Training in progress, epoch 1
Browse files
config.json
CHANGED
@@ -1,25 +1,26 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
11 |
"initializer_range": 0.02,
|
|
|
|
|
12 |
"max_position_embeddings": 512,
|
13 |
-
"model_type": "
|
14 |
-
"
|
15 |
-
"
|
16 |
"pad_token_id": 0,
|
|
|
17 |
"problem_type": "single_label_classification",
|
18 |
-
"qa_dropout": 0.1,
|
19 |
-
"seq_classif_dropout": 0.2,
|
20 |
-
"sinusoidal_pos_embds": false,
|
21 |
-
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
"transformers_version": "4.37.0.dev0",
|
|
|
|
|
24 |
"vocab_size": 30522
|
25 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"architectures": [
|
3 |
+
"BertForSequenceClassification"
|
4 |
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 512,
|
11 |
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.37.0.dev0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
"vocab_size": 30522
|
26 |
}
|
logs/events.out.tfevents.1708354402.f88e78bfdce9.58471.0
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 sha256:97ee68da748620208dcf470873d3654cbebb2b12a464e151ff175db1bf8c62bc
|
3 |
+
size 10196
|
logs/events.out.tfevents.1708354931.f88e78bfdce9.58471.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2d72f5d5f256a3fda6768853f7aa6c94f0328ccd6608ea12a9a31aa1fd7f45a
|
3 |
+
size 457
|
logs/events.out.tfevents.1708355064.f88e78bfdce9.58831.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a7ea8a54c2e90a98212c4d9deb8c1fef55bb2c91363f09dc1bd7b03ecb08396
|
3 |
+
size 5180
|
model.safetensors
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 sha256:1355aa4930eb6971b675526c8ece61ec5e308c4195355259c1c07cfba71d419c
|
3 |
+
size 266339248
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74b4e8ec1dfd68ee4775f190a24c1a6f9f036aa785221b28f7f085613bea4503
|
3 |
size 4728
|