End of training

README.md

@@ -0,0 +1,58 @@
+---
+license: mit
+base_model: Tommert25/RobBERTBestModelOct11
+tags:
+- generated_from_trainer
+model-index:
+- name: RobBERTBestModelOct13
+  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. -->
+
+# RobBERTBestModelOct13
+
+This model is a fine-tuned version of [Tommert25/RobBERTBestModelOct11](https://huggingface.co/Tommert25/RobBERTBestModelOct11) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.3695
+- eval_precisions: 0.8647
+- eval_recall: 0.8151
+- eval_f-measure: 0.8341
+- eval_accuracy: 0.9448
+- eval_runtime: 9.7585
+- eval_samples_per_second: 82.698
+- eval_steps_per_second: 5.226
+- step: 0
+
+## 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: 7.5e-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: 14
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 2,
+  "<mask>": 39984,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "Tommert25/RobBERTBestModelOct11",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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": "NAME",
+    "1": "OTH",
+    "2": "NL",
+    "3": "VAR",
+    "4": "ARAB",
+    "5": "ENG",
+    "6": "NON"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ARAB": 4,
+    "ENG": 5,
+    "NL": 2,
+    "NON": 6,
+    "Name": 0,
+    "OTH": 1,
+    "VAR": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 40000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5eeb39e92ee52836c23bb275ca406fe48db70fc4d3905d9bcd0dfe66016edc0
+size 464775913

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "add_prefix_space": true,
+  "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
+    },
+    "39984": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37badb99ac87cee8a53f194cae92da78cdc56f627c79197670c31661eb2704fa
+size 4091