Training in progress, epoch 1

README.md

@@ -0,0 +1,94 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: LLMGUARD-roberta-11
+  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. -->
+
+# LLMGUARD-roberta-11
+
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7933
+- Accuracy: 0.7696
+
+## 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-06
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 32
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 2.2522        | 1.0   | 1564  | 1.9637          | 0.3163   |
+| 1.0671        | 2.0   | 3128  | 0.8108          | 0.7662   |
+| 0.7146        | 3.0   | 4692  | 0.6397          | 0.7953   |
+| 0.6354        | 4.0   | 6256  | 0.5867          | 0.8027   |
+| 0.5794        | 5.0   | 7820  | 0.5669          | 0.8107   |
+| 0.5303        | 6.0   | 9384  | 0.5505          | 0.8105   |
+| 0.504         | 7.0   | 10948 | 0.5560          | 0.8081   |
+| 0.4664        | 8.0   | 12512 | 0.5553          | 0.8071   |
+| 0.4559        | 9.0   | 14076 | 0.5613          | 0.8073   |
+| 0.4393        | 10.0  | 15640 | 0.5734          | 0.8044   |
+| 0.4292        | 11.0  | 17204 | 0.5735          | 0.7995   |
+| 0.4065        | 12.0  | 18768 | 0.5987          | 0.8007   |
+| 0.3905        | 13.0  | 20332 | 0.6292          | 0.7951   |
+| 0.3828        | 14.0  | 21896 | 0.6233          | 0.7927   |
+| 0.3658        | 15.0  | 23460 | 0.6490          | 0.7887   |
+| 0.3663        | 16.0  | 25024 | 0.6571          | 0.7913   |
+| 0.3551        | 17.0  | 26588 | 0.6533          | 0.7852   |
+| 0.3439        | 18.0  | 28152 | 0.6814          | 0.7833   |
+| 0.3316        | 19.0  | 29716 | 0.6764          | 0.7817   |
+| 0.3297        | 20.0  | 31280 | 0.6896          | 0.7798   |
+| 0.318         | 21.0  | 32844 | 0.6947          | 0.7775   |
+| 0.323         | 22.0  | 34408 | 0.7231          | 0.7767   |
+| 0.304         | 23.0  | 35972 | 0.7333          | 0.7707   |
+| 0.3145        | 24.0  | 37536 | 0.7491          | 0.7742   |
+| 0.2975        | 25.0  | 39100 | 0.7502          | 0.7708   |
+| 0.2812        | 26.0  | 40664 | 0.7632          | 0.7719   |
+| 0.2825        | 27.0  | 42228 | 0.7734          | 0.7664   |
+| 0.2828        | 28.0  | 43792 | 0.7767          | 0.7697   |
+| 0.2872        | 29.0  | 45356 | 0.7865          | 0.7683   |
+| 0.2759        | 30.0  | 46920 | 0.7849          | 0.7700   |
+| 0.2758        | 31.0  | 48484 | 0.7915          | 0.7692   |
+| 0.2797        | 32.0  | 50048 | 0.7933          | 0.7696   |
+
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "FacebookAI/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": "Cybercrime",
+    "1": "Drugs",
+    "2": "Hate",
+    "3": "Human Crime",
+    "4": "Politics",
+    "5": "Pornography",
+    "6": "Sarcasm",
+    "7": "Suicide",
+    "8": "Weapons",
+    "9": "Gambling",
+    "10": "Advice"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Advice": 10,
+    "Cybercrime": 0,
+    "Drugs": 1,
+    "Gambling": 9,
+    "Hate": 2,
+    "Human Crime": 3,
+    "Politics": 4,
+    "Pornography": 5,
+    "Sarcasm": 6,
+    "Suicide": 7,
+    "Weapons": 8
+  },
+  "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": "4.48.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d24113ff1eba50740caa401db68a57db2b70899b3d1f8eeb1b64209c8386a8
+size 498640508

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 +1,58 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "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 sha256:88e5803902782f182be2636d2ac8d72bb74001d09ace02cb98f78407f9f94019
+size 5368