Upload 11 files
Browse files- .gitattributes +1 -0
- config.json +35 -0
- generation_config.json +9 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +219 -0
- tokenizer.json +3 -0
- tokenizer_config.json +24 -0
- trainer_state.json +230 -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 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/nllb-200-distilled-600M",
|
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,
|
14 |
+
"decoder_layers": 12,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 16,
|
18 |
+
"encoder_ffn_dim": 4096,
|
19 |
+
"encoder_layerdrop": 0,
|
20 |
+
"encoder_layers": 12,
|
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": 12,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"scale_embedding": true,
|
30 |
+
"tokenizer_class": "NllbTokenizer",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.30.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 256206
|
35 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"max_length": 200,
|
7 |
+
"pad_token_id": 1,
|
8 |
+
"transformers_version": "4.30.2"
|
9 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe7bcf7f44d4c29dd0cc342142cc27d530e7bf9a86ac4d3a56ce28c70555e687
|
3 |
+
size 4920898372
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20909eee6ef004f627e5576cc2a10cf462785bd1634828f52744538d1a61e22d
|
3 |
+
size 2468874822
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b17573dd1396c9f4fd6dbb0fa7f603421b1472b932c35d17ecec5384171364c6
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b22cd2fc45f5b9171a57629b33c06034f8187a0d3e18d3222146e05c7af6fd7
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
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 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,230 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.844827586206897,
|
5 |
+
"global_step": 16500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.09,
|
12 |
+
"learning_rate": 1.942873563218391e-05,
|
13 |
+
"loss": 5.5518,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.17,
|
18 |
+
"learning_rate": 1.885402298850575e-05,
|
19 |
+
"loss": 0.3979,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.26,
|
24 |
+
"learning_rate": 1.8279310344827587e-05,
|
25 |
+
"loss": 0.1115,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.34,
|
30 |
+
"learning_rate": 1.7704597701149427e-05,
|
31 |
+
"loss": 0.1044,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.43,
|
36 |
+
"learning_rate": 1.7129885057471266e-05,
|
37 |
+
"loss": 0.0986,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.52,
|
42 |
+
"learning_rate": 1.6555172413793105e-05,
|
43 |
+
"loss": 0.0899,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.6,
|
48 |
+
"learning_rate": 1.5980459770114944e-05,
|
49 |
+
"loss": 0.0872,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.69,
|
54 |
+
"learning_rate": 1.5405747126436783e-05,
|
55 |
+
"loss": 0.085,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.78,
|
60 |
+
"learning_rate": 1.4831034482758623e-05,
|
61 |
+
"loss": 0.0869,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.86,
|
66 |
+
"learning_rate": 1.425632183908046e-05,
|
67 |
+
"loss": 0.0879,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.95,
|
72 |
+
"learning_rate": 1.36816091954023e-05,
|
73 |
+
"loss": 0.0797,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.0,
|
78 |
+
"eval_loss": 0.07041613757610321,
|
79 |
+
"eval_runtime": 64.4372,
|
80 |
+
"eval_samples_per_second": 40.008,
|
81 |
+
"eval_steps_per_second": 10.01,
|
82 |
+
"step": 5800
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 1.03,
|
86 |
+
"learning_rate": 1.310689655172414e-05,
|
87 |
+
"loss": 0.079,
|
88 |
+
"step": 6000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.12,
|
92 |
+
"learning_rate": 1.253218390804598e-05,
|
93 |
+
"loss": 0.071,
|
94 |
+
"step": 6500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.21,
|
98 |
+
"learning_rate": 1.1957471264367817e-05,
|
99 |
+
"loss": 0.0701,
|
100 |
+
"step": 7000
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.29,
|
104 |
+
"learning_rate": 1.1382758620689656e-05,
|
105 |
+
"loss": 0.0739,
|
106 |
+
"step": 7500
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 1.38,
|
110 |
+
"learning_rate": 1.0808045977011495e-05,
|
111 |
+
"loss": 0.0723,
|
112 |
+
"step": 8000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 1.47,
|
116 |
+
"learning_rate": 1.0233333333333336e-05,
|
117 |
+
"loss": 0.0682,
|
118 |
+
"step": 8500
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 1.55,
|
122 |
+
"learning_rate": 9.658620689655173e-06,
|
123 |
+
"loss": 0.068,
|
124 |
+
"step": 9000
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 1.64,
|
128 |
+
"learning_rate": 9.083908045977013e-06,
|
129 |
+
"loss": 0.0686,
|
130 |
+
"step": 9500
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.72,
|
134 |
+
"learning_rate": 8.509195402298852e-06,
|
135 |
+
"loss": 0.0662,
|
136 |
+
"step": 10000
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 1.81,
|
140 |
+
"learning_rate": 7.934482758620691e-06,
|
141 |
+
"loss": 0.0671,
|
142 |
+
"step": 10500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.9,
|
146 |
+
"learning_rate": 7.359770114942529e-06,
|
147 |
+
"loss": 0.0684,
|
148 |
+
"step": 11000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 1.98,
|
152 |
+
"learning_rate": 6.785057471264368e-06,
|
153 |
+
"loss": 0.0669,
|
154 |
+
"step": 11500
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 2.0,
|
158 |
+
"eval_loss": 0.06483030319213867,
|
159 |
+
"eval_runtime": 64.5114,
|
160 |
+
"eval_samples_per_second": 39.962,
|
161 |
+
"eval_steps_per_second": 9.998,
|
162 |
+
"step": 11600
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 2.07,
|
166 |
+
"learning_rate": 6.211494252873563e-06,
|
167 |
+
"loss": 0.062,
|
168 |
+
"step": 12000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 2.16,
|
172 |
+
"learning_rate": 5.636781609195403e-06,
|
173 |
+
"loss": 0.061,
|
174 |
+
"step": 12500
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.24,
|
178 |
+
"learning_rate": 5.062068965517242e-06,
|
179 |
+
"loss": 0.0581,
|
180 |
+
"step": 13000
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 2.33,
|
184 |
+
"learning_rate": 4.487356321839081e-06,
|
185 |
+
"loss": 0.0575,
|
186 |
+
"step": 13500
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 2.41,
|
190 |
+
"learning_rate": 3.913793103448276e-06,
|
191 |
+
"loss": 0.0643,
|
192 |
+
"step": 14000
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 2.5,
|
196 |
+
"learning_rate": 3.3390804597701155e-06,
|
197 |
+
"loss": 0.0623,
|
198 |
+
"step": 14500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.59,
|
202 |
+
"learning_rate": 2.764367816091954e-06,
|
203 |
+
"loss": 0.0565,
|
204 |
+
"step": 15000
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 2.67,
|
208 |
+
"learning_rate": 2.1896551724137934e-06,
|
209 |
+
"loss": 0.0592,
|
210 |
+
"step": 15500
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 2.76,
|
214 |
+
"learning_rate": 1.6149425287356323e-06,
|
215 |
+
"loss": 0.0627,
|
216 |
+
"step": 16000
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 2.84,
|
220 |
+
"learning_rate": 1.0402298850574713e-06,
|
221 |
+
"loss": 0.0565,
|
222 |
+
"step": 16500
|
223 |
+
}
|
224 |
+
],
|
225 |
+
"max_steps": 17400,
|
226 |
+
"num_train_epochs": 3,
|
227 |
+
"total_flos": 3.575505883024589e+16,
|
228 |
+
"trial_name": null,
|
229 |
+
"trial_params": null
|
230 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9bbdb248063ae18680f88926ff76113d9e472a12817e20504cc0231790fd78f
|
3 |
+
size 4536
|