End of training

README.md

@@ -0,0 +1,77 @@
+---
+base_model: vinai/bertweet-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: bertweet-base_3epoch10
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bertweet-base_3epoch10
+
+This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7005
+- Accuracy: 0.7392
+- F1: 0.4217
+- Precision: 0.5789
+- Recall: 0.3317
+- Precision Sarcastic: 0.5789
+- Recall Sarcastic: 0.3317
+- F1 Sarcastic: 0.4217
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------------:|:----------------:|:------------:|
+| No log        | 1.0   | 174  | 1.3971          | 0.7493   | 0.4    | 0.6374    | 0.2915 | 0.6374              | 0.2915           | 0.4          |
+| No log        | 2.0   | 348  | 1.0371          | 0.7334   | 0.3854 | 0.5686    | 0.2915 | 0.5686              | 0.2915           | 0.3854       |
+| 0.0617        | 3.0   | 522  | 1.6060          | 0.7147   | 0.4277 | 0.5034    | 0.3719 | 0.5034              | 0.3719           | 0.4277       |
+| 0.0617        | 4.0   | 696  | 1.3603          | 0.7464   | 0.4172 | 0.6117    | 0.3166 | 0.6117              | 0.3166           | 0.4172       |
+| 0.0617        | 5.0   | 870  | 1.5872          | 0.7478   | 0.4373 | 0.6071    | 0.3417 | 0.6071              | 0.3417           | 0.4373       |
+| 0.032         | 6.0   | 1044 | 1.4206          | 0.7493   | 0.3916 | 0.6437    | 0.2814 | 0.6437              | 0.2814           | 0.3916       |
+| 0.032         | 7.0   | 1218 | 1.4775          | 0.7507   | 0.4055 | 0.6413    | 0.2965 | 0.6413              | 0.2965           | 0.4055       |
+| 0.032         | 8.0   | 1392 | 1.5835          | 0.7421   | 0.4389 | 0.5833    | 0.3518 | 0.5833              | 0.3518           | 0.4389       |
+| 0.0125        | 9.0   | 1566 | 1.7009          | 0.7464   | 0.3846 | 0.6322    | 0.2764 | 0.6322              | 0.2764           | 0.3846       |
+| 0.0125        | 10.0  | 1740 | 1.7005          | 0.7392   | 0.4217 | 0.5789    | 0.3317 | 0.5789              | 0.3317           | 0.4217       |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

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

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "vinai/bertweet-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertweetTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa1d547612befd8bcaf0cd6e86cc1169bc3ca9cd7e0be9afad6a30c4be696b4
+size 539630168

runs/May31_16-41-45_e05c0a46fc41/events.out.tfevents.1717173706.e05c0a46fc41.1080.54

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92461cd3884f8df76031c1e5103325376a34deec1d03796732466f9e98e3d268
+size 12507

runs/May31_16-41-45_e05c0a46fc41/events.out.tfevents.1717174070.e05c0a46fc41.1080.55

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05170ff31167e807ff4d3ccabc28404b9d0f8a7873102991dc4bfccc5fb75f20
+size 739

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>"
+}

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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4f9aad385a6585630a925a662d61e1a511f07f8b7d820ce37fdccca30a04ae
+size 5112