End of training

README.md

@@ -0,0 +1,79 @@
+---
+base_model: cardiffnlp/twitter-roberta-base-irony
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: Twroberta-baseB_15epoch
+  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. -->
+
+# Twroberta-baseB_15epoch
+
+This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-irony](https://huggingface.co/cardiffnlp/twitter-roberta-base-irony) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1971
+- Accuracy: 0.7686
+- Precision: 0.2328
+- Recall: 0.3210
+- F1: 0.2693
+
+## 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: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 217  | 0.1248          | 0.8571   | 0.0       | 0.0    | 0.0    |
+| No log        | 2.0   | 434  | 0.1250          | 0.8679   | 0.5258    | 0.0701 | 0.1237 |
+| 0.1617        | 3.0   | 651  | 0.1225          | 0.825    | 0.2771    | 0.2657 | 0.2712 |
+| 0.1617        | 4.0   | 868  | 0.1325          | 0.8079   | 0.3164    | 0.2583 | 0.2554 |
+| 0.0885        | 5.0   | 1085 | 0.1553          | 0.7707   | 0.2169    | 0.2694 | 0.2391 |
+| 0.0885        | 6.0   | 1302 | 0.1680          | 0.7507   | 0.2112    | 0.3358 | 0.2592 |
+| 0.0392        | 7.0   | 1519 | 0.2129          | 0.7093   | 0.1936    | 0.3875 | 0.2575 |
+| 0.0392        | 8.0   | 1736 | 0.1717          | 0.7764   | 0.2316    | 0.2841 | 0.2528 |
+| 0.0392        | 9.0   | 1953 | 0.1915          | 0.7507   | 0.2287    | 0.3321 | 0.2671 |
+| 0.0178        | 10.0  | 2170 | 0.1987          | 0.7586   | 0.2294    | 0.3653 | 0.2809 |
+| 0.0178        | 11.0  | 2387 | 0.1923          | 0.7564   | 0.2287    | 0.3358 | 0.2710 |
+| 0.0108        | 12.0  | 2604 | 0.1925          | 0.7586   | 0.2317    | 0.3358 | 0.2729 |
+| 0.0108        | 13.0  | 2821 | 0.1965          | 0.775    | 0.2356    | 0.3284 | 0.2743 |
+| 0.0078        | 14.0  | 3038 | 0.1964          | 0.7621   | 0.2326    | 0.3284 | 0.2712 |
+| 0.0078        | 15.0  | 3255 | 0.1971          | 0.7686   | 0.2328    | 0.3210 | 0.2693 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-irony",
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30a9ddc30b3c762b836eca072eb3a79f6f83b0bd35cf66d92293dcb56dcafbe
+size 498625128

runs/Jun06_12-40-59_b9092328a211/events.out.tfevents.1717677660.b9092328a211.7542.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f31e6006291388fa298b4f5c3c1c079c561e3aafe2e34ad56d737b09f154b8e
+size 13880

runs/Jun06_12-40-59_b9092328a211/events.out.tfevents.1717678358.b9092328a211.7542.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45a114ff4db7df39ddbed353025e009e6672110ef88d221684933758c8cab19
+size 560

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b86085f00dab5d3c4db75db35ec6381dc854cf55d027b6fc50789048fecc9ea
+size 5112