End of training

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8243
+- Loss: 0.7400
 
 ## Model description
 
@@ -44,16 +44,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.8893        | 1.0   | 6    | 2.1271          |
-| 1.9669        | 2.0   | 12   | 1.8233          |
-| 1.6822        | 3.0   | 18   | 1.5134          |
-| 1.3991        | 4.0   | 24   | 1.2639          |
-| 1.1731        | 5.0   | 30   | 1.1030          |
-| 1.0664        | 6.0   | 36   | 0.9758          |
-| 0.9729        | 7.0   | 42   | 0.9245          |
-| 0.9171        | 8.0   | 48   | 0.8696          |
-| 0.8722        | 9.0   | 54   | 0.8384          |
-| 0.8487        | 10.0  | 60   | 0.8243          |
+| 2.966         | 1.0   | 6    | 2.2765          |
+| 2.0606        | 2.0   | 12   | 1.7855          |
+| 1.6303        | 3.0   | 18   | 1.4249          |
+| 1.2968        | 4.0   | 24   | 1.1742          |
+| 1.1342        | 5.0   | 30   | 1.0421          |
+| 0.9916        | 6.0   | 36   | 0.9159          |
+| 0.8864        | 7.0   | 42   | 0.8410          |
+| 0.8119        | 8.0   | 48   | 0.7857          |
+| 0.7691        | 9.0   | 54   | 0.7509          |
+| 0.7515        | 10.0  | 60   | 0.7400          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c786ce574c7b54427c775c1c401bc60b3a2a1bf4da9d34ebd224728b1d9fdb1
+oid sha256:52242b7293996d19398d1cb5904e713f5bce9bdcddfa61064c3e552d21d77ae3
 size 31213760

runs/Feb28_13-41-13_3897ec21fae5/events.out.tfevents.1709127675.3897ec21fae5.21575.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0421b0459a1f756991e9096e9a3c2ce821a636db440b83873ad27b613c136813
+size 12864

tokenizer.json

@@ -71,7 +71,69 @@
   "pre_tokenizer": {
     "type": "Whitespace"
   },
-  "post_processor": null,
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[EOS]",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[CLS]": {
+        "id": "[CLS]",
+        "ids": [
+          0
+        ],
+        "tokens": [
+          "[CLS]"
+        ]
+      },
+      "[EOS]": {
+        "id": "[EOS]",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "[EOS]"
+        ]
+      }
+    }
+  },
   "decoder": null,
   "model": {
     "type": "BPE",
@@ -106,18 +168,18 @@
       "10": 21,
       "98": 22,
       "11": 23,
-      "12": 24,
-      "97": 25,
-      "13": 26,
-      "96": 27,
+      "97": 24,
+      "12": 25,
+      "96": 26,
+      "13": 27,
       "95": 28,
       "14": 29,
       "94": 30,
       "15": 31,
-      "16": 32,
-      "93": 33,
-      "17": 34,
-      "92": 35,
+      "93": 32,
+      "16": 33,
+      "92": 34,
+      "17": 35,
       "91": 36,
       "18": 37,
       "19": 38,
@@ -130,10 +192,10 @@
       "87": 45,
       "23": 46,
       "86": 47,
-      "24": 48,
-      "85": 49,
-      "84": 50,
-      "25": 51,
+      "85": 48,
+      "24": 49,
+      "25": 50,
+      "84": 51,
       "26": 52,
       "83": 53,
       "27": 54,
@@ -144,18 +206,18 @@
       "1 0",
       "9 8",
       "1 1",
-      "1 2",
       "9 7",
-      "1 3",
+      "1 2",
       "9 6",
+      "1 3",
       "9 5",
       "1 4",
       "9 4",
       "1 5",
-      "1 6",
       "9 3",
-      "1 7",
+      "1 6",
       "9 2",
+      "1 7",
       "9 1",
       "1 8",
       "1 9",
@@ -168,10 +230,10 @@
       "8 7",
       "2 3",
       "8 6",
-      "2 4",
       "8 5",
-      "8 4",
+      "2 4",
       "2 5",
+      "8 4",
       "2 6",
       "8 3",
       "2 7",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6659b0093eeff414bea7b0676fa26b8ced67d1bab20bc510776e16dcea6efb68
+oid sha256:e54a33d2f290f85e42924b5f98306a6bedf48ced4afa93e90600479ea6cfd23f
 size 4920