End of training

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: allenai/longformer-base-4096
+tags:
+- generated_from_trainer
+metrics:
+- recall
+- precision
+model-index:
+- name: longformer-8bitadam-2048-main
+  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-8bitadam-2048-main
+
+This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0103
+- Recall: 0.9643
+- Precision: 0.9643
+- F5: 0.9643
+
+## 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Recall | Precision | F5     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|
+| 0.0015        | 1.0   | 100  | 0.0197          | 1.0    | 0.9032    | 0.9959 |
+| 0.0012        | 2.0   | 200  | 0.0179          | 0.9643 | 0.9643    | 0.9643 |
+| 0.0008        | 3.0   | 300  | 0.0103          | 0.9643 | 0.9643    | 0.9643 |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForTokenClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-EMAIL",
+    "1": "B-ID_NUM",
+    "2": "B-NAME_STUDENT",
+    "3": "B-PHONE_NUM",
+    "4": "B-STREET_ADDRESS",
+    "5": "B-URL_PERSONAL",
+    "6": "B-USERNAME",
+    "7": "I-ID_NUM",
+    "8": "I-NAME_STUDENT",
+    "9": "I-PHONE_NUM",
+    "10": "I-STREET_ADDRESS",
+    "11": "I-URL_PERSONAL",
+    "12": "O"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EMAIL": 0,
+    "B-ID_NUM": 1,
+    "B-NAME_STUDENT": 2,
+    "B-PHONE_NUM": 3,
+    "B-STREET_ADDRESS": 4,
+    "B-URL_PERSONAL": 5,
+    "B-USERNAME": 6,
+    "I-ID_NUM": 7,
+    "I-NAME_STUDENT": 8,
+    "I-PHONE_NUM": 9,
+    "I-STREET_ADDRESS": 10,
+    "I-URL_PERSONAL": 11,
+    "O": 12
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 1,
+  "vocab_size": 50272
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4a5609112cd6aea1d9fe2ddc3c2fab8807e702b4c84fc48fb457c330249b72
+size 592370940

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "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": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cc4fddf553a42d6d49c743748809c2c1a8ac6ce7d7e2881951e6f315bb5f37
+size 4920