Nekofox commited on
Commit
ff06a40
1 Parent(s): 4615c77

Training in progress, step 8000

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Nekofox/M2M100-ja-zh",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "M2M100ForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 4096,
13
+ "decoder_layerdrop": 0.05,
14
+ "decoder_layers": 12,
15
+ "decoder_start_token_id": 2,
16
+ "dropout": 0.1,
17
+ "early_stopping": true,
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 4096,
20
+ "encoder_layerdrop": 0.05,
21
+ "encoder_layers": 12,
22
+ "eos_token_id": 2,
23
+ "gradient_checkpointing": false,
24
+ "init_std": 0.02,
25
+ "is_encoder_decoder": true,
26
+ "max_length": 200,
27
+ "max_position_embeddings": 1024,
28
+ "model_type": "m2m_100",
29
+ "num_beams": 5,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "scale_embedding": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.28.1",
35
+ "use_cache": true,
36
+ "vocab_size": 128112
37
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 200,
7
+ "num_beams": 5,
8
+ "pad_token_id": 1,
9
+ "transformers_version": "4.28.1"
10
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5fee8207f36c1b9e1aef79d344f7acbd6caf908727460d1f50dc9581e679367
3
+ size 3871543575
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c41eab122f41bae21df10cfc712894e9e7bd882238893269188f80c7cb7ed36
3
+ size 1944201353
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5c6b922987d8fae6a92f121f201440c06fdcfa4c266591d2fae2c8688a68dd
3
+ size 14575
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f93db576e82558e0b61e6e8b192bf5aac925b16461b57945ec850e5bbb2bc68
3
+ size 557
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90692e4f477275b35625e5ab8f213a0dc1ef39bc5eead93ee278d535c0ddbd06
3
+ size 627
last-checkpoint/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
3
+ size 2423393
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
+ ],
104
+ "bos_token": "<s>",
105
+ "eos_token": "</s>",
106
+ "pad_token": "<pad>",
107
+ "sep_token": "</s>",
108
+ "unk_token": "<unk>"
109
+ }
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
+ ],
104
+ "bos_token": "<s>",
105
+ "clean_up_tokenization_spaces": true,
106
+ "eos_token": "</s>",
107
+ "language_codes": "m2m100",
108
+ "model_max_length": 1024,
109
+ "num_madeup_words": 8,
110
+ "pad_token": "<pad>",
111
+ "sep_token": "</s>",
112
+ "sp_model_kwargs": {},
113
+ "src_lang": "ja",
114
+ "tgt_lang": "zh",
115
+ "tokenizer_class": "M2M100Tokenizer",
116
+ "tokenizer_file": null,
117
+ "unk_token": "<unk>"
118
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5642544787699252,
5
+ "global_step": 8000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 3.0211480362537768e-05,
13
+ "loss": 1.4914,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.11,
18
+ "learning_rate": 3.985424375207197e-05,
19
+ "loss": 1.103,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.16,
24
+ "learning_rate": 3.910964926929347e-05,
25
+ "loss": 1.1117,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.21,
30
+ "learning_rate": 3.775641735336502e-05,
31
+ "loss": 1.1636,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.26,
36
+ "learning_rate": 3.583764809409783e-05,
37
+ "loss": 1.1947,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.32,
42
+ "learning_rate": 3.34144538007923e-05,
43
+ "loss": 1.1979,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.37,
48
+ "learning_rate": 3.05640125908444e-05,
49
+ "loss": 1.4767,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.35,
54
+ "learning_rate": 3.1554332626816203e-05,
55
+ "loss": 0.9765,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.4,
60
+ "learning_rate": 2.9009680903546416e-05,
61
+ "loss": 1.4107,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.44,
66
+ "learning_rate": 2.6260730367115988e-05,
67
+ "loss": 1.5024,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.39,
72
+ "learning_rate": 2.9542651711125413e-05,
73
+ "loss": 0.975,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.42,
78
+ "learning_rate": 2.7394824453041223e-05,
79
+ "loss": 1.1808,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.46,
84
+ "learning_rate": 2.5133790365330005e-05,
85
+ "loss": 1.1449,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.49,
90
+ "learning_rate": 2.2799977645691646e-05,
91
+ "loss": 1.4763,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.53,
96
+ "learning_rate": 2.0426471341395805e-05,
97
+ "loss": 1.6014,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.56,
102
+ "learning_rate": 1.8046919211584273e-05,
103
+ "loss": 1.6065,
104
+ "step": 8000
105
+ }
106
+ ],
107
+ "max_steps": 14178,
108
+ "num_train_epochs": 1,
109
+ "total_flos": 8919658633003008.0,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397440f6ded868db50187647727a51c936dbe1d3cb7915d6fd9d630c8ac2cee2
3
+ size 3835
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e40757a7fcbb40c6ea5471e72b4d7ed3d36a573801fb8fbe4f8a3c6e7667cd2a
3
  size 1944201353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c41eab122f41bae21df10cfc712894e9e7bd882238893269188f80c7cb7ed36
3
  size 1944201353
runs/May10_02-55-16_b2d6d2516701/1683687398.0241933/events.out.tfevents.1683687398.b2d6d2516701.23622.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8a70fc0f2221acc83d462039537f5f21eaf9efdbdd449a750f66e856714223
3
+ size 6187
runs/May10_02-55-16_b2d6d2516701/events.out.tfevents.1683687397.b2d6d2516701.23622.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:812ec24f2d9f01a57a1d494fafaa11761b3579d5d107404c9283441b4c53c150
3
+ size 4778
runs/May10_03-07-14_b2d6d2516701/1683688088.2852163/events.out.tfevents.1683688088.b2d6d2516701.27129.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc3605ee3434b26e02191d575b6afda5004b3a3703722486f49ef5c636b4c9c
3
+ size 6187
runs/May10_03-07-14_b2d6d2516701/events.out.tfevents.1683688088.b2d6d2516701.27129.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b660f32af3ed8fed0df52f192f6f10c0b5f171723400813e13bfebaecd1837
3
+ size 4464
runs/May10_03-17-42_b2d6d2516701/1683688721.1927097/events.out.tfevents.1683688721.b2d6d2516701.29824.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9edc93891b870bdaca01eaef12ba248aa28fab570761573e75010b425c16eda
3
+ size 6187
runs/May10_03-17-42_b2d6d2516701/events.out.tfevents.1683688721.b2d6d2516701.29824.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9cdc3b7dc9f0a9334f68d4ab84e2677d25b7b7b015981df23c23909a05acfee
3
+ size 4935
runs/May10_03-30-00_b2d6d2516701/1683689456.2658033/events.out.tfevents.1683689456.b2d6d2516701.33377.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9106c591050ec74113c478379355d9987f267858b51d64604c76ad3853ca217
3
+ size 6187
runs/May10_03-30-00_b2d6d2516701/events.out.tfevents.1683689456.b2d6d2516701.33377.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a70d3ed55f0b2c023c4ba5e7aa43ccd012e1164a2e7cee2be4a996bcbc83e55
3
+ size 5404
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07d990933e37cfc9bfdc78c4a30a9ead0c9b32b99ec33e9a02c12dc256a2f36f
3
- size 3771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397440f6ded868db50187647727a51c936dbe1d3cb7915d6fd9d630c8ac2cee2
3
+ size 3835