Training in progress, epoch 1
Browse files- config.json +44 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"BartForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.0,
|
10 |
+
"d_model": 768,
|
11 |
+
"decoder_attention_heads": 6,
|
12 |
+
"decoder_ffn_dim": 768,
|
13 |
+
"decoder_layerdrop": 0.0,
|
14 |
+
"decoder_layers": 6,
|
15 |
+
"decoder_start_token_id": 1,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 6,
|
18 |
+
"encoder_ffn_dim": 768,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_layers": 6,
|
21 |
+
"eos_token_id": 1,
|
22 |
+
"forced_eos_token_id": 1,
|
23 |
+
"id2label": {
|
24 |
+
"0": "LABEL_0",
|
25 |
+
"1": "LABEL_1",
|
26 |
+
"2": "LABEL_2"
|
27 |
+
},
|
28 |
+
"init_std": 0.02,
|
29 |
+
"is_encoder_decoder": true,
|
30 |
+
"label2id": {
|
31 |
+
"LABEL_0": 0,
|
32 |
+
"LABEL_1": 1,
|
33 |
+
"LABEL_2": 2
|
34 |
+
},
|
35 |
+
"max_position_embeddings": 1000,
|
36 |
+
"model_type": "bart",
|
37 |
+
"num_hidden_layers": 6,
|
38 |
+
"pad_token_id": 3,
|
39 |
+
"scale_embedding": false,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.39.0",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 55000
|
44 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1182d92e3d4cfe9319276af642442af4834f9db498c65323e08c4cfbe3ed7b8
|
3 |
+
size 402350000
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a3118d978dc80b9c8bdd88ff335b03f7204faa1795324644b24a94f77fff19f
|
3 |
+
size 4920
|