Model save

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: sinonimayzer/roberta-1.8-v2
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # roberta-1.8-v3
 
-This model is a fine-tuned version of [sinonimayzer/roberta-1.8-v2](https://huggingface.co/sinonimayzer/roberta-1.8-v2) on the None dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 
 ## Model description
 
@@ -32,7 +31,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 40
+- train_batch_size: 20
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "sinonimayzer/roberta-1.8-v2",
   "architectures": [
     "RobertaForMaskedLM"
   ],
@@ -16,7 +15,7 @@
   "max_position_embeddings": 512,
   "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0929d979f4cd0e29531486e56950ed2d76685a1c2e4bb53a7c50f675cb1aa9
-size 334024120
+oid sha256:bd0d77f0daded24e4aa1e38834f93bc25d0d65adc6394594554b4240838dffc3
+size 504144664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d93dfa729e617b8fb6ad48caa8e862b222fec2678e86e76d362ea7ec86c1b22
+oid sha256:4b8350c544a4792de44325caefa8763ea5cb3376ee1e3e3391a60160d9bbf4c2
 size 4600