Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- runs/Jan09_01-44-49_8592160d703d/1641692826.4497333/events.out.tfevents.1641692826.8592160d703d.76.1 +3 -0
- runs/Jan09_01-44-49_8592160d703d/events.out.tfevents.1641692826.8592160d703d.76.0 +3 -0
- runs/Jan09_02-17-57_8592160d703d/1641694708.109343/events.out.tfevents.1641694708.8592160d703d.76.3 +3 -0
- runs/Jan09_02-17-57_8592160d703d/events.out.tfevents.1641694708.8592160d703d.76.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/bertweet-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 130,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"tokenizer_class": "BertweetTokenizer",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.15.0",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 64001
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84583f862831422829798f7cdf5444eb9ce035069adb50defe672da1a9f129af
|
3 |
+
size 539944619
|
runs/Jan09_01-44-49_8592160d703d/1641692826.4497333/events.out.tfevents.1641692826.8592160d703d.76.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e97e8b387ccd521335a444c71382ef70b70891071f16d100b988f8ada7ab04f
|
3 |
+
size 4812
|
runs/Jan09_01-44-49_8592160d703d/events.out.tfevents.1641692826.8592160d703d.76.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:065ff477899cef0c96a1f3e64b48af7cb3e0ffe6b16ea4f26a625995d8dc6b4c
|
3 |
+
size 3447
|
runs/Jan09_02-17-57_8592160d703d/1641694708.109343/events.out.tfevents.1641694708.8592160d703d.76.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c54f460db002f15818442d8d0e8881fb262b64f992fa286f5b353c7271c28b1
|
3 |
+
size 4812
|
runs/Jan09_02-17-57_8592160d703d/events.out.tfevents.1641694708.8592160d703d.76.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ee00fbbc3f5e959c3de654ad6a9d288f1719aefef44ed0441e43f50f22afadc
|
3 |
+
size 3604
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68d1b6a9a2ed0c9ab4fed5a01ddbce29824e04839931ca3e742fb7c406192c62
|
3 |
+
size 2991
|