Text2Text Generation
Transformers
PyTorch
English
Kinyarwanda
m2m_100
Inference Endpoints
Kleber commited on
Commit
9e4609b
1 Parent(s): f9d278d

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": "checkpoint-53168",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "M2M100ForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 8192,
13
+ "decoder_layerdrop": 0,
14
+ "decoder_layers": 24,
15
+ "decoder_start_token_id": 2,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 16,
18
+ "encoder_ffn_dim": 8192,
19
+ "encoder_layerdrop": 0,
20
+ "encoder_layers": 24,
21
+ "eos_token_id": 2,
22
+ "init_std": 0.02,
23
+ "is_encoder_decoder": true,
24
+ "max_length": 200,
25
+ "max_position_embeddings": 1024,
26
+ "model_type": "m2m_100",
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 1,
29
+ "scale_embedding": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.31.0",
32
+ "use_cache": true,
33
+ "vocab_size": 256206
34
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "max_length": 200,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.31.0"
8
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1298a741392fbbcee6e6b479e682e7d26eb65370d03e91f9654e457c21568434
3
+ size 10965715027
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2677370d8c4684bdf90f5bf5a10101e0613c43c8deba08989b740ea878e400
3
+ size 5482902982
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3409d10d68e644417eec2acad78fa376b96421607840965c009407e776528179
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b26cc114b3e70e6ac287169083be6a69a3d4f8fd69aa2c74320c9e16f75789
3
+ size 627
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
special_tokens_map.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ace_Arab",
4
+ "ace_Latn",
5
+ "acm_Arab",
6
+ "acq_Arab",
7
+ "aeb_Arab",
8
+ "afr_Latn",
9
+ "ajp_Arab",
10
+ "aka_Latn",
11
+ "amh_Ethi",
12
+ "apc_Arab",
13
+ "arb_Arab",
14
+ "ars_Arab",
15
+ "ary_Arab",
16
+ "arz_Arab",
17
+ "asm_Beng",
18
+ "ast_Latn",
19
+ "awa_Deva",
20
+ "ayr_Latn",
21
+ "azb_Arab",
22
+ "azj_Latn",
23
+ "bak_Cyrl",
24
+ "bam_Latn",
25
+ "ban_Latn",
26
+ "bel_Cyrl",
27
+ "bem_Latn",
28
+ "ben_Beng",
29
+ "bho_Deva",
30
+ "bjn_Arab",
31
+ "bjn_Latn",
32
+ "bod_Tibt",
33
+ "bos_Latn",
34
+ "bug_Latn",
35
+ "bul_Cyrl",
36
+ "cat_Latn",
37
+ "ceb_Latn",
38
+ "ces_Latn",
39
+ "cjk_Latn",
40
+ "ckb_Arab",
41
+ "crh_Latn",
42
+ "cym_Latn",
43
+ "dan_Latn",
44
+ "deu_Latn",
45
+ "dik_Latn",
46
+ "dyu_Latn",
47
+ "dzo_Tibt",
48
+ "ell_Grek",
49
+ "eng_Latn",
50
+ "epo_Latn",
51
+ "est_Latn",
52
+ "eus_Latn",
53
+ "ewe_Latn",
54
+ "fao_Latn",
55
+ "pes_Arab",
56
+ "fij_Latn",
57
+ "fin_Latn",
58
+ "fon_Latn",
59
+ "fra_Latn",
60
+ "fur_Latn",
61
+ "fuv_Latn",
62
+ "gla_Latn",
63
+ "gle_Latn",
64
+ "glg_Latn",
65
+ "grn_Latn",
66
+ "guj_Gujr",
67
+ "hat_Latn",
68
+ "hau_Latn",
69
+ "heb_Hebr",
70
+ "hin_Deva",
71
+ "hne_Deva",
72
+ "hrv_Latn",
73
+ "hun_Latn",
74
+ "hye_Armn",
75
+ "ibo_Latn",
76
+ "ilo_Latn",
77
+ "ind_Latn",
78
+ "isl_Latn",
79
+ "ita_Latn",
80
+ "jav_Latn",
81
+ "jpn_Jpan",
82
+ "kab_Latn",
83
+ "kac_Latn",
84
+ "kam_Latn",
85
+ "kan_Knda",
86
+ "kas_Arab",
87
+ "kas_Deva",
88
+ "kat_Geor",
89
+ "knc_Arab",
90
+ "knc_Latn",
91
+ "kaz_Cyrl",
92
+ "kbp_Latn",
93
+ "kea_Latn",
94
+ "khm_Khmr",
95
+ "kik_Latn",
96
+ "kin_Latn",
97
+ "kir_Cyrl",
98
+ "kmb_Latn",
99
+ "kon_Latn",
100
+ "kor_Hang",
101
+ "kmr_Latn",
102
+ "lao_Laoo",
103
+ "lvs_Latn",
104
+ "lij_Latn",
105
+ "lim_Latn",
106
+ "lin_Latn",
107
+ "lit_Latn",
108
+ "lmo_Latn",
109
+ "ltg_Latn",
110
+ "ltz_Latn",
111
+ "lua_Latn",
112
+ "lug_Latn",
113
+ "luo_Latn",
114
+ "lus_Latn",
115
+ "mag_Deva",
116
+ "mai_Deva",
117
+ "mal_Mlym",
118
+ "mar_Deva",
119
+ "min_Latn",
120
+ "mkd_Cyrl",
121
+ "plt_Latn",
122
+ "mlt_Latn",
123
+ "mni_Beng",
124
+ "khk_Cyrl",
125
+ "mos_Latn",
126
+ "mri_Latn",
127
+ "zsm_Latn",
128
+ "mya_Mymr",
129
+ "nld_Latn",
130
+ "nno_Latn",
131
+ "nob_Latn",
132
+ "npi_Deva",
133
+ "nso_Latn",
134
+ "nus_Latn",
135
+ "nya_Latn",
136
+ "oci_Latn",
137
+ "gaz_Latn",
138
+ "ory_Orya",
139
+ "pag_Latn",
140
+ "pan_Guru",
141
+ "pap_Latn",
142
+ "pol_Latn",
143
+ "por_Latn",
144
+ "prs_Arab",
145
+ "pbt_Arab",
146
+ "quy_Latn",
147
+ "ron_Latn",
148
+ "run_Latn",
149
+ "rus_Cyrl",
150
+ "sag_Latn",
151
+ "san_Deva",
152
+ "sat_Beng",
153
+ "scn_Latn",
154
+ "shn_Mymr",
155
+ "sin_Sinh",
156
+ "slk_Latn",
157
+ "slv_Latn",
158
+ "smo_Latn",
159
+ "sna_Latn",
160
+ "snd_Arab",
161
+ "som_Latn",
162
+ "sot_Latn",
163
+ "spa_Latn",
164
+ "als_Latn",
165
+ "srd_Latn",
166
+ "srp_Cyrl",
167
+ "ssw_Latn",
168
+ "sun_Latn",
169
+ "swe_Latn",
170
+ "swh_Latn",
171
+ "szl_Latn",
172
+ "tam_Taml",
173
+ "tat_Cyrl",
174
+ "tel_Telu",
175
+ "tgk_Cyrl",
176
+ "tgl_Latn",
177
+ "tha_Thai",
178
+ "tir_Ethi",
179
+ "taq_Latn",
180
+ "taq_Tfng",
181
+ "tpi_Latn",
182
+ "tsn_Latn",
183
+ "tso_Latn",
184
+ "tuk_Latn",
185
+ "tum_Latn",
186
+ "tur_Latn",
187
+ "twi_Latn",
188
+ "tzm_Tfng",
189
+ "uig_Arab",
190
+ "ukr_Cyrl",
191
+ "umb_Latn",
192
+ "urd_Arab",
193
+ "uzn_Latn",
194
+ "vec_Latn",
195
+ "vie_Latn",
196
+ "war_Latn",
197
+ "wol_Latn",
198
+ "xho_Latn",
199
+ "ydd_Hebr",
200
+ "yor_Latn",
201
+ "yue_Hant",
202
+ "zho_Hans",
203
+ "zho_Hant",
204
+ "zul_Latn"
205
+ ],
206
+ "bos_token": "<s>",
207
+ "cls_token": "<s>",
208
+ "eos_token": "</s>",
209
+ "mask_token": {
210
+ "content": "<mask>",
211
+ "lstrip": true,
212
+ "normalized": true,
213
+ "rstrip": false,
214
+ "single_word": false
215
+ },
216
+ "pad_token": "<pad>",
217
+ "sep_token": "</s>",
218
+ "unk_token": "<unk>"
219
+ }
220
+
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e316b82de11d0f951f370943b3c438311629547285129b0b81dadabd01bca665
3
+ size 17331176
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 1024,
15
+ "name_or_path": "facebook/nllb-200-distilled-600M",
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "src_lang": null,
21
+ "tgt_lang": null,
22
+ "tokenizer_class": "NllbTokenizer",
23
+ "unk_token": "<unk>"
24
+ }
25
+
trainer_state.json ADDED
@@ -0,0 +1,600 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 46602,
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": 4.946354233723875e-05,
13
+ "loss": 1.0067,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.892708467447749e-05,
19
+ "loss": 0.9999,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.839062701171624e-05,
25
+ "loss": 0.9592,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.09,
30
+ "learning_rate": 4.785416934895498e-05,
31
+ "loss": 0.9386,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.11,
36
+ "learning_rate": 4.731771168619373e-05,
37
+ "loss": 0.9855,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.13,
42
+ "learning_rate": 4.6781254023432475e-05,
43
+ "loss": 0.9377,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "learning_rate": 4.6244796360671214e-05,
49
+ "loss": 0.9157,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.17,
54
+ "learning_rate": 4.5708338697909966e-05,
55
+ "loss": 0.9202,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.19,
60
+ "learning_rate": 4.517188103514871e-05,
61
+ "loss": 0.9141,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.21,
66
+ "learning_rate": 4.463542337238745e-05,
67
+ "loss": 0.9193,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.24,
72
+ "learning_rate": 4.40989657096262e-05,
73
+ "loss": 0.9009,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.26,
78
+ "learning_rate": 4.356250804686494e-05,
79
+ "loss": 0.9039,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.28,
84
+ "learning_rate": 4.3026050384103686e-05,
85
+ "loss": 0.9168,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.3,
90
+ "learning_rate": 4.248959272134244e-05,
91
+ "loss": 0.8819,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.32,
96
+ "learning_rate": 4.195313505858118e-05,
97
+ "loss": 0.9244,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.34,
102
+ "learning_rate": 4.141667739581992e-05,
103
+ "loss": 0.8773,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.36,
108
+ "learning_rate": 4.088021973305867e-05,
109
+ "loss": 0.8875,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.39,
114
+ "learning_rate": 4.034376207029741e-05,
115
+ "loss": 0.8741,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.41,
120
+ "learning_rate": 3.980730440753616e-05,
121
+ "loss": 0.8557,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.43,
126
+ "learning_rate": 3.9270846744774904e-05,
127
+ "loss": 0.8757,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.45,
132
+ "learning_rate": 3.873438908201365e-05,
133
+ "loss": 0.8607,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.47,
138
+ "learning_rate": 3.8197931419252395e-05,
139
+ "loss": 0.8673,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.49,
144
+ "learning_rate": 3.766147375649114e-05,
145
+ "loss": 0.8819,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.51,
150
+ "learning_rate": 3.7125016093729886e-05,
151
+ "loss": 0.8619,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.54,
156
+ "learning_rate": 3.658855843096863e-05,
157
+ "loss": 0.8415,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.56,
162
+ "learning_rate": 3.605210076820738e-05,
163
+ "loss": 0.839,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.58,
168
+ "learning_rate": 3.551564310544612e-05,
169
+ "loss": 0.8342,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.6,
174
+ "learning_rate": 3.497918544268486e-05,
175
+ "loss": 0.8431,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.62,
180
+ "learning_rate": 3.444272777992361e-05,
181
+ "loss": 0.8524,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.64,
186
+ "learning_rate": 3.390627011716235e-05,
187
+ "loss": 0.8397,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.67,
192
+ "learning_rate": 3.33698124544011e-05,
193
+ "loss": 0.8083,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.69,
198
+ "learning_rate": 3.283335479163985e-05,
199
+ "loss": 0.8509,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.71,
204
+ "learning_rate": 3.229689712887859e-05,
205
+ "loss": 0.8382,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.73,
210
+ "learning_rate": 3.176043946611733e-05,
211
+ "loss": 0.847,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.75,
216
+ "learning_rate": 3.122398180335608e-05,
217
+ "loss": 0.8309,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.77,
222
+ "learning_rate": 3.0687524140594824e-05,
223
+ "loss": 0.8202,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.79,
228
+ "learning_rate": 3.0151066477833573e-05,
229
+ "loss": 0.8044,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.82,
234
+ "learning_rate": 2.9614608815072315e-05,
235
+ "loss": 0.8184,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.84,
240
+ "learning_rate": 2.907815115231106e-05,
241
+ "loss": 0.8094,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.86,
246
+ "learning_rate": 2.8541693489549803e-05,
247
+ "loss": 0.8048,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.88,
252
+ "learning_rate": 2.800523582678855e-05,
253
+ "loss": 0.836,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.9,
258
+ "learning_rate": 2.7468778164027297e-05,
259
+ "loss": 0.7955,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.92,
264
+ "learning_rate": 2.693232050126604e-05,
265
+ "loss": 0.8221,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.94,
270
+ "learning_rate": 2.6395862838504788e-05,
271
+ "loss": 0.8056,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.97,
276
+ "learning_rate": 2.5859405175743533e-05,
277
+ "loss": 0.8292,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.99,
282
+ "learning_rate": 2.5322947512982275e-05,
283
+ "loss": 0.789,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.0,
288
+ "eval_bleu": 43.6468,
289
+ "eval_chrf++": 67.5204,
290
+ "eval_gen_len": 29.2541,
291
+ "eval_loss": 0.6743187308311462,
292
+ "eval_runtime": 1508.9571,
293
+ "eval_samples_per_second": 3.255,
294
+ "eval_spbleu": 56.2871,
295
+ "eval_steps_per_second": 0.651,
296
+ "eval_ter": 46.5481,
297
+ "step": 23301
298
+ },
299
+ {
300
+ "epoch": 1.01,
301
+ "learning_rate": 2.4786489850221024e-05,
302
+ "loss": 0.7236,
303
+ "step": 23500
304
+ },
305
+ {
306
+ "epoch": 1.03,
307
+ "learning_rate": 2.4250032187459766e-05,
308
+ "loss": 0.5744,
309
+ "step": 24000
310
+ },
311
+ {
312
+ "epoch": 1.05,
313
+ "learning_rate": 2.371357452469851e-05,
314
+ "loss": 0.5704,
315
+ "step": 24500
316
+ },
317
+ {
318
+ "epoch": 1.07,
319
+ "learning_rate": 2.3177116861937257e-05,
320
+ "loss": 0.5804,
321
+ "step": 25000
322
+ },
323
+ {
324
+ "epoch": 1.09,
325
+ "learning_rate": 2.2640659199176002e-05,
326
+ "loss": 0.5753,
327
+ "step": 25500
328
+ },
329
+ {
330
+ "epoch": 1.12,
331
+ "learning_rate": 2.2104201536414748e-05,
332
+ "loss": 0.6005,
333
+ "step": 26000
334
+ },
335
+ {
336
+ "epoch": 1.14,
337
+ "learning_rate": 2.1567743873653493e-05,
338
+ "loss": 0.5813,
339
+ "step": 26500
340
+ },
341
+ {
342
+ "epoch": 1.16,
343
+ "learning_rate": 2.103128621089224e-05,
344
+ "loss": 0.5689,
345
+ "step": 27000
346
+ },
347
+ {
348
+ "epoch": 1.18,
349
+ "learning_rate": 2.049482854813098e-05,
350
+ "loss": 0.5756,
351
+ "step": 27500
352
+ },
353
+ {
354
+ "epoch": 1.2,
355
+ "learning_rate": 1.995837088536973e-05,
356
+ "loss": 0.5856,
357
+ "step": 28000
358
+ },
359
+ {
360
+ "epoch": 1.22,
361
+ "learning_rate": 1.9421913222608475e-05,
362
+ "loss": 0.5632,
363
+ "step": 28500
364
+ },
365
+ {
366
+ "epoch": 1.24,
367
+ "learning_rate": 1.8885455559847217e-05,
368
+ "loss": 0.579,
369
+ "step": 29000
370
+ },
371
+ {
372
+ "epoch": 1.27,
373
+ "learning_rate": 1.8348997897085962e-05,
374
+ "loss": 0.5605,
375
+ "step": 29500
376
+ },
377
+ {
378
+ "epoch": 1.29,
379
+ "learning_rate": 1.7812540234324708e-05,
380
+ "loss": 0.5785,
381
+ "step": 30000
382
+ },
383
+ {
384
+ "epoch": 1.31,
385
+ "learning_rate": 1.7276082571563453e-05,
386
+ "loss": 0.5727,
387
+ "step": 30500
388
+ },
389
+ {
390
+ "epoch": 1.33,
391
+ "learning_rate": 1.67396249088022e-05,
392
+ "loss": 0.5666,
393
+ "step": 31000
394
+ },
395
+ {
396
+ "epoch": 1.35,
397
+ "learning_rate": 1.6203167246040944e-05,
398
+ "loss": 0.5807,
399
+ "step": 31500
400
+ },
401
+ {
402
+ "epoch": 1.37,
403
+ "learning_rate": 1.5666709583279686e-05,
404
+ "loss": 0.566,
405
+ "step": 32000
406
+ },
407
+ {
408
+ "epoch": 1.39,
409
+ "learning_rate": 1.5130251920518435e-05,
410
+ "loss": 0.5912,
411
+ "step": 32500
412
+ },
413
+ {
414
+ "epoch": 1.42,
415
+ "learning_rate": 1.4593794257757179e-05,
416
+ "loss": 0.5665,
417
+ "step": 33000
418
+ },
419
+ {
420
+ "epoch": 1.44,
421
+ "learning_rate": 1.4057336594995924e-05,
422
+ "loss": 0.5563,
423
+ "step": 33500
424
+ },
425
+ {
426
+ "epoch": 1.46,
427
+ "learning_rate": 1.3520878932234668e-05,
428
+ "loss": 0.5848,
429
+ "step": 34000
430
+ },
431
+ {
432
+ "epoch": 1.48,
433
+ "learning_rate": 1.2984421269473413e-05,
434
+ "loss": 0.5491,
435
+ "step": 34500
436
+ },
437
+ {
438
+ "epoch": 1.5,
439
+ "learning_rate": 1.2447963606712159e-05,
440
+ "loss": 0.5713,
441
+ "step": 35000
442
+ },
443
+ {
444
+ "epoch": 1.52,
445
+ "learning_rate": 1.1911505943950904e-05,
446
+ "loss": 0.5862,
447
+ "step": 35500
448
+ },
449
+ {
450
+ "epoch": 1.54,
451
+ "learning_rate": 1.1375048281189648e-05,
452
+ "loss": 0.5592,
453
+ "step": 36000
454
+ },
455
+ {
456
+ "epoch": 1.57,
457
+ "learning_rate": 1.0838590618428395e-05,
458
+ "loss": 0.5658,
459
+ "step": 36500
460
+ },
461
+ {
462
+ "epoch": 1.59,
463
+ "learning_rate": 1.0302132955667139e-05,
464
+ "loss": 0.5794,
465
+ "step": 37000
466
+ },
467
+ {
468
+ "epoch": 1.61,
469
+ "learning_rate": 9.765675292905884e-06,
470
+ "loss": 0.5462,
471
+ "step": 37500
472
+ },
473
+ {
474
+ "epoch": 1.63,
475
+ "learning_rate": 9.22921763014463e-06,
476
+ "loss": 0.5624,
477
+ "step": 38000
478
+ },
479
+ {
480
+ "epoch": 1.65,
481
+ "learning_rate": 8.692759967383375e-06,
482
+ "loss": 0.5504,
483
+ "step": 38500
484
+ },
485
+ {
486
+ "epoch": 1.67,
487
+ "learning_rate": 8.15630230462212e-06,
488
+ "loss": 0.5679,
489
+ "step": 39000
490
+ },
491
+ {
492
+ "epoch": 1.7,
493
+ "learning_rate": 7.619844641860864e-06,
494
+ "loss": 0.5642,
495
+ "step": 39500
496
+ },
497
+ {
498
+ "epoch": 1.72,
499
+ "learning_rate": 7.0833869790996095e-06,
500
+ "loss": 0.5778,
501
+ "step": 40000
502
+ },
503
+ {
504
+ "epoch": 1.74,
505
+ "learning_rate": 6.546929316338354e-06,
506
+ "loss": 0.54,
507
+ "step": 40500
508
+ },
509
+ {
510
+ "epoch": 1.76,
511
+ "learning_rate": 6.0104716535771e-06,
512
+ "loss": 0.5535,
513
+ "step": 41000
514
+ },
515
+ {
516
+ "epoch": 1.78,
517
+ "learning_rate": 5.474013990815846e-06,
518
+ "loss": 0.5497,
519
+ "step": 41500
520
+ },
521
+ {
522
+ "epoch": 1.8,
523
+ "learning_rate": 4.9375563280545895e-06,
524
+ "loss": 0.5556,
525
+ "step": 42000
526
+ },
527
+ {
528
+ "epoch": 1.82,
529
+ "learning_rate": 4.401098665293335e-06,
530
+ "loss": 0.5476,
531
+ "step": 42500
532
+ },
533
+ {
534
+ "epoch": 1.85,
535
+ "learning_rate": 3.86464100253208e-06,
536
+ "loss": 0.5392,
537
+ "step": 43000
538
+ },
539
+ {
540
+ "epoch": 1.87,
541
+ "learning_rate": 3.3281833397708254e-06,
542
+ "loss": 0.5515,
543
+ "step": 43500
544
+ },
545
+ {
546
+ "epoch": 1.89,
547
+ "learning_rate": 2.7917256770095704e-06,
548
+ "loss": 0.5403,
549
+ "step": 44000
550
+ },
551
+ {
552
+ "epoch": 1.91,
553
+ "learning_rate": 2.255268014248316e-06,
554
+ "loss": 0.5544,
555
+ "step": 44500
556
+ },
557
+ {
558
+ "epoch": 1.93,
559
+ "learning_rate": 1.7188103514870608e-06,
560
+ "loss": 0.5628,
561
+ "step": 45000
562
+ },
563
+ {
564
+ "epoch": 1.95,
565
+ "learning_rate": 1.1823526887258058e-06,
566
+ "loss": 0.575,
567
+ "step": 45500
568
+ },
569
+ {
570
+ "epoch": 1.97,
571
+ "learning_rate": 6.458950259645509e-07,
572
+ "loss": 0.546,
573
+ "step": 46000
574
+ },
575
+ {
576
+ "epoch": 2.0,
577
+ "learning_rate": 1.0943736320329599e-07,
578
+ "loss": 0.5278,
579
+ "step": 46500
580
+ },
581
+ {
582
+ "epoch": 2.0,
583
+ "eval_bleu": 45.9774,
584
+ "eval_chrf++": 69.0406,
585
+ "eval_gen_len": 29.0554,
586
+ "eval_loss": 0.6565608382225037,
587
+ "eval_runtime": 1493.1741,
588
+ "eval_samples_per_second": 3.29,
589
+ "eval_spbleu": 58.5933,
590
+ "eval_steps_per_second": 0.658,
591
+ "eval_ter": 43.8556,
592
+ "step": 46602
593
+ }
594
+ ],
595
+ "max_steps": 46602,
596
+ "num_train_epochs": 2,
597
+ "total_flos": 1.983240667660288e+17,
598
+ "trial_name": null,
599
+ "trial_params": null
600
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a041e0331f548bfcd74ad5974e50c3d0a670e69a46d748fe37a238f5ab48667
3
+ size 4091