Upload 10 files
Browse files- config.json +43 -24
- generation_config.json +9 -5
- optimizer.pt +2 -2
- pytorch_model.bin +2 -2
- rng_state.pth +2 -2
- scaler.pt +1 -1
- scheduler.pt +1 -1
- tokenizer.json +0 -0
- trainer_state.json +0 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,56 +1,75 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation_dropout": 0.
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
6 |
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
"BartForConditionalGeneration"
|
9 |
],
|
10 |
-
"attention_dropout": 0.
|
11 |
-
"
|
12 |
-
"bos_token_id": 1,
|
13 |
"classif_dropout": 0.1,
|
14 |
-
"classifier_dropout": 0.
|
15 |
"d_model": 768,
|
16 |
-
"decoder_attention_heads":
|
17 |
"decoder_ffn_dim": 3072,
|
18 |
"decoder_layerdrop": 0.0,
|
19 |
"decoder_layers": 6,
|
20 |
-
"decoder_start_token_id":
|
21 |
-
"do_blenderbot_90_layernorm": false,
|
22 |
"dropout": 0.1,
|
23 |
-
"
|
|
|
24 |
"encoder_ffn_dim": 3072,
|
25 |
"encoder_layerdrop": 0.0,
|
26 |
"encoder_layers": 6,
|
27 |
-
"eos_token_id":
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"forced_eos_token_id": 1,
|
31 |
"gradient_checkpointing": false,
|
32 |
"id2label": {
|
33 |
-
"0": "
|
34 |
-
"1": "
|
|
|
35 |
},
|
36 |
"init_std": 0.02,
|
37 |
"is_encoder_decoder": true,
|
38 |
-
"kobart_version": 2.0,
|
39 |
"label2id": {
|
40 |
-
"
|
41 |
-
"
|
|
|
42 |
},
|
43 |
-
"max_position_embeddings":
|
44 |
"model_type": "bart",
|
|
|
45 |
"normalize_before": false,
|
46 |
"normalize_embedding": true,
|
|
|
47 |
"num_hidden_layers": 6,
|
48 |
-
"pad_token_id":
|
49 |
"scale_embedding": false,
|
50 |
-
"
|
51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
"torch_dtype": "float32",
|
53 |
"transformers_version": "4.29.1",
|
54 |
"use_cache": true,
|
55 |
-
"vocab_size":
|
56 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/bart-base",
|
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": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
"decoder_ffn_dim": 3072,
|
17 |
"decoder_layerdrop": 0.0,
|
18 |
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
|
|
20 |
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
"encoder_ffn_dim": 3072,
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
"encoder_layers": 6,
|
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",
|
33 |
+
"2": "LABEL_2"
|
34 |
},
|
35 |
"init_std": 0.02,
|
36 |
"is_encoder_decoder": true,
|
|
|
37 |
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1,
|
40 |
+
"LABEL_2": 2
|
41 |
},
|
42 |
+
"max_position_embeddings": 1024,
|
43 |
"model_type": "bart",
|
44 |
+
"no_repeat_ngram_size": 3,
|
45 |
"normalize_before": false,
|
46 |
"normalize_embedding": true,
|
47 |
+
"num_beams": 4,
|
48 |
"num_hidden_layers": 6,
|
49 |
+
"pad_token_id": 1,
|
50 |
"scale_embedding": false,
|
51 |
+
"task_specific_params": {
|
52 |
+
"summarization": {
|
53 |
+
"length_penalty": 1.0,
|
54 |
+
"max_length": 128,
|
55 |
+
"min_length": 12,
|
56 |
+
"num_beams": 4
|
57 |
+
},
|
58 |
+
"summarization_cnn": {
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"num_beams": 4
|
63 |
+
},
|
64 |
+
"summarization_xsum": {
|
65 |
+
"length_penalty": 1.0,
|
66 |
+
"max_length": 62,
|
67 |
+
"min_length": 11,
|
68 |
+
"num_beams": 6
|
69 |
+
}
|
70 |
+
},
|
71 |
"torch_dtype": "float32",
|
72 |
"transformers_version": "4.29.1",
|
73 |
"use_cache": true,
|
74 |
+
"vocab_size": 50265
|
75 |
}
|
generation_config.json
CHANGED
@@ -1,9 +1,13 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"decoder_start_token_id":
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
|
|
|
|
|
|
|
|
8 |
"transformers_version": "4.29.1"
|
9 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"forced_bos_token_id": 0,
|
8 |
+
"forced_eos_token_id": 2,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
+
"pad_token_id": 1,
|
12 |
"transformers_version": "4.29.1"
|
13 |
}
|
optimizer.pt
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 sha256:7f6ab35be500545856987fe9d586dfeb18508b3b62ed40e43aab2e0b957fa668
|
3 |
+
size 1115515845
|
pytorch_model.bin
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 sha256:80aeb3da6af94ab828b0739cd6ecdababb0e1ee5b8cdeb02627314b4624a0c00
|
3 |
+
size 557971229
|
rng_state.pth
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 sha256:20582476337d0a64b36e4d7b43445d716c5c0a6e593283ae5fcfd56db0a2afe5
|
3 |
+
size 14575
|
scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffd239d2716132c3e5a88fbffe2943138db630758010917213dc7a42bdcedde5
|
3 |
size 557
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d57f954e769bfbe2797ee88375209be15bc3da362765aad40f7d1ba37bfa430
|
3 |
size 627
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:922a1055c14319efab3f72297cd15e331cfd573ddae895964e8811525514d304
|
3 |
size 4027
|