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 [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.0256
+- Loss: 2.6829
 
 ## Model description
 
@@ -43,13 +43,20 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
-- training_steps: 10
+- training_steps: 80
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.4203        | 0.0   | 10   | 5.0256          |
+| 3.2351        | 0.0   | 10   | 5.9935          |
+| 5.153         | 0.01  | 20   | 4.4330          |
+| 4.6793        | 0.01  | 30   | 4.4511          |
+| 3.6354        | 0.01  | 40   | 3.4206          |
+| 3.1289        | 0.02  | 50   | 3.1252          |
+| 2.8439        | 0.02  | 60   | 2.9242          |
+| 2.6681        | 0.02  | 70   | 2.7407          |
+| 2.494         | 0.03  | 80   | 2.6829          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ebc636d1342ed98fae943c43a14615f8db30ba0332739bd3ceadab1ee1eebb
+oid sha256:e329caa7308d9dd598372a93fb017d90c23519a0749051b3c66672f1de88a25b
 size 1825928473

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91666b4dec151ac80e3e2528854f441bb415e54bfc771856475e1ec1d3f049ef
+oid sha256:42235c285e4ea1b94e0c38f6e10d5dce95faaf14b62641a4ab4e706d3c2ce7e1
 size 4027