Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +34 -0
- generation_config.json +8 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +220 -0
- tokenizer.json +3 -0
- tokenizer_config.json +25 -0
- trainer_state.json +276 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "checkpoint-53168",
|
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": 8192,
|
13 |
+
"decoder_layerdrop": 0,
|
14 |
+
"decoder_layers": 24,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 16,
|
18 |
+
"encoder_ffn_dim": 8192,
|
19 |
+
"encoder_layerdrop": 0,
|
20 |
+
"encoder_layers": 24,
|
21 |
+
"eos_token_id": 2,
|
22 |
+
"init_std": 0.02,
|
23 |
+
"is_encoder_decoder": true,
|
24 |
+
"max_length": 200,
|
25 |
+
"max_position_embeddings": 1024,
|
26 |
+
"model_type": "m2m_100",
|
27 |
+
"num_hidden_layers": 24,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"scale_embedding": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.31.0",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 256206
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 200,
|
6 |
+
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.31.0"
|
8 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88d7098c6d88733cea062740fbbf6f691ff82c156e4e34c1abebb1297cd6f3b6
|
3 |
+
size 10965715027
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38820a77c622a03563be28191b1c502830a8dc5eaddb395fcdfaffe07029e49a
|
3 |
+
size 5482902982
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e95e409639f9c9d88073775f84c96a6033aff88b2547cc693ba9c7e7536cd4f
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e76e819a0e81bcdfbc2387da3e713f3ec92d981087df2402fe03a386d40c70b
|
3 |
+
size 627
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
|
3 |
+
size 4852054
|
special_tokens_map.json
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"ace_Arab",
|
4 |
+
"ace_Latn",
|
5 |
+
"acm_Arab",
|
6 |
+
"acq_Arab",
|
7 |
+
"aeb_Arab",
|
8 |
+
"afr_Latn",
|
9 |
+
"ajp_Arab",
|
10 |
+
"aka_Latn",
|
11 |
+
"amh_Ethi",
|
12 |
+
"apc_Arab",
|
13 |
+
"arb_Arab",
|
14 |
+
"ars_Arab",
|
15 |
+
"ary_Arab",
|
16 |
+
"arz_Arab",
|
17 |
+
"asm_Beng",
|
18 |
+
"ast_Latn",
|
19 |
+
"awa_Deva",
|
20 |
+
"ayr_Latn",
|
21 |
+
"azb_Arab",
|
22 |
+
"azj_Latn",
|
23 |
+
"bak_Cyrl",
|
24 |
+
"bam_Latn",
|
25 |
+
"ban_Latn",
|
26 |
+
"bel_Cyrl",
|
27 |
+
"bem_Latn",
|
28 |
+
"ben_Beng",
|
29 |
+
"bho_Deva",
|
30 |
+
"bjn_Arab",
|
31 |
+
"bjn_Latn",
|
32 |
+
"bod_Tibt",
|
33 |
+
"bos_Latn",
|
34 |
+
"bug_Latn",
|
35 |
+
"bul_Cyrl",
|
36 |
+
"cat_Latn",
|
37 |
+
"ceb_Latn",
|
38 |
+
"ces_Latn",
|
39 |
+
"cjk_Latn",
|
40 |
+
"ckb_Arab",
|
41 |
+
"crh_Latn",
|
42 |
+
"cym_Latn",
|
43 |
+
"dan_Latn",
|
44 |
+
"deu_Latn",
|
45 |
+
"dik_Latn",
|
46 |
+
"dyu_Latn",
|
47 |
+
"dzo_Tibt",
|
48 |
+
"ell_Grek",
|
49 |
+
"eng_Latn",
|
50 |
+
"epo_Latn",
|
51 |
+
"est_Latn",
|
52 |
+
"eus_Latn",
|
53 |
+
"ewe_Latn",
|
54 |
+
"fao_Latn",
|
55 |
+
"pes_Arab",
|
56 |
+
"fij_Latn",
|
57 |
+
"fin_Latn",
|
58 |
+
"fon_Latn",
|
59 |
+
"fra_Latn",
|
60 |
+
"fur_Latn",
|
61 |
+
"fuv_Latn",
|
62 |
+
"gla_Latn",
|
63 |
+
"gle_Latn",
|
64 |
+
"glg_Latn",
|
65 |
+
"grn_Latn",
|
66 |
+
"guj_Gujr",
|
67 |
+
"hat_Latn",
|
68 |
+
"hau_Latn",
|
69 |
+
"heb_Hebr",
|
70 |
+
"hin_Deva",
|
71 |
+
"hne_Deva",
|
72 |
+
"hrv_Latn",
|
73 |
+
"hun_Latn",
|
74 |
+
"hye_Armn",
|
75 |
+
"ibo_Latn",
|
76 |
+
"ilo_Latn",
|
77 |
+
"ind_Latn",
|
78 |
+
"isl_Latn",
|
79 |
+
"ita_Latn",
|
80 |
+
"jav_Latn",
|
81 |
+
"jpn_Jpan",
|
82 |
+
"kab_Latn",
|
83 |
+
"kac_Latn",
|
84 |
+
"kam_Latn",
|
85 |
+
"kan_Knda",
|
86 |
+
"kas_Arab",
|
87 |
+
"kas_Deva",
|
88 |
+
"kat_Geor",
|
89 |
+
"knc_Arab",
|
90 |
+
"knc_Latn",
|
91 |
+
"kaz_Cyrl",
|
92 |
+
"kbp_Latn",
|
93 |
+
"kea_Latn",
|
94 |
+
"khm_Khmr",
|
95 |
+
"kik_Latn",
|
96 |
+
"kin_Latn",
|
97 |
+
"kir_Cyrl",
|
98 |
+
"kmb_Latn",
|
99 |
+
"kon_Latn",
|
100 |
+
"kor_Hang",
|
101 |
+
"kmr_Latn",
|
102 |
+
"lao_Laoo",
|
103 |
+
"lvs_Latn",
|
104 |
+
"lij_Latn",
|
105 |
+
"lim_Latn",
|
106 |
+
"lin_Latn",
|
107 |
+
"lit_Latn",
|
108 |
+
"lmo_Latn",
|
109 |
+
"ltg_Latn",
|
110 |
+
"ltz_Latn",
|
111 |
+
"lua_Latn",
|
112 |
+
"lug_Latn",
|
113 |
+
"luo_Latn",
|
114 |
+
"lus_Latn",
|
115 |
+
"mag_Deva",
|
116 |
+
"mai_Deva",
|
117 |
+
"mal_Mlym",
|
118 |
+
"mar_Deva",
|
119 |
+
"min_Latn",
|
120 |
+
"mkd_Cyrl",
|
121 |
+
"plt_Latn",
|
122 |
+
"mlt_Latn",
|
123 |
+
"mni_Beng",
|
124 |
+
"khk_Cyrl",
|
125 |
+
"mos_Latn",
|
126 |
+
"mri_Latn",
|
127 |
+
"zsm_Latn",
|
128 |
+
"mya_Mymr",
|
129 |
+
"nld_Latn",
|
130 |
+
"nno_Latn",
|
131 |
+
"nob_Latn",
|
132 |
+
"npi_Deva",
|
133 |
+
"nso_Latn",
|
134 |
+
"nus_Latn",
|
135 |
+
"nya_Latn",
|
136 |
+
"oci_Latn",
|
137 |
+
"gaz_Latn",
|
138 |
+
"ory_Orya",
|
139 |
+
"pag_Latn",
|
140 |
+
"pan_Guru",
|
141 |
+
"pap_Latn",
|
142 |
+
"pol_Latn",
|
143 |
+
"por_Latn",
|
144 |
+
"prs_Arab",
|
145 |
+
"pbt_Arab",
|
146 |
+
"quy_Latn",
|
147 |
+
"ron_Latn",
|
148 |
+
"run_Latn",
|
149 |
+
"rus_Cyrl",
|
150 |
+
"sag_Latn",
|
151 |
+
"san_Deva",
|
152 |
+
"sat_Beng",
|
153 |
+
"scn_Latn",
|
154 |
+
"shn_Mymr",
|
155 |
+
"sin_Sinh",
|
156 |
+
"slk_Latn",
|
157 |
+
"slv_Latn",
|
158 |
+
"smo_Latn",
|
159 |
+
"sna_Latn",
|
160 |
+
"snd_Arab",
|
161 |
+
"som_Latn",
|
162 |
+
"sot_Latn",
|
163 |
+
"spa_Latn",
|
164 |
+
"als_Latn",
|
165 |
+
"srd_Latn",
|
166 |
+
"srp_Cyrl",
|
167 |
+
"ssw_Latn",
|
168 |
+
"sun_Latn",
|
169 |
+
"swe_Latn",
|
170 |
+
"swh_Latn",
|
171 |
+
"szl_Latn",
|
172 |
+
"tam_Taml",
|
173 |
+
"tat_Cyrl",
|
174 |
+
"tel_Telu",
|
175 |
+
"tgk_Cyrl",
|
176 |
+
"tgl_Latn",
|
177 |
+
"tha_Thai",
|
178 |
+
"tir_Ethi",
|
179 |
+
"taq_Latn",
|
180 |
+
"taq_Tfng",
|
181 |
+
"tpi_Latn",
|
182 |
+
"tsn_Latn",
|
183 |
+
"tso_Latn",
|
184 |
+
"tuk_Latn",
|
185 |
+
"tum_Latn",
|
186 |
+
"tur_Latn",
|
187 |
+
"twi_Latn",
|
188 |
+
"tzm_Tfng",
|
189 |
+
"uig_Arab",
|
190 |
+
"ukr_Cyrl",
|
191 |
+
"umb_Latn",
|
192 |
+
"urd_Arab",
|
193 |
+
"uzn_Latn",
|
194 |
+
"vec_Latn",
|
195 |
+
"vie_Latn",
|
196 |
+
"war_Latn",
|
197 |
+
"wol_Latn",
|
198 |
+
"xho_Latn",
|
199 |
+
"ydd_Hebr",
|
200 |
+
"yor_Latn",
|
201 |
+
"yue_Hant",
|
202 |
+
"zho_Hans",
|
203 |
+
"zho_Hant",
|
204 |
+
"zul_Latn"
|
205 |
+
],
|
206 |
+
"bos_token": "<s>",
|
207 |
+
"cls_token": "<s>",
|
208 |
+
"eos_token": "</s>",
|
209 |
+
"mask_token": {
|
210 |
+
"content": "<mask>",
|
211 |
+
"lstrip": true,
|
212 |
+
"normalized": true,
|
213 |
+
"rstrip": false,
|
214 |
+
"single_word": false
|
215 |
+
},
|
216 |
+
"pad_token": "<pad>",
|
217 |
+
"sep_token": "</s>",
|
218 |
+
"unk_token": "<unk>"
|
219 |
+
}
|
220 |
+
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e316b82de11d0f951f370943b3c438311629547285129b0b81dadabd01bca665
|
3 |
+
size 17331176
|
tokenizer_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 1024,
|
15 |
+
"name_or_path": "facebook/nllb-200-distilled-600M",
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"special_tokens_map_file": null,
|
20 |
+
"src_lang": null,
|
21 |
+
"tgt_lang": null,
|
22 |
+
"tokenizer_class": "NllbTokenizer",
|
23 |
+
"unk_token": "<unk>"
|
24 |
+
}
|
25 |
+
|
trainer_state.json
ADDED
@@ -0,0 +1,276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 19806,
|
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": 4.87377562354842e-05,
|
13 |
+
"loss": 0.5877,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.1,
|
18 |
+
"learning_rate": 4.74755124709684e-05,
|
19 |
+
"loss": 0.6317,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.15,
|
24 |
+
"learning_rate": 4.6213268706452596e-05,
|
25 |
+
"loss": 0.6456,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.2,
|
30 |
+
"learning_rate": 4.4951024941936785e-05,
|
31 |
+
"loss": 0.6473,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.25,
|
36 |
+
"learning_rate": 4.368878117742099e-05,
|
37 |
+
"loss": 0.6499,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.3,
|
42 |
+
"learning_rate": 4.242653741290518e-05,
|
43 |
+
"loss": 0.6602,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.35,
|
48 |
+
"learning_rate": 4.116429364838938e-05,
|
49 |
+
"loss": 0.6699,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.4,
|
54 |
+
"learning_rate": 3.9902049883873574e-05,
|
55 |
+
"loss": 0.6624,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.45,
|
60 |
+
"learning_rate": 3.8639806119357776e-05,
|
61 |
+
"loss": 0.651,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.5,
|
66 |
+
"learning_rate": 3.7377562354841965e-05,
|
67 |
+
"loss": 0.6709,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.56,
|
72 |
+
"learning_rate": 3.611531859032616e-05,
|
73 |
+
"loss": 0.6582,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.61,
|
78 |
+
"learning_rate": 3.485307482581036e-05,
|
79 |
+
"loss": 0.6698,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.66,
|
84 |
+
"learning_rate": 3.359083106129456e-05,
|
85 |
+
"loss": 0.6522,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.71,
|
90 |
+
"learning_rate": 3.2328587296778754e-05,
|
91 |
+
"loss": 0.6863,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.76,
|
96 |
+
"learning_rate": 3.1066343532262956e-05,
|
97 |
+
"loss": 0.6602,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.81,
|
102 |
+
"learning_rate": 2.9804099767747152e-05,
|
103 |
+
"loss": 0.6466,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.86,
|
108 |
+
"learning_rate": 2.8541856003231344e-05,
|
109 |
+
"loss": 0.7011,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.91,
|
114 |
+
"learning_rate": 2.727961223871554e-05,
|
115 |
+
"loss": 0.677,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.96,
|
120 |
+
"learning_rate": 2.601736847419974e-05,
|
121 |
+
"loss": 0.6581,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.0,
|
126 |
+
"eval_bleu": 30.9028,
|
127 |
+
"eval_chrf++": 57.3001,
|
128 |
+
"eval_gen_len": 27.1266,
|
129 |
+
"eval_loss": 1.247955083847046,
|
130 |
+
"eval_runtime": 1316.7682,
|
131 |
+
"eval_samples_per_second": 3.718,
|
132 |
+
"eval_spbleu": 43.0506,
|
133 |
+
"eval_steps_per_second": 0.744,
|
134 |
+
"eval_ter": 59.7925,
|
135 |
+
"step": 9903
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.01,
|
139 |
+
"learning_rate": 2.4755124709683934e-05,
|
140 |
+
"loss": 0.6144,
|
141 |
+
"step": 10000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.06,
|
145 |
+
"learning_rate": 2.3492880945168133e-05,
|
146 |
+
"loss": 0.4286,
|
147 |
+
"step": 10500
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 1.11,
|
151 |
+
"learning_rate": 2.223063718065233e-05,
|
152 |
+
"loss": 0.4329,
|
153 |
+
"step": 11000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 1.16,
|
157 |
+
"learning_rate": 2.0968393416136524e-05,
|
158 |
+
"loss": 0.4324,
|
159 |
+
"step": 11500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 1.21,
|
163 |
+
"learning_rate": 1.9706149651620723e-05,
|
164 |
+
"loss": 0.4403,
|
165 |
+
"step": 12000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.26,
|
169 |
+
"learning_rate": 1.844390588710492e-05,
|
170 |
+
"loss": 0.4353,
|
171 |
+
"step": 12500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 1.31,
|
175 |
+
"learning_rate": 1.7181662122589115e-05,
|
176 |
+
"loss": 0.4312,
|
177 |
+
"step": 13000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.36,
|
181 |
+
"learning_rate": 1.5919418358073314e-05,
|
182 |
+
"loss": 0.4212,
|
183 |
+
"step": 13500
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 1.41,
|
187 |
+
"learning_rate": 1.4657174593557507e-05,
|
188 |
+
"loss": 0.4158,
|
189 |
+
"step": 14000
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 1.46,
|
193 |
+
"learning_rate": 1.3394930829041705e-05,
|
194 |
+
"loss": 0.4061,
|
195 |
+
"step": 14500
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.51,
|
199 |
+
"learning_rate": 1.2132687064525902e-05,
|
200 |
+
"loss": 0.4202,
|
201 |
+
"step": 15000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 1.57,
|
205 |
+
"learning_rate": 1.0870443300010098e-05,
|
206 |
+
"loss": 0.4448,
|
207 |
+
"step": 15500
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.62,
|
211 |
+
"learning_rate": 9.608199535494297e-06,
|
212 |
+
"loss": 0.4351,
|
213 |
+
"step": 16000
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 1.67,
|
217 |
+
"learning_rate": 8.345955770978492e-06,
|
218 |
+
"loss": 0.4072,
|
219 |
+
"step": 16500
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.72,
|
223 |
+
"learning_rate": 7.083712006462688e-06,
|
224 |
+
"loss": 0.4157,
|
225 |
+
"step": 17000
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.77,
|
229 |
+
"learning_rate": 5.821468241946885e-06,
|
230 |
+
"loss": 0.4338,
|
231 |
+
"step": 17500
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.82,
|
235 |
+
"learning_rate": 4.559224477431081e-06,
|
236 |
+
"loss": 0.4212,
|
237 |
+
"step": 18000
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.87,
|
241 |
+
"learning_rate": 3.2969807129152782e-06,
|
242 |
+
"loss": 0.411,
|
243 |
+
"step": 18500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.92,
|
247 |
+
"learning_rate": 2.0347369483994747e-06,
|
248 |
+
"loss": 0.4179,
|
249 |
+
"step": 19000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.97,
|
253 |
+
"learning_rate": 7.724931838836716e-07,
|
254 |
+
"loss": 0.4255,
|
255 |
+
"step": 19500
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 2.0,
|
259 |
+
"eval_bleu": 31.3408,
|
260 |
+
"eval_chrf++": 57.4539,
|
261 |
+
"eval_gen_len": 27.0633,
|
262 |
+
"eval_loss": 1.3426777124404907,
|
263 |
+
"eval_runtime": 1310.3387,
|
264 |
+
"eval_samples_per_second": 3.736,
|
265 |
+
"eval_spbleu": 43.1979,
|
266 |
+
"eval_steps_per_second": 0.748,
|
267 |
+
"eval_ter": 59.0383,
|
268 |
+
"step": 19806
|
269 |
+
}
|
270 |
+
],
|
271 |
+
"max_steps": 19806,
|
272 |
+
"num_train_epochs": 2,
|
273 |
+
"total_flos": 8.428883485392896e+16,
|
274 |
+
"trial_name": null,
|
275 |
+
"trial_params": null
|
276 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef1aa6540cbe88561036b418b0031f6e178a7ac67e834c2ad5e6a5eab47c9017
|
3 |
+
size 4091
|