Training in progress epoch 0

README.md

@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [KoichiYasuoka/roberta-classical-chinese-base-char](https://huggingface.co/KoichiYasuoka/roberta-classical-chinese-base-char) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.7947
-- Validation Loss: 0.9816
+- Train Loss: 0.7456
+- Validation Loss: 0.0584
 - Epoch: 0
 
 ## Model description
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.7947     | 0.9816          | 0     |
+| 0.7456     | 0.0584          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "KoichiYasuoka/roberta-classical-chinese-base-char",
   "architectures": [
-    "RobertaForMaskedLM"
+    "RobertaForCausalLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.2"
+}

logs/train/events.out.tfevents.1713373181.d16d92757244.2533.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e8fdc5880eed67e5882b2c646221c82795ffad94381fdc69546847935aaff5
+size 2393306

logs/train/events.out.tfevents.1713373844.d16d92757244.9304.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b237f373d99486ca8aca60921c3f90612cf6986adfe4d0aedbf9273b13fb90
+size 2393372

logs/validation/events.out.tfevents.1713374414.d16d92757244.9304.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d403c7e92e383e00c6fb3e0ad536c46e714d7c9b552c7ac9b68d076e6db70b
+size 232

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3626d98357e1edb5213028e9af1e46124a5ae261f847e57bdd7e8696e34255f
+oid sha256:ceb893f4e2499917dbe7e48d72d42df383c19241010b81624f189d042aba4856
 size 507845000