gsarti commited on
Commit
8775e0c
1 Parent(s): 5618330

Training in progress epoch 0

Browse files
.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>": 59514
3
+ }
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "context-mt/iwslt17-marian-small-target-ctx4-cwd0-en-fr",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 59513
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 59513,
26
+ "decoder_vocab_size": 59515,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "forced_eos_token_id": 0,
34
+ "gradient_checkpointing": false,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1",
38
+ "2": "LABEL_2"
39
+ },
40
+ "init_std": 0.02,
41
+ "is_encoder_decoder": true,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1,
45
+ "LABEL_2": 2
46
+ },
47
+ "max_length": 512,
48
+ "max_position_embeddings": 512,
49
+ "model_type": "marian",
50
+ "normalize_before": false,
51
+ "normalize_embedding": false,
52
+ "num_beams": 4,
53
+ "num_hidden_layers": 6,
54
+ "pad_token_id": 59513,
55
+ "scale_embedding": true,
56
+ "share_encoder_decoder_embeddings": true,
57
+ "static_position_embeddings": true,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.28.0",
60
+ "use_cache": true,
61
+ "vocab_size": 59515
62
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 59513
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 59513,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 4,
14
+ "pad_token_id": 59513,
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 sha256:6ae32a5b63254b973985534dc6adc91b31554cb013f433e1f519ee5985338856
3
+ size 298765253
source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173e9f493a668fe396d599e28d414a201193094e6ffd7a4678e5aab0f6d3d838
3
+ size 778395
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 sha256:78d0e717c77053f1c4b856d8661d9cb87c64f083a35418c087b9146300e4f585
3
+ size 802397
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/1687954900.928281/events.out.tfevents.1687954900.a100gpu3.2039806.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f48c2ea02afcb1c5cc6e476cabc5c7f3796f3e96d499f37245831fab908164
3
+ size 2321
translation_no_trainer/1687954900.9395692/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: 1
8
+ hub_model_id: context-mt/scat-marian-small-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-small-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-small-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: 16
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.1687954900.a100gpu3.2039806.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07c41ca6c9087d755dd9db794b8e3e9c9bae82e43f5ba24cdba14799aae5238d
3
+ size 675
vocab.json ADDED
The diff for this file is too large to render. See raw diff