End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Twitter/twhin-bert-base](https://huggingface.co/Twitter/twhin-bert-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4442
-- Accuracy: 0.8332
+- Loss: 0.4282
+- Accuracy: 0.8345
 
 ## Model description
 
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 381  | 0.4086          | 0.8267   |
-| 0.3876        | 2.0   | 762  | 0.4442          | 0.8332   |
+| No log        | 1.0   | 381  | 0.4140          | 0.8352   |
+| 0.4233        | 2.0   | 762  | 0.4282          | 0.8345   |
 
 
 ### Framework versions

config.json

@@ -10,6 +10,10 @@
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "label2id": {
+    "Disaster": 1,
+    "Not disaster": 0
+  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9b1fc6fb8a53fbe2adaa51abfa24cdf9a00d54c36d529db23d2e4fb0476205
+oid sha256:9e8f7451a648ceba364863d56d96348849e2e482c6b74d69b895d2abde0c8951
 size 1115392993

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20a6cd3f352030309aa11d63a4675405d354860f97287f76de5c704c4e236261
+oid sha256:cf282028815dfe793b197abdb80558677e1fba969088812e01dda4cf507fa5fb
 size 4027