Model save

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+base_model: DTAI-KULeuven/robbert-2023-dutch-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: robbert-2023-dutch-base-gender
+  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. -->
+
+# robbert-2023-dutch-base-gender
+
+This model is a fine-tuned version of [DTAI-KULeuven/robbert-2023-dutch-base](https://huggingface.co/DTAI-KULeuven/robbert-2023-dutch-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6600
+- Precision: 0.6285
+- Recall: 0.6293
+- Fscore: 0.6282
+- Accuracy: 0.6290
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Fscore | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.616         | 0.29  | 2000 | 0.6498          | 0.6295    | 0.6299 | 0.6266 | 0.6267   |
+| 0.6033        | 0.59  | 4000 | 0.6584          | 0.6278    | 0.6274 | 0.6228 | 0.6228   |
+| 0.5896        | 0.88  | 6000 | 0.6600          | 0.6285    | 0.6293 | 0.6282 | 0.6290   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.5
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_fscore": 0.6321511851241228,
+    "eval_loss": 0.6710947155952454,
+    "eval_precision": 0.6327920074497231,
+    "eval_recall": 0.6336155271716182,
+    "eval_runtime": 2673.8432,
+    "eval_samples": 834159,
+    "eval_samples_per_second": 311.97,
+    "eval_steps_per_second": 19.498,
+    "train_loss": 0.5972718149742211,
+    "train_runtime": 22981.0662,
+    "train_samples": 868047,
+    "train_samples_per_second": 37.772,
+    "train_steps_per_second": 0.59
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "DTAI-KULeuven/robbert-2023-dutch-base",
+  "additional_special_tokens_ids": [],
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_token_id": 0,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "F",
+    "1": "M"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "F": 0,
+    "M": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 4,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "sep_token_id": 3,
+  "tokenizer_class": "RobertaTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 1,
+  "unk_token_id": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.0,
+    "eval_fscore": 0.6321511851241228,
+    "eval_loss": 0.6710947155952454,
+    "eval_precision": 0.6327920074497231,
+    "eval_recall": 0.6336155271716182,
+    "eval_runtime": 2673.8432,
+    "eval_samples": 834159,
+    "eval_samples_per_second": 311.97,
+    "eval_steps_per_second": 19.498
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53837539a16ce3b468e2c4526d10a05d18829428816227f773df46255f4ec442
+size 497798744

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.5972718149742211,
+    "train_runtime": 22981.0662,
+    "train_samples": 868047,
+    "train_samples_per_second": 37.772,
+    "train_steps_per_second": 0.59
+}

trainer_state.json

@@ -0,0 +1,247 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999815678395665,
+  "eval_steps": 2500,
+  "global_step": 13563,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.634299196342994e-06,
+      "loss": 0.6609,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.267861092678611e-06,
+      "loss": 0.6467,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.899211088992112e-06,
+      "loss": 0.6414,
+      "step": 1500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 8.530561085305612e-06,
+      "loss": 0.6322,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.161911081619111e-06,
+      "loss": 0.6266,
+      "step": 2500
+    },
+    {
+      "epoch": 0.18,
+      "eval_fscore": 0.6023351654273126,
+      "eval_loss": 0.6601094007492065,
+      "eval_precision": 0.6348626173773073,
+      "eval_recall": 0.6216278871239599,
+      "eval_runtime": 2683.597,
+      "eval_samples_per_second": 310.836,
+      "eval_steps_per_second": 19.427,
+      "step": 2500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 7.793261077932612e-06,
+      "loss": 0.6193,
+      "step": 3000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 7.424611074246111e-06,
+      "loss": 0.6134,
+      "step": 3500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 7.055961070559611e-06,
+      "loss": 0.6069,
+      "step": 4000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 6.687311066873111e-06,
+      "loss": 0.6043,
+      "step": 4500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 6.318661063186611e-06,
+      "loss": 0.6008,
+      "step": 5000
+    },
+    {
+      "epoch": 0.37,
+      "eval_fscore": 0.6295517813114804,
+      "eval_loss": 0.6481114625930786,
+      "eval_precision": 0.6323627402469738,
+      "eval_recall": 0.6327219192535836,
+      "eval_runtime": 2681.3189,
+      "eval_samples_per_second": 311.1,
+      "eval_steps_per_second": 19.444,
+      "step": 5000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5.950011059500111e-06,
+      "loss": 0.5989,
+      "step": 5500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5.581361055813611e-06,
+      "loss": 0.6005,
+      "step": 6000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.212711052127111e-06,
+      "loss": 0.5894,
+      "step": 6500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.8440610484406105e-06,
+      "loss": 0.5871,
+      "step": 7000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.475411044754111e-06,
+      "loss": 0.5925,
+      "step": 7500
+    },
+    {
+      "epoch": 0.55,
+      "eval_fscore": 0.6292509682845455,
+      "eval_loss": 0.6569201946258545,
+      "eval_precision": 0.6303328699646444,
+      "eval_recall": 0.6311007791866495,
+      "eval_runtime": 2678.5974,
+      "eval_samples_per_second": 311.416,
+      "eval_steps_per_second": 19.464,
+      "step": 7500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.1074983410749835e-06,
+      "loss": 0.5859,
+      "step": 8000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.7388483373884836e-06,
+      "loss": 0.5817,
+      "step": 8500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.370935633709357e-06,
+      "loss": 0.5819,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.0022856300228566e-06,
+      "loss": 0.5812,
+      "step": 9500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.6336356263363567e-06,
+      "loss": 0.5824,
+      "step": 10000
+    },
+    {
+      "epoch": 0.74,
+      "eval_fscore": 0.6275101578247589,
+      "eval_loss": 0.6671798825263977,
+      "eval_precision": 0.6346007218237036,
+      "eval_recall": 0.6333714931104397,
+      "eval_runtime": 2680.7422,
+      "eval_samples_per_second": 311.167,
+      "eval_steps_per_second": 19.448,
+      "step": 10000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.2649856226498564e-06,
+      "loss": 0.5762,
+      "step": 10500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8963356189633564e-06,
+      "loss": 0.5709,
+      "step": 11000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.5276856152768563e-06,
+      "loss": 0.5717,
+      "step": 11500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.159035611590356e-06,
+      "loss": 0.5687,
+      "step": 12000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.903856079038562e-07,
+      "loss": 0.5661,
+      "step": 12500
+    },
+    {
+      "epoch": 0.92,
+      "eval_fscore": 0.6327639400151716,
+      "eval_loss": 0.672634482383728,
+      "eval_precision": 0.6340222342544792,
+      "eval_recall": 0.6347830614243537,
+      "eval_runtime": 2680.9501,
+      "eval_samples_per_second": 311.143,
+      "eval_steps_per_second": 19.446,
+      "step": 12500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.2247290422472906e-07,
+      "loss": 0.5723,
+      "step": 13000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.3822900538229014e-08,
+      "loss": 0.5705,
+      "step": 13500
+    },
+    {
+      "epoch": 1.0,
+      "step": 13563,
+      "total_flos": 2.0223656129308262e+17,
+      "train_loss": 0.5972718149742211,
+      "train_runtime": 22981.0662,
+      "train_samples_per_second": 37.772,
+      "train_steps_per_second": 0.59
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13563,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.0223656129308262e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa67f1b6275897851da077b203af9143e2d9b7f4344e12a50f455a88ba55a82
+size 4856