Training in progress, epoch 1

README.md

@@ -1,3 +1,67 @@
----
-license: apache-2.0
----
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: RoBERTa-MGT-Test
+  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. -->
+
+# RoBERTa-MGT-Test
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5149
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.1922        | 1.0   | 7200  | 0.5149          |
+| 0.2333        | 2.0   | 14400 | 0.7551          |
+| 1.3892        | 3.0   | 21600 | 1.3879          |
+| 1.3963        | 4.0   | 28800 | 1.3893          |
+| 1.3887        | 5.0   | 36000 | 1.3871          |
+| 1.3857        | 6.0   | 43200 | 1.3901          |
+| 1.3911        | 7.0   | 50400 | 1.3873          |
+| 1.3888        | 8.0   | 57600 | 1.3866          |
+| 1.3866        | 9.0   | 64800 | 1.3865          |
+| 1.3863        | 10.0  | 72000 | 1.3863          |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": "human",
+    "1": "llm",
+    "2": "machine-polished",
+    "3": "machine-humanized"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

logs/events.out.tfevents.1717667565.ws-l1-006.57189.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c6abe1fbedc0df1f5a63f49dead81abfb00f6929b77d78fb0e64da54b182f4
+size 20459

logs/events.out.tfevents.1717667730.ws-l1-006.57189.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0488420875416cc3a121d3ca4e9645a446a4489a3aa9c89a26f034886cfb58e
+size 311

logs/events.out.tfevents.1717670060.ws-l1-006.188956.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:febc8ad5ca6f7c95287d2064b49e1da0e4de5855c503631b0ea867a05d46db07
+size 20459

logs/events.out.tfevents.1717670193.ws-l1-006.188956.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6549523542169b3ab64cd09bb281ed13f5f08eeabd4854de669e3659caa578
+size 311

logs/events.out.tfevents.1717672675.ws-l1-006.256407.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a0ed4aee3afb031d39c12fd66aada9d1d48d70df752c272ceffe8a5d45af5f8
+size 20459

logs/events.out.tfevents.1717672829.ws-l1-006.256407.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2930b323c0a31e1ea91ad7effcddb8a58532f4e77a32fbfd8223bed0307933
+size 311

logs/events.out.tfevents.1717680354.ws-l1-006.278612.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce5903ec3b5ebfdbb0118f4c11d9489fe371f360178d2f52acf71b180b911fd
+size 38045

logs/events.out.tfevents.1717680620.ws-l1-006.278612.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a603ea1c378ee73ae390a6c248f4716d431b16fd040d0bbf4f2aa7f42141e2
+size 311

logs/events.out.tfevents.1717681673.ws-l1-006.501191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e701b3c3a55ae28b63eb831d1474bbcb13b82cc8b0871794f93c10cd3018c46
+size 71051

logs/events.out.tfevents.1717682199.ws-l1-006.501191.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff9daee6692b0e0268ec193206d41ca324d603b336da8290f610bf3068eebd4
+size 311

logs/events.out.tfevents.1717753158.ws-l1-006.2415736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3dcc55a7cac49e1fd8bc0c46a979597caea53faef85d9d30ac58b323429c09
+size 1162240

logs/events.out.tfevents.1717761096.ws-l1-006.2415736.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629cd66da7478f853d345c4c5f44b5d29ec13edb09e7c7d169279eaa14358585
+size 316

logs/events.out.tfevents.1718001155.ws-l1-007.4151678.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1da6798f84caac2cdbf5850d984301658f2601ce02ed4d9ee3be97b3e25fc3a
+size 162020

logs/events.out.tfevents.1718012418.ws-l1-007.4151678.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bf53dfd7f199d1342b86e810886a6aa49ef16411342ffc7f62057c3aafc7da
+size 316

logs/events.out.tfevents.1718013341.ws-l1-007.120415.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ee2d81d8511d2c5a055a127d78d7273e62adec4cbe8d7514c22234dda7fc07
+size 4767

logs/events.out.tfevents.1718013357.ws-l1-007.120415.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4724a23b201fd75c055cebed238c12d056b7c3e254123540e39046f6c9b85133
+size 5249

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb9e78b8f82cc694d82f952de1c1f17554c7791d6922de126434d532a8787eb
+size 498618976

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": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8b5bae675727916d7948b4f7dc9e7eec23724a6534ba226400e515f8f7bb26
+size 5048