genejalston
commited on
Commit
•
28eadf7
1
Parent(s):
81d78b2
Training in progress, step 500
Browse files- config.json +21 -11
- model.safetensors +1 -1
config.json
CHANGED
@@ -1,16 +1,15 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"
|
4 |
-
"activation_dropout": 0.0,
|
5 |
"activation_function": "gelu",
|
6 |
"add_bias_logits": false,
|
7 |
"add_final_layer_norm": false,
|
8 |
"architectures": [
|
9 |
"BartForConditionalGeneration"
|
10 |
],
|
11 |
-
"attention_dropout": 0.
|
12 |
"bos_token_id": 0,
|
13 |
-
"classif_dropout": 0.
|
14 |
"classifier_dropout": 0.0,
|
15 |
"d_model": 1024,
|
16 |
"decoder_attention_heads": 16,
|
@@ -19,12 +18,15 @@
|
|
19 |
"decoder_layers": 12,
|
20 |
"decoder_start_token_id": 2,
|
21 |
"dropout": 0.1,
|
|
|
22 |
"encoder_attention_heads": 16,
|
23 |
"encoder_ffn_dim": 4096,
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
"encoder_layers": 12,
|
26 |
"eos_token_id": 2,
|
|
|
27 |
"forced_eos_token_id": 2,
|
|
|
28 |
"id2label": {
|
29 |
"0": "LABEL_0",
|
30 |
"1": "LABEL_1",
|
@@ -39,22 +41,30 @@
|
|
39 |
},
|
40 |
"max_position_embeddings": 1024,
|
41 |
"model_type": "bart",
|
|
|
42 |
"normalize_before": false,
|
43 |
-
"
|
44 |
"num_hidden_layers": 12,
|
45 |
-
"output_past": false,
|
46 |
"pad_token_id": 1,
|
47 |
-
"prefix": " ",
|
48 |
"scale_embedding": false,
|
49 |
-
"static_position_embeddings": false,
|
50 |
"task_specific_params": {
|
51 |
"summarization": {
|
52 |
-
"
|
|
|
|
|
|
|
|
|
|
|
53 |
"length_penalty": 2.0,
|
54 |
"max_length": 142,
|
55 |
"min_length": 56,
|
56 |
-
"no_repeat_ngram_size": 3,
|
57 |
"num_beams": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
},
|
60 |
"torch_dtype": "float32",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
3 |
+
"activation_dropout": 0.1,
|
|
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
6 |
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
"BartForConditionalGeneration"
|
9 |
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
"classifier_dropout": 0.0,
|
14 |
"d_model": 1024,
|
15 |
"decoder_attention_heads": 16,
|
|
|
18 |
"decoder_layers": 12,
|
19 |
"decoder_start_token_id": 2,
|
20 |
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
"encoder_attention_heads": 16,
|
23 |
"encoder_ffn_dim": 4096,
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
"encoder_layers": 12,
|
26 |
"eos_token_id": 2,
|
27 |
+
"forced_bos_token_id": 0,
|
28 |
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
"id2label": {
|
31 |
"0": "LABEL_0",
|
32 |
"1": "LABEL_1",
|
|
|
41 |
},
|
42 |
"max_position_embeddings": 1024,
|
43 |
"model_type": "bart",
|
44 |
+
"no_repeat_ngram_size": 3,
|
45 |
"normalize_before": false,
|
46 |
+
"num_beams": 4,
|
47 |
"num_hidden_layers": 12,
|
|
|
48 |
"pad_token_id": 1,
|
|
|
49 |
"scale_embedding": false,
|
|
|
50 |
"task_specific_params": {
|
51 |
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
"length_penalty": 2.0,
|
59 |
"max_length": 142,
|
60 |
"min_length": 56,
|
|
|
61 |
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
}
|
69 |
},
|
70 |
"torch_dtype": "float32",
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625426996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:394dfb894024b92bbbfb1b862531d2d6e28d88e7bc8c60fa638c57e06c43164d
|
3 |
size 1625426996
|