stevemobs commited on
Commit
73d1d76
1 Parent(s): 9e2caf8

Training in progress, step 10000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-base",
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 sha256:4d462d38c3f1343297deaef09ec4485555e17717c8cff30a5cd13b7d6a202f2b
3
+ size 554483891
runs/May30_18-30-40_d77b6b68b17c/1653935482.0700798/events.out.tfevents.1653935482.d77b6b68b17c.100.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db58d3c0e2cb2e6bad7a3134a2902a9f6da89f4a7dea039b5d30bfb9c2093996
3
+ size 4921
runs/May30_18-30-40_d77b6b68b17c/events.out.tfevents.1653935482.d77b6b68b17c.100.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a989850deefe07ba96b33b6b9d43b9ab3a11476b1660f451d4adae0e135e719a
3
+ size 40
runs/May30_18-32-37_d77b6b68b17c/1653935568.4743328/events.out.tfevents.1653935568.d77b6b68b17c.100.3 ADDED
File without changes
runs/May30_18-32-37_d77b6b68b17c/events.out.tfevents.1653935568.d77b6b68b17c.100.2 ADDED
File without changes
runs/May30_18-40-40_615ccaad82a5/1653936072.9171717/events.out.tfevents.1653936072.615ccaad82a5.74.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2465219dc089958f54dd5524082ad99b212021b1481e5e8e16671df5065a955c
3
+ size 4921
runs/May30_18-40-40_615ccaad82a5/events.out.tfevents.1653936072.615ccaad82a5.74.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd1495b11ee3a26b1c5f9e16959bb81ca8e99316ccb4f603e30af1f9b7b0063
3
+ size 6622
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": "microsoft/deberta-base", "tokenizer_class": "DebertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a17cdbf835e23c9c89c8e2eba0b5af8c6504847dee6b617a0efebaf0f08968b
3
+ size 3119
vocab.json ADDED
The diff for this file is too large to render. See raw diff