Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: svenbl80/deberta-v3-Base-finetuned-chatdoc-V3
+  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/deberta-v3-Base-finetuned-chatdoc-V3
+
+This model is a fine-tuned version of [microsoft/deberta-v3-Base](https://huggingface.co/microsoft/deberta-v3-Base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.9425
+- Validation Loss: 0.5627
+- Train Accuracy: 0.8652
+- 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': 165, '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 |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 0.9425     | 0.5627          | 0.8652         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.28.0
+- TensorFlow 2.9.1
+- Datasets 2.15.0
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-Base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

logs/train/events.out.tfevents.1704354502.104-171-203-254.2449629.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38830692f3c76bcfa6693630fa63391dedd4d6bc82320cb233a19bdc760e6ca7
+size 7060542

logs/validation/events.out.tfevents.1704354549.104-171-203-254.2449629.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10657e1bfa38599aaadca81d76f3f2cfc294becde1d95f1a67d0a7ffeb04a71b
+size 193

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2866626cc86e52816f616fa3aba39dbf2c4fea93a4095312ab41a34021389c
+size 737974552

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}