eskayML/plaba_adaptations

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Vamsi/T5_Paraphrase_Paws](https://huggingface.co/Vamsi/T5_Paraphrase_Paws) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4212
+- Loss: 2.3917
 
 ## Model description
 
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 454  | 0.4414          |
-| 1.373         | 2.0   | 908  | 0.4246          |
-| 0.4716        | 3.0   | 1362 | 0.4212          |
+| No log        | 1.0   | 42   | 3.2087          |
+| No log        | 2.0   | 84   | 2.5296          |
+| No log        | 3.0   | 126  | 2.3917          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c73f832f0aaec2957c6a45a7bfb218ee6fb59236d8c9c00eb6cd08a11e0b65b
+oid sha256:242d18341961d9a19df90e8b6945ed522e5c6e2de40cef6627d9526f141db9d9
 size 891644712

runs/Aug28_08-07-15_8492ab503b0e/events.out.tfevents.1724832436.8492ab503b0e.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84813e4791560ca0f82534f95881ef382bae1e198595f98078e9504c7e01dce
+size 6844

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 128
+      "Fixed": 256
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0d26bd4f6780f4b0f0bfb200d118a44ce31de8e26aae675838cdd60390d0f8
+oid sha256:72585ddfe1eb3039471368a4d591bd95947e3fb9baeb721f414f91adf1c2a800
 size 5112