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: 0.9621
+- Loss: 0.0914
 
 ## Model description
 
@@ -44,46 +44,46 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.3921        | 1.0   | 6    | 2.7637          |
-| 2.386         | 2.0   | 12   | 1.9662          |
-| 1.806         | 3.0   | 18   | 1.6665          |
-| 1.6316        | 4.0   | 24   | 1.6027          |
-| 1.5599        | 5.0   | 30   | 1.5819          |
-| 1.545         | 6.0   | 36   | 1.5583          |
-| 1.5233        | 7.0   | 42   | 1.5560          |
-| 1.5514        | 8.0   | 48   | 1.5608          |
-| 1.52          | 9.0   | 54   | 1.5412          |
-| 1.5306        | 10.0  | 60   | 1.5668          |
-| 1.5282        | 11.0  | 66   | 1.5833          |
-| 1.5391        | 12.0  | 72   | 1.5328          |
-| 1.5006        | 13.0  | 78   | 1.5128          |
-| 1.512         | 14.0  | 84   | 1.5062          |
-| 1.4894        | 15.0  | 90   | 1.5007          |
-| 1.4774        | 16.0  | 96   | 1.4810          |
-| 1.4577        | 17.0  | 102  | 1.4795          |
-| 1.4376        | 18.0  | 108  | 1.4520          |
-| 1.4544        | 19.0  | 114  | 1.4020          |
-| 1.414         | 20.0  | 120  | 1.3980          |
-| 1.387         | 21.0  | 126  | 1.3803          |
-| 1.3705        | 22.0  | 132  | 1.3771          |
-| 1.3678        | 23.0  | 138  | 1.4197          |
-| 1.399         | 24.0  | 144  | 1.3305          |
-| 1.3433        | 25.0  | 150  | 1.3018          |
-| 1.2802        | 26.0  | 156  | 1.3064          |
-| 1.2539        | 27.0  | 162  | 1.2275          |
-| 1.226         | 28.0  | 168  | 1.1709          |
-| 1.1791        | 29.0  | 174  | 1.1317          |
-| 1.1483        | 30.0  | 180  | 1.1103          |
-| 1.1277        | 31.0  | 186  | 1.1094          |
-| 1.131         | 32.0  | 192  | 1.0660          |
-| 1.0806        | 33.0  | 198  | 1.0386          |
-| 1.0699        | 34.0  | 204  | 1.0208          |
-| 1.0642        | 35.0  | 210  | 0.9989          |
-| 1.0459        | 36.0  | 216  | 0.9866          |
-| 1.0318        | 37.0  | 222  | 0.9810          |
-| 1.0269        | 38.0  | 228  | 0.9739          |
-| 1.0379        | 39.0  | 234  | 0.9649          |
-| 1.0051        | 40.0  | 240  | 0.9621          |
+| 2.9231        | 1.0   | 6    | 2.2571          |
+| 2.0141        | 2.0   | 12   | 1.6996          |
+| 1.5309        | 3.0   | 18   | 1.2998          |
+| 1.1976        | 4.0   | 24   | 1.0513          |
+| 1.0164        | 5.0   | 30   | 0.9962          |
+| 0.9314        | 6.0   | 36   | 0.8360          |
+| 0.8189        | 7.0   | 42   | 0.7625          |
+| 0.7377        | 8.0   | 48   | 0.6906          |
+| 0.6797        | 9.0   | 54   | 0.6286          |
+| 0.6326        | 10.0  | 60   | 0.6023          |
+| 0.6027        | 11.0  | 66   | 0.5696          |
+| 0.5668        | 12.0  | 72   | 0.5291          |
+| 0.5397        | 13.0  | 78   | 0.5183          |
+| 0.5151        | 14.0  | 84   | 0.4830          |
+| 0.4827        | 15.0  | 90   | 0.4806          |
+| 0.471         | 16.0  | 96   | 0.4802          |
+| 0.472         | 17.0  | 102  | 0.4500          |
+| 0.4374        | 18.0  | 108  | 0.4284          |
+| 0.4336        | 19.0  | 114  | 0.3807          |
+| 0.3985        | 20.0  | 120  | 0.3672          |
+| 0.38          | 21.0  | 126  | 0.3423          |
+| 0.3577        | 22.0  | 132  | 0.3290          |
+| 0.3397        | 23.0  | 138  | 0.2871          |
+| 0.3092        | 24.0  | 144  | 0.2936          |
+| 0.3086        | 25.0  | 150  | 0.2556          |
+| 0.2831        | 26.0  | 156  | 0.2386          |
+| 0.2589        | 27.0  | 162  | 0.2183          |
+| 0.2458        | 28.0  | 168  | 0.2022          |
+| 0.2312        | 29.0  | 174  | 0.1880          |
+| 0.2213        | 30.0  | 180  | 0.1704          |
+| 0.2023        | 31.0  | 186  | 0.1577          |
+| 0.1948        | 32.0  | 192  | 0.1401          |
+| 0.1776        | 33.0  | 198  | 0.1287          |
+| 0.1645        | 34.0  | 204  | 0.1158          |
+| 0.1569        | 35.0  | 210  | 0.1128          |
+| 0.1495        | 36.0  | 216  | 0.1032          |
+| 0.1435        | 37.0  | 222  | 0.0988          |
+| 0.1364        | 38.0  | 228  | 0.0972          |
+| 0.138         | 39.0  | 234  | 0.0930          |
+| 0.1294        | 40.0  | 240  | 0.0914          |
 
 
 ### 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 sha256:9970368facf1451f616ebc9137d52735022fab384de4d6f1270cbef3077d3c15
-size 31205552
+oid sha256:bf444c542344de4bd3ed82e5f1b260d744fe2e6768426188c5c9199301fd7001
+size 31207604

runs/Mar04_14-30-34_7c339ad63e68/events.out.tfevents.1709562635.7c339ad63e68.836.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d644bc3a8531102a57bcad3e1f47daa10b8a68fc8e83ad81efed5e41f41a782
+size 27997

tokenizer.json

@@ -112,54 +112,55 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "99": 16,
+      "=": 16,
       "10": 17,
-      "11": 18,
+      "99": 18,
       "98": 19,
-      "12": 20,
-      "96": 21,
-      "97": 22,
-      "13": 23,
-      "14": 24,
+      "11": 20,
+      "97": 21,
+      "12": 22,
+      "96": 23,
+      "13": 24,
       "95": 25,
-      "94": 26,
-      "15": 27,
-      "93": 28,
-      "16": 29,
-      "17": 30,
-      "92": 31,
-      "18": 32,
-      "91": 33,
-      "90": 34,
-      "19": 35,
-      "20": 36,
-      "89": 37,
-      "21": 38,
-      "88": 39,
-      "22": 40,
+      "14": 26,
+      "94": 27,
+      "15": 28,
+      "93": 29,
+      "16": 30,
+      "17": 31,
+      "92": 32,
+      "18": 33,
+      "91": 34,
+      "90": 35,
+      "19": 36,
+      "20": 37,
+      "89": 38,
+      "21": 39,
+      "88": 40,
       "87": 41,
-      "23": 42,
-      "86": 43,
-      "24": 44,
+      "22": 42,
+      "23": 43,
+      "86": 44,
       "85": 45,
-      "84": 46,
+      "24": 46,
       "25": 47,
-      "26": 48,
+      "84": 48,
       "83": 49,
-      "27": 50,
-      "82": 51
+      "26": 50,
+      "27": 51,
+      "82": 52
     },
     "merges": [
-      "9 9",
       "1 0",
-      "1 1",
+      "9 9",
       "9 8",
+      "1 1",
+      "9 7",
       "1 2",
       "9 6",
-      "9 7",
       "1 3",
-      "1 4",
       "9 5",
+      "1 4",
       "9 4",
       "1 5",
       "9 3",
@@ -174,16 +175,16 @@
       "8 9",
       "2 1",
       "8 8",
-      "2 2",
       "8 7",
+      "2 2",
       "2 3",
       "8 6",
-      "2 4",
       "8 5",
-      "8 4",
+      "2 4",
       "2 5",
-      "2 6",
+      "8 4",
       "8 3",
+      "2 6",
       "2 7",
       "8 2"
     ]

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6af906f97e4ae573d4411e754b32e559a3816de73cd5ad98b02aa2d2d00fbb
+oid sha256:7a8d5009d93cc0b28f0827c6753d8c862fb9c99bee9458d4004349b229359acd
 size 5112