End of training

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+base_model: bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: FrozenLAST-BERT-multilingual-finetuned-CEFR_ner-3000news
+  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. -->
+
+# FrozenLAST-BERT-multilingual-finetuned-CEFR_ner-3000news
+
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5231
+- Accuracy: 0.4029
+- Precision: 0.4730
+- Recall: 0.6519
+- F1: 0.4491
+
+## 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: 2e-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: 12
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 132  | 0.6719          | 0.3466   | 0.5010    | 0.4385 | 0.3075 |
+| No log        | 2.0   | 264  | 0.5498          | 0.3741   | 0.5375    | 0.5142 | 0.3600 |
+| No log        | 3.0   | 396  | 0.4966          | 0.3872   | 0.4761    | 0.5740 | 0.3970 |
+| 0.6209        | 4.0   | 528  | 0.4753          | 0.3937   | 0.4654    | 0.5910 | 0.4146 |
+| 0.6209        | 5.0   | 660  | 0.4714          | 0.3952   | 0.4558    | 0.6100 | 0.4200 |
+| 0.6209        | 6.0   | 792  | 0.4684          | 0.3989   | 0.4640    | 0.6139 | 0.4275 |
+| 0.6209        | 7.0   | 924  | 0.4813          | 0.3994   | 0.4673    | 0.6276 | 0.4376 |
+| 0.2738        | 8.0   | 1056 | 0.4890          | 0.4015   | 0.4760    | 0.6404 | 0.4470 |
+| 0.2738        | 9.0   | 1188 | 0.5157          | 0.4013   | 0.4723    | 0.6386 | 0.4432 |
+| 0.2738        | 10.0  | 1320 | 0.5229          | 0.4019   | 0.4665    | 0.6498 | 0.4433 |
+| 0.2738        | 11.0  | 1452 | 0.5188          | 0.4024   | 0.4673    | 0.6529 | 0.4448 |
+| 0.1745        | 12.0  | 1584 | 0.5231          | 0.4029   | 0.4730    | 0.6519 | 0.4491 |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "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,
+    "LABEL_6": 6
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24135e9cbfb8875505a3e92fe204f6fe23cdb501d76c576563405766663b59a8
+size 709096284

runs/May24_14-47-52_ee6ee594f155/events.out.tfevents.1716562083.ee6ee594f155.253.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0b1fccd6cc76b1cfb5a5f92db3e80449cdf2c9da2b06755394c8a69844a7a1
+size 12048

runs/May24_14-47-52_ee6ee594f155/events.out.tfevents.1716563106.ee6ee594f155.253.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814ee5a0751b48bd193a8d134078dde78fcb94bb6df64f7f4d9bf1f7a9c373a5
+size 560

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d0b953e23915ebbbb160a195b3ddc8a81c121cb1916644ef3715989b072fcf
+size 5176