End of training

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-ru-uk
+tags:
+- generated_from_keras_callback
+model-index:
+- name: serhii-korobchenko/mt5-small_poetry_Helsinki-2024-02-23-17-44-34
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# serhii-korobchenko/mt5-small_poetry_Helsinki-2024-02-23-17-44-34
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ru-uk](https://huggingface.co/Helsinki-NLP/opus-mt-ru-uk) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.2018
+- Validation Loss: 2.2975
+- Epoch: 9
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-06, 'decay_steps': 170, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 1e-06}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.3109     | 2.2869          | 0     |
+| 0.2907     | 2.2903          | 1     |
+| 0.2609     | 2.2948          | 2     |
+| 0.2368     | 2.2973          | 3     |
+| 0.2376     | 2.2974          | 4     |
+| 0.2182     | 2.2975          | 5     |
+| 0.2131     | 2.2975          | 6     |
+| 0.2131     | 2.2975          | 7     |
+| 0.2025     | 2.2973          | 8     |
+| 0.2018     | 2.2975          | 9     |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- TensorFlow 2.15.0
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-ru-uk",
+  "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": [
+    [
+      57776
+    ]
+  ],
+  "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": 57776,
+  "decoder_vocab_size": 57777,
+  "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": 57777,
+  "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": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 57776,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 57777
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      57776
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 57776,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 57776,
+  "transformers_version": "4.37.2"
+}

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d989ee1653a22aa05280110ca2abaccb8a77b397a64f14576984f0a9f9a8d2ec
+size 1049819

special_tokens_map.json

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

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8d0a245c07efca75da76f0c68e9d61bc9667af1ee81d230faf14869653b234
+size 1031670

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca8224feabec2301707eefa0fbced7ed8c496418b9b48fed8b5f62d7415d78e
+size 297496948

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
+    },
+    "57776": {
+      "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": "rus",
+  "sp_model_kwargs": {},
+  "target_lang": "ukr",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}