Upload model

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: es-en-model
+  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. -->
+
+# es-en-model
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-en](https://huggingface.co/Helsinki-NLP/opus-mt-es-en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.2348
+- Train Acc: 0.3632
+- Validation Loss: 0.4936
+- Validation Acc: 0.3406
+- Epoch: 6
+
+## 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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Acc | Validation Loss | Validation Acc | Epoch |
+|:----------:|:---------:|:---------------:|:--------------:|:-----:|
+| 0.5028     | 0.3416    | 0.4575          | 0.3401         | 0     |
+| 0.4209     | 0.3483    | 0.4518          | 0.3409         | 1     |
+| 0.3689     | 0.3519    | 0.4544          | 0.3410         | 2     |
+| 0.3269     | 0.3535    | 0.4618          | 0.3410         | 3     |
+| 0.2914     | 0.3579    | 0.4712          | 0.3412         | 4     |
+| 0.2611     | 0.3598    | 0.4824          | 0.3411         | 5     |
+| 0.2348     | 0.3632    | 0.4936          | 0.3406         | 6     |
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- TensorFlow 2.9.2
+- Datasets 2.6.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-es-en",
+  "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,
+  "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,
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 65001
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334c229f2dd3e81645a861b49570a8287243ec57a4da0647ca2efb7ca0e1b66a
+size 312320660