add model

README.md

@@ -12,9 +12,13 @@ probably proofread and complete it, then remove this comment. -->
 
 # europython-imdb
 
-This model is a fine-tuned version of [Rocketknight1/europython-imdb](https://huggingface.co/Rocketknight1/europython-imdb) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-
+- Train Loss: 0.1279
+- Train Accuracy: 0.9548
+- Validation Loss: 0.1595
+- Validation Accuracy: 0.9418
+- Epoch: 1
 
 ## Model description
 
@@ -33,11 +37,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: None
+- optimizer: {'name': 'Adam', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
+| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
+|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
+| 0.2073     | 0.9203         | 0.1486          | 0.9435              | 0     |
+| 0.1279     | 0.9548         | 0.1595          | 0.9418              | 1     |
 
 
 ### Framework versions

config.json

@@ -1,26 +1,38 @@
 {
-  "_name_or_path": "Rocketknight1/europython-imdb",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "Negative",
+    "1": "Positive"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "transformers_version": "4.21.0.dev0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18fa14d632fc4c63bcb15d7bd151961eb20dfdcbee2422ae8c4702bf9b595d41
-size 498878336
+oid sha256:758dd785fc3710bc567f3a2748776b11ac07397c3e6605080b80d5679892343d
+size 737986944