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: 0.6928
+- Loss: 0.1142
 
 ## Model description
 
@@ -44,46 +44,46 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.3995        | 1.0   | 6    | 2.7654          |
-| 2.3627        | 2.0   | 12   | 2.0026          |
-| 1.8401        | 3.0   | 18   | 1.6902          |
-| 1.662         | 4.0   | 24   | 1.6234          |
-| 1.5803        | 5.0   | 30   | 1.5471          |
-| 1.526         | 6.0   | 36   | 1.5404          |
-| 1.5392        | 7.0   | 42   | 1.5229          |
-| 1.488         | 8.0   | 48   | 1.4944          |
-| 1.492         | 9.0   | 54   | 1.4652          |
-| 1.4448        | 10.0  | 60   | 1.4098          |
-| 1.3673        | 11.0  | 66   | 1.3128          |
-| 1.3264        | 12.0  | 72   | 1.2688          |
-| 1.2517        | 13.0  | 78   | 1.1730          |
-| 1.1956        | 14.0  | 84   | 1.1706          |
-| 1.1611        | 15.0  | 90   | 1.1054          |
-| 1.1071        | 16.0  | 96   | 1.0976          |
-| 1.0902        | 17.0  | 102  | 1.0297          |
-| 1.0608        | 18.0  | 108  | 1.0287          |
-| 1.0572        | 19.0  | 114  | 1.0717          |
-| 1.0308        | 20.0  | 120  | 0.9988          |
-| 0.993         | 21.0  | 126  | 0.9327          |
-| 0.9265        | 22.0  | 132  | 0.9105          |
-| 0.9157        | 23.0  | 138  | 0.8810          |
-| 0.9134        | 24.0  | 144  | 0.9195          |
-| 0.9301        | 25.0  | 150  | 1.0128          |
-| 0.9529        | 26.0  | 156  | 0.9117          |
-| 0.9287        | 27.0  | 162  | 0.9456          |
-| 0.9075        | 28.0  | 168  | 0.8443          |
-| 0.8507        | 29.0  | 174  | 0.8308          |
-| 0.8232        | 30.0  | 180  | 0.7894          |
-| 0.8086        | 31.0  | 186  | 0.7883          |
-| 0.7955        | 32.0  | 192  | 0.7545          |
-| 0.7791        | 33.0  | 198  | 0.7381          |
-| 0.7835        | 34.0  | 204  | 0.7364          |
-| 0.7744        | 35.0  | 210  | 0.7281          |
-| 0.7675        | 36.0  | 216  | 0.7230          |
-| 0.7549        | 37.0  | 222  | 0.7100          |
-| 0.7459        | 38.0  | 228  | 0.6969          |
-| 0.7449        | 39.0  | 234  | 0.6945          |
-| 0.7257        | 40.0  | 240  | 0.6928          |
+| 2.9994        | 1.0   | 6    | 2.3829          |
+| 2.1071        | 2.0   | 12   | 1.8146          |
+| 1.6604        | 3.0   | 18   | 1.4548          |
+| 1.3344        | 4.0   | 24   | 1.2129          |
+| 1.1057        | 5.0   | 30   | 1.1267          |
+| 0.9979        | 6.0   | 36   | 0.9518          |
+| 0.8972        | 7.0   | 42   | 0.8461          |
+| 0.7958        | 8.0   | 48   | 0.7534          |
+| 0.7312        | 9.0   | 54   | 0.7009          |
+| 0.6649        | 10.0  | 60   | 0.6680          |
+| 0.6393        | 11.0  | 66   | 0.7051          |
+| 0.6601        | 12.0  | 72   | 0.6567          |
+| 0.6068        | 13.0  | 78   | 0.5767          |
+| 0.5647        | 14.0  | 84   | 0.5255          |
+| 0.4983        | 15.0  | 90   | 0.4750          |
+| 0.5041        | 16.0  | 96   | 0.4331          |
+| 0.4763        | 17.0  | 102  | 0.4182          |
+| 0.4353        | 18.0  | 108  | 0.3774          |
+| 0.3764        | 19.0  | 114  | 0.3496          |
+| 0.3449        | 20.0  | 120  | 0.3113          |
+| 0.3256        | 21.0  | 126  | 0.2987          |
+| 0.2946        | 22.0  | 132  | 0.2670          |
+| 0.3009        | 23.0  | 138  | 0.2560          |
+| 0.2382        | 24.0  | 144  | 0.2373          |
+| 0.2447        | 25.0  | 150  | 0.2340          |
+| 0.2641        | 26.0  | 156  | 0.3113          |
+| 0.2926        | 27.0  | 162  | 0.1925          |
+| 0.2231        | 28.0  | 168  | 0.1932          |
+| 0.2826        | 29.0  | 174  | 0.1867          |
+| 0.1928        | 30.0  | 180  | 0.1672          |
+| 0.1924        | 31.0  | 186  | 0.1577          |
+| 0.1727        | 32.0  | 192  | 0.1451          |
+| 0.1715        | 33.0  | 198  | 0.1365          |
+| 0.1582        | 34.0  | 204  | 0.1334          |
+| 0.1606        | 35.0  | 210  | 0.1278          |
+| 0.1556        | 36.0  | 216  | 0.1282          |
+| 0.1355        | 37.0  | 222  | 0.1226          |
+| 0.1305        | 38.0  | 228  | 0.1184          |
+| 0.1494        | 39.0  | 234  | 0.1148          |
+| 0.1392        | 40.0  | 240  | 0.1142          |
 
 
 ### Framework versions

config.json

@@ -78,7 +78,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 52
+    "vocab_size": 53
   },
   "decoder_start_token_id": 2,
   "encoder": {
@@ -157,7 +157,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 52
+    "vocab_size": 53
   },
   "eos_token_id": 0,
   "is_encoder_decoder": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a145ff9ebf9cb627a777a9a18ed169d88476f9abf4752cfe35e888b5b69abb3
-size 31205552
+oid sha256:c42cb91277d22ed8d3b996c4a0bcd18d710e0c99e81b92739765eff35e217f21
+size 31207604

runs/Mar04_14-28-09_af6ff0e52cb3/events.out.tfevents.1709562490.af6ff0e52cb3.543.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04f34608326da58f6ac8b8fa6736fb11a04e991f25cd2c75aa3ddb858ffdefc
+size 27997

tokenizer.json

@@ -112,78 +112,79 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "10": 16,
-      "99": 17,
-      "98": 18,
-      "11": 19,
-      "12": 20,
-      "97": 21,
-      "13": 22,
-      "96": 23,
-      "95": 24,
-      "14": 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,
+      "=": 16,
+      "10": 17,
+      "11": 18,
+      "12": 19,
+      "13": 20,
+      "14": 21,
+      "15": 22,
+      "99": 23,
+      "98": 24,
+      "16": 25,
+      "97": 26,
+      "96": 27,
+      "17": 28,
+      "95": 29,
+      "94": 30,
+      "18": 31,
+      "93": 32,
+      "92": 33,
+      "91": 34,
+      "19": 35,
+      "90": 36,
+      "20": 37,
+      "89": 38,
       "21": 39,
-      "22": 40,
-      "87": 41,
-      "23": 42,
+      "88": 40,
+      "22": 41,
+      "87": 42,
       "86": 43,
-      "85": 44,
+      "23": 44,
       "24": 45,
-      "84": 46,
-      "25": 47,
-      "26": 48,
+      "85": 46,
+      "84": 47,
+      "25": 48,
       "83": 49,
-      "27": 50,
-      "82": 51
+      "26": 50,
+      "27": 51,
+      "82": 52
     },
     "merges": [
       "1 0",
-      "9 9",
-      "9 8",
       "1 1",
       "1 2",
-      "9 7",
       "1 3",
-      "9 6",
-      "9 5",
       "1 4",
-      "9 4",
       "1 5",
+      "9 9",
+      "9 8",
       "1 6",
-      "9 3",
-      "9 2",
+      "9 7",
+      "9 6",
       "1 7",
+      "9 5",
+      "9 4",
       "1 8",
+      "9 3",
+      "9 2",
       "9 1",
       "1 9",
       "9 0",
       "2 0",
       "8 9",
-      "8 8",
       "2 1",
+      "8 8",
       "2 2",
       "8 7",
-      "2 3",
       "8 6",
-      "8 5",
+      "2 3",
       "2 4",
+      "8 5",
       "8 4",
       "2 5",
-      "2 6",
       "8 3",
+      "2 6",
       "2 7",
       "8 2"
     ]

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff1c739f49f1d5e41ec51ab373535b8a764a50d8baebabfa83575e1ac23c1259
+oid sha256:73f1fc7c92e5da9ab6501822b5f2d2a56bd159953c98e128e16c9e34ef8bc6a4
 size 5112