pszemraj commited on
Commit
f3b3f0a
1 Parent(s): a491ddf

Training in progress, step 100

Browse files
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pszemraj/random-mega-small-2048",
3
+ "activation": "silu",
4
+ "add_lm_hidden_dense_layer": false,
5
+ "add_token_type_embeddings": true,
6
+ "architectures": [
7
+ "MegaForMaskedLM"
8
+ ],
9
+ "attention_activation": "softmax",
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bidirectional": true,
12
+ "bos_token_id": 0,
13
+ "chunk_size": 1024,
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": 64,
20
+ "eos_token_id": 2,
21
+ "hidden_dropout_prob": 0.1,
22
+ "hidden_size": 512,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1024,
25
+ "max_positions": 2048,
26
+ "model_type": "mega",
27
+ "nffn_activation_dropout_prob": 0.1,
28
+ "nffn_hidden_size": 1024,
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": 12,
35
+ "pad_token_id": 1,
36
+ "relative_positional_bias": "rotary",
37
+ "shared_representation_size": 128,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.33.1",
40
+ "truncation": null,
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "use_chunking": true,
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
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3e8b26fb4ffb3d6af805d58fb81070da0f38824d179e1db732a7834af5738b
3
+ size 270274934
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "max_length": 2048,
10
+ "model_max_length": 2048,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a4814234be00290efa1cfbbe1a825d9c108425ecbed73400f3e574768c3bd3
3
+ size 4728
vocab.json ADDED
The diff for this file is too large to render. See raw diff