End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 19.3114
+- Loss: 3.7059
 
 ## Model description
 
@@ -49,17 +49,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 20.339        | 0.36  | 4    | 20.7522         |
-| 18.817        | 0.71  | 8    | 20.7752         |
-| 19.8054       | 1.07  | 12   | 20.9602         |
-| 20.1845       | 1.42  | 16   | 20.5820         |
-| 19.0897       | 1.78  | 20   | 20.4297         |
-| 19.4773       | 2.13  | 24   | 20.5561         |
-| 19.448        | 2.49  | 28   | 20.3986         |
-| 18.6107       | 2.84  | 32   | 20.1962         |
-| 19.3799       | 3.2   | 36   | 20.0190         |
-| 19.0794       | 3.56  | 40   | 19.8159         |
-| 18.489        | 3.91  | 44   | 19.3114         |
+| 4.4747        | 0.36  | 4    | 4.0650          |
+| 3.6551        | 0.71  | 8    | 4.6086          |
+| 3.6023        | 1.07  | 12   | 3.2223          |
+| 4.1356        | 1.42  | 16   | 4.3734          |
+| 3.5103        | 1.78  | 20   | 3.4911          |
+| 3.8186        | 2.13  | 24   | 4.5828          |
+| 3.5699        | 2.49  | 28   | 3.9042          |
+| 3.9307        | 2.84  | 32   | 3.8804          |
+| 3.4662        | 3.2   | 36   | 3.8901          |
+| 4.0907        | 3.56  | 40   | 4.0173          |
+| 3.7467        | 3.91  | 44   | 3.7059          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f460d7b59084037bdf348c26c8aca3ff3e61ea7a0fb8f142ab5c90d5d79994ff
+oid sha256:265c28cd1e5c1e744079d8c3e34fdcdb6d10326dcb723b6817e2a8af2ee68755
 size 594941266

special_tokens_map.json

@@ -9,7 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -49,7 +49,7 @@
   "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 4096,
-  "pad_token": "</s>",
+  "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "LongformerTokenizer",
   "trim_offsets": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aac62db9fee002e6152d6fdc2ed8982411ae77a86726793ccde63b0fac1cd27
+oid sha256:a767253255c6344443e8ccbc9aeae5206ac26c39ffe44b82ff14c024665eb89e
 size 4536