Kleber commited on
Commit
6ec1322
1 Parent(s): ea27839

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/kk/tmp1.3B/checkpoint-4000",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "M2M100ForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 8192,
13
+ "decoder_layerdrop": 0,
14
+ "decoder_layers": 24,
15
+ "decoder_start_token_id": 2,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 16,
18
+ "encoder_ffn_dim": 8192,
19
+ "encoder_layerdrop": 0,
20
+ "encoder_layers": 24,
21
+ "eos_token_id": 2,
22
+ "init_std": 0.02,
23
+ "is_encoder_decoder": true,
24
+ "max_length": 200,
25
+ "max_position_embeddings": 1024,
26
+ "model_type": "m2m_100",
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 1,
29
+ "scale_embedding": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.31.0",
32
+ "use_cache": true,
33
+ "vocab_size": 256206
34
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "max_length": 200,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.31.0"
8
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04f22c94e2e7aaac7a13b2606430ddf3306be8c2383bf5cc0701d6642bd036f
3
+ size 10965715027
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8f1b8ad6d85bca8df4f5903238c841b0f481fdec6b3f657e6316fc093533a7
3
+ size 5482902982
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c568d936a4d1b0a99d718696bf82098e7d69629aab722fdf771c47a3b9f275
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d653c8f8ec18acad537bdd4ad915bb75f1beae13b413e299ab26909344ad45
3
+ size 627
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
special_tokens_map.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ace_Arab",
4
+ "ace_Latn",
5
+ "acm_Arab",
6
+ "acq_Arab",
7
+ "aeb_Arab",
8
+ "afr_Latn",
9
+ "ajp_Arab",
10
+ "aka_Latn",
11
+ "amh_Ethi",
12
+ "apc_Arab",
13
+ "arb_Arab",
14
+ "ars_Arab",
15
+ "ary_Arab",
16
+ "arz_Arab",
17
+ "asm_Beng",
18
+ "ast_Latn",
19
+ "awa_Deva",
20
+ "ayr_Latn",
21
+ "azb_Arab",
22
+ "azj_Latn",
23
+ "bak_Cyrl",
24
+ "bam_Latn",
25
+ "ban_Latn",
26
+ "bel_Cyrl",
27
+ "bem_Latn",
28
+ "ben_Beng",
29
+ "bho_Deva",
30
+ "bjn_Arab",
31
+ "bjn_Latn",
32
+ "bod_Tibt",
33
+ "bos_Latn",
34
+ "bug_Latn",
35
+ "bul_Cyrl",
36
+ "cat_Latn",
37
+ "ceb_Latn",
38
+ "ces_Latn",
39
+ "cjk_Latn",
40
+ "ckb_Arab",
41
+ "crh_Latn",
42
+ "cym_Latn",
43
+ "dan_Latn",
44
+ "deu_Latn",
45
+ "dik_Latn",
46
+ "dyu_Latn",
47
+ "dzo_Tibt",
48
+ "ell_Grek",
49
+ "eng_Latn",
50
+ "epo_Latn",
51
+ "est_Latn",
52
+ "eus_Latn",
53
+ "ewe_Latn",
54
+ "fao_Latn",
55
+ "pes_Arab",
56
+ "fij_Latn",
57
+ "fin_Latn",
58
+ "fon_Latn",
59
+ "fra_Latn",
60
+ "fur_Latn",
61
+ "fuv_Latn",
62
+ "gla_Latn",
63
+ "gle_Latn",
64
+ "glg_Latn",
65
+ "grn_Latn",
66
+ "guj_Gujr",
67
+ "hat_Latn",
68
+ "hau_Latn",
69
+ "heb_Hebr",
70
+ "hin_Deva",
71
+ "hne_Deva",
72
+ "hrv_Latn",
73
+ "hun_Latn",
74
+ "hye_Armn",
75
+ "ibo_Latn",
76
+ "ilo_Latn",
77
+ "ind_Latn",
78
+ "isl_Latn",
79
+ "ita_Latn",
80
+ "jav_Latn",
81
+ "jpn_Jpan",
82
+ "kab_Latn",
83
+ "kac_Latn",
84
+ "kam_Latn",
85
+ "kan_Knda",
86
+ "kas_Arab",
87
+ "kas_Deva",
88
+ "kat_Geor",
89
+ "knc_Arab",
90
+ "knc_Latn",
91
+ "kaz_Cyrl",
92
+ "kbp_Latn",
93
+ "kea_Latn",
94
+ "khm_Khmr",
95
+ "kik_Latn",
96
+ "kin_Latn",
97
+ "kir_Cyrl",
98
+ "kmb_Latn",
99
+ "kon_Latn",
100
+ "kor_Hang",
101
+ "kmr_Latn",
102
+ "lao_Laoo",
103
+ "lvs_Latn",
104
+ "lij_Latn",
105
+ "lim_Latn",
106
+ "lin_Latn",
107
+ "lit_Latn",
108
+ "lmo_Latn",
109
+ "ltg_Latn",
110
+ "ltz_Latn",
111
+ "lua_Latn",
112
+ "lug_Latn",
113
+ "luo_Latn",
114
+ "lus_Latn",
115
+ "mag_Deva",
116
+ "mai_Deva",
117
+ "mal_Mlym",
118
+ "mar_Deva",
119
+ "min_Latn",
120
+ "mkd_Cyrl",
121
+ "plt_Latn",
122
+ "mlt_Latn",
123
+ "mni_Beng",
124
+ "khk_Cyrl",
125
+ "mos_Latn",
126
+ "mri_Latn",
127
+ "zsm_Latn",
128
+ "mya_Mymr",
129
+ "nld_Latn",
130
+ "nno_Latn",
131
+ "nob_Latn",
132
+ "npi_Deva",
133
+ "nso_Latn",
134
+ "nus_Latn",
135
+ "nya_Latn",
136
+ "oci_Latn",
137
+ "gaz_Latn",
138
+ "ory_Orya",
139
+ "pag_Latn",
140
+ "pan_Guru",
141
+ "pap_Latn",
142
+ "pol_Latn",
143
+ "por_Latn",
144
+ "prs_Arab",
145
+ "pbt_Arab",
146
+ "quy_Latn",
147
+ "ron_Latn",
148
+ "run_Latn",
149
+ "rus_Cyrl",
150
+ "sag_Latn",
151
+ "san_Deva",
152
+ "sat_Beng",
153
+ "scn_Latn",
154
+ "shn_Mymr",
155
+ "sin_Sinh",
156
+ "slk_Latn",
157
+ "slv_Latn",
158
+ "smo_Latn",
159
+ "sna_Latn",
160
+ "snd_Arab",
161
+ "som_Latn",
162
+ "sot_Latn",
163
+ "spa_Latn",
164
+ "als_Latn",
165
+ "srd_Latn",
166
+ "srp_Cyrl",
167
+ "ssw_Latn",
168
+ "sun_Latn",
169
+ "swe_Latn",
170
+ "swh_Latn",
171
+ "szl_Latn",
172
+ "tam_Taml",
173
+ "tat_Cyrl",
174
+ "tel_Telu",
175
+ "tgk_Cyrl",
176
+ "tgl_Latn",
177
+ "tha_Thai",
178
+ "tir_Ethi",
179
+ "taq_Latn",
180
+ "taq_Tfng",
181
+ "tpi_Latn",
182
+ "tsn_Latn",
183
+ "tso_Latn",
184
+ "tuk_Latn",
185
+ "tum_Latn",
186
+ "tur_Latn",
187
+ "twi_Latn",
188
+ "tzm_Tfng",
189
+ "uig_Arab",
190
+ "ukr_Cyrl",
191
+ "umb_Latn",
192
+ "urd_Arab",
193
+ "uzn_Latn",
194
+ "vec_Latn",
195
+ "vie_Latn",
196
+ "war_Latn",
197
+ "wol_Latn",
198
+ "xho_Latn",
199
+ "ydd_Hebr",
200
+ "yor_Latn",
201
+ "yue_Hant",
202
+ "zho_Hans",
203
+ "zho_Hant",
204
+ "zul_Latn"
205
+ ],
206
+ "bos_token": "<s>",
207
+ "cls_token": "<s>",
208
+ "eos_token": "</s>",
209
+ "mask_token": {
210
+ "content": "<mask>",
211
+ "lstrip": true,
212
+ "normalized": true,
213
+ "rstrip": false,
214
+ "single_word": false
215
+ },
216
+ "pad_token": "<pad>",
217
+ "sep_token": "</s>",
218
+ "unk_token": "<unk>"
219
+ }
220
+
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e316b82de11d0f951f370943b3c438311629547285129b0b81dadabd01bca665
3
+ size 17331176
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 1024,
15
+ "name_or_path": "facebook/nllb-200-distilled-600M",
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "src_lang": null,
21
+ "tgt_lang": null,
22
+ "tokenizer_class": "NllbTokenizer",
23
+ "unk_token": "<unk>"
24
+ }
trainer_state.json ADDED
@@ -0,0 +1,966 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9696311523096615,
5
+ "global_step": 25000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.980607376953807e-05,
13
+ "loss": 0.2765,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "eval_bleu": 31.7549,
19
+ "eval_chrf++": 58.7253,
20
+ "eval_gen_len": 22.1982,
21
+ "eval_loss": 1.1465204954147339,
22
+ "eval_runtime": 2452.853,
23
+ "eval_samples_per_second": 6.832,
24
+ "eval_spbleu": 45.4525,
25
+ "eval_steps_per_second": 0.683,
26
+ "eval_ter": 56.1665,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 0.04,
31
+ "learning_rate": 4.9612147539076136e-05,
32
+ "loss": 0.2494,
33
+ "step": 1000
34
+ },
35
+ {
36
+ "epoch": 0.04,
37
+ "eval_bleu": 30.6155,
38
+ "eval_chrf++": 58.4159,
39
+ "eval_gen_len": 22.5912,
40
+ "eval_loss": 1.1881319284439087,
41
+ "eval_runtime": 2483.4163,
42
+ "eval_samples_per_second": 6.748,
43
+ "eval_spbleu": 43.8898,
44
+ "eval_steps_per_second": 0.675,
45
+ "eval_ter": 57.8655,
46
+ "step": 1000
47
+ },
48
+ {
49
+ "epoch": 0.06,
50
+ "learning_rate": 4.94182213086142e-05,
51
+ "loss": 0.2576,
52
+ "step": 1500
53
+ },
54
+ {
55
+ "epoch": 0.06,
56
+ "eval_bleu": 29.789,
57
+ "eval_chrf++": 57.4443,
58
+ "eval_gen_len": 22.689,
59
+ "eval_loss": 1.1570631265640259,
60
+ "eval_runtime": 2516.9829,
61
+ "eval_samples_per_second": 6.658,
62
+ "eval_spbleu": 43.1911,
63
+ "eval_steps_per_second": 0.666,
64
+ "eval_ter": 59.1299,
65
+ "step": 1500
66
+ },
67
+ {
68
+ "epoch": 0.08,
69
+ "learning_rate": 4.922429507815227e-05,
70
+ "loss": 0.2624,
71
+ "step": 2000
72
+ },
73
+ {
74
+ "epoch": 0.08,
75
+ "eval_bleu": 31.0288,
76
+ "eval_chrf++": 58.4502,
77
+ "eval_gen_len": 22.467,
78
+ "eval_loss": 1.1633208990097046,
79
+ "eval_runtime": 2478.0629,
80
+ "eval_samples_per_second": 6.763,
81
+ "eval_spbleu": 44.5894,
82
+ "eval_steps_per_second": 0.676,
83
+ "eval_ter": 57.6651,
84
+ "step": 2000
85
+ },
86
+ {
87
+ "epoch": 0.1,
88
+ "learning_rate": 4.9030368847690336e-05,
89
+ "loss": 0.2284,
90
+ "step": 2500
91
+ },
92
+ {
93
+ "epoch": 0.1,
94
+ "eval_bleu": 31.2885,
95
+ "eval_chrf++": 58.0527,
96
+ "eval_gen_len": 22.7715,
97
+ "eval_loss": 1.1723754405975342,
98
+ "eval_runtime": 2538.3187,
99
+ "eval_samples_per_second": 6.602,
100
+ "eval_spbleu": 44.5546,
101
+ "eval_steps_per_second": 0.66,
102
+ "eval_ter": 57.8341,
103
+ "step": 2500
104
+ },
105
+ {
106
+ "epoch": 0.12,
107
+ "learning_rate": 4.88364426172284e-05,
108
+ "loss": 0.2314,
109
+ "step": 3000
110
+ },
111
+ {
112
+ "epoch": 0.12,
113
+ "eval_bleu": 30.7414,
114
+ "eval_chrf++": 58.1161,
115
+ "eval_gen_len": 22.5233,
116
+ "eval_loss": 1.1770201921463013,
117
+ "eval_runtime": 2476.3422,
118
+ "eval_samples_per_second": 6.767,
119
+ "eval_spbleu": 44.334,
120
+ "eval_steps_per_second": 0.677,
121
+ "eval_ter": 58.228,
122
+ "step": 3000
123
+ },
124
+ {
125
+ "epoch": 0.14,
126
+ "learning_rate": 4.8642516386766476e-05,
127
+ "loss": 0.2294,
128
+ "step": 3500
129
+ },
130
+ {
131
+ "epoch": 0.14,
132
+ "eval_bleu": 31.7781,
133
+ "eval_chrf++": 58.9642,
134
+ "eval_gen_len": 22.4762,
135
+ "eval_loss": 1.2094552516937256,
136
+ "eval_runtime": 2449.7863,
137
+ "eval_samples_per_second": 6.841,
138
+ "eval_spbleu": 45.3044,
139
+ "eval_steps_per_second": 0.684,
140
+ "eval_ter": 56.8016,
141
+ "step": 3500
142
+ },
143
+ {
144
+ "epoch": 0.16,
145
+ "learning_rate": 4.844859015630454e-05,
146
+ "loss": 0.2457,
147
+ "step": 4000
148
+ },
149
+ {
150
+ "epoch": 0.16,
151
+ "eval_bleu": 31.0111,
152
+ "eval_chrf++": 58.203,
153
+ "eval_gen_len": 22.8377,
154
+ "eval_loss": 1.1406781673431396,
155
+ "eval_runtime": 2532.244,
156
+ "eval_samples_per_second": 6.618,
157
+ "eval_spbleu": 44.1543,
158
+ "eval_steps_per_second": 0.662,
159
+ "eval_ter": 57.7781,
160
+ "step": 4000
161
+ },
162
+ {
163
+ "epoch": 0.17,
164
+ "learning_rate": 4.825466392584262e-05,
165
+ "loss": 0.5335,
166
+ "step": 4500
167
+ },
168
+ {
169
+ "epoch": 0.17,
170
+ "eval_bleu": 31.2577,
171
+ "eval_chrf++": 58.4688,
172
+ "eval_gen_len": 22.6196,
173
+ "eval_loss": 1.0519380569458008,
174
+ "eval_runtime": 2534.3052,
175
+ "eval_samples_per_second": 6.612,
176
+ "eval_spbleu": 44.8062,
177
+ "eval_steps_per_second": 0.661,
178
+ "eval_ter": 57.333,
179
+ "step": 4500
180
+ },
181
+ {
182
+ "epoch": 0.19,
183
+ "learning_rate": 4.8060737695380683e-05,
184
+ "loss": 0.5162,
185
+ "step": 5000
186
+ },
187
+ {
188
+ "epoch": 0.19,
189
+ "eval_bleu": 32.2483,
190
+ "eval_chrf++": 59.2532,
191
+ "eval_gen_len": 22.461,
192
+ "eval_loss": 1.0528730154037476,
193
+ "eval_runtime": 2496.711,
194
+ "eval_samples_per_second": 6.712,
195
+ "eval_spbleu": 45.5671,
196
+ "eval_steps_per_second": 0.671,
197
+ "eval_ter": 56.2061,
198
+ "step": 5000
199
+ },
200
+ {
201
+ "epoch": 0.21,
202
+ "learning_rate": 4.786681146491875e-05,
203
+ "loss": 0.5135,
204
+ "step": 5500
205
+ },
206
+ {
207
+ "epoch": 0.21,
208
+ "eval_bleu": 32.273,
209
+ "eval_chrf++": 59.7056,
210
+ "eval_gen_len": 22.429,
211
+ "eval_loss": 1.0336111783981323,
212
+ "eval_runtime": 2482.8365,
213
+ "eval_samples_per_second": 6.75,
214
+ "eval_spbleu": 46.0401,
215
+ "eval_steps_per_second": 0.675,
216
+ "eval_ter": 56.4706,
217
+ "step": 5500
218
+ },
219
+ {
220
+ "epoch": 0.23,
221
+ "learning_rate": 4.767288523445682e-05,
222
+ "loss": 0.5227,
223
+ "step": 6000
224
+ },
225
+ {
226
+ "epoch": 0.23,
227
+ "eval_bleu": 32.9242,
228
+ "eval_chrf++": 59.8998,
229
+ "eval_gen_len": 22.6151,
230
+ "eval_loss": 1.0207685232162476,
231
+ "eval_runtime": 2489.8807,
232
+ "eval_samples_per_second": 6.73,
233
+ "eval_spbleu": 46.3519,
234
+ "eval_steps_per_second": 0.673,
235
+ "eval_ter": 55.7539,
236
+ "step": 6000
237
+ },
238
+ {
239
+ "epoch": 0.25,
240
+ "learning_rate": 4.7478959003994884e-05,
241
+ "loss": 0.5181,
242
+ "step": 6500
243
+ },
244
+ {
245
+ "epoch": 0.25,
246
+ "eval_bleu": 33.276,
247
+ "eval_chrf++": 60.0419,
248
+ "eval_gen_len": 22.3479,
249
+ "eval_loss": 1.0149798393249512,
250
+ "eval_runtime": 2483.325,
251
+ "eval_samples_per_second": 6.748,
252
+ "eval_spbleu": 46.8525,
253
+ "eval_steps_per_second": 0.675,
254
+ "eval_ter": 55.268,
255
+ "step": 6500
256
+ },
257
+ {
258
+ "epoch": 0.27,
259
+ "learning_rate": 4.728503277353295e-05,
260
+ "loss": 0.4933,
261
+ "step": 7000
262
+ },
263
+ {
264
+ "epoch": 0.27,
265
+ "eval_bleu": 33.8673,
266
+ "eval_chrf++": 60.2337,
267
+ "eval_gen_len": 22.3286,
268
+ "eval_loss": 1.013890027999878,
269
+ "eval_runtime": 2447.8332,
270
+ "eval_samples_per_second": 6.846,
271
+ "eval_spbleu": 47.5698,
272
+ "eval_steps_per_second": 0.685,
273
+ "eval_ter": 54.9242,
274
+ "step": 7000
275
+ },
276
+ {
277
+ "epoch": 0.29,
278
+ "learning_rate": 4.709110654307102e-05,
279
+ "loss": 0.5043,
280
+ "step": 7500
281
+ },
282
+ {
283
+ "epoch": 0.29,
284
+ "eval_bleu": 33.4038,
285
+ "eval_chrf++": 60.1428,
286
+ "eval_gen_len": 22.5602,
287
+ "eval_loss": 1.0105745792388916,
288
+ "eval_runtime": 2487.4813,
289
+ "eval_samples_per_second": 6.737,
290
+ "eval_spbleu": 47.2035,
291
+ "eval_steps_per_second": 0.674,
292
+ "eval_ter": 55.3892,
293
+ "step": 7500
294
+ },
295
+ {
296
+ "epoch": 0.31,
297
+ "learning_rate": 4.6897180312609084e-05,
298
+ "loss": 0.5013,
299
+ "step": 8000
300
+ },
301
+ {
302
+ "epoch": 0.31,
303
+ "eval_bleu": 34.3818,
304
+ "eval_chrf++": 60.7806,
305
+ "eval_gen_len": 22.365,
306
+ "eval_loss": 1.0027358531951904,
307
+ "eval_runtime": 2471.8949,
308
+ "eval_samples_per_second": 6.779,
309
+ "eval_spbleu": 47.8553,
310
+ "eval_steps_per_second": 0.678,
311
+ "eval_ter": 54.3031,
312
+ "step": 8000
313
+ },
314
+ {
315
+ "epoch": 0.33,
316
+ "learning_rate": 4.670325408214715e-05,
317
+ "loss": 0.4898,
318
+ "step": 8500
319
+ },
320
+ {
321
+ "epoch": 0.33,
322
+ "eval_bleu": 34.5081,
323
+ "eval_chrf++": 60.6054,
324
+ "eval_gen_len": 22.1483,
325
+ "eval_loss": 0.9998334646224976,
326
+ "eval_runtime": 2464.0531,
327
+ "eval_samples_per_second": 6.801,
328
+ "eval_spbleu": 48.0651,
329
+ "eval_steps_per_second": 0.68,
330
+ "eval_ter": 53.7379,
331
+ "step": 8500
332
+ },
333
+ {
334
+ "epoch": 0.35,
335
+ "learning_rate": 4.650932785168522e-05,
336
+ "loss": 0.5011,
337
+ "step": 9000
338
+ },
339
+ {
340
+ "epoch": 0.35,
341
+ "eval_bleu": 33.9543,
342
+ "eval_chrf++": 60.3165,
343
+ "eval_gen_len": 22.2106,
344
+ "eval_loss": 0.9939271211624146,
345
+ "eval_runtime": 2455.6708,
346
+ "eval_samples_per_second": 6.824,
347
+ "eval_spbleu": 47.6339,
348
+ "eval_steps_per_second": 0.683,
349
+ "eval_ter": 54.3159,
350
+ "step": 9000
351
+ },
352
+ {
353
+ "epoch": 0.37,
354
+ "learning_rate": 4.6315401621223284e-05,
355
+ "loss": 0.5014,
356
+ "step": 9500
357
+ },
358
+ {
359
+ "epoch": 0.37,
360
+ "eval_bleu": 35.12,
361
+ "eval_chrf++": 61.0072,
362
+ "eval_gen_len": 22.2949,
363
+ "eval_loss": 0.9882155060768127,
364
+ "eval_runtime": 2466.3803,
365
+ "eval_samples_per_second": 6.795,
366
+ "eval_spbleu": 48.5338,
367
+ "eval_steps_per_second": 0.68,
368
+ "eval_ter": 53.6108,
369
+ "step": 9500
370
+ },
371
+ {
372
+ "epoch": 0.39,
373
+ "learning_rate": 4.612147539076135e-05,
374
+ "loss": 0.4861,
375
+ "step": 10000
376
+ },
377
+ {
378
+ "epoch": 0.39,
379
+ "eval_bleu": 34.2002,
380
+ "eval_chrf++": 60.9191,
381
+ "eval_gen_len": 22.472,
382
+ "eval_loss": 0.9832409620285034,
383
+ "eval_runtime": 2528.4848,
384
+ "eval_samples_per_second": 6.628,
385
+ "eval_spbleu": 47.7142,
386
+ "eval_steps_per_second": 0.663,
387
+ "eval_ter": 54.9125,
388
+ "step": 10000
389
+ },
390
+ {
391
+ "epoch": 0.41,
392
+ "learning_rate": 4.5927549160299424e-05,
393
+ "loss": 0.4777,
394
+ "step": 10500
395
+ },
396
+ {
397
+ "epoch": 0.41,
398
+ "eval_bleu": 35.0653,
399
+ "eval_chrf++": 61.3647,
400
+ "eval_gen_len": 22.1853,
401
+ "eval_loss": 0.9780123829841614,
402
+ "eval_runtime": 2478.2202,
403
+ "eval_samples_per_second": 6.762,
404
+ "eval_spbleu": 48.6202,
405
+ "eval_steps_per_second": 0.676,
406
+ "eval_ter": 53.7728,
407
+ "step": 10500
408
+ },
409
+ {
410
+ "epoch": 0.43,
411
+ "learning_rate": 4.573362292983749e-05,
412
+ "loss": 0.4882,
413
+ "step": 11000
414
+ },
415
+ {
416
+ "epoch": 0.43,
417
+ "eval_bleu": 34.4099,
418
+ "eval_chrf++": 60.8297,
419
+ "eval_gen_len": 22.4734,
420
+ "eval_loss": 0.9755488038063049,
421
+ "eval_runtime": 2481.0601,
422
+ "eval_samples_per_second": 6.754,
423
+ "eval_spbleu": 48.1346,
424
+ "eval_steps_per_second": 0.676,
425
+ "eval_ter": 54.8636,
426
+ "step": 11000
427
+ },
428
+ {
429
+ "epoch": 0.45,
430
+ "learning_rate": 4.5539696699375565e-05,
431
+ "loss": 0.489,
432
+ "step": 11500
433
+ },
434
+ {
435
+ "epoch": 0.45,
436
+ "eval_bleu": 35.3644,
437
+ "eval_chrf++": 61.3208,
438
+ "eval_gen_len": 22.2351,
439
+ "eval_loss": 0.9737293720245361,
440
+ "eval_runtime": 2438.4039,
441
+ "eval_samples_per_second": 6.873,
442
+ "eval_spbleu": 49.0035,
443
+ "eval_steps_per_second": 0.687,
444
+ "eval_ter": 53.0538,
445
+ "step": 11500
446
+ },
447
+ {
448
+ "epoch": 0.47,
449
+ "learning_rate": 4.534577046891363e-05,
450
+ "loss": 0.4778,
451
+ "step": 12000
452
+ },
453
+ {
454
+ "epoch": 0.47,
455
+ "eval_bleu": 35.2536,
456
+ "eval_chrf++": 61.1847,
457
+ "eval_gen_len": 22.3455,
458
+ "eval_loss": 0.9639460444450378,
459
+ "eval_runtime": 2456.4058,
460
+ "eval_samples_per_second": 6.822,
461
+ "eval_spbleu": 48.8273,
462
+ "eval_steps_per_second": 0.682,
463
+ "eval_ter": 53.7647,
464
+ "step": 12000
465
+ },
466
+ {
467
+ "epoch": 0.48,
468
+ "learning_rate": 4.51518442384517e-05,
469
+ "loss": 0.4659,
470
+ "step": 12500
471
+ },
472
+ {
473
+ "epoch": 0.48,
474
+ "eval_bleu": 35.0392,
475
+ "eval_chrf++": 61.2274,
476
+ "eval_gen_len": 22.6852,
477
+ "eval_loss": 0.9616146683692932,
478
+ "eval_runtime": 2525.3804,
479
+ "eval_samples_per_second": 6.636,
480
+ "eval_spbleu": 48.3755,
481
+ "eval_steps_per_second": 0.664,
482
+ "eval_ter": 54.1807,
483
+ "step": 12500
484
+ },
485
+ {
486
+ "epoch": 0.5,
487
+ "learning_rate": 4.4957918007989765e-05,
488
+ "loss": 0.4882,
489
+ "step": 13000
490
+ },
491
+ {
492
+ "epoch": 0.5,
493
+ "eval_bleu": 35.2876,
494
+ "eval_chrf++": 61.5126,
495
+ "eval_gen_len": 22.4171,
496
+ "eval_loss": 0.9623438715934753,
497
+ "eval_runtime": 2448.0204,
498
+ "eval_samples_per_second": 6.846,
499
+ "eval_spbleu": 48.9762,
500
+ "eval_steps_per_second": 0.685,
501
+ "eval_ter": 53.5118,
502
+ "step": 13000
503
+ },
504
+ {
505
+ "epoch": 0.52,
506
+ "learning_rate": 4.476399177752783e-05,
507
+ "loss": 0.4757,
508
+ "step": 13500
509
+ },
510
+ {
511
+ "epoch": 0.52,
512
+ "eval_bleu": 36.1928,
513
+ "eval_chrf++": 61.7736,
514
+ "eval_gen_len": 22.2772,
515
+ "eval_loss": 0.9600822925567627,
516
+ "eval_runtime": 2458.1658,
517
+ "eval_samples_per_second": 6.817,
518
+ "eval_spbleu": 49.4709,
519
+ "eval_steps_per_second": 0.682,
520
+ "eval_ter": 52.9163,
521
+ "step": 13500
522
+ },
523
+ {
524
+ "epoch": 0.54,
525
+ "learning_rate": 4.45700655470659e-05,
526
+ "loss": 0.4532,
527
+ "step": 14000
528
+ },
529
+ {
530
+ "epoch": 0.54,
531
+ "eval_bleu": 35.3757,
532
+ "eval_chrf++": 61.4145,
533
+ "eval_gen_len": 22.4656,
534
+ "eval_loss": 0.9569535255432129,
535
+ "eval_runtime": 2509.366,
536
+ "eval_samples_per_second": 6.678,
537
+ "eval_spbleu": 48.8161,
538
+ "eval_steps_per_second": 0.668,
539
+ "eval_ter": 53.6143,
540
+ "step": 14000
541
+ },
542
+ {
543
+ "epoch": 0.56,
544
+ "learning_rate": 4.4376139316603965e-05,
545
+ "loss": 0.4624,
546
+ "step": 14500
547
+ },
548
+ {
549
+ "epoch": 0.56,
550
+ "eval_bleu": 35.5809,
551
+ "eval_chrf++": 61.5561,
552
+ "eval_gen_len": 22.6749,
553
+ "eval_loss": 0.9505798816680908,
554
+ "eval_runtime": 2539.8539,
555
+ "eval_samples_per_second": 6.598,
556
+ "eval_spbleu": 48.7951,
557
+ "eval_steps_per_second": 0.66,
558
+ "eval_ter": 53.478,
559
+ "step": 14500
560
+ },
561
+ {
562
+ "epoch": 0.58,
563
+ "learning_rate": 4.418221308614203e-05,
564
+ "loss": 0.4731,
565
+ "step": 15000
566
+ },
567
+ {
568
+ "epoch": 0.58,
569
+ "eval_bleu": 36.0873,
570
+ "eval_chrf++": 61.7264,
571
+ "eval_gen_len": 22.5004,
572
+ "eval_loss": 0.9501732587814331,
573
+ "eval_runtime": 2492.0241,
574
+ "eval_samples_per_second": 6.725,
575
+ "eval_spbleu": 49.4647,
576
+ "eval_steps_per_second": 0.673,
577
+ "eval_ter": 52.7939,
578
+ "step": 15000
579
+ },
580
+ {
581
+ "epoch": 0.6,
582
+ "learning_rate": 4.39882868556801e-05,
583
+ "loss": 0.4794,
584
+ "step": 15500
585
+ },
586
+ {
587
+ "epoch": 0.6,
588
+ "eval_bleu": 36.1453,
589
+ "eval_chrf++": 61.9504,
590
+ "eval_gen_len": 22.3361,
591
+ "eval_loss": 0.9433434009552002,
592
+ "eval_runtime": 2532.9385,
593
+ "eval_samples_per_second": 6.616,
594
+ "eval_spbleu": 49.3902,
595
+ "eval_steps_per_second": 0.662,
596
+ "eval_ter": 52.9862,
597
+ "step": 15500
598
+ },
599
+ {
600
+ "epoch": 0.62,
601
+ "learning_rate": 4.3794360625218165e-05,
602
+ "loss": 0.4616,
603
+ "step": 16000
604
+ },
605
+ {
606
+ "epoch": 0.62,
607
+ "eval_bleu": 36.4514,
608
+ "eval_chrf++": 62.2395,
609
+ "eval_gen_len": 22.4107,
610
+ "eval_loss": 0.9410406351089478,
611
+ "eval_runtime": 2518.4187,
612
+ "eval_samples_per_second": 6.654,
613
+ "eval_spbleu": 49.7739,
614
+ "eval_steps_per_second": 0.665,
615
+ "eval_ter": 52.5317,
616
+ "step": 16000
617
+ },
618
+ {
619
+ "epoch": 0.64,
620
+ "learning_rate": 4.360043439475623e-05,
621
+ "loss": 0.4768,
622
+ "step": 16500
623
+ },
624
+ {
625
+ "epoch": 0.64,
626
+ "eval_bleu": 36.8462,
627
+ "eval_chrf++": 62.2425,
628
+ "eval_gen_len": 22.348,
629
+ "eval_loss": 0.9391294717788696,
630
+ "eval_runtime": 2464.2252,
631
+ "eval_samples_per_second": 6.801,
632
+ "eval_spbleu": 50.2231,
633
+ "eval_steps_per_second": 0.68,
634
+ "eval_ter": 52.1938,
635
+ "step": 16500
636
+ },
637
+ {
638
+ "epoch": 0.66,
639
+ "learning_rate": 4.3406508164294306e-05,
640
+ "loss": 0.4482,
641
+ "step": 17000
642
+ },
643
+ {
644
+ "epoch": 0.66,
645
+ "eval_bleu": 36.9137,
646
+ "eval_chrf++": 62.5127,
647
+ "eval_gen_len": 22.5448,
648
+ "eval_loss": 0.9357725381851196,
649
+ "eval_runtime": 2549.3781,
650
+ "eval_samples_per_second": 6.573,
651
+ "eval_spbleu": 49.9168,
652
+ "eval_steps_per_second": 0.657,
653
+ "eval_ter": 52.3604,
654
+ "step": 17000
655
+ },
656
+ {
657
+ "epoch": 0.68,
658
+ "learning_rate": 4.321258193383237e-05,
659
+ "loss": 0.4648,
660
+ "step": 17500
661
+ },
662
+ {
663
+ "epoch": 0.68,
664
+ "eval_bleu": 37.1733,
665
+ "eval_chrf++": 62.7256,
666
+ "eval_gen_len": 22.4406,
667
+ "eval_loss": 0.935612678527832,
668
+ "eval_runtime": 2499.4089,
669
+ "eval_samples_per_second": 6.705,
670
+ "eval_spbleu": 50.417,
671
+ "eval_steps_per_second": 0.671,
672
+ "eval_ter": 51.7731,
673
+ "step": 17500
674
+ },
675
+ {
676
+ "epoch": 0.7,
677
+ "learning_rate": 4.301865570337044e-05,
678
+ "loss": 0.4642,
679
+ "step": 18000
680
+ },
681
+ {
682
+ "epoch": 0.7,
683
+ "eval_bleu": 37.1839,
684
+ "eval_chrf++": 62.648,
685
+ "eval_gen_len": 22.4244,
686
+ "eval_loss": 0.9331343770027161,
687
+ "eval_runtime": 2493.1006,
688
+ "eval_samples_per_second": 6.722,
689
+ "eval_spbleu": 50.1902,
690
+ "eval_steps_per_second": 0.672,
691
+ "eval_ter": 51.702,
692
+ "step": 18000
693
+ },
694
+ {
695
+ "epoch": 0.72,
696
+ "learning_rate": 4.2824729472908506e-05,
697
+ "loss": 0.4691,
698
+ "step": 18500
699
+ },
700
+ {
701
+ "epoch": 0.72,
702
+ "eval_bleu": 37.1915,
703
+ "eval_chrf++": 62.7489,
704
+ "eval_gen_len": 22.4675,
705
+ "eval_loss": 0.9320312142372131,
706
+ "eval_runtime": 2469.7829,
707
+ "eval_samples_per_second": 6.785,
708
+ "eval_spbleu": 50.4819,
709
+ "eval_steps_per_second": 0.679,
710
+ "eval_ter": 51.5528,
711
+ "step": 18500
712
+ },
713
+ {
714
+ "epoch": 0.74,
715
+ "learning_rate": 4.263080324244658e-05,
716
+ "loss": 0.4676,
717
+ "step": 19000
718
+ },
719
+ {
720
+ "epoch": 0.74,
721
+ "eval_bleu": 36.4381,
722
+ "eval_chrf++": 62.2257,
723
+ "eval_gen_len": 22.7873,
724
+ "eval_loss": 0.9254695177078247,
725
+ "eval_runtime": 2555.4331,
726
+ "eval_samples_per_second": 6.558,
727
+ "eval_spbleu": 49.2678,
728
+ "eval_steps_per_second": 0.656,
729
+ "eval_ter": 52.7193,
730
+ "step": 19000
731
+ },
732
+ {
733
+ "epoch": 0.76,
734
+ "learning_rate": 4.2436877011984646e-05,
735
+ "loss": 0.4515,
736
+ "step": 19500
737
+ },
738
+ {
739
+ "epoch": 0.76,
740
+ "eval_bleu": 37.2335,
741
+ "eval_chrf++": 62.7349,
742
+ "eval_gen_len": 22.3555,
743
+ "eval_loss": 0.9193410277366638,
744
+ "eval_runtime": 2451.9368,
745
+ "eval_samples_per_second": 6.835,
746
+ "eval_spbleu": 50.8378,
747
+ "eval_steps_per_second": 0.684,
748
+ "eval_ter": 51.103,
749
+ "step": 19500
750
+ },
751
+ {
752
+ "epoch": 0.78,
753
+ "learning_rate": 4.224295078152271e-05,
754
+ "loss": 0.4605,
755
+ "step": 20000
756
+ },
757
+ {
758
+ "epoch": 0.78,
759
+ "eval_bleu": 37.615,
760
+ "eval_chrf++": 62.9994,
761
+ "eval_gen_len": 22.4271,
762
+ "eval_loss": 0.920886218547821,
763
+ "eval_runtime": 2460.502,
764
+ "eval_samples_per_second": 6.811,
765
+ "eval_spbleu": 50.9187,
766
+ "eval_steps_per_second": 0.681,
767
+ "eval_ter": 51.1974,
768
+ "step": 20000
769
+ },
770
+ {
771
+ "epoch": 0.8,
772
+ "learning_rate": 4.204902455106078e-05,
773
+ "loss": 0.462,
774
+ "step": 20500
775
+ },
776
+ {
777
+ "epoch": 0.8,
778
+ "eval_bleu": 37.4618,
779
+ "eval_chrf++": 62.7306,
780
+ "eval_gen_len": 22.3868,
781
+ "eval_loss": 0.9150309562683105,
782
+ "eval_runtime": 2485.0566,
783
+ "eval_samples_per_second": 6.744,
784
+ "eval_spbleu": 50.7521,
785
+ "eval_steps_per_second": 0.674,
786
+ "eval_ter": 51.4503,
787
+ "step": 20500
788
+ },
789
+ {
790
+ "epoch": 0.81,
791
+ "learning_rate": 4.1855098320598846e-05,
792
+ "loss": 0.4584,
793
+ "step": 21000
794
+ },
795
+ {
796
+ "epoch": 0.81,
797
+ "eval_bleu": 37.6302,
798
+ "eval_chrf++": 62.7543,
799
+ "eval_gen_len": 22.2999,
800
+ "eval_loss": 0.9146909713745117,
801
+ "eval_runtime": 2475.6351,
802
+ "eval_samples_per_second": 6.769,
803
+ "eval_spbleu": 50.9152,
804
+ "eval_steps_per_second": 0.677,
805
+ "eval_ter": 51.2347,
806
+ "step": 21000
807
+ },
808
+ {
809
+ "epoch": 0.83,
810
+ "learning_rate": 4.166117209013691e-05,
811
+ "loss": 0.4511,
812
+ "step": 21500
813
+ },
814
+ {
815
+ "epoch": 0.83,
816
+ "eval_bleu": 37.4586,
817
+ "eval_chrf++": 62.7716,
818
+ "eval_gen_len": 22.491,
819
+ "eval_loss": 0.9128248691558838,
820
+ "eval_runtime": 2475.0464,
821
+ "eval_samples_per_second": 6.771,
822
+ "eval_spbleu": 50.7685,
823
+ "eval_steps_per_second": 0.677,
824
+ "eval_ter": 51.1974,
825
+ "step": 21500
826
+ },
827
+ {
828
+ "epoch": 0.85,
829
+ "learning_rate": 4.146724585967498e-05,
830
+ "loss": 0.4463,
831
+ "step": 22000
832
+ },
833
+ {
834
+ "epoch": 0.85,
835
+ "eval_bleu": 37.352,
836
+ "eval_chrf++": 62.9395,
837
+ "eval_gen_len": 22.5926,
838
+ "eval_loss": 0.9129999876022339,
839
+ "eval_runtime": 2497.6416,
840
+ "eval_samples_per_second": 6.71,
841
+ "eval_spbleu": 50.4575,
842
+ "eval_steps_per_second": 0.671,
843
+ "eval_ter": 51.5074,
844
+ "step": 22000
845
+ },
846
+ {
847
+ "epoch": 0.87,
848
+ "learning_rate": 4.1273319629213047e-05,
849
+ "loss": 0.4442,
850
+ "step": 22500
851
+ },
852
+ {
853
+ "epoch": 0.87,
854
+ "eval_bleu": 37.2191,
855
+ "eval_chrf++": 62.6919,
856
+ "eval_gen_len": 22.3296,
857
+ "eval_loss": 0.913128137588501,
858
+ "eval_runtime": 2479.804,
859
+ "eval_samples_per_second": 6.758,
860
+ "eval_spbleu": 50.5573,
861
+ "eval_steps_per_second": 0.676,
862
+ "eval_ter": 51.8057,
863
+ "step": 22500
864
+ },
865
+ {
866
+ "epoch": 0.89,
867
+ "learning_rate": 4.107939339875111e-05,
868
+ "loss": 0.4398,
869
+ "step": 23000
870
+ },
871
+ {
872
+ "epoch": 0.89,
873
+ "eval_bleu": 37.4159,
874
+ "eval_chrf++": 62.7847,
875
+ "eval_gen_len": 22.3621,
876
+ "eval_loss": 0.9087494611740112,
877
+ "eval_runtime": 2492.9389,
878
+ "eval_samples_per_second": 6.722,
879
+ "eval_spbleu": 50.7329,
880
+ "eval_steps_per_second": 0.672,
881
+ "eval_ter": 51.1589,
882
+ "step": 23000
883
+ },
884
+ {
885
+ "epoch": 0.91,
886
+ "learning_rate": 4.088546716828918e-05,
887
+ "loss": 0.4601,
888
+ "step": 23500
889
+ },
890
+ {
891
+ "epoch": 0.91,
892
+ "eval_bleu": 37.6768,
893
+ "eval_chrf++": 63.0053,
894
+ "eval_gen_len": 22.2636,
895
+ "eval_loss": 0.9055464267730713,
896
+ "eval_runtime": 2494.326,
897
+ "eval_samples_per_second": 6.718,
898
+ "eval_spbleu": 50.7562,
899
+ "eval_steps_per_second": 0.672,
900
+ "eval_ter": 51.2394,
901
+ "step": 23500
902
+ },
903
+ {
904
+ "epoch": 0.93,
905
+ "learning_rate": 4.0691540937827254e-05,
906
+ "loss": 0.4436,
907
+ "step": 24000
908
+ },
909
+ {
910
+ "epoch": 0.93,
911
+ "eval_bleu": 37.7386,
912
+ "eval_chrf++": 63.1409,
913
+ "eval_gen_len": 22.6223,
914
+ "eval_loss": 0.9039002656936646,
915
+ "eval_runtime": 2526.9249,
916
+ "eval_samples_per_second": 6.632,
917
+ "eval_spbleu": 50.7251,
918
+ "eval_steps_per_second": 0.663,
919
+ "eval_ter": 51.3804,
920
+ "step": 24000
921
+ },
922
+ {
923
+ "epoch": 0.95,
924
+ "learning_rate": 4.049761470736532e-05,
925
+ "loss": 0.4654,
926
+ "step": 24500
927
+ },
928
+ {
929
+ "epoch": 0.95,
930
+ "eval_bleu": 38.0304,
931
+ "eval_chrf++": 63.2108,
932
+ "eval_gen_len": 22.343,
933
+ "eval_loss": 0.9021787047386169,
934
+ "eval_runtime": 2462.9496,
935
+ "eval_samples_per_second": 6.804,
936
+ "eval_spbleu": 51.3142,
937
+ "eval_steps_per_second": 0.68,
938
+ "eval_ter": 50.4096,
939
+ "step": 24500
940
+ },
941
+ {
942
+ "epoch": 0.97,
943
+ "learning_rate": 4.030368847690339e-05,
944
+ "loss": 0.4485,
945
+ "step": 25000
946
+ },
947
+ {
948
+ "epoch": 0.97,
949
+ "eval_bleu": 38.1296,
950
+ "eval_chrf++": 63.3962,
951
+ "eval_gen_len": 22.518,
952
+ "eval_loss": 0.9031027555465698,
953
+ "eval_runtime": 2500.9301,
954
+ "eval_samples_per_second": 6.701,
955
+ "eval_spbleu": 51.1976,
956
+ "eval_steps_per_second": 0.67,
957
+ "eval_ter": 51.0377,
958
+ "step": 25000
959
+ }
960
+ ],
961
+ "max_steps": 128915,
962
+ "num_train_epochs": 5,
963
+ "total_flos": 2.127904100057088e+17,
964
+ "trial_name": null,
965
+ "trial_params": null
966
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a51c41e9bcb265c14bf6e059ed6da99d8ecffcc3f577048f7aeb9a5d8e19e3cb
3
+ size 4091