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: 0.1675
+- Loss: 0.3578
 
 ## Model description
 
@@ -38,57 +38,47 @@ 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: 40
+- num_epochs: 30
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.9654        | 1.0   | 6    | 2.2731          |
-| 2.0238        | 2.0   | 12   | 1.7268          |
-| 1.5275        | 3.0   | 18   | 1.2838          |
-| 1.187         | 4.0   | 24   | 1.0874          |
-| 1.0242        | 5.0   | 30   | 0.9517          |
-| 0.9122        | 6.0   | 36   | 0.8367          |
-| 0.8028        | 7.0   | 42   | 0.8002          |
-| 0.762         | 8.0   | 48   | 0.7533          |
-| 0.6956        | 9.0   | 54   | 0.6658          |
-| 0.6503        | 10.0  | 60   | 0.6102          |
-| 0.6071        | 11.0  | 66   | 0.5720          |
-| 0.5785        | 12.0  | 72   | 0.5378          |
-| 0.5367        | 13.0  | 78   | 0.5026          |
-| 0.5118        | 14.0  | 84   | 0.5035          |
-| 0.4987        | 15.0  | 90   | 0.4639          |
-| 0.4704        | 16.0  | 96   | 0.4410          |
-| 0.441         | 17.0  | 102  | 0.4364          |
-| 0.4407        | 18.0  | 108  | 0.4112          |
-| 0.4173        | 19.0  | 114  | 0.3852          |
-| 0.4001        | 20.0  | 120  | 0.3590          |
-| 0.3669        | 21.0  | 126  | 0.3375          |
-| 0.3402        | 22.0  | 132  | 0.3207          |
-| 0.3276        | 23.0  | 138  | 0.3187          |
-| 0.3205        | 24.0  | 144  | 0.2961          |
-| 0.2985        | 25.0  | 150  | 0.2673          |
-| 0.2897        | 26.0  | 156  | 0.2524          |
-| 0.2611        | 27.0  | 162  | 0.2408          |
-| 0.2597        | 28.0  | 168  | 0.2408          |
-| 0.2523        | 29.0  | 174  | 0.2277          |
-| 0.2385        | 30.0  | 180  | 0.2111          |
-| 0.2269        | 31.0  | 186  | 0.2068          |
-| 0.2272        | 32.0  | 192  | 0.2047          |
-| 0.2174        | 33.0  | 198  | 0.1927          |
-| 0.2097        | 34.0  | 204  | 0.1848          |
-| 0.1966        | 35.0  | 210  | 0.1817          |
-| 0.1894        | 36.0  | 216  | 0.1768          |
-| 0.1939        | 37.0  | 222  | 0.1760          |
-| 0.1884        | 38.0  | 228  | 0.1701          |
-| 0.1863        | 39.0  | 234  | 0.1683          |
-| 0.1824        | 40.0  | 240  | 0.1675          |
+| 2.9444        | 1.0   | 6    | 2.3826          |
+| 2.1543        | 2.0   | 12   | 1.8663          |
+| 1.7072        | 3.0   | 18   | 1.5640          |
+| 1.4261        | 4.0   | 24   | 1.3127          |
+| 1.2227        | 5.0   | 30   | 1.1949          |
+| 1.061         | 6.0   | 36   | 1.0322          |
+| 0.9789        | 7.0   | 42   | 0.9130          |
+| 0.8812        | 8.0   | 48   | 0.8633          |
+| 0.8289        | 9.0   | 54   | 0.7872          |
+| 0.693         | 10.0  | 60   | 0.7300          |
+| 0.7416        | 11.0  | 66   | 0.7454          |
+| 0.6965        | 12.0  | 72   | 0.6641          |
+| 0.6592        | 13.0  | 78   | 0.6362          |
+| 0.6411        | 14.0  | 84   | 0.5824          |
+| 0.5677        | 15.0  | 90   | 0.5541          |
+| 0.5575        | 16.0  | 96   | 0.5299          |
+| 0.5305        | 17.0  | 102  | 0.5435          |
+| 0.5371        | 18.0  | 108  | 0.4937          |
+| 0.4795        | 19.0  | 114  | 0.4800          |
+| 0.4693        | 20.0  | 120  | 0.4486          |
+| 0.4836        | 21.0  | 126  | 0.4478          |
+| 0.4351        | 22.0  | 132  | 0.4323          |
+| 0.47          | 23.0  | 138  | 0.4131          |
+| 0.414         | 24.0  | 144  | 0.4023          |
+| 0.4396        | 25.0  | 150  | 0.3961          |
+| 0.4079        | 26.0  | 156  | 0.3870          |
+| 0.4052        | 27.0  | 162  | 0.3846          |
+| 0.3914        | 28.0  | 168  | 0.3676          |
+| 0.4287        | 29.0  | 174  | 0.3593          |
+| 0.3583        | 30.0  | 180  | 0.3578          |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
+- Transformers 4.38.1
 - Pytorch 2.1.0+cu121
 - Datasets 2.17.1
 - Tokenizers 0.15.2

config.json

@@ -164,6 +164,6 @@
   "model_type": "encoder-decoder",
   "pad_token_id": 3,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.38.1",
   "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": "4.37.2"
+  "transformers_version": "4.38.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc27a663e8618358ac7d8ac485aeefb415193b7eab7325fa800606372f02f23
+oid sha256:167f72c4e239a9640669bd8575ebb02c93b5e1a3e22a64d06dd428bbe1e8cd7b
 size 31207604

runs/Mar01_00-04-39_f85640113c2d/events.out.tfevents.1709251480.f85640113c2d.685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d6cd48ae835475c67b1692920019d15893296a60deb4426426b4342aae3e7f
+size 23177

tokenizer.json

@@ -113,76 +113,76 @@
       "8": 14,
       "9": 15,
       "=": 16,
-      "10": 17,
-      "99": 18,
-      "11": 19,
-      "98": 20,
+      "99": 17,
+      "10": 18,
+      "98": 19,
+      "11": 20,
       "97": 21,
       "12": 22,
       "13": 23,
       "96": 24,
-      "14": 25,
-      "95": 26,
-      "15": 27,
-      "94": 28,
-      "16": 29,
-      "93": 30,
+      "95": 25,
+      "14": 26,
+      "94": 27,
+      "15": 28,
+      "93": 29,
+      "16": 30,
       "17": 31,
       "92": 32,
       "18": 33,
       "91": 34,
-      "19": 35,
-      "90": 36,
+      "90": 35,
+      "19": 36,
       "20": 37,
       "89": 38,
       "21": 39,
       "88": 40,
-      "87": 41,
-      "22": 42,
-      "23": 43,
-      "86": 44,
-      "85": 45,
-      "24": 46,
-      "25": 47,
-      "84": 48,
+      "22": 41,
+      "87": 42,
+      "86": 43,
+      "23": 44,
+      "24": 45,
+      "85": 46,
+      "84": 47,
+      "25": 48,
       "26": 49,
       "83": 50,
       "27": 51,
       "82": 52
     },
     "merges": [
-      "1 0",
       "9 9",
-      "1 1",
+      "1 0",
       "9 8",
+      "1 1",
       "9 7",
       "1 2",
       "1 3",
       "9 6",
-      "1 4",
       "9 5",
-      "1 5",
+      "1 4",
       "9 4",
-      "1 6",
+      "1 5",
       "9 3",
+      "1 6",
       "1 7",
       "9 2",
       "1 8",
       "9 1",
-      "1 9",
       "9 0",
+      "1 9",
       "2 0",
       "8 9",
       "2 1",
       "8 8",
-      "8 7",
       "2 2",
-      "2 3",
+      "8 7",
       "8 6",
-      "8 5",
+      "2 3",
       "2 4",
-      "2 5",
+      "8 5",
       "8 4",
+      "2 5",
       "2 6",
       "8 3",
       "2 7",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5295e2924564bea6263a351ff515e8a2133e6bce451f891ddb63bb59cf45e69d
-size 4920
+oid sha256:9b65476e169e5915d0d98245574cb840abef742cd27134fa31a767c9d1641c6e
+size 5112