Training in progress, epoch 1

README.md

@@ -1,25 +1,25 @@
 ---
 library_name: transformers
 license: mit
-base_model: roberta-large
+base_model: roberta-base
 tags:
 - generated_from_trainer
 model-index:
-- name: Emotionality_continuous
+- name: Artistic_Interests_continuous
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Emotionality_continuous
+# Artistic_Interests_continuous
 
-This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the None dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0453
-- Rmse: 0.2129
-- Mae: 0.1713
-- Corr: 0.3372
+- Loss: 0.0492
+- Rmse: 0.2217
+- Mae: 0.1795
+- Corr: 0.3117
 
 ## Model description
 
@@ -44,14 +44,15 @@ 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: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rmse   | Mae    | Corr   |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
-| No log        | 1.0   | 268  | 0.0417          | 0.2043 | 0.1637 | 0.2994 |
-| 0.0655        | 2.0   | 536  | 0.0453          | 0.2129 | 0.1713 | 0.3372 |
+| No log        | 1.0   | 268  | 0.0512          | 0.2263 | 0.1837 | 0.2633 |
+| 0.0617        | 2.0   | 536  | 0.0524          | 0.2288 | 0.1838 | 0.2989 |
+| 0.0617        | 3.0   | 804  | 0.0492          | 0.2217 | 0.1795 | 0.3117 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-large",
+  "_name_or_path": "roberta-base",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -9,20 +9,20 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "regression",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a2586e9545786bfc0f74bb58082b144825690f510d11cefcd5e527b764e2f7
-size 1421491316
+oid sha256:59945ccb6dabebfe3da9a4ea9ed2435f14bc3b7adb239d52351c28210376db27
+size 498609748

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b00b3fdb87f07279e40eb6c5081186dbed624c83ced6e8e7957ac276d4ceba
+oid sha256:5faa4b917858bd4760b1ab8075dd5f0ff338844a2844f5694e2421b7d360d6d4
 size 4719