Upload 12 files
Browse files- .gitattributes +1 -0
- config.json +35 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +219 -0
- tokenizer.json +3 -0
- tokenizer_config.json +24 -0
- trainer_state.json +886 -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": "/gpfsstore/rech/czj/uef37or/pretrained_models/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": "4.21.3",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 256206
|
| 35 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0eda85569e032db7326f7b5350690c60845a0e005a7147ffafc9c2c29932dae2
|
| 3 |
+
size 4920895691
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb5b13c12db9d1d053adca03bef97d32f9b04236472af32d39640c9d74955325
|
| 3 |
+
size 2460465095
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4c502688b3c8d100c5c91e0f011f9f000269aabe5bfb5f901ae06020c695025
|
| 3 |
+
size 14503
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8041a12f3d72b37ca186162a29f4b8011e36d4af10086c4b6cc7a28fe7221bac
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f6144e2055aa91ee2466d042f319d7046f57925b44cbcf921b2e3588a6048d1
|
| 3 |
+
size 623
|
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 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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:ed20b685c621748600c1a62798b8a4ec02527181dba1471f9bff546be8dd09ec
|
| 3 |
+
size 17331196
|
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": "/gpfsstore/rech/czj/uef37or/pretrained_models/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 +1,886 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.15070733428001404,
|
| 3 |
+
"best_model_checkpoint": "checkpoints_orfeo/checkpoint-65079",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"global_step": 65079,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 1.996542663532015e-05,
|
| 13 |
+
"loss": 1.5229,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"learning_rate": 1.99308532706403e-05,
|
| 19 |
+
"loss": 0.7443,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.21,
|
| 24 |
+
"learning_rate": 1.989627990596045e-05,
|
| 25 |
+
"loss": 0.5936,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.28,
|
| 30 |
+
"learning_rate": 1.986177568800996e-05,
|
| 31 |
+
"loss": 0.508,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.35,
|
| 36 |
+
"learning_rate": 1.982720232333011e-05,
|
| 37 |
+
"loss": 0.4597,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.41,
|
| 42 |
+
"learning_rate": 1.9792628958650257e-05,
|
| 43 |
+
"loss": 0.4274,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.48,
|
| 48 |
+
"learning_rate": 1.9758055593970406e-05,
|
| 49 |
+
"loss": 0.3898,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.55,
|
| 54 |
+
"learning_rate": 1.9723482229290554e-05,
|
| 55 |
+
"loss": 0.3645,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.62,
|
| 60 |
+
"learning_rate": 1.9688978011340064e-05,
|
| 61 |
+
"loss": 0.3486,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.69,
|
| 66 |
+
"learning_rate": 1.9654404646660216e-05,
|
| 67 |
+
"loss": 0.337,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.76,
|
| 72 |
+
"learning_rate": 1.9619831281980364e-05,
|
| 73 |
+
"loss": 0.3175,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.83,
|
| 78 |
+
"learning_rate": 1.9585257917300513e-05,
|
| 79 |
+
"loss": 0.3015,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.9,
|
| 84 |
+
"learning_rate": 1.955068455262066e-05,
|
| 85 |
+
"loss": 0.2914,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.97,
|
| 90 |
+
"learning_rate": 1.9516111187940813e-05,
|
| 91 |
+
"loss": 0.2843,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.0,
|
| 96 |
+
"eval_bleu": 83.675,
|
| 97 |
+
"eval_gen_len": 14.2653,
|
| 98 |
+
"eval_loss": 0.24304039776325226,
|
| 99 |
+
"eval_runtime": 556.3105,
|
| 100 |
+
"eval_samples_per_second": 51.762,
|
| 101 |
+
"eval_steps_per_second": 1.618,
|
| 102 |
+
"step": 7231
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.04,
|
| 106 |
+
"learning_rate": 1.948160696999032e-05,
|
| 107 |
+
"loss": 0.2721,
|
| 108 |
+
"step": 7500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.11,
|
| 112 |
+
"learning_rate": 1.944703360531047e-05,
|
| 113 |
+
"loss": 0.2533,
|
| 114 |
+
"step": 8000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.18,
|
| 118 |
+
"learning_rate": 1.941246024063062e-05,
|
| 119 |
+
"loss": 0.2493,
|
| 120 |
+
"step": 8500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.24,
|
| 124 |
+
"learning_rate": 1.937788687595077e-05,
|
| 125 |
+
"loss": 0.2444,
|
| 126 |
+
"step": 9000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.31,
|
| 130 |
+
"learning_rate": 1.9343313511270917e-05,
|
| 131 |
+
"loss": 0.2432,
|
| 132 |
+
"step": 9500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.38,
|
| 136 |
+
"learning_rate": 1.930874014659107e-05,
|
| 137 |
+
"loss": 0.2329,
|
| 138 |
+
"step": 10000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.45,
|
| 142 |
+
"learning_rate": 1.9274166781911217e-05,
|
| 143 |
+
"loss": 0.2318,
|
| 144 |
+
"step": 10500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.52,
|
| 148 |
+
"learning_rate": 1.9239662563960727e-05,
|
| 149 |
+
"loss": 0.2296,
|
| 150 |
+
"step": 11000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.59,
|
| 154 |
+
"learning_rate": 1.9205089199280876e-05,
|
| 155 |
+
"loss": 0.2297,
|
| 156 |
+
"step": 11500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.66,
|
| 160 |
+
"learning_rate": 1.9170515834601024e-05,
|
| 161 |
+
"loss": 0.2226,
|
| 162 |
+
"step": 12000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.73,
|
| 166 |
+
"learning_rate": 1.9135942469921173e-05,
|
| 167 |
+
"loss": 0.2214,
|
| 168 |
+
"step": 12500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.8,
|
| 172 |
+
"learning_rate": 1.9101369105241325e-05,
|
| 173 |
+
"loss": 0.2193,
|
| 174 |
+
"step": 13000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.87,
|
| 178 |
+
"learning_rate": 1.9066795740561473e-05,
|
| 179 |
+
"loss": 0.2141,
|
| 180 |
+
"step": 13500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.94,
|
| 184 |
+
"learning_rate": 1.903222237588162e-05,
|
| 185 |
+
"loss": 0.2121,
|
| 186 |
+
"step": 14000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.0,
|
| 190 |
+
"eval_bleu": 86.0981,
|
| 191 |
+
"eval_gen_len": 14.1714,
|
| 192 |
+
"eval_loss": 0.19072701036930084,
|
| 193 |
+
"eval_runtime": 554.6671,
|
| 194 |
+
"eval_samples_per_second": 51.916,
|
| 195 |
+
"eval_steps_per_second": 1.623,
|
| 196 |
+
"step": 14462
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.01,
|
| 200 |
+
"learning_rate": 1.899764901120177e-05,
|
| 201 |
+
"loss": 0.207,
|
| 202 |
+
"step": 14500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.07,
|
| 206 |
+
"learning_rate": 1.896314479325128e-05,
|
| 207 |
+
"loss": 0.1895,
|
| 208 |
+
"step": 15000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.14,
|
| 212 |
+
"learning_rate": 1.892857142857143e-05,
|
| 213 |
+
"loss": 0.1903,
|
| 214 |
+
"step": 15500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.21,
|
| 218 |
+
"learning_rate": 1.889399806389158e-05,
|
| 219 |
+
"loss": 0.1883,
|
| 220 |
+
"step": 16000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.28,
|
| 224 |
+
"learning_rate": 1.885942469921173e-05,
|
| 225 |
+
"loss": 0.1911,
|
| 226 |
+
"step": 16500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.35,
|
| 230 |
+
"learning_rate": 1.8824851334531877e-05,
|
| 231 |
+
"loss": 0.1912,
|
| 232 |
+
"step": 17000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.42,
|
| 236 |
+
"learning_rate": 1.8790277969852026e-05,
|
| 237 |
+
"loss": 0.1856,
|
| 238 |
+
"step": 17500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 2.49,
|
| 242 |
+
"learning_rate": 1.8755773751901536e-05,
|
| 243 |
+
"loss": 0.1836,
|
| 244 |
+
"step": 18000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.56,
|
| 248 |
+
"learning_rate": 1.8721200387221684e-05,
|
| 249 |
+
"loss": 0.1842,
|
| 250 |
+
"step": 18500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.63,
|
| 254 |
+
"learning_rate": 1.8686627022541836e-05,
|
| 255 |
+
"loss": 0.1789,
|
| 256 |
+
"step": 19000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.7,
|
| 260 |
+
"learning_rate": 1.8652053657861984e-05,
|
| 261 |
+
"loss": 0.1826,
|
| 262 |
+
"step": 19500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.77,
|
| 266 |
+
"learning_rate": 1.8617480293182133e-05,
|
| 267 |
+
"loss": 0.1793,
|
| 268 |
+
"step": 20000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.84,
|
| 272 |
+
"learning_rate": 1.8582976075231643e-05,
|
| 273 |
+
"loss": 0.1747,
|
| 274 |
+
"step": 20500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.9,
|
| 278 |
+
"learning_rate": 1.854840271055179e-05,
|
| 279 |
+
"loss": 0.1725,
|
| 280 |
+
"step": 21000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.97,
|
| 284 |
+
"learning_rate": 1.851382934587194e-05,
|
| 285 |
+
"loss": 0.1768,
|
| 286 |
+
"step": 21500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 3.0,
|
| 290 |
+
"eval_bleu": 87.1351,
|
| 291 |
+
"eval_gen_len": 14.2257,
|
| 292 |
+
"eval_loss": 0.17269779741764069,
|
| 293 |
+
"eval_runtime": 554.1036,
|
| 294 |
+
"eval_samples_per_second": 51.969,
|
| 295 |
+
"eval_steps_per_second": 1.624,
|
| 296 |
+
"step": 21693
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.04,
|
| 300 |
+
"learning_rate": 1.847925598119209e-05,
|
| 301 |
+
"loss": 0.1662,
|
| 302 |
+
"step": 22000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.11,
|
| 306 |
+
"learning_rate": 1.844468261651224e-05,
|
| 307 |
+
"loss": 0.164,
|
| 308 |
+
"step": 22500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.18,
|
| 312 |
+
"learning_rate": 1.841010925183239e-05,
|
| 313 |
+
"loss": 0.1614,
|
| 314 |
+
"step": 23000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.25,
|
| 318 |
+
"learning_rate": 1.837553588715254e-05,
|
| 319 |
+
"loss": 0.1604,
|
| 320 |
+
"step": 23500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.32,
|
| 324 |
+
"learning_rate": 1.834096252247269e-05,
|
| 325 |
+
"loss": 0.155,
|
| 326 |
+
"step": 24000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.39,
|
| 330 |
+
"learning_rate": 1.8306389157792837e-05,
|
| 331 |
+
"loss": 0.1574,
|
| 332 |
+
"step": 24500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.46,
|
| 336 |
+
"learning_rate": 1.8271884939842347e-05,
|
| 337 |
+
"loss": 0.1593,
|
| 338 |
+
"step": 25000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.53,
|
| 342 |
+
"learning_rate": 1.82373115751625e-05,
|
| 343 |
+
"loss": 0.1573,
|
| 344 |
+
"step": 25500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.6,
|
| 348 |
+
"learning_rate": 1.8202738210482648e-05,
|
| 349 |
+
"loss": 0.1561,
|
| 350 |
+
"step": 26000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.66,
|
| 354 |
+
"learning_rate": 1.8168164845802796e-05,
|
| 355 |
+
"loss": 0.1544,
|
| 356 |
+
"step": 26500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.73,
|
| 360 |
+
"learning_rate": 1.8133591481122945e-05,
|
| 361 |
+
"loss": 0.1562,
|
| 362 |
+
"step": 27000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.8,
|
| 366 |
+
"learning_rate": 1.809908726317245e-05,
|
| 367 |
+
"loss": 0.1596,
|
| 368 |
+
"step": 27500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.87,
|
| 372 |
+
"learning_rate": 1.806458304522196e-05,
|
| 373 |
+
"loss": 0.1513,
|
| 374 |
+
"step": 28000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.94,
|
| 378 |
+
"learning_rate": 1.8030009680542113e-05,
|
| 379 |
+
"loss": 0.1576,
|
| 380 |
+
"step": 28500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.0,
|
| 384 |
+
"eval_bleu": 87.7394,
|
| 385 |
+
"eval_gen_len": 14.2568,
|
| 386 |
+
"eval_loss": 0.1625259518623352,
|
| 387 |
+
"eval_runtime": 551.0375,
|
| 388 |
+
"eval_samples_per_second": 52.258,
|
| 389 |
+
"eval_steps_per_second": 1.633,
|
| 390 |
+
"step": 28924
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 4.01,
|
| 394 |
+
"learning_rate": 1.799543631586226e-05,
|
| 395 |
+
"loss": 0.1499,
|
| 396 |
+
"step": 29000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 4.08,
|
| 400 |
+
"learning_rate": 1.796086295118241e-05,
|
| 401 |
+
"loss": 0.1397,
|
| 402 |
+
"step": 29500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.15,
|
| 406 |
+
"learning_rate": 1.792635873323192e-05,
|
| 407 |
+
"loss": 0.1391,
|
| 408 |
+
"step": 30000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 4.22,
|
| 412 |
+
"learning_rate": 1.7891785368552068e-05,
|
| 413 |
+
"loss": 0.1415,
|
| 414 |
+
"step": 30500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 4.29,
|
| 418 |
+
"learning_rate": 1.7857212003872216e-05,
|
| 419 |
+
"loss": 0.1384,
|
| 420 |
+
"step": 31000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 4.36,
|
| 424 |
+
"learning_rate": 1.7822638639192368e-05,
|
| 425 |
+
"loss": 0.1397,
|
| 426 |
+
"step": 31500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 4.43,
|
| 430 |
+
"learning_rate": 1.7788065274512517e-05,
|
| 431 |
+
"loss": 0.1431,
|
| 432 |
+
"step": 32000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 4.49,
|
| 436 |
+
"learning_rate": 1.7753561056562027e-05,
|
| 437 |
+
"loss": 0.1398,
|
| 438 |
+
"step": 32500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 4.56,
|
| 442 |
+
"learning_rate": 1.7718987691882175e-05,
|
| 443 |
+
"loss": 0.1387,
|
| 444 |
+
"step": 33000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 4.63,
|
| 448 |
+
"learning_rate": 1.7684414327202324e-05,
|
| 449 |
+
"loss": 0.142,
|
| 450 |
+
"step": 33500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 4.7,
|
| 454 |
+
"learning_rate": 1.7649840962522472e-05,
|
| 455 |
+
"loss": 0.1393,
|
| 456 |
+
"step": 34000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 4.77,
|
| 460 |
+
"learning_rate": 1.7615267597842624e-05,
|
| 461 |
+
"loss": 0.1381,
|
| 462 |
+
"step": 34500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.84,
|
| 466 |
+
"learning_rate": 1.7580694233162772e-05,
|
| 467 |
+
"loss": 0.141,
|
| 468 |
+
"step": 35000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 4.91,
|
| 472 |
+
"learning_rate": 1.7546120868482924e-05,
|
| 473 |
+
"loss": 0.1369,
|
| 474 |
+
"step": 35500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 4.98,
|
| 478 |
+
"learning_rate": 1.7511547503803073e-05,
|
| 479 |
+
"loss": 0.1361,
|
| 480 |
+
"step": 36000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 5.0,
|
| 484 |
+
"eval_bleu": 88.1298,
|
| 485 |
+
"eval_gen_len": 14.2962,
|
| 486 |
+
"eval_loss": 0.1563238501548767,
|
| 487 |
+
"eval_runtime": 552.3181,
|
| 488 |
+
"eval_samples_per_second": 52.137,
|
| 489 |
+
"eval_steps_per_second": 1.629,
|
| 490 |
+
"step": 36155
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 5.05,
|
| 494 |
+
"learning_rate": 1.747697413912322e-05,
|
| 495 |
+
"loss": 0.1286,
|
| 496 |
+
"step": 36500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 5.12,
|
| 500 |
+
"learning_rate": 1.7442469921172728e-05,
|
| 501 |
+
"loss": 0.1253,
|
| 502 |
+
"step": 37000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.19,
|
| 506 |
+
"learning_rate": 1.740789655649288e-05,
|
| 507 |
+
"loss": 0.1278,
|
| 508 |
+
"step": 37500
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 5.26,
|
| 512 |
+
"learning_rate": 1.7373323191813028e-05,
|
| 513 |
+
"loss": 0.1258,
|
| 514 |
+
"step": 38000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 5.32,
|
| 518 |
+
"learning_rate": 1.733874982713318e-05,
|
| 519 |
+
"loss": 0.127,
|
| 520 |
+
"step": 38500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 5.39,
|
| 524 |
+
"learning_rate": 1.7304245609182686e-05,
|
| 525 |
+
"loss": 0.1242,
|
| 526 |
+
"step": 39000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 5.46,
|
| 530 |
+
"learning_rate": 1.7269672244502838e-05,
|
| 531 |
+
"loss": 0.1224,
|
| 532 |
+
"step": 39500
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 5.53,
|
| 536 |
+
"learning_rate": 1.7235098879822987e-05,
|
| 537 |
+
"loss": 0.1267,
|
| 538 |
+
"step": 40000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 5.6,
|
| 542 |
+
"learning_rate": 1.7200594661872493e-05,
|
| 543 |
+
"loss": 0.1275,
|
| 544 |
+
"step": 40500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 5.67,
|
| 548 |
+
"learning_rate": 1.716602129719264e-05,
|
| 549 |
+
"loss": 0.1277,
|
| 550 |
+
"step": 41000
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 5.74,
|
| 554 |
+
"learning_rate": 1.7131447932512794e-05,
|
| 555 |
+
"loss": 0.1285,
|
| 556 |
+
"step": 41500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 5.81,
|
| 560 |
+
"learning_rate": 1.7096874567832945e-05,
|
| 561 |
+
"loss": 0.126,
|
| 562 |
+
"step": 42000
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 5.88,
|
| 566 |
+
"learning_rate": 1.7062301203153094e-05,
|
| 567 |
+
"loss": 0.1246,
|
| 568 |
+
"step": 42500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 5.95,
|
| 572 |
+
"learning_rate": 1.7027727838473242e-05,
|
| 573 |
+
"loss": 0.1256,
|
| 574 |
+
"step": 43000
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.0,
|
| 578 |
+
"eval_bleu": 88.3004,
|
| 579 |
+
"eval_gen_len": 14.2442,
|
| 580 |
+
"eval_loss": 0.15259724855422974,
|
| 581 |
+
"eval_runtime": 550.8856,
|
| 582 |
+
"eval_samples_per_second": 52.272,
|
| 583 |
+
"eval_steps_per_second": 1.634,
|
| 584 |
+
"step": 43386
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.02,
|
| 588 |
+
"learning_rate": 1.699315447379339e-05,
|
| 589 |
+
"loss": 0.1258,
|
| 590 |
+
"step": 43500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.08,
|
| 594 |
+
"learning_rate": 1.695858110911354e-05,
|
| 595 |
+
"loss": 0.112,
|
| 596 |
+
"step": 44000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 6.15,
|
| 600 |
+
"learning_rate": 1.692407689116305e-05,
|
| 601 |
+
"loss": 0.1127,
|
| 602 |
+
"step": 44500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 6.22,
|
| 606 |
+
"learning_rate": 1.68895035264832e-05,
|
| 607 |
+
"loss": 0.1139,
|
| 608 |
+
"step": 45000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 6.29,
|
| 612 |
+
"learning_rate": 1.685493016180335e-05,
|
| 613 |
+
"loss": 0.1163,
|
| 614 |
+
"step": 45500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 6.36,
|
| 618 |
+
"learning_rate": 1.6820356797123498e-05,
|
| 619 |
+
"loss": 0.1157,
|
| 620 |
+
"step": 46000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 6.43,
|
| 624 |
+
"learning_rate": 1.6785783432443647e-05,
|
| 625 |
+
"loss": 0.1142,
|
| 626 |
+
"step": 46500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 6.5,
|
| 630 |
+
"learning_rate": 1.67512100677638e-05,
|
| 631 |
+
"loss": 0.1123,
|
| 632 |
+
"step": 47000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.57,
|
| 636 |
+
"learning_rate": 1.6716636703083947e-05,
|
| 637 |
+
"loss": 0.1135,
|
| 638 |
+
"step": 47500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 6.64,
|
| 642 |
+
"learning_rate": 1.6682063338404095e-05,
|
| 643 |
+
"loss": 0.1146,
|
| 644 |
+
"step": 48000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 6.71,
|
| 648 |
+
"learning_rate": 1.6647489973724244e-05,
|
| 649 |
+
"loss": 0.1159,
|
| 650 |
+
"step": 48500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 6.78,
|
| 654 |
+
"learning_rate": 1.6612916609044392e-05,
|
| 655 |
+
"loss": 0.1157,
|
| 656 |
+
"step": 49000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 6.85,
|
| 660 |
+
"learning_rate": 1.6578343244364544e-05,
|
| 661 |
+
"loss": 0.1148,
|
| 662 |
+
"step": 49500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.91,
|
| 666 |
+
"learning_rate": 1.6543769879684693e-05,
|
| 667 |
+
"loss": 0.1139,
|
| 668 |
+
"step": 50000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 6.98,
|
| 672 |
+
"learning_rate": 1.6509265661734203e-05,
|
| 673 |
+
"loss": 0.1164,
|
| 674 |
+
"step": 50500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.0,
|
| 678 |
+
"eval_bleu": 88.4796,
|
| 679 |
+
"eval_gen_len": 14.2928,
|
| 680 |
+
"eval_loss": 0.15147347748279572,
|
| 681 |
+
"eval_runtime": 552.236,
|
| 682 |
+
"eval_samples_per_second": 52.144,
|
| 683 |
+
"eval_steps_per_second": 1.63,
|
| 684 |
+
"step": 50617
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 7.05,
|
| 688 |
+
"learning_rate": 1.647469229705435e-05,
|
| 689 |
+
"loss": 0.1055,
|
| 690 |
+
"step": 51000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 7.12,
|
| 694 |
+
"learning_rate": 1.64401189323745e-05,
|
| 695 |
+
"loss": 0.1028,
|
| 696 |
+
"step": 51500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 7.19,
|
| 700 |
+
"learning_rate": 1.640561471442401e-05,
|
| 701 |
+
"loss": 0.1055,
|
| 702 |
+
"step": 52000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 7.26,
|
| 706 |
+
"learning_rate": 1.6371041349744158e-05,
|
| 707 |
+
"loss": 0.105,
|
| 708 |
+
"step": 52500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 7.33,
|
| 712 |
+
"learning_rate": 1.6336537131793668e-05,
|
| 713 |
+
"loss": 0.1052,
|
| 714 |
+
"step": 53000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 7.4,
|
| 718 |
+
"learning_rate": 1.6301963767113816e-05,
|
| 719 |
+
"loss": 0.1063,
|
| 720 |
+
"step": 53500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 7.47,
|
| 724 |
+
"learning_rate": 1.6267390402433968e-05,
|
| 725 |
+
"loss": 0.1048,
|
| 726 |
+
"step": 54000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 7.54,
|
| 730 |
+
"learning_rate": 1.6232817037754117e-05,
|
| 731 |
+
"loss": 0.1073,
|
| 732 |
+
"step": 54500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 7.61,
|
| 736 |
+
"learning_rate": 1.6198243673074265e-05,
|
| 737 |
+
"loss": 0.106,
|
| 738 |
+
"step": 55000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 7.68,
|
| 742 |
+
"learning_rate": 1.6163670308394413e-05,
|
| 743 |
+
"loss": 0.1036,
|
| 744 |
+
"step": 55500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 7.74,
|
| 748 |
+
"learning_rate": 1.6129096943714565e-05,
|
| 749 |
+
"loss": 0.1057,
|
| 750 |
+
"step": 56000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 7.81,
|
| 754 |
+
"learning_rate": 1.6094592725764072e-05,
|
| 755 |
+
"loss": 0.1051,
|
| 756 |
+
"step": 56500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 7.88,
|
| 760 |
+
"learning_rate": 1.6060019361084224e-05,
|
| 761 |
+
"loss": 0.1057,
|
| 762 |
+
"step": 57000
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 7.95,
|
| 766 |
+
"learning_rate": 1.6025445996404372e-05,
|
| 767 |
+
"loss": 0.1051,
|
| 768 |
+
"step": 57500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 8.0,
|
| 772 |
+
"eval_bleu": 88.7364,
|
| 773 |
+
"eval_gen_len": 14.3991,
|
| 774 |
+
"eval_loss": 0.1514560878276825,
|
| 775 |
+
"eval_runtime": 559.4528,
|
| 776 |
+
"eval_samples_per_second": 51.472,
|
| 777 |
+
"eval_steps_per_second": 1.609,
|
| 778 |
+
"step": 57848
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 8.02,
|
| 782 |
+
"learning_rate": 1.599087263172452e-05,
|
| 783 |
+
"loss": 0.103,
|
| 784 |
+
"step": 58000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 8.09,
|
| 788 |
+
"learning_rate": 1.595629926704467e-05,
|
| 789 |
+
"loss": 0.0925,
|
| 790 |
+
"step": 58500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 8.16,
|
| 794 |
+
"learning_rate": 1.592172590236482e-05,
|
| 795 |
+
"loss": 0.0942,
|
| 796 |
+
"step": 59000
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 8.23,
|
| 800 |
+
"learning_rate": 1.588715253768497e-05,
|
| 801 |
+
"loss": 0.0965,
|
| 802 |
+
"step": 59500
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 8.3,
|
| 806 |
+
"learning_rate": 1.585264831973448e-05,
|
| 807 |
+
"loss": 0.0952,
|
| 808 |
+
"step": 60000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 8.37,
|
| 812 |
+
"learning_rate": 1.5818074955054628e-05,
|
| 813 |
+
"loss": 0.0967,
|
| 814 |
+
"step": 60500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 8.44,
|
| 818 |
+
"learning_rate": 1.5783501590374776e-05,
|
| 819 |
+
"loss": 0.0957,
|
| 820 |
+
"step": 61000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 8.51,
|
| 824 |
+
"learning_rate": 1.5748928225694925e-05,
|
| 825 |
+
"loss": 0.0938,
|
| 826 |
+
"step": 61500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 8.57,
|
| 830 |
+
"learning_rate": 1.5714354861015077e-05,
|
| 831 |
+
"loss": 0.0981,
|
| 832 |
+
"step": 62000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 8.64,
|
| 836 |
+
"learning_rate": 1.5679781496335225e-05,
|
| 837 |
+
"loss": 0.1008,
|
| 838 |
+
"step": 62500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 8.71,
|
| 842 |
+
"learning_rate": 1.5645208131655374e-05,
|
| 843 |
+
"loss": 0.0987,
|
| 844 |
+
"step": 63000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 8.78,
|
| 848 |
+
"learning_rate": 1.5610703913704883e-05,
|
| 849 |
+
"loss": 0.0985,
|
| 850 |
+
"step": 63500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 8.85,
|
| 854 |
+
"learning_rate": 1.5576130549025032e-05,
|
| 855 |
+
"loss": 0.097,
|
| 856 |
+
"step": 64000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 8.92,
|
| 860 |
+
"learning_rate": 1.554155718434518e-05,
|
| 861 |
+
"loss": 0.0985,
|
| 862 |
+
"step": 64500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 8.99,
|
| 866 |
+
"learning_rate": 1.5506983819665332e-05,
|
| 867 |
+
"loss": 0.0966,
|
| 868 |
+
"step": 65000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 9.0,
|
| 872 |
+
"eval_bleu": 88.826,
|
| 873 |
+
"eval_gen_len": 14.3624,
|
| 874 |
+
"eval_loss": 0.15070733428001404,
|
| 875 |
+
"eval_runtime": 553.1909,
|
| 876 |
+
"eval_samples_per_second": 52.054,
|
| 877 |
+
"eval_steps_per_second": 1.627,
|
| 878 |
+
"step": 65079
|
| 879 |
+
}
|
| 880 |
+
],
|
| 881 |
+
"max_steps": 289240,
|
| 882 |
+
"num_train_epochs": 40,
|
| 883 |
+
"total_flos": 2.004229422148485e+17,
|
| 884 |
+
"trial_name": null,
|
| 885 |
+
"trial_params": null
|
| 886 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d37fb052d2b19dd939ee4a5a2f12697ce68af24b9813aff491fcd50eef5d2023
|
| 3 |
+
size 3439
|