Training in progress, epoch 1
Browse files- config.json +16 -14
- pytorch_model.bin +2 -2
- runs/Mar13_11-39-59_teesta/events.out.tfevents.1710310231.teesta.27037.0 +2 -2
- runs/Mar13_11-39-59_teesta/events.out.tfevents.1710315006.teesta.27037.1 +3 -0
- runs/Mar13_13-37-38_teesta/events.out.tfevents.1710317271.teesta.21161.0 +3 -0
- special_tokens_map.json +5 -13
- tokenizer.json +2 -2
- tokenizer_config.json +9 -15
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,15 +1,14 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
-
"
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size":
|
13 |
"id2label": {
|
14 |
"0": "center",
|
15 |
"1": "left",
|
@@ -17,25 +16,28 @@
|
|
17 |
"3": "roundup"
|
18 |
},
|
19 |
"initializer_range": 0.02,
|
20 |
-
"intermediate_size":
|
21 |
"label2id": {
|
22 |
"center": "0",
|
23 |
"left": "1",
|
24 |
"right": "2",
|
25 |
"roundup": "3"
|
26 |
},
|
27 |
-
"layer_norm_eps": 1e-
|
28 |
-
"max_position_embeddings":
|
29 |
-
"model_type": "
|
30 |
-
"num_attention_heads":
|
31 |
"num_hidden_layers": 12,
|
32 |
-
"
|
33 |
-
"pad_token_id": 1,
|
34 |
"position_embedding_type": "absolute",
|
35 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
36 |
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.30.2",
|
38 |
-
"type_vocab_size":
|
39 |
"use_cache": true,
|
40 |
-
"vocab_size":
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/electra-small-discriminator",
|
3 |
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
+
"embedding_size": 128,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 256,
|
12 |
"id2label": {
|
13 |
"0": "center",
|
14 |
"1": "left",
|
|
|
16 |
"3": "roundup"
|
17 |
},
|
18 |
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 1024,
|
20 |
"label2id": {
|
21 |
"center": "0",
|
22 |
"left": "1",
|
23 |
"right": "2",
|
24 |
"roundup": "3"
|
25 |
},
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"max_position_embeddings": 512,
|
28 |
+
"model_type": "electra",
|
29 |
+
"num_attention_heads": 4,
|
30 |
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 0,
|
|
|
32 |
"position_embedding_type": "absolute",
|
33 |
"problem_type": "single_label_classification",
|
34 |
+
"summary_activation": "gelu",
|
35 |
+
"summary_last_dropout": 0.1,
|
36 |
+
"summary_type": "first",
|
37 |
+
"summary_use_proj": true,
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.30.2",
|
40 |
+
"type_vocab_size": 2,
|
41 |
"use_cache": true,
|
42 |
+
"vocab_size": 30522
|
43 |
}
|
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:f2f3b1d0f0102d9d6e9d17d6bae4919368f58c205d7f0fadfdef5da41b829235
|
3 |
+
size 54273341
|
runs/Mar13_11-39-59_teesta/events.out.tfevents.1710310231.teesta.27037.0
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 sha256:0f90332cda70b2df147c276743f4b5b3179f23b04f351990a550e3dafb235b89
|
3 |
+
size 10218
|
runs/Mar13_11-39-59_teesta/events.out.tfevents.1710315006.teesta.27037.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6f2d084c9e771216506e76b088e4a4fa1ae34c6e620dd4fd8adc26a7a97860d
|
3 |
+
size 512
|
runs/Mar13_13-37-38_teesta/events.out.tfevents.1710317271.teesta.21161.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae3d00ac9b03fc44f2ee7a74b6d6afaa6b56132d92ce660cb54d927cfec5736d
|
3 |
+
size 4753
|
special_tokens_map.json
CHANGED
@@ -1,15 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
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 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer.json
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:d3017b453f25baee53b6d06e915bd42bde81de83e478b8e2b1e2760404026dff
|
3 |
+
size 711551
|
tokenizer_config.json
CHANGED
@@ -1,19 +1,13 @@
|
|
1 |
{
|
2 |
-
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
-
"cls_token": "
|
5 |
-
"
|
6 |
-
"mask_token":
|
7 |
-
"__type": "AddedToken",
|
8 |
-
"content": "<mask>",
|
9 |
-
"lstrip": true,
|
10 |
-
"normalized": true,
|
11 |
-
"rstrip": false,
|
12 |
-
"single_word": false
|
13 |
-
},
|
14 |
"model_max_length": 512,
|
15 |
-
"pad_token": "
|
16 |
-
"sep_token": "
|
17 |
-
"
|
18 |
-
"
|
|
|
|
|
19 |
}
|
|
|
1 |
{
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "ElectraTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b9e1948454a0ec7e7534a99c4279890913056fcee3e35979e48ee87c2bef465
|
3 |
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|