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: 5.9052
+- Loss: 5.4455
 
 ## Model description
 
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 1    | 5.9417          |
-| No log        | 2.0   | 2    | 5.9173          |
-| No log        | 3.0   | 3    | 5.9052          |
+| No log        | 1.0   | 7    | 5.6515          |
+| No log        | 2.0   | 14   | 5.5036          |
+| No log        | 3.0   | 21   | 5.4455          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9416e48aa79377268b8c10a185ed0b14eae06da5fffda3cd6212ccd5e1dac0
+oid sha256:81a0b793aaef60ea1d147ec1c606ac7fa43e87d60399ab720413efa134f18062
 size 132874824

runs/Apr21_12-22-45_LAPTOP-E27K5G14/events.out.tfevents.1713723766.LAPTOP-E27K5G14.12616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6633469165ad70f74a9b495ceaf8cd0170afd2995625628953c8bbd26087f51c
+size 5807

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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
+  }
 }

tokenizer.json

@@ -6,7 +6,16 @@
     "strategy": "OnlySecond",
     "stride": 128
   },
-  "padding": null,
+  "padding": {
+    "strategy": {
+      "Fixed": 384
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -46,12 +46,16 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 384,
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
   "pad_token": "[PAD]",
   "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 sha256:158578abb00a0bac856835796ecfb956e305353a9c742ba446ede0e61b068d16
+oid sha256:4b71566a688b58294e846bba9274b48118b20e631ad9b9e8f94e8b5945a7ecd2
 size 4920