Training in progress, step 10000
Browse files- .gitignore +1 -0
- config.json +32 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May29_11-01-50_55a5beb5c56a/1653822150.9425046/events.out.tfevents.1653822150.55a5beb5c56a.108.1 +3 -0
- runs/May29_11-01-50_55a5beb5c56a/events.out.tfevents.1653822150.55a5beb5c56a.108.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stevemobs/deberta-base-combined-squad1-aqa-newsqa",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"layer_norm_eps": 1e-07,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"max_relative_positions": -1,
|
15 |
+
"model_type": "deberta",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"pooler_dropout": 0,
|
20 |
+
"pooler_hidden_act": "gelu",
|
21 |
+
"pooler_hidden_size": 768,
|
22 |
+
"pos_att_type": [
|
23 |
+
"c2p",
|
24 |
+
"p2c"
|
25 |
+
],
|
26 |
+
"position_biased_input": false,
|
27 |
+
"relative_attention": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.18.0",
|
30 |
+
"type_vocab_size": 0,
|
31 |
+
"vocab_size": 50265
|
32 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05dca4fba87bdc0d09c73a93a676cc8015a841ba1f650c6c646ffddb9f3f40d9
|
3 |
+
size 554483891
|
runs/May29_11-01-50_55a5beb5c56a/1653822150.9425046/events.out.tfevents.1653822150.55a5beb5c56a.108.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0615b2df5c1180c035acf4f20e7cc9f4a7944b81e157c8a0763e52f82b3d040
|
3 |
+
size 4945
|
runs/May29_11-01-50_55a5beb5c56a/events.out.tfevents.1653822150.55a5beb5c56a.108.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa101d0b9377639580c8155debb80ee1de82bda15e411c7eca4f7b6d05f35fce
|
3 |
+
size 6761
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "vocab_type": "gpt2", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "stevemobs/deberta-base-combined-squad1-aqa-newsqa", "add_bos_token": false, "tokenizer_class": "DebertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cd0ed0da8bcf869574d01e04129bbb602a0e50d07d567d08b27abf601c4e394
|
3 |
+
size 3119
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|