Training in progress epoch 0

README.md

@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: nan
-- Epoch: 3
+- Train Loss: 15.0522
+- Epoch: 0
 
 ## Model description
 
@@ -34,22 +34,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 596, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 596, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| nan        | 0     |
-| nan        | 1     |
-| nan        | 2     |
-| nan        | 3     |
+| 15.0522    | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.20.0
+- Transformers 4.20.1
 - TensorFlow 2.8.2
 - Datasets 2.3.2
 - Tokenizers 0.12.1

config.json

@@ -24,7 +24,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
-  "transformers_version": "4.20.0",
+  "transformers_version": "4.20.1",
   "use_cache": true,
   "vocab_size": 250112
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaba0d72edacb6f659c29ae5cd5b37c48cb331974e8001c611c7e2f6b92d45e0
-size 1201097104
+oid sha256:74216e5fdc601bb0d3eac31984df9219035154b9ee696b1e554ea68622179239
+size 1201092992