End of training

README.md

@@ -0,0 +1,60 @@
+---
+base_model: vinai/phobert-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: process_classification
+  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. -->
+
+# process_classification
+
+This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6159
+- Accuracy: 0.9667
+
+## 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: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 15   | 0.7506          | 0.9667   |
+| No log        | 2.0   | 30   | 0.6159          | 0.9667   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

added_tokens.json

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

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "vinai/phobert-base-v2",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": "In gi\u1ea5y ho\u00e3n ngh\u0129a v\u1ee5",
+    "1": "Nh\u1eadp k\u1ebf ho\u1ea1ch h\u1ecdc t\u1eadp",
+    "2": "\u0110\u0103ng k\u00fd h\u1ecdc ph\u1ea7n"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "In gi\u1ea5y ho\u00e3n ngh\u0129a v\u1ee5": 0,
+    "Nh\u1eadp k\u1ebf ho\u1ea1ch h\u1ecdc t\u1eadp": 1,
+    "\u0110\u0103ng k\u00fd h\u1ecdc ph\u1ea7n": 2
+  },
+  "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": "4.36.2",
+  "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 sha256:42a21952a8f4425ea112d33a20e461302cd4018525bf71f9befc33931fcd4f9c
+size 540026460

runs/Jan13_15-15-54_38d2f633ed9b/events.out.tfevents.1705158955.38d2f633ed9b.326.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfe58b2b1b270cb12e4b9c8eeaa0c371b1e016d2b95e43c3e4d37683c46b0ee
+size 4822

runs/Jan13_15-24-50_38d2f633ed9b/events.out.tfevents.1705159491.38d2f633ed9b.326.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:122b743c1fac744e71501329aed3acc9e3de89bf880e3b529d053f9cbd063028
+size 4818

runs/Jan13_15-27-31_38d2f633ed9b/events.out.tfevents.1705159652.38d2f633ed9b.326.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eabd7c9ab1d6f6553b86e55f3bfb8050cb42735a63791e23b52a1467553bdb54
+size 4818

runs/Jan13_15-52-34_38d2f633ed9b/events.out.tfevents.1705161155.38d2f633ed9b.326.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763efdbeff0b3ea97a410abca49ef99fee228fba86ec472eb178c8ef4ef8b5fb
+size 4818

runs/Jan13_16-01-18_38d2f633ed9b/events.out.tfevents.1705161678.38d2f633ed9b.326.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624e02f834571a8cb8d6fd5ade09d15caf08e54b0784a3bcbc7cb1fd66b446dc
+size 4975

runs/Jan13_16-10-49_38d2f633ed9b/events.out.tfevents.1705162250.38d2f633ed9b.14527.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a115994d205cf68c81ab9941e17dcb98b978c77d6b88cdab0a1148a12467ec
+size 5800

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 sha256:71836fccc22e8ad6f4c5190ef4e6fc9118b1bc41e852c8e0a42b3cf1ca9e1bbc
+size 4728