End of training

README.md

@@ -1,6 +1,5 @@
 ---
-license: apache-2.0
-base_model: temporary0-0name/run_opt1
+base_model: temporary0-0name/rand_model
 tags:
 - generated_from_trainer
 datasets:
@@ -15,9 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # run_opt1
 
-This model is a fine-tuned version of [temporary0-0name/run_opt1](https://huggingface.co/temporary0-0name/run_opt1) on the wikitext dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0540
+This model is a fine-tuned version of [temporary0-0name/rand_model](https://huggingface.co/temporary0-0name/rand_model) on the wikitext dataset.
 
 ## Model description
 
@@ -45,18 +42,16 @@ 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: 3
+- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.0126        | 0.55  | 100  | 0.0540          |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
-- Pytorch 1.12.1
+- Transformers 4.35.0
+- Pytorch 2.0.1+cu118
 - Datasets 2.14.6
-- Tokenizers 0.13.3
+- Tokenizers 0.14.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "temporary0-0name/run_opt1",
+  "_name_or_path": "temporary0-0name/rand_model",
   "architectures": [
     "BertLMHeadModel"
   ],
@@ -19,7 +19,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.35.0",
   "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": "4.33.1"
+  "transformers_version": "4.35.0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32343c48106fcbf4a07ef352cc6efa7421a6a613dd6e76a4e570a66c90f54ac
+size 438080896

special_tokens_map.json

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

tokenizer_config.json

@@ -1,4 +1,46 @@
 {
+  "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 sha256:3465c38b6a9e045bdb1cadce337bd3213dcaba04565b1610e342db5753c2c75a
-size 3951
+oid sha256:e3c35310a37ecf2fc81c922a1e33d5ce9798882501cc8dfe7a456af7650fe663
+size 4091