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: 0.5850
+- Loss: 0.4351
 
 ## Model description
 
@@ -38,62 +38,32 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 50
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.396         | 1.0   | 6    | 2.7406          |
-| 2.3939        | 2.0   | 12   | 1.9948          |
-| 1.7939        | 3.0   | 18   | 1.6558          |
-| 1.5985        | 4.0   | 24   | 1.6015          |
-| 1.6024        | 5.0   | 30   | 1.5540          |
-| 1.5383        | 6.0   | 36   | 1.5356          |
-| 1.4729        | 7.0   | 42   | 1.5437          |
-| 1.4981        | 8.0   | 48   | 1.4425          |
-| 1.3622        | 9.0   | 54   | 1.4418          |
-| 1.3585        | 10.0  | 60   | 1.3501          |
-| 1.2883        | 11.0  | 66   | 1.2932          |
-| 1.2361        | 12.0  | 72   | 1.3210          |
-| 1.2274        | 13.0  | 78   | 1.2883          |
-| 1.2667        | 14.0  | 84   | 1.2169          |
-| 1.1679        | 15.0  | 90   | 1.1638          |
-| 1.1237        | 16.0  | 96   | 1.1617          |
-| 1.144         | 17.0  | 102  | 1.0919          |
-| 1.0771        | 18.0  | 108  | 1.0928          |
-| 1.059         | 19.0  | 114  | 1.0184          |
-| 1.0024        | 20.0  | 120  | 0.9676          |
-| 0.9949        | 21.0  | 126  | 0.9555          |
-| 0.986         | 22.0  | 132  | 1.0286          |
-| 1.0278        | 23.0  | 138  | 0.9337          |
-| 0.9413        | 24.0  | 144  | 0.9162          |
-| 0.912         | 25.0  | 150  | 0.9396          |
-| 0.9621        | 26.0  | 156  | 0.8786          |
-| 0.9102        | 27.0  | 162  | 0.8947          |
-| 0.9384        | 28.0  | 168  | 0.8820          |
-| 0.868         | 29.0  | 174  | 0.8468          |
-| 0.8512        | 30.0  | 180  | 0.8478          |
-| 0.8302        | 31.0  | 186  | 0.8099          |
-| 0.8327        | 32.0  | 192  | 0.7622          |
-| 0.8193        | 33.0  | 198  | 0.7596          |
-| 0.7834        | 34.0  | 204  | 0.7329          |
-| 0.7608        | 35.0  | 210  | 0.7229          |
-| 0.7686        | 36.0  | 216  | 0.7257          |
-| 0.7262        | 37.0  | 222  | 0.6940          |
-| 0.7342        | 38.0  | 228  | 0.7117          |
-| 0.7209        | 39.0  | 234  | 0.6646          |
-| 0.7099        | 40.0  | 240  | 0.6530          |
-| 0.6908        | 41.0  | 246  | 0.6397          |
-| 0.6895        | 42.0  | 252  | 0.6356          |
-| 0.6761        | 43.0  | 258  | 0.6202          |
-| 0.668         | 44.0  | 264  | 0.6174          |
-| 0.6735        | 45.0  | 270  | 0.6074          |
-| 0.6502        | 46.0  | 276  | 0.6019          |
-| 0.6427        | 47.0  | 282  | 0.5953          |
-| 0.6326        | 48.0  | 288  | 0.5904          |
-| 0.6467        | 49.0  | 294  | 0.5872          |
-| 0.6307        | 50.0  | 300  | 0.5850          |
+| 3.0154        | 1.0   | 6    | 2.2475          |
+| 2.0355        | 2.0   | 12   | 1.7612          |
+| 1.6034        | 3.0   | 18   | 1.3483          |
+| 1.2488        | 4.0   | 24   | 1.1102          |
+| 1.0428        | 5.0   | 30   | 0.9643          |
+| 0.9306        | 6.0   | 36   | 0.8449          |
+| 0.8076        | 7.0   | 42   | 0.7526          |
+| 0.7471        | 8.0   | 48   | 0.6843          |
+| 0.6988        | 9.0   | 54   | 0.6786          |
+| 0.6455        | 10.0  | 60   | 0.6155          |
+| 0.6157        | 11.0  | 66   | 0.5713          |
+| 0.5822        | 12.0  | 72   | 0.5486          |
+| 0.5499        | 13.0  | 78   | 0.5163          |
+| 0.526         | 14.0  | 84   | 0.4938          |
+| 0.5133        | 15.0  | 90   | 0.4823          |
+| 0.4917        | 16.0  | 96   | 0.4683          |
+| 0.4792        | 17.0  | 102  | 0.4520          |
+| 0.4677        | 18.0  | 108  | 0.4449          |
+| 0.4616        | 19.0  | 114  | 0.4378          |
+| 0.4502        | 20.0  | 120  | 0.4351          |
 
 
 ### 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:a6dd0c10a93bc861dfdb78a028c4f50ca6a5ec612bb363bbe7288196804c2809
-size 31205552
+oid sha256:4fa2da13138b531d55f6ba8798759b13e7c681b3e218c0d889210907f8945795
+size 31207604

runs/Feb28_20-27-18_3897ec21fae5/events.out.tfevents.1709152038.3897ec21fae5.112417.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c6d204f75edfc019062f526d5d9b75566f6fe45ea229d24117376f6a7243b0
+size 17089

tokenizer.json

@@ -112,78 +112,79 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "10": 16,
+      "=": 16,
       "99": 17,
-      "11": 18,
+      "10": 18,
       "98": 19,
-      "12": 20,
+      "11": 20,
       "97": 21,
-      "13": 22,
+      "12": 22,
       "96": 23,
-      "14": 24,
+      "13": 24,
       "95": 25,
-      "94": 26,
-      "15": 27,
-      "16": 28,
+      "14": 26,
+      "94": 27,
+      "15": 28,
       "93": 29,
-      "17": 30,
-      "92": 31,
-      "91": 32,
+      "16": 30,
+      "17": 31,
+      "92": 32,
       "18": 33,
-      "19": 34,
+      "91": 34,
       "90": 35,
-      "20": 36,
-      "89": 37,
-      "21": 38,
-      "88": 39,
-      "87": 40,
-      "22": 41,
-      "86": 42,
+      "19": 36,
+      "20": 37,
+      "89": 38,
+      "21": 39,
+      "88": 40,
+      "87": 41,
+      "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",
       "9 9",
-      "1 1",
+      "1 0",
       "9 8",
-      "1 2",
+      "1 1",
       "9 7",
-      "1 3",
+      "1 2",
       "9 6",
-      "1 4",
+      "1 3",
       "9 5",
+      "1 4",
       "9 4",
       "1 5",
-      "1 6",
       "9 3",
+      "1 6",
       "1 7",
       "9 2",
-      "9 1",
       "1 8",
-      "1 9",
+      "9 1",
       "9 0",
+      "1 9",
       "2 0",
       "8 9",
       "2 1",
       "8 8",
       "8 7",
       "2 2",
-      "8 6",
       "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 sha256:4842f4a0fd629ccc59cab7f2313be44d4264afb1d3e03281108215f6061469f3
+oid sha256:0840d9a1587d77d590c2fbc24bb261d94dac38000a3cf8827c725907f177e98c
 size 4920