End of training

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-nl
+tags:
+- generated_from_trainer
+model-index:
+- name: translator
+ 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. -->
+
+# translator
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-nl](https://huggingface.co/Helsinki-NLP/opus-mt-en-nl) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1557
+- Blue: 17.9685
+- Gen Len: 33.605
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Blue | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| No log | 1.0 | 50 | 2.1831 | 17.9315 | 33.73 |
+| No log | 2.0 | 100 | 2.1557 | 17.9685 | 33.605 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,61 @@
+{
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-nl",
+ "_num_labels": 3,
+ "activation_dropout": 0.0,
+ "activation_function": "swish",
+ "add_bias_logits": false,
+ "add_final_layer_norm": false,
+ "architectures": [
+ "MarianMTModel"
+ ],
+ "attention_dropout": 0.0,
+ "bad_words_ids": [
+ [
+ 67027
+ ]
+ ],
+ "bos_token_id": 0,
+ "classif_dropout": 0.0,
+ "classifier_dropout": 0.0,
+ "d_model": 512,
+ "decoder_attention_heads": 8,
+ "decoder_ffn_dim": 2048,
+ "decoder_layerdrop": 0.0,
+ "decoder_layers": 6,
+ "decoder_start_token_id": 67027,
+ "decoder_vocab_size": 67028,
+ "dropout": 0.1,
+ "encoder_attention_heads": 8,
+ "encoder_ffn_dim": 2048,
+ "encoder_layerdrop": 0.0,
+ "encoder_layers": 6,
+ "eos_token_id": 0,
+ "forced_eos_token_id": 0,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2"
+ },
+ "init_std": 0.02,
+ "is_encoder_decoder": true,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2
+ },
+ "max_length": 512,
+ "max_position_embeddings": 512,
+ "model_type": "marian",
+ "normalize_before": false,
+ "normalize_embedding": false,
+ "num_beams": 4,
+ "num_hidden_layers": 6,
+ "pad_token_id": 67027,
+ "scale_embedding": true,
+ "share_encoder_decoder_embeddings": true,
+ "static_position_embeddings": true,
+ "torch_dtype": "float32",
+ "transformers_version": "4.35.2",
+ "use_cache": true,
+ "vocab_size": 67028
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+ "bad_words_ids": [
+ [
+ 67027
+ ]
+ ],
+ "bos_token_id": 0,
+ "decoder_start_token_id": 67027,
+ "eos_token_id": 0,
+ "forced_eos_token_id": 0,
+ "max_length": 512,
+ "num_beams": 4,
+ "pad_token_id": 67027,
+ "renormalize_logits": true,
+ "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7301692680a2251ff0d56b2b8b815a5f18c9711176ef524a69c498a54ab04d6b
+size 314124496

runs/Jan24_16-03-16_9212c44340eb/events.out.tfevents.1706112196.9212c44340eb.1449.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e7bdd495e2f7d68f5daa19cfa0d3cc55d88414dd5cb6e7786ed5ba19b87684
+size 6147

runs/Jan24_16-08-28_9212c44340eb/events.out.tfevents.1706112509.9212c44340eb.4978.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd35b55aedc71e6d648410dcf7d956d294d8f8985bd851ba803c2f096fd7dec
+size 6145

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+ "eos_token": "</s>",
+ "pad_token": "<pad>",
+ "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "67027": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "</s>",
+ "model_max_length": 512,
+ "pad_token": "<pad>",
+ "separate_vocabs": false,
+ "source_lang": "en",
+ "sp_model_kwargs": {},
+ "target_lang": "nl",
+ "tokenizer_class": "MarianTokenizer",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c03e4056c975e1c9757445c0870e69005cd2b165fd1f42817923e64492e20b
+size 4728