Training in progress, step 100

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: temporary0-0name/run_opt
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
@@ -15,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # run_opt
 
-This model is a fine-tuned version of [temporary0-0name/run_opt](https://huggingface.co/temporary0-0name/run_opt) on the wikitext dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the wikitext dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0107
 
 ## Model description
 
@@ -43,18 +45,35 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 1    | 10.4150         |
+| 7.6252        | 0.55  | 100  | 6.4113          |
+| 4.839         | 1.1   | 200  | 2.0385          |
+| 0.9137        | 1.65  | 300  | 0.3108          |
+| 0.171         | 2.2   | 400  | 0.0877          |
+| 0.0542        | 2.75  | 500  | 0.0396          |
+| 0.025         | 3.29  | 600  | 0.0242          |
+| 0.0148        | 3.84  | 700  | 0.0180          |
+| 0.0098        | 4.39  | 800  | 0.0148          |
+| 0.0077        | 4.94  | 900  | 0.0130          |
+| 0.006         | 5.49  | 1000 | 0.0121          |
+| 0.0053        | 6.04  | 1100 | 0.0115          |
+| 0.0045        | 6.59  | 1200 | 0.0112          |
+| 0.0042        | 7.14  | 1300 | 0.0110          |
+| 0.0039        | 7.69  | 1400 | 0.0109          |
+| 0.0038        | 8.24  | 1500 | 0.0108          |
+| 0.0037        | 8.79  | 1600 | 0.0107          |
+| 0.0037        | 9.33  | 1700 | 0.0107          |
+| 0.0036        | 9.88  | 1800 | 0.0107          |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+- Transformers 4.33.1
+- Pytorch 1.12.1
+- Datasets 2.14.6
+- Tokenizers 0.13.3

config.json

@@ -19,7 +19,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.33.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

generation_config.json

@@ -1,5 +1,5 @@
 {
   "_from_model_config": true,
   "pad_token_id": 0,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.33.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153d131dfeceac8dd97ca99344b36811f898e872944df85e63b1aa8453e176be
+oid sha256:cdd8f113d389f61fde19184ebf65e6dd85c933e950529fa92f416eb7355be49d
 size 438124333

special_tokens_map.json

@@ -1,13 +1,7 @@
 {
   "cls_token": "[CLS]",
   "mask_token": "[MASK]",
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,46 +1,4 @@
 {
-  "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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1146ba05bdf0c271e8b37a2ab61d281c22a60ddc7dcdfed6827b245935c474a4
-size 4536
+oid sha256:8e0d0bb29f293a55e44e7583d04f2a3e382a5ea8209ae54677a2375f081f16a2
+size 3951