Upload TFBertForMaskedLM
Browse files- README.md +5 -6
- config.json +10 -11
- tf_model.h5 +2 -2
README.md
CHANGED
|
@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# tf_roberta_v1
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Train Loss:
|
| 18 |
-
- Validation Loss:
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -42,8 +42,7 @@ The following hyperparameters were used during training:
|
|
| 42 |
|
| 43 |
| Train Loss | Validation Loss | Epoch |
|
| 44 |
|:----------:|:---------------:|:-----:|
|
| 45 |
-
|
|
| 46 |
-
| 2.1033 | 1.8383 | 1 |
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
|
|
|
| 12 |
|
| 13 |
# tf_roberta_v1
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 3.0890
|
| 18 |
+
- Validation Loss: 3.0774
|
| 19 |
+
- Epoch: 0
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 42 |
|
| 43 |
| Train Loss | Validation Loss | Epoch |
|
| 44 |
|:----------:|:---------------:|:-----:|
|
| 45 |
+
| 3.0890 | 3.0774 | 0 |
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,26 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"bos_token_id": 0,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
-
"
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 3072,
|
| 15 |
-
"layer_norm_eps": 1e-
|
| 16 |
-
"max_position_embeddings":
|
| 17 |
-
"model_type": "
|
| 18 |
"num_attention_heads": 12,
|
| 19 |
-
"num_hidden_layers":
|
| 20 |
-
"pad_token_id":
|
| 21 |
"position_embedding_type": "absolute",
|
| 22 |
"transformers_version": "4.27.2",
|
| 23 |
-
"type_vocab_size":
|
| 24 |
"use_cache": true,
|
| 25 |
-
"vocab_size":
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
"position_embedding_type": "absolute",
|
| 21 |
"transformers_version": "4.27.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
"use_cache": true,
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:473beab816282e4b023332ad8ded564cd81dfdacc89a40a9a7ef25610fed5574
|
| 3 |
+
size 533687680
|