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 [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 6.4077
-- Validation Loss: 6.2838
-- Epoch: 1
+- Train Loss: 7.0679
+- Validation Loss: 6.4768
+- Epoch: 0
 
 ## Model description
 
@@ -42,8 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 7.0931     | 6.5030          | 0     |
-| 6.4077     | 6.2838          | 1     |
+| 7.0679     | 6.4768          | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1658239748.matt-TRX40-AORUS-PRO-WIFI.22452.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c13cb8c35354f43b347e38349bcd9df6bd72cbde57292cbb55a5d8fc5e98f87
+size 2178078

logs/validation/events.out.tfevents.1658239888.matt-TRX40-AORUS-PRO-WIFI.22452.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b153afdb0f41b66c163de2e5fb1d75729fa266aae5e631896afe9fcab303d51
+size 194

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a823806ad92f852943bd1e4057298156e26aa367e7e587ff4b126bd48fb3d1
+oid sha256:74179ea40bbf66e63280f0710418c7e93a4ed524def1ac0cbbecf4b610606e26
 size 524305832

tokenizer_config.json

@@ -3,7 +3,7 @@
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "sgugger/bert-like-tokenizer",
+  "name_or_path": "bert-base-cased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,