kyle Hamilton commited on
Commit
1ea115a
1 Parent(s): 228b305
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Ngram_size": 32768,
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "block_size": 128,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_Ngram_layers": 1,
21
+ "num_hidden_layers": 24,
22
+ "pad_token_id": 1,
23
+ "type_vocab_size": 1,
24
+ "vocab_size": 50265
25
+ }
eval_results_lm.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ perplexity = 2.1671416699631867
log_history.json ADDED
@@ -0,0 +1 @@
 
 
1
+ []
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 sha256:6595c00ef02320f77a04904c076ed1c6f123d68e163e63125734da3138fb5fd2
3
+ size 1606439113
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"Ngram_vocab_size": 32768, "model_max_length": 512}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e0a451d019fddad9c92bc25858f0b5290580616ab86bc77dc14b068c09835c
3
+ size 2363
vocab.json ADDED
The diff for this file is too large to render. See raw diff