miguelvictor
commited on
Commit
•
c03460b
1
Parent(s):
383b805
added model checkpoint
Browse files- config.json +28 -0
- events.out.tfevents.1619091856.abddc95b08b9.345.0 +0 -0
- pytorch_model.bin +3 -0
- spm-default-16k.model +3 -0
- spm-default-16k.vocab +0 -0
- training.logs +0 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"T5ForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"bos_token_id": 2,
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 6,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 6,
|
21 |
+
"output_past": false,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"tokenizer": "default",
|
25 |
+
"transformers_version": "4.5.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 16000
|
28 |
+
}
|
events.out.tfevents.1619091856.abddc95b08b9.345.0
ADDED
Binary file (2.31 MB). View file
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bcf8c2aa97559ef467959a50d29da0e8158acb6d75a9909a27202c6a98822e8
|
3 |
+
size 445683254
|
spm-default-16k.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5682bb73fbe4efee67a087751ce4d2bc801e0fec4f0753bc5a871a4ef725bb25
|
3 |
+
size 10521992
|
spm-default-16k.vocab
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training.logs
ADDED
The diff for this file is too large to render.
See raw diff
|
|