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: 0.7556
+- Loss: 2.9524
 
 ## Model description
 
@@ -32,7 +32,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
+- learning_rate: 0.01
 - train_batch_size: 512
 - eval_batch_size: 512
 - seed: 42
@@ -44,46 +44,46 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.1456        | 1.0   | 6    | 2.5517          |
-| 2.1398        | 2.0   | 12   | 1.8461          |
-| 1.7232        | 3.0   | 18   | 1.6222          |
-| 1.6435        | 4.0   | 24   | 1.6869          |
-| 1.6417        | 5.0   | 30   | 1.5262          |
-| 1.4634        | 6.0   | 36   | 1.4824          |
-| 1.4507        | 7.0   | 42   | 1.8991          |
-| 1.54          | 8.0   | 48   | 1.4370          |
-| 1.483         | 9.0   | 54   | 1.4203          |
-| 1.4086        | 10.0  | 60   | 1.4349          |
-| 1.4063        | 11.0  | 66   | 1.5677          |
-| 1.4235        | 12.0  | 72   | 1.3646          |
-| 1.2839        | 13.0  | 78   | 1.2074          |
-| 1.2127        | 14.0  | 84   | 1.2050          |
-| 1.1447        | 15.0  | 90   | 1.1797          |
-| 1.1515        | 16.0  | 96   | 1.1440          |
-| 1.1138        | 17.0  | 102  | 1.1293          |
-| 1.07          | 18.0  | 108  | 1.1061          |
-| 1.0295        | 19.0  | 114  | 1.1572          |
-| 1.1086        | 20.0  | 120  | 1.3547          |
-| 1.1835        | 21.0  | 126  | 1.1306          |
-| 1.0968        | 22.0  | 132  | 1.0152          |
-| 1.0012        | 23.0  | 138  | 1.0467          |
-| 1.0088        | 24.0  | 144  | 0.9831          |
-| 0.9616        | 25.0  | 150  | 0.9141          |
-| 0.9385        | 26.0  | 156  | 0.9093          |
-| 0.8887        | 27.0  | 162  | 0.9188          |
-| 0.9549        | 28.0  | 168  | 0.9369          |
-| 0.8972        | 29.0  | 174  | 0.8518          |
-| 0.8973        | 30.0  | 180  | 0.8424          |
-| 0.8419        | 31.0  | 186  | 0.8858          |
-| 0.8887        | 32.0  | 192  | 0.8781          |
-| 0.8509        | 33.0  | 198  | 0.8372          |
-| 0.8473        | 34.0  | 204  | 0.8021          |
-| 0.8361        | 35.0  | 210  | 0.7912          |
-| 0.8037        | 36.0  | 216  | 0.7771          |
-| 0.7776        | 37.0  | 222  | 0.7742          |
-| 0.7767        | 38.0  | 228  | 0.7602          |
-| 0.795         | 39.0  | 234  | 0.7568          |
-| 0.8284        | 40.0  | 240  | 0.7556          |
+| 3.6485        | 1.0   | 6    | 3.2312          |
+| 3.1316        | 2.0   | 12   | 2.9996          |
+| 3.037         | 3.0   | 18   | 3.0512          |
+| 3.0193        | 4.0   | 24   | 3.0006          |
+| 2.9967        | 5.0   | 30   | 2.9620          |
+| 2.9847        | 6.0   | 36   | 2.9710          |
+| 2.9765        | 7.0   | 42   | 2.9646          |
+| 2.9729        | 8.0   | 48   | 2.9598          |
+| 2.9755        | 9.0   | 54   | 2.9601          |
+| 2.9644        | 10.0  | 60   | 2.9621          |
+| 2.967         | 11.0  | 66   | 2.9609          |
+| 2.9713        | 12.0  | 72   | 2.9563          |
+| 2.9704        | 13.0  | 78   | 2.9534          |
+| 2.9708        | 14.0  | 84   | 2.9552          |
+| 2.9582        | 15.0  | 90   | 2.9530          |
+| 2.9729        | 16.0  | 96   | 2.9547          |
+| 2.9628        | 17.0  | 102  | 2.9576          |
+| 2.9621        | 18.0  | 108  | 2.9559          |
+| 2.968         | 19.0  | 114  | 2.9524          |
+| 2.9663        | 20.0  | 120  | 2.9556          |
+| 2.9609        | 21.0  | 126  | 2.9534          |
+| 2.9661        | 22.0  | 132  | 2.9523          |
+| 2.9563        | 23.0  | 138  | 2.9593          |
+| 2.9656        | 24.0  | 144  | 2.9551          |
+| 2.9604        | 25.0  | 150  | 2.9534          |
+| 2.9694        | 26.0  | 156  | 2.9525          |
+| 2.9636        | 27.0  | 162  | 2.9522          |
+| 2.9561        | 28.0  | 168  | 2.9535          |
+| 2.9762        | 29.0  | 174  | 2.9548          |
+| 2.962         | 30.0  | 180  | 2.9530          |
+| 2.9537        | 31.0  | 186  | 2.9501          |
+| 2.9592        | 32.0  | 192  | 2.9513          |
+| 2.9695        | 33.0  | 198  | 2.9519          |
+| 2.9664        | 34.0  | 204  | 2.9527          |
+| 2.9594        | 35.0  | 210  | 2.9532          |
+| 2.9582        | 36.0  | 216  | 2.9529          |
+| 2.9718        | 37.0  | 222  | 2.9533          |
+| 2.9563        | 38.0  | 228  | 2.9530          |
+| 2.9599        | 39.0  | 234  | 2.9525          |
+| 2.9615        | 40.0  | 240  | 2.9524          |
 
 
 ### 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:aac6b2a604579ceb3da782ae54c341d32a629e1cd50b9f20eea47ba3eae91145
-size 31205552
+oid sha256:4624a45de91282f047b17d2f4fcf3b7d651cffacd9f833701f580bed957b5aab
+size 31207604

runs/Mar04_10-15-03_c80d5fea20ad/events.out.tfevents.1709547304.c80d5fea20ad.139.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b38305991b5bd12eded201b427f7af93f9906f6d106b2dd283b10d0342c3e06
+size 15303

runs/Mar04_10-22-11_c80d5fea20ad/events.out.tfevents.1709547732.c80d5fea20ad.139.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0150a45616450d7d666e8bb427712c0d4eea0bae3fc388650bfed1a2f86dfe5e
+size 27996

tokenizer.json

@@ -112,42 +112,43 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "10": 16,
-      "99": 17,
-      "98": 18,
-      "11": 19,
-      "97": 20,
-      "12": 21,
-      "13": 22,
+      "=": 16,
+      "10": 17,
+      "99": 18,
+      "98": 19,
+      "11": 20,
+      "97": 21,
+      "12": 22,
       "96": 23,
-      "95": 24,
-      "14": 25,
-      "94": 26,
-      "15": 27,
-      "93": 28,
-      "16": 29,
-      "92": 30,
+      "13": 24,
+      "95": 25,
+      "14": 26,
+      "94": 27,
+      "15": 28,
+      "93": 29,
+      "16": 30,
       "17": 31,
-      "91": 32,
+      "92": 32,
       "18": 33,
-      "90": 34,
-      "19": 35,
-      "20": 36,
-      "89": 37,
-      "88": 38,
+      "91": 34,
+      "90": 35,
+      "19": 36,
+      "20": 37,
+      "89": 38,
       "21": 39,
-      "22": 40,
+      "88": 40,
       "87": 41,
-      "86": 42,
+      "22": 42,
       "23": 43,
-      "24": 44,
+      "86": 44,
       "85": 45,
-      "25": 46,
-      "84": 47,
-      "26": 48,
+      "24": 46,
+      "25": 47,
+      "84": 48,
       "83": 49,
-      "27": 50,
-      "82": 51
+      "26": 50,
+      "27": 51,
+      "82": 52
     },
     "merges": [
       "1 0",
@@ -156,34 +157,34 @@
       "1 1",
       "9 7",
       "1 2",
-      "1 3",
       "9 6",
+      "1 3",
       "9 5",
       "1 4",
       "9 4",
       "1 5",
       "9 3",
       "1 6",
-      "9 2",
       "1 7",
-      "9 1",
+      "9 2",
       "1 8",
+      "9 1",
       "9 0",
       "1 9",
       "2 0",
       "8 9",
-      "8 8",
       "2 1",
-      "2 2",
+      "8 8",
       "8 7",
-      "8 6",
+      "2 2",
       "2 3",
-      "2 4",
+      "8 6",
       "8 5",
+      "2 4",
       "2 5",
       "8 4",
-      "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 sha256:018a1b683f3740f2832794a3b95bb71f04f3c029f972d9abc1dca51f7ba897d0
+oid sha256:c442b4abff85481bb4365240162bad56919332b7b6f174a7892012f02caf99ce
 size 5112