End of training

README.md

@@ -0,0 +1,72 @@
+---
+base_model: vinai/bertweet-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: bertweet-base_3epoch5
+  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_3epoch5
+
+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: 1.0827
+- Accuracy: 0.7464
+- F1: 0.4094
+- Precision: 0.6162
+- Recall: 0.3065
+- Precision Sarcastic: 0.6162
+- Recall Sarcastic: 0.3065
+- F1 Sarcastic: 0.4094
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------------:|:----------------:|:------------:|
+| No log        | 1.0   | 347  | 0.7068          | 0.7147   | 0.01   | 1.0       | 0.0050 | 1.0                 | 0.0050           | 0.01         |
+| 0.52          | 2.0   | 694  | 0.5626          | 0.7478   | 0.4957 | 0.5811    | 0.4322 | 0.5811              | 0.4322           | 0.4957       |
+| 0.3534        | 3.0   | 1041 | 0.8067          | 0.7651   | 0.4475 | 0.6875    | 0.3317 | 0.6875              | 0.3317           | 0.4475       |
+| 0.3534        | 4.0   | 1388 | 0.9764          | 0.7378   | 0.4709 | 0.5586    | 0.4070 | 0.5586              | 0.4070           | 0.4709       |
+| 0.1664        | 5.0   | 1735 | 1.0827          | 0.7464   | 0.4094 | 0.6162    | 0.3065 | 0.6162              | 0.3065           | 0.4094       |
+
+
+### 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:c2a7ef2c657615635e4c08712635dd08257d330152ee25753256e3fad933b649
+size 539630168

runs/May31_16-26-47_e05c0a46fc41/events.out.tfevents.1717172807.e05c0a46fc41.1080.50

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f17e0baa15dac5611fe3a8f082280e4a27e47997c8d0e0dfa7e370859172e2
+size 9246

runs/May31_16-26-47_e05c0a46fc41/events.out.tfevents.1717173034.e05c0a46fc41.1080.51

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbf3f93dce808a115da196eb9308ec82a2876ac32bcb3c5d41470fbf10b35fe
+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 sha256:19e2d28bf948483624058133ad685288f315689e11f1bc4d910453f4c7f40aa3
+size 5112