Training complete

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+base_model: vinai/phobert-base
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9580
+
+## 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: 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 347  | 1.1776          |
+| 0.7473        | 2.0   | 694  | 1.2132          |
+| 0.5222        | 3.0   | 1041 | 1.1805          |
+| 0.5222        | 4.0   | 1388 | 1.3843          |
+| 0.3822        | 5.0   | 1735 | 1.5071          |
+| 0.2506        | 6.0   | 2082 | 1.6778          |
+| 0.2506        | 7.0   | 2429 | 1.8481          |
+| 0.1706        | 8.0   | 2776 | 2.0948          |
+| 0.1146        | 9.0   | 3123 | 2.2835          |
+| 0.1146        | 10.0  | 3470 | 2.3527          |
+| 0.0985        | 11.0  | 3817 | 2.6191          |
+| 0.0514        | 12.0  | 4164 | 2.6513          |
+| 0.0387        | 13.0  | 4511 | 2.8331          |
+| 0.0387        | 14.0  | 4858 | 2.9059          |
+| 0.0345        | 15.0  | 5205 | 2.8839          |
+| 0.0239        | 16.0  | 5552 | 2.9872          |
+| 0.0239        | 17.0  | 5899 | 3.0006          |
+| 0.011         | 18.0  | 6246 | 3.0611          |
+| 0.0138        | 19.0  | 6593 | 3.0957          |
+| 0.0138        | 20.0  | 6940 | 3.1291          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.2

added_tokens.json

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

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "vinai/phobert-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "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:a48d1e1af998c88e37818262e6830f0ece59cff43345b10a3f4ef674e895d43a
+size 540038764

runs/Aug29_16-14-03_84f8e7b35b2d/events.out.tfevents.1724948044.84f8e7b35b2d.454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819ed701bade2817a25040269dac5c6d85ddca544ecd67fd71d349f9446ce3a7
+size 4273

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": 256,
+  "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 sha256:96881f394cfa44b064512fb5838114d0d9a17143da019e5ba08fb43d581b8bdb
+size 4536