Training in progress, epoch 1

README.md

@@ -0,0 +1,77 @@
+---
+license: agpl-3.0
+base_model: vesteinn/ScandiBERT
+tags:
+- generated_from_trainer
+model-index:
+- name: MeMo_BERT-SA_ScandiBERT
+  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. -->
+
+# MeMo_BERT-SA_ScandiBERT
+
+This model is a fine-tuned version of [vesteinn/ScandiBERT](https://huggingface.co/vesteinn/ScandiBERT) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2243
+- F1-score: 0.7419
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1-score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 297  | 0.9412          | 0.6171   |
+| 0.9566        | 2.0   | 594  | 0.8714          | 0.6663   |
+| 0.9566        | 3.0   | 891  | 0.8782          | 0.6326   |
+| 0.7393        | 4.0   | 1188 | 1.0449          | 0.7003   |
+| 0.7393        | 5.0   | 1485 | 0.9099          | 0.7046   |
+| 0.5862        | 6.0   | 1782 | 0.8663          | 0.7145   |
+| 0.4349        | 7.0   | 2079 | 1.3081          | 0.6875   |
+| 0.4349        | 8.0   | 2376 | 1.3457          | 0.7119   |
+| 0.3452        | 9.0   | 2673 | 1.2243          | 0.7419   |
+| 0.3452        | 10.0  | 2970 | 1.3430          | 0.7227   |
+| 0.2313        | 11.0  | 3267 | 1.5762          | 0.7273   |
+| 0.1486        | 12.0  | 3564 | 1.5626          | 0.7295   |
+| 0.1486        | 13.0  | 3861 | 1.8689          | 0.7113   |
+| 0.0888        | 14.0  | 4158 | 1.9944          | 0.7161   |
+| 0.0888        | 15.0  | 4455 | 1.9063          | 0.7115   |
+| 0.0647        | 16.0  | 4752 | 2.0000          | 0.7283   |
+| 0.0288        | 17.0  | 5049 | 2.0464          | 0.7278   |
+| 0.0288        | 18.0  | 5346 | 2.0158          | 0.7319   |
+| 0.0334        | 19.0  | 5643 | 2.0396          | 0.7324   |
+| 0.0334        | 20.0  | 5940 | 2.0772          | 0.7245   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "vesteinn/ScandiBERT",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e7632720c0b13c68244d25ba2bd63dbc109d3fc70141228e87001e83de6eaf
+size 497817180

runs/Mar18_10-28-45_086076f4e303/events.out.tfevents.1710757805.086076f4e303.3693.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a6dd8bfc54bc1818dc6959e686bb0431b001c516a94747ea9c91801bbfb33a
+size 6654

runs/Mar18_10-39-12_086076f4e303/events.out.tfevents.1710758363.086076f4e303.3693.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a46ba0b91b92f6a1145fb712cf5fa9ed98447cb957f56a43313ba19eb273ec1
+size 14075

runs/Mar18_10-39-12_086076f4e303/events.out.tfevents.1710759815.086076f4e303.3693.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197e4e62b506096dd2d5d0fcb5717c247c8e7cf70e1a791318b205494a6b12ca
+size 411

runs/Mar18_11-32-56_086076f4e303/events.out.tfevents.1710761589.086076f4e303.26852.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a54a635b2ab4acaeb2c945a701b0a280e65ac736ec2ab73a5b94bd354d1ceb
+size 5263

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fca70379c621cffc6910d3988182faedd75c5b01a8adcb552405a8f83ce7a41
+size 1084241

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+    },
+    "50004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "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,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063520f4ed9df0a615f465372c58ed050ebff0683edc25db8dd832bdc4eaea9c
+size 5048