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: 0.4373
+- Loss: 0.1675
 
 ## Model description
 
@@ -38,32 +38,52 @@ 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: 20
+- num_epochs: 40
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.9387        | 1.0   | 6    | 2.2225          |
-| 1.9975        | 2.0   | 12   | 1.6708          |
-| 1.5075        | 3.0   | 18   | 1.2869          |
-| 1.192         | 4.0   | 24   | 1.0852          |
-| 1.0194        | 5.0   | 30   | 0.9349          |
-| 0.8763        | 6.0   | 36   | 0.8014          |
-| 0.777         | 7.0   | 42   | 0.7309          |
-| 0.7214        | 8.0   | 48   | 0.6808          |
-| 0.6716        | 9.0   | 54   | 0.6422          |
-| 0.6235        | 10.0  | 60   | 0.5947          |
-| 0.6023        | 11.0  | 66   | 0.5575          |
-| 0.5757        | 12.0  | 72   | 0.5380          |
-| 0.5418        | 13.0  | 78   | 0.5109          |
-| 0.5253        | 14.0  | 84   | 0.4918          |
-| 0.5081        | 15.0  | 90   | 0.4780          |
-| 0.4872        | 16.0  | 96   | 0.4696          |
-| 0.4816        | 17.0  | 102  | 0.4536          |
-| 0.467         | 18.0  | 108  | 0.4458          |
-| 0.4583        | 19.0  | 114  | 0.4396          |
-| 0.4508        | 20.0  | 120  | 0.4373          |
+| 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          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530b56ac95629a59f930966137d5db318c75ffe80eba4854c2166370f6c24dee
+oid sha256:acc27a663e8618358ac7d8ac485aeefb415193b7eab7325fa800606372f02f23
 size 31207604

runs/Feb28_20-49-03_3897ec21fae5/events.out.tfevents.1709153344.3897ec21fae5.125073.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed338c255b9cfa2214ae29bb2a362ab5bcf4c08c6112754ac6f7143c7096df71
+size 25647

tokenizer.json

@@ -113,26 +113,26 @@
       "8": 14,
       "9": 15,
       "=": 16,
-      "99": 17,
-      "10": 18,
-      "98": 19,
-      "11": 20,
+      "10": 17,
+      "99": 18,
+      "11": 19,
+      "98": 20,
       "97": 21,
       "12": 22,
-      "96": 23,
-      "13": 24,
-      "95": 25,
-      "14": 26,
-      "94": 27,
-      "15": 28,
-      "93": 29,
-      "16": 30,
+      "13": 23,
+      "96": 24,
+      "14": 25,
+      "95": 26,
+      "15": 27,
+      "94": 28,
+      "16": 29,
+      "93": 30,
       "17": 31,
       "92": 32,
       "18": 33,
       "91": 34,
-      "90": 35,
-      "19": 36,
+      "19": 35,
+      "90": 36,
       "20": 37,
       "89": 38,
       "21": 39,
@@ -145,32 +145,32 @@
       "24": 46,
       "25": 47,
       "84": 48,
-      "83": 49,
-      "26": 50,
+      "26": 49,
+      "83": 50,
       "27": 51,
       "82": 52
     },
     "merges": [
-      "9 9",
       "1 0",
-      "9 8",
+      "9 9",
       "1 1",
+      "9 8",
       "9 7",
       "1 2",
-      "9 6",
       "1 3",
-      "9 5",
+      "9 6",
       "1 4",
-      "9 4",
+      "9 5",
       "1 5",
-      "9 3",
+      "9 4",
       "1 6",
+      "9 3",
       "1 7",
       "9 2",
       "1 8",
       "9 1",
-      "9 0",
       "1 9",
+      "9 0",
       "2 0",
       "8 9",
       "2 1",
@@ -183,8 +183,8 @@
       "2 4",
       "2 5",
       "8 4",
-      "8 3",
       "2 6",
+      "8 3",
       "2 7",
       "8 2"
     ]

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f26d29d4f2114e0ece86e6996348f7ee2d5a2f73ad33e6938c6332793ceb08
+oid sha256:5295e2924564bea6263a351ff515e8a2133e6bce451f891ddb63bb59cf45e69d
 size 4920