End of training

README.md

@@ -0,0 +1,51 @@
+---
+base_model: KBLab/megatron-bert-large-swedish-cased-165-zero-shot
+tags:
+- generated_from_trainer
+model-index:
+- name: swedish
+  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. -->
+
+# swedish
+
+This model is a fine-tuned version of [KBLab/megatron-bert-large-swedish-cased-165-zero-shot](https://huggingface.co/KBLab/megatron-bert-large-swedish-cased-165-zero-shot) on an unknown dataset.
+
+## 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
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "KBLab/megatron-bert-large-swedish-cased-165-zero-shot",
+  "architectures": [
+    "MegatronBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "mnli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "informational",
+    "1": "transactional",
+    "2": "navigational_informational",
+    "3": "navigational_transactional",
+    "4": "transactional_download"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "informational": 0,
+    "navigational_informational": 2,
+    "navigational_transactional": 3,
+    "transactional": 1,
+    "transactional_download": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "megatron-bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_type": "BertWordPieceCase",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34cfe7e42a212a61af5b9d0c629abfd04a42b11880b05a851d9d6eedff398b17
+size 1478283988

runs/Jan29_07-18-53_5a5c1570a3d8/events.out.tfevents.1706512876.5a5c1570a3d8.21370.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510e845896542460eac3bb02a49fe9289d35cb17456c3a9165b9778a24ede7af
+size 4686

runs/Jan29_07-18-53_5a5c1570a3d8/events.out.tfevents.1706513107.5a5c1570a3d8.21370.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ec072d77edc7e2ae7ae00e56de8b21a2bd7ebe5baee841115e299ba3d126b9
+size 4686

runs/Jan29_07-34-17_5a5c1570a3d8/events.out.tfevents.1706513683.5a5c1570a3d8.25466.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1218db2fb49c59236c520b6ff349f37452a5b9ab23f1e42d2382d77019a31cbf
+size 10670

runs/Jan29_09-30-38_5a5c1570a3d8/events.out.tfevents.1706520640.5a5c1570a3d8.50458.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fada1b363303dc303b53ad2b48d6d853f94b4b8d214d37da5935d61b8d4edf
+size 13110

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccdf317e3b81238dc68832bde56adf5e167f4512c53edab4f1792dfa53c1156
+size 4536