Model save

README.md

@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.0
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -21,7 +21,7 @@
   "pad_token_id": 3,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.41.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 32000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e99b6fcbe51e8f10e87206b681885a143b114f04dd118a471bf762b02eecd7
+oid sha256:d2614e522c8efa78979be57f25b12a4b139d72261f7f52900ccc09ac367c8273
 size 440143216

runs/May31_07-27-25_0af2644edfbe/events.out.tfevents.1717140456.0af2644edfbe.1260.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90c6d4e7865ae1ff1d3630a8885b57c7f6b01b286a9412b94d81cc3fccb1bec
+size 9417

special_tokens_map.json

@@ -1,9 +1,51 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "[CLS]",
-  "eos_token": "</s>",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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

@@ -100,8 +100,8 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "prepend_scheme": "always",
+    "split": true
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -160,8 +160,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "prepend_scheme": "always",
+    "split": true
   },
   "model": {
     "type": "Unigram",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e91787ec7df233286a7d961d64a5470f812c0bb4c75ccea0d46922870a3a01
-size 4600
+oid sha256:e6b51f566aa44ea19a40fd003edd17d3db239ce7bcc97d6f90881bfdb7d35b18
+size 5112