vasudevgupta
commited on
Commit
•
ece1485
1
Parent(s):
efdb368
ckpt-10000
Browse files- config.json +32 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bigbird-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"BigBirdForNaturalQuestions"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"attention_type": "block_sparse",
|
8 |
+
"block_size": 64,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": true,
|
12 |
+
"hidden_act": "gelu_fast",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"layer_norm_eps": 1e-12,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "big_bird",
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_hidden_layers": 12,
|
22 |
+
"num_random_blocks": 3,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"position_embedding_type": "absolute",
|
25 |
+
"rescale_embeddings": false,
|
26 |
+
"sep_token_id": 66,
|
27 |
+
"transformers_version": "4.6.0.dev0",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_bias": true,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 50358
|
32 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54cfe91451a45afbbf4b9dac9271c65e0f500565970a0869c03ba20b9a754b42
|
3 |
+
size 1057712183
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a85a0701a87ccb875eac0b66bd0eb501a7b3fdff8c44bcf7e861b84dbdd8fbe
|
3 |
+
size 528910843
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f491d5175ab9257eb3986019bf5ab8e6edc0e0700bb813e9ed6dde81c5ef050f
|
3 |
+
size 623
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2963be898f6a57a489d9cdf3e1619f1c76ff2e23493848d151dd5e1f7e84cb01
|
3 |
+
size 2479
|