End of training

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-es
+tags:
+- generated_from_trainer
+datasets:
+- kde4
+metrics:
+- bleu
+model-index:
+- name: finetuned-model
+ results:
+ - task:
+ name: Sequence-to-sequence Language Modeling
+ type: text2text-generation
+ dataset:
+ name: kde4
+ type: kde4
+ config: en-es
+ split: train
+ args: en-es
+ metrics:
+ - name: Bleu
+ type: bleu
+ value: 42.22590503762825
+---
+
+<!-- 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. -->
+
+# finetuned-model
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-es](https://huggingface.co/Helsinki-NLP/opus-mt-en-es) on the kde4 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0902
+- Bleu: 42.2259
+- Bert Score: 0.9004
+
+## 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: 4
+- 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 4.34.1
+- Pytorch 2.0.1
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,63 @@
+{
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-es",
+ "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": [
+ [
+ 65000
+ ]
+ ],
+ "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": 65000,
+ "decoder_vocab_size": 65001,
+ "dropout": 0.1,
+ "encoder_attention_heads": 8,
+ "encoder_ffn_dim": 2048,
+ "encoder_layerdrop": 0.0,
+ "encoder_layers": 6,
+ "eos_token_id": 0,
+ "extra_pos_embeddings": 65001,
+ "force_bos_token_to_be_generated": false,
+ "forced_eos_token_id": 0,
+ "gradient_checkpointing": false,
+ "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": 65000,
+ "scale_embedding": true,
+ "share_encoder_decoder_embeddings": true,
+ "static_position_embeddings": true,
+ "torch_dtype": "float32",
+ "transformers_version": "4.34.1",
+ "use_cache": true,
+ "vocab_size": 65001
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+ "bad_words_ids": [
+ [
+ 65000
+ ]
+ ],
+ "bos_token_id": 0,
+ "decoder_start_token_id": 65000,
+ "eos_token_id": 0,
+ "forced_eos_token_id": 0,
+ "max_length": 512,
+ "num_beams": 4,
+ "pad_token_id": 65000,
+ "renormalize_logits": true,
+ "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b7f3853abd40bfe5e7e2865acd4eaec1eac9ddaad47a6c94aa411714437de4
+size 310018949

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
+ },
+ "65000": {
+ "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": "eng",
+ "sp_model_kwargs": {},
+ "target_lang": "spa",
+ "tokenizer_class": "MarianTokenizer",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12f7694c4fe88842fb61b2bf3c80fa56f81f5cb5460d64ac968a44d29c1683e
+size 4219