Training in progress, epoch 1

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: roberta-base
+base_model: roberta-large
 tags:
 - generated_from_trainer
 metrics:
@@ -10,22 +10,22 @@ metrics:
 - recall
 - f1
 model-index:
-- name: psychopathy_binary
+- name: machiavellianism_binary
   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. -->
 
-# psychopathy_binary
+# machiavellianism_binary
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5869
-- Accuracy: 0.7047
-- Precision: 0.7698
-- Recall: 0.4609
-- F1: 0.5766
+- Loss: 0.6000
+- Accuracy: 0.7284
+- Precision: 0.7104
+- Recall: 0.6075
+- F1: 0.6549
 
 ## Model description
 
@@ -50,14 +50,15 @@ 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 | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| No log        | 1.0   | 140  | 0.5715          | 0.6993   | 0.7254    | 0.5    | 0.5920 |
-| No log        | 2.0   | 280  | 0.5869          | 0.7047   | 0.7698    | 0.4609 | 0.5766 |
+| No log        | 1.0   | 127  | 0.5672          | 0.7284   | 0.7895    | 0.4907 | 0.6052 |
+| No log        | 2.0   | 254  | 0.6207          | 0.7195   | 0.8372    | 0.4206 | 0.5599 |
+| No log        | 3.0   | 381  | 0.6000          | 0.7284   | 0.7104    | 0.6075 | 0.6549 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "roberta-large",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -9,14 +9,14 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c446090fbfc40c39d974726a0571ddf3b51313039f2fb81f44ec235215d55fe1
-size 498612824
+oid sha256:9e30296c69ff71f2367ff5185c14195d981163908b0168c977f5d8515724df74
+size 1421495416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875820a868754a6be17cbb559a498934adfffe01c798fc71f097d50cb12547bb
+oid sha256:ded6bede6eb00bc1d58a8e1dc7e452b94a0db065fb66753494fb8d02ac6d1206
 size 4719