Training in progress epoch 0
Browse files- .gitattributes +2 -0
- .gitignore +2 -0
- added_tokens.json +3 -0
- config.json +46 -0
- generation_config.json +16 -0
- pytorch_model.bin +3 -0
- source.spm +3 -0
- special_tokens_map.json +8 -0
- target.spm +3 -0
- tokenizer_config.json +12 -0
- translation_no_trainer/1687954715.6148415/events.out.tfevents.1687954715.a100gpu3.2039018.1 +3 -0
- translation_no_trainer/1687954715.63408/hparams.yml +44 -0
- translation_no_trainer/events.out.tfevents.1687954715.a100gpu3.2039018.0 +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
37 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
step_*
|
2 |
+
epoch_*
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<brk>": 53017
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "context-mt/iwslt17-marian-big-target-ctx4-cwd0-en-fr",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"MarianMTModel"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bad_words_ids": [
|
10 |
+
[
|
11 |
+
53016
|
12 |
+
]
|
13 |
+
],
|
14 |
+
"bos_token_id": 0,
|
15 |
+
"classifier_dropout": 0.0,
|
16 |
+
"d_model": 1024,
|
17 |
+
"decoder_attention_heads": 16,
|
18 |
+
"decoder_ffn_dim": 4096,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 53016,
|
22 |
+
"decoder_vocab_size": 53018,
|
23 |
+
"dropout": 0.1,
|
24 |
+
"encoder_attention_heads": 16,
|
25 |
+
"encoder_ffn_dim": 4096,
|
26 |
+
"encoder_layerdrop": 0.0,
|
27 |
+
"encoder_layers": 6,
|
28 |
+
"eos_token_id": 43311,
|
29 |
+
"forced_eos_token_id": 43311,
|
30 |
+
"init_std": 0.02,
|
31 |
+
"is_encoder_decoder": true,
|
32 |
+
"max_length": 512,
|
33 |
+
"max_position_embeddings": 1024,
|
34 |
+
"model_type": "marian",
|
35 |
+
"normalize_embedding": false,
|
36 |
+
"num_beams": 4,
|
37 |
+
"num_hidden_layers": 6,
|
38 |
+
"pad_token_id": 53016,
|
39 |
+
"scale_embedding": true,
|
40 |
+
"share_encoder_decoder_embeddings": true,
|
41 |
+
"static_position_embeddings": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.28.0",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 53018
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bad_words_ids": [
|
4 |
+
[
|
5 |
+
53016
|
6 |
+
]
|
7 |
+
],
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"decoder_start_token_id": 53016,
|
10 |
+
"eos_token_id": 43311,
|
11 |
+
"forced_eos_token_id": 43311,
|
12 |
+
"max_length": 512,
|
13 |
+
"num_beams": 4,
|
14 |
+
"pad_token_id": 53016,
|
15 |
+
"transformers_version": "4.28.0"
|
16 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:149160f37ec20a41100fb8e9ee9c6679217dc751dc09eef3b36fdab6824204cf
|
3 |
+
size 922889797
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18bb5a422a53a0bd699b005c8086cbd58a85c4be427fd57ca687c958588edcc9
|
3 |
+
size 802408
|
special_tokens_map.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<brk>"
|
4 |
+
],
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"unk_token": "<unk>"
|
8 |
+
}
|
target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6437b5600d2ae14888939e589773b09bc667c77e81326e20e3f57698a4078593
|
3 |
+
size 819955
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"model_max_length": 512,
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"separate_vocabs": false,
|
7 |
+
"source_lang": "en",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"target_lang": "fr",
|
10 |
+
"tokenizer_class": "MarianTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
translation_no_trainer/1687954715.6148415/events.out.tfevents.1687954715.a100gpu3.2039018.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5194ef6475eee10c41a0dfac3e2007a08c43b8ee691844db1770c1e2303fc8f
|
3 |
+
size 2315
|
translation_no_trainer/1687954715.63408/hparams.yml
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
checkpointing_steps: '1000'
|
2 |
+
config_name: null
|
3 |
+
context_size: 4
|
4 |
+
context_word_dropout: 0.0
|
5 |
+
dataset_config_name: sentences
|
6 |
+
dataset_name: inseq/scat
|
7 |
+
gradient_accumulation_steps: 2
|
8 |
+
hub_model_id: context-mt/scat-marian-big-target-ctx4-cwd0-en-fr
|
9 |
+
hub_token: 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
|
10 |
+
ignore_pad_token_for_loss: true
|
11 |
+
learning_rate: 5.0e-05
|
12 |
+
logging_steps: '200'
|
13 |
+
lr_scheduler_type: linear
|
14 |
+
max_length: 128
|
15 |
+
max_source_length: 512
|
16 |
+
max_target_length: 512
|
17 |
+
max_train_steps: 1388
|
18 |
+
model_name_or_path: context-mt/iwslt17-marian-big-target-ctx4-cwd0-en-fr
|
19 |
+
model_type: null
|
20 |
+
num_beams: 5
|
21 |
+
num_train_epochs: 2
|
22 |
+
num_warmup_steps: 0
|
23 |
+
output_dir: /scratch/p305238/scat-marian-big-target-ctx4-cwd0-en-fr
|
24 |
+
overwrite_cache: false
|
25 |
+
pad_to_max_length: true
|
26 |
+
per_device_eval_batch_size: 8
|
27 |
+
per_device_train_batch_size: 8
|
28 |
+
predict_with_generate: true
|
29 |
+
preprocessing_num_workers: null
|
30 |
+
push_to_hub: true
|
31 |
+
report_to: tensorboard
|
32 |
+
resume_from_checkpoint: null
|
33 |
+
sample_context: true
|
34 |
+
seed: null
|
35 |
+
source_lang: en_XX
|
36 |
+
target_lang: fr_XX
|
37 |
+
tokenizer_name: null
|
38 |
+
train_file: null
|
39 |
+
use_slow_tokenizer: false
|
40 |
+
use_target_context: true
|
41 |
+
val_max_target_length: null
|
42 |
+
validation_file: null
|
43 |
+
weight_decay: 0.0
|
44 |
+
with_tracking: true
|
translation_no_trainer/events.out.tfevents.1687954715.a100gpu3.2039018.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb63ec3a2a573f71e4acc6142a3fb22e8b4f690ba44b90ec9cc7a366b407636
|
3 |
+
size 1083
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|