Commit
•
b8f83da
1
Parent(s):
d07ef5b
Upload 11 files
Browse files- all_results.json +9 -0
- config.json +37 -0
- generation_config.json +11 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +109 -0
- tokenizer_config.json +118 -0
- train_results.json +9 -0
- trainer_state.json +49 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 590265116000256.0,
|
4 |
+
"train_loss": 1.4712043319923291,
|
5 |
+
"train_runtime": 392.2574,
|
6 |
+
"train_samples": 2758,
|
7 |
+
"train_samples_per_second": 21.093,
|
8 |
+
"train_steps_per_second": 5.277
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/m2m100_418M",
|
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": "4.31.0",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 128104
|
37 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"max_length": 200,
|
8 |
+
"num_beams": 5,
|
9 |
+
"pad_token_id": 1,
|
10 |
+
"transformers_version": "4.31.0"
|
11 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d67a29feecd8e42fb372de3e1b160eb17d1b08c11a32bc45cbb956fc7a751868
|
3 |
+
size 1935759303
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
|
3 |
+
size 2423393
|
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 |
+
}
|
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": null,
|
114 |
+
"tgt_lang": null,
|
115 |
+
"tokenizer_class": "M2M100Tokenizer",
|
116 |
+
"tokenizer_file": null,
|
117 |
+
"unk_token": "<unk>"
|
118 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 590265116000256.0,
|
4 |
+
"train_loss": 1.4712043319923291,
|
5 |
+
"train_runtime": 392.2574,
|
6 |
+
"train_samples": 2758,
|
7 |
+
"train_samples_per_second": 21.093,
|
8 |
+
"train_steps_per_second": 5.277
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 2070,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.72,
|
12 |
+
"learning_rate": 3.7922705314009665e-05,
|
13 |
+
"loss": 2.2113,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.45,
|
18 |
+
"learning_rate": 2.5845410628019323e-05,
|
19 |
+
"loss": 1.4796,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.17,
|
24 |
+
"learning_rate": 1.3768115942028985e-05,
|
25 |
+
"loss": 1.226,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.9,
|
30 |
+
"learning_rate": 1.6908212560386474e-06,
|
31 |
+
"loss": 1.0334,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"step": 2070,
|
37 |
+
"total_flos": 590265116000256.0,
|
38 |
+
"train_loss": 1.4712043319923291,
|
39 |
+
"train_runtime": 392.2574,
|
40 |
+
"train_samples_per_second": 21.093,
|
41 |
+
"train_steps_per_second": 5.277
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"max_steps": 2070,
|
45 |
+
"num_train_epochs": 3,
|
46 |
+
"total_flos": 590265116000256.0,
|
47 |
+
"trial_name": null,
|
48 |
+
"trial_params": null
|
49 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7211f1dbcdf16d2bdf33ff1b29ded8788a0ece2b5c598a467a4b8109cfb76c9
|
3 |
+
size 4207
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|