End of training

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1559
+- Loss: 1.1742
 
 ## Model description
 
@@ -47,14 +48,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.2231        | 1.0   | 5533  | 1.1573          |
-| 0.9589        | 2.0   | 11066 | 1.1232          |
-| 0.7616        | 3.0   | 16599 | 1.1559          |
+| 1.2132        | 1.0   | 5533  | 1.1774          |
+| 0.9302        | 2.0   | 11066 | 1.1182          |
+| 0.7419        | 3.0   | 16599 | 1.1742          |
 
 
 ### Framework versions
 
-- Transformers 4.17.0
-- Pytorch 2.1.0+cu118
+- Transformers 4.35.2
+- Pytorch 1.12.1+cu113
 - Datasets 2.15.0
 - Tokenizers 0.15.0

config.json

@@ -19,6 +19,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.17.0",
+  "transformers_version": "4.35.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1bc0bea9a89f1afb3b1969ffaaeb9f22d699ab22f15c58bd7f65d0c6144d965
+size 265470032

runs/Dec12_09-58-59_DESKTOP-8H9FK5A/events.out.tfevents.1702403954.DESKTOP-8H9FK5A.5200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0bbe0b9dfd95f1a8c474b52d4c30484f3221e85b7acc29c02d20c970e13aff
+size 10528

special_tokens_map.json

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

tokenizer_config.json

@@ -1 +1,55 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377c8894c7723104e220ddf30884cc2db0ceb5f7b52fbc3109b25b5e9e22f7ce
-size 3512
+oid sha256:945564281851131d85b8f165811d5cff51ff3853ff5826ebce6fa378addfebe4
+size 4143