Upload 11 files
Browse files- .gitattributes +1 -0
- config.json +35 -0
- generation_config.json +8 -0
- pytorch_model.bin +3 -0
- rng_state.pth +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 +1372 -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": "4.32.1",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 256206
|
| 35 |
+
}
|
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": "4.32.1"
|
| 8 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6898506f3c102a1f6e48cf201f1e3b96dc6d7bbb28a9587b6c3bb3614aa28ab9
|
| 3 |
+
size 2460469182
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25772a151b7d17fd11a98507401e7c15dfd41da42bcdaa4af0a563fdc30b5799
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fddbd70ca32e254cd4ea3865389dcbce1c04e82f577c61ae350f154ff4e2dff
|
| 3 |
+
size 1064
|
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 sha256:643ad36f91931f94a61d683ee8465d3b96ad53133f13cfa6594335b79ed88b77
|
| 3 |
+
size 17331491
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"legacy_behaviour": false,
|
| 8 |
+
"mask_token": {
|
| 9 |
+
"__type": "AddedToken",
|
| 10 |
+
"content": "<mask>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"model_max_length": 1024,
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"sep_token": "</s>",
|
| 19 |
+
"sp_model_kwargs": {},
|
| 20 |
+
"src_lang": "eng_Latn",
|
| 21 |
+
"tgt_lang": null,
|
| 22 |
+
"tokenizer_class": "NllbTokenizer",
|
| 23 |
+
"unk_token": "<unk>"
|
| 24 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1372 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6904399394989014,
|
| 3 |
+
"best_model_checkpoint": "nllb_200_distilled_600M_ENtoFO_bsz_64_epochs_10lr7e-05/checkpoint-16500",
|
| 4 |
+
"epoch": 5.798947842417985,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 16500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 1.4e-05,
|
| 14 |
+
"loss": 1.6553,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 2.8e-05,
|
| 20 |
+
"loss": 1.3075,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 4.2e-05,
|
| 26 |
+
"loss": 1.2606,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.14,
|
| 31 |
+
"learning_rate": 5.6e-05,
|
| 32 |
+
"loss": 1.2085,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.18,
|
| 37 |
+
"learning_rate": 7e-05,
|
| 38 |
+
"loss": 1.1956,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.18,
|
| 43 |
+
"eval_bleu": 36.3211,
|
| 44 |
+
"eval_chrf++": 55.6095,
|
| 45 |
+
"eval_gen_len": 17.5404,
|
| 46 |
+
"eval_loss": 1.01542067527771,
|
| 47 |
+
"eval_runtime": 1596.0286,
|
| 48 |
+
"eval_samples_per_second": 4.587,
|
| 49 |
+
"eval_steps_per_second": 2.294,
|
| 50 |
+
"step": 500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.21,
|
| 54 |
+
"learning_rate": 6.974955277280858e-05,
|
| 55 |
+
"loss": 1.1487,
|
| 56 |
+
"step": 600
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.25,
|
| 60 |
+
"learning_rate": 6.949910554561716e-05,
|
| 61 |
+
"loss": 1.1406,
|
| 62 |
+
"step": 700
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.28,
|
| 66 |
+
"learning_rate": 6.924865831842576e-05,
|
| 67 |
+
"loss": 1.1197,
|
| 68 |
+
"step": 800
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.32,
|
| 72 |
+
"learning_rate": 6.899821109123434e-05,
|
| 73 |
+
"loss": 1.0739,
|
| 74 |
+
"step": 900
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.35,
|
| 78 |
+
"learning_rate": 6.874776386404293e-05,
|
| 79 |
+
"loss": 1.0817,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.35,
|
| 84 |
+
"eval_bleu": 37.9118,
|
| 85 |
+
"eval_chrf++": 57.1775,
|
| 86 |
+
"eval_gen_len": 17.6499,
|
| 87 |
+
"eval_loss": 0.9288437962532043,
|
| 88 |
+
"eval_runtime": 1599.8831,
|
| 89 |
+
"eval_samples_per_second": 4.576,
|
| 90 |
+
"eval_steps_per_second": 2.288,
|
| 91 |
+
"step": 1000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.39,
|
| 95 |
+
"learning_rate": 6.849731663685151e-05,
|
| 96 |
+
"loss": 1.0784,
|
| 97 |
+
"step": 1100
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.42,
|
| 101 |
+
"learning_rate": 6.824686940966009e-05,
|
| 102 |
+
"loss": 1.0538,
|
| 103 |
+
"step": 1200
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.46,
|
| 107 |
+
"learning_rate": 6.799642218246869e-05,
|
| 108 |
+
"loss": 1.0431,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.49,
|
| 113 |
+
"learning_rate": 6.774597495527727e-05,
|
| 114 |
+
"loss": 1.0347,
|
| 115 |
+
"step": 1400
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.53,
|
| 119 |
+
"learning_rate": 6.749552772808586e-05,
|
| 120 |
+
"loss": 1.0162,
|
| 121 |
+
"step": 1500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.53,
|
| 125 |
+
"eval_bleu": 39.3818,
|
| 126 |
+
"eval_chrf++": 58.3559,
|
| 127 |
+
"eval_gen_len": 17.6375,
|
| 128 |
+
"eval_loss": 0.8730005025863647,
|
| 129 |
+
"eval_runtime": 1591.8771,
|
| 130 |
+
"eval_samples_per_second": 4.599,
|
| 131 |
+
"eval_steps_per_second": 2.3,
|
| 132 |
+
"step": 1500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.56,
|
| 136 |
+
"learning_rate": 6.724508050089444e-05,
|
| 137 |
+
"loss": 0.9995,
|
| 138 |
+
"step": 1600
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.6,
|
| 142 |
+
"learning_rate": 6.699463327370304e-05,
|
| 143 |
+
"loss": 0.987,
|
| 144 |
+
"step": 1700
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.63,
|
| 148 |
+
"learning_rate": 6.674418604651162e-05,
|
| 149 |
+
"loss": 1.0009,
|
| 150 |
+
"step": 1800
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.67,
|
| 154 |
+
"learning_rate": 6.64937388193202e-05,
|
| 155 |
+
"loss": 0.9843,
|
| 156 |
+
"step": 1900
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7,
|
| 160 |
+
"learning_rate": 6.624329159212879e-05,
|
| 161 |
+
"loss": 0.974,
|
| 162 |
+
"step": 2000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.7,
|
| 166 |
+
"eval_bleu": 40.0752,
|
| 167 |
+
"eval_chrf++": 58.9288,
|
| 168 |
+
"eval_gen_len": 17.741,
|
| 169 |
+
"eval_loss": 0.8381767272949219,
|
| 170 |
+
"eval_runtime": 1584.9965,
|
| 171 |
+
"eval_samples_per_second": 4.619,
|
| 172 |
+
"eval_steps_per_second": 2.31,
|
| 173 |
+
"step": 2000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.74,
|
| 177 |
+
"learning_rate": 6.599284436493739e-05,
|
| 178 |
+
"loss": 0.9649,
|
| 179 |
+
"step": 2100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.77,
|
| 183 |
+
"learning_rate": 6.574239713774597e-05,
|
| 184 |
+
"loss": 0.9511,
|
| 185 |
+
"step": 2200
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.81,
|
| 189 |
+
"learning_rate": 6.549194991055455e-05,
|
| 190 |
+
"loss": 0.9689,
|
| 191 |
+
"step": 2300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.84,
|
| 195 |
+
"learning_rate": 6.524150268336314e-05,
|
| 196 |
+
"loss": 0.9512,
|
| 197 |
+
"step": 2400
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.88,
|
| 201 |
+
"learning_rate": 6.499105545617173e-05,
|
| 202 |
+
"loss": 0.9513,
|
| 203 |
+
"step": 2500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.88,
|
| 207 |
+
"eval_bleu": 40.6133,
|
| 208 |
+
"eval_chrf++": 59.5241,
|
| 209 |
+
"eval_gen_len": 17.7642,
|
| 210 |
+
"eval_loss": 0.8131038546562195,
|
| 211 |
+
"eval_runtime": 1608.2394,
|
| 212 |
+
"eval_samples_per_second": 4.552,
|
| 213 |
+
"eval_steps_per_second": 2.276,
|
| 214 |
+
"step": 2500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.91,
|
| 218 |
+
"learning_rate": 6.474060822898032e-05,
|
| 219 |
+
"loss": 0.9476,
|
| 220 |
+
"step": 2600
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.95,
|
| 224 |
+
"learning_rate": 6.44901610017889e-05,
|
| 225 |
+
"loss": 0.9202,
|
| 226 |
+
"step": 2700
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.98,
|
| 230 |
+
"learning_rate": 6.423971377459748e-05,
|
| 231 |
+
"loss": 0.9423,
|
| 232 |
+
"step": 2800
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.02,
|
| 236 |
+
"learning_rate": 6.398926654740608e-05,
|
| 237 |
+
"loss": 0.8949,
|
| 238 |
+
"step": 2900
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.05,
|
| 242 |
+
"learning_rate": 6.373881932021467e-05,
|
| 243 |
+
"loss": 0.8405,
|
| 244 |
+
"step": 3000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.05,
|
| 248 |
+
"eval_bleu": 40.8822,
|
| 249 |
+
"eval_chrf++": 59.9339,
|
| 250 |
+
"eval_gen_len": 17.7189,
|
| 251 |
+
"eval_loss": 0.7998338937759399,
|
| 252 |
+
"eval_runtime": 1592.0637,
|
| 253 |
+
"eval_samples_per_second": 4.598,
|
| 254 |
+
"eval_steps_per_second": 2.3,
|
| 255 |
+
"step": 3000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.09,
|
| 259 |
+
"learning_rate": 6.348837209302325e-05,
|
| 260 |
+
"loss": 0.8431,
|
| 261 |
+
"step": 3100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.12,
|
| 265 |
+
"learning_rate": 6.323792486583183e-05,
|
| 266 |
+
"loss": 0.8383,
|
| 267 |
+
"step": 3200
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.16,
|
| 271 |
+
"learning_rate": 6.298747763864043e-05,
|
| 272 |
+
"loss": 0.838,
|
| 273 |
+
"step": 3300
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.19,
|
| 277 |
+
"learning_rate": 6.273703041144901e-05,
|
| 278 |
+
"loss": 0.8527,
|
| 279 |
+
"step": 3400
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.23,
|
| 283 |
+
"learning_rate": 6.24865831842576e-05,
|
| 284 |
+
"loss": 0.8252,
|
| 285 |
+
"step": 3500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.23,
|
| 289 |
+
"eval_bleu": 41.6082,
|
| 290 |
+
"eval_chrf++": 60.3254,
|
| 291 |
+
"eval_gen_len": 17.7662,
|
| 292 |
+
"eval_loss": 0.7859154939651489,
|
| 293 |
+
"eval_runtime": 1613.9109,
|
| 294 |
+
"eval_samples_per_second": 4.536,
|
| 295 |
+
"eval_steps_per_second": 2.268,
|
| 296 |
+
"step": 3500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.27,
|
| 300 |
+
"learning_rate": 6.22361359570662e-05,
|
| 301 |
+
"loss": 0.836,
|
| 302 |
+
"step": 3600
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.3,
|
| 306 |
+
"learning_rate": 6.198568872987478e-05,
|
| 307 |
+
"loss": 0.8274,
|
| 308 |
+
"step": 3700
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.34,
|
| 312 |
+
"learning_rate": 6.173524150268336e-05,
|
| 313 |
+
"loss": 0.8257,
|
| 314 |
+
"step": 3800
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.37,
|
| 318 |
+
"learning_rate": 6.148479427549194e-05,
|
| 319 |
+
"loss": 0.8301,
|
| 320 |
+
"step": 3900
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.41,
|
| 324 |
+
"learning_rate": 6.123434704830053e-05,
|
| 325 |
+
"loss": 0.8235,
|
| 326 |
+
"step": 4000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.41,
|
| 330 |
+
"eval_bleu": 41.9785,
|
| 331 |
+
"eval_chrf++": 60.615,
|
| 332 |
+
"eval_gen_len": 17.6996,
|
| 333 |
+
"eval_loss": 0.7718562483787537,
|
| 334 |
+
"eval_runtime": 1591.3834,
|
| 335 |
+
"eval_samples_per_second": 4.6,
|
| 336 |
+
"eval_steps_per_second": 2.301,
|
| 337 |
+
"step": 4000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.44,
|
| 341 |
+
"learning_rate": 6.098389982110912e-05,
|
| 342 |
+
"loss": 0.8335,
|
| 343 |
+
"step": 4100
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.48,
|
| 347 |
+
"learning_rate": 6.073345259391771e-05,
|
| 348 |
+
"loss": 0.8184,
|
| 349 |
+
"step": 4200
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.51,
|
| 353 |
+
"learning_rate": 6.048300536672629e-05,
|
| 354 |
+
"loss": 0.8139,
|
| 355 |
+
"step": 4300
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.55,
|
| 359 |
+
"learning_rate": 6.0232558139534877e-05,
|
| 360 |
+
"loss": 0.8121,
|
| 361 |
+
"step": 4400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.58,
|
| 365 |
+
"learning_rate": 5.998211091234346e-05,
|
| 366 |
+
"loss": 0.8174,
|
| 367 |
+
"step": 4500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.58,
|
| 371 |
+
"eval_bleu": 41.9942,
|
| 372 |
+
"eval_chrf++": 60.7015,
|
| 373 |
+
"eval_gen_len": 17.7548,
|
| 374 |
+
"eval_loss": 0.7601388692855835,
|
| 375 |
+
"eval_runtime": 1610.8686,
|
| 376 |
+
"eval_samples_per_second": 4.545,
|
| 377 |
+
"eval_steps_per_second": 2.273,
|
| 378 |
+
"step": 4500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.62,
|
| 382 |
+
"learning_rate": 5.973166368515206e-05,
|
| 383 |
+
"loss": 0.8232,
|
| 384 |
+
"step": 4600
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.65,
|
| 388 |
+
"learning_rate": 5.948121645796064e-05,
|
| 389 |
+
"loss": 0.8099,
|
| 390 |
+
"step": 4700
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.69,
|
| 394 |
+
"learning_rate": 5.9230769230769225e-05,
|
| 395 |
+
"loss": 0.8154,
|
| 396 |
+
"step": 4800
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.72,
|
| 400 |
+
"learning_rate": 5.898032200357781e-05,
|
| 401 |
+
"loss": 0.818,
|
| 402 |
+
"step": 4900
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.76,
|
| 406 |
+
"learning_rate": 5.87298747763864e-05,
|
| 407 |
+
"loss": 0.7992,
|
| 408 |
+
"step": 5000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.76,
|
| 412 |
+
"eval_bleu": 42.3622,
|
| 413 |
+
"eval_chrf++": 61.0481,
|
| 414 |
+
"eval_gen_len": 17.8145,
|
| 415 |
+
"eval_loss": 0.7486168146133423,
|
| 416 |
+
"eval_runtime": 1597.5591,
|
| 417 |
+
"eval_samples_per_second": 4.583,
|
| 418 |
+
"eval_steps_per_second": 2.292,
|
| 419 |
+
"step": 5000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.79,
|
| 423 |
+
"learning_rate": 5.847942754919499e-05,
|
| 424 |
+
"loss": 0.8087,
|
| 425 |
+
"step": 5100
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.83,
|
| 429 |
+
"learning_rate": 5.822898032200357e-05,
|
| 430 |
+
"loss": 0.7958,
|
| 431 |
+
"step": 5200
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.86,
|
| 435 |
+
"learning_rate": 5.7978533094812156e-05,
|
| 436 |
+
"loss": 0.8022,
|
| 437 |
+
"step": 5300
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.9,
|
| 441 |
+
"learning_rate": 5.7728085867620747e-05,
|
| 442 |
+
"loss": 0.7876,
|
| 443 |
+
"step": 5400
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.93,
|
| 447 |
+
"learning_rate": 5.747763864042934e-05,
|
| 448 |
+
"loss": 0.7915,
|
| 449 |
+
"step": 5500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.93,
|
| 453 |
+
"eval_bleu": 42.4851,
|
| 454 |
+
"eval_chrf++": 61.1145,
|
| 455 |
+
"eval_gen_len": 17.7756,
|
| 456 |
+
"eval_loss": 0.7351738810539246,
|
| 457 |
+
"eval_runtime": 1598.7533,
|
| 458 |
+
"eval_samples_per_second": 4.579,
|
| 459 |
+
"eval_steps_per_second": 2.29,
|
| 460 |
+
"step": 5500
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.97,
|
| 464 |
+
"learning_rate": 5.722719141323792e-05,
|
| 465 |
+
"loss": 0.7795,
|
| 466 |
+
"step": 5600
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.0,
|
| 470 |
+
"learning_rate": 5.6976744186046504e-05,
|
| 471 |
+
"loss": 0.8015,
|
| 472 |
+
"step": 5700
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.04,
|
| 476 |
+
"learning_rate": 5.6726296958855094e-05,
|
| 477 |
+
"loss": 0.7219,
|
| 478 |
+
"step": 5800
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.07,
|
| 482 |
+
"learning_rate": 5.647584973166368e-05,
|
| 483 |
+
"loss": 0.7231,
|
| 484 |
+
"step": 5900
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.11,
|
| 488 |
+
"learning_rate": 5.622540250447227e-05,
|
| 489 |
+
"loss": 0.718,
|
| 490 |
+
"step": 6000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.11,
|
| 494 |
+
"eval_bleu": 42.5957,
|
| 495 |
+
"eval_chrf++": 61.1828,
|
| 496 |
+
"eval_gen_len": 17.7144,
|
| 497 |
+
"eval_loss": 0.7349444627761841,
|
| 498 |
+
"eval_runtime": 1593.2386,
|
| 499 |
+
"eval_samples_per_second": 4.595,
|
| 500 |
+
"eval_steps_per_second": 2.298,
|
| 501 |
+
"step": 6000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.14,
|
| 505 |
+
"learning_rate": 5.597495527728085e-05,
|
| 506 |
+
"loss": 0.7155,
|
| 507 |
+
"step": 6100
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.18,
|
| 511 |
+
"learning_rate": 5.572450805008944e-05,
|
| 512 |
+
"loss": 0.7222,
|
| 513 |
+
"step": 6200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.21,
|
| 517 |
+
"learning_rate": 5.5474060822898026e-05,
|
| 518 |
+
"loss": 0.7113,
|
| 519 |
+
"step": 6300
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.25,
|
| 523 |
+
"learning_rate": 5.522361359570661e-05,
|
| 524 |
+
"loss": 0.7067,
|
| 525 |
+
"step": 6400
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.28,
|
| 529 |
+
"learning_rate": 5.497316636851521e-05,
|
| 530 |
+
"loss": 0.714,
|
| 531 |
+
"step": 6500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.28,
|
| 535 |
+
"eval_bleu": 43.1947,
|
| 536 |
+
"eval_chrf++": 61.6389,
|
| 537 |
+
"eval_gen_len": 17.7485,
|
| 538 |
+
"eval_loss": 0.7279652953147888,
|
| 539 |
+
"eval_runtime": 1602.3425,
|
| 540 |
+
"eval_samples_per_second": 4.569,
|
| 541 |
+
"eval_steps_per_second": 2.285,
|
| 542 |
+
"step": 6500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.32,
|
| 546 |
+
"learning_rate": 5.472271914132379e-05,
|
| 547 |
+
"loss": 0.7284,
|
| 548 |
+
"step": 6600
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.35,
|
| 552 |
+
"learning_rate": 5.4472271914132374e-05,
|
| 553 |
+
"loss": 0.7106,
|
| 554 |
+
"step": 6700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.39,
|
| 558 |
+
"learning_rate": 5.422182468694096e-05,
|
| 559 |
+
"loss": 0.7226,
|
| 560 |
+
"step": 6800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.43,
|
| 564 |
+
"learning_rate": 5.3971377459749555e-05,
|
| 565 |
+
"loss": 0.7151,
|
| 566 |
+
"step": 6900
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.46,
|
| 570 |
+
"learning_rate": 5.372093023255814e-05,
|
| 571 |
+
"loss": 0.7242,
|
| 572 |
+
"step": 7000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.46,
|
| 576 |
+
"eval_bleu": 43.0217,
|
| 577 |
+
"eval_chrf++": 61.4,
|
| 578 |
+
"eval_gen_len": 17.7472,
|
| 579 |
+
"eval_loss": 0.7255465984344482,
|
| 580 |
+
"eval_runtime": 1596.9259,
|
| 581 |
+
"eval_samples_per_second": 4.584,
|
| 582 |
+
"eval_steps_per_second": 2.293,
|
| 583 |
+
"step": 7000
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.5,
|
| 587 |
+
"learning_rate": 5.347048300536672e-05,
|
| 588 |
+
"loss": 0.7115,
|
| 589 |
+
"step": 7100
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.53,
|
| 593 |
+
"learning_rate": 5.3220035778175306e-05,
|
| 594 |
+
"loss": 0.6996,
|
| 595 |
+
"step": 7200
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.57,
|
| 599 |
+
"learning_rate": 5.296958855098389e-05,
|
| 600 |
+
"loss": 0.7226,
|
| 601 |
+
"step": 7300
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.6,
|
| 605 |
+
"learning_rate": 5.2719141323792486e-05,
|
| 606 |
+
"loss": 0.7023,
|
| 607 |
+
"step": 7400
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 2.64,
|
| 611 |
+
"learning_rate": 5.246869409660107e-05,
|
| 612 |
+
"loss": 0.7035,
|
| 613 |
+
"step": 7500
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.64,
|
| 617 |
+
"eval_bleu": 42.9886,
|
| 618 |
+
"eval_chrf++": 61.5585,
|
| 619 |
+
"eval_gen_len": 17.7513,
|
| 620 |
+
"eval_loss": 0.7192216515541077,
|
| 621 |
+
"eval_runtime": 1608.427,
|
| 622 |
+
"eval_samples_per_second": 4.552,
|
| 623 |
+
"eval_steps_per_second": 2.276,
|
| 624 |
+
"step": 7500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.67,
|
| 628 |
+
"learning_rate": 5.2218246869409654e-05,
|
| 629 |
+
"loss": 0.7175,
|
| 630 |
+
"step": 7600
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.71,
|
| 634 |
+
"learning_rate": 5.1967799642218244e-05,
|
| 635 |
+
"loss": 0.7164,
|
| 636 |
+
"step": 7700
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 2.74,
|
| 640 |
+
"learning_rate": 5.171735241502683e-05,
|
| 641 |
+
"loss": 0.703,
|
| 642 |
+
"step": 7800
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.78,
|
| 646 |
+
"learning_rate": 5.146690518783542e-05,
|
| 647 |
+
"loss": 0.7067,
|
| 648 |
+
"step": 7900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.81,
|
| 652 |
+
"learning_rate": 5.1216457960644e-05,
|
| 653 |
+
"loss": 0.7048,
|
| 654 |
+
"step": 8000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.81,
|
| 658 |
+
"eval_bleu": 42.9399,
|
| 659 |
+
"eval_chrf++": 61.4851,
|
| 660 |
+
"eval_gen_len": 17.7067,
|
| 661 |
+
"eval_loss": 0.7168448567390442,
|
| 662 |
+
"eval_runtime": 1552.4929,
|
| 663 |
+
"eval_samples_per_second": 4.716,
|
| 664 |
+
"eval_steps_per_second": 2.358,
|
| 665 |
+
"step": 8000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.85,
|
| 669 |
+
"learning_rate": 5.096601073345259e-05,
|
| 670 |
+
"loss": 0.7127,
|
| 671 |
+
"step": 8100
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.88,
|
| 675 |
+
"learning_rate": 5.0715563506261176e-05,
|
| 676 |
+
"loss": 0.7091,
|
| 677 |
+
"step": 8200
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.92,
|
| 681 |
+
"learning_rate": 5.046511627906976e-05,
|
| 682 |
+
"loss": 0.7122,
|
| 683 |
+
"step": 8300
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.95,
|
| 687 |
+
"learning_rate": 5.021466905187835e-05,
|
| 688 |
+
"loss": 0.6949,
|
| 689 |
+
"step": 8400
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.99,
|
| 693 |
+
"learning_rate": 4.996422182468694e-05,
|
| 694 |
+
"loss": 0.685,
|
| 695 |
+
"step": 8500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.99,
|
| 699 |
+
"eval_bleu": 43.114,
|
| 700 |
+
"eval_chrf++": 61.6028,
|
| 701 |
+
"eval_gen_len": 17.844,
|
| 702 |
+
"eval_loss": 0.7094260454177856,
|
| 703 |
+
"eval_runtime": 1415.2591,
|
| 704 |
+
"eval_samples_per_second": 5.173,
|
| 705 |
+
"eval_steps_per_second": 2.587,
|
| 706 |
+
"step": 8500
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.02,
|
| 710 |
+
"learning_rate": 4.9713774597495524e-05,
|
| 711 |
+
"loss": 0.6618,
|
| 712 |
+
"step": 8600
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 3.06,
|
| 716 |
+
"learning_rate": 4.946332737030411e-05,
|
| 717 |
+
"loss": 0.6417,
|
| 718 |
+
"step": 8700
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 3.09,
|
| 722 |
+
"learning_rate": 4.92128801431127e-05,
|
| 723 |
+
"loss": 0.65,
|
| 724 |
+
"step": 8800
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 3.13,
|
| 728 |
+
"learning_rate": 4.896243291592129e-05,
|
| 729 |
+
"loss": 0.6375,
|
| 730 |
+
"step": 8900
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 3.16,
|
| 734 |
+
"learning_rate": 4.871198568872987e-05,
|
| 735 |
+
"loss": 0.632,
|
| 736 |
+
"step": 9000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.16,
|
| 740 |
+
"eval_bleu": 43.3779,
|
| 741 |
+
"eval_chrf++": 61.8915,
|
| 742 |
+
"eval_gen_len": 17.7121,
|
| 743 |
+
"eval_loss": 0.7186790108680725,
|
| 744 |
+
"eval_runtime": 1408.2967,
|
| 745 |
+
"eval_samples_per_second": 5.198,
|
| 746 |
+
"eval_steps_per_second": 2.6,
|
| 747 |
+
"step": 9000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 3.2,
|
| 751 |
+
"learning_rate": 4.8461538461538455e-05,
|
| 752 |
+
"loss": 0.6434,
|
| 753 |
+
"step": 9100
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 3.23,
|
| 757 |
+
"learning_rate": 4.821109123434704e-05,
|
| 758 |
+
"loss": 0.6354,
|
| 759 |
+
"step": 9200
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.27,
|
| 763 |
+
"learning_rate": 4.7960644007155636e-05,
|
| 764 |
+
"loss": 0.6374,
|
| 765 |
+
"step": 9300
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.3,
|
| 769 |
+
"learning_rate": 4.771019677996422e-05,
|
| 770 |
+
"loss": 0.6478,
|
| 771 |
+
"step": 9400
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 3.34,
|
| 775 |
+
"learning_rate": 4.74597495527728e-05,
|
| 776 |
+
"loss": 0.6444,
|
| 777 |
+
"step": 9500
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.34,
|
| 781 |
+
"eval_bleu": 43.0761,
|
| 782 |
+
"eval_chrf++": 61.6092,
|
| 783 |
+
"eval_gen_len": 17.7518,
|
| 784 |
+
"eval_loss": 0.7161450982093811,
|
| 785 |
+
"eval_runtime": 1412.5727,
|
| 786 |
+
"eval_samples_per_second": 5.183,
|
| 787 |
+
"eval_steps_per_second": 2.592,
|
| 788 |
+
"step": 9500
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.37,
|
| 792 |
+
"learning_rate": 4.720930232558139e-05,
|
| 793 |
+
"loss": 0.6358,
|
| 794 |
+
"step": 9600
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.41,
|
| 798 |
+
"learning_rate": 4.695885509838998e-05,
|
| 799 |
+
"loss": 0.6502,
|
| 800 |
+
"step": 9700
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.44,
|
| 804 |
+
"learning_rate": 4.670840787119857e-05,
|
| 805 |
+
"loss": 0.6376,
|
| 806 |
+
"step": 9800
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.48,
|
| 810 |
+
"learning_rate": 4.645796064400715e-05,
|
| 811 |
+
"loss": 0.638,
|
| 812 |
+
"step": 9900
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 3.51,
|
| 816 |
+
"learning_rate": 4.6207513416815735e-05,
|
| 817 |
+
"loss": 0.6302,
|
| 818 |
+
"step": 10000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.51,
|
| 822 |
+
"eval_bleu": 43.4763,
|
| 823 |
+
"eval_chrf++": 61.8105,
|
| 824 |
+
"eval_gen_len": 17.7754,
|
| 825 |
+
"eval_loss": 0.7070448398590088,
|
| 826 |
+
"eval_runtime": 1409.243,
|
| 827 |
+
"eval_samples_per_second": 5.195,
|
| 828 |
+
"eval_steps_per_second": 2.598,
|
| 829 |
+
"step": 10000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 3.55,
|
| 833 |
+
"learning_rate": 4.5957066189624325e-05,
|
| 834 |
+
"loss": 0.632,
|
| 835 |
+
"step": 10100
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 3.58,
|
| 839 |
+
"learning_rate": 4.570661896243291e-05,
|
| 840 |
+
"loss": 0.6364,
|
| 841 |
+
"step": 10200
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.62,
|
| 845 |
+
"learning_rate": 4.54561717352415e-05,
|
| 846 |
+
"loss": 0.6466,
|
| 847 |
+
"step": 10300
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 3.66,
|
| 851 |
+
"learning_rate": 4.520572450805009e-05,
|
| 852 |
+
"loss": 0.6373,
|
| 853 |
+
"step": 10400
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 3.69,
|
| 857 |
+
"learning_rate": 4.495527728085867e-05,
|
| 858 |
+
"loss": 0.6478,
|
| 859 |
+
"step": 10500
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 3.69,
|
| 863 |
+
"eval_bleu": 43.725,
|
| 864 |
+
"eval_chrf++": 62.0616,
|
| 865 |
+
"eval_gen_len": 17.788,
|
| 866 |
+
"eval_loss": 0.705007016658783,
|
| 867 |
+
"eval_runtime": 1414.2328,
|
| 868 |
+
"eval_samples_per_second": 5.177,
|
| 869 |
+
"eval_steps_per_second": 2.589,
|
| 870 |
+
"step": 10500
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 3.73,
|
| 874 |
+
"learning_rate": 4.470483005366726e-05,
|
| 875 |
+
"loss": 0.6516,
|
| 876 |
+
"step": 10600
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 3.76,
|
| 880 |
+
"learning_rate": 4.445438282647585e-05,
|
| 881 |
+
"loss": 0.6334,
|
| 882 |
+
"step": 10700
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 3.8,
|
| 886 |
+
"learning_rate": 4.420393559928444e-05,
|
| 887 |
+
"loss": 0.6542,
|
| 888 |
+
"step": 10800
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 3.83,
|
| 892 |
+
"learning_rate": 4.395348837209302e-05,
|
| 893 |
+
"loss": 0.646,
|
| 894 |
+
"step": 10900
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 3.87,
|
| 898 |
+
"learning_rate": 4.3703041144901605e-05,
|
| 899 |
+
"loss": 0.6374,
|
| 900 |
+
"step": 11000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 3.87,
|
| 904 |
+
"eval_bleu": 43.7206,
|
| 905 |
+
"eval_chrf++": 62.1048,
|
| 906 |
+
"eval_gen_len": 17.7229,
|
| 907 |
+
"eval_loss": 0.6963800191879272,
|
| 908 |
+
"eval_runtime": 1413.4358,
|
| 909 |
+
"eval_samples_per_second": 5.18,
|
| 910 |
+
"eval_steps_per_second": 2.59,
|
| 911 |
+
"step": 11000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.9,
|
| 915 |
+
"learning_rate": 4.345259391771019e-05,
|
| 916 |
+
"loss": 0.6416,
|
| 917 |
+
"step": 11100
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.94,
|
| 921 |
+
"learning_rate": 4.3202146690518786e-05,
|
| 922 |
+
"loss": 0.6249,
|
| 923 |
+
"step": 11200
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.97,
|
| 927 |
+
"learning_rate": 4.295169946332737e-05,
|
| 928 |
+
"loss": 0.638,
|
| 929 |
+
"step": 11300
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.01,
|
| 933 |
+
"learning_rate": 4.270125223613595e-05,
|
| 934 |
+
"loss": 0.6352,
|
| 935 |
+
"step": 11400
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.04,
|
| 939 |
+
"learning_rate": 4.2450805008944536e-05,
|
| 940 |
+
"loss": 0.5804,
|
| 941 |
+
"step": 11500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.04,
|
| 945 |
+
"eval_bleu": 43.8669,
|
| 946 |
+
"eval_chrf++": 62.1364,
|
| 947 |
+
"eval_gen_len": 17.7865,
|
| 948 |
+
"eval_loss": 0.7024260759353638,
|
| 949 |
+
"eval_runtime": 1410.9857,
|
| 950 |
+
"eval_samples_per_second": 5.189,
|
| 951 |
+
"eval_steps_per_second": 2.595,
|
| 952 |
+
"step": 11500
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 4.08,
|
| 956 |
+
"learning_rate": 4.220035778175313e-05,
|
| 957 |
+
"loss": 0.5799,
|
| 958 |
+
"step": 11600
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 4.11,
|
| 962 |
+
"learning_rate": 4.194991055456172e-05,
|
| 963 |
+
"loss": 0.5852,
|
| 964 |
+
"step": 11700
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 4.15,
|
| 968 |
+
"learning_rate": 4.16994633273703e-05,
|
| 969 |
+
"loss": 0.5801,
|
| 970 |
+
"step": 11800
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 4.18,
|
| 974 |
+
"learning_rate": 4.1449016100178884e-05,
|
| 975 |
+
"loss": 0.5945,
|
| 976 |
+
"step": 11900
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.22,
|
| 980 |
+
"learning_rate": 4.1198568872987475e-05,
|
| 981 |
+
"loss": 0.5919,
|
| 982 |
+
"step": 12000
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 4.22,
|
| 986 |
+
"eval_bleu": 43.6775,
|
| 987 |
+
"eval_chrf++": 61.9586,
|
| 988 |
+
"eval_gen_len": 17.8369,
|
| 989 |
+
"eval_loss": 0.7032192945480347,
|
| 990 |
+
"eval_runtime": 1420.6308,
|
| 991 |
+
"eval_samples_per_second": 5.153,
|
| 992 |
+
"eval_steps_per_second": 2.577,
|
| 993 |
+
"step": 12000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 4.25,
|
| 997 |
+
"learning_rate": 4.094812164579606e-05,
|
| 998 |
+
"loss": 0.5928,
|
| 999 |
+
"step": 12100
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 4.29,
|
| 1003 |
+
"learning_rate": 4.069767441860465e-05,
|
| 1004 |
+
"loss": 0.5923,
|
| 1005 |
+
"step": 12200
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 4.32,
|
| 1009 |
+
"learning_rate": 4.044722719141323e-05,
|
| 1010 |
+
"loss": 0.5943,
|
| 1011 |
+
"step": 12300
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 4.36,
|
| 1015 |
+
"learning_rate": 4.019677996422182e-05,
|
| 1016 |
+
"loss": 0.5905,
|
| 1017 |
+
"step": 12400
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 4.39,
|
| 1021 |
+
"learning_rate": 3.9946332737030406e-05,
|
| 1022 |
+
"loss": 0.5879,
|
| 1023 |
+
"step": 12500
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 4.39,
|
| 1027 |
+
"eval_bleu": 43.9642,
|
| 1028 |
+
"eval_chrf++": 62.2021,
|
| 1029 |
+
"eval_gen_len": 17.7873,
|
| 1030 |
+
"eval_loss": 0.7024480104446411,
|
| 1031 |
+
"eval_runtime": 1420.746,
|
| 1032 |
+
"eval_samples_per_second": 5.153,
|
| 1033 |
+
"eval_steps_per_second": 2.577,
|
| 1034 |
+
"step": 12500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 4.43,
|
| 1038 |
+
"learning_rate": 3.9695885509839e-05,
|
| 1039 |
+
"loss": 0.5855,
|
| 1040 |
+
"step": 12600
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 4.46,
|
| 1044 |
+
"learning_rate": 3.944543828264758e-05,
|
| 1045 |
+
"loss": 0.5855,
|
| 1046 |
+
"step": 12700
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 4.5,
|
| 1050 |
+
"learning_rate": 3.919499105545617e-05,
|
| 1051 |
+
"loss": 0.5833,
|
| 1052 |
+
"step": 12800
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 4.53,
|
| 1056 |
+
"learning_rate": 3.8944543828264754e-05,
|
| 1057 |
+
"loss": 0.5767,
|
| 1058 |
+
"step": 12900
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 4.57,
|
| 1062 |
+
"learning_rate": 3.869409660107334e-05,
|
| 1063 |
+
"loss": 0.5858,
|
| 1064 |
+
"step": 13000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 4.57,
|
| 1068 |
+
"eval_bleu": 44.027,
|
| 1069 |
+
"eval_chrf++": 62.2226,
|
| 1070 |
+
"eval_gen_len": 17.7678,
|
| 1071 |
+
"eval_loss": 0.6992958784103394,
|
| 1072 |
+
"eval_runtime": 1410.8973,
|
| 1073 |
+
"eval_samples_per_second": 5.189,
|
| 1074 |
+
"eval_steps_per_second": 2.595,
|
| 1075 |
+
"step": 13000
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 4.6,
|
| 1079 |
+
"learning_rate": 3.8443649373881935e-05,
|
| 1080 |
+
"loss": 0.5775,
|
| 1081 |
+
"step": 13100
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.64,
|
| 1085 |
+
"learning_rate": 3.819320214669052e-05,
|
| 1086 |
+
"loss": 0.5825,
|
| 1087 |
+
"step": 13200
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 4.67,
|
| 1091 |
+
"learning_rate": 3.79427549194991e-05,
|
| 1092 |
+
"loss": 0.5851,
|
| 1093 |
+
"step": 13300
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 4.71,
|
| 1097 |
+
"learning_rate": 3.7692307692307686e-05,
|
| 1098 |
+
"loss": 0.5913,
|
| 1099 |
+
"step": 13400
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 4.74,
|
| 1103 |
+
"learning_rate": 3.744186046511627e-05,
|
| 1104 |
+
"loss": 0.5877,
|
| 1105 |
+
"step": 13500
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 4.74,
|
| 1109 |
+
"eval_bleu": 44.1426,
|
| 1110 |
+
"eval_chrf++": 62.3429,
|
| 1111 |
+
"eval_gen_len": 17.7805,
|
| 1112 |
+
"eval_loss": 0.6957116723060608,
|
| 1113 |
+
"eval_runtime": 1414.8882,
|
| 1114 |
+
"eval_samples_per_second": 5.174,
|
| 1115 |
+
"eval_steps_per_second": 2.587,
|
| 1116 |
+
"step": 13500
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.78,
|
| 1120 |
+
"learning_rate": 3.719141323792487e-05,
|
| 1121 |
+
"loss": 0.5857,
|
| 1122 |
+
"step": 13600
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 4.81,
|
| 1126 |
+
"learning_rate": 3.694096601073345e-05,
|
| 1127 |
+
"loss": 0.5776,
|
| 1128 |
+
"step": 13700
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 4.85,
|
| 1132 |
+
"learning_rate": 3.6690518783542034e-05,
|
| 1133 |
+
"loss": 0.5985,
|
| 1134 |
+
"step": 13800
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 4.89,
|
| 1138 |
+
"learning_rate": 3.644007155635062e-05,
|
| 1139 |
+
"loss": 0.5855,
|
| 1140 |
+
"step": 13900
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 4.92,
|
| 1144 |
+
"learning_rate": 3.618962432915921e-05,
|
| 1145 |
+
"loss": 0.5895,
|
| 1146 |
+
"step": 14000
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 4.92,
|
| 1150 |
+
"eval_bleu": 44.2097,
|
| 1151 |
+
"eval_chrf++": 62.4158,
|
| 1152 |
+
"eval_gen_len": 17.7713,
|
| 1153 |
+
"eval_loss": 0.6944009065628052,
|
| 1154 |
+
"eval_runtime": 1417.3776,
|
| 1155 |
+
"eval_samples_per_second": 5.165,
|
| 1156 |
+
"eval_steps_per_second": 2.583,
|
| 1157 |
+
"step": 14000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 4.96,
|
| 1161 |
+
"learning_rate": 3.59391771019678e-05,
|
| 1162 |
+
"loss": 0.581,
|
| 1163 |
+
"step": 14100
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 4.99,
|
| 1167 |
+
"learning_rate": 3.568872987477638e-05,
|
| 1168 |
+
"loss": 0.5835,
|
| 1169 |
+
"step": 14200
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 5.03,
|
| 1173 |
+
"learning_rate": 3.543828264758497e-05,
|
| 1174 |
+
"loss": 0.5512,
|
| 1175 |
+
"step": 14300
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 5.06,
|
| 1179 |
+
"learning_rate": 3.5187835420393556e-05,
|
| 1180 |
+
"loss": 0.5324,
|
| 1181 |
+
"step": 14400
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 5.1,
|
| 1185 |
+
"learning_rate": 3.4937388193202146e-05,
|
| 1186 |
+
"loss": 0.5381,
|
| 1187 |
+
"step": 14500
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 5.1,
|
| 1191 |
+
"eval_bleu": 43.9778,
|
| 1192 |
+
"eval_chrf++": 62.2087,
|
| 1193 |
+
"eval_gen_len": 17.8153,
|
| 1194 |
+
"eval_loss": 0.7013605833053589,
|
| 1195 |
+
"eval_runtime": 1419.0259,
|
| 1196 |
+
"eval_samples_per_second": 5.159,
|
| 1197 |
+
"eval_steps_per_second": 2.58,
|
| 1198 |
+
"step": 14500
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 5.13,
|
| 1202 |
+
"learning_rate": 3.468694096601073e-05,
|
| 1203 |
+
"loss": 0.5364,
|
| 1204 |
+
"step": 14600
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 5.17,
|
| 1208 |
+
"learning_rate": 3.443649373881932e-05,
|
| 1209 |
+
"loss": 0.543,
|
| 1210 |
+
"step": 14700
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 5.2,
|
| 1214 |
+
"learning_rate": 3.4186046511627904e-05,
|
| 1215 |
+
"loss": 0.5432,
|
| 1216 |
+
"step": 14800
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 5.24,
|
| 1220 |
+
"learning_rate": 3.3935599284436494e-05,
|
| 1221 |
+
"loss": 0.542,
|
| 1222 |
+
"step": 14900
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 5.27,
|
| 1226 |
+
"learning_rate": 3.368515205724508e-05,
|
| 1227 |
+
"loss": 0.5385,
|
| 1228 |
+
"step": 15000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 5.27,
|
| 1232 |
+
"eval_bleu": 44.1326,
|
| 1233 |
+
"eval_chrf++": 62.3372,
|
| 1234 |
+
"eval_gen_len": 17.8174,
|
| 1235 |
+
"eval_loss": 0.7036887407302856,
|
| 1236 |
+
"eval_runtime": 1418.4921,
|
| 1237 |
+
"eval_samples_per_second": 5.161,
|
| 1238 |
+
"eval_steps_per_second": 2.581,
|
| 1239 |
+
"step": 15000
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 5.31,
|
| 1243 |
+
"learning_rate": 3.343470483005367e-05,
|
| 1244 |
+
"loss": 0.5467,
|
| 1245 |
+
"step": 15100
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 5.34,
|
| 1249 |
+
"learning_rate": 3.318425760286225e-05,
|
| 1250 |
+
"loss": 0.5466,
|
| 1251 |
+
"step": 15200
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 5.38,
|
| 1255 |
+
"learning_rate": 3.2933810375670835e-05,
|
| 1256 |
+
"loss": 0.5439,
|
| 1257 |
+
"step": 15300
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 5.41,
|
| 1261 |
+
"learning_rate": 3.2683363148479426e-05,
|
| 1262 |
+
"loss": 0.5403,
|
| 1263 |
+
"step": 15400
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 5.45,
|
| 1267 |
+
"learning_rate": 3.243291592128801e-05,
|
| 1268 |
+
"loss": 0.5481,
|
| 1269 |
+
"step": 15500
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 5.45,
|
| 1273 |
+
"eval_bleu": 44.053,
|
| 1274 |
+
"eval_chrf++": 62.418,
|
| 1275 |
+
"eval_gen_len": 17.7614,
|
| 1276 |
+
"eval_loss": 0.6976599097251892,
|
| 1277 |
+
"eval_runtime": 1417.644,
|
| 1278 |
+
"eval_samples_per_second": 5.164,
|
| 1279 |
+
"eval_steps_per_second": 2.582,
|
| 1280 |
+
"step": 15500
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 5.48,
|
| 1284 |
+
"learning_rate": 3.21824686940966e-05,
|
| 1285 |
+
"loss": 0.5445,
|
| 1286 |
+
"step": 15600
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 5.52,
|
| 1290 |
+
"learning_rate": 3.1932021466905183e-05,
|
| 1291 |
+
"loss": 0.5518,
|
| 1292 |
+
"step": 15700
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 5.55,
|
| 1296 |
+
"learning_rate": 3.1681574239713774e-05,
|
| 1297 |
+
"loss": 0.5451,
|
| 1298 |
+
"step": 15800
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 5.59,
|
| 1302 |
+
"learning_rate": 3.143112701252236e-05,
|
| 1303 |
+
"loss": 0.5387,
|
| 1304 |
+
"step": 15900
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 5.62,
|
| 1308 |
+
"learning_rate": 3.118067978533094e-05,
|
| 1309 |
+
"loss": 0.5473,
|
| 1310 |
+
"step": 16000
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 5.62,
|
| 1314 |
+
"eval_bleu": 44.2406,
|
| 1315 |
+
"eval_chrf++": 62.4882,
|
| 1316 |
+
"eval_gen_len": 17.8263,
|
| 1317 |
+
"eval_loss": 0.6982511878013611,
|
| 1318 |
+
"eval_runtime": 1415.9788,
|
| 1319 |
+
"eval_samples_per_second": 5.17,
|
| 1320 |
+
"eval_steps_per_second": 2.585,
|
| 1321 |
+
"step": 16000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 5.66,
|
| 1325 |
+
"learning_rate": 3.093023255813953e-05,
|
| 1326 |
+
"loss": 0.5483,
|
| 1327 |
+
"step": 16100
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 5.69,
|
| 1331 |
+
"learning_rate": 3.0679785330948115e-05,
|
| 1332 |
+
"loss": 0.537,
|
| 1333 |
+
"step": 16200
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 5.73,
|
| 1337 |
+
"learning_rate": 3.0429338103756705e-05,
|
| 1338 |
+
"loss": 0.5479,
|
| 1339 |
+
"step": 16300
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 5.76,
|
| 1343 |
+
"learning_rate": 3.0178890876565292e-05,
|
| 1344 |
+
"loss": 0.5445,
|
| 1345 |
+
"step": 16400
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 5.8,
|
| 1349 |
+
"learning_rate": 2.992844364937388e-05,
|
| 1350 |
+
"loss": 0.5466,
|
| 1351 |
+
"step": 16500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 5.8,
|
| 1355 |
+
"eval_bleu": 44.2692,
|
| 1356 |
+
"eval_chrf++": 62.4172,
|
| 1357 |
+
"eval_gen_len": 17.7783,
|
| 1358 |
+
"eval_loss": 0.6904399394989014,
|
| 1359 |
+
"eval_runtime": 1415.8621,
|
| 1360 |
+
"eval_samples_per_second": 5.171,
|
| 1361 |
+
"eval_steps_per_second": 2.586,
|
| 1362 |
+
"step": 16500
|
| 1363 |
+
}
|
| 1364 |
+
],
|
| 1365 |
+
"logging_steps": 100,
|
| 1366 |
+
"max_steps": 28450,
|
| 1367 |
+
"num_train_epochs": 10,
|
| 1368 |
+
"save_steps": 1500,
|
| 1369 |
+
"total_flos": 2.2884516243072614e+18,
|
| 1370 |
+
"trial_name": null,
|
| 1371 |
+
"trial_params": null
|
| 1372 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb48f2e608fd6bf18e446724f849abe2dd8a18b3cb10cdd4bff2b84d2d209d9
|
| 3 |
+
size 4728
|