End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the scitldr dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7611
+- Loss: 2.1169
 
 ## Model description
 
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1638        | 0.4   | 800  | 2.6916          |
-| 2.297         | 0.8   | 1600 | 2.6541          |
-| 1.8784        | 1.2   | 2400 | 2.7509          |
-| 1.9204        | 1.61  | 3200 | 2.7611          |
+| 2.1545        | 0.4   | 800  | 2.1836          |
+| 1.9782        | 0.8   | 1600 | 2.0954          |
+| 1.6786        | 1.2   | 2400 | 2.1249          |
+| 1.6459        | 1.61  | 3200 | 2.1169          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609c74e33e88a5216d6e7105ae612dec5ad8ea34534e2adcbcb3f51d8589f2a4
+oid sha256:f62c38dfe8fa5bc5e385fd89c444a2f811ec20e2c81c42db46998ca31ac99691
 size 6308286

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07f383f2e75db42a0ed36e83f12b7f6bb7ad3393b845f0fa8828d87118f07fe
+oid sha256:084cb0c4ae268a1804e7ce0e56f1130bfc365d6da1aac0ce2a8163a90f690b8e
 size 4536