add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,60 @@
+---
+tags:
+- generated_from_trainer
+model_index:
+- name: gpt2-medium-dutch-finetuned-text-generation
+ results:
+ - task:
+ name: Causal Language Modeling
+ type: text-generation
+---
+
+<!-- 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. -->
+
+# gpt2-medium-dutch-finetuned-text-generation
+
+This model is a fine-tuned version of [GroNLP/gpt2-medium-dutch-embeddings](https://huggingface.co/GroNLP/gpt2-medium-dutch-embeddings) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.9035
+
+## 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: 2e-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: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log | 1.0 | 402 | 3.9891 |
+| 3.3731 | 2.0 | 804 | 3.9156 |
+| 2.7263 | 3.0 | 1206 | 3.9035 |
+
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,46 @@
+{
+ "_name_or_path": "GroNLP/gpt2-medium-dutch-embeddings",
+ "activation_function": "gelu_new",
+ "architectures": [
+ "GPT2LMHeadModel"
+ ],
+ "attn_pdrop": 0.1,
+ "bos_token_id": 1,
+ "embd_pdrop": 0.1,
+ "eos_token_id": 2,
+ "gradient_checkpointing": false,
+ "initializer_range": 0.02,
+ "layer_norm_epsilon": 1e-05,
+ "model_type": "gpt2",
+ "n_ctx": 1024,
+ "n_embd": 1024,
+ "n_head": 16,
+ "n_inner": null,
+ "n_layer": 24,
+ "n_positions": 1024,
+ "n_special": 0,
+ "pad_token_id": 0,
+ "predict_special_tokens": true,
+ "resid_pdrop": 0.1,
+ "scale_attn_weights": true,
+ "summary_activation": null,
+ "summary_first_dropout": 0.1,
+ "summary_proj_to_labels": true,
+ "summary_type": "cls_index",
+ "summary_use_proj": true,
+ "task_specific_params": {
+ "text-generation": {
+ "do_sample": true,
+ "max_length": 100,
+ "no_repeat_ngram_size": 4,
+ "num_beams": 10,
+ "repetition_penalty": 10.0,
+ "temperature": 2.0,
+ "top_k": 20,
+ "top_p": 0.9
+ }
+ },
+ "transformers_version": "4.8.2",
+ "use_cache": true,
+ "vocab_size": 40000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79eb6b03af4d0782563daf7f797488dedefc87aa3260833134946076c91aab65
+size 1402568665

runs/Jul22_07-09-09_262749f64873/1626937783.167601/events.out.tfevents.1626937783.262749f64873.367.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb38d660d447e535b0b41ecb45103cef220178877ff5a4010efe581d7af63717
+size 4207

runs/Jul22_07-09-09_262749f64873/events.out.tfevents.1626937783.262749f64873.367.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d48ec84d9aff7e71af48613dc7a8da7507739051e2c04a7543e77ecc3ed01b
+size 4895

runs/Jul22_07-09-09_262749f64873/events.out.tfevents.1626938455.262749f64873.367.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6f9053687026839de53e2cba553f0ac4d126d4c54dd10eb8866e279365aae3
+size 311

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52809dd18e9fe24e894e8067a1c557e0f43d143ef658b141491c6852209815d3
+size 2671