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: 0.1167
+- Loss: 0.2167
 
 ## Model description
 
@@ -44,51 +44,51 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.9273        | 1.0   | 6    | 2.2511          |
-| 1.9997        | 2.0   | 12   | 1.7899          |
-| 1.5879        | 3.0   | 18   | 1.4061          |
-| 1.2647        | 4.0   | 24   | 1.1517          |
-| 1.0856        | 5.0   | 30   | 0.9960          |
-| 0.9355        | 6.0   | 36   | 0.8942          |
-| 0.8536        | 7.0   | 42   | 0.8276          |
-| 0.7951        | 8.0   | 48   | 0.7920          |
-| 0.7389        | 9.0   | 54   | 0.6889          |
-| 0.6781        | 10.0  | 60   | 0.6773          |
-| 0.652         | 11.0  | 66   | 0.6381          |
-| 0.6175        | 12.0  | 72   | 0.6497          |
-| 0.6544        | 13.0  | 78   | 0.6204          |
-| 0.6023        | 14.0  | 84   | 0.6196          |
-| 0.5674        | 15.0  | 90   | 0.5411          |
-| 0.5383        | 16.0  | 96   | 0.5058          |
-| 0.5099        | 17.0  | 102  | 0.4813          |
-| 0.479         | 18.0  | 108  | 0.4456          |
-| 0.4579        | 19.0  | 114  | 0.4139          |
-| 0.4268        | 20.0  | 120  | 0.4113          |
-| 0.4266        | 21.0  | 126  | 0.3853          |
-| 0.3894        | 22.0  | 132  | 0.3489          |
-| 0.371         | 23.0  | 138  | 0.3318          |
-| 0.3349        | 24.0  | 144  | 0.2997          |
-| 0.3145        | 25.0  | 150  | 0.2812          |
-| 0.2893        | 26.0  | 156  | 0.2696          |
-| 0.2861        | 27.0  | 162  | 0.2355          |
-| 0.2639        | 28.0  | 168  | 0.2197          |
-| 0.2356        | 29.0  | 174  | 0.2040          |
-| 0.2205        | 30.0  | 180  | 0.1951          |
-| 0.2146        | 31.0  | 186  | 0.1785          |
-| 0.199         | 32.0  | 192  | 0.1649          |
-| 0.1886        | 33.0  | 198  | 0.1496          |
-| 0.1728        | 34.0  | 204  | 0.1400          |
-| 0.1933        | 35.0  | 210  | 0.1311          |
-| 0.1546        | 36.0  | 216  | 0.1296          |
-| 0.1633        | 37.0  | 222  | 0.1237          |
-| 0.1524        | 38.0  | 228  | 0.1202          |
-| 0.156         | 39.0  | 234  | 0.1177          |
-| 0.1439        | 40.0  | 240  | 0.1167          |
+| 2.9708        | 1.0   | 6    | 2.2532          |
+| 2.0334        | 2.0   | 12   | 1.7317          |
+| 1.5636        | 3.0   | 18   | 1.3306          |
+| 1.2228        | 4.0   | 24   | 1.1101          |
+| 1.0587        | 5.0   | 30   | 0.9678          |
+| 0.9399        | 6.0   | 36   | 0.8654          |
+| 0.8269        | 7.0   | 42   | 0.7420          |
+| 0.7354        | 8.0   | 48   | 0.6981          |
+| 0.6841        | 9.0   | 54   | 0.6609          |
+| 0.6499        | 10.0  | 60   | 0.6128          |
+| 0.592         | 11.0  | 66   | 0.5730          |
+| 0.5651        | 12.0  | 72   | 0.5324          |
+| 0.53          | 13.0  | 78   | 0.5232          |
+| 0.5087        | 14.0  | 84   | 0.5066          |
+| 0.5052        | 15.0  | 90   | 0.4966          |
+| 0.4933        | 16.0  | 96   | 0.4476          |
+| 0.4622        | 17.0  | 102  | 0.4559          |
+| 0.4604        | 18.0  | 108  | 0.4520          |
+| 0.4386        | 19.0  | 114  | 0.4525          |
+| 0.4453        | 20.0  | 120  | 0.4345          |
+| 0.4293        | 21.0  | 126  | 0.3955          |
+| 0.3904        | 22.0  | 132  | 0.3695          |
+| 0.3793        | 23.0  | 138  | 0.3614          |
+| 0.3648        | 24.0  | 144  | 0.3463          |
+| 0.3471        | 25.0  | 150  | 0.3247          |
+| 0.3391        | 26.0  | 156  | 0.3100          |
+| 0.3084        | 27.0  | 162  | 0.2981          |
+| 0.3188        | 28.0  | 168  | 0.2901          |
+| 0.3074        | 29.0  | 174  | 0.2791          |
+| 0.2847        | 30.0  | 180  | 0.2832          |
+| 0.2832        | 31.0  | 186  | 0.2637          |
+| 0.2762        | 32.0  | 192  | 0.2596          |
+| 0.2928        | 33.0  | 198  | 0.2487          |
+| 0.2759        | 34.0  | 204  | 0.2408          |
+| 0.2634        | 35.0  | 210  | 0.2334          |
+| 0.2585        | 36.0  | 216  | 0.2270          |
+| 0.2444        | 37.0  | 222  | 0.2227          |
+| 0.2394        | 38.0  | 228  | 0.2183          |
+| 0.2376        | 39.0  | 234  | 0.2174          |
+| 0.2394        | 40.0  | 240  | 0.2167          |
 
 
 ### Framework versions
 
-- Transformers 4.39.1
+- Transformers 4.38.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

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": {
@@ -157,13 +157,13 @@
     "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_type": "encoder-decoder",
   "pad_token_id": 3,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.1",
+  "transformers_version": "4.38.2",
   "unk_token_id": null
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 2,
   "eos_token_id": 0,
   "pad_token_id": 3,
-  "transformers_version": "4.39.1"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1153cedfc85ec5d686a11284c8328805e31efaec488f840a6503823e6955c3db
-size 31205552
+oid sha256:fab7ebca07c1654775fe9566420c379fa893d378403fdf2efb22053f5e40528e
+size 31207604

runs/Mar24_14-32-40_6999fcd7abc0/events.out.tfevents.1711290761.6999fcd7abc0.344.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655d3e8ec7efbd55091af0cb0ac9f4cbe9559c2d2cefaa1373817fd42949c79f
+size 27997

tokenizer.json

@@ -115,76 +115,78 @@
       "=": 16,
       "10": 17,
       "99": 18,
-      "98": 19,
-      "11": 20,
+      "11": 19,
+      "98": 20,
       "12": 21,
       "97": 22,
       "96": 23,
       "13": 24,
       "95": 25,
       "14": 26,
-      "94": 27,
-      "15": 28,
+      "15": 27,
+      "94": 28,
       "16": 29,
       "93": 30,
-      "92": 31,
-      "17": 32,
+      "17": 31,
+      "92": 32,
       "91": 33,
       "18": 34,
-      "19": 35,
-      "90": 36,
-      "89": 37,
-      "20": 38,
-      "88": 39,
-      "21": 40,
+      "90": 35,
+      "19": 36,
+      "20": 37,
+      "89": 38,
+      "21": 39,
+      "88": 40,
       "22": 41,
       "87": 42,
-      "23": 43,
-      "86": 44,
+      "86": 43,
+      "23": 44,
       "85": 45,
       "24": 46,
       "25": 47,
       "84": 48,
       "26": 49,
       "83": 50,
-      "27": 51
+      "27": 51,
+      "82": 52
     },
     "merges": [
       "1 0",
       "9 9",
-      "9 8",
       "1 1",
+      "9 8",
       "1 2",
       "9 7",
       "9 6",
       "1 3",
       "9 5",
       "1 4",
-      "9 4",
       "1 5",
+      "9 4",
       "1 6",
       "9 3",
-      "9 2",
       "1 7",
+      "9 2",
       "9 1",
       "1 8",
-      "1 9",
       "9 0",
-      "8 9",
+      "1 9",
       "2 0",
-      "8 8",
+      "8 9",
       "2 1",
+      "8 8",
       "2 2",
       "8 7",
-      "2 3",
       "8 6",
+      "2 3",
       "8 5",
       "2 4",
       "2 5",
       "8 4",
       "2 6",
       "8 3",
-      "2 7"
+      "2 7",
+      "8 2"
     ]
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b9f3f5874638aabbe2e04368849eece01253418968201c2f118982fc0761f0
+oid sha256:160d6026e0184d20fa6b068e287f3fa90f6d2471cb2d32c45c963f3a6f69912f
 size 5112