Upload TFT5ForConditionalGeneration

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: t5-small
+tags:
+- generated_from_keras_callback
+model-index:
+- name: keyword-masked-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. -->
+
+# keyword-masked-model
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.9545
+- Validation Loss: 0.7767
+- Train Rouge1: 76.8067
+- Train Rouge2: 64.2138
+- Train Rougel: 76.1124
+- Train Rougelsum: 76.0843
+- 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': 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 | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Epoch |
+|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-----:|
+| 2.7609     | 2.0508          | 69.5404      | 56.1190      | 67.9736      | 67.9553         | 0     |
+| 2.0227     | 1.5912          | 71.6288      | 58.5009      | 70.6498      | 70.7363         | 1     |
+| 1.6780     | 1.3604          | 70.8191      | 58.1082      | 70.0231      | 69.8913         | 2     |
+| 1.4974     | 1.2163          | 69.9943      | 57.3099      | 68.7338      | 68.7593         | 3     |
+| 1.3525     | 1.1001          | 70.4850      | 57.7869      | 69.2259      | 69.2106         | 4     |
+| 1.2480     | 1.0154          | 71.1204      | 58.1709      | 69.9356      | 69.9324         | 5     |
+| 1.1556     | 0.9368          | 72.5520      | 59.4597      | 71.3193      | 71.4219         | 6     |
+| 1.0820     | 0.8754          | 74.5839      | 61.6499      | 73.6577      | 73.6458         | 7     |
+| 1.0117     | 0.8244          | 75.0935      | 62.3254      | 74.3574      | 74.2253         | 8     |
+| 0.9545     | 0.7767          | 76.8067      | 64.2138      | 76.1124      | 76.0843         | 9     |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- TensorFlow 2.12.0
+- Datasets 2.13.1
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a32409fe8fa8ba11ab3352738c0ddd1027e2fd73f3713d8bd18547dd11a5dc2
+size 373902664