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: 0.8854
+- Loss: 0.8243
 
 ## Model description
 
@@ -44,16 +44,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.0459        | 1.0   | 5    | 2.4452          |
-| 2.2781        | 2.0   | 10   | 2.0536          |
-| 1.883         | 3.0   | 15   | 1.6599          |
-| 1.5519        | 4.0   | 20   | 1.4205          |
-| 1.3589        | 5.0   | 25   | 1.2785          |
-| 1.2145        | 6.0   | 30   | 1.1344          |
-| 1.0845        | 7.0   | 35   | 1.0183          |
-| 0.9945        | 8.0   | 40   | 0.9482          |
-| 0.9314        | 9.0   | 45   | 0.8990          |
-| 0.8972        | 10.0  | 50   | 0.8854          |
+| 2.8893        | 1.0   | 6    | 2.1271          |
+| 1.9669        | 2.0   | 12   | 1.8233          |
+| 1.6822        | 3.0   | 18   | 1.5134          |
+| 1.3991        | 4.0   | 24   | 1.2639          |
+| 1.1731        | 5.0   | 30   | 1.1030          |
+| 1.0664        | 6.0   | 36   | 0.9758          |
+| 0.9729        | 7.0   | 42   | 0.9245          |
+| 0.9171        | 8.0   | 48   | 0.8696          |
+| 0.8722        | 9.0   | 54   | 0.8384          |
+| 0.8487        | 10.0  | 60   | 0.8243          |
 
 
 ### Framework versions

config.json

@@ -78,9 +78,9 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 51
+    "vocab_size": 56
   },
-  "decoder_start_token_id": 49,
+  "decoder_start_token_id": 1,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -157,12 +157,12 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 51
+    "vocab_size": 56
   },
-  "eos_token_id": 50,
+  "eos_token_id": 6,
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
-  "pad_token_id": 48,
+  "pad_token_id": 3,
   "torch_dtype": "float32",
   "transformers_version": "4.37.2"
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
-  "decoder_start_token_id": 49,
-  "eos_token_id": 50,
-  "pad_token_id": 48,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 6,
+  "pad_token_id": 3,
   "transformers_version": "4.37.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d68eedd7c2ce4a569ddec467812d03352c8a7b222c55e6dde6b7c022a7ea4859
-size 31203500
+oid sha256:3c786ce574c7b54427c775c1c401bc60b3a2a1bf4da9d34ebd224728b1d9fdb1
+size 31213760

runs/Feb28_13-26-30_3897ec21fae5/events.out.tfevents.1709126790.3897ec21fae5.17803.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8918b9c98527482fb0ae44af3cc57d56c66e466f5fc8108c4c2b57a3b6988cb3
+size 4184

runs/Feb28_13-28-13_3897ec21fae5/events.out.tfevents.1709126894.3897ec21fae5.18243.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f49d302e9b6efdd89a1ff829ad435c123743f3b816dcc97ded912b68c1e009e
+size 12864

tokenizer.json

@@ -4,8 +4,8 @@
   "padding": null,
   "added_tokens": [
     {
-      "id": 48,
-      "content": "[PAD]",
+      "id": 0,
+      "content": "[UNK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -13,7 +13,7 @@
       "special": true
     },
     {
-      "id": 49,
+      "id": 1,
       "content": "[CLS]",
       "single_word": false,
       "lstrip": false,
@@ -22,7 +22,43 @@
       "special": true
     },
     {
-      "id": 50,
+      "id": 2,
+      "content": "[SEP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "[BOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6,
       "content": "[EOS]",
       "single_word": false,
       "lstrip": false,
@@ -40,86 +76,94 @@
   "model": {
     "type": "BPE",
     "dropout": null,
-    "unk_token": null,
+    "unk_token": "[UNK]",
     "continuing_subword_prefix": null,
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
     "vocab": {
-      "+": 0,
-      "-": 1,
-      "0": 2,
-      "1": 3,
-      "2": 4,
-      "3": 5,
-      "4": 6,
-      "5": 7,
-      "6": 8,
-      "7": 9,
-      "8": 10,
-      "9": 11,
-      "=": 12,
-      "10": 13,
-      "99": 14,
-      "11": 15,
-      "98": 16,
-      "12": 17,
-      "97": 18,
-      "96": 19,
-      "13": 20,
-      "14": 21,
-      "95": 22,
-      "15": 23,
-      "94": 24,
-      "16": 25,
-      "93": 26,
-      "17": 27,
-      "92": 28,
-      "18": 29,
-      "91": 30,
-      "19": 31,
-      "90": 32,
-      "20": 33,
-      "89": 34,
-      "88": 35,
-      "21": 36,
-      "22": 37,
-      "87": 38,
-      "23": 39,
-      "86": 40,
-      "24": 41,
-      "85": 42,
-      "84": 43,
-      "25": 44,
-      "26": 45,
-      "83": 46,
-      "27": 47
+      "[UNK]": 0,
+      "[CLS]": 1,
+      "[SEP]": 2,
+      "[PAD]": 3,
+      "[MASK]": 4,
+      "[BOS]": 5,
+      "[EOS]": 6,
+      "+": 7,
+      "-": 8,
+      "0": 9,
+      "1": 10,
+      "2": 11,
+      "3": 12,
+      "4": 13,
+      "5": 14,
+      "6": 15,
+      "7": 16,
+      "8": 17,
+      "9": 18,
+      "=": 19,
+      "99": 20,
+      "10": 21,
+      "98": 22,
+      "11": 23,
+      "12": 24,
+      "97": 25,
+      "13": 26,
+      "96": 27,
+      "95": 28,
+      "14": 29,
+      "94": 30,
+      "15": 31,
+      "16": 32,
+      "93": 33,
+      "17": 34,
+      "92": 35,
+      "91": 36,
+      "18": 37,
+      "19": 38,
+      "90": 39,
+      "20": 40,
+      "89": 41,
+      "21": 42,
+      "88": 43,
+      "22": 44,
+      "87": 45,
+      "23": 46,
+      "86": 47,
+      "24": 48,
+      "85": 49,
+      "84": 50,
+      "25": 51,
+      "26": 52,
+      "83": 53,
+      "27": 54,
+      "82": 55
     },
     "merges": [
-      "1 0",
       "9 9",
-      "1 1",
+      "1 0",
       "9 8",
+      "1 1",
       "1 2",
       "9 7",
-      "9 6",
       "1 3",
-      "1 4",
+      "9 6",
       "9 5",
-      "1 5",
+      "1 4",
       "9 4",
+      "1 5",
       "1 6",
       "9 3",
       "1 7",
       "9 2",
-      "1 8",
       "9 1",
+      "1 8",
       "1 9",
       "9 0",
       "2 0",
       "8 9",
-      "8 8",
       "2 1",
+      "8 8",
       "2 2",
       "8 7",
       "2 3",
@@ -130,7 +174,8 @@
       "2 5",
       "2 6",
       "8 3",
-      "2 7"
+      "2 7",
+      "8 2"
     ]
   }
 }

tokenizer_config.json

@@ -1,14 +1,14 @@
 {
   "added_tokens_decoder": {
-    "48": {
-      "content": "[PAD]",
+    "0": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "49": {
+    "1": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,39 @@
       "single_word": false,
       "special": true
     },
-    "50": {
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
       "content": "[EOS]",
       "lstrip": false,
       "normalized": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22510d433bcd6c8ab9f638615a22414f615f7dc618aab32a485345ef2763c73
+oid sha256:6659b0093eeff414bea7b0676fa26b8ced67d1bab20bc510776e16dcea6efb68
 size 4920