Upload 10 files
Browse files- 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 +592 -0
- training_args.bin +3 -0
- vocab.json +0 -0
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": "4.33.2",
|
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": "4.33.2"
|
11 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cd097b131e4df6b1be3c3e4e0444264ca59ea3c7acdb125c8f860d9496c7b6c
|
3 |
+
size 1935762945
|
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": 5.0,
|
3 |
+
"total_flos": 7.799978327959142e+17,
|
4 |
+
"train_loss": 1.65651271519492,
|
5 |
+
"train_runtime": 12815.2129,
|
6 |
+
"train_samples": 605118,
|
7 |
+
"train_samples_per_second": 236.094,
|
8 |
+
"train_steps_per_second": 3.689
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,592 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 47275,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05,
|
13 |
+
"learning_rate": 4.9471179270227394e-05,
|
14 |
+
"loss": 2.856,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.11,
|
19 |
+
"learning_rate": 4.8942358540454786e-05,
|
20 |
+
"loss": 2.5599,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.16,
|
25 |
+
"learning_rate": 4.841353781068218e-05,
|
26 |
+
"loss": 2.4166,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.21,
|
31 |
+
"learning_rate": 4.7884717080909575e-05,
|
32 |
+
"loss": 2.3151,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.26,
|
37 |
+
"learning_rate": 4.735589635113697e-05,
|
38 |
+
"loss": 2.2732,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.32,
|
43 |
+
"learning_rate": 4.682707562136436e-05,
|
44 |
+
"loss": 2.2248,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.37,
|
49 |
+
"learning_rate": 4.629825489159175e-05,
|
50 |
+
"loss": 2.1665,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.42,
|
55 |
+
"learning_rate": 4.576943416181915e-05,
|
56 |
+
"loss": 2.1445,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.48,
|
61 |
+
"learning_rate": 4.524061343204653e-05,
|
62 |
+
"loss": 2.1219,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.53,
|
67 |
+
"learning_rate": 4.471179270227393e-05,
|
68 |
+
"loss": 2.0906,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.58,
|
73 |
+
"learning_rate": 4.418297197250132e-05,
|
74 |
+
"loss": 2.0674,
|
75 |
+
"step": 5500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.63,
|
79 |
+
"learning_rate": 4.365415124272872e-05,
|
80 |
+
"loss": 2.0508,
|
81 |
+
"step": 6000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.69,
|
85 |
+
"learning_rate": 4.3125330512956106e-05,
|
86 |
+
"loss": 2.0176,
|
87 |
+
"step": 6500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.74,
|
91 |
+
"learning_rate": 4.2596509783183505e-05,
|
92 |
+
"loss": 1.9954,
|
93 |
+
"step": 7000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.79,
|
97 |
+
"learning_rate": 4.2067689053410896e-05,
|
98 |
+
"loss": 1.9745,
|
99 |
+
"step": 7500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.85,
|
103 |
+
"learning_rate": 4.153886832363829e-05,
|
104 |
+
"loss": 1.9776,
|
105 |
+
"step": 8000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.9,
|
109 |
+
"learning_rate": 4.1011105235325226e-05,
|
110 |
+
"loss": 1.9579,
|
111 |
+
"step": 8500
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.95,
|
115 |
+
"learning_rate": 4.048228450555262e-05,
|
116 |
+
"loss": 1.9384,
|
117 |
+
"step": 9000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 1.0,
|
121 |
+
"learning_rate": 3.9953463775780016e-05,
|
122 |
+
"loss": 1.914,
|
123 |
+
"step": 9500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.06,
|
127 |
+
"learning_rate": 3.94246430460074e-05,
|
128 |
+
"loss": 1.7926,
|
129 |
+
"step": 10000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.11,
|
133 |
+
"learning_rate": 3.8896879957694345e-05,
|
134 |
+
"loss": 1.7862,
|
135 |
+
"step": 10500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.16,
|
139 |
+
"learning_rate": 3.8369116869381283e-05,
|
140 |
+
"loss": 1.7798,
|
141 |
+
"step": 11000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.22,
|
145 |
+
"learning_rate": 3.7841353781068215e-05,
|
146 |
+
"loss": 1.7871,
|
147 |
+
"step": 11500
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 1.27,
|
151 |
+
"learning_rate": 3.731253305129561e-05,
|
152 |
+
"loss": 1.7872,
|
153 |
+
"step": 12000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 1.32,
|
157 |
+
"learning_rate": 3.6783712321523005e-05,
|
158 |
+
"loss": 1.7669,
|
159 |
+
"step": 12500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 1.37,
|
163 |
+
"learning_rate": 3.62548915917504e-05,
|
164 |
+
"loss": 1.7631,
|
165 |
+
"step": 13000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.43,
|
169 |
+
"learning_rate": 3.572607086197779e-05,
|
170 |
+
"loss": 1.7672,
|
171 |
+
"step": 13500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 1.48,
|
175 |
+
"learning_rate": 3.5197250132205186e-05,
|
176 |
+
"loss": 1.7741,
|
177 |
+
"step": 14000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.53,
|
181 |
+
"learning_rate": 3.466842940243258e-05,
|
182 |
+
"loss": 1.7571,
|
183 |
+
"step": 14500
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 1.59,
|
187 |
+
"learning_rate": 3.413960867265997e-05,
|
188 |
+
"loss": 1.7444,
|
189 |
+
"step": 15000
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 1.64,
|
193 |
+
"learning_rate": 3.361078794288736e-05,
|
194 |
+
"loss": 1.742,
|
195 |
+
"step": 15500
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.69,
|
199 |
+
"learning_rate": 3.30830248545743e-05,
|
200 |
+
"loss": 1.734,
|
201 |
+
"step": 16000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 1.75,
|
205 |
+
"learning_rate": 3.25542041248017e-05,
|
206 |
+
"loss": 1.7277,
|
207 |
+
"step": 16500
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.8,
|
211 |
+
"learning_rate": 3.202538339502908e-05,
|
212 |
+
"loss": 1.7379,
|
213 |
+
"step": 17000
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 1.85,
|
217 |
+
"learning_rate": 3.149656266525648e-05,
|
218 |
+
"loss": 1.7307,
|
219 |
+
"step": 17500
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.9,
|
223 |
+
"learning_rate": 3.096879957694342e-05,
|
224 |
+
"loss": 1.7145,
|
225 |
+
"step": 18000
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.96,
|
229 |
+
"learning_rate": 3.0439978847170807e-05,
|
230 |
+
"loss": 1.7195,
|
231 |
+
"step": 18500
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 2.01,
|
235 |
+
"learning_rate": 2.99111581173982e-05,
|
236 |
+
"loss": 1.6885,
|
237 |
+
"step": 19000
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 2.06,
|
241 |
+
"learning_rate": 2.9382337387625597e-05,
|
242 |
+
"loss": 1.5763,
|
243 |
+
"step": 19500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 2.12,
|
247 |
+
"learning_rate": 2.885351665785299e-05,
|
248 |
+
"loss": 1.5877,
|
249 |
+
"step": 20000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.17,
|
253 |
+
"learning_rate": 2.832469592808038e-05,
|
254 |
+
"loss": 1.5775,
|
255 |
+
"step": 20500
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 2.22,
|
259 |
+
"learning_rate": 2.7795875198307775e-05,
|
260 |
+
"loss": 1.584,
|
261 |
+
"step": 21000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.27,
|
265 |
+
"learning_rate": 2.726705446853517e-05,
|
266 |
+
"loss": 1.5868,
|
267 |
+
"step": 21500
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 2.33,
|
271 |
+
"learning_rate": 2.6738233738762558e-05,
|
272 |
+
"loss": 1.583,
|
273 |
+
"step": 22000
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 2.38,
|
277 |
+
"learning_rate": 2.6209413008989953e-05,
|
278 |
+
"loss": 1.5835,
|
279 |
+
"step": 22500
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 2.43,
|
283 |
+
"learning_rate": 2.568164992067689e-05,
|
284 |
+
"loss": 1.5769,
|
285 |
+
"step": 23000
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 2.49,
|
289 |
+
"learning_rate": 2.5152829190904286e-05,
|
290 |
+
"loss": 1.565,
|
291 |
+
"step": 23500
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 2.54,
|
295 |
+
"learning_rate": 2.4624008461131677e-05,
|
296 |
+
"loss": 1.5741,
|
297 |
+
"step": 24000
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 2.59,
|
301 |
+
"learning_rate": 2.409518773135907e-05,
|
302 |
+
"loss": 1.5794,
|
303 |
+
"step": 24500
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 2.64,
|
307 |
+
"learning_rate": 2.3566367001586464e-05,
|
308 |
+
"loss": 1.548,
|
309 |
+
"step": 25000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 2.7,
|
313 |
+
"learning_rate": 2.3037546271813855e-05,
|
314 |
+
"loss": 1.5791,
|
315 |
+
"step": 25500
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 2.75,
|
319 |
+
"learning_rate": 2.2509783183500794e-05,
|
320 |
+
"loss": 1.5628,
|
321 |
+
"step": 26000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 2.8,
|
325 |
+
"learning_rate": 2.198096245372819e-05,
|
326 |
+
"loss": 1.5574,
|
327 |
+
"step": 26500
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 2.86,
|
331 |
+
"learning_rate": 2.145214172395558e-05,
|
332 |
+
"loss": 1.5635,
|
333 |
+
"step": 27000
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 2.91,
|
337 |
+
"learning_rate": 2.0923320994182975e-05,
|
338 |
+
"loss": 1.5682,
|
339 |
+
"step": 27500
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 2.96,
|
343 |
+
"learning_rate": 2.0394500264410367e-05,
|
344 |
+
"loss": 1.5423,
|
345 |
+
"step": 28000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 3.01,
|
349 |
+
"learning_rate": 1.986567953463776e-05,
|
350 |
+
"loss": 1.5218,
|
351 |
+
"step": 28500
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 3.07,
|
355 |
+
"learning_rate": 1.9336858804865153e-05,
|
356 |
+
"loss": 1.4528,
|
357 |
+
"step": 29000
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 3.12,
|
361 |
+
"learning_rate": 1.8808038075092545e-05,
|
362 |
+
"loss": 1.4557,
|
363 |
+
"step": 29500
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 3.17,
|
367 |
+
"learning_rate": 1.8280274986779483e-05,
|
368 |
+
"loss": 1.4418,
|
369 |
+
"step": 30000
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 3.23,
|
373 |
+
"learning_rate": 1.775251189846642e-05,
|
374 |
+
"loss": 1.4528,
|
375 |
+
"step": 30500
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 3.28,
|
379 |
+
"learning_rate": 1.7223691168693816e-05,
|
380 |
+
"loss": 1.4406,
|
381 |
+
"step": 31000
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 3.33,
|
385 |
+
"learning_rate": 1.6694870438921207e-05,
|
386 |
+
"loss": 1.4369,
|
387 |
+
"step": 31500
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 3.38,
|
391 |
+
"learning_rate": 1.6166049709148602e-05,
|
392 |
+
"loss": 1.4498,
|
393 |
+
"step": 32000
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 3.44,
|
397 |
+
"learning_rate": 1.5637228979375994e-05,
|
398 |
+
"loss": 1.4466,
|
399 |
+
"step": 32500
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 3.49,
|
403 |
+
"learning_rate": 1.5109465891062929e-05,
|
404 |
+
"loss": 1.4383,
|
405 |
+
"step": 33000
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 3.54,
|
409 |
+
"learning_rate": 1.4580645161290324e-05,
|
410 |
+
"loss": 1.4497,
|
411 |
+
"step": 33500
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 3.6,
|
415 |
+
"learning_rate": 1.4051824431517715e-05,
|
416 |
+
"loss": 1.4426,
|
417 |
+
"step": 34000
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 3.65,
|
421 |
+
"learning_rate": 1.352300370174511e-05,
|
422 |
+
"loss": 1.4311,
|
423 |
+
"step": 34500
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 3.7,
|
427 |
+
"learning_rate": 1.2994182971972502e-05,
|
428 |
+
"loss": 1.4384,
|
429 |
+
"step": 35000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 3.75,
|
433 |
+
"learning_rate": 1.2465362242199895e-05,
|
434 |
+
"loss": 1.4399,
|
435 |
+
"step": 35500
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 3.81,
|
439 |
+
"learning_rate": 1.1936541512427288e-05,
|
440 |
+
"loss": 1.4395,
|
441 |
+
"step": 36000
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 3.86,
|
445 |
+
"learning_rate": 1.1407720782654681e-05,
|
446 |
+
"loss": 1.428,
|
447 |
+
"step": 36500
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 3.91,
|
451 |
+
"learning_rate": 1.0878900052882075e-05,
|
452 |
+
"loss": 1.4439,
|
453 |
+
"step": 37000
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 3.97,
|
457 |
+
"learning_rate": 1.0351136964569011e-05,
|
458 |
+
"loss": 1.4361,
|
459 |
+
"step": 37500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 4.02,
|
463 |
+
"learning_rate": 9.822316234796404e-06,
|
464 |
+
"loss": 1.4036,
|
465 |
+
"step": 38000
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 4.07,
|
469 |
+
"learning_rate": 9.293495505023798e-06,
|
470 |
+
"loss": 1.3662,
|
471 |
+
"step": 38500
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 4.12,
|
475 |
+
"learning_rate": 8.76467477525119e-06,
|
476 |
+
"loss": 1.3538,
|
477 |
+
"step": 39000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 4.18,
|
481 |
+
"learning_rate": 8.236911686938129e-06,
|
482 |
+
"loss": 1.3632,
|
483 |
+
"step": 39500
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 4.23,
|
487 |
+
"learning_rate": 7.708090957165522e-06,
|
488 |
+
"loss": 1.3554,
|
489 |
+
"step": 40000
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 4.28,
|
493 |
+
"learning_rate": 7.1792702273929146e-06,
|
494 |
+
"loss": 1.3577,
|
495 |
+
"step": 40500
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 4.34,
|
499 |
+
"learning_rate": 6.650449497620308e-06,
|
500 |
+
"loss": 1.3537,
|
501 |
+
"step": 41000
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 4.39,
|
505 |
+
"learning_rate": 6.1216287678477e-06,
|
506 |
+
"loss": 1.3581,
|
507 |
+
"step": 41500
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 4.44,
|
511 |
+
"learning_rate": 5.5928080380750935e-06,
|
512 |
+
"loss": 1.3637,
|
513 |
+
"step": 42000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 4.49,
|
517 |
+
"learning_rate": 5.063987308302486e-06,
|
518 |
+
"loss": 1.3432,
|
519 |
+
"step": 42500
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 4.55,
|
523 |
+
"learning_rate": 4.535166578529878e-06,
|
524 |
+
"loss": 1.3463,
|
525 |
+
"step": 43000
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 4.6,
|
529 |
+
"learning_rate": 4.007403490216817e-06,
|
530 |
+
"loss": 1.3481,
|
531 |
+
"step": 43500
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 4.65,
|
535 |
+
"learning_rate": 3.4785827604442092e-06,
|
536 |
+
"loss": 1.353,
|
537 |
+
"step": 44000
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 4.71,
|
541 |
+
"learning_rate": 2.9508196721311478e-06,
|
542 |
+
"loss": 1.3505,
|
543 |
+
"step": 44500
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 4.76,
|
547 |
+
"learning_rate": 2.4219989423585406e-06,
|
548 |
+
"loss": 1.3404,
|
549 |
+
"step": 45000
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 4.81,
|
553 |
+
"learning_rate": 1.8931782125859334e-06,
|
554 |
+
"loss": 1.3574,
|
555 |
+
"step": 45500
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 4.87,
|
559 |
+
"learning_rate": 1.3643574828133265e-06,
|
560 |
+
"loss": 1.3532,
|
561 |
+
"step": 46000
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 4.92,
|
565 |
+
"learning_rate": 8.355367530407193e-07,
|
566 |
+
"loss": 1.3357,
|
567 |
+
"step": 46500
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 4.97,
|
571 |
+
"learning_rate": 3.077736647276573e-07,
|
572 |
+
"loss": 1.3374,
|
573 |
+
"step": 47000
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 5.0,
|
577 |
+
"step": 47275,
|
578 |
+
"total_flos": 7.799978327959142e+17,
|
579 |
+
"train_loss": 1.65651271519492,
|
580 |
+
"train_runtime": 12815.2129,
|
581 |
+
"train_samples_per_second": 236.094,
|
582 |
+
"train_steps_per_second": 3.689
|
583 |
+
}
|
584 |
+
],
|
585 |
+
"logging_steps": 500,
|
586 |
+
"max_steps": 47275,
|
587 |
+
"num_train_epochs": 5,
|
588 |
+
"save_steps": 10000000,
|
589 |
+
"total_flos": 7.799978327959142e+17,
|
590 |
+
"trial_name": null,
|
591 |
+
"trial_params": null
|
592 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ae11dfd4ff1695f394228d131d0d2c467887927cbded469fe87052104268103
|
3 |
+
size 4283
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|