Upload TFMT5ForConditionalGeneration

README.md

@@ -0,0 +1,103 @@
+---
+license: apache-2.0
+base_model: serhii-korobchenko/mt5-small_poetry_test-2024-02-23-11-37-04
+tags:
+- generated_from_keras_callback
+model-index:
+- name: mt5-small_poetry_test-2024-02-23-15-43-02
+  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. -->
+
+# mt5-small_poetry_test-2024-02-23-15-43-02
+
+This model is a fine-tuned version of [serhii-korobchenko/mt5-small_poetry_test-2024-02-23-11-37-04](https://huggingface.co/serhii-korobchenko/mt5-small_poetry_test-2024-02-23-11-37-04) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 1.0719
+- Validation Loss: 8.8056
+- Epoch: 49
+
+## 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0056, 'decay_steps': 750, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 1e-06}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 10.6051    | 8.0186          | 0     |
+| 7.2838     | 7.5097          | 1     |
+| 6.1079     | 7.5227          | 2     |
+| 5.8520     | 7.6991          | 3     |
+| 5.7403     | 7.6098          | 4     |
+| 5.7371     | 7.6277          | 5     |
+| 5.6356     | 7.6047          | 6     |
+| 5.6156     | 7.7156          | 7     |
+| 5.5722     | 7.5735          | 8     |
+| 5.5118     | 7.5908          | 9     |
+| 5.4539     | 7.6017          | 10    |
+| 5.3815     | 7.6174          | 11    |
+| 5.3763     | 7.6022          | 12    |
+| 5.2895     | 7.4830          | 13    |
+| 5.2140     | 7.5455          | 14    |
+| 5.1843     | 7.4243          | 15    |
+| 5.1056     | 7.3897          | 16    |
+| 4.9740     | 7.2854          | 17    |
+| 4.9361     | 7.2887          | 18    |
+| 4.8234     | 7.4561          | 19    |
+| 4.9462     | 7.3764          | 20    |
+| 4.8029     | 7.2209          | 21    |
+| 4.6122     | 7.1327          | 22    |
+| 4.4010     | 7.3362          | 23    |
+| 4.2291     | 7.0549          | 24    |
+| 4.0323     | 7.2076          | 25    |
+| 3.8655     | 7.2932          | 26    |
+| 3.6406     | 7.3575          | 27    |
+| 3.4665     | 7.2689          | 28    |
+| 3.4070     | 7.1520          | 29    |
+| 3.3049     | 7.4382          | 30    |
+| 3.0354     | 7.5552          | 31    |
+| 2.7136     | 7.2149          | 32    |
+| 2.5568     | 7.8140          | 33    |
+| 2.2594     | 7.7701          | 34    |
+| 2.1743     | 7.9400          | 35    |
+| 2.0776     | 8.1060          | 36    |
+| 1.8686     | 7.7733          | 37    |
+| 1.8453     | 8.1850          | 38    |
+| 1.7281     | 7.8816          | 39    |
+| 1.5912     | 7.8918          | 40    |
+| 1.4447     | 8.4160          | 41    |
+| 1.4090     | 8.5857          | 42    |
+| 1.2143     | 8.5367          | 43    |
+| 1.2254     | 8.3491          | 44    |
+| 1.0937     | 8.8601          | 45    |
+| 1.1357     | 8.4994          | 46    |
+| 1.0708     | 8.9421          | 47    |
+| 1.0830     | 8.9817          | 48    |
+| 1.0719     | 8.8056          | 49    |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- TensorFlow 2.15.0
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "serhii-korobchenko/mt5-small_poetry_test-2024-02-23-11-37-04",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

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": "4.37.2"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108f0fae6d7a3f1fc2e246e8c79bec0187f2893878bf843d5405346815a3c187
+size 2225556280