Training in progress epoch 0

README.md

@@ -14,9 +14,9 @@ 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: 4.1574
-- Validation Loss: 3.4068
-- Epoch: 7
+- Train Loss: 9.6302
+- Validation Loss: 4.2399
+- Epoch: 0
 
 ## Model description
 
@@ -42,19 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 10.5328    | 4.9229          | 0     |
-| 6.3261     | 4.1139          | 1     |
-| 5.4130     | 3.7304          | 2     |
-| 4.8950     | 3.5726          | 3     |
-| 4.5543     | 3.4901          | 4     |
-| 4.3561     | 3.4474          | 5     |
-| 4.2291     | 3.4171          | 6     |
-| 4.1574     | 3.4068          | 7     |
+| 9.6302     | 4.2399          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.18.0
+- Transformers 4.19.2
 - TensorFlow 2.8.0
-- Datasets 2.0.0
-- Tokenizers 0.11.6
+- Datasets 2.2.2
+- Tokenizers 0.12.1

config.json

@@ -22,7 +22,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
-  "transformers_version": "4.18.0",
+  "transformers_version": "4.19.2",
   "use_cache": true,
   "vocab_size": 250112
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cadfb0a8f6d141aa672533e0d7ade3d373f0d1cc0069f16f577329100a1436a
+oid sha256:c504bde652d2b729158b743202fb144aa93c4b0630fdb634b826dd5cf7366bd7
 size 1201092992