End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-it
+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-it
+      split: train
+      args: en-it
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 46.572303901517024
+---
+
+<!-- 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-it](https://huggingface.co/Helsinki-NLP/opus-mt-en-it) on the kde4 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9843
+- Bleu: 46.5723
+- Bert Score: 0.8878
+
+## 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: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-it",
+  "_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": [
+    [
+      80034
+    ]
+  ],
+  "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": 80034,
+  "decoder_vocab_size": 80035,
+  "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": 80034,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 80035
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      80034
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 80034,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 80034,
+  "renormalize_logits": true,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73425b340ecb732e4d3208bae2d419ab9030657211e527e99172dbc308da8564
+size 340814860

runs/Apr21_13-20-22_84f7eeb3c140/events.out.tfevents.1713705643.84f7eeb3c140.191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0337b0be654ff1098310895af28a922c97f3a8b75951279289580f4a784228
+size 6213

runs/Apr21_13-20-22_84f7eeb3c140/events.out.tfevents.1713706127.84f7eeb3c140.191.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e8c178c63ee51658d3eecf959a4f49794ecbd5bdd548277bc0c8946ba755ea
+size 6213

runs/Apr21_14-04-58_84f7eeb3c140/events.out.tfevents.1713708319.84f7eeb3c140.191.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de1a1fedaf2e163c59e1aa4af11108292aaeedc27afdfccb4a2d5b018b6564d6
+size 4184

runs/Apr21_14-09-55_84f7eeb3c140/events.out.tfevents.1713708617.84f7eeb3c140.13373.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6473409f18336abe4dd859ebe1418e7f329f03eefbb4deb03738fe52beaeb7a
+size 6635

runs/Apr21_14-09-55_84f7eeb3c140/events.out.tfevents.1713709884.84f7eeb3c140.13373.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322e0ee75e197d0753e40bb966a757676a9c61b12e9432f87e18a4783e30b4f5
+size 461

runs/Apr21_14-35-17_84f7eeb3c140/events.out.tfevents.1713710136.84f7eeb3c140.20099.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457db3f995174ce5a01d833fbc866bb2bcb6a5e4b3a0c155558b46947339348a
+size 6846

runs/Apr21_14-35-17_84f7eeb3c140/events.out.tfevents.1713711909.84f7eeb3c140.20099.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8285e758b3cebe5837caeaea02af98de050151028e1d6abda7ab8c8d66b1dd75
+size 461

runs/Apr21_14-35-17_84f7eeb3c140/events.out.tfevents.1713712525.84f7eeb3c140.20099.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828573548c030ec2001020631dd42b752957bc4b90e9b1cfc8beee40a848856a
+size 6846

runs/Apr21_14-35-17_84f7eeb3c140/events.out.tfevents.1713715617.84f7eeb3c140.20099.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14e87d2a12de913e38dce4481839ebafd88aa5cf376df6b3fe0c4d6e6293f4a
+size 461

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
+    },
+    "80034": {
+      "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": "it",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ff27f283cd98f1131339625e468cd86c80c8ccf9dc8342678ec2d5859872ed
+size 5048