Xenopilus commited on
Commit
daf9967
1 Parent(s): 93f7445

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mnaylor/mega-base-wikitext",
3
+ "activation": "silu",
4
+ "add_lm_hidden_dense_layer": false,
5
+ "add_token_type_embeddings": false,
6
+ "architectures": [
7
+ "MegaForMultipleChoice"
8
+ ],
9
+ "attention_activation": "softmax",
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bidirectional": true,
12
+ "bos_token_id": 0,
13
+ "chunk_size": -1,
14
+ "classifier_dropout": null,
15
+ "dropout_prob": 0.1,
16
+ "ema_beta_range": 0.02,
17
+ "ema_delta_alpha_range": 0.2,
18
+ "ema_gamma_omega_range": 1.0,
19
+ "ema_projection_size": 16,
20
+ "eos_token_id": 2,
21
+ "hidden_dropout_prob": 0.1,
22
+ "hidden_size": 128,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 256,
25
+ "max_positions": 10000,
26
+ "model_type": "mega",
27
+ "nffn_activation_dropout_prob": 0.0,
28
+ "nffn_hidden_size": 256,
29
+ "norm_affine": true,
30
+ "normalization_type": "scalenorm",
31
+ "normalize_before_ffn": true,
32
+ "normalize_before_mega": true,
33
+ "num_attention_heads": 1,
34
+ "num_hidden_layers": 4,
35
+ "pad_token_id": 1,
36
+ "relative_positional_bias": "rotary",
37
+ "shared_representation_size": 64,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.35.2",
40
+ "truncation": null,
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "use_chunking": false,
44
+ "use_feature_dropout": false,
45
+ "use_normalized_ffn": true,
46
+ "vocab_size": 50265
47
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64698529bc200a542ed0953d731129a4de55b4bace9b2d4606d6f12c3d9f121e
3
+ size 29381028
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
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": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": 256,
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "stride": 0,
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00ea29a207a3afee17450644110da0cfa92eaa27128d2fb54bae0572931fa69
3
+ size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff