End of training

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: Kielak2/calculator_model_test
 tags:
 - generated_from_trainer
 model-index:
@@ -12,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # calculator_model_test
 
-This model is a fine-tuned version of [Kielak2/calculator_model_test](https://huggingface.co/Kielak2/calculator_model_test) on the None dataset.
+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: 0.1439
+- Loss: 0.7602
 
 ## Model description
 
@@ -46,46 +45,46 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.3404        | 1.0   | 41   | 0.9112          |
-| 1.0195        | 2.0   | 82   | 1.0749          |
-| 0.9524        | 3.0   | 123  | 0.9697          |
-| 0.8765        | 4.0   | 164  | 0.7983          |
-| 0.8274        | 5.0   | 205  | 0.9082          |
-| 0.7727        | 6.0   | 246  | 0.7641          |
-| 1.3801        | 7.0   | 287  | 0.7807          |
-| 0.7733        | 8.0   | 328  | 0.8173          |
-| 0.7062        | 9.0   | 369  | 0.6003          |
-| 0.6671        | 10.0  | 410  | 0.7683          |
-| 0.6935        | 11.0  | 451  | 0.6048          |
-| 0.6598        | 12.0  | 492  | 0.6386          |
-| 0.6553        | 13.0  | 533  | 0.5399          |
-| 0.6033        | 14.0  | 574  | 0.5085          |
-| 0.5972        | 15.0  | 615  | 0.5428          |
-| 0.5928        | 16.0  | 656  | 0.5449          |
-| 0.6432        | 17.0  | 697  | 0.5153          |
-| 0.5887        | 18.0  | 738  | 0.4591          |
-| 0.5011        | 19.0  | 779  | 0.4463          |
-| 0.5117        | 20.0  | 820  | 0.4133          |
-| 0.4846        | 21.0  | 861  | 0.5346          |
-| 0.4815        | 22.0  | 902  | 0.3905          |
-| 0.4375        | 23.0  | 943  | 0.3758          |
-| 0.4313        | 24.0  | 984  | 0.3518          |
-| 0.4049        | 25.0  | 1025 | 0.3904          |
-| 0.4028        | 26.0  | 1066 | 0.2871          |
-| 0.3749        | 27.0  | 1107 | 0.3456          |
-| 0.3682        | 28.0  | 1148 | 0.3105          |
-| 0.3442        | 29.0  | 1189 | 0.2684          |
-| 0.3515        | 30.0  | 1230 | 0.2455          |
-| 0.3199        | 31.0  | 1271 | 0.2793          |
-| 0.3196        | 32.0  | 1312 | 0.2236          |
-| 0.3139        | 33.0  | 1353 | 0.2613          |
-| 0.2875        | 34.0  | 1394 | 0.2020          |
-| 0.2639        | 35.0  | 1435 | 0.1783          |
-| 0.261         | 36.0  | 1476 | 0.1987          |
-| 0.2455        | 37.0  | 1517 | 0.1795          |
-| 0.2355        | 38.0  | 1558 | 0.1632          |
-| 0.228         | 39.0  | 1599 | 0.1480          |
-| 0.2177        | 40.0  | 1640 | 0.1439          |
+| 1.6045        | 1.0   | 3    | 1.5511          |
+| 1.3068        | 2.0   | 6    | 1.6045          |
+| 1.4803        | 3.0   | 9    | 1.3825          |
+| 1.3351        | 4.0   | 12   | 1.3222          |
+| 1.259         | 5.0   | 15   | 1.4317          |
+| 1.237         | 6.0   | 18   | 1.3714          |
+| 1.2416        | 7.0   | 21   | 1.3284          |
+| 1.1719        | 8.0   | 24   | 1.2900          |
+| 1.1413        | 9.0   | 27   | 1.2300          |
+| 1.0976        | 10.0  | 30   | 1.2427          |
+| 1.1137        | 11.0  | 33   | 1.1367          |
+| 1.0512        | 12.0  | 36   | 1.0890          |
+| 1.0176        | 13.0  | 39   | 1.1537          |
+| 1.0737        | 14.0  | 42   | 1.1180          |
+| 0.9744        | 15.0  | 45   | 1.0935          |
+| 0.9448        | 16.0  | 48   | 0.9942          |
+| 0.9564        | 17.0  | 51   | 1.0161          |
+| 0.9895        | 18.0  | 54   | 0.9486          |
+| 0.9088        | 19.0  | 57   | 0.9694          |
+| 0.9169        | 20.0  | 60   | 0.9542          |
+| 0.8814        | 21.0  | 63   | 0.9105          |
+| 0.8952        | 22.0  | 66   | 0.9043          |
+| 0.8635        | 23.0  | 69   | 0.8930          |
+| 0.8357        | 24.0  | 72   | 0.9285          |
+| 0.8266        | 25.0  | 75   | 0.8613          |
+| 0.8271        | 26.0  | 78   | 0.9072          |
+| 0.7921        | 27.0  | 81   | 0.8674          |
+| 0.775         | 28.0  | 84   | 0.8476          |
+| 0.7766        | 29.0  | 87   | 0.8600          |
+| 0.7682        | 30.0  | 90   | 0.8438          |
+| 0.7844        | 31.0  | 93   | 0.8022          |
+| 0.7114        | 32.0  | 96   | 0.8131          |
+| 0.7391        | 33.0  | 99   | 0.7957          |
+| 0.7347        | 34.0  | 102  | 0.7810          |
+| 0.7104        | 35.0  | 105  | 0.7740          |
+| 0.7248        | 36.0  | 108  | 0.7665          |
+| 0.7359        | 37.0  | 111  | 0.7819          |
+| 0.7358        | 38.0  | 114  | 0.7668          |
+| 0.7235        | 39.0  | 117  | 0.7601          |
+| 0.7203        | 40.0  | 120  | 0.7602          |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "Kielak2/calculator_model_test",
   "architectures": [
     "EncoderDecoderModel"
   ],
@@ -79,7 +78,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 52
+    "vocab_size": 34
   },
   "decoder_start_token_id": 2,
   "encoder": {
@@ -158,7 +157,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 52
+    "vocab_size": 34
   },
   "eos_token_id": 0,
   "is_encoder_decoder": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97567041561ef6d2029ea413b9bac3f6431f442eba5b41017ba49e30a7c08a5
-size 31205552
+oid sha256:df9c10b98f96c659b466edd2d980791d10d4deb5d08b741932448182b3aeaae4
+size 31168616

runs/Mar04_10-14-36_c60a5c456cbd/events.out.tfevents.1709547276.c60a5c456cbd.796.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd2cced393dacc1aa0050892f55e089c3d88aa323a109fe666c719919ee600f
+size 17063

runs/Mar04_10-14-58_c60a5c456cbd/events.out.tfevents.1709547299.c60a5c456cbd.796.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5dc0289c0f784ce1fc1ec5ee8362c18a41449e9a7c03e46aabac810895d99df
+size 27817

tokenizer.json

@@ -112,80 +112,44 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "99": 16,
-      "10": 17,
+      "10": 16,
+      "99": 17,
       "11": 18,
       "98": 19,
       "12": 20,
       "97": 21,
       "13": 22,
       "96": 23,
-      "95": 24,
-      "14": 25,
-      "94": 26,
-      "15": 27,
-      "93": 28,
-      "16": 29,
-      "92": 30,
-      "17": 31,
-      "91": 32,
-      "18": 33,
-      "19": 34,
-      "90": 35,
-      "89": 36,
-      "20": 37,
-      "88": 38,
-      "21": 39,
-      "22": 40,
-      "87": 41,
-      "23": 42,
-      "86": 43,
-      "24": 44,
-      "85": 45,
-      "25": 46,
-      "84": 47,
-      "83": 48,
-      "26": 49,
-      "27": 50,
-      "82": 51
+      "14": 24,
+      "95": 25,
+      "15": 26,
+      "94": 27,
+      "16": 28,
+      "93": 29,
+      "17": 30,
+      "92": 31,
+      "18": 32,
+      "91": 33
     },
     "merges": [
-      "9 9",
       "1 0",
+      "9 9",
       "1 1",
       "9 8",
       "1 2",
       "9 7",
       "1 3",
       "9 6",
-      "9 5",
       "1 4",
-      "9 4",
+      "9 5",
       "1 5",
-      "9 3",
+      "9 4",
       "1 6",
-      "9 2",
+      "9 3",
       "1 7",
-      "9 1",
+      "9 2",
       "1 8",
-      "1 9",
-      "9 0",
-      "8 9",
-      "2 0",
-      "8 8",
-      "2 1",
-      "2 2",
-      "8 7",
-      "2 3",
-      "8 6",
-      "2 4",
-      "8 5",
-      "2 5",
-      "8 4",
-      "8 3",
-      "2 6",
-      "2 7",
-      "8 2"
+      "9 1"
     ]
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e59a4b8d41f27a7dcf7361beba8089142b2dac8dc20d9a658a018a6d96e2820
+oid sha256:f3c4bf818af65907f79e24432ebc4058fd991b8135d7bde889b44d524743e7d0
 size 5112