089097803,
+      "eval_runtime": 110.0803,
+      "eval_samples_per_second": 275.217,
+      "eval_steps_per_second": 8.603,
+      "step": 7574
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 75740,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 3.188485013274624e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4772f8a285e51b1f4ce6642661575acc9fd8a88e7426990be06d9ff304b38418
+size 4091