Upload TFT5ForConditionalGeneration

README.md

@@ -1,3 +1,83 @@
 ---
 license: apache-2.0
+base_model: t5-base
+tags:
+- generated_from_keras_callback
+model-index:
+- name: t5-base-en-to-svo-converter
+  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. -->
+
+# t5-base-en-to-svo-converter
+
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 1.4502
+- Validation Loss: 0.9447
+- Epoch: 29
+
+## 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 | Epoch |
+|:----------:|:---------------:|:-----:|
+| 6.1759     | 5.0248          | 0     |
+| 4.8012     | 4.0190          | 1     |
+| 4.1438     | 3.3283          | 2     |
+| 3.6919     | 3.0962          | 3     |
+| 3.4139     | 2.7165          | 4     |
+| 3.2353     | 2.6857          | 5     |
+| 3.0536     | 2.5674          | 6     |
+| 2.9421     | 2.3690          | 7     |
+| 2.7912     | 2.2234          | 8     |
+| 2.7126     | 2.0857          | 9     |
+| 2.5692     | 1.9333          | 10    |
+| 2.4803     | 1.8273          | 11    |
+| 2.3759     | 1.7388          | 12    |
+| 2.3160     | 1.6881          | 13    |
+| 2.2398     | 1.6645          | 14    |
+| 2.1722     | 1.6141          | 15    |
+| 2.1018     | 1.6087          | 16    |
+| 2.0382     | 1.4362          | 17    |
+| 1.9601     | 1.3715          | 18    |
+| 1.8813     | 1.3523          | 19    |
+| 1.8604     | 1.2811          | 20    |
+| 1.8046     | 1.3163          | 21    |
+| 1.7001     | 1.2058          | 22    |
+| 1.7068     | 1.2065          | 23    |
+| 1.6475     | 1.1352          | 24    |
+| 1.5943     | 1.1278          | 25    |
+| 1.5792     | 0.9393          | 26    |
+| 1.5407     | 1.0137          | 27    |
+| 1.4625     | 1.0382          | 28    |
+| 1.4502     | 0.9447          | 29    |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- TensorFlow 2.14.0
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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": "4.34.1",
+  "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": "4.34.1"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24faf70d54d218bbfb212fefbb19a2c23945ad441bab157509e18f968dbb60fe
+size 1089544048