Hugging Face's logo

yhavinga
/
byt5-small-ccmatrix-en-nl

Translation
Transformers
PyTorch
JAX
TensorBoard
Safetensors
Dutch
English
multilingual
t5
text2text-generation
byt5
seq2seq
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
2
yhavinga commited on
Commit
97881df
•
1 Parent(s): c58755c

Add model

Browse files
Files changed (10) hide show
  1. README.md +21 -0
  2. config.json +36 -0
  3. events.out.tfevents.1660827063.t1v-n-f1cbc6da-w-0.91882.0.v2 +3 -0
  4. flax_model.msgpack +3 -0
  5. pytorch_model.bin +3 -0
  6. run_s2s_byt5_small_ccmatrix_en-nl.sh +54 -0
  7. special_tokens_map.json +150 -0
  8. test_results.json +10 -0
  9. tokenizer_config.json +157 -0
  10. training_state.json +1 -0
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - nl
4
+ - en
5
+ datasets:
6
+ - yhavinga/mc4_nl_cleaned
7
+ - yhavinga/ccmatrix
8
+ tags:
9
+ - byt5
10
+ - translation
11
+ - seq2seq
12
+
13
+ pipeline_tag: translation
14
+ widget:
15
+ - text: "It is a painful and tragic spectacle that rises before me: I have drawn back the curtain from the rottenness of man. This word, in my mouth, is at least free from one suspicion: that it involves a moral accusation against humanity."
16
+ - text: "Young Wehling was hunched in his chair, his head in his hand. He was so rumpled, so still and colorless as to be virtually invisible. His camouflage was perfect, since the waiting room had a disorderly and demoralized air, too. Chairs and ashtrays had been moved away from the walls. The floor was paved with spattered dropcloths."
17
+ license: apache-2.0
18
+ ---
19
+
20
+
21
+ Logs at https://wandb.ai/yepster/byt5-small-ccmatrix-en-nl/runs/1wm9igj9?workspace=user-yepster
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3584,
7
+ "d_kv": 64,
8
+ "d_model": 1472,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 4,
21
+ "num_heads": 6,
22
+ "num_layers": 12,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "ByT5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.21.1",
30
+ "use_cache": true,
31
+ "vocab_size": 384,
32
+ "early_stopping": true,
33
+ "max_length": 352,
34
+ "num_beams": 4,
35
+ "length_penalty": 1.3
36
+ }
events.out.tfevents.1660827063.t1v-n-f1cbc6da-w-0.91882.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf1d7e60c4dffee7f29292bf0446cd361b2d6cde8e300f9b4c40156f69abbce
3
+ size 551683
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e5c6a1df499649997c941b166dae824e1af09c68d972967b0871d57e5895190
3
+ size 1198558445
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c2815c2251e14cc41df09f62bcd33827c138699e6f2654cfa6fe0e4a5857a1
3
+ size 1198605613
run_s2s_byt5_small_ccmatrix_en-nl.sh ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ export CORES=`grep -c ^processor /proc/cpuinfo`
2
+ #export XLA_PYTHON_CLIENT_PREALLOCATE=false
3
+ export HF_PROJECT="byt5-small-ccmatrix-en-nl"
4
+ #
5
+ export SOURCE_LANG="en"
6
+ export TARGET_LANG="nl"
7
+ export DATASET="yhavinga/ccmatrix"
8
+ export DATASET_CONFIG="en-nl-25_000_000"
9
+ export MODEL_NAME_OR_PATH="yhavinga/byt5-small-dutch-english"
10
+ export MODEL_PATH="${HOME}/data/${HF_PROJECT}" # Path to the model
11
+ export HF_DATASETS_CACHE=/mnt/ramdisk
12
+
13
+ mkdir -p ${MODEL_PATH}
14
+
15
+ python ../run_s2s_flax_pmap.py \
16
+ --output_dir="${MODEL_PATH}" \
17
+ --model_name_or_path ${MODEL_NAME_OR_PATH} \
18
+ --dataset_name ${DATASET} \
19
+ --dataset_config_name ${DATASET_CONFIG} \
20
+ --preprocessing_num_workers="${CORES}" \
21
+ --source_lang="${SOURCE_LANG}" \
22
+ --target_lang="${TARGET_LANG}" \
23
+ --metric_name="sacrebleu" \
24
+ --do_train --do_eval --do_predict \
25
+ --predict_with_generate \
26
+ --learning_rate="0.0008475" \
27
+ --adam_beta1="0.9" \
28
+ --adam_beta2="0.9969" \
29
+ --adam_epsilon="1e-8" \
30
+ --weight_decay="0.03458" \
31
+ --label_smoothing_factor="0.15" \
32
+ --length_penalty="1.3" \
33
+ --warmup_steps 500 \
34
+ --dropout_rate="0.1" \
35
+ --dtype="bfloat16" \
36
+ --z_loss="1e-4" \
37
+ --per_device_train_batch_size 32 \
38
+ --per_device_eval_batch_size 32 \
39
+ --gradient_accumulation_steps 4 \
40
+ --overwrite_output_dir \
41
+ --max_source_length 352 --max_target_length 352 \
42
+ --num_beams 5 \
43
+ --overwrite_output_dir \
44
+ --logging_steps 10 \
45
+ --save_steps 1000 \
46
+ --eval_steps 1000 \
47
+ --num_train_epochs 1 \
48
+ --max_eval_samples 2000 \
49
+ --max_predict_samples 2000 \
50
+ --validation_split_count 2000 \
51
+ --wandb_project="byt5-small-ccmatrix-en-nl" \
52
+ --wandb_job_type="pmap"
53
+
54
+ # --max_train_samples="1_064_886" \
special_tokens_map.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
+ "eos_token": {
130
+ "content": "</s>",
131
+ "lstrip": false,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ "pad_token": {
137
+ "content": "<pad>",
138
+ "lstrip": false,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ "unk_token": {
144
+ "content": "<unk>",
145
+ "lstrip": false,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ }
150
+ }
test_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "test_bp": 0.9162371160590491,
3
+ "test_precision_ng1": 74.53357453357454,
4
+ "test_precision_ng2": 54.180734856007945,
5
+ "test_precision_ng3": 41.918512539981464,
6
+ "test_precision_ng4": 33.143831722569644,
7
+ "test_ref_len": 40277,
8
+ "test_score": 44.592234547281166,
9
+ "test_sys_len": 37037
10
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
+ "eos_token": {
130
+ "__type": "AddedToken",
131
+ "content": "</s>",
132
+ "lstrip": false,
133
+ "normalized": true,
134
+ "rstrip": false,
135
+ "single_word": false
136
+ },
137
+ "extra_ids": 125,
138
+ "name_or_path": "yhavinga/byt5-small-dutch-english",
139
+ "pad_token": {
140
+ "__type": "AddedToken",
141
+ "content": "<pad>",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false
146
+ },
147
+ "special_tokens_map_file": "/home/yeb/.cache/huggingface/transformers/3715c3de7f5eda8f5c9274c55ea8e8632fe6e4cdfdf8e9066ae173b956cd9b80.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109",
148
+ "tokenizer_class": "ByT5Tokenizer",
149
+ "unk_token": {
150
+ "__type": "AddedToken",
151
+ "content": "<unk>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ }
157
+ }
training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 96001}