Training in progress epoch 0

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: dccuchile/distilbert-base-spanish-uncased
+base_model: dccuchile/distilbert-base-spanish-uncased-finetuned-qa-mlqa
 tags:
 - generated_from_keras_callback
 model-index:
@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # 0xJCarlos/QuestionAnswer_ESP
 
-This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on an unknown dataset.
+This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased-finetuned-qa-mlqa](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased-finetuned-qa-mlqa) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.8875
-- Validation Loss: 3.0355
-- Epoch: 4
+- Train Loss: 1.8953
+- Validation Loss: 1.7447
+- Epoch: 0
 
 ## Model description
 
@@ -42,11 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 4.1940     | 3.3924          | 0     |
-| 3.1417     | 3.0355          | 1     |
-| 2.8924     | 3.0355          | 2     |
-| 2.8880     | 3.0355          | 3     |
-| 2.8875     | 3.0355          | 4     |
+| 1.8953     | 1.7447          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dccuchile/distilbert-base-spanish-uncased",
+  "_name_or_path": "dccuchile/distilbert-base-spanish-uncased-finetuned-qa-mlqa",
   "activation": "gelu",
   "architectures": [
     "DistilBertForQuestionAnswering"

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ebace1b523fdef282b0ab3d51890b4a6a2f1cd195f0f0fce611be87c9e3542
+oid sha256:9558238310bc09a82d4ab5542d5e0779ac2b720555c2d470c74b873d249f635f
 size 267058152