End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+vocab.txt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: result-colab
+  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. -->
+
+# result-colab
+
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3751
+- Accuracy: 0.8853
+- Precision: 0.8785
+- Recall: 0.8773
+- F1: 0.8773
+
+## 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: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.3635        | 1.0   | 48   | 1.1593          | 0.5963   | 0.4671    | 0.5259 | 0.4501 |
+| 0.9895        | 2.0   | 96   | 0.7987          | 0.6881   | 0.6824    | 0.6271 | 0.6017 |
+| 0.6845        | 3.0   | 144  | 0.6432          | 0.7523   | 0.7789    | 0.7076 | 0.7071 |
+| 0.5856        | 4.0   | 192  | 0.5896          | 0.7844   | 0.8315    | 0.7457 | 0.7463 |
+| 0.4328        | 5.0   | 240  | 0.4232          | 0.8716   | 0.8750    | 0.8585 | 0.8645 |
+| 0.4298        | 6.0   | 288  | 0.4118          | 0.8853   | 0.8783    | 0.8810 | 0.8789 |
+| 0.322         | 7.0   | 336  | 0.3988          | 0.8807   | 0.8824    | 0.8655 | 0.8712 |
+| 0.3561        | 8.0   | 384  | 0.4169          | 0.8716   | 0.8630    | 0.8679 | 0.8637 |
+| 0.27          | 9.0   | 432  | 0.3779          | 0.8991   | 0.8972    | 0.8913 | 0.8938 |
+| 0.2472        | 10.0  | 480  | 0.3850          | 0.8991   | 0.8928    | 0.8942 | 0.8924 |
+| 0.2349        | 11.0  | 528  | 0.3749          | 0.8945   | 0.8855    | 0.8919 | 0.8875 |
+| 0.2491        | 12.0  | 576  | 0.3798          | 0.9037   | 0.8969    | 0.8992 | 0.8975 |
+| 0.2239        | 13.0  | 624  | 0.3778          | 0.8853   | 0.8783    | 0.8810 | 0.8793 |
+| 0.2276        | 14.0  | 672  | 0.3755          | 0.8899   | 0.8827    | 0.8823 | 0.8822 |
+| 0.206         | 15.0  | 720  | 0.3751          | 0.8853   | 0.8785    | 0.8773 | 0.8773 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 548052
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79bd51370f31d48ea0de60a3293a1cf9c445b1540288efaebc20d0f52e7c989
+size 2027820436

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "added_tokens_decoder": {
+    "302880": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "FastTextTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716937c1b15324b985dc0cb8be786f4a6dc58f5fb6d4e1c98ab265a8e4bfb6e6
+size 5048

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900f7d87e4835a2274c2cee2ac5709feffe239d2dd807146e9f482796a3ed37c
+size 17455191