Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +28 -0
- logs/1677660835.4229982/events.out.tfevents.1677660835.kyoto.1079667.1 +3 -0
- logs/events.out.tfevents.1677660835.kyoto.1079667.0 +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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"label2id": {
|
| 13 |
+
"acceptable": 1,
|
| 14 |
+
"unacceptable": 0
|
| 15 |
+
},
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"model_type": "hybridbert",
|
| 18 |
+
"n_heads": 12,
|
| 19 |
+
"n_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"qa_dropout": 0.1,
|
| 23 |
+
"seq_classif_dropout": 0.2,
|
| 24 |
+
"sinusoidal_pos_embds": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.26.1",
|
| 27 |
+
"vocab_size": 30522
|
| 28 |
+
}
|
logs/1677660835.4229982/events.out.tfevents.1677660835.kyoto.1079667.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4905f4ec3fae3b1efe1bcd354150ff8db66b9150aee2f55bf83d08487014b41
|
| 3 |
+
size 5684
|
logs/events.out.tfevents.1677660835.kyoto.1079667.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81c27bc4de9e4a02e1f1c861ce4f426741e0c4923ada6dabf0c92854aca4b43a
|
| 3 |
+
size 4275
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:119e20d3f77abbc4880c67e0c89d5ea8ae55ae3b0a2ecc3fe4191a9ef7dc61d3
|
| 3 |
+
size 419780621
|
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 sha256:9c04f959f919b30a0708d6cb7ec7ec1f3254acc5b8a5f6c2e7d31870b5643a81
|
| 3 |
+
size 3515
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|