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: 5.4455
+- Loss: 2.8642
 
 ## Model description
 
@@ -44,14 +44,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 7    | 5.6515          |
-| No log        | 2.0   | 14   | 5.5036          |
-| No log        | 3.0   | 21   | 5.4455          |
+| No log        | 1.0   | 64   | 4.0447          |
+| No log        | 2.0   | 128  | 3.0124          |
+| No log        | 3.0   | 192  | 2.8642          |
 
 
 ### Framework versions
 
 - Transformers 4.39.3
-- Pytorch 2.2.1+cpu
+- Pytorch 2.2.2+cpu
 - Datasets 2.18.0
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a0b793aaef60ea1d147ec1c606ac7fa43e87d60399ab720413efa134f18062
+oid sha256:7acb911f55e83a2d03afa97159fb63c5db19e1c2f212b1b44dfab618be359758
 size 132874824

runs/Apr21_14-01-41_LAPTOP-E27K5G14/events.out.tfevents.1713729702.LAPTOP-E27K5G14.15992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f960733e74592c65e8e44a74b5321f90af5cbc062f370a7067043c82e8e1f8e
+size 5738

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.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

@@ -46,16 +46,12 @@
   "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 sha256:4b71566a688b58294e846bba9274b48118b20e631ad9b9e8f94e8b5945a7ecd2
+oid sha256:e4276b929ddd352dee06c0b2acc778cffcaa1e099bb48ed40f01ab5d9ded85d4
 size 4920