PoptropicaSahil
commited on
Commit
·
c27814d
1
Parent(s):
43dd154
Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +34 -0
- pytorch_model.bin +3 -0
- runs/Oct30_10-04-22_bc5c7503f97b/1667124274.52672/events.out.tfevents.1667124274.bc5c7503f97b.77.1 +3 -0
- runs/Oct30_10-04-22_bc5c7503f97b/events.out.tfevents.1667124274.bc5c7503f97b.77.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ai4bharat/indic-bert",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"inner_group_num": 1,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "albert",
|
22 |
+
"net_structure_type": 0,
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_groups": 1,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"num_memory_blocks": 0,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.13.0",
|
32 |
+
"type_vocab_size": 2,
|
33 |
+
"vocab_size": 200000
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:244e4d371b2b7ef392614e3a6e63e68be86c019b553a83168c9b53fd03343abe
|
3 |
+
size 133795537
|
runs/Oct30_10-04-22_bc5c7503f97b/1667124274.52672/events.out.tfevents.1667124274.bc5c7503f97b.77.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3e274ba8125f087c4412c8d0100c588a2dc5f537fd56593ad32b2c636cef660
|
3 |
+
size 4778
|
runs/Oct30_10-04-22_bc5c7503f97b/events.out.tfevents.1667124274.bc5c7503f97b.77.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ae2ac2822f15d497a5048e9ce17b7e45021d7113dd6e616cc6f51e45f401bef
|
3 |
+
size 3459
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "lowercase": false, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/290471f6a01c9af0dd0bcf02112dc77b9b0aee820ebb1fb023c96ac2dda9d8ef.750293617705dd39d21eef1e163d80ca5b23e1a0ec507fff24a087c44632142c", "name_or_path": "google/muril-base-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5303cdc8c7224a5ab918fe7dbeb91fa9f6330eecc397af04a1e8158fcae726d0
|
3 |
+
size 2991
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|