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: 0.8293
+- Loss: 0.0408
 
 ## Model description
 
@@ -38,22 +38,62 @@ 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: 10
+- num_epochs: 50
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.1137        | 1.0   | 5    | 2.4084          |
-| 2.2183        | 2.0   | 10   | 1.9525          |
-| 1.8245        | 3.0   | 15   | 1.6233          |
-| 1.4964        | 4.0   | 20   | 1.3035          |
-| 1.2386        | 5.0   | 25   | 1.1278          |
-| 1.1028        | 6.0   | 30   | 1.0257          |
-| 1.0138        | 7.0   | 35   | 0.9629          |
-| 0.9489        | 8.0   | 40   | 0.8972          |
-| 0.8914        | 9.0   | 45   | 0.8501          |
-| 0.8541        | 10.0  | 50   | 0.8293          |
+| 3.1232        | 1.0   | 5    | 2.3752          |
+| 2.1776        | 2.0   | 10   | 1.8879          |
+| 1.7349        | 3.0   | 15   | 1.4779          |
+| 1.3722        | 4.0   | 20   | 1.2288          |
+| 1.1464        | 5.0   | 25   | 1.0354          |
+| 0.995         | 6.0   | 30   | 0.9079          |
+| 0.8838        | 7.0   | 35   | 0.8040          |
+| 0.7827        | 8.0   | 40   | 0.7075          |
+| 0.7079        | 9.0   | 45   | 0.6453          |
+| 0.6523        | 10.0  | 50   | 0.5931          |
+| 0.6042        | 11.0  | 55   | 0.5485          |
+| 0.5548        | 12.0  | 60   | 0.5170          |
+| 0.5339        | 13.0  | 65   | 0.5695          |
+| 0.5492        | 14.0  | 70   | 0.4823          |
+| 0.4951        | 15.0  | 75   | 0.4626          |
+| 0.464         | 16.0  | 80   | 0.4308          |
+| 0.4377        | 17.0  | 85   | 0.3924          |
+| 0.4059        | 18.0  | 90   | 0.3690          |
+| 0.3782        | 19.0  | 95   | 0.3322          |
+| 0.3458        | 20.0  | 100  | 0.3135          |
+| 0.3307        | 21.0  | 105  | 0.2936          |
+| 0.2999        | 22.0  | 110  | 0.2577          |
+| 0.2739        | 23.0  | 115  | 0.2444          |
+| 0.2461        | 24.0  | 120  | 0.2236          |
+| 0.2264        | 25.0  | 125  | 0.1957          |
+| 0.2046        | 26.0  | 130  | 0.1637          |
+| 0.1819        | 27.0  | 135  | 0.1415          |
+| 0.16          | 28.0  | 140  | 0.1238          |
+| 0.1454        | 29.0  | 145  | 0.1092          |
+| 0.1297        | 30.0  | 150  | 0.0997          |
+| 0.1188        | 31.0  | 155  | 0.0876          |
+| 0.1105        | 32.0  | 160  | 0.0897          |
+| 0.1033        | 33.0  | 165  | 0.0779          |
+| 0.0941        | 34.0  | 170  | 0.0702          |
+| 0.0897        | 35.0  | 175  | 0.0656          |
+| 0.085         | 36.0  | 180  | 0.0634          |
+| 0.0796        | 37.0  | 185  | 0.0596          |
+| 0.0768        | 38.0  | 190  | 0.0560          |
+| 0.0728        | 39.0  | 195  | 0.0556          |
+| 0.0702        | 40.0  | 200  | 0.0516          |
+| 0.0662        | 41.0  | 205  | 0.0493          |
+| 0.063         | 42.0  | 210  | 0.0472          |
+| 0.0613        | 43.0  | 215  | 0.0459          |
+| 0.0617        | 44.0  | 220  | 0.0449          |
+| 0.0579        | 45.0  | 225  | 0.0425          |
+| 0.0556        | 46.0  | 230  | 0.0428          |
+| 0.0555        | 47.0  | 235  | 0.0413          |
+| 0.0536        | 48.0  | 240  | 0.0409          |
+| 0.053         | 49.0  | 245  | 0.0409          |
+| 0.0532        | 50.0  | 250  | 0.0408          |
 
 
 ### Framework versions

config.json

@@ -164,5 +164,6 @@
   "model_type": "encoder-decoder",
   "pad_token_id": 3,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2"
+  "transformers_version": "4.37.2",
+  "unk_token_id": null
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81fc7b57152471f3a7e91ddb5748cb31d364cdf1231993b9b2e9a2e4935eacc2
+oid sha256:88677a6bc13ac58099475a50c0deea5f6f7c48e5d529d97000cfbd253bc7678d
 size 31207604

runs/Feb28_16-35-15_3897ec21fae5/events.out.tfevents.1709138116.3897ec21fae5.63513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec06d2cbb04ab48a0419546960deedcc1588037691c2935a1cd2ec2051d5ee6
+size 29894

tokenizer.json

@@ -117,18 +117,18 @@
       "99": 18,
       "11": 19,
       "98": 20,
-      "12": 21,
-      "97": 22,
-      "13": 23,
-      "96": 24,
+      "97": 21,
+      "12": 22,
+      "96": 23,
+      "13": 24,
       "14": 25,
       "95": 26,
       "94": 27,
       "15": 28,
       "93": 29,
       "16": 30,
-      "17": 31,
-      "92": 32,
+      "92": 31,
+      "17": 32,
       "91": 33,
       "18": 34,
       "19": 35,
@@ -141,8 +141,8 @@
       "87": 42,
       "86": 43,
       "23": 44,
-      "24": 45,
-      "85": 46,
+      "85": 45,
+      "24": 46,
       "25": 47,
       "84": 48,
       "26": 49,
@@ -155,18 +155,18 @@
       "9 9",
       "1 1",
       "9 8",
-      "1 2",
       "9 7",
-      "1 3",
+      "1 2",
       "9 6",
+      "1 3",
       "1 4",
       "9 5",
       "9 4",
       "1 5",
       "9 3",
       "1 6",
-      "1 7",
       "9 2",
+      "1 7",
       "9 1",
       "1 8",
       "1 9",
@@ -179,8 +179,8 @@
       "8 7",
       "8 6",
       "2 3",
-      "2 4",
       "8 5",
+      "2 4",
       "2 5",
       "8 4",
       "2 6",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e46815b331bc7909d4a5070fdf40bbc45cf7721c8d9b964c3fe72a560bdecce
+oid sha256:8118a074521f462d1f96fea1964baf76db0a332f1b116d058695b88f02ef809e
 size 4920