lsimon commited on
Commit
724d64a
·
1 Parent(s): b3122cd

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForMaskedLM"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.28.1",
23
+ "vocab_size": 30522
24
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1cea98f36d7982834814fe647336b13eec964fd8a87e340dc8cdc3584e0e30f
3
+ size 267978033
runs/May11_17-44-06_LukesRazer/1683852734.0417778/events.out.tfevents.1683852734.LukesRazer.458.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae82c28d8e301af84e3ad2257b28a34d3cf48c04990e7f4e5c8060877547dc33
3
+ size 5935
runs/May11_17-44-06_LukesRazer/events.out.tfevents.1683852703.LukesRazer.458.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae21eab5ef61be873dcb4b9f6e0e5acfbbd5f33fe633107a7b0873c1f0ae98e
3
+ size 4148
runs/May11_18-02-01_LukesRazer/1683853359.0847945/events.out.tfevents.1683853359.LukesRazer.1080.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804bd804676becd34dceb8dfb356fe4c43c8d48865bba1553fc4975906834dad
3
+ size 5935
runs/May11_18-02-01_LukesRazer/events.out.tfevents.1683853359.LukesRazer.1080.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7cf0b8f12c64b475b779aa022503d9973c89128171bbb473940aac2b845215
3
+ size 3938
runs/May11_18-15-03_LukesRazer/1683854157.2418272/events.out.tfevents.1683854157.LukesRazer.1230.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0263eaac177888c66fbd72b5507a0d1744e948557d828c9ef8afad627c4bc7
3
+ size 5935
runs/May11_18-15-03_LukesRazer/events.out.tfevents.1683854157.LukesRazer.1230.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa92a3b0dc6b7d308d1e03f971daab106ef36f5ee73e203c4f4655f5a1c1c6a
3
+ size 3938
runs/May11_18-43-08_LukesRazer/1683855849.1340694/events.out.tfevents.1683855849.LukesRazer.1789.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac7dd6ec605f19f9194e9cb56f7bfad3422d6c3a2ae0d3d28d1c53cd797a125
3
+ size 5935
runs/May11_18-43-08_LukesRazer/events.out.tfevents.1683855849.LukesRazer.1789.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e299b1ffaccd0457362bf434b3261e6478b9c63b6ab84f4367ac0deeb8d94bdd
3
+ size 4367
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5be2917ddc820f83f5b8c8c87c7435517556b3241adc72b512b9a71586da9c2
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff