test_linsearch_only_abstract

README.md

@@ -6,9 +6,6 @@ tags:
 - generated_from_trainer
 metrics:
 - accuracy
-- precision
-- recall
-- f1
 model-index:
 - name: test_linsearch_only_abstract
   results: []
@@ -21,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1038
-- Accuracy: 0.6548
-- Precision: 0.6548
-- Recall: 0.6548
-- F1: 0.6548
+- Loss: 1.0720
+- Accuracy: 0.6632
+- F1 Macro: 0.5884
+- Precision Macro: 0.5996
+- Recall Macro: 0.5849
 
 ## Model description
 
@@ -45,23 +42,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
+- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 1.19          | 1.0   | 5122  | 1.1851          | 0.6284   | 0.6284    | 0.6284 | 0.6284 |
-| 1.0146        | 2.0   | 10244 | 1.1038          | 0.6548   | 0.6548    | 0.6548 | 0.6548 |
-| 0.8889        | 3.0   | 15366 | 1.1175          | 0.6511   | 0.6511    | 0.6511 | 0.6511 |
-| 0.7382        | 4.0   | 20488 | 1.1474          | 0.6537   | 0.6537    | 0.6537 | 0.6537 |
-| 0.6511        | 5.0   | 25610 | 1.1825          | 0.6512   | 0.6512    | 0.6512 | 0.6512 |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|
+| 1.2733        | 1.0   | 2466  | 1.1829          | 0.6367   | 0.5383   | 0.5442          | 0.5569       |
+| 1.0527        | 2.0   | 4932  | 1.0834          | 0.6557   | 0.5651   | 0.5747          | 0.5635       |
+| 0.9238        | 3.0   | 7398  | 1.0705          | 0.6626   | 0.5866   | 0.5963          | 0.5860       |
+| 0.7971        | 4.0   | 9864  | 1.0720          | 0.6632   | 0.5884   | 0.5996          | 0.5849       |
+| 0.6842        | 5.0   | 12330 | 1.0961          | 0.6603   | 0.5846   | 0.5892          | 0.5834       |
 
 
 ### Framework versions

config.json

@@ -38,8 +38,7 @@
     "25": "LABEL_25",
     "26": "LABEL_26",
     "27": "LABEL_27",
-    "28": "LABEL_28",
-    "29": "LABEL_29"
+    "28": "LABEL_28"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -66,7 +65,6 @@
     "LABEL_26": 26,
     "LABEL_27": 27,
     "LABEL_28": 28,
-    "LABEL_29": 29,
     "LABEL_3": 3,
     "LABEL_4": 4,
     "LABEL_5": 5,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f06d964151b65398ad31c7d76fc173aab14c6eb86ba309c2babaed3c2ff539b7
-size 1112291136
+oid sha256:5568aa04e5fd949423e0d323c7e8a0b52c6e09f463510b8f064a62ff2f65e5a7
+size 1112288060

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4827ac23c19ba12856a86529592fcd4cdec2b59399e03de606f059100b56b571
+oid sha256:358ca8053e5fb0f635f17ddc7729bced42c0657fcd96090451d700b817f12c45
 size 5304