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_3epoch10.2
+  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_3epoch10.2
+
+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: 1.8545
+- Accuracy: 0.7493
+- F1: 0.4663
+- Precision: 0.5984
+- Recall: 0.3819
+- Precision Sarcastic: 0.5984
+- Recall Sarcastic: 0.3819
+- F1 Sarcastic: 0.4663
+
+## 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: 5e-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  | 1.8493          | 0.7464   | 0.4323 | 0.6036    | 0.3367 | 0.6036              | 0.3367           | 0.4323       |
+| No log        | 2.0   | 348  | 1.5481          | 0.7522   | 0.5301 | 0.5808    | 0.4874 | 0.5808              | 0.4874           | 0.5301       |
+| 0.0477        | 3.0   | 522  | 1.6249          | 0.7565   | 0.4531 | 0.6364    | 0.3518 | 0.6364              | 0.3518           | 0.4531       |
+| 0.0477        | 4.0   | 696  | 1.6593          | 0.7464   | 0.4793 | 0.5827    | 0.4070 | 0.5827              | 0.4070           | 0.4793       |
+| 0.0477        | 5.0   | 870  | 1.7213          | 0.7493   | 0.42   | 0.6238    | 0.3166 | 0.6238              | 0.3166           | 0.42         |
+| 0.0277        | 6.0   | 1044 | 1.7249          | 0.7450   | 0.4381 | 0.5948    | 0.3467 | 0.5948              | 0.3467           | 0.4381       |
+| 0.0277        | 7.0   | 1218 | 1.8038          | 0.7450   | 0.4486 | 0.5902    | 0.3618 | 0.5902              | 0.3618           | 0.4486       |
+| 0.0277        | 8.0   | 1392 | 1.8409          | 0.7493   | 0.4387 | 0.6126    | 0.3417 | 0.6126              | 0.3417           | 0.4387       |
+| 0.0105        | 9.0   | 1566 | 1.8427          | 0.7522   | 0.4487 | 0.6195    | 0.3518 | 0.6195              | 0.3518           | 0.4487       |
+| 0.0105        | 10.0  | 1740 | 1.8545          | 0.7493   | 0.4663 | 0.5984    | 0.3819 | 0.5984              | 0.3819           | 0.4663       |
+
+
+### 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 sha256:7371e4e9e5dc7cd2af2f49076d29e36b5d11fdead330730598e6b71d8f7e26d8
+size 539630168

runs/May31_16-48-37_e05c0a46fc41/events.out.tfevents.1717174117.e05c0a46fc41.1080.56

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5669e3ab24bf1ba97958ccf75a1c0ee1a9615aa9636c0ce12c101915d4294997
+size 12513

runs/May31_16-48-37_e05c0a46fc41/events.out.tfevents.1717174483.e05c0a46fc41.1080.57

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb7150461052f78359c8dc587e1eb772f72a6c66917e1164f42bd6851777afd
+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 sha256:03a37e7238776764c8ac04b07ce286b427a88335c285a4fb10aec38bf075caa3
+size 5112