Upload TFT5ForConditionalGeneration

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-small
+tags:
+- generated_from_keras_callback
+model-index:
+- name: demo
+  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. -->
+
+# demo
+
+This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 1.1764
+- Validation Loss: 0.9237
+- Epoch: 24
+
+## 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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 2e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 1.6824     | 1.3619          | 0     |
+| 1.5733     | 1.3030          | 1     |
+| 1.5199     | 1.2730          | 2     |
+| 1.4833     | 1.2379          | 3     |
+| 1.4591     | 1.2201          | 4     |
+| 1.4278     | 1.1945          | 5     |
+| 1.4101     | 1.1755          | 6     |
+| 1.3870     | 1.1561          | 7     |
+| 1.3740     | 1.1366          | 8     |
+| 1.3559     | 1.1163          | 9     |
+| 1.3420     | 1.1007          | 10    |
+| 1.3265     | 1.0871          | 11    |
+| 1.3082     | 1.0708          | 12    |
+| 1.2984     | 1.0586          | 13    |
+| 1.2832     | 1.0429          | 14    |
+| 1.2724     | 1.0305          | 15    |
+| 1.2634     | 1.0170          | 16    |
+| 1.2486     | 1.0090          | 17    |
+| 1.2375     | 0.9901          | 18    |
+| 1.2259     | 0.9760          | 19    |
+| 1.2128     | 0.9659          | 20    |
+| 1.2038     | 0.9556          | 21    |
+| 1.1965     | 0.9446          | 22    |
+| 1.1833     | 0.9369          | 23    |
+| 1.1764     | 0.9237          | 24    |
+
+
+### Framework versions
+
+- Transformers 4.32.0
+- TensorFlow 2.13.0
+- Datasets 2.14.4
+- Tokenizers 0.12.1

config.json

@@ -1,16 +1,20 @@
 {
+  "_name_or_path": "google/flan-t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
+  "classifier_dropout": 0.0,
   "d_ff": 1024,
   "d_kv": 64,
   "d_model": 512,
   "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
@@ -51,7 +55,7 @@
     }
   },
   "tie_word_embeddings": false,
-  "transformers_version": "4.23.1",
+  "transformers_version": "4.32.0",
   "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": "4.32.0"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02013fd5c9c9da87d569609cebe165db97bbb8f0a8bc8eaf3f574301be741cdf
+size 439831352