End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: mit
-base_model: LIAMF-USP/roberta-large-finetuned-race
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # roberta-mqa
 
-This model is a fine-tuned version of [LIAMF-USP/roberta-large-finetuned-race](https://huggingface.co/LIAMF-USP/roberta-large-finetuned-race) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6094
-- Accuracy: 0.2120
-- F1: 0.1945
-- Precision: 0.2027
-- Recall: 0.2057
+- Loss: 1.4631
+- Accuracy: 0.3793
+- F1: 0.3774
+- Precision: 0.3819
+- Recall: 0.3760
 
 ## Model description
 
@@ -44,8 +42,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 16
+- train_batch_size: 28
+- eval_batch_size: 28
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -54,11 +52,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 1.6124        | 1.0   | 3712  | 1.6094          | 0.2079   | 0.1810 | 0.1981    | 0.2006 |
-| 1.613         | 2.0   | 7424  | 1.6094          | 0.2077   | 0.0871 | 0.1713    | 0.1975 |
-| 1.61          | 3.0   | 11136 | 1.6094          | 0.2120   | 0.1945 | 0.2027    | 0.2057 |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 1.5076        | 1.0   | 1061 | 1.4901          | 0.3372   | 0.3328 | 0.3366    | 0.3321 |
+| 1.4244        | 2.0   | 2122 | 1.4584          | 0.3594   | 0.3560 | 0.3615    | 0.3545 |
+| 1.3553        | 3.0   | 3183 | 1.4631          | 0.3793   | 0.3774 | 0.3819    | 0.3760 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355975a656b3dd01f2004661fdb8602866177f506299c5266560d02baa036844
+oid sha256:a69d4df6a1517a588ac45ca0ba0ca3dffc7ce35a95e241e259c47da914da8517
 size 1421491284

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 256
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -48,10 +48,17 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 128,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1586777c2c3d51f3d19369f0acd98471143cffee8b778dc238892df728228d
+oid sha256:29833ff135368169c490c02f10b2e299fbd028f85b3ec2ea7cc8875ffdebb575
 size 4920