End of training

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.6955
+- Loss: 5.9052
 
 ## Model description
 
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 7    | 4.9599          |
-| No log        | 2.0   | 14   | 4.7586          |
-| No log        | 3.0   | 21   | 4.6955          |
+| No log        | 1.0   | 1    | 5.9417          |
+| No log        | 2.0   | 2    | 5.9173          |
+| No log        | 3.0   | 3    | 5.9052          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc5372b1f1f069e86cffab9338014d9c8287009cce179166c7e2b1f14f32712c
+oid sha256:1d9416e48aa79377268b8c10a185ed0b14eae06da5fffda3cd6212ccd5e1dac0
 size 132874824

runs/Apr21_12-16-35_LAPTOP-E27K5G14/events.out.tfevents.1713723395.LAPTOP-E27K5G14.11056.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab2f0508e7f24f3f84860f13a73caa066bfdfdab585cff9368094e91bd4f2fa
+size 5722

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -46,19 +46,12 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 384,
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 128,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "only_second",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f616e05199c59920de5288e1307ba8795123c3901a1d4dc689f9bd525c36a0d9
+oid sha256:158578abb00a0bac856835796ecfb956e305353a9c742ba446ede0e61b068d16
 size 4920