Text2Text Generation
Transformers
PyTorch
English
Kinyarwanda
m2m_100
Inference Endpoints
Kleber commited on
Commit
af01bd9
1 Parent(s): 84665c0

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": "tourism_models_1/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": "4.32.0",
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": "4.32.0"
8
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3c874eea2610ca8f3d3e1911cb84a55da76687fd6befa78e78dcd8bc4983e7
3
+ size 10965980440
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7831358f2cf54cf4ba458681afc10c0329ad13344407426d16b393e1410ed84
3
+ size 5482902982
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe366580e1050cbb2f27badf10ca3229140188646f805dcf9f3c0a73dd5b38f
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e6613a21899346384bbeed68b98273ad8353ff120e7720fa3b6079e841987a
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 +1,504 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 35370,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07,
13
+ "learning_rate": 4.929318631608708e-05,
14
+ "loss": 0.5887,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.14,
19
+ "learning_rate": 4.858637263217416e-05,
20
+ "loss": 0.6212,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.21,
25
+ "learning_rate": 4.787955894826124e-05,
26
+ "loss": 0.6428,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.28,
31
+ "learning_rate": 4.717274526434832e-05,
32
+ "loss": 0.6492,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.35,
37
+ "learning_rate": 4.64659315804354e-05,
38
+ "loss": 0.643,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.42,
43
+ "learning_rate": 4.575911789652248e-05,
44
+ "loss": 0.6446,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.49,
49
+ "learning_rate": 4.505230421260956e-05,
50
+ "loss": 0.6578,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.57,
55
+ "learning_rate": 4.434549052869664e-05,
56
+ "loss": 0.6545,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.64,
61
+ "learning_rate": 4.3638676844783716e-05,
62
+ "loss": 0.6706,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.71,
67
+ "learning_rate": 4.2931863160870795e-05,
68
+ "loss": 0.673,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.78,
73
+ "learning_rate": 4.222504947695788e-05,
74
+ "loss": 0.6592,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.85,
79
+ "learning_rate": 4.151823579304496e-05,
80
+ "loss": 0.6771,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.92,
85
+ "learning_rate": 4.081142210913204e-05,
86
+ "loss": 0.6889,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.99,
91
+ "learning_rate": 4.0104608425219116e-05,
92
+ "loss": 0.6697,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "eval_bleu": 30.7024,
98
+ "eval_chrf++": 57.2458,
99
+ "eval_gen_len": 27.1368,
100
+ "eval_loss": 1.2473633289337158,
101
+ "eval_runtime": 1116.0922,
102
+ "eval_samples_per_second": 4.387,
103
+ "eval_spbleu": 42.8416,
104
+ "eval_steps_per_second": 0.627,
105
+ "eval_ter": 59.9898,
106
+ "step": 7074
107
+ },
108
+ {
109
+ "epoch": 1.06,
110
+ "learning_rate": 3.9397794741306194e-05,
111
+ "loss": 0.4754,
112
+ "step": 7500
113
+ },
114
+ {
115
+ "epoch": 1.13,
116
+ "learning_rate": 3.869098105739327e-05,
117
+ "loss": 0.4397,
118
+ "step": 8000
119
+ },
120
+ {
121
+ "epoch": 1.2,
122
+ "learning_rate": 3.798416737348035e-05,
123
+ "loss": 0.4587,
124
+ "step": 8500
125
+ },
126
+ {
127
+ "epoch": 1.27,
128
+ "learning_rate": 3.727735368956743e-05,
129
+ "loss": 0.4694,
130
+ "step": 9000
131
+ },
132
+ {
133
+ "epoch": 1.34,
134
+ "learning_rate": 3.6570540005654515e-05,
135
+ "loss": 0.458,
136
+ "step": 9500
137
+ },
138
+ {
139
+ "epoch": 1.41,
140
+ "learning_rate": 3.5863726321741594e-05,
141
+ "loss": 0.4628,
142
+ "step": 10000
143
+ },
144
+ {
145
+ "epoch": 1.48,
146
+ "learning_rate": 3.515691263782867e-05,
147
+ "loss": 0.4549,
148
+ "step": 10500
149
+ },
150
+ {
151
+ "epoch": 1.55,
152
+ "learning_rate": 3.445009895391575e-05,
153
+ "loss": 0.4579,
154
+ "step": 11000
155
+ },
156
+ {
157
+ "epoch": 1.63,
158
+ "learning_rate": 3.374328527000283e-05,
159
+ "loss": 0.4775,
160
+ "step": 11500
161
+ },
162
+ {
163
+ "epoch": 1.7,
164
+ "learning_rate": 3.303647158608991e-05,
165
+ "loss": 0.4674,
166
+ "step": 12000
167
+ },
168
+ {
169
+ "epoch": 1.77,
170
+ "learning_rate": 3.2329657902176986e-05,
171
+ "loss": 0.4659,
172
+ "step": 12500
173
+ },
174
+ {
175
+ "epoch": 1.84,
176
+ "learning_rate": 3.162284421826407e-05,
177
+ "loss": 0.4693,
178
+ "step": 13000
179
+ },
180
+ {
181
+ "epoch": 1.91,
182
+ "learning_rate": 3.091603053435115e-05,
183
+ "loss": 0.4554,
184
+ "step": 13500
185
+ },
186
+ {
187
+ "epoch": 1.98,
188
+ "learning_rate": 3.0209216850438226e-05,
189
+ "loss": 0.4671,
190
+ "step": 14000
191
+ },
192
+ {
193
+ "epoch": 2.0,
194
+ "eval_bleu": 31.3008,
195
+ "eval_chrf++": 57.3245,
196
+ "eval_gen_len": 26.9416,
197
+ "eval_loss": 1.328170895576477,
198
+ "eval_runtime": 1121.14,
199
+ "eval_samples_per_second": 4.367,
200
+ "eval_spbleu": 43.1798,
201
+ "eval_steps_per_second": 0.624,
202
+ "eval_ter": 59.0032,
203
+ "step": 14148
204
+ },
205
+ {
206
+ "epoch": 2.05,
207
+ "learning_rate": 2.9502403166525304e-05,
208
+ "loss": 0.3415,
209
+ "step": 14500
210
+ },
211
+ {
212
+ "epoch": 2.12,
213
+ "learning_rate": 2.8795589482612383e-05,
214
+ "loss": 0.3063,
215
+ "step": 15000
216
+ },
217
+ {
218
+ "epoch": 2.19,
219
+ "learning_rate": 2.808877579869946e-05,
220
+ "loss": 0.3058,
221
+ "step": 15500
222
+ },
223
+ {
224
+ "epoch": 2.26,
225
+ "learning_rate": 2.738196211478654e-05,
226
+ "loss": 0.3089,
227
+ "step": 16000
228
+ },
229
+ {
230
+ "epoch": 2.33,
231
+ "learning_rate": 2.6675148430873625e-05,
232
+ "loss": 0.3205,
233
+ "step": 16500
234
+ },
235
+ {
236
+ "epoch": 2.4,
237
+ "learning_rate": 2.5968334746960704e-05,
238
+ "loss": 0.3082,
239
+ "step": 17000
240
+ },
241
+ {
242
+ "epoch": 2.47,
243
+ "learning_rate": 2.5261521063047782e-05,
244
+ "loss": 0.3425,
245
+ "step": 17500
246
+ },
247
+ {
248
+ "epoch": 2.54,
249
+ "learning_rate": 2.455470737913486e-05,
250
+ "loss": 0.3189,
251
+ "step": 18000
252
+ },
253
+ {
254
+ "epoch": 2.62,
255
+ "learning_rate": 2.384789369522194e-05,
256
+ "loss": 0.3257,
257
+ "step": 18500
258
+ },
259
+ {
260
+ "epoch": 2.69,
261
+ "learning_rate": 2.3141080011309018e-05,
262
+ "loss": 0.3249,
263
+ "step": 19000
264
+ },
265
+ {
266
+ "epoch": 2.76,
267
+ "learning_rate": 2.24342663273961e-05,
268
+ "loss": 0.3271,
269
+ "step": 19500
270
+ },
271
+ {
272
+ "epoch": 2.83,
273
+ "learning_rate": 2.1727452643483178e-05,
274
+ "loss": 0.3362,
275
+ "step": 20000
276
+ },
277
+ {
278
+ "epoch": 2.9,
279
+ "learning_rate": 2.1020638959570257e-05,
280
+ "loss": 0.3334,
281
+ "step": 20500
282
+ },
283
+ {
284
+ "epoch": 2.97,
285
+ "learning_rate": 2.031382527565734e-05,
286
+ "loss": 0.3229,
287
+ "step": 21000
288
+ },
289
+ {
290
+ "epoch": 3.0,
291
+ "eval_bleu": 30.103,
292
+ "eval_chrf++": 56.7595,
293
+ "eval_gen_len": 27.2512,
294
+ "eval_loss": 1.4371376037597656,
295
+ "eval_runtime": 1144.2163,
296
+ "eval_samples_per_second": 4.279,
297
+ "eval_spbleu": 42.008,
298
+ "eval_steps_per_second": 0.612,
299
+ "eval_ter": 60.4163,
300
+ "step": 21222
301
+ },
302
+ {
303
+ "epoch": 3.04,
304
+ "learning_rate": 1.9607011591744417e-05,
305
+ "loss": 0.2754,
306
+ "step": 21500
307
+ },
308
+ {
309
+ "epoch": 3.11,
310
+ "learning_rate": 1.8900197907831496e-05,
311
+ "loss": 0.2294,
312
+ "step": 22000
313
+ },
314
+ {
315
+ "epoch": 3.18,
316
+ "learning_rate": 1.8193384223918574e-05,
317
+ "loss": 0.2256,
318
+ "step": 22500
319
+ },
320
+ {
321
+ "epoch": 3.25,
322
+ "learning_rate": 1.7486570540005656e-05,
323
+ "loss": 0.2248,
324
+ "step": 23000
325
+ },
326
+ {
327
+ "epoch": 3.32,
328
+ "learning_rate": 1.6779756856092735e-05,
329
+ "loss": 0.2268,
330
+ "step": 23500
331
+ },
332
+ {
333
+ "epoch": 3.39,
334
+ "learning_rate": 1.6072943172179813e-05,
335
+ "loss": 0.2215,
336
+ "step": 24000
337
+ },
338
+ {
339
+ "epoch": 3.46,
340
+ "learning_rate": 1.5366129488266895e-05,
341
+ "loss": 0.2233,
342
+ "step": 24500
343
+ },
344
+ {
345
+ "epoch": 3.53,
346
+ "learning_rate": 1.4659315804353974e-05,
347
+ "loss": 0.2305,
348
+ "step": 25000
349
+ },
350
+ {
351
+ "epoch": 3.6,
352
+ "learning_rate": 1.3952502120441052e-05,
353
+ "loss": 0.2212,
354
+ "step": 25500
355
+ },
356
+ {
357
+ "epoch": 3.68,
358
+ "learning_rate": 1.3245688436528131e-05,
359
+ "loss": 0.2248,
360
+ "step": 26000
361
+ },
362
+ {
363
+ "epoch": 3.75,
364
+ "learning_rate": 1.2538874752615213e-05,
365
+ "loss": 0.2161,
366
+ "step": 26500
367
+ },
368
+ {
369
+ "epoch": 3.82,
370
+ "learning_rate": 1.1832061068702292e-05,
371
+ "loss": 0.2367,
372
+ "step": 27000
373
+ },
374
+ {
375
+ "epoch": 3.89,
376
+ "learning_rate": 1.112524738478937e-05,
377
+ "loss": 0.2326,
378
+ "step": 27500
379
+ },
380
+ {
381
+ "epoch": 3.96,
382
+ "learning_rate": 1.041843370087645e-05,
383
+ "loss": 0.2257,
384
+ "step": 28000
385
+ },
386
+ {
387
+ "epoch": 4.0,
388
+ "eval_bleu": 29.9341,
389
+ "eval_chrf++": 56.6787,
390
+ "eval_gen_len": 27.2226,
391
+ "eval_loss": 1.529828429222107,
392
+ "eval_runtime": 1139.5818,
393
+ "eval_samples_per_second": 4.296,
394
+ "eval_spbleu": 42.0167,
395
+ "eval_steps_per_second": 0.614,
396
+ "eval_ter": 60.6963,
397
+ "step": 28296
398
+ },
399
+ {
400
+ "epoch": 4.03,
401
+ "learning_rate": 9.711620016963529e-06,
402
+ "loss": 0.2022,
403
+ "step": 28500
404
+ },
405
+ {
406
+ "epoch": 4.1,
407
+ "learning_rate": 9.004806333050609e-06,
408
+ "loss": 0.1638,
409
+ "step": 29000
410
+ },
411
+ {
412
+ "epoch": 4.17,
413
+ "learning_rate": 8.297992649137688e-06,
414
+ "loss": 0.1778,
415
+ "step": 29500
416
+ },
417
+ {
418
+ "epoch": 4.24,
419
+ "learning_rate": 7.591178965224767e-06,
420
+ "loss": 0.1752,
421
+ "step": 30000
422
+ },
423
+ {
424
+ "epoch": 4.31,
425
+ "learning_rate": 6.884365281311847e-06,
426
+ "loss": 0.1678,
427
+ "step": 30500
428
+ },
429
+ {
430
+ "epoch": 4.38,
431
+ "learning_rate": 6.177551597398926e-06,
432
+ "loss": 0.1723,
433
+ "step": 31000
434
+ },
435
+ {
436
+ "epoch": 4.45,
437
+ "learning_rate": 5.470737913486006e-06,
438
+ "loss": 0.1655,
439
+ "step": 31500
440
+ },
441
+ {
442
+ "epoch": 4.52,
443
+ "learning_rate": 4.763924229573085e-06,
444
+ "loss": 0.1658,
445
+ "step": 32000
446
+ },
447
+ {
448
+ "epoch": 4.59,
449
+ "learning_rate": 4.057110545660164e-06,
450
+ "loss": 0.1776,
451
+ "step": 32500
452
+ },
453
+ {
454
+ "epoch": 4.66,
455
+ "learning_rate": 3.350296861747244e-06,
456
+ "loss": 0.1632,
457
+ "step": 33000
458
+ },
459
+ {
460
+ "epoch": 4.74,
461
+ "learning_rate": 2.643483177834323e-06,
462
+ "loss": 0.1653,
463
+ "step": 33500
464
+ },
465
+ {
466
+ "epoch": 4.81,
467
+ "learning_rate": 1.9366694939214022e-06,
468
+ "loss": 0.1639,
469
+ "step": 34000
470
+ },
471
+ {
472
+ "epoch": 4.88,
473
+ "learning_rate": 1.2298558100084818e-06,
474
+ "loss": 0.1655,
475
+ "step": 34500
476
+ },
477
+ {
478
+ "epoch": 4.95,
479
+ "learning_rate": 5.230421260955612e-07,
480
+ "loss": 0.1722,
481
+ "step": 35000
482
+ },
483
+ {
484
+ "epoch": 5.0,
485
+ "eval_bleu": 30.6094,
486
+ "eval_chrf++": 56.9952,
487
+ "eval_gen_len": 27.0588,
488
+ "eval_loss": 1.5824342966079712,
489
+ "eval_runtime": 1129.1112,
490
+ "eval_samples_per_second": 4.336,
491
+ "eval_spbleu": 42.6439,
492
+ "eval_steps_per_second": 0.62,
493
+ "eval_ter": 59.923,
494
+ "step": 35370
495
+ }
496
+ ],
497
+ "logging_steps": 500,
498
+ "max_steps": 35370,
499
+ "num_train_epochs": 5,
500
+ "save_steps": 500,
501
+ "total_flos": 2.107220927048581e+17,
502
+ "trial_name": null,
503
+ "trial_params": null
504
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15302a05e48e8ca1f9d1211d299bcdd4add36fc5861ec446151e9c0e4b7a8a4
3
+ size 4219