End of training

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: cservan/malbert-base-cased-128k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: MalBERT-multilingual-finetuned-CEFR_sentences
+  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. -->
+
+# MalBERT-multilingual-finetuned-CEFR_sentences
+
+This model is a fine-tuned version of [cservan/malbert-base-cased-128k](https://huggingface.co/cservan/malbert-base-cased-128k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9301
+- Accuracy: 0.6113
+- Precision: 0.5964
+- Recall: 0.6113
+- F1: 0.6029
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 449  | 0.9743          | 0.5966   | 0.5933    | 0.5966 | 0.5874 |
+| 1.0509        | 2.0   | 898  | 0.9987          | 0.5673   | 0.5650    | 0.5673 | 0.5574 |
+| 0.8073        | 3.0   | 1347 | 0.9301          | 0.6113   | 0.5964    | 0.6113 | 0.6029 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "cservan/malbert-base-cased-128k",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "eos_token_ids": null,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "A1",
+    "2": "A2",
+    "3": "B1",
+    "4": "B2",
+    "5": "C1",
+    "6": "C2"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "A1": 1,
+    "A2": 2,
+    "B1": 3,
+    "B2": 4,
+    "C1": 5,
+    "C2": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "vocab_size": 128000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf7cdee9a5d4f94951e2a664dfe2962cdaf615ad917a1c7c41c89dedbf9d505
+size 96935292

runs/Jun23_18-38-00_fbe13c4cce02/events.out.tfevents.1719167890.fbe13c4cce02.1139.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a7a892ef4ba06112e93ea70053b60d04c538e49a12d69e7089deac589f33e6
+size 5351

runs/Jun23_18-38-00_fbe13c4cce02/events.out.tfevents.1719168023.fbe13c4cce02.1139.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7503f5969ad56fcd7d9354f874c45213b591f4e6e1fdf521b46b70bbe264fde2
+size 5400

runs/Jun23_18-38-00_fbe13c4cce02/events.out.tfevents.1719168168.fbe13c4cce02.1139.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e543316ae084a39a85272e47b8e3b624218ae5c7cedd483859eb7ea35dcca2
+size 9641

runs/Jun23_18-49-39_fbe13c4cce02/events.out.tfevents.1719168589.fbe13c4cce02.1139.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89807781f1312f1564f7a64cd73799e230323cf194649e6477555e5db456799c
+size 7543

runs/Jun23_18-49-39_fbe13c4cce02/events.out.tfevents.1719168770.fbe13c4cce02.1139.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c700702d11db7b60a7434d16008ea113fe774250848ef64a004809c844e46557
+size 560

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0989df2caa3d2e7ae3871b903708bb5192e8f25ad7423b56cb29e81f9385f98d
+size 2409017

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df02d53e5979fcec80d27707775b482481cbe99cbda92c33155ba0aa5709e6b4
+size 5176