add: best model
Browse files- .gitattributes +0 -1
- last-checkpoint/generation_config.json → generation_config.json +0 -0
- last-checkpoint/config.json +0 -75
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scaler.pt +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/special_tokens_map.json +0 -15
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -15
- last-checkpoint/trainer_state.json +0 -3
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.json +0 -0
- pytorch_model.bin +1 -1
- runs/Jul12_21-40-00_social-medium-3/events.out.tfevents.1689198019.social-medium-3.14337.0 +2 -2
.gitattributes
CHANGED
@@ -34,4 +34,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
validation_predictions.txt filter=lfs diff=lfs merge=lfs -text
|
37 |
-
last-checkpoint/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
validation_predictions.txt filter=lfs diff=lfs merge=lfs -text
|
|
last-checkpoint/generation_config.json → generation_config.json
RENAMED
File without changes
|
last-checkpoint/config.json
DELETED
@@ -1,75 +0,0 @@
|
|
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": "4.29.2",
|
73 |
-
"use_cache": true,
|
74 |
-
"vocab_size": 50265
|
75 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:af00a9649b6595bf110dbc20b455e39d92e907047e86b618f47bf30fe5f03fbd
|
3 |
-
size 1115579397
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:c10883eaaf24456fca8c5426d3a322f4f81001b7319cd4f049353cf1c2923335
|
3 |
-
size 557971229
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:15fec3042f715a8f976b8c5d2b5dcf03e34725d7c28e6cbf6d5292a17b6a9317
|
3 |
-
size 14511
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:0175c1ad5cbb70b6febb8ff11e11e82f390277be16a31a9baee2a08f3963b570
|
3 |
-
size 557
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:07d8d876101deed82be0a94b662ee512a747c1a0abae8693137289344b31b7ac
|
3 |
-
size 627
|
|
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
@@ -1,15 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
-
"unk_token": "<unk>"
|
15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
DELETED
@@ -1,15 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": "<s>",
|
4 |
-
"clean_up_tokenization_spaces": true,
|
5 |
-
"cls_token": "<s>",
|
6 |
-
"eos_token": "</s>",
|
7 |
-
"errors": "replace",
|
8 |
-
"mask_token": "<mask>",
|
9 |
-
"model_max_length": 1024,
|
10 |
-
"pad_token": "<pad>",
|
11 |
-
"sep_token": "</s>",
|
12 |
-
"tokenizer_class": "BartTokenizer",
|
13 |
-
"trim_offsets": true,
|
14 |
-
"unk_token": "<unk>"
|
15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:3c0e9abd1c5a236f78a788d2a92f4e4e9f621c4f76ab328f17e0ee088f23aef6
|
3 |
-
size 16570305
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:4e6123892909258c7be033aa869e6e269fa28e30d1e3a9da83d97500f7064bf8
|
3 |
-
size 4347
|
|
|
|
|
|
|
|
last-checkpoint/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557971229
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34bd0ec2f4b8e2297b869aa7196313b80b0a1b6295bc3f3ce9f6aa4098b616d6
|
3 |
size 557971229
|
runs/Jul12_21-40-00_social-medium-3/events.out.tfevents.1689198019.social-medium-3.14337.0
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:fd4291fe30b87c2c663e95c91b20ce0f25bd62e0ac9c0c76f1eac96d41911201
|
3 |
+
size 22355363
|