Upload TFT5ForConditionalGeneration

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: test-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. -->
+
+# test-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: 1.0322
+- Validation Loss: 0.9818
+- Train Rouge1: 63.3560
+- Train Rouge2: 39.8622
+- Train Rougel: 62.5870
+- Train Rougelsum: 62.5573
+- 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 |
+|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-----:|
+| 1.2033     | 1.1011          | 63.0488      | 39.8152      | 62.3015      | 62.2699         | 0     |
+| 1.1660     | 1.0732          | 63.6556      | 40.2704      | 62.8821      | 62.8498         | 1     |
+| 1.1394     | 1.0532          | 63.8815      | 40.5348      | 63.1276      | 63.0965         | 2     |
+| 1.1149     | 1.0386          | 64.2783      | 40.8596      | 63.5115      | 63.4840         | 3     |
+| 1.0969     | 1.0245          | 63.6975      | 40.1645      | 62.9323      | 62.8990         | 4     |
+| 1.0831     | 1.0122          | 63.7146      | 40.3383      | 62.9457      | 62.9173         | 5     |
+| 1.0678     | 1.0044          | 63.3129      | 39.9492      | 62.5462      | 62.5154         | 6     |
+| 1.0551     | 0.9949          | 62.5523      | 39.2999      | 61.7963      | 61.7831         | 7     |
+| 1.0417     | 0.9869          | 63.3126      | 40.0112      | 62.5606      | 62.5360         | 8     |
+| 1.0322     | 0.9818          | 63.3560      | 39.8622      | 62.5870      | 62.5573         | 9     |
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- TensorFlow 2.9.2
+- Datasets 2.8.0
+- Tokenizers 0.13.2

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": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74ef9246a3c49f3013b0f8252733eed0567e799e08691195e670c0f1cc78d84
+size 373902848