Training in progress, epoch 1

README.md

@@ -1,6 +1,7 @@
 ---
+library_name: transformers
 license: mit
-base_model: roberta-base
+base_model: roberta-large
 tags:
 - generated_from_trainer
 metrics:
@@ -9,22 +10,22 @@ metrics:
 - recall
 - f1
 model-index:
-- name: Neuro_binary
+- name: Agree_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. -->
 
-# Neuro_binary
+# Agree_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: 0.5428
-- Accuracy: 0.7274
-- Precision: 0.7614
-- Recall: 0.7065
-- F1: 0.7329
+- Loss: 0.5568
+- Accuracy: 0.7523
+- Precision: 0.7235
+- Recall: 0.7924
+- F1: 0.7564
 
 ## Model description
 
@@ -49,19 +50,20 @@ 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   | 135  | 0.5469          | 0.7265   | 0.7835    | 0.6678 | 0.7211 |
-| No log        | 2.0   | 270  | 0.5428          | 0.7274   | 0.7614    | 0.7065 | 0.7329 |
+| No log        | 1.0   | 136  | 0.5167          | 0.7606   | 0.7309    | 0.8019 | 0.7648 |
+| No log        | 2.0   | 272  | 0.4849          | 0.7662   | 0.7429    | 0.7924 | 0.7668 |
+| No log        | 3.0   | 408  | 0.5568          | 0.7523   | 0.7235    | 0.7924 | 0.7564 |
 
 
 ### Framework versions
 
-- Transformers 4.43.3
-- Pytorch 2.4.0
-- Datasets 2.20.0
+- Transformers 4.44.1
+- Pytorch 1.11.0
+- Datasets 2.12.0
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "roberta-large",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -9,19 +9,19 @@
   "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",
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
+  "transformers_version": "4.44.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0028144f7a928a7771a19ce6be24c066da49db8258e2f155f3f72fb704c413e4
-size 498612824
+oid sha256:18ff11dbd3c357f09e7cb50dfc7680f3e34bddb29eec3a087c73921fe6a6aedc
+size 1421495416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef82f1b5e188744205128c0c924146804aaaf4be64ba43e35c80dbbc1d5d2fc
-size 5176
+oid sha256:71559dde15a6bd4ad2cdc7b92df89de2534f1993ee03aceb76f5ce22b34e94a0
+size 4719