Training in progress epoch 0

README.md

@@ -15,9 +15,9 @@ 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
-- Validation Loss: nan
-- Epoch: 7
+- Train Loss: 10.4070
+- Validation Loss: 4.6558
+- Epoch: 0
 
 ## Model description
 
@@ -36,26 +36,19 @@ 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': 9672, '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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 9672, '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': 0.01}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| nan        | nan             | 0     |
-| nan        | nan             | 1     |
-| nan        | nan             | 2     |
-| nan        | nan             | 3     |
-| nan        | nan             | 4     |
-| nan        | nan             | 5     |
-| nan        | nan             | 6     |
-| nan        | nan             | 7     |
+| 10.4070    | 4.6558          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.33.0
-- TensorFlow 2.12.0
-- Datasets 2.14.6.dev0
-- Tokenizers 0.13.3
+- Transformers 4.34.0
+- TensorFlow 2.13.0
+- Datasets 2.14.5
+- Tokenizers 0.14.0

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 1,
+  "<pad>": 0,
+  "<unk>": 2
+}

config.json

@@ -25,7 +25,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
-  "transformers_version": "4.33.0",
+  "transformers_version": "4.34.0",
   "use_cache": true,
   "vocab_size": 250112
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.33.0"
+  "transformers_version": "4.34.0"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2bfa3ca63c5731b7ea1f66cf0be7af07141d86f93eff577ca42858885f714b
-size 2225560376
+oid sha256:f052862ce085cf998ff9072eda8946567d51f9f5fa1fed11b4784fbb0b360923
+size 2225556280

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd38144ed4e51886247b55a7fd9b6fcca7afd7355345b522149ba074b455f2cb
-size 16330466
+oid sha256:7723ef4657f28d318b7de49edfa0fddff5ac8cedca4747782d597d10b416d58b
+size 16330485

tokenizer_config.json

@@ -1,5 +1,31 @@
 {
-  "additional_special_tokens": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 0,