End of training

README.md

@@ -0,0 +1,77 @@
+---
+license: cc-by-nc-4.0
+base_model: s2w-ai/DarkBERT
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: DarkBERT-finetuned-ner
+  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. -->
+
+# DarkBERT-finetuned-ner
+
+This model is a fine-tuned version of [s2w-ai/DarkBERT](https://huggingface.co/s2w-ai/DarkBERT) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6416
+- Precision: 0.4628
+- Recall: 0.5470
+- F1: 0.5014
+- Accuracy: 0.8901
+
+## 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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 111  | 0.3933          | 0.3563    | 0.4337 | 0.3912 | 0.8726   |
+| No log        | 2.0   | 222  | 0.3491          | 0.4345    | 0.5672 | 0.4921 | 0.8886   |
+| No log        | 3.0   | 333  | 0.3991          | 0.4284    | 0.5405 | 0.4780 | 0.8795   |
+| No log        | 4.0   | 444  | 0.3969          | 0.4565    | 0.5797 | 0.5108 | 0.8877   |
+| 0.2744        | 5.0   | 555  | 0.4276          | 0.4737    | 0.5690 | 0.5170 | 0.8887   |
+| 0.2744        | 6.0   | 666  | 0.5237          | 0.4918    | 0.5637 | 0.5253 | 0.8862   |
+| 0.2744        | 7.0   | 777  | 0.5472          | 0.4855    | 0.5503 | 0.5159 | 0.8877   |
+| 0.2744        | 8.0   | 888  | 0.6319          | 0.4581    | 0.5699 | 0.5079 | 0.8855   |
+| 0.2744        | 9.0   | 999  | 0.6511          | 0.4901    | 0.5744 | 0.5289 | 0.8901   |
+| 0.0627        | 10.0  | 1110 | 0.6758          | 0.4900    | 0.5681 | 0.5262 | 0.8899   |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "s2w-ai/DarkBERT",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ACTION",
+    "2": "I-ACTION",
+    "3": "B-ACTOR",
+    "4": "I-ACTOR",
+    "5": "B-ASSETS",
+    "6": "I-ASSETS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ACTION": 1,
+    "B-ACTOR": 3,
+    "B-ASSETS": 5,
+    "I-ACTION": 2,
+    "I-ACTOR": 4,
+    "I-ASSETS": 6,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa28789f66d20c405daf7b7db0d99cfe26f8f71fbd5c02dfd5365895cf75248
+size 496265620

runs/Aug15_00-54-34_4df4d7b697aa/events.out.tfevents.1723683337.4df4d7b697aa.1580.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263d3050d5742054f29b8c4e45925177095736471c0325ed3301ae61a50ec689
+size 10673

runs/Aug15_00-54-34_4df4d7b697aa/events.out.tfevents.1723684438.4df4d7b697aa.1580.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16343b7daf2b3098b48ca17da895ad90dead126f8848d99fb8c437fb9e9ea6f0
+size 560

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": false,
+    "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 +1,57 @@
+{
+  "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
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3863923adcfc27757425bd670d79ea3963df6fbcf7c38b0bc9146a7d1ee84125
+size 5112