batch_size=64

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-large
+tags:
+- generated_from_keras_callback
+model-index:
+- name: t5-large-mmlu-qa2a
+  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-large-mmlu-qa2a
+
+This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1894
+- Validation Loss: 0.0719
+- Epoch: 0
+
+## 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': False, 'is_legacy_optimizer': False, 'learning_rate': 0.001, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.1894     | 0.0719          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- TensorFlow 2.12.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/flan-t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.31.0",
+  "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": "4.31.0"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3f9e9f1bbc2d99b29d6ce711617df87c60d2e8cade78214b21c4138ccf29f4
+size 3396920920