yonathanstwn commited on
Commit
e169dc5
1 Parent(s): 1c16198

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -32,3 +32,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ last-checkpoint/source.spm filter=lfs diff=lfs merge=lfs -text
36
+ last-checkpoint/target.spm filter=lfs diff=lfs merge=lfs -text
37
+ source.spm filter=lfs diff=lfs merge=lfs -text
38
+ target.spm filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/opus-mt-id-en",
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
+ 54795
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": 54795,
26
+ "decoder_vocab_size": 54796,
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
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 6,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 54795,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.26.1",
59
+ "use_cache": true,
60
+ "vocab_size": 54796
61
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/opus-mt-id-en",
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
+ 54795
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": 54795,
26
+ "decoder_vocab_size": 54796,
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
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 6,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 54795,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.26.1",
59
+ "use_cache": true,
60
+ "vocab_size": 54796
61
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 54795
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 54795,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 6,
14
+ "pad_token_id": 54795,
15
+ "transformers_version": "4.26.1"
16
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a7a088d29c23e47b58d6da5a4f958e751486cfe867c689745224bf8c26723f
3
+ size 577700869
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d31f44bafa9aa9c5a8953fcecd6de4bc07bc7e20324e3e83ba8aa351ced121
3
+ size 289081861
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b8b7370c9d491922dd403ea1b05ce9ad11a3b302f27f9b40e124144c42f953
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a90a786e94ac780099fc2980a864f2f6add8d9a9dcb8ecc15bbcedbbf80ea8d
3
+ size 627
last-checkpoint/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8fefe71c7f26cb0c6aa1b9f0cc0f8d18006b20fe41c547af7f25b9c8333465
3
+ size 800687
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
last-checkpoint/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88300911c2c573ec5526777a1e84bae698d20925b82dcef9c7248bb0e537ed0
3
+ size 795925
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "model_max_length": 512,
4
+ "name_or_path": "./models/opus-mt-id-en",
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "id",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": null,
10
+ "target_lang": "en",
11
+ "tokenizer_class": "MarianTokenizer",
12
+ "unk_token": "<unk>"
13
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.6302595138549805,
3
+ "best_model_checkpoint": "models/opus-mt-id-en-opus100/checkpoint-31250",
4
+ "epoch": 1.0,
5
+ "global_step": 31250,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9.649404953361209e-05,
13
+ "loss": 1.4869,
14
+ "step": 31250
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_bleu": 32.7596,
19
+ "eval_loss": 1.6302595138549805,
20
+ "eval_runtime": 39.1839,
21
+ "eval_samples_per_second": 51.041,
22
+ "eval_steps_per_second": 1.608,
23
+ "step": 31250
24
+ }
25
+ ],
26
+ "max_steps": 781250,
27
+ "num_train_epochs": 25,
28
+ "total_flos": 1.0234272304594944e+16,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79820bb39691c16bb62047f02b445612c8b232a5f94e8f71f50b78ce19e35b6
3
+ size 3643
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d31f44bafa9aa9c5a8953fcecd6de4bc07bc7e20324e3e83ba8aa351ced121
3
+ size 289081861
source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8fefe71c7f26cb0c6aa1b9f0cc0f8d18006b20fe41c547af7f25b9c8333465
3
+ size 800687
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88300911c2c573ec5526777a1e84bae698d20925b82dcef9c7248bb0e537ed0
3
+ size 795925
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "model_max_length": 512,
4
+ "name_or_path": "./models/opus-mt-id-en",
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "id",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": null,
10
+ "target_lang": "en",
11
+ "tokenizer_class": "MarianTokenizer",
12
+ "unk_token": "<unk>"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79820bb39691c16bb62047f02b445612c8b232a5f94e8f71f50b78ce19e35b6
3
+ size 3643
vocab.json ADDED
The diff for this file is too large to render. See raw diff