Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +45 -0
- pytorch_model.bin +3 -0
- runs/Sep25_18-12-58_94ab9a87efd3/1664129623.3043156/events.out.tfevents.1664129623.94ab9a87efd3.74.1 +3 -0
- runs/Sep25_18-12-58_94ab9a87efd3/events.out.tfevents.1664129623.94ab9a87efd3.74.0 +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Gabriel/bart-base-cnn-swe",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"BartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 768,
|
12 |
+
"decoder_attention_heads": 16,
|
13 |
+
"decoder_ffn_dim": 3072,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 6,
|
16 |
+
"decoder_start_token_id": 2,
|
17 |
+
"dropout": 0.1,
|
18 |
+
"encoder_attention_heads": 16,
|
19 |
+
"encoder_ffn_dim": 3072,
|
20 |
+
"encoder_layerdrop": 0.0,
|
21 |
+
"encoder_layers": 6,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"forced_eos_token_id": 2,
|
24 |
+
"id2label": {
|
25 |
+
"0": "LABEL_0",
|
26 |
+
"1": "LABEL_1",
|
27 |
+
"2": "LABEL_2"
|
28 |
+
},
|
29 |
+
"init_std": 0.02,
|
30 |
+
"is_encoder_decoder": true,
|
31 |
+
"label2id": {
|
32 |
+
"LABEL_0": 0,
|
33 |
+
"LABEL_1": 1,
|
34 |
+
"LABEL_2": 2
|
35 |
+
},
|
36 |
+
"max_position_embeddings": 1024,
|
37 |
+
"model_type": "bart",
|
38 |
+
"num_hidden_layers": 6,
|
39 |
+
"pad_token_id": 1,
|
40 |
+
"scale_embedding": false,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.22.1",
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 50185
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dea6c5297671052b7fb92ca266a11efa4c386a5f10c5a0c8cc90827406383617
|
3 |
+
size 557723065
|
runs/Sep25_18-12-58_94ab9a87efd3/1664129623.3043156/events.out.tfevents.1664129623.94ab9a87efd3.74.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bda6e64aed95b5f02cacce4b80e02e32b67ca67aeb91c7d0077a7a0a73b5254f
|
3 |
+
size 5752
|
runs/Sep25_18-12-58_94ab9a87efd3/events.out.tfevents.1664129623.94ab9a87efd3.74.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f7e688975fef158abd82c60678590c90eca378081dff2a11003a7cd45f9b4aa
|
3 |
+
size 4395
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "</s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "</s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"name_or_path": "Gabriel/bart-base-cnn-swe",
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"sep_token": "</s>",
|
9 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/eeba8b7f723def8f95951bb301a16f684eb8a2b6bfbc13e715d200a2df8a7e61.4405f81af4d0c9b936ce3368cc07277d6d61ec031eac1137ba8e4d9acedd61ee",
|
10 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:300bc7c0c446b1e49ab60c14356c46bbe650d464f8b5f5b95e0ea874b1d3528e
|
3 |
+
size 3503
|