GBaker commited on
Commit
1f9a955
1 Parent(s): 94b7b0e

Training in progress, epoch 0

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uw-madison/nystromformer-4096",
3
+ "architectures": [
4
+ "NystromformerForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "conv_kernel_size": 65,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu_new",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "inv_coeff_init_option": false,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 4096,
18
+ "model_type": "nystromformer",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "num_landmarks": 64,
22
+ "pad_token_id": 1,
23
+ "segment_means_seq_len": 64,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.26.1",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 30000
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0495e228cd43c283fa1922705da3ada60fd744b084ae266f283913b2657d1f32
3
+ size 447489125
runs/Feb12_17-57-06_dc7637cf824d/1676224641.6307414/events.out.tfevents.1676224641.dc7637cf824d.3249.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad37339d684035c014be2c311316400bde56dc56bead3971d1cc1e093bbb232
3
+ size 5745
runs/Feb12_17-57-06_dc7637cf824d/events.out.tfevents.1676224641.dc7637cf824d.3249.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed755ae18d6403d986956be8d5bf556db5171de90a52700bbb194679a2aa008
3
+ size 4293
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "eos_token": "[SEP]",
6
+ "keep_accents": false,
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "[MASK]",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "name_or_path": "uw-madison/nystromformer-4096",
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "special_tokens_map_file": null,
21
+ "tokenizer_class": "AlbertTokenizer",
22
+ "unk_token": "<unk>"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74cf7fd4c2fb2002d579dc4214d40ece898b15359eced3abdb82b70e8785e24b
3
+ size 3579