Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +35 -0
- logs/1678030036.6017163/events.out.tfevents.1678030036.serv-3317.65033.25 +3 -0
- logs/events.out.tfevents.1678030036.serv-3317.65033.24 +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gokuls/bert_12_layer_model_v2",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"finetuning_task": "mnli",
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "entailment",
|
14 |
+
"1": "neutral",
|
15 |
+
"2": "contradiction"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"contradiction": 2,
|
20 |
+
"entailment": 0,
|
21 |
+
"neutral": 1
|
22 |
+
},
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "hybridbert",
|
25 |
+
"n_heads": 12,
|
26 |
+
"n_layers": 12,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"qa_dropout": 0.1,
|
30 |
+
"seq_classif_dropout": 0.2,
|
31 |
+
"sinusoidal_pos_embds": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.26.1",
|
34 |
+
"vocab_size": 30522
|
35 |
+
}
|
logs/1678030036.6017163/events.out.tfevents.1678030036.serv-3317.65033.25
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:026d4caa4b49f46c0e8430d6bee5630df47b47259add18576dd7cc1cd4ef89db
|
3 |
+
size 5684
|
logs/events.out.tfevents.1678030036.serv-3317.65033.24
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beac4b69d19a657cddf4d2b0b24372cf33dbbb9edc7cfe8814052208306e3e37
|
3 |
+
size 4409
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b62bda8c55d2da699d80e922d75b3b82018791f304863984ff039f12bd4d602e
|
3 |
+
size 419783693
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "bert-base-uncased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "BertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a080ec7cc0f9030953804f6f8939d3b8e80170a82fc5b71de1e22d1b405ead9
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|