Training in progress epoch 0

README.md

@@ -13,8 +13,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [robingeibel/longformer-base-finetuned-big_patent](https://huggingface.co/robingeibel/longformer-base-finetuned-big_patent) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.2195
-- Validation Loss: 1.0887
+- Train Loss: 1.1860
+- Validation Loss: 1.0692
 - Epoch: 0
 
 ## Model description
@@ -41,12 +41,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.2195     | 1.0887          | 0     |
+| 1.1860     | 1.0692          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.19.3
+- Transformers 4.19.4
 - TensorFlow 2.8.2
 - Datasets 2.2.2
 - Tokenizers 0.12.1

config.json

@@ -37,7 +37,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "sep_token_id": 2,
-  "transformers_version": "4.19.3",
+  "transformers_version": "4.19.4",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e25f4fa2eec0706ec4e528ac981bed5a3253a02e858c746f855bcfca265f81
+oid sha256:4433bd535acdd02d20f3fac9b954aef7dbba5082257db8cb3c0f3a1014ec50d5
 size 762211788