Training in progress epoch 0

README.md

@@ -11,10 +11,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # robingeibel/longformer-large-finetuned-big_patent
 
-This model is a fine-tuned version of [allenai/longformer-large-4096](https://huggingface.co/allenai/longformer-large-4096) on an unknown dataset.
+This model is a fine-tuned version of [robingeibel/longformer-large-finetuned-big_patent](https://huggingface.co/robingeibel/longformer-large-finetuned-big_patent) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.2679
-- Validation Loss: 1.0674
+- Train Loss: 1.1854
+- Validation Loss: 1.0492
 - Epoch: 0
 
 ## Model description
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.2679     | 1.0674          | 0     |
+| 1.1854     | 1.0492          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "allenai/longformer-large-4096",
+  "_name_or_path": "robingeibel/longformer-large-finetuned-big_patent",
   "architectures": [
     "LongformerForMaskedLM"
   ],

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f265e0bb0e21855ff191b59a7fd71613300c07350dfbfca7ce9fdd0674891f4
+oid sha256:31cb0020b1c8c5da8c13739e19b30dee39e624a910d125e4a7d085ff7e47aede
 size 1961973772

tokenizer_config.json

@@ -6,7 +6,7 @@
   "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 4096,
-  "name_or_path": "allenai/longformer-large-4096",
+  "name_or_path": "robingeibel/longformer-large-finetuned-big_patent",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "special_tokens_map_file": null,