Upload TFT5ForConditionalGeneration

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: t5-small
 tags:
 - generated_from_keras_callback
 model-index:
@@ -14,7 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 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: 2.9206
+- Validation Loss: 2.5902
+- Train Rougel: tf.Tensor(0.18895291, shape=(), dtype=float32)
+- Epoch: 0
 
 ## Model description
 
@@ -33,16 +37,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: None
+- 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 | Train Rougel                                   | Epoch |
+|:----------:|:---------------:|:----------------------------------------------:|:-----:|
+| 2.9206     | 2.5902          | tf.Tensor(0.18895291, shape=(), dtype=float32) | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.20.0
+- Transformers 4.31.0
 - TensorFlow 2.13.0
 - Datasets 2.10.0
-- Tokenizers 0.12.1
+- Tokenizers 0.13.3

config.json

@@ -9,19 +9,26 @@
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
+  "early_stopping": true,
   "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,
+  "length_penalty": 2.0,
+  "max_length": 200,
+  "min_length": 30,
   "model_type": "t5",
   "n_positions": 512,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
   "num_decoder_layers": 6,
   "num_heads": 8,
   "num_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
+  "prefix": "summarize: ",
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "task_specific_params": {
@@ -53,7 +60,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "transformers_version": "4.20.0",
+  "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 1,
+  "length_penalty": 2.0,
+  "max_length": 200,
+  "min_length": 30,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b6345cc5a50ef6f44dab75fbbd1d17d7e10b9d551759efdb6a4969488a645a
-size 242301696
+oid sha256:f71a27850a9bc15dbc3cfda75fd9fc8c29432024236198cd7dcd4dfadfb7d82d
+size 373902664