vasudevgupta
commited on
Commit
•
d1800b5
1
Parent(s):
8057ded
add epoch-0
Browse files- args.joblib +3 -0
- config.json +31 -0
- data_collator.joblib +3 -0
- flax_model.msgpack +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
- training_state.json +1 -0
args.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38584a94d7930b3f2aa08edbfd862dfb0bd3b71593ce9ad27afdd06207f26a3a
|
3 |
+
size 418
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BigBirdForNaturalQuestions"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"attention_type": "block_sparse",
|
7 |
+
"block_size": 64,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu_new",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 4096,
|
18 |
+
"model_type": "big_bird",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"num_random_blocks": 3,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"rescale_embeddings": false,
|
25 |
+
"sep_token_id": 66,
|
26 |
+
"transformers_version": "4.7.0.dev0",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"use_bias": true,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 50358
|
31 |
+
}
|
data_collator.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33663cd2aa23ddcb692aa6974528132c0e1de43e1b12626b32a164c3d7fb7fdd
|
3 |
+
size 75
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d815ae3bd060dae8791d6cbe2291cd9b25a54995acb650d0ed34c1b7baf346bd
|
3 |
+
size 528800098
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
|
3 |
+
size 845731
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 4096, "special_tokens_map_file": "/home/vasudevgupta/.cache/huggingface/transformers/e1ae56febb08d6573cc0652dca4183840ad6d69a89acbf59731052ef1acfb11b.75b358ecb30fa6b001d9d87bfde336c02d9123e7a8f5b90cc890d0f6efc3d4a3", "tokenizer_file": null, "name_or_path": "google/bigbird-base-trivia-itc"}
|
training_state.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"step": 42000}
|