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: 6.4127
-- Validation Loss: 6.2672
-- Epoch: 1
+- Train Loss: 7.0829
+- Validation Loss: 6.4809
+- Epoch: 0
 
 ## Model description
 
@@ -42,13 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 7.0794     | 6.5111          | 0     |
-| 6.4127     | 6.2672          | 1     |
+| 7.0829     | 6.4809          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.16.0.dev0
+- Transformers 4.19.0.dev0
 - TensorFlow 2.8.0-rc0
-- Datasets 1.17.0
+- Datasets 2.1.1.dev0
 - Tokenizers 0.11.0

config.json

@@ -18,7 +18,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.16.0.dev0",
+  "transformers_version": "4.19.0.dev0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 28996

logs/train/events.out.tfevents.1651588775.matt-TRX40-AORUS-PRO-WIFI.59064.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d40078462f6d466dd537d2b2111f90d36d7f2ceb799ebb77e0096c8b0f4d06
+size 1937488

logs/validation/events.out.tfevents.1651588927.matt-TRX40-AORUS-PRO-WIFI.59064.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:face6cf0203ab831799333730fdbbdb5c1a27e6c404178576d15232332ab40ee
+size 194

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8cd234155ebe4bf06e13b41b8a65dbd4355f54c2012d50da1bdacedd9d4dd9
+oid sha256:ad4a34ad122b2ce2c41b8f340dcb7a110f9b5e502b0139c05b944128cf44894e
 size 524305832