Upload TFT5ForConditionalGeneration

README.md

@@ -0,0 +1,61 @@
+---
+base_model: deanna-emery/ASL_t5_word_epoch15_1204
+tags:
+- generated_from_keras_callback
+model-index:
+- name: ASL_t5_movinet_sentence
+  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. -->
+
+# ASL_t5_movinet_sentence
+
+This model is a fine-tuned version of [deanna-emery/ASL_t5_word_epoch15_1204](https://huggingface.co/deanna-emery/ASL_t5_word_epoch15_1204) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.2835
+- Train Top 1: 0.9429
+- Train Top 5: 0.9663
+- Validation Loss: 0.3456
+- Validation Top 1: 0.9379
+- Validation Top 5: 0.9602
+- Train Bleu: 0.8177
+- Train Gen Len: 14.9924
+- Epoch: 2
+
+## 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': 'Adafactor', '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': {'module': 'keras.optimizers.schedules', 'class_name': 'CosineDecay', 'config': {'initial_learning_rate': 0.0005, 'decay_steps': 1335, 'alpha': 0.0, 'name': None, 'warmup_target': 0.0005, 'warmup_steps': 400}, 'registered_name': None}, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Top 1 | Train Top 5 | Validation Loss | Validation Top 1 | Validation Top 5 | Train Bleu | Train Gen Len | Epoch |
+|:----------:|:-----------:|:-----------:|:---------------:|:----------------:|:----------------:|:----------:|:-------------:|:-----:|
+| 0.3382     | 0.9366      | 0.9593      | 0.3506          | 0.9365           | 0.9592           | 0.5417     | 17.4659       | 0     |
+| 0.3085     | 0.9398      | 0.9631      | 0.3450          | 0.9373           | 0.9600           | 0.6583     | 15.1629       | 1     |
+| 0.2835     | 0.9429      | 0.9663      | 0.3456          | 0.9379           | 0.9602           | 0.8177     | 14.9924       | 2     |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- TensorFlow 2.13.0
+- Datasets 2.15.0
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "deanna-emery/ASL_t5_word_epoch15_1204",
+  "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:d2d2bd109946a4a581d0cd62281c7c0f3b0ff1865d84844a6947381d4f378f1b
+size 1089544048