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 [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4789
+- Loss: 1.1706
 
 ## Model description
 
@@ -40,20 +40,23 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.9432        | 1.0   | 72   | 1.9258          |
-| 2.2068        | 2.0   | 144  | 1.5627          |
-| 1.3339        | 3.0   | 216  | 1.4789          |
+| 2.3938        | 1.0   | 72   | 1.8482          |
+| 1.5735        | 2.0   | 144  | 1.4687          |
+| 2.0029        | 3.0   | 216  | 1.3260          |
+| 1.6424        | 4.0   | 288  | 1.2291          |
+| 1.2187        | 5.0   | 360  | 1.1848          |
+| 0.5262        | 6.0   | 432  | 1.1706          |
 
 
 ### Framework versions
 
-- Transformers 4.43.4
-- Pytorch 2.4.0+cu121
+- Transformers 4.41.2
+- Pytorch 2.4.0
 - Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -23,7 +23,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.43.4",
+  "transformers_version": "4.41.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f102435f4f80f0c68fc7b295a31e2a6a3d146e436f235962f04449f2fbc6542d
+oid sha256:35e5b0428008e59ee0ee7a5d84c8bc7e2a9b91f551a27c2f19da99eb30e59c62
 size 496250232

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6e32daa03b7c861330289f350452edca2db39fc5fb685c7c0fd18225ad0de3
-size 5176
+oid sha256:fe674f5550a770b4439a4694756bb78e65dfaaafd65c486a726b0cf6942a562e
+size 5048