add model

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: mbart
+  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. -->
+
+# mbart
+
+This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3396
+- Validation Loss: 0.3603
+- Epoch: 13
+
+## 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': 'SGD', 'learning_rate': 0.01, 'decay': 0.0, 'momentum': 0.9, 'nesterov': False}
+- training_precision: mixed_bfloat16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 3.5941     | 2.0152          | 0     |
+| 1.5811     | 0.9978          | 1     |
+| 1.0165     | 0.8390          | 2     |
+| 0.7382     | 0.6526          | 3     |
+| 0.5833     | 0.5010          | 4     |
+| 0.5206     | 0.4613          | 5     |
+| 0.4762     | 0.4520          | 6     |
+| 0.4438     | 0.4119          | 7     |
+| 0.4009     | 0.4285          | 8     |
+| 0.3987     | 0.3728          | 9     |
+| 0.3767     | 0.3873          | 10    |
+| 0.3561     | 0.3521          | 11    |
+| 0.3470     | 0.3541          | 12    |
+| 0.3396     | 0.3603          | 13    |
+
+
+### Framework versions
+
+- Transformers 4.19.2
+- TensorFlow 2.8.0
+- Datasets 2.2.1
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "facebook/mbart-large-50",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "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": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "transformers_version": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 250054
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0abd65b377c0e9481d7b00f2a6de650daff573bcefcb31ad9e76436626eb959
+size 2445079280