Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +34 -0
- pytorch_model.bin +3 -0
- runs/Feb24_23-24-38_9faec81de0d0/1677281167.9686096/events.out.tfevents.1677281167.9faec81de0d0.249.1 +3 -0
- runs/Feb24_23-24-38_9faec81de0d0/events.out.tfevents.1677281167.9faec81de0d0.249.0 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "uclanlp/plbart-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"PLBartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 768,
|
12 |
+
"decoder_attention_heads": 12,
|
13 |
+
"decoder_ffn_dim": 3072,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 6,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 12,
|
18 |
+
"encoder_ffn_dim": 3072,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_layers": 6,
|
21 |
+
"eos_token_id": 2,
|
22 |
+
"forced_eos_token_id": 2,
|
23 |
+
"init_std": 0.02,
|
24 |
+
"is_encoder_decoder": true,
|
25 |
+
"max_position_embeddings": 1024,
|
26 |
+
"model_type": "plbart",
|
27 |
+
"num_hidden_layers": 6,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"scale_embedding": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.26.1",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 50005
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b98faee05ec09681ddd1ae0f09fe6d5d3d1b10dd0db7296db523c0fac931af8
|
3 |
+
size 557171485
|
runs/Feb24_23-24-38_9faec81de0d0/1677281167.9686096/events.out.tfevents.1677281167.9faec81de0d0.249.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8674c44e3c87cec1410b275c04d7b47588be1195178e22c6d6bae8777b2bcd1
|
3 |
+
size 5954
|
runs/Feb24_23-24-38_9faec81de0d0/events.out.tfevents.1677281167.9faec81de0d0.249.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95bd6ef85681421e4354dfd0c6efdc8c03a7cc50450e31b5e440d4e8e1b49526
|
3 |
+
size 6298
|
tokenizer_config.json
CHANGED
@@ -13,7 +13,7 @@
|
|
13 |
"single_word": false
|
14 |
},
|
15 |
"model_max_length": 1024,
|
16 |
-
"name_or_path": "
|
17 |
"pad_token": "<pad>",
|
18 |
"sep_token": "</s>",
|
19 |
"sp_model_kwargs": {},
|
|
|
13 |
"single_word": false
|
14 |
},
|
15 |
"model_max_length": 1024,
|
16 |
+
"name_or_path": "Minata/plbart-base-finetuned-ut-generator",
|
17 |
"pad_token": "<pad>",
|
18 |
"sep_token": "</s>",
|
19 |
"sp_model_kwargs": {},
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2869ba681bffea18eeaa48db6ae9de10f88f8dafa777383d9e366229d3710d4
|
3 |
+
size 3643
|