Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: svenbl80/roberta-base-finetuned-chatdoc
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# svenbl80/roberta-base-finetuned-chatdoc
+
+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:
+- Train Loss: 1.0838
+- Validation Loss: 1.0321
+- Train Accuracy: 0.7222
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 120, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 1.0838     | 1.0321          | 0.7222         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.28.0
+- TensorFlow 2.9.1
+- Datasets 2.15.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,36 @@
+{
+  "_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": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

logs/train/events.out.tfevents.1704206093.104-171-203-254.2108881.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49fc96ff9c276493de2d2e292a41fbdc0184186f99dab26bac3ea06efd8f3e1
+size 40

logs/train/events.out.tfevents.1704213063.104-171-203-254.2121495.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda5ae0a46eac8dbda50212de597223206833dcb3aefe70bb499feec50763c69
+size 40

logs/train/events.out.tfevents.1704215792.104-171-203-254.2121879.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07a1f0e074517b3d8dfb1acdebba976cde3e2fd219b4226e7f8e1d2aec85d06
+size 2837613

logs/validation/events.out.tfevents.1704215808.104-171-203-254.2121879.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9bb79e652010ea7868bafadb131540a3466fd375710c0a806348e8de6f7cd2
+size 193

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>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45baa3a1694c50fe21463db52bc10070502b8629f0064c0fa1c7ed2af831f6a
+size 498865280

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "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>"
+}