End of training

README.md

@@ -0,0 +1,74 @@
+---
+base_model: vinai/phobert-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: phobert-base-v2-finetuned-ner-thesis-dseb
+  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. -->
+
+# phobert-base-v2-finetuned-ner-thesis-dseb
+
+This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3842
+- Precision: 0.75
+- Recall: 0.8329
+- F1: 0.7893
+- Accuracy: 0.9491
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 2.0671        | 1.0   | 23   | 1.4715          | 0.0       | 0.0    | 0.0    | 0.6125   |
+| 1.3776        | 2.0   | 46   | 0.9706          | 0.9471    | 0.3860 | 0.5485 | 0.7545   |
+| 0.9833        | 3.0   | 69   | 0.6568          | 0.8144    | 0.7207 | 0.7647 | 0.9034   |
+| 0.7423        | 4.0   | 92   | 0.4905          | 0.9215    | 0.9045 | 0.9130 | 0.9595   |
+| 0.5928        | 5.0   | 115  | 0.3919          | 0.9626    | 0.9517 | 0.9572 | 0.9893   |
+| 0.4955        | 6.0   | 138  | 0.3377          | 0.9658    | 0.9579 | 0.9619 | 0.9913   |
+| 0.4013        | 7.0   | 161  | 0.3058          | 0.9658    | 0.9579 | 0.9619 | 0.9915   |
+| 0.3747        | 8.0   | 184  | 0.2874          | 0.9658    | 0.9579 | 0.9619 | 0.9915   |
+| 0.3618        | 9.0   | 207  | 0.2781          | 0.9658    | 0.9579 | 0.9619 | 0.9915   |
+| 0.3477        | 10.0  | 230  | 0.2748          | 0.9658    | 0.9579 | 0.9619 | 0.9915   |
+
+
+### Framework versions
+
+- Transformers 4.36.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "vinai/phobert-base-v2",
+  "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-NAME",
+    "2": "I-NAME",
+    "3": "B-DATE",
+    "4": "I-DATE",
+    "5": "B-UNI",
+    "6": "I-UNI",
+    "7": "B-MAJ",
+    "8": "I-MAJ",
+    "9": "B-MAIL",
+    "10": "I-MAIL",
+    "11": "B-UNI_ABRREV",
+    "12": "I-PHONE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DATE": 3,
+    "B-MAIL": 9,
+    "B-MAJ": 7,
+    "B-NAME": 1,
+    "B-UNI": 5,
+    "B-UNI_ABBREV": 11,
+    "I-DATE": 4,
+    "I-MAIL": 10,
+    "I-MAJ": 8,
+    "I-NAME": 2,
+    "I-PHONE": 12,
+    "I-UNI": 6,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2db9950429b5964da50fea79d2b99f3007c48761308373344b3e66c5006443
+size 537694636

runs/Dec14_02-44-42_bc0cbd9c575c/events.out.tfevents.1702521901.bc0cbd9c575c.685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8093aab4b40b1ca50b83d8b34b0cc9aaca8aa4a0bc8bf560c0cdace0ea5a94
+size 7174

runs/Dec14_02-52-20_bc0cbd9c575c/events.out.tfevents.1702522349.bc0cbd9c575c.685.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e1ca06eae4bcc5894db0ab24e07a62e6c58f2d2fccb5f7c61b25109cb3a09e
+size 11753

runs/Dec14_02-52-20_bc0cbd9c575c/events.out.tfevents.1702522434.bc0cbd9c575c.685.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de13822e6ab8b5a7b3dff0758f9f92ccf19a84959ba5fc4f8a418dc03e8a736
+size 560

runs/Dec14_02-58-38_bc0cbd9c575c/events.out.tfevents.1702522726.bc0cbd9c575c.5438.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2ab6d99a173c81f80b06d1fbcd24f39beec76b91a3e4ef4b15fa888b512ece
+size 11753

runs/Dec14_02-58-38_bc0cbd9c575c/events.out.tfevents.1702522809.bc0cbd9c575c.5438.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c59fcc1b9a4f3cdf5412b48bb07282902fea0edbcf9a6d3a84a74407f054ea
+size 560

runs/Dec14_03-11-09_bc0cbd9c575c/events.out.tfevents.1702523503.bc0cbd9c575c.8703.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ce5203df5b5785af656e4825a6867a80c85a0348eac97f1bbe424965b07c9a
+size 11753

runs/Dec14_03-11-09_bc0cbd9c575c/events.out.tfevents.1702523584.bc0cbd9c575c.8703.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081bb6d542289b8affd82f6ddff829a069c36829346daf1c11916ea4b43311d2
+size 1032

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "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 +1,54 @@
+{
+  "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
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65e4fca5a4364f9407e7a86ca40d99ecbd33dd376273f6c6c929e0da7dcfa49
+size 4728