Training complete

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,103 @@
+---
+license: mit
+base_model: severinsimmler/xlm-roberta-longformer-base-16384
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: longformer_pos_neg
+  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. -->
+
+# longformer_pos_neg
+
+This model is a fine-tuned version of [severinsimmler/xlm-roberta-longformer-base-16384](https://huggingface.co/severinsimmler/xlm-roberta-longformer-base-16384) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5549
+- Precision: 0.5599
+- Recall: 0.5786
+- F1: 0.5691
+- Accuracy: 0.9030
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.35  | 50   | 0.7729          | 0.0       | 0.0    | 0.0    | 0.7762   |
+| No log        | 2.7   | 100  | 0.5497          | 0.0220    | 0.0078 | 0.0115 | 0.8017   |
+| No log        | 4.05  | 150  | 0.4143          | 0.0706    | 0.0698 | 0.0702 | 0.8383   |
+| No log        | 5.41  | 200  | 0.3607          | 0.2329    | 0.2578 | 0.2447 | 0.8632   |
+| No log        | 6.76  | 250  | 0.3320          | 0.3628    | 0.3101 | 0.3344 | 0.8807   |
+| No log        | 8.11  | 300  | 0.3261          | 0.5108    | 0.4574 | 0.4826 | 0.8939   |
+| No log        | 9.46  | 350  | 0.3190          | 0.4229    | 0.5950 | 0.4944 | 0.8826   |
+| No log        | 10.81 | 400  | 0.2662          | 0.4821    | 0.6008 | 0.5349 | 0.9014   |
+| No log        | 12.16 | 450  | 0.2714          | 0.5901    | 0.5775 | 0.5837 | 0.9137   |
+| 0.3792        | 13.51 | 500  | 0.2852          | 0.5769    | 0.5891 | 0.5829 | 0.9105   |
+| 0.3792        | 14.86 | 550  | 0.3868          | 0.5876    | 0.5329 | 0.5589 | 0.9082   |
+| 0.3792        | 16.22 | 600  | 0.3218          | 0.5444    | 0.6531 | 0.5938 | 0.9129   |
+| 0.3792        | 17.57 | 650  | 0.3022          | 0.5645    | 0.6357 | 0.5980 | 0.9112   |
+| 0.3792        | 18.92 | 700  | 0.3737          | 0.5419    | 0.6764 | 0.6017 | 0.9025   |
+| 0.3792        | 20.27 | 750  | 0.3730          | 0.5411    | 0.6628 | 0.5958 | 0.9119   |
+| 0.3792        | 21.62 | 800  | 0.4021          | 0.6145    | 0.6240 | 0.6192 | 0.9109   |
+| 0.3792        | 22.97 | 850  | 0.3358          | 0.5159    | 0.6298 | 0.5672 | 0.9008   |
+| 0.3792        | 24.32 | 900  | 0.3779          | 0.6065    | 0.6124 | 0.6095 | 0.9138   |
+| 0.3792        | 25.68 | 950  | 0.4435          | 0.5293    | 0.6298 | 0.5752 | 0.9063   |
+| 0.0755        | 27.03 | 1000 | 0.4230          | 0.6333    | 0.6124 | 0.6227 | 0.9169   |
+| 0.0755        | 28.38 | 1050 | 0.3666          | 0.5911    | 0.6415 | 0.6152 | 0.9163   |
+| 0.0755        | 29.73 | 1100 | 0.3335          | 0.6098    | 0.6512 | 0.6298 | 0.9178   |
+| 0.0755        | 31.08 | 1150 | 0.4606          | 0.5725    | 0.6202 | 0.5953 | 0.9075   |
+| 0.0755        | 32.43 | 1200 | 0.4280          | 0.5656    | 0.6434 | 0.6020 | 0.9065   |
+| 0.0755        | 33.78 | 1250 | 0.4003          | 0.5833    | 0.6376 | 0.6093 | 0.9158   |
+| 0.0755        | 35.14 | 1300 | 0.5802          | 0.6422    | 0.5775 | 0.6082 | 0.9020   |
+| 0.0755        | 36.49 | 1350 | 0.4503          | 0.6014    | 0.6550 | 0.6271 | 0.9172   |
+| 0.0755        | 37.84 | 1400 | 0.5614          | 0.6643    | 0.5523 | 0.6032 | 0.9044   |
+| 0.0755        | 39.19 | 1450 | 0.5082          | 0.628     | 0.6085 | 0.6181 | 0.9119   |
+| 0.0407        | 40.54 | 1500 | 0.3964          | 0.6072    | 0.6531 | 0.6293 | 0.9165   |
+| 0.0407        | 41.89 | 1550 | 0.5447          | 0.4572    | 0.6938 | 0.5512 | 0.8799   |
+| 0.0407        | 43.24 | 1600 | 0.5303          | 0.4816    | 0.6589 | 0.5565 | 0.8947   |
+| 0.0407        | 44.59 | 1650 | 0.4461          | 0.6409    | 0.6260 | 0.6333 | 0.9138   |
+| 0.0407        | 45.95 | 1700 | 0.6884          | 0.5561    | 0.4031 | 0.4674 | 0.8766   |
+| 0.0407        | 47.3  | 1750 | 0.4556          | 0.5431    | 0.6105 | 0.5748 | 0.9097   |
+| 0.0407        | 48.65 | 1800 | 0.4272          | 0.6771    | 0.5853 | 0.6279 | 0.9183   |
+| 0.0407        | 50.0  | 1850 | 0.4904          | 0.5603    | 0.6570 | 0.6048 | 0.9015   |
+| 0.0407        | 51.35 | 1900 | 0.4206          | 0.5655    | 0.6357 | 0.5985 | 0.9135   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "severinsimmler/xlm-roberta-longformer-base-16384",
+  "architectures": [
+    "LongformerForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    256,
+    256,
+    256,
+    256,
+    256,
+    256,
+    256,
+    256,
+    256,
+    256,
+    256,
+    256
+  ],
+  "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-symp",
+    "2": "I-symp"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": "O",
+    "1": "B-symp",
+    "2": "I-symp"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 16386,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cc07d9a47b3fef604235e15b032ceefe9a7658dee17ffc3834a307c0bf8985
+size 1243659772

runs/May07_12-58-13_8dd371958cdf/events.out.tfevents.1715086695.8dd371958cdf.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:158032ceded1d86be692a675ad6f0234747e4621730bdfc314f59b8bf0725021
+size 23825

runs/May07_12-58-13_8dd371958cdf/events.out.tfevents.1715088092.8dd371958cdf.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996ec25323d21ecfd1b5d304787b2a07864e22027f82927c75e364be87285c54
+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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a1396e1ff4e78518af44b7521d9e5b9c6219fed36303610d202b685bab9782
+size 17082856

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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
+    },
+    "250001": {
+      "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>",
+  "mask_token": "<mask>",
+  "model_max_length": 16384,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a927b64d182885a8c093a76d760f7159e5f9fb5f4f57819d03b779844378810
+size 4920