Upload . with huggingface_hub
Browse files- bpe.codes +0 -0
- checkpoint-10610/config.json +34 -0
- checkpoint-10610/optimizer.pt +3 -0
- checkpoint-10610/pytorch_model.bin +3 -0
- checkpoint-10610/rng_state.pth +3 -0
- checkpoint-10610/scheduler.pt +3 -0
- checkpoint-10610/trainer_state.json +0 -0
- checkpoint-10610/training_args.bin +3 -0
- config.json +34 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-10610/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/bertweet-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "NOT ENGAGED",
|
16 |
+
"1": "ENGAGED"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"layer_norm_eps": 1e-05,
|
21 |
+
"max_position_embeddings": 130,
|
22 |
+
"model_type": "roberta",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 1,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"problem_type": "single_label_classification",
|
28 |
+
"tokenizer_class": "BertweetTokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.28.1",
|
31 |
+
"type_vocab_size": 1,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 64001
|
34 |
+
}
|
checkpoint-10610/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2cef42ea36209d7fd619d4205f367e13896c8876d6b67c4c66f554fac251644
|
3 |
+
size 1079329925
|
checkpoint-10610/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d042b48a7eb187fff472b27f73a602c2b2fc5a1da20728c06a695e57abd6b524
|
3 |
+
size 539676341
|
checkpoint-10610/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaf7ec3d584e53885d677f6188b01dbad1a9c0983c6c5aa9f6a645de58afdce6
|
3 |
+
size 14575
|
checkpoint-10610/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:609915a9b9764097c1a3c622919f28b815079a296a6cc3b6ab969e496f8ebf94
|
3 |
+
size 627
|
checkpoint-10610/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-10610/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d381448784682693057f6ae24ee4009087c7dc083eac1d812a1173f2df061868
|
3 |
+
size 3515
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/bertweet-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "NOT ENGAGED",
|
16 |
+
"1": "ENGAGED"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"layer_norm_eps": 1e-05,
|
21 |
+
"max_position_embeddings": 130,
|
22 |
+
"model_type": "roberta",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 1,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"problem_type": "single_label_classification",
|
28 |
+
"tokenizer_class": "BertweetTokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.28.1",
|
31 |
+
"type_vocab_size": 1,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 64001
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d042b48a7eb187fff472b27f73a602c2b2fc5a1da20728c06a695e57abd6b524
|
3 |
+
size 539676341
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d381448784682693057f6ae24ee4009087c7dc083eac1d812a1173f2df061868
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|