Training in progress, epoch 1

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: test_model
+  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. -->
+
+# test_model
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1413
+- F1: 0.0
+- Roc Auc: 0.5
+- Accuracy: 0.8875
+
+## 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: 0.001
+- train_batch_size: 32
+- eval_batch_size: 32
+- 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
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1  | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---:|:-------:|:--------:|
+| No log        | 1.0   | 35   | 0.1413          | 0.0 | 0.5     | 0.8875   |
+| No log        | 2.0   | 70   | 0.1451          | 0.0 | 0.5     | 0.8875   |
+| No log        | 3.0   | 105  | 0.1469          | 0.0 | 0.5     | 0.8875   |
+| No log        | 4.0   | 140  | 0.1437          | 0.0 | 0.5     | 0.8875   |
+| No log        | 5.0   | 175  | 0.1426          | 0.0 | 0.5     | 0.8875   |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,44 @@
+{
+  "_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": "toxic",
+    "1": "severe_toxic",
+    "2": "obscene",
+    "3": "threat",
+    "4": "insult",
+    "5": "identity_hate"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "identity_hate": 5,
+    "insult": 4,
+    "obscene": 2,
+    "severe_toxic": 1,
+    "threat": 3,
+    "toxic": 0
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "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 sha256:207b41b74510d7323331c6d126f72a40fb9e958318a743a504eabb0150c0c579
+size 498625128

runs/Dec09_21-33-55_debian/events.out.tfevents.1733776467.debian.8074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a457d416dadbacd3fa0389f01729e181aae0791edffa1910d654803db0ce0fb
+size 5328

runs/Dec09_21-37-53_debian/events.out.tfevents.1733776704.debian.8462.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc1ffef866d5f85f5ed799d1efa9a497cf26eb95ebdc6d7f6d8bfc5e731981d
+size 5328

runs/Dec09_21-50-01_debian/events.out.tfevents.1733777405.debian.12085.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1a920e6fc6cb40deb548eca96b0fc169cd7b2e71ba1ed94ddabec389efa0f9
+size 5328

runs/Dec09_21-51-53_debian/events.out.tfevents.1733777514.debian.14644.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587b0eb3901698a02d6c2494c0f4ca718f1abbc249ac6ab1f229beb9baa1f450
+size 7758

runs/Dec09_21-51-53_debian/events.out.tfevents.1733777732.debian.14644.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:195cb75d0eae41e4278e300bb43b2c9428cbcca2eddcd935176a03d20f1474ff
+size 460

runs/Dec09_22-07-15_debian/events.out.tfevents.1733778442.debian.20649.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263508efc90a0a2ef2feef9c42308aa66de18dc36367b08ae912cd24f09d6faa
+size 5328

runs/Dec09_22-08-52_debian/events.out.tfevents.1733778532.debian.21667.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd5d09c73bf440a120cfc100621cb38d417757183f8c68ca81add90ac58cb03
+size 5740

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 +1,59 @@
+{
+  "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",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "num_labels": 6,
+  "pad_token": "<pad>",
+  "problem_type": "multi_label_classification",
+  "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 sha256:5345a6bae29be10a3b11bd9f8ecbb637106dd3c3bfb4f33120181e824cc47137
+size 5304