Upload 10 files

.gitattributes

@@ -1,3 +1,3 @@
+logs/train/events.out.tfevents.1693499425.NOTEBOOK-PABLO.14724.2.v2 filter=lfs diff=lfs merge=lfs -text
+logs/validation/events.out.tfevents.1693499524.NOTEBOOK-PABLO.14724.3.v2 filter=lfs diff=lfs merge=lfs -text
 tf_model.h5 filter=lfs diff=lfs merge=lfs -text
-logs/train/events.out.tfevents.1693496252.NOTEBOOK-PABLO.14724.0.v2 filter=lfs diff=lfs merge=lfs -text
-logs/validation/events.out.tfevents.1693496334.NOTEBOOK-PABLO.14724.1.v2 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -14,12 +14,12 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es](https://huggingface.co/mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.8897
+- Train Loss: 3.7249
 - Train End Logits Accuracy: 0.1667
-- Train Start Logits Accuracy: 0.5
-- Validation Loss: 3.3441
-- Validation End Logits Accuracy: 0.1667
-- Validation Start Logits Accuracy: 0.6667
+- Train Start Logits Accuracy: 0.1667
+- Validation Loss: 3.2576
+- Validation End Logits Accuracy: 0.0
+- Validation Start Logits Accuracy: 0.8333
 - Epoch: 1
 
 ## Model description
@@ -46,8 +46,8 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
-| 4.4853     | 0.1667                    | 0.5                         | 3.4503          | 0.1667                         | 0.5                              | 0     |
-| 3.8897     | 0.1667                    | 0.5                         | 3.3441          | 0.1667                         | 0.6667                           | 1     |
+| 4.7073     | 0.1667                    | 0.1667                      | 3.5715          | 0.0                            | 0.8333                           | 0     |
+| 3.7249     | 0.1667                    | 0.1667                      | 3.2576          | 0.0                            | 0.8333                           | 1     |
 
 
 ### Framework versions

config.json

@@ -11,7 +11,9 @@
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
+  "max_length": 128,
   "max_position_embeddings": 512,
+  "min_length": 128,
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5436a4cc88d0a64a4e541d20fcb1700cf9de2880f0d9ee0682d62933357ae1ac
+oid sha256:d554bba3b1dd86a20813666a4481976d27ec7fb7792035277c9d2d01c40b4b36
 size 437320656