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: NLP_91_1
+  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. -->
+
+# NLP_91_1
+
+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: 0.4408
+- Accuracy: 0.9220
+- Precision: 0.9156
+- Recall: 0.9170
+- F1: 0.9158
+
+## 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     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.309         | 1.0   | 48   | 0.4280          | 0.8532   | 0.8506    | 0.8461 | 0.8454 |
+| 0.2595        | 2.0   | 96   | 0.4335          | 0.8807   | 0.8767    | 0.8766 | 0.8738 |
+| 0.2196        | 3.0   | 144  | 0.3883          | 0.8945   | 0.8956    | 0.8869 | 0.8876 |
+| 0.1812        | 4.0   | 192  | 0.4664          | 0.8761   | 0.8856    | 0.8614 | 0.8638 |
+| 0.1256        | 5.0   | 240  | 0.4764          | 0.8670   | 0.8750    | 0.8627 | 0.8625 |
+| 0.142         | 6.0   | 288  | 0.5258          | 0.8670   | 0.8818    | 0.8580 | 0.8607 |
+| 0.1006        | 7.0   | 336  | 0.4323          | 0.9037   | 0.8961    | 0.8989 | 0.8970 |
+| 0.0897        | 8.0   | 384  | 0.4659          | 0.8991   | 0.8959    | 0.8891 | 0.8914 |
+| 0.0595        | 9.0   | 432  | 0.4569          | 0.9174   | 0.9149    | 0.9099 | 0.9115 |
+| 0.0399        | 10.0  | 480  | 0.4592          | 0.9037   | 0.8981    | 0.8970 | 0.8966 |
+| 0.056         | 11.0  | 528  | 0.4461          | 0.9174   | 0.9102    | 0.9091 | 0.9094 |
+| 0.0451        | 12.0  | 576  | 0.4772          | 0.8991   | 0.8926    | 0.8891 | 0.8906 |
+| 0.0309        | 13.0  | 624  | 0.4396          | 0.9220   | 0.9160    | 0.9169 | 0.9155 |
+| 0.0338        | 14.0  | 672  | 0.4423          | 0.9220   | 0.9156    | 0.9170 | 0.9158 |
+| 0.0458        | 15.0  | 720  | 0.4408          | 0.9220   | 0.9156    | 0.9170 | 0.9158 |
+
+
+### 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": 548133
+}

fasttext_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edae19e61dbf3964d4d41c959199d644783b07e31fa84c97a2e74e8abed9c737
+size 9534119835

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66cb4507e9930ee9320cb73c92b5b42df3374c9ebffea808a7de85a935343828
+size 2028069268

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ee997794dc35fb390bf3b2e61e989defd99344c5e09526efd4f08b8b752a77
+size 5112

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a2c8ad1723b1952d64ad5155b3cc87e13ae15e55cc9c6c2a2c078c7ce90216
+size 17457360