End of training

README.md

@@ -14,7 +14,7 @@ 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: 0.5500
+- Loss: 0.6688
 
 ## Model description
 
@@ -45,46 +45,46 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.4851        | 1.0   | 5    | 2.9408          |
-| 2.5835        | 2.0   | 10   | 2.1787          |
-| 1.9668        | 3.0   | 15   | 1.7919          |
-| 1.7209        | 4.0   | 20   | 1.6411          |
-| 1.5973        | 5.0   | 25   | 1.5588          |
-| 1.5383        | 6.0   | 30   | 1.4900          |
-| 1.4628        | 7.0   | 35   | 1.4556          |
-| 1.4427        | 8.0   | 40   | 1.4175          |
-| 1.3979        | 9.0   | 45   | 1.3629          |
-| 1.3421        | 10.0  | 50   | 1.2893          |
-| 1.2395        | 11.0  | 55   | 1.1524          |
-| 1.1789        | 12.0  | 60   | 1.1692          |
-| 1.1266        | 13.0  | 65   | 1.0435          |
-| 1.0469        | 14.0  | 70   | 0.9994          |
-| 1.0149        | 15.0  | 75   | 1.0576          |
-| 1.0010        | 16.0  | 80   | 0.9336          |
-| 0.9451        | 17.0  | 85   | 0.8939          |
-| 0.9079        | 18.0  | 90   | 0.8588          |
-| 0.8922        | 19.0  | 95   | 0.8718          |
-| 0.8619        | 20.0  | 100  | 0.8359          |
-| 0.8458        | 21.0  | 105  | 0.7859          |
-| 0.8284        | 22.0  | 110  | 0.7901          |
-| 0.8187        | 23.0  | 115  | 0.7792          |
-| 0.7879        | 24.0  | 120  | 0.7507          |
-| 0.7589        | 25.0  | 125  | 0.7389          |
-| 0.7497        | 26.0  | 130  | 0.7087          |
-| 0.7263        | 27.0  | 135  | 0.6955          |
-| 0.7082        | 28.0  | 140  | 0.6706          |
-| 0.6982        | 29.0  | 145  | 0.6740          |
-| 0.6815        | 30.0  | 150  | 0.6415          |
-| 0.6655        | 31.0  | 155  | 0.6237          |
-| 0.6555        | 32.0  | 160  | 0.6191          |
-| 0.6435        | 33.0  | 165  | 0.6018          |
-| 0.6303        | 34.0  | 170  | 0.5913          |
-| 0.6235        | 35.0  | 175  | 0.5822          |
-| 0.6098        | 36.0  | 180  | 0.5722          |
-| 0.6044        | 37.0  | 185  | 0.5670          |
-| 0.5995        | 38.0  | 190  | 0.5563          |
-| 0.5915        | 39.0  | 195  | 0.5555          |
-| 0.5864        | 40.0  | 200  | 0.5500          |
+| 3.4045        | 1.0   | 6    | 2.7587          |
+| 2.3917        | 2.0   | 12   | 1.9900          |
+| 1.8734        | 3.0   | 18   | 1.6958          |
+| 1.6324        | 4.0   | 24   | 1.6081          |
+| 1.5676        | 5.0   | 30   | 1.5619          |
+| 1.5436        | 6.0   | 36   | 1.6197          |
+| 1.5139        | 7.0   | 42   | 1.4991          |
+| 1.4614        | 8.0   | 48   | 1.4779          |
+| 1.4407        | 9.0   | 54   | 1.4234          |
+| 1.3644        | 10.0  | 60   | 1.3460          |
+| 1.3096        | 11.0  | 66   | 1.3823          |
+| 1.2634        | 12.0  | 72   | 1.2711          |
+| 1.1912        | 13.0  | 78   | 1.2382          |
+| 1.1856        | 14.0  | 84   | 1.1337          |
+| 1.1019        | 15.0  | 90   | 1.2100          |
+| 1.1441        | 16.0  | 96   | 1.1382          |
+| 1.0611        | 17.0  | 102  | 1.0282          |
+| 0.9967        | 18.0  | 108  | 0.9920          |
+| 0.9765        | 19.0  | 114  | 0.9946          |
+| 0.9517        | 20.0  | 120  | 0.9478          |
+| 0.9374        | 21.0  | 126  | 0.9441          |
+| 0.8931        | 22.0  | 132  | 0.9748          |
+| 0.8756        | 23.0  | 138  | 0.8511          |
+| 0.8523        | 24.0  | 144  | 0.8759          |
+| 0.8757        | 25.0  | 150  | 0.8253          |
+| 0.8209        | 26.0  | 156  | 0.8182          |
+| 0.8190        | 27.0  | 162  | 0.7820          |
+| 0.7795        | 28.0  | 168  | 0.7740          |
+| 0.8097        | 29.0  | 174  | 0.7571          |
+| 0.7626        | 30.0  | 180  | 0.7584          |
+| 0.7491        | 31.0  | 186  | 0.7444          |
+| 0.7320        | 32.0  | 192  | 0.7177          |
+| 0.7235        | 33.0  | 198  | 0.7124          |
+| 0.7145        | 34.0  | 204  | 0.7032          |
+| 0.7085        | 35.0  | 210  | 0.6888          |
+| 0.7138        | 36.0  | 216  | 0.6866          |
+| 0.6910        | 37.0  | 222  | 0.6789          |
+| 0.6801        | 38.0  | 228  | 0.6731          |
+| 0.6819        | 39.0  | 234  | 0.6715          |
+| 0.6750        | 40.0  | 240  | 0.6688          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953334a2882f1b73612ab6395f352673190781e4f503bb027afc517c6ee080c8
+oid sha256:b8b8bb882d932f050659ba49f3b6b56b5605ef404cb44129b57bd382a88094cb
 size 31205552

tokenizer.json

@@ -113,63 +113,59 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "10": 16,
-      "99": 17,
+      "99": 16,
+      "10": 17,
       "11": 18,
       "98": 19,
-      "97": 20,
-      "12": 21,
-      "96": 22,
-      "13": 23,
-      "95": 24,
-      "14": 25,
-      "15": 26,
-      "94": 27,
-      "93": 28,
-      "16": 29,
-      "17": 30,
-      "92": 31,
+      "12": 20,
+      "97": 21,
+      "13": 22,
+      "96": 23,
+      "14": 24,
+      "95": 25,
+      "94": 26,
+      "15": 27,
+      "16": 28,
+      "93": 29,
+      "92": 30,
+      "17": 31,
       "18": 32,
       "91": 33,
       "19": 34,
       "90": 35,
-      "20": 36,
-      "89": 37,
-      "88": 38,
-      "21": 39,
-      "22": 40,
-      "87": 41,
-      "86": 42,
-      "23": 43,
+      "89": 36,
+      "20": 37,
+      "21": 38,
+      "88": 39,
+      "87": 40,
+      "22": 41,
+      "23": 42,
+      "86": 43,
       "24": 44,
-      "25": 45,
-      "84": 46,
-      "85": 47,
+      "85": 45,
+      "25": 46,
+      "84": 47,
       "26": 48,
       "83": 49,
       "27": 50,
       "82": 51
     },
     "merges": [
-      [
-        "1",
-        "0"
-      ],
       [
         "9",
         "9"
       ],
       [
         "1",
-        "1"
+        "0"
       ],
       [
-        "9",
-        "8"
+        "1",
+        "1"
       ],
       [
         "9",
-        "7"
+        "8"
       ],
       [
         "1",
@@ -177,7 +173,7 @@
       ],
       [
         "9",
-        "6"
+        "7"
       ],
       [
         "1",
@@ -185,14 +181,14 @@
       ],
       [
         "9",
-        "5"
+        "6"
       ],
       [
         "1",
         "4"
       ],
       [
-        "1",
+        "9",
         "5"
       ],
       [
@@ -200,21 +196,25 @@
         "4"
       ],
       [
-        "9",
-        "3"
+        "1",
+        "5"
       ],
       [
         "1",
         "6"
       ],
       [
-        "1",
-        "7"
+        "9",
+        "3"
       ],
       [
         "9",
         "2"
       ],
+      [
+        "1",
+        "7"
+      ],
       [
         "1",
         "8"
@@ -231,29 +231,33 @@
         "9",
         "0"
       ],
+      [
+        "8",
+        "9"
+      ],
       [
         "2",
         "0"
       ],
       [
-        "8",
-        "9"
+        "2",
+        "1"
       ],
       [
         "8",
         "8"
       ],
       [
-        "2",
-        "1"
+        "8",
+        "7"
       ],
       [
         "2",
         "2"
       ],
       [
-        "8",
-        "7"
+        "2",
+        "3"
       ],
       [
         "8",
@@ -261,11 +265,11 @@
       ],
       [
         "2",
-        "3"
+        "4"
       ],
       [
-        "2",
-        "4"
+        "8",
+        "5"
       ],
       [
         "2",
@@ -275,10 +279,6 @@
         "8",
         "4"
       ],
-      [
-        "8",
-        "5"
-      ],
       [
         "2",
         "6"