yi zhou
commited on
Commit
•
9942070
1
Parent(s):
a6bbcab
Step 1, loss 11.031
Browse files- config.json +32 -0
- optimizer_state.pt +3 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"AlbertForPreTraining"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0,
|
6 |
+
"bos_token_id": 2,
|
7 |
+
"classifier_dropout_prob": 0.1,
|
8 |
+
"down_scale_factor": 1,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"eos_token_id": 3,
|
11 |
+
"gap_size": 0,
|
12 |
+
"hidden_act": "gelu_new",
|
13 |
+
"hidden_dropout_prob": 0,
|
14 |
+
"hidden_size": 1024,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"inner_group_num": 1,
|
17 |
+
"intermediate_size": 4096,
|
18 |
+
"layer_norm_eps": 1e-12,
|
19 |
+
"max_position_embeddings": 512,
|
20 |
+
"model_type": "albert",
|
21 |
+
"net_structure_type": 0,
|
22 |
+
"num_attention_heads": 16,
|
23 |
+
"num_hidden_groups": 1,
|
24 |
+
"num_hidden_layers": 24,
|
25 |
+
"num_memory_blocks": 0,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.12.2",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"vocab_size": 30000
|
32 |
+
}
|
optimizer_state.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39cdcfc71ea139cd0096c7a76a41f92a73d5dabf024587fb3db696e5424a361a
|
3 |
+
size 141764093
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab06c979183ae142e23395ca15804ab710188207423af96092314694e3d255d9
|
3 |
+
size 71406466
|