100k (512)

README.md

@@ -1,3 +1,64 @@
 ---
-license: cc-by-4.0
+tags:
+- generated_from_trainer
+datasets:
+- danish_legal_pile
+model-index:
+- name: danish-legal-xlm-base-mlm
+  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. -->
+
+# danish-legal-xlm-base-mlm
+
+This model is a fine-tuned version of [data/plms/danish-legal-xlm-base](https://huggingface.co/data/plms/danish-legal-xlm-base) on the danish_legal_pile dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7384
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: tpu
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 256
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- training_steps: 100000
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 0.8936        | 22.9  | 50000  | 0.7870          |
+| 0.827         | 45.81 | 100000 | 0.7385          |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- Pytorch 1.12.0+cu102
+- Datasets 2.0.0
+- Tokenizers 0.12.0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "data/plms/danish-legal-xlm-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9039a9e06bcc8953591a0b2f9b0c66e968c79b14aa38a925b6dafbe2d74b7a45
+size 442675755

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "special_tokens_map_file": "data/PLMs/danish-lm/danish-lex-lm-base/special_tokens_map.json", "name_or_path": "data/plms/danish-legal-xlm-base", "tokenizer_class": "PreTrainedTokenizerFast"}