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 [kz-transformers/kaz-roberta-conversational](https://huggingface.co/kz-transformers/kaz-roberta-conversational) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4868
+- Loss: 0.3160
 
 ## Model description
 
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 0.4746        | 1.0   | 10125 | 0.4868          |
-| 0.3703        | 2.0   | 20250 | 0.5347          |
-| 0.1326        | 3.0   | 30375 | 0.6513          |
-| 0.2879        | 4.0   | 40500 | 0.8209          |
-| 0.1149        | 5.0   | 50625 | 0.8983          |
+| 0.1891        | 1.0   | 6750  | 0.3160          |
+| 0.3396        | 2.0   | 13500 | 0.3678          |
+| 0.0354        | 3.0   | 20250 | 0.4509          |
+| 0.0762        | 4.0   | 27000 | 0.5246          |
+| 0.0003        | 5.0   | 33750 | 0.6247          |
 
 
 ### Framework versions

logs/events.out.tfevents.1721978984.b606c03fd097.410.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566e7e0206388c7911418893ae521d461f1dc6dbebb95edfce782bbd9b30add8
-size 725215
+oid sha256:3a1cfeb0da4e919833625933eb414377b94a926ac18ae8784de6451f4c22f9d3
+size 725851

logs/events.out.tfevents.1721981257.b606c03fd097.410.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a910f846d0465cc5636487c5503378658f781905f50ffef6a206c1132353c7
+size 316

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e426a6a6163268c26ce13d1124123daabfbaaef4eea99681e78d970d1a6b8d79
+oid sha256:1cf271796e808d48db5d2b6cd47d48eb68d7cebbbe667b4484c9bf2348d8c13b
 size 333828352