Model save

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0156
-- Precision: 0.6569
-- Recall: 0.4290
-- F1: 0.5190
-- Accuracy: 0.9959
+- Loss: 0.0490
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.9893
 
 ## Model description
 
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 137  | 0.0394          | 0.0419    | 0.0191 | 0.0263 | 0.9893   |
-| No log        | 2.0   | 274  | 0.0195          | 0.5622    | 0.3825 | 0.4553 | 0.9956   |
-| No log        | 3.0   | 411  | 0.0156          | 0.6569    | 0.4290 | 0.5190 | 0.9959   |
+| No log        | 1.0   | 77   | 0.0905          | 0.0       | 0.0    | 0.0    | 0.9829   |
+| No log        | 2.0   | 154  | 0.0540          | 0.02      | 0.0068 | 0.0101 | 0.9885   |
+| No log        | 3.0   | 231  | 0.0490          | 0.0       | 0.0    | 0.0    | 0.9893   |
 
 
 ### Framework versions
 
-- Transformers 4.34.1
+- Transformers 4.35.0
 - Pytorch 2.1.0+cu118
 - Datasets 2.14.6
 - Tokenizers 0.14.1

config.json

@@ -55,7 +55,7 @@
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
+  "transformers_version": "4.35.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 29794

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c90050d3e7e457f3c338b1c6f4e287d653b2f2949a71bacd617a0c5be34420
+size 433393508

runs/Nov03_18-01-36_c6b92884a012/events.out.tfevents.1699034525.c6b92884a012.1786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006c44739a9423eecd4a4b08dcf4bcd4721811677ae863004743357cc5310d06
+size 6781

runs/Nov03_18-01-36_c6b92884a012/events.out.tfevents.1699034767.c6b92884a012.1786.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fd2163ed07c85344292bfe8e6a4dd22ecb91bc5b873a4910bbacdc52c26645
+size 560

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7229dc18020dda80c91c9577fe1f5cfb9d63760b2fcb4c4c89f8fb8fa34e26e
-size 4536
+oid sha256:43b6a07fed565f39315f7f391b3e5d77064af072b4810e7639d31f779e049d87
+size 4600