End of training

README.md

@@ -0,0 +1,79 @@
+---
+base_model: vinai/bertweet-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: bertweetB_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. -->
+
+# bertweetB_15epoch
+
+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: 0.1645
+- Accuracy: 0.77
+- Precision: 0.2476
+- Recall: 0.3173
+- F1: 0.2757
+
+## 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  | 0.1306          | 0.8571   | 0.0       | 0.0    | 0.0    |
+| No log        | 2.0   | 434  | 0.1295          | 0.8571   | 0.0       | 0.0    | 0.0    |
+| 0.1937        | 3.0   | 651  | 0.1268          | 0.8571   | 0.0       | 0.0    | 0.0    |
+| 0.1937        | 4.0   | 868  | 0.1227          | 0.8593   | 0.3712    | 0.0701 | 0.1179 |
+| 0.1473        | 5.0   | 1085 | 0.1307          | 0.765    | 0.2292    | 0.4354 | 0.3003 |
+| 0.1473        | 6.0   | 1302 | 0.1270          | 0.7964   | 0.2457    | 0.3469 | 0.2877 |
+| 0.1018        | 7.0   | 1519 | 0.1398          | 0.7607   | 0.2276    | 0.4354 | 0.2978 |
+| 0.1018        | 8.0   | 1736 | 0.1449          | 0.7821   | 0.2323    | 0.3506 | 0.2786 |
+| 0.1018        | 9.0   | 1953 | 0.1408          | 0.7843   | 0.2681    | 0.3764 | 0.3127 |
+| 0.0648        | 10.0  | 2170 | 0.1535          | 0.78     | 0.2455    | 0.2878 | 0.2634 |
+| 0.0648        | 11.0  | 2387 | 0.1585          | 0.7593   | 0.2375    | 0.3911 | 0.2954 |
+| 0.0396        | 12.0  | 2604 | 0.1591          | 0.7757   | 0.2642    | 0.3100 | 0.2809 |
+| 0.0396        | 13.0  | 2821 | 0.1670          | 0.7614   | 0.2347    | 0.3432 | 0.2774 |
+| 0.0284        | 14.0  | 3038 | 0.1623          | 0.7793   | 0.2561    | 0.3026 | 0.2745 |
+| 0.0284        | 15.0  | 3255 | 0.1645          | 0.77     | 0.2476    | 0.3173 | 0.2757 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

added_tokens.json

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

config.json

@@ -0,0 +1,46 @@
+{
+  "_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,
+  "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": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_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 sha256:3c1da10645ab24a24faa9573687d9b6d851c4bd06548203215489a7139a85791
+size 539642472

runs/Jun06_12-00-05_b9092328a211/events.out.tfevents.1717675205.b9092328a211.7542.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9000cfe9603b770d2e8638f70e8bb5fb70b38503333f53ff6e8d5493c67650c3
+size 13872

runs/Jun06_12-00-05_b9092328a211/events.out.tfevents.1717675914.b9092328a211.7542.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b55bc4fe6956927cce9089d6abdfaa4ad10e51d9fab5223e952fb3918ec0089
+size 560

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 sha256:3a6f2bd880195fa0a6e8c0c500dfdf24b0f7fe844cd33399eb38cfc5e2f5bdd6
+size 5112