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: Self-consciousness_continuous
+- name: Depression_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. -->
 
-# Self-consciousness_continuous
+# Depression_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: 0.0414
-- Rmse: 0.2034
-- Mae: 0.1638
-- Corr: 0.2866
+- Loss: 0.0674
+- Rmse: 0.2596
+- Mae: 0.2114
+- Corr: 0.4863
 
 ## 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  | 0.0427          | 0.2067 | 0.1669 | 0.2611 |
-| 0.0634        | 2.0   | 536  | 0.0414          | 0.2034 | 0.1638 | 0.2866 |
+| No log        | 1.0   | 268  | 0.0765          | 0.2765 | 0.2304 | 0.4583 |
+| 0.0728        | 2.0   | 536  | 0.0676          | 0.2600 | 0.2117 | 0.4750 |
+| 0.0728        | 3.0   | 804  | 0.0674          | 0.2596 | 0.2114 | 0.4863 |
 
 
 ### 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 sha256:0141232709bc541e22a1de03f84f6e140bed7f0253a10c8c9825d3f3983328f8
-size 1421491316
+oid sha256:ce861552181e8810840384eb3411465df9c8bb64f4c96d2d56ccdc8144b20eec
+size 498609748

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d24b0e881b69d6b2d42e5060224fe131af1e8d5bb2d19904de29e0ed7d7b286
+oid sha256:c9e1251ee2776b677a38f442e2c6c405f0edb36c695079d7dfb813c3c2fb9705
 size 4783