Commit
•
32cad2b
1
Parent(s):
1e11588
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +32 -0
- pytorch_model.bin +3 -0
- runs/Apr19_16-45-04_e6b878380328/1681922719.5602937/events.out.tfevents.1681922719.e6b878380328.24.1 +3 -0
- runs/Apr19_16-45-04_e6b878380328/events.out.tfevents.1681922719.e6b878380328.24.0 +3 -0
- runs/Apr19_16-48-17_e6b878380328/1681922904.293608/events.out.tfevents.1681922904.e6b878380328.24.3 +3 -0
- runs/Apr19_16-48-17_e6b878380328/events.out.tfevents.1681922904.e6b878380328.24.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/araelectra-base-discriminator",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 768,
|
| 9 |
+
"generator_hidden_size": 0.33333,
|
| 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-12,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"model_type": "electra",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"summary_activation": "gelu",
|
| 24 |
+
"summary_last_dropout": 0.1,
|
| 25 |
+
"summary_type": "first",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.20.1",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 64000
|
| 32 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2ad402a56109df58467cfc4efafd159985df3851f4930510b8309b455d6f553
|
| 3 |
+
size 540851117
|
runs/Apr19_16-45-04_e6b878380328/1681922719.5602937/events.out.tfevents.1681922719.e6b878380328.24.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9497d536350f078fe86435b16a5570f738f6a46ec92a42ce4e2916bf4bb891c6
|
| 3 |
+
size 5357
|
runs/Apr19_16-45-04_e6b878380328/events.out.tfevents.1681922719.e6b878380328.24.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bea6d1c4440135efcd872f5cd262ac7c5f44163ec52f04f21b449c6aca1adce
|
| 3 |
+
size 3810
|
runs/Apr19_16-48-17_e6b878380328/1681922904.293608/events.out.tfevents.1681922904.e6b878380328.24.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f10cc27060b535943b8ab4e708ff81b2f6986224d6d30d8c00570619c81b9051
|
| 3 |
+
size 5357
|
runs/Apr19_16-48-17_e6b878380328/events.out.tfevents.1681922904.e6b878380328.24.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7faac07e283393e814185b3d263ffcfbd2289453b970dc6188b993efea51e075
|
| 3 |
+
size 4759
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a80add7c7a1425b5d3f0a215053bd8b250854e5aa07fac419aedd4475aa451e3
|
| 3 |
+
size 3311
|